system

Abstract

The system according to this embodiment aims to allow users to easily create avatars with their preferred visuals and voices. [Solution] The system according to the embodiment comprises an image upload unit, an avatar generation unit, an audio upload unit, an audio generation unit, and a confirmation / correction unit. The image upload unit allows the user to upload an image of their preferred face. The avatar generation unit analyzes the image uploaded by the image upload unit to create an avatar. The audio upload unit allows the user to upload a video file or URL containing their preferred voice. The audio generation unit analyzes the audio data uploaded by the audio upload unit to generate the voice of the avatar. The confirmation / correction unit confirms the avatar and audio generated by the avatar generation unit and the audio generation unit, and makes corrections as necessary.

Description

Technical Field

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

Background Art

[0002] Patent Document 1 discloses a persona chatbot control method performed by at least one processor, including steps of receiving a user utterance, adding the user utterance to a prompt including an instruction sentence related to an explanation of a chatbot character, encoding the prompt, and inputting the encoded prompt into a language model to generate a chatbot utterance 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 was a problem that it was difficult for a user to easily create an avatar with their preferred visual and voice.

[0005] The system according to the embodiment aims to enable a user to easily create an avatar with their preferred visual and voice.

Means for Solving the Problems

[0006] The system according to this embodiment comprises an image upload unit, an avatar generation unit, an audio upload unit, an audio generation unit, and a confirmation / correction unit. The image upload unit allows the user to upload an image of their preferred face. The avatar generation unit analyzes the image uploaded by the image upload unit to create an avatar. The audio upload unit allows the user to upload a video file or URL containing their preferred voice. The audio generation unit analyzes the audio data uploaded by the audio upload unit to generate the voice for the avatar. The confirmation / correction unit confirms the avatar and audio generated by the avatar generation unit and the audio generation unit, and makes corrections as necessary. [Effects of the Invention]

[0007] The system according to this embodiment allows users to easily create avatars with their preferred visuals and voices. [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 tagged storage is one or more non-volatile storage devices that store various programs, various parameters, and the like. 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 tagged communication I / F (Interface) is an interface that includes a communication processor, an antenna, and the like. The communication I / F manages communication between a plurality of computers. Examples of communication standards applied to the communication I / F include wireless communication standards including 5G (5th Generation Mobile Communication System), Wi-Fi (registered trademark), 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 includes a computer 36, a reception device 38, an output device 40, a camera 42, and a communication I / F 44. The computer 36 includes a processor 46, a RAM 48, and a storage 50. The processor 46, the RAM 48, and the storage 50 are connected to a bus 52. Also, the reception device 38, the output device 40, and the camera 42 are connected to the bus 52.

[0020] The reception device 38 includes a touch panel 38A and a microphone 38B, etc., and receives user input. The touch panel 38A receives user input by contact of an indicator (e.g., a pen or a finger, etc.) by detecting the contact of the indicator. The microphone 38B receives user input by voice by detecting the voice of the user. The control unit 46A transmits data indicating the user input received by the touch panel 38A and the microphone 38B to the data processing device 12. In the data processing device 12, the specific processing unit 290 (see FIG. 2) acquires data indicating the user input.

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

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

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

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

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

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

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

[0028] (Example of form 1) An AI agent service according to an embodiment of the present invention is a service that allows users to easily change the visual appearance and voice to their liking. This service includes a function to create an avatar by uploading several to dozens of images of the user's preferred face. It also provides a function to generate voice by uploading a video file or URL containing the user's preferred voice. This allows users to converse with an AI agent of their liking. For example, a user uploads several to dozens of images of their preferred face. The generating AI analyzes these images and creates an avatar. The user can check the visual appearance of the generated avatar and make modifications as needed. Next, the user uploads a video file or URL containing the user's preferred voice. The generating AI analyzes this audio data and generates the voice of the avatar. The user can check the generated voice and make modifications as needed. This service allows users to converse with an AI agent of their liking, making the interaction with the AI ​​agent more enjoyable and familiar. Furthermore, the function to easily change the visual appearance and voice of the AI ​​agent can be one of the differentiating factors of the AI ​​agent. This allows the AI ​​agent service to allow users to easily create and modify avatars and voices to their liking.

[0029] The AI ​​agent service according to this embodiment comprises an image upload unit, an avatar generation unit, an audio upload unit, an audio generation unit, and a confirmation / correction unit. The image upload unit allows the user to upload an image of their preferred face. The images uploaded by the user include, but are not limited to, images in JPEG or PNG format, or facial photographs. The image upload unit saves the images uploaded by the user to cloud storage, for example. The image upload unit can also check the quality of the uploaded images and correct them as needed. For example, the image upload unit can adjust the resolution of the image and automatically cut out the face portion. The avatar generation unit uses a generation AI to analyze the image uploaded by the image upload unit and create an avatar. The generation AI uses, for example, deep learning technology to extract facial features and generate the avatar. The avatar generation unit presents the visual representation of the generated avatar to the user and allows the user to make corrections as needed. For example, the avatar generation unit provides an interface that allows the user to change the avatar's hairstyle and clothing. The audio upload unit allows the user to upload a video file or URL containing a voice they like. The audio data uploaded by users may include, but is not limited to, video files in MP4 or AVI format, or URLs to video sharing sites. The audio upload unit saves the uploaded audio data to cloud storage. The audio upload unit can also check the quality of the audio data and correct it as needed. For example, the audio upload unit can remove noise from the audio and adjust the volume. The audio generation unit uses a generation AI to analyze the audio data uploaded by the audio upload unit and generate the avatar's voice. The generation AI uses, for example, deep learning technology to extract audio features and generate the avatar's voice. The audio generation unit presents the generated audio to the user and allows the user to make modifications as needed. For example, the audio generation unit provides an interface that allows the user to change the tone and pitch of the avatar's voice.The confirmation and modification unit checks the avatar and voice generated by the avatar generation unit and the voice generation unit, and makes corrections as necessary. The confirmation and modification unit provides, for example, an interface for the user to check and modify the visual and voice of the generated avatar. The confirmation and modification unit has a function that allows the user to preview the avatar's visual and voice in real time. For example, the confirmation and modification unit provides an interface that allows the user to rotate the avatar's visual 360 degrees for review. As a result, the AI ​​agent service according to the embodiment allows the user to easily create and modify avatars and voices to their liking.

[0030] The image upload section allows users to upload images of their preferred faces. These images may include, but are not limited to, JPEG or PNG images, or photographs of faces. The image upload section can, for example, save the uploaded images to cloud storage. Cloud storage is a secure environment, and encryption technology is used to protect user privacy. The image upload section can also check the quality of uploaded images and correct them as needed. For example, it can adjust the image resolution and automatically crop the face. Resolution adjustment optimizes the number of pixels in the image to ensure quality suitable for avatar generation. Automatic face cropping is performed using an image processing algorithm that removes the background and accurately extracts the facial contours. This allows the avatar generation section to accurately analyze facial features. Furthermore, the image upload section allows users to upload multiple images, providing images of faces from different angles to collect data for generating more detailed avatars. This allows users to provide high-quality images to create avatars tailored to their preferences.

[0031] The avatar generation unit uses a generation AI to analyze images uploaded by the image upload unit and create avatars. The generation AI, for example, uses deep learning technology to extract facial features and generate avatars. Deep learning technology analyzes image data using a multi-layered neural network to identify facial feature points. This allows the avatar generation unit to generate avatars that accurately reproduce the user's facial features, such as shape, eyes, nose, and mouth. The avatar generation unit presents the generated avatar to the user, allowing them to make modifications as needed. For example, the avatar generation unit provides an interface that allows the user to change the avatar's hairstyle and clothing. Through this interface, the user can freely select and customize the avatar's hairstyle, hair color, clothing, accessories, etc. This allows the user to create an avatar that suits their preferences. Furthermore, the avatar generation unit has a function to simulate the movement of the generated avatar, allowing the user to check the avatar's expressions and movements and make real-time modifications. This allows the user to create more natural and realistic avatars.

[0032] The audio upload unit allows users to upload video files or URLs containing their preferred voices. Uploaded audio data may include, but is not limited to, video files in MP4 or AVI format, or URLs to video sharing sites. The audio upload unit stores the uploaded audio data in cloud storage. Cloud storage uses encryption technology to ensure the security of the audio data and protect user privacy. The audio upload unit can also check the quality of the audio data and perform audio correction as needed. For example, it can remove audio noise and adjust the volume. Noise reduction is performed using an audio processing algorithm to remove background noise and unwanted sounds. Volume adjustment is performed to improve audio clarity and maintain a consistent volume level. Furthermore, the audio upload unit has an audio data format conversion function, allowing it to convert audio data in different formats into a unified format. This prepares the audio generation unit to efficiently analyze the audio data and generate avatar voices.

[0033] The voice generation unit uses a generation AI to analyze audio data uploaded by the voice upload unit and generate a voice for the avatar. The generation AI, for example, uses deep learning technology to extract audio features and generate the avatar's voice. Deep learning technology analyzes audio data using a multi-layered neural network to identify features such as tone, pitch, and rhythm. This allows the voice generation unit to naturally reproduce the avatar's voice based on the user's uploaded audio data. The voice generation unit presents the generated voice to the user, allowing them to make modifications as needed. For example, the voice generation unit provides an interface that allows the user to change the tone and pitch of the avatar's voice. Through the interface, the user can adjust the pitch, speed, and emotional expression of the avatar's voice to create a voice tailored to their preferences. Furthermore, the voice generation unit has a function to evaluate the quality of the generated voice, allowing the user to check the clarity and naturalness of the voice and make modifications as needed. This enables the user to create a high-quality avatar voice tailored to their preferences.

[0034] The verification and correction unit verifies the avatar and voice generated by the avatar generation unit and voice generation unit, and makes corrections as needed. For example, the verification and correction unit provides an interface for the user to verify and correct the visual and voice of the generated avatar. The verification and correction unit has a function that allows the user to preview the avatar's visual and voice in real time. For example, the verification and correction unit provides an interface that allows the user to rotate the avatar's visual 360 degrees for verification. This allows the user to verify the overall appearance of the avatar and make corrections down to the smallest detail. The verification and correction unit also has a function that simulates the avatar's facial expressions and movements, allowing the user to verify the avatar's movements and make corrections in real time. Furthermore, the verification and correction unit plays the generated voice and provides an interface for the user to verify the tone and pitch of the voice and make corrections as needed. This allows the user to verify and correct the avatar's visual and voice in an integrated manner. The verification and correction unit collects user feedback and provides data for continuously improving the quality of the generated avatar and voice. As a result, the AI ​​agent service according to the embodiment allows the user to easily create and modify avatars and voices to their liking.

[0035] The avatar generation unit can create avatars by analyzing images using generative AI. For example, the avatar generation unit can use generative AI to analyze images uploaded by users and extract facial features. The generative AI can extract facial features with high accuracy using deep learning technology. For example, the generative AI can identify the contours of the face and the positions of the eyes, nose, and mouth, and generate an avatar based on that. The avatar generation unit can also use generative AI to integrate multiple images and generate more realistic avatars. For example, the generative AI can integrate images of faces taken from different angles and generate a 3D model. Furthermore, the avatar generation unit can use generative AI to customize the avatar's visual appearance according to the user's preferences. For example, the generative AI can generate an avatar that reflects the hairstyle and clothing specified by the user. This improves the accuracy of avatar generation by using generative AI. The generative AI can generate realistic avatars using, for example, GAN (Generative Opposite Network). A GAN consists of two networks: a generative model and a discriminative model. The generative model generates realistic images, and the discriminative model distinguishes between the generated images and actual images. This allows the generative model to generate realistic images that deceive the discriminative model. Some or all of the above processing in the avatar generation unit is performed using a generative AI. For example, the avatar generation unit inputs an image uploaded by the user into the generative AI, which analyzes the image and generates an avatar.

[0036] The voice generation unit can analyze audio data using generative AI and generate avatar voices. For example, the voice generation unit can use generative AI to analyze user-uploaded audio data and extract audio features. The generative AI can extract audio features with high accuracy using deep learning technology. For example, the generative AI analyzes the tone, pitch, and rhythm of the audio and generates the avatar voice based on that. The voice generation unit can also use generative AI to integrate multiple audio data to generate a more natural avatar voice. For example, the generative AI integrates audio data from different speakers to generate a unique voice. Furthermore, the voice generation unit can use generative AI to customize the avatar voice according to the user's preferences. For example, the generative AI generates an avatar voice that reflects the tone and pitch of the voice specified by the user. This improves the accuracy of voice generation by using generative AI. The generative AI can, for example, use GAN (Generative Opposite Network) to generate realistic audio. A GAN consists of two networks: a generative model and a discriminative model. The generative model generates realistic audio, and the discriminative model distinguishes between the generated audio and actual audio. This allows the generative model to generate realistic voices that deceive the identification model. Some or all of the above-described processes in the voice generation unit are performed using a generative AI. For example, the voice generation unit inputs voice data uploaded by the user into the generative AI, which analyzes the voice data and generates the avatar's voice.

[0037] The confirmation and modification unit allows the user to review the generated avatar and voice and make corrections as needed. For example, the confirmation and modification unit provides an interface for the user to review and modify the visual and voice aspects of the generated avatar. The confirmation and modification unit has a function that allows the user to preview the avatar's visual and voice aspects in real time. For example, the confirmation and modification unit provides an interface that allows the user to rotate the avatar's visual aspects 360 degrees for review. The confirmation and modification unit also provides an interface that allows the user to change the avatar's hairstyle, clothing, voice tone, and pitch. This allows the user to review and modify the generated avatar and voice aspects. Some or all of the above processing in the confirmation and modification unit may be performed using AI or not. For example, the confirmation and modification unit can input the visual and voice aspects of the generated avatar into the AI, which can then suggest corrections.

[0038] The avatar generation unit can generate avatars based on images uploaded by the user. For example, the avatar generation unit analyzes the user-uploaded image and extracts facial features. The generation AI uses deep learning technology to extract facial features with high accuracy. For example, the generation AI identifies the contours of the face and the positions of the eyes, nose, and mouth, and generates an avatar based on that. The avatar generation unit can also use the generation AI to integrate multiple images and generate a more realistic avatar. For example, the generation AI integrates images of faces taken from different angles to generate a 3D model. Furthermore, the avatar generation unit can use the generation AI to customize the avatar's appearance according to the user's preferences. For example, the generation AI generates an avatar that reflects the hairstyle and clothing specified by the user. This allows the avatar to be generated based on images uploaded by the user. Some or all of the above processes in the avatar generation unit are performed using the generation AI. For example, the avatar generation unit inputs the user-uploaded image into the generation AI, which analyzes the image and generates an avatar.

[0039] The voice generation unit can generate an avatar's voice based on audio data uploaded by the user. For example, the voice generation unit analyzes the user-uploaded audio data and extracts its characteristics. The generation AI uses deep learning technology to extract these characteristics with high accuracy. For example, the generation AI analyzes the tone, pitch, and rhythm of the voice and generates the avatar's voice based on this. Furthermore, the voice generation unit can use the generation AI to integrate multiple audio data sets to generate a more natural-sounding avatar voice. For example, the generation AI integrates audio data from different speakers to generate a unique voice. Additionally, the voice generation unit can use the generation AI to customize the avatar's voice according to the user's preferences. For example, the generation AI generates an avatar voice that reflects the tone and pitch specified by the user. This allows the voice generation unit to generate an avatar's voice based on the user-uploaded audio data. Some or all of the above-described processes in the voice generation unit are performed using the generation AI. For example, the voice generation unit inputs the user-uploaded audio data into the generation AI, which analyzes the audio data and generates the avatar's voice.

[0040] The image upload unit can analyze the user's past image upload history and select the optimal upload method. For example, the image upload unit may prioritize suggesting upload methods that the user has frequently used in the past. The image upload unit can also select and suggest the most efficient upload method based on the user's past upload history. For example, the image upload unit may analyze the user's past upload history and suggest the optimal image format and resolution. This allows the optimal upload method to be selected based on the user's past history. Some or all of the above processing in the image upload unit may be performed using AI or not. For example, the image upload unit may input the user's past upload history data into the AI, and the AI ​​may select the optimal upload method.

[0041] The image upload unit can filter images based on the user's current projects and areas of interest when uploading them. For example, the image upload unit can prioritize uploading images related to the user's current project. The image upload unit can also filter and upload images based on the user's areas of interest. For example, the image upload unit can automatically exclude unnecessary images based on the user's projects and areas of interest. This allows for image filtering based on the user's projects and areas of interest. Some or all of the above processing in the image upload unit may be performed using AI or not. For example, the image upload unit can input data on the user's projects and areas of interest into the AI, which then filters out the most relevant images.

[0042] The image upload unit can prioritize uploading highly relevant images by considering the user's geographical location information during image upload. For example, the image upload unit can prioritize uploading images related to the user's current location. The image upload unit can also filter and upload highly relevant images based on the user's geographical location information. For example, the image upload unit can automatically exclude unnecessary images based on the user's location information. This allows the uploading of highly relevant images based on the user's geographical location information. Some or all of the above processing in the image upload unit may be performed using AI or not. For example, the image upload unit inputs the user's geographical location information data into the AI, and the AI ​​filters out highly relevant images.

[0043] The image upload unit can analyze the user's social media activity when uploading images and upload relevant images. For example, the image upload unit can prioritize uploading images that are highly relevant to the user's social media activity. The image upload unit can also analyze the user's social media activity and automatically exclude unnecessary images. For example, the image upload unit can suggest the optimal image format and resolution based on the user's social media activity. This allows the user to upload relevant images based on their social media activity. Some or all of the above processing in the image upload unit may be performed using AI or not. For example, the image upload unit can input the user's social media activity data into the AI, and the AI ​​can select relevant images.

[0044] The avatar generation unit can adjust the level of detail of the avatar based on the importance of the image during avatar generation. For example, the avatar generation unit can generate a detailed avatar based on an important image. The avatar generation unit can also generate a simplified avatar based on an image of low importance. For example, the avatar generation unit adjusts the level of detail of the avatar's facial expressions and clothing according to the importance of the image. This allows the level of detail of the avatar to be adjusted according to the importance of the image. Some or all of the above processing in the avatar generation unit is performed using a generation AI. For example, the avatar generation unit inputs an image uploaded by the user into the generation AI, which evaluates the importance of the image and adjusts the level of detail of the avatar.

[0045] The avatar generation unit can apply different generation algorithms depending on the image category when generating an avatar. For example, the avatar generation unit can apply an algorithm to generate a realistic avatar based on a portrait image. It can also apply an algorithm to generate an anime-style avatar based on an illustration image. For example, the avatar generation unit can apply an algorithm to generate a photorealistic avatar based on a photographic image. This allows the optimal generation algorithm to be applied according to the image category. Some or all of the above processing in the avatar generation unit is performed using a generation AI. For example, the avatar generation unit inputs an image uploaded by the user into the generation AI, which determines the image category and applies the optimal generation algorithm.

[0046] The audio upload unit can analyze the user's past audio upload history and select the optimal upload method. For example, the audio upload unit may prioritize suggesting upload methods that the user has frequently used in the past. The audio upload unit can also select and suggest the most efficient upload method based on the user's past upload history. For example, the audio upload unit may analyze the user's past upload history and suggest the optimal audio format and resolution. This allows the system to select the optimal upload method based on the user's past history. Some or all of the above processing in the audio upload unit may be performed using AI or not. For example, the audio upload unit may input the user's past upload history data into the AI, which will then select the optimal upload method.

[0047] The audio upload unit can filter audio uploads based on the user's current projects and areas of interest. For example, the audio upload unit prioritizes uploading audio related to the user's current projects. The audio upload unit can also filter and upload highly relevant audio based on the user's areas of interest. For example, the audio upload unit automatically excludes unnecessary audio based on the user's projects and areas of interest. This allows for filtering audio based on the user's projects and areas of interest. Some or all of the above processing in the audio upload unit may be performed using AI or not. For example, the audio upload unit inputs data on the user's projects and areas of interest into the AI, which then filters the audio for high relevance.

[0048] The voice generation unit can adjust the level of detail of the audio based on the importance of the audio data during voice generation. For example, the voice generation unit can generate detailed audio based on important audio data. The voice generation unit can also generate simplified audio based on less important audio data. For example, the voice generation unit adjusts the level of detail of the tone and intonation of the audio according to the importance of the audio data. This allows the level of detail of the audio to be adjusted according to the importance of the audio data. Some or all of the above processing in the voice generation unit is performed using a generation AI. For example, the voice generation unit inputs audio data uploaded by the user into the generation AI, which evaluates the importance of the audio data and adjusts the level of detail of the audio.

[0049] The voice generation unit can apply different generation algorithms depending on the category of the audio data during voice generation. For example, the voice generation unit can apply an algorithm to generate smooth audio based on narration audio. The voice generation unit can also apply an algorithm to generate natural dialogue audio based on conversational audio. For example, the voice generation unit can apply an algorithm to generate melodious audio based on singing voice. This allows the optimal generation algorithm to be applied according to the category of the audio data. Some or all of the above processing in the voice generation unit is performed using a generation AI. For example, the voice generation unit inputs audio data uploaded by the user into the generation AI, which determines the category of the audio data and applies the optimal generation algorithm.

[0050] The voice generation unit can determine the priority of voices based on when the voice data was submitted. For example, the voice generation unit can prioritize generating voices based on the most recent voice data. The voice generation unit can also postpone generating voices based on older voice data. For example, the voice generation unit adjusts the voice generation order according to the submission date. This allows the priority of voices to be determined according to when the voice data was submitted. Some or all of the above processing in the voice generation unit is performed using a generation AI. For example, the voice generation unit inputs the voice data uploaded by the user into the generation AI, which evaluates the submission date and determines the priority of the voices.

[0051] The voice generation unit can adjust the order of audio based on the relevance of the audio data during voice generation. For example, the voice generation unit can prioritize generating audio based on highly relevant audio data. The voice generation unit can also postpone generating audio based on less relevant audio data. For example, the voice generation unit adjusts the order of voice generation according to the relevance of the audio data. This allows the order of audio to be adjusted according to the relevance of the audio data. Some or all of the above processing in the voice generation unit is performed using a generation AI. For example, the voice generation unit inputs audio data uploaded by the user into the generation AI, which evaluates the relevance and adjusts the order of the audio.

[0052] The verification and correction unit can select the optimal correction method by referring to the user's past correction history during the verification and correction process. For example, the verification and correction unit may prioritize suggesting correction methods that the user has frequently used in the past. The verification and correction unit can also select and suggest the most efficient correction method from the user's past correction history. For example, the verification and correction unit may analyze the user's past correction history and suggest the optimal correction option. This allows the optimal correction method to be selected based on the user's past correction history. Some or all of the above processes in the verification and correction unit may be performed using AI or not. For example, the verification and correction unit may input the user's past correction history data into the AI, and the AI ​​may select the optimal correction method.

[0053] The confirmation and correction unit can customize the means of correction based on the user's current living situation during the confirmation and correction process. For example, if the user is busy, the confirmation and correction unit can provide simplified correction options. If the user is relaxed, the confirmation and correction unit can also provide detailed correction options. For example, the confirmation and correction unit can suggest the optimal correction method according to the user's living situation. This allows the means of correction to be customized according to the user's living situation. Some or all of the above processing in the confirmation and correction unit may be performed using AI or not. For example, the confirmation and correction unit inputs the user's living situation data into the AI, and the AI ​​suggests the optimal correction method.

[0054] The verification and correction unit can select the optimal correction method by considering the user's geographical location information during verification and correction. For example, the verification and correction unit may prioritize corrections related to the user's current location. The verification and correction unit can also select the optimal correction method based on the user's geographical location information. For example, the verification and correction unit may automatically exclude unnecessary corrections based on the user's location information. This allows the unit to select the optimal correction method based on the user's geographical location information. Some or all of the above processes in the verification and correction unit may be performed using AI or not. For example, the verification and correction unit may input the user's geographical location information data into the AI, and the AI ​​may select the optimal correction method.

[0055] The verification and correction unit can analyze the user's social media activity and propose correction measures during the verification and correction process. For example, the verification and correction unit can propose highly relevant correction measures based on the user's social media activity. The verification and correction unit can also analyze the user's social media activity and automatically exclude unnecessary correction measures. For example, the verification and correction unit can propose the optimal correction measure based on the user's social media activity. This allows the unit to propose the optimal correction measure based on the user's social media activity. Some or all of the above processing in the verification and correction unit may be performed using AI or not. For example, the verification and correction unit inputs the user's social media activity data into the AI, and the AI ​​proposes the optimal correction measure.

[0056] The system according to the embodiment is not limited to the example described above, and various modifications are possible, for example, as follows.

[0057] The avatar generation unit can be equipped with the function to dynamically change the avatar's facial expression based on images uploaded by the user. For example, if the user uploads an image of a smiling face, the avatar can be generated to display a smiling face. Similarly, if the user uploads an image of a serious face, the avatar can be generated to display a serious face. Furthermore, if the user uploads images of multiple different facial expressions, the avatar can be made to seamlessly switch between these expressions. This allows users to customize their avatar's facial expressions to be more realistic.

[0058] The avatar generation unit can have a function to automatically suggest avatar clothing based on images uploaded by the user. For example, the avatar generation unit can analyze the background and color scheme of the image uploaded by the user and suggest clothing that matches it. Furthermore, if the user uploads an image based on a specific theme, it can suggest clothing that matches that theme. In addition, the avatar generation unit can refer to the user's past selection history and suggest clothing that suits the user's preferences. This allows users to easily customize their avatar's clothing.

[0059] The confirmation and editing unit can include features for sharing user-generated avatars and voices with other users. For example, the confirmation and editing unit can generate links for sharing user-generated avatars and voices on social media or messaging apps. It can also provide features for sharing user-generated avatars and voices with other users in real time. Furthermore, the confirmation and editing unit can provide features for collaboratively editing user-generated avatars and voices with other users. This allows users to easily share and collaboratively edit their generated avatars and voices with other users.

[0060] The avatar generation unit can have the function to automatically generate avatar movements based on images uploaded by the user. For example, the avatar generation unit can analyze the pose of an image uploaded by the user and generate avatar movements based on that. Furthermore, if the user uploads an image expressing a specific movement, it can generate an avatar that reflects that movement. In addition, the avatar generation unit can refer to the user's past movement selection history and suggest movements that suit the user's preferences. This allows users to easily customize their avatar movements.

[0061] The image upload unit can have a function to automatically generate avatar backgrounds based on images uploaded by the user. For example, the image upload unit can analyze the background of an image uploaded by the user and generate an avatar background based on that analysis. Furthermore, if the user uploads an image depicting a specific background, it can generate an avatar that reflects that background. In addition, the image upload unit can refer to the user's past background selection history and suggest backgrounds that match the user's preferences. This allows users to easily customize their avatar backgrounds.

[0062] The voice generation unit can have a function to adjust the speed of the avatar's voice based on the voice data uploaded by the user. For example, the voice generation unit can analyze the speed of the voice data uploaded by the user and adjust the speed of the avatar's voice accordingly. Furthermore, if the user uploads voice data spoken at a specific speed, the unit can generate a voice that reflects that speed. In addition, the voice generation unit can refer to the user's past voice data and suggest a speed that suits the user's preferences. This allows users to easily customize the speed of their avatar's voice.

[0063] The following briefly describes the processing flow for example form 1.

[0064] Step 1: The image upload section allows users to upload images of their preferred faces. These images can include JPEG and PNG formats, as well as portraits. The image upload section saves the uploaded images to cloud storage, checks their quality, and performs image corrections as needed. For example, it can adjust the image resolution and automatically crop out the face. Step 2: The avatar generation unit uses a generation AI to analyze the image uploaded by the image upload unit and create an avatar. The generation AI uses deep learning technology to extract facial features and generate the avatar. The avatar generation unit presents the generated avatar's visual appearance to the user and allows the user to make modifications as needed. For example, it provides an interface that allows the user to change the avatar's hairstyle or clothing. Step 3: The audio upload section allows users to upload video files or URLs containing their favorite voices. The audio data uploaded by users can include video files in MP4 or AVI format, or URLs to video sharing sites. The audio upload section saves the uploaded audio data to cloud storage, checks the audio quality, and performs audio correction as needed. For example, it can remove audio noise and adjust the volume. Step 4: The voice generation unit uses a generation AI to analyze the audio data uploaded by the voice upload unit and generate the avatar's voice. The generation AI uses deep learning technology to extract audio features and generate the avatar's voice. The voice generation unit presents the generated voice to the user and allows the user to make modifications as needed. For example, it provides an interface that allows the user to change the tone and pitch of the avatar's voice. Step 5: The confirmation and modification unit checks the avatar and voice generated by the avatar generation unit and voice generation unit, and makes corrections as needed. The confirmation and modification unit provides an interface for the user to check and modify the visual and voice of the generated avatar. For example, it provides an interface that allows the user to rotate the avatar's visual appearance 360 ​​degrees for review.

[0065] (Example of form 2) An AI agent service according to an embodiment of the present invention is a service that allows users to easily change the visual appearance and voice to their liking. This service includes a function to create an avatar by uploading several to dozens of images of the user's preferred face. It also provides a function to generate voice by uploading a video file or URL containing the user's preferred voice. This allows users to converse with an AI agent of their liking. For example, a user uploads several to dozens of images of their preferred face. The generating AI analyzes these images and creates an avatar. The user can check the visual appearance of the generated avatar and make modifications as needed. Next, the user uploads a video file or URL containing the user's preferred voice. The generating AI analyzes this audio data and generates the voice of the avatar. The user can check the generated voice and make modifications as needed. This service allows users to converse with an AI agent of their liking, making the interaction with the AI ​​agent more enjoyable and familiar. Furthermore, the function to easily change the visual appearance and voice of the AI ​​agent can be one of the differentiating factors of the AI ​​agent. This allows the AI ​​agent service to allow users to easily create and modify avatars and voices to their liking.

[0066] The AI ​​agent service according to this embodiment comprises an image upload unit, an avatar generation unit, an audio upload unit, an audio generation unit, and a confirmation / correction unit. The image upload unit allows the user to upload an image of their preferred face. The images uploaded by the user include, but are not limited to, images in JPEG or PNG format, or facial photographs. The image upload unit saves the images uploaded by the user to cloud storage, for example. The image upload unit can also check the quality of the uploaded images and correct them as needed. For example, the image upload unit can adjust the resolution of the image and automatically cut out the face portion. The avatar generation unit uses a generation AI to analyze the image uploaded by the image upload unit and create an avatar. The generation AI uses, for example, deep learning technology to extract facial features and generate the avatar. The avatar generation unit presents the visual representation of the generated avatar to the user and allows the user to make corrections as needed. For example, the avatar generation unit provides an interface that allows the user to change the avatar's hairstyle and clothing. The audio upload unit allows the user to upload a video file or URL containing a voice they like. The audio data uploaded by users may include, but is not limited to, video files in MP4 or AVI format, or URLs to video sharing sites. The audio upload unit saves the uploaded audio data to cloud storage. The audio upload unit can also check the quality of the audio data and correct it as needed. For example, the audio upload unit can remove noise from the audio and adjust the volume. The audio generation unit uses a generation AI to analyze the audio data uploaded by the audio upload unit and generate the avatar's voice. The generation AI uses, for example, deep learning technology to extract audio features and generate the avatar's voice. The audio generation unit presents the generated audio to the user and allows the user to make modifications as needed. For example, the audio generation unit provides an interface that allows the user to change the tone and pitch of the avatar's voice.The confirmation and modification unit checks the avatar and voice generated by the avatar generation unit and the voice generation unit, and makes corrections as necessary. The confirmation and modification unit provides, for example, an interface for the user to check and modify the visual and voice of the generated avatar. The confirmation and modification unit has a function that allows the user to preview the avatar's visual and voice in real time. For example, the confirmation and modification unit provides an interface that allows the user to rotate the avatar's visual 360 degrees for review. As a result, the AI ​​agent service according to the embodiment allows the user to easily create and modify avatars and voices to their liking.

[0067] The image upload section allows users to upload images of their preferred faces. These images may include, but are not limited to, JPEG or PNG images, or photographs of faces. The image upload section can, for example, save the uploaded images to cloud storage. Cloud storage is a secure environment, and encryption technology is used to protect user privacy. The image upload section can also check the quality of uploaded images and correct them as needed. For example, it can adjust the image resolution and automatically crop the face. Resolution adjustment optimizes the number of pixels in the image to ensure quality suitable for avatar generation. Automatic face cropping is performed using an image processing algorithm that removes the background and accurately extracts the facial contours. This allows the avatar generation section to accurately analyze facial features. Furthermore, the image upload section allows users to upload multiple images, providing images of faces from different angles to collect data for generating more detailed avatars. This allows users to provide high-quality images to create avatars tailored to their preferences.

[0068] The avatar generation unit uses a generation AI to analyze images uploaded by the image upload unit and create avatars. The generation AI, for example, uses deep learning technology to extract facial features and generate avatars. Deep learning technology analyzes image data using a multi-layered neural network to identify facial feature points. This allows the avatar generation unit to generate avatars that accurately reproduce the user's facial features, such as shape, eyes, nose, and mouth. The avatar generation unit presents the generated avatar to the user, allowing them to make modifications as needed. For example, the avatar generation unit provides an interface that allows the user to change the avatar's hairstyle and clothing. Through this interface, the user can freely select and customize the avatar's hairstyle, hair color, clothing, accessories, etc. This allows the user to create an avatar that suits their preferences. Furthermore, the avatar generation unit has a function to simulate the movement of the generated avatar, allowing the user to check the avatar's expressions and movements and make real-time modifications. This allows the user to create more natural and realistic avatars.

[0069] The audio upload unit allows users to upload video files or URLs containing their preferred voices. Uploaded audio data may include, but is not limited to, video files in MP4 or AVI format, or URLs to video sharing sites. The audio upload unit stores the uploaded audio data in cloud storage. Cloud storage uses encryption technology to ensure the security of the audio data and protect user privacy. The audio upload unit can also check the quality of the audio data and perform audio correction as needed. For example, it can remove audio noise and adjust the volume. Noise reduction is performed using an audio processing algorithm to remove background noise and unwanted sounds. Volume adjustment is performed to improve audio clarity and maintain a consistent volume level. Furthermore, the audio upload unit has an audio data format conversion function, allowing it to convert audio data in different formats into a unified format. This prepares the audio generation unit to efficiently analyze the audio data and generate avatar voices.

[0070] The voice generation unit uses a generation AI to analyze audio data uploaded by the voice upload unit and generate a voice for the avatar. The generation AI, for example, uses deep learning technology to extract audio features and generate the avatar's voice. Deep learning technology analyzes audio data using a multi-layered neural network to identify features such as tone, pitch, and rhythm. This allows the voice generation unit to naturally reproduce the avatar's voice based on the user's uploaded audio data. The voice generation unit presents the generated voice to the user, allowing them to make modifications as needed. For example, the voice generation unit provides an interface that allows the user to change the tone and pitch of the avatar's voice. Through the interface, the user can adjust the pitch, speed, and emotional expression of the avatar's voice to create a voice tailored to their preferences. Furthermore, the voice generation unit has a function to evaluate the quality of the generated voice, allowing the user to check the clarity and naturalness of the voice and make modifications as needed. This enables the user to create a high-quality avatar voice tailored to their preferences.

[0071] The verification and correction unit verifies the avatar and voice generated by the avatar generation unit and voice generation unit, and makes corrections as needed. For example, the verification and correction unit provides an interface for the user to verify and correct the visual and voice of the generated avatar. The verification and correction unit has a function that allows the user to preview the avatar's visual and voice in real time. For example, the verification and correction unit provides an interface that allows the user to rotate the avatar's visual 360 degrees for verification. This allows the user to verify the overall appearance of the avatar and make corrections down to the smallest detail. The verification and correction unit also has a function that simulates the avatar's facial expressions and movements, allowing the user to verify the avatar's movements and make corrections in real time. Furthermore, the verification and correction unit plays the generated voice and provides an interface for the user to verify the tone and pitch of the voice and make corrections as needed. This allows the user to verify and correct the avatar's visual and voice in an integrated manner. The verification and correction unit collects user feedback and provides data for continuously improving the quality of the generated avatar and voice. As a result, the AI ​​agent service according to the embodiment allows the user to easily create and modify avatars and voices to their liking.

[0072] The avatar generation unit can create avatars by analyzing images using generative AI. For example, the avatar generation unit can use generative AI to analyze images uploaded by users and extract facial features. The generative AI can extract facial features with high accuracy using deep learning technology. For example, the generative AI can identify the contours of the face and the positions of the eyes, nose, and mouth, and generate an avatar based on that. The avatar generation unit can also use generative AI to integrate multiple images and generate more realistic avatars. For example, the generative AI can integrate images of faces taken from different angles and generate a 3D model. Furthermore, the avatar generation unit can use generative AI to customize the avatar's visual appearance according to the user's preferences. For example, the generative AI can generate an avatar that reflects the hairstyle and clothing specified by the user. This improves the accuracy of avatar generation by using generative AI. The generative AI can generate realistic avatars using, for example, GAN (Generative Opposite Network). A GAN consists of two networks: a generative model and a discriminative model. The generative model generates realistic images, and the discriminative model distinguishes between the generated images and actual images. This allows the generative model to generate realistic images that deceive the discriminative model. Some or all of the above processing in the avatar generation unit is performed using a generative AI. For example, the avatar generation unit inputs an image uploaded by the user into the generative AI, which analyzes the image and generates an avatar.

[0073] The voice generation unit can analyze audio data using generative AI and generate avatar voices. For example, the voice generation unit can use generative AI to analyze user-uploaded audio data and extract audio features. The generative AI can extract audio features with high accuracy using deep learning technology. For example, the generative AI analyzes the tone, pitch, and rhythm of the audio and generates the avatar voice based on that. The voice generation unit can also use generative AI to integrate multiple audio data to generate a more natural avatar voice. For example, the generative AI integrates audio data from different speakers to generate a unique voice. Furthermore, the voice generation unit can use generative AI to customize the avatar voice according to the user's preferences. For example, the generative AI generates an avatar voice that reflects the tone and pitch of the voice specified by the user. This improves the accuracy of voice generation by using generative AI. The generative AI can, for example, use GAN (Generative Opposite Network) to generate realistic audio. A GAN consists of two networks: a generative model and a discriminative model. The generative model generates realistic audio, and the discriminative model distinguishes between the generated audio and actual audio. This allows the generative model to generate realistic voices that deceive the identification model. Some or all of the above-described processes in the voice generation unit are performed using a generative AI. For example, the voice generation unit inputs voice data uploaded by the user into the generative AI, which analyzes the voice data and generates the avatar's voice.

[0074] The confirmation and modification unit allows the user to review the generated avatar and voice and make corrections as needed. For example, the confirmation and modification unit provides an interface for the user to review and modify the visual and voice aspects of the generated avatar. The confirmation and modification unit has a function that allows the user to preview the avatar's visual and voice aspects in real time. For example, the confirmation and modification unit provides an interface that allows the user to rotate the avatar's visual aspects 360 degrees for review. The confirmation and modification unit also provides an interface that allows the user to change the avatar's hairstyle, clothing, voice tone, and pitch. This allows the user to review and modify the generated avatar and voice aspects. Some or all of the above processing in the confirmation and modification unit may be performed using AI or not. For example, the confirmation and modification unit can input the visual and voice aspects of the generated avatar into the AI, which can then suggest corrections.

[0075] The avatar generation unit can generate avatars based on images uploaded by the user. For example, the avatar generation unit analyzes the user-uploaded image and extracts facial features. The generation AI uses deep learning technology to extract facial features with high accuracy. For example, the generation AI identifies the contours of the face and the positions of the eyes, nose, and mouth, and generates an avatar based on that. The avatar generation unit can also use the generation AI to integrate multiple images and generate a more realistic avatar. For example, the generation AI integrates images of faces taken from different angles to generate a 3D model. Furthermore, the avatar generation unit can use the generation AI to customize the avatar's appearance according to the user's preferences. For example, the generation AI generates an avatar that reflects the hairstyle and clothing specified by the user. This allows the avatar to be generated based on images uploaded by the user. Some or all of the above processes in the avatar generation unit are performed using the generation AI. For example, the avatar generation unit inputs the user-uploaded image into the generation AI, which analyzes the image and generates an avatar.

[0076] The voice generation unit can generate an avatar's voice based on audio data uploaded by the user. For example, the voice generation unit analyzes the user-uploaded audio data and extracts its characteristics. The generation AI uses deep learning technology to extract these characteristics with high accuracy. For example, the generation AI analyzes the tone, pitch, and rhythm of the voice and generates the avatar's voice based on this. Furthermore, the voice generation unit can use the generation AI to integrate multiple audio data sets to generate a more natural-sounding avatar voice. For example, the generation AI integrates audio data from different speakers to generate a unique voice. Additionally, the voice generation unit can use the generation AI to customize the avatar's voice according to the user's preferences. For example, the generation AI generates an avatar voice that reflects the tone and pitch specified by the user. This allows the voice generation unit to generate an avatar's voice based on the user-uploaded audio data. Some or all of the above-described processes in the voice generation unit are performed using the generation AI. For example, the voice generation unit inputs the user-uploaded audio data into the generation AI, which analyzes the audio data and generates the avatar's voice.

[0077] The image upload unit can estimate the user's emotions and adjust the image upload timing based on the estimated emotions. For example, if the user is relaxed, the image upload unit can flexibly set the image upload timing, allowing the user to upload at their preferred time. If the user is stressed, the image upload unit can speed up the image upload timing to complete the upload in a short time. For example, if the user is in a hurry, the image upload unit can optimize the image upload timing to complete the upload in the shortest possible time. This allows the image upload timing to be adjusted 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 image upload unit may be performed using AI or not. For example, the image upload unit inputs the user's facial expression data into the generative AI, which estimates the emotions and adjusts the upload timing.

[0078] The image upload unit can analyze the user's past image upload history and select the optimal upload method. For example, the image upload unit may prioritize suggesting upload methods that the user has frequently used in the past. The image upload unit can also select and suggest the most efficient upload method based on the user's past upload history. For example, the image upload unit may analyze the user's past upload history and suggest the optimal image format and resolution. This allows the optimal upload method to be selected based on the user's past history. Some or all of the above processing in the image upload unit may be performed using AI or not. For example, the image upload unit may input the user's past upload history data into the AI, and the AI ​​may select the optimal upload method.

[0079] The image upload unit can filter images based on the user's current projects and areas of interest when uploading them. For example, the image upload unit can prioritize uploading images related to the user's current project. The image upload unit can also filter and upload images based on the user's areas of interest. For example, the image upload unit can automatically exclude unnecessary images based on the user's projects and areas of interest. This allows for image filtering based on the user's projects and areas of interest. Some or all of the above processing in the image upload unit may be performed using AI or not. For example, the image upload unit can input data on the user's projects and areas of interest into the AI, which then filters out the most relevant images.

[0080] The image upload unit can estimate the user's emotions and determine the priority of images to upload based on the estimated emotions. For example, if the user is relaxed, the image upload unit will prioritize uploading images selected by the user. If the user is stressed, the image upload unit can also prioritize uploading important images. For example, if the user is in a hurry, the image upload unit will prioritize uploading the most important images. This allows the image priority to be determined 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 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 image upload unit may be performed using AI or not. For example, the image upload unit inputs the user's facial expression data into the generative AI, which estimates the emotions and determines the image priority.

[0081] The image upload unit can prioritize uploading highly relevant images by considering the user's geographical location information during image upload. For example, the image upload unit can prioritize uploading images related to the user's current location. The image upload unit can also filter and upload highly relevant images based on the user's geographical location information. For example, the image upload unit can automatically exclude unnecessary images based on the user's location information. This allows the uploading of highly relevant images based on the user's geographical location information. Some or all of the above processing in the image upload unit may be performed using AI or not. For example, the image upload unit inputs the user's geographical location information data into the AI, and the AI ​​filters out highly relevant images.

[0082] The image upload unit can analyze the user's social media activity when uploading images and upload relevant images. For example, the image upload unit can prioritize uploading images that are highly relevant to the user's social media activity. The image upload unit can also analyze the user's social media activity and automatically exclude unnecessary images. For example, the image upload unit can suggest the optimal image format and resolution based on the user's social media activity. This allows the user to upload relevant images based on their social media activity. Some or all of the above processing in the image upload unit may be performed using AI or not. For example, the image upload unit can input the user's social media activity data into the AI, and the AI ​​can select relevant images.

[0083] The avatar generation unit can estimate the user's emotions and adjust the avatar's expression based on the estimated emotions. For example, if the user is relaxed, the avatar generation unit will generate an avatar with a soft expression. If the user is excited, the avatar generation unit can also generate an avatar with an energetic expression. For example, if the user is sad, the avatar generation unit will generate an avatar with a calm expression. This allows the avatar's expression to be adjusted according to the user's emotions. Emotion estimation is achieved using an emotion estimation function, such as an emotion engine or a generative AI. The generative AI is, but is not limited to, a text generation AI (e.g., LLM) or a multimodal generation AI. Some or all of the above processing in the avatar generation unit is performed using the generative AI. For example, the avatar generation unit inputs the user's facial expression data into the generative AI, which estimates the emotions and adjusts the avatar's expression.

[0084] The avatar generation unit can adjust the level of detail of the avatar based on the importance of the image during avatar generation. For example, the avatar generation unit can generate a detailed avatar based on an important image. The avatar generation unit can also generate a simplified avatar based on an image of low importance. For example, the avatar generation unit adjusts the level of detail of the avatar's facial expressions and clothing according to the importance of the image. This allows the level of detail of the avatar to be adjusted according to the importance of the image. Some or all of the above processing in the avatar generation unit is performed using a generation AI. For example, the avatar generation unit inputs an image uploaded by the user into the generation AI, which evaluates the importance of the image and adjusts the level of detail of the avatar.

[0085] The avatar generation unit can apply different generation algorithms depending on the image category when generating an avatar. For example, the avatar generation unit can apply an algorithm to generate a realistic avatar based on a portrait image. It can also apply an algorithm to generate an anime-style avatar based on an illustration image. For example, the avatar generation unit can apply an algorithm to generate a photorealistic avatar based on a photographic image. This allows the optimal generation algorithm to be applied according to the image category. Some or all of the above processing in the avatar generation unit is performed using a generation AI. For example, the avatar generation unit inputs an image uploaded by the user into the generation AI, which determines the image category and applies the optimal generation algorithm.

[0086] The audio upload unit can estimate the user's emotions and adjust the timing of the audio upload based on the estimated emotions. For example, if the user is relaxed, the audio upload unit can flexibly set the timing of the audio upload, allowing the user to upload at their preferred time. If the user is stressed, the audio upload unit can speed up the audio upload, completing the upload in a short time. For example, if the user is in a hurry, the audio upload unit can optimize the timing of the audio upload, completing the upload in the shortest possible time. This allows the timing of the audio upload to be adjusted 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 audio upload unit may be performed using AI or not. For example, the audio upload unit inputs the user's facial expression data into the generative AI, which estimates the emotions and adjusts the upload timing.

[0087] The audio upload unit can analyze the user's past audio upload history and select the optimal upload method. For example, the audio upload unit may prioritize suggesting upload methods that the user has frequently used in the past. The audio upload unit can also select and suggest the most efficient upload method based on the user's past upload history. For example, the audio upload unit may analyze the user's past upload history and suggest the optimal audio format and resolution. This allows the system to select the optimal upload method based on the user's past history. Some or all of the above processing in the audio upload unit may be performed using AI or not. For example, the audio upload unit may input the user's past upload history data into the AI, which will then select the optimal upload method.

[0088] The audio upload unit can filter audio uploads based on the user's current projects and areas of interest. For example, the audio upload unit prioritizes uploading audio related to the user's current projects. The audio upload unit can also filter and upload highly relevant audio based on the user's areas of interest. For example, the audio upload unit automatically excludes unnecessary audio based on the user's projects and areas of interest. This allows for filtering audio based on the user's projects and areas of interest. Some or all of the above processing in the audio upload unit may be performed using AI or not. For example, the audio upload unit inputs data on the user's projects and areas of interest into the AI, which then filters the audio for high relevance.

[0089] The voice generation unit can estimate the user's emotions and adjust the voice expression based on the estimated emotions. For example, if the user is relaxed, the voice generation unit will produce a soft voice. If the user is excited, the voice generation unit can also produce an energetic voice. For example, if the user is sad, the voice generation unit will produce a calm voice. This allows the voice expression to be 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 voice generation unit is performed using the generative AI. For example, the voice generation unit inputs the user's facial expression data into the generative AI, which estimates the emotions and adjusts the voice expression.

[0090] The voice generation unit can adjust the level of detail of the audio based on the importance of the audio data during voice generation. For example, the voice generation unit can generate detailed audio based on important audio data. The voice generation unit can also generate simplified audio based on less important audio data. For example, the voice generation unit adjusts the level of detail of the tone and intonation of the audio according to the importance of the audio data. This allows the level of detail of the audio to be adjusted according to the importance of the audio data. Some or all of the above processing in the voice generation unit is performed using a generation AI. For example, the voice generation unit inputs audio data uploaded by the user into the generation AI, which evaluates the importance of the audio data and adjusts the level of detail of the audio.

[0091] The voice generation unit can apply different generation algorithms depending on the category of the audio data during voice generation. For example, the voice generation unit can apply an algorithm to generate smooth audio based on narration audio. The voice generation unit can also apply an algorithm to generate natural dialogue audio based on conversational audio. For example, the voice generation unit can apply an algorithm to generate melodious audio based on singing voice. This allows the optimal generation algorithm to be applied according to the category of the audio data. Some or all of the above processing in the voice generation unit is performed using a generation AI. For example, the voice generation unit inputs audio data uploaded by the user into the generation AI, which determines the category of the audio data and applies the optimal generation algorithm.

[0092] The voice generation unit can estimate the user's emotions and adjust the length of the speech based on the estimated emotions. For example, if the user is relaxed, the voice generation unit will generate a longer speech. If the user is in a hurry, the voice generation unit can also generate a shorter speech. For example, if the user is excited, the voice generation unit will generate a more dynamic speech. This allows the length of the speech to be adjusted according to the user's emotions. Emotion estimation is achieved using an emotion estimation function, such as an emotion engine or a generative AI. The generative AI is, but is not limited to, a text generation AI (e.g., LLM) or a multimodal generation AI. Some or all of the above processing in the voice generation unit is performed using the generative AI. For example, the voice generation unit inputs the user's facial expression data into the generative AI, which estimates the emotions and adjusts the length of the speech.

[0093] The voice generation unit can determine the priority of voices based on when the voice data was submitted. For example, the voice generation unit can prioritize generating voices based on the most recent voice data. The voice generation unit can also postpone generating voices based on older voice data. For example, the voice generation unit adjusts the voice generation order according to the submission date. This allows the priority of voices to be determined according to when the voice data was submitted. Some or all of the above processing in the voice generation unit is performed using a generation AI. For example, the voice generation unit inputs the voice data uploaded by the user into the generation AI, which evaluates the submission date and determines the priority of the voices.

[0094] The voice generation unit can adjust the order of audio based on the relevance of the audio data during voice generation. For example, the voice generation unit can prioritize generating audio based on highly relevant audio data. The voice generation unit can also postpone generating audio based on less relevant audio data. For example, the voice generation unit adjusts the order of voice generation according to the relevance of the audio data. This allows the order of audio to be adjusted according to the relevance of the audio data. Some or all of the above processing in the voice generation unit is performed using a generation AI. For example, the voice generation unit inputs audio data uploaded by the user into the generation AI, which evaluates the relevance and adjusts the order of the audio.

[0095] The confirmation / correction unit can estimate the user's emotions and adjust the confirmation / correction method based on the estimated user emotions. For example, if the user is relaxed, the confirmation / correction unit can provide detailed confirmation / correction options. If the user is stressed, the confirmation / correction unit can also provide simplified confirmation / correction options. For example, if the user is in a hurry, the confirmation / correction unit can provide an option for quick confirmation / correction. This allows the confirmation / correction method to be adjusted according to the user's emotions. Emotion estimation is achieved using an emotion estimation function, for example, using an emotion engine or generative AI. The generative AI is, but is not limited to, text generation AI (e.g., LLM) or multimodal generation AI. Some or all of the above processing in the confirmation / correction unit may be performed using AI or not. For example, the confirmation / correction unit inputs the user's facial expression data into the generative AI, which estimates the emotions and adjusts the confirmation / correction method.

[0096] The verification and correction unit can select the optimal correction method by referring to the user's past correction history during the verification and correction process. For example, the verification and correction unit may prioritize suggesting correction methods that the user has frequently used in the past. The verification and correction unit can also select and suggest the most efficient correction method from the user's past correction history. For example, the verification and correction unit may analyze the user's past correction history and suggest the optimal correction option. This allows the optimal correction method to be selected based on the user's past correction history. Some or all of the above processes in the verification and correction unit may be performed using AI or not. For example, the verification and correction unit may input the user's past correction history data into the AI, and the AI ​​may select the optimal correction method.

[0097] The confirmation and correction unit can customize the means of correction based on the user's current living situation during the confirmation and correction process. For example, if the user is busy, the confirmation and correction unit can provide simplified correction options. If the user is relaxed, the confirmation and correction unit can also provide detailed correction options. For example, the confirmation and correction unit can suggest the optimal correction method according to the user's living situation. This allows the means of correction to be customized according to the user's living situation. Some or all of the above processing in the confirmation and correction unit may be performed using AI or not. For example, the confirmation and correction unit inputs the user's living situation data into the AI, and the AI ​​suggests the optimal correction method.

[0098] The confirmation and correction unit can estimate the user's emotions and determine the priority of confirmation and correction based on the estimated user emotions. For example, if the user is relaxed, the confirmation and correction unit will prioritize the corrections selected by the user. If the user is stressed, the confirmation and correction unit can also prioritize important corrections. For example, if the user is in a hurry, the confirmation and correction unit will prioritize the most important corrections. This allows the priority of confirmation and correction to be determined 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 confirmation and correction unit may be performed using AI or not. For example, the confirmation and correction unit inputs the user's facial expression data into the generative AI, which estimates the emotions and determines the priority of confirmation and correction.

[0099] The verification and correction unit can select the optimal correction method by considering the user's geographical location information during verification and correction. For example, the verification and correction unit may prioritize corrections related to the user's current location. The verification and correction unit can also select the optimal correction method based on the user's geographical location information. For example, the verification and correction unit may automatically exclude unnecessary corrections based on the user's location information. This allows the unit to select the optimal correction method based on the user's geographical location information. Some or all of the above processes in the verification and correction unit may be performed using AI or not. For example, the verification and correction unit may input the user's geographical location information data into the AI, and the AI ​​may select the optimal correction method.

[0100] The verification and correction unit can analyze the user's social media activity and propose correction measures during the verification and correction process. For example, the verification and correction unit can propose highly relevant correction measures based on the user's social media activity. The verification and correction unit can also analyze the user's social media activity and automatically exclude unnecessary correction measures. For example, the verification and correction unit can propose the optimal correction measure based on the user's social media activity. This allows the unit to propose the optimal correction measure based on the user's social media activity. Some or all of the above processing in the verification and correction unit may be performed using AI or not. For example, the verification and correction unit inputs the user's social media activity data into the AI, and the AI ​​proposes the optimal correction measure.

[0101] The system according to the embodiment is not limited to the example described above, and various modifications are possible, for example, as follows.

[0102] The avatar generation unit can be equipped with the function to dynamically change the avatar's facial expression based on images uploaded by the user. For example, if the user uploads an image of a smiling face, the avatar can be generated to display a smiling face. Similarly, if the user uploads an image of a serious face, the avatar can be generated to display a serious face. Furthermore, if the user uploads images of multiple different facial expressions, the avatar can be made to seamlessly switch between these expressions. This allows users to customize their avatar's facial expressions to be more realistic.

[0103] The avatar generation unit can have a function to automatically suggest avatar clothing based on images uploaded by the user. For example, the avatar generation unit can analyze the background and color scheme of the image uploaded by the user and suggest clothing that matches it. Furthermore, if the user uploads an image based on a specific theme, it can suggest clothing that matches that theme. In addition, the avatar generation unit can refer to the user's past selection history and suggest clothing that suits the user's preferences. This allows users to easily customize their avatar's clothing.

[0104] The voice generation unit can be equipped with the function to adjust the emotional expression of the avatar's voice based on the voice data uploaded by the user. For example, the voice generation unit can analyze the tone and pitch of the voice data uploaded by the user and adjust the emotional expression of the avatar's voice based on that. Furthermore, if the user uploads voice data expressing a specific emotion, it can also generate a voice that reflects that emotion. In addition, the voice generation unit can refer to the user's past voice data and suggest emotional expressions that suit the user's preferences. This allows users to customize the emotional expression of their avatar's voice to be more realistic.

[0105] The confirmation and editing unit can include features for sharing user-generated avatars and voices with other users. For example, the confirmation and editing unit can generate links for sharing user-generated avatars and voices on social media or messaging apps. It can also provide features for sharing user-generated avatars and voices with other users in real time. Furthermore, the confirmation and editing unit can provide features for collaboratively editing user-generated avatars and voices with other users. This allows users to easily share and collaboratively edit their generated avatars and voices with other users.

[0106] The avatar generation unit can have the function to automatically generate avatar movements based on images uploaded by the user. For example, the avatar generation unit can analyze the pose of an image uploaded by the user and generate avatar movements based on that. Furthermore, if the user uploads an image expressing a specific movement, it can generate an avatar that reflects that movement. In addition, the avatar generation unit can refer to the user's past movement selection history and suggest movements that suit the user's preferences. This allows users to easily customize their avatar movements.

[0107] The voice generation unit can be equipped with a function to adjust the accent of the avatar's voice based on voice data uploaded by the user. For example, the voice generation unit can analyze the accent of the voice data uploaded by the user and adjust the accent of the avatar's voice accordingly. Furthermore, if the user uploads voice data expressing a specific regional accent, the unit can generate a voice that reflects that accent. In addition, the voice generation unit can refer to the user's past voice data and suggest accents that suit the user's preferences. This allows users to customize the accent of their avatar's voice more realistically.

[0108] The image upload unit can have a function to automatically generate avatar backgrounds based on images uploaded by the user. For example, the image upload unit can analyze the background of an image uploaded by the user and generate an avatar background based on that analysis. Furthermore, if the user uploads an image depicting a specific background, it can generate an avatar that reflects that background. In addition, the image upload unit can refer to the user's past background selection history and suggest backgrounds that match the user's preferences. This allows users to easily customize their avatar backgrounds.

[0109] The image upload unit can estimate the user's emotions and filter images based on those emotions. For example, if the user is relaxed, the image upload unit will prioritize uploading images with soft colors. If the user is excited, the image upload unit can also prioritize uploading images with vibrant colors. Furthermore, if the user is sad, the image upload unit can also prioritize uploading images with calm colors. This allows for image filtering according to the user's emotions.

[0110] The voice generation unit can have a function to adjust the speed of the avatar's voice based on the voice data uploaded by the user. For example, the voice generation unit can analyze the speed of the voice data uploaded by the user and adjust the speed of the avatar's voice accordingly. Furthermore, if the user uploads voice data spoken at a specific speed, the unit can generate a voice that reflects that speed. In addition, the voice generation unit can refer to the user's past voice data and suggest a speed that suits the user's preferences. This allows users to easily customize the speed of their avatar's voice.

[0111] The confirmation and correction unit can estimate the user's emotions and customize the confirmation and correction interface based on those estimated emotions. For example, if the user is relaxed, the confirmation and correction unit can provide detailed confirmation and correction options. If the user is stressed, it can also provide simplified confirmation and correction options. Furthermore, if the user is in a hurry, the confirmation and correction unit can provide an option for quick confirmation and correction. This allows the confirmation and correction interface to be customized according to the user's emotions.

[0112] The following briefly describes the processing flow for example form 2.

[0113] Step 1: The image upload section allows users to upload images of their preferred faces. These images can include JPEG and PNG formats, as well as portraits. The image upload section saves the uploaded images to cloud storage, checks their quality, and performs image corrections as needed. For example, it can adjust the image resolution and automatically crop out the face. Step 2: The avatar generation unit uses a generation AI to analyze the image uploaded by the image upload unit and create an avatar. The generation AI uses deep learning technology to extract facial features and generate the avatar. The avatar generation unit presents the generated avatar's visual appearance to the user and allows the user to make modifications as needed. For example, it provides an interface that allows the user to change the avatar's hairstyle or clothing. Step 3: The audio upload section allows users to upload video files or URLs containing their favorite voices. The audio data uploaded by users can include video files in MP4 or AVI format, or URLs to video sharing sites. The audio upload section saves the uploaded audio data to cloud storage, checks the audio quality, and performs audio correction as needed. For example, it can remove audio noise and adjust the volume. Step 4: The voice generation unit uses a generation AI to analyze the audio data uploaded by the voice upload unit and generate the avatar's voice. The generation AI uses deep learning technology to extract audio features and generate the avatar's voice. The voice generation unit presents the generated voice to the user and allows the user to make modifications as needed. For example, it provides an interface that allows the user to change the tone and pitch of the avatar's voice. Step 5: The confirmation and modification unit checks the avatar and voice generated by the avatar generation unit and voice generation unit, and makes corrections as needed. The confirmation and modification unit provides an interface for the user to check and modify the visual and voice of the generated avatar. For example, it provides an interface that allows the user to rotate the avatar's visual appearance 360 ​​degrees for review.

[0114] 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.

[0115] 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.

[0116] 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.

[0117] Each of the multiple elements described above, including the image upload unit, avatar generation unit, voice upload unit, voice generation unit, and confirmation / correction unit, is implemented in at least one of the smart device 14 and the data processing device 12. For example, the image upload unit is implemented by the control unit 46A of the smart device 14, allowing the user to upload an image of their preferred face. The avatar generation unit is implemented by the specific processing unit 290 of the data processing device 12, creating an avatar using a generation AI. The voice upload unit is implemented by the control unit 46A of the smart device 14, allowing the user to upload a video file or URL containing their preferred voice. The voice generation unit is implemented by the specific processing unit 290 of the data processing device 12, generating the avatar's voice using a generation AI. The confirmation / correction unit is implemented by the control unit 46A of the smart device 14, allowing the user to confirm the generated avatar and voice and make corrections as needed. The correspondence between each unit and the device or control unit is not limited to the example described above, and various changes are possible.

[0118] [Second Embodiment] Figure 3 shows an example of the configuration of the data processing system 210 according to the second embodiment.

[0119] 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.

[0120] 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.

[0121] 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.

[0122] 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.

[0123] 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).

[0124] 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.

[0125] 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.

[0126] 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.

[0127] 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.

[0128] 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.

[0129] 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.).

[0130] 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.

[0131] 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.

[0132] 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.

[0133] Each of the multiple elements described above, including the image upload unit, avatar generation unit, voice upload unit, voice generation unit, and confirmation / correction unit, is implemented in at least one of the smart glasses 214 and the data processing device 12. For example, the image upload unit is implemented by the control unit 46A of the smart glasses 214, allowing the user to upload an image of their preferred face. The avatar generation unit is implemented by the specific processing unit 290 of the data processing device 12, creating an avatar using a generation AI. The voice upload unit is implemented by the control unit 46A of the smart glasses 214, allowing the user to upload a video file or URL containing a voice they like. The voice generation unit is implemented by the specific processing unit 290 of the data processing device 12, generating the avatar's voice using a generation AI. The confirmation / correction unit is implemented by the control unit 46A of the smart glasses 214, allowing the user to confirm the generated avatar and voice and make corrections as needed. The correspondence between each unit and the device or control unit is not limited to the example described above, and various changes are possible.

[0134] [Third Embodiment] Figure 5 shows an example of the configuration of the data processing system 310 according to the third embodiment.

[0135] 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.

[0136] 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.

[0137] 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.

[0138] 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.

[0139] 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).

[0140] 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.

[0141] 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.

[0142] 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.

[0143] 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.

[0144] 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.

[0145] 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.).

[0146] 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.

[0147] 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.

[0148] 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.

[0149] Each of the multiple elements described above, including the image upload unit, avatar generation unit, voice upload unit, voice generation unit, and confirmation / correction unit, is implemented in at least one of the headset terminal 314 and the data processing device 12. For example, the image upload unit is implemented by the control unit 46A of the headset terminal 314, allowing the user to upload an image of their preferred face. The avatar generation unit is implemented by the specific processing unit 290 of the data processing device 12, creating an avatar using a generation AI. The voice upload unit is implemented by the control unit 46A of the headset terminal 314, allowing the user to upload a video file or URL containing their preferred voice. The voice generation unit is implemented by the specific processing unit 290 of the data processing device 12, generating the avatar's voice using a generation AI. The confirmation / correction unit is implemented by the control unit 46A of the headset terminal 314, allowing the user to confirm the generated avatar and voice and make corrections as needed. The correspondence between each unit and the device or control unit is not limited to the example described above, and various changes are possible.

[0150] [Fourth Embodiment] Figure 7 shows an example of the configuration of the data processing system 410 according to the fourth embodiment.

[0151] 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.

[0152] 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.

[0153] 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.

[0154] 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.

[0155] 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).

[0156] 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.

[0157] 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.

[0158] 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.

[0159] 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.

[0160] 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.

[0161] 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.

[0162] 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.).

[0163] 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.

[0164] 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.

[0165] 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.

[0166] Each of the multiple elements described above, including the image upload unit, avatar generation unit, voice upload unit, voice generation unit, and confirmation / correction unit, is implemented in at least one of the robot 414 and the data processing unit 12. For example, the image upload unit is implemented by the control unit 46A of the robot 414, allowing the user to upload an image of their preferred face. The avatar generation unit is implemented by the specific processing unit 290 of the data processing unit 12, creating an avatar using a generation AI. The voice upload unit is implemented by the control unit 46A of the robot 414, allowing the user to upload a video file or URL containing their preferred voice. The voice generation unit is implemented by the specific processing unit 290 of the data processing unit 12, generating the avatar's voice using a generation AI. The confirmation / correction unit is implemented by the control unit 46A of the robot 414, allowing the user to review the generated avatar and voice and make corrections as needed. The correspondence between each unit and the device or control unit is not limited to the example described above, and various modifications are possible.

[0167] 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.

[0168] 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.

[0169] 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.

[0170] 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.

[0171] 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.

[0172] 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."

[0173] 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.

[0174] 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.

[0175] 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.

[0176] 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.

[0177] 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.

[0178] 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.

[0179] 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.

[0180] 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.

[0181] 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.

[0182] 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.

[0183] 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.

[0184] 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.

[0185] (Note 1) An image upload section where users upload images of their preferred faces, An avatar generation unit that analyzes the image uploaded by the aforementioned image upload unit to create an avatar, The audio upload section allows users to upload video files or URLs containing their favorite voices, A voice generation unit analyzes the voice data uploaded by the voice upload unit and generates the voice of an avatar, The system includes a confirmation and correction unit that checks the avatar and voice generated by the avatar generation unit and voice generation unit, and makes corrections as necessary. A system characterized by the following features. (Note 2) The avatar generation unit is, We use generative AI to analyze images and create avatars. The system described in Appendix 1, characterized by the features described herein. (Note 3) The aforementioned speech generation unit, Using a generative AI, audio data is analyzed to generate the voice of an avatar. The system described in Appendix 1, characterized by the features described herein. (Note 4) The aforementioned verification and correction unit is: Users can review the generated avatar and voice and make corrections as needed. The system described in Appendix 1, characterized by the features described herein. (Note 5) The avatar generation unit is, Avatars are generated based on images uploaded by the user. The system described in Appendix 1, characterized by the features described herein. (Note 6) The aforementioned speech generation unit, The system generates avatar voices based on user-uploaded audio data. The system described in Appendix 1, characterized by the features described herein. (Note 7) The aforementioned image upload unit is It estimates the user's emotions and adjusts the timing of image uploads based on those estimated emotions. The system described in Appendix 1, characterized by the features described herein. (Note 8) The aforementioned image upload unit is Analyze the user's past image upload history and select the optimal upload method. The system described in Appendix 1, characterized by the features described herein. (Note 9) The aforementioned image upload unit is When uploading images, filtering is performed based on the user's current projects and areas of interest. The system described in Appendix 1, characterized by the features described herein. (Note 10) The aforementioned image upload unit is It estimates the user's emotions and prioritizes the images to upload based on those estimated emotions. The system described in Appendix 1, characterized by the features described herein. (Note 11) The aforementioned image upload unit is When uploading images, the system prioritizes uploading images that are more relevant to the user's geographical location. The system described in Appendix 1, characterized by the features described herein. (Note 12) The aforementioned image upload unit is When uploading an image, the system analyzes the user's social media activity and uploads relevant images. The system described in Appendix 1, characterized by the features described herein. (Note 13) The avatar generation unit is, It estimates the user's emotions and adjusts the avatar's representation based on those estimated emotions. The system described in Appendix 1, characterized by the features described herein. (Note 14) The avatar generation unit is, When generating an avatar, the level of detail of the avatar is adjusted based on the importance of the image. The system described in Appendix 1, characterized by the features described herein. (Note 15) The avatar generation unit is, When generating avatars, different generation algorithms are applied depending on the image category. The system described in Appendix 1, characterized by the features described herein. (Note 16) The aforementioned audio upload unit is It estimates the user's emotions and adjusts the timing of audio uploads based on the estimated emotions. The system described in Appendix 1, characterized by the features described herein. (Note 17) The aforementioned audio upload unit is Analyze the user's past audio upload history and select the optimal upload method. The system described in Appendix 1, characterized by the features described herein. (Note 18) The aforementioned audio upload unit is When uploading audio, filtering is performed based on the user's current projects and areas of interest. The system described in Appendix 1, characterized by the features described herein. (Note 19) The aforementioned speech generation unit, It estimates the user's emotions and adjusts the way the voice is expressed based on those estimated emotions. The system described in Appendix 1, characterized by the features described herein. (Note 20) The aforementioned speech generation unit, During speech generation, adjust the level of detail in the speech based on the importance of the speech data. The system described in Appendix 1, characterized by the features described herein. (Note 21) The aforementioned speech generation unit, When generating speech, different generation algorithms are applied depending on the category of the speech data. The system described in Appendix 1, characterized by the features described herein. (Note 22) The aforementioned speech generation unit, It estimates the user's emotions and adjusts the length of the audio based on those emotions. The system described in Appendix 1, characterized by the features described herein. (Note 23) The aforementioned speech generation unit, When generating audio, the priority of the audio is determined based on when the audio data was submitted. The system described in Appendix 1, characterized by the features described herein. (Note 24) The aforementioned speech generation unit, During speech generation, the order of speech is adjusted based on the relationships between the speech data. The system described in Appendix 1, characterized by the features described herein. (Note 25) The aforementioned verification and correction unit is: We estimate the user's emotions and adjust the confirmation and correction methods based on the estimated user emotions. The system described in Appendix 1, characterized by the features described herein. (Note 26) The aforementioned verification and correction unit is: During the review and correction process, the system will refer to the user's past correction history to select the most appropriate correction method. The system described in Appendix 1, characterized by the features described herein. (Note 27) The aforementioned verification and correction unit is: During the review and correction process, the correction method is customized based on the user's current living situation. The system described in Appendix 1, characterized by the features described herein. (Note 28) The aforementioned verification and correction unit is: The system estimates the user's emotions and determines the priority of confirmation and correction based on the estimated user emotions. The system described in Appendix 1, characterized by the features described herein. (Note 29) The aforementioned verification and correction unit is: During the review and correction process, the optimal correction method will be selected considering the user's geographical location information. The system described in Appendix 1, characterized by the features described herein. (Note 30) The aforementioned verification and correction unit is: During the review and correction process, we analyze the user's social media activity and suggest corrective measures. The system described in Appendix 1, characterized by the features described herein. [Explanation of Symbols]

[0186] 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 image upload section where users upload images of their preferred faces, An avatar generation unit that analyzes the image uploaded by the aforementioned image upload unit to create an avatar, The audio upload section allows users to upload video files or URLs containing their favorite voices, A voice generation unit analyzes the voice data uploaded by the voice upload unit and generates the voice of an avatar, The system includes a confirmation and correction unit that checks the avatar and voice generated by the avatar generation unit and the voice generation unit, and makes corrections as necessary. A system characterized by the following features.

2. The avatar generation unit is, Use generative AI to analyze images and create avatars. The system according to feature 1.

3. The aforementioned speech generation unit, Generative AI is used to analyze audio data and generate the voice of an avatar. The system according to feature 1.

4. The aforementioned verification and correction unit is: Users can review the generated avatar and voice and make corrections as needed. The system according to feature 1.

5. The avatar generation unit is, Avatars are generated based on images uploaded by the user. The system according to feature 1.

6. The aforementioned speech generation unit, Generates avatar voices based on user-uploaded audio data. The system according to feature 1.

7. The aforementioned image upload unit is It estimates the user's emotions and adjusts the timing of image uploads based on those estimated emotions. The system according to feature 1.

8. The aforementioned image upload unit is Analyze the user's past image upload history and select the optimal upload method. The system according to feature 1.

Images