System

Abstract

An object of the system according to the embodiment is to generate a natural virtual avatar by utilizing the regularity of voice and face.SOLUTION: In one embodiment, a system comprises a voice analyzer, a feature extractor, a mapper, an illustration generator, an actor face generator, and an avatar generator. The voice analysis unit analyzes a voice. The feature extraction unit extracts a feature of the voice analyzed by the voice analysis unit. The mapping unit maps the feature of the voice extracted by the feature extraction unit and the regularity of the face. The illustration generation unit generates an animation-style illustration based on a result of the mapping by the mapping unit. The actor's face generation unit generates an actor's face based on the result of mapping by the mapping unit. An avatar generation part generates a virtual avatar on the basis of the illustration and the face generated by the illustration generation part and the actor face generation part.SELECTED DRAWING: Figure 1

Description

[Technical Field]

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

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

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

[0004] Conventional technologies have not adequately utilized voice and facial regularities to generate virtual avatars, and there is room for improvement.

[0005] The system according to the embodiment aims to generate a natural looking virtual avatar by utilizing the regularity of voices and faces. [Means for solving the problem]

[0006] The system according to the embodiment includes a voice analysis unit, a feature extraction unit, a mapping unit, an illustration generation unit, an actor face generation unit, and an avatar generation unit. The voice analysis unit analyzes the voice. The feature extraction unit extracts the voice features analyzed by the voice analysis unit. The mapping unit maps the voice features extracted by the feature extraction unit to facial regularities. The illustration generation unit generates an anime-style illustration based on the results of mapping by the mapping unit. The actor face generation unit generates an actor's face based on the results of mapping by the mapping unit. The avatar generation unit generates a virtual avatar based on the illustration and face generated by the illustration generation unit and the actor face generation unit. [Effects of the Invention]

[0007] The system according to the embodiment can generate a natural looking virtual avatar by utilizing the regularity of voices and faces. [Brief explanation of the drawings]

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

[0025] The storage 32 stores a data generation model 58 and an emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290. The identification processing unit 290 can estimate the user's emotion using the emotion identification model 59 and perform identification processing using the user's emotion.

[0026] In the smart device 14, the specific processing is performed by the processor 46. The storage 50 stores a specific processing program 60. The specific processing program 60 is used together with the specific processing program 56 by the data processing system 10. The processor 46 reads the specific processing program 60 from the storage 50 and executes the read specific processing program 60 on the RAM 48. The specific processing is realized by the processor 46 operating as the control unit 46A in accordance with the specific processing program 60 executed on the RAM 48. Note that the smart device 14 may have a data generation model and an emotion identification model similar to the data generation model 58 and the emotion identification model 59.

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

[0028] (Example 1) The image generation system according to the embodiment of the present invention is a system that generates anime-style illustrations and actor's faces from voices and creates virtual avatars. This allows the image generation system to directly generate anime-style illustrations and actor's faces from voices and use them as virtual avatars.

[0029] An image generation system according to an embodiment includes a voice analysis unit, a feature extraction unit, a mapping unit, an illustration generation unit, an actor face generation unit, and an avatar generation unit. The voice analysis unit analyzes the voice. For example, the voice analysis unit analyzes input voice waveform data and extracts features such as pitch, tone, and rhythm. The voice analysis unit can also analyze the emotional state of the voice. The feature extraction unit extracts features of the voice analyzed by the voice analysis unit. For example, the feature extraction unit extracts elements such as pitch, tone, rhythm, and emotion as numerical data. The feature extraction unit can also model the physical characteristics of the voice source (e.g., throat, mouth, nose) to extract more precise features. The mapping unit maps the voice features extracted by the feature extraction unit to facial regularities. For example, the mapping unit learns facial features (e.g., eye shape, mouth size) that correspond to specific voice pitches and tones, and generates corresponding facial features from the voice features. The mapping unit can also model subtle changes in facial expressions and muscle movements to generate more realistic facial features. The illustration generation unit generates anime-style illustrations based on the results mapped by the mapping unit. For example, the illustration generation unit determines eye shape, hairstyle, facial expression, etc. based on voice characteristics to draw anime-style characters. The illustration generation unit can also generate character movements and poses in real time to create dynamic animations. The actor face generation unit generates an actor's face based on the results mapped by the mapping unit. For example, the actor face generation unit determines facial contours, facial features, hairstyle, etc. based on voice characteristics to draw a realistic actor's face. The actor face generation unit can also reflect the actor's expressions and emotions in real time to generate facial changes according to emotions. The avatar generation unit generates a virtual avatar based on the illustrations and faces generated by the illustration generation unit and the actor face generation unit. For example, the avatar generation unit utilizes voice characteristics and facial regularity to generate an avatar with a natural appearance while maintaining consistency with the voice. The avatar generation unit can also generate avatar movements and gestures in real time, allowing for more natural movements.As a result, the image generation system according to the embodiment can generate anime-style illustrations or actor's faces from voices and create virtual avatars. For example, a user can generate an avatar with the face of an anime character or actor that resembles them simply by inputting their own voice. This will realize new forms of entertainment and communication that utilize XR technology.

[0030] The voice analysis unit can analyze subtle changes in voice and intonation in real time to extract more detailed features. For example, the voice analysis unit develops a highly accurate voice analysis algorithm to analyze subtle changes in voice and intonation in real time. For example, it divides voice waveform data into small segments and analyzes the frequency components and amplitude fluctuations of each segment. The voice analysis unit also builds a system that analyzes voice intonation and rhythm in real time to extract detailed voice features. For example, it analyzes the pitch and tempo of the audio signal to estimate the emotion and intention of the voice. The voice analysis unit also collects voice data using multiple audio sensors to capture subtle changes in voice and analyzes it in real time. For example, it uses a microphone array to measure the direction and distance of the voice and extract detailed features. This allows for real-time analysis of subtle changes in voice and intonation to extract detailed features.

[0031] The voice analysis unit models the physical characteristics of the voice source, allowing for more precise extraction of voice features. For example, the voice analysis unit models the physical characteristics of the throat, mouth, and nose, which are the voice source, and develops a system that precisely extracts voice features. For example, it simulates the vibration of the vocal cords and the resonance characteristics of the oral cavity. In addition, to analyze the physical characteristics of the voice source, the voice analysis unit reproduces the voice production process using acoustic simulation technology. For example, it models the movement of the vocal cords and the changes in the shape of the oral cavity. In addition, the voice analysis unit develops an algorithm that analyzes voice features in detail based on the physical characteristics of the voice source. For example, it analyzes the vibration pattern of the vocal cords and the resonance frequency of the oral cavity to extract voice features. This allows for modeling the physical characteristics of the voice source and for precise extraction of voice features.

[0032] The voice analysis unit can accommodate different languages ​​and dialects, enabling global user support. For example, the voice analysis unit develops a multilingual voice analysis algorithm to accommodate different languages ​​and dialects. For example, it collects voice data for each language and dialect and trains features. In addition, the voice analysis unit analyzes voice data from different languages ​​and dialects to build a system that extracts common features, enabling global user support. For example, it analyzes differences in voice rhythm and intonation. In addition, in order to accommodate different languages ​​and dialects, the voice analysis unit converts voice data into text using voice recognition technology and extracts features based on the text data. For example, it analyzes the content and context of the voice. This allows the system to accommodate different languages ​​and dialects and global users.

[0033] The voice analysis unit can also be applied to music and singing voices and used to generate musical avatars. For example, the voice analysis unit develops an algorithm specialized for analyzing music and singing voices and uses it to generate musical avatars. For example, it analyzes the pitch and rhythm of singing voices and generates the movements of a musical avatar. The voice analysis unit also analyzes the characteristics of music and singing voices and builds a system that generates musical avatars based on those characteristics. For example, it analyzes the emotions and expressions of singing voices and generates the facial expressions and movements of an avatar. The voice analysis unit also optimizes the musical avatar generation process based on the analysis results of music and singing voices. For example, it analyzes the characteristics of singing voices in detail and generates the movements and facial expressions of an avatar in real time. This allows it to be applied to music and singing voices and used to generate musical avatars.

[0034] The mapping unit can model subtle changes in facial expression or muscle movements to generate more realistic facial features. For example, the mapping unit develops a highly accurate facial recognition algorithm to model subtle changes in facial expression and muscle movements. For example, it simulates facial muscle movements to generate realistic facial expressions. The mapping unit also analyzes facial expression changes and muscle movements in detail and builds a system that generates facial features based on that data. For example, it models facial muscle movements and skin changes. The mapping unit also analyzes facial movements in real time using multiple cameras to capture subtle changes in facial expression and generates facial features based on that data. For example, it reproduces facial muscle movements in a 3D model. This makes it possible to model subtle changes in facial expression and muscle movements to generate realistic facial features.

[0035] The mapping unit can also be applied to animals and fantasy characters to generate a variety of avatars. For example, the mapping unit trains a dataset of specific animals or characters to apply the mapping between voice features and facial regularity to animals and fantasy characters. For example, the mapping unit analyzes the facial features of animals and fantasy characters' designs. The mapping unit also analyzes the facial features of animals and fantasy characters and builds a system that generates a variety of avatars based on that data. For example, the mapping unit models the facial expressions of animals and character features. The mapping unit also applies the mapping between voice features and facial regularity to animals and fantasy characters to develop a system that generates avatars in real time. For example, the mapping unit generates the faces of animals and characters based on voice features. This allows the mapping to be applied to animals and fantasy characters to generate a variety of avatars.

[0036] The mapping unit can accommodate facial features of different cultures and ethnicities and support global users. For example, the mapping unit analyzes facial features of different cultures and ethnicities and builds a system that maps voice features and facial regularities based on the data. For example, the mapping unit learns the facial features of each culture and ethnicity. In addition, to accommodate global users, the mapping unit analyzes facial features of different cultures and ethnicities and develops an algorithm that generates facial features based on the data. For example, it models face shape and skin color. In addition, to accommodate facial features of different cultures and ethnicities, the mapping unit integrates voice data and facial features and develops a system that supports global users. For example, it generates faces for different cultures and ethnicities based on voice features. This allows the system to accommodate facial features of different cultures and ethnicities and support global users.

[0037] The illustration generation unit can generate character movements and poses in real time to create dynamic animations. For example, the illustration generation unit develops a motion analysis algorithm to generate character movements and poses in real time. For example, it reproduces character movements based on motion capture data. The illustration generation unit also builds a system to generate character poses in real time and create dynamic animations. For example, it dynamically changes character poses in response to user input. The illustration generation unit also uses a machine learning algorithm to generate character movements and poses in real time and create animations. For example, it learns from past animation data and generates movements in real time. This allows character movements and poses to be generated in real time and dynamic animations to be created.

[0038] The illustration generation unit allows customization of the character's clothing and accessories, and can generate illustrations according to the user's preferences. The illustration generation unit, for example, develops a user interface to enable customization of the character's clothing and accessories. For example, it provides a function that allows selection of clothing and accessories by drag and drop. The illustration generation unit also builds a system that generates the character's clothing and accessories according to the user's preferences. For example, it dynamically changes the character's appearance based on the user's selection. The illustration generation unit also develops a system that allows customization of the character's clothing and accessories, and allows the user to generate illustrations according to their preferences. For example, it provides a function that allows free change of colors and designs. This allows customization of the character's clothing and accessories, and can generate illustrations according to the user's preferences.

[0039] The illustration generation unit can generate a variety of illustrations to accommodate different anime styles. For example, the illustration generation unit trains realistic and deformed datasets to accommodate different anime styles. For example, the unit analyzes the characteristics of each style and reflects them in the illustration generation algorithm. The illustration generation unit also develops an interface that allows users to select a style to accommodate a variety of anime styles. For example, the unit selects a realistic or deformed style and generates an illustration. The illustration generation unit also develops a style conversion algorithm to accommodate different anime styles and generates an illustration according to the user's selection. For example, the unit converts a realistic illustration into a deformed illustration. This allows the unit to generate a variety of illustrations to accommodate different anime styles.

[0040] The illustration generation unit can also be applied to manga and comic characters to generate manga-style illustrations. For example, the illustration generation unit trains a manga-style dataset to apply to manga and comic characters. For example, it analyzes the characteristic line and shadow expressions of manga and reflects this in the illustration generation algorithm. In addition, the illustration generation unit develops an interface that allows a user to select a manga style to generate manga-style illustrations. For example, it selects a manga-style style and generates an illustration. In addition, the illustration generation unit develops a style conversion algorithm to apply to manga and comic characters and generates manga-style illustrations according to the user's selection. For example, it converts an anime-style illustration into a manga style. This allows it to be applied to manga and comic characters to generate manga-style illustrations.

[0041] The actor face generation unit generates facial features according to the actor's age and gender, allowing for the creation of a more realistic face. For example, the actor face generation unit learns data sets for each age and gender in order to generate facial features according to the actor's age and gender. For example, it analyzes facial changes due to age and gender and reflects this in the face generation algorithm. The actor face generation unit also analyzes facial features according to the actor's age and gender in detail, and builds a system that generates a realistic face based on that data. For example, it models facial wrinkles due to age and facial contours due to gender. The actor face generation unit also learns facial features using a machine learning algorithm in order to generate facial features according to the actor's age and gender. For example, it analyzes facial features for each age and gender in detail to generate a realistic face. This allows for the generation of facial features according to the actor's age and gender, allowing for the creation of a realistic face.

[0042] The actor face generation unit can generate facial features according to different movie genres. For example, to support different movie genres, the actor face generation unit learns datasets for each genre. For example, the facial features of actors in action movies and comedy movies are analyzed and reflected in the face generation algorithm. The actor face generation unit also develops an interface that allows a user to select a genre in order to generate facial features according to the movie genre. For example, the genre of action movies or comedy movies is selected and a face is generated. The actor face generation unit also develops a genre conversion algorithm to support different movie genres and generates facial features according to the user's selection. For example, the face of an action movie actor is converted to look like a comedy movie. This allows facial features to be generated according to different movie genres.

[0043] The actor face generation unit can be applied to historical figures and fictional characters to generate a variety of faces. For example, the actor face generation unit trains a specific dataset to be applied to historical figures and fictional characters. For example, portraits of historical figures and designs of fictional characters are analyzed and reflected in the face generation algorithm. The actor face generation unit also analyzes the facial features of historical figures and fictional characters and builds a system that generates a variety of faces based on that data. For example, the facial features of historical figures and designs of fictional characters are modeled. The actor face generation unit also develops a system that can be applied to historical figures and fictional characters to generate faces in real time. For example, the face of a historical figure or fictional character is generated based on voice characteristics. This allows the system to be applied to historical figures and fictional characters to generate a variety of faces.

[0044] The avatar generation unit generates avatar movements and gestures in real time, enabling more natural movements. The avatar generation unit, for example, develops a motion analysis algorithm to generate avatar movements and gestures in real time. For example, the avatar generation unit reproduces avatar movements based on motion capture data. The avatar generation unit also builds a system that generates avatar movements in real time and enables natural movements. For example, the avatar generation unit dynamically changes avatar movements in response to user input. The avatar generation unit also uses a machine learning algorithm to generate avatar movements and gestures in real time and enable natural movements. For example, the avatar generation unit learns past movement data and generates movements in real time. This allows avatar movements and gestures to be generated in real time and enable natural movements.

[0045] The avatar generation unit allows the avatar's clothing and accessories to be customized, and can generate an avatar according to the user's preferences. The avatar generation unit, for example, develops a user interface to enable the avatar's clothing and accessories to be customized. For example, it provides a function that allows the user to select clothing and accessories by drag and drop. The avatar generation unit also builds a system that generates the avatar's clothing and accessories according to the user's preferences. For example, it dynamically changes the avatar's appearance based on the user's selection. The avatar generation unit also develops a system that allows the avatar's clothing and accessories to be customized, and allows the user to generate an avatar according to their preferences. For example, it provides a function that allows the user to freely change colors and designs. This allows the avatar's clothing and accessories to be customized, and an avatar can be generated according to the user's preferences.

[0046] The avatar generation unit can support different platforms and make the avatar usable for a variety of purposes. For example, to support different platforms, the avatar generation unit develops avatar generation algorithms tailored to the specifications of each platform. For example, the avatar data format is converted according to the specifications of games and social networking sites. The avatar generation unit also develops an interface that allows users to select a platform to generate avatars that can be used for a variety of purposes. For example, the avatar generation unit selects and generates avatars for games and social networking sites. The avatar generation unit also builds a system that allows avatar data to be shared between platforms to support different platforms. For example, the avatar created in a game can be used on social networking sites. This allows the avatar to be compatible with different platforms and used for a variety of purposes.

[0047] The avatar generation unit can accommodate the characteristics of different cultures and ethnicities and can accommodate global users. The avatar generation unit, for example, analyzes the characteristics of different cultures and ethnicities and builds a system that generates avatars based on that data. For example, it learns the facial features and clothing of each culture and ethnicity. In addition, to accommodate global users, the avatar generation unit analyzes the characteristics of different cultures and ethnicities and develops an algorithm that generates avatar characteristics based on that data. For example, it models facial shapes and skin colors. In addition, to accommodate the characteristics of different cultures and ethnicities, the avatar generation unit integrates voice data and facial features to develop a system that accommodates global users. For example, it generates avatars of different cultures and ethnicities based on voice features. This allows it to accommodate the characteristics of different cultures and ethnicities and accommodate global users.

[0048] The system according to the embodiment is not limited to the above-described example, and various modifications are possible, for example, as follows.

[0049] The image generation system may further include a voice recognition unit. The voice recognition unit converts the user's voice into text and controls the avatar's movements and facial expressions based on the text data. For example, if the user says "smile," the avatar will smile. The voice recognition unit can also change the avatar's pose according to the user's instructions. For example, if the user says "raise your hand," the avatar will raise its hand. The voice recognition unit can also change the avatar's background or scene based on the content of the user's voice. For example, if the user says "I want to go to the beach," the avatar's background will change to a seaside scene. This makes it possible to dynamically change the avatar's movements and scene based on the user's voice instructions.

[0050] The image generation system may further include a gesture recognition unit. The gesture recognition unit can capture the user's hand and body movements with a camera and reflect those movements in the avatar. For example, when the user waves their hand, the avatar waves their hand in the same way. The gesture recognition unit can also change the pose of the avatar based on the user's body movements. For example, when the user jumps, the avatar also jumps. The gesture recognition unit can also analyze the user's facial expressions and reflect those expressions in the avatar. For example, when the user smiles, the avatar also smiles. This makes it possible to change the avatar's movements and expressions in real time based on the user's gestures and expressions.

[0051] The image generation system may further include an environment recognition unit. The environment recognition unit captures the user's surrounding environment using a camera or sensor and can change the avatar's behavior and background based on that information. For example, if the user is outdoors, the avatar's background can be changed to an outdoor scene. The environment recognition unit can also analyze the sounds around the user and change the avatar's behavior in response to those sounds. For example, if the surroundings are quiet, the avatar will behave in a relaxed manner. The environment recognition unit can also change the avatar's behavior and background based on the user's location information. For example, if the user is in a park, the avatar's background can be changed to a park scene. This allows the avatar's behavior and background to be dynamically changed according to the user's surrounding environment.

[0052] The image generation system may further include a biometrics recognition unit. The biometrics recognition unit measures the user's biometric information (e.g., heart rate, skin temperature, sweat rate) using a sensor and can control the avatar's movements and facial expressions based on that information. For example, if the user's heart rate increases, the avatar will show an excited expression. The biometrics recognition unit can also change the avatar's movements based on the user's biometric information. For example, if the user's skin temperature increases, the avatar will act as if it is sweating. The biometrics recognition unit can also change the avatar's background or scene based on the user's biometric information. For example, if the user is relaxing, the avatar's background will be changed to a landscape with a relaxing atmosphere. This makes it possible to dynamically change the avatar's movements and background according to the user's biometric information.

[0053] The image generation system may further include a context recognition unit. The context recognition unit analyzes the content of a user's conversation and behavioral history, and can control the avatar's behavior and facial expression based on that information. For example, the avatar may show an appropriate facial expression based on what the user has said in the past. The context recognition unit may also change the avatar's behavior based on the user's behavioral history. For example, the avatar's background may be changed based on places the user has visited in the past. The context recognition unit may also analyze the content of a user's conversation and change the avatar's behavior and facial expression according to that content. For example, if the user is having an enjoyable conversation, the avatar may smile. This makes it possible to dynamically change the avatar's behavior and facial expression according to the user's conversation content and behavioral history.

[0054] The processing flow of the first embodiment will be briefly explained below.

[0055] Step 1: The voice analysis unit analyzes the voice. For example, the voice analysis unit analyzes the input voice waveform data and extracts features such as pitch, tone, and rhythm. The voice analysis unit can also analyze the emotional state of the voice. Step 2: The feature extraction unit extracts the voice features analyzed by the voice analysis unit. For example, the feature extraction unit extracts elements such as pitch, tone, rhythm, and emotion as numerical data. The feature extraction unit can also model the physical characteristics of the voice source (e.g., throat, mouth, nose) to extract more precise features. Step 3: The mapping unit maps the vocal features extracted by the feature extraction unit to facial regularities. For example, the mapping unit learns which facial features (eye shape, mouth size, etc.) correspond to a specific vocal pitch or tone, and generates corresponding facial features from the vocal features. The mapping unit can also model subtle changes in facial expressions and muscle movements to generate more realistic facial features. Step 4: The illustration generation unit generates anime-style illustrations based on the results of mapping by the mapping unit. For example, the illustration generation unit determines the eye shape, hairstyle, facial expression, etc. based on the voice characteristics, and draws an anime-style character. The illustration generation unit can also generate character movements and poses in real time to create dynamic animations. Step 5: The actor face generation unit generates the actor's face based on the results of mapping by the mapping unit. For example, the actor face generation unit determines the facial contours, facial features, hairstyle, etc. based on the voice characteristics, and draws a realistic actor's face. The actor face generation unit can also reflect the actor's expressions and emotions in real time and generate facial changes according to the emotions. Step 6: The avatar generation unit generates a virtual avatar based on the illustration and face generated by the illustration generation unit and the actor face generation unit. For example, the avatar generation unit utilizes voice characteristics and facial regularity to generate an avatar with a natural appearance while maintaining consistency with the voice. The avatar generation unit can also generate the avatar's movements and gestures in real time to achieve more natural movements.

[0056] (Example 2) The image generation system according to the embodiment of the present invention is a system that generates anime-style illustrations and actor's faces from voices and creates virtual avatars. This allows the image generation system to directly generate anime-style illustrations and actor's faces from voices and use them as virtual avatars.

[0057] An image generation system according to an embodiment includes a voice analysis unit, a feature extraction unit, a mapping unit, an illustration generation unit, an actor face generation unit, and an avatar generation unit. The voice analysis unit analyzes the voice. For example, the voice analysis unit analyzes input voice waveform data and extracts features such as pitch, tone, and rhythm. The voice analysis unit can also analyze the emotional state of the voice. The feature extraction unit extracts features of the voice analyzed by the voice analysis unit. For example, the feature extraction unit extracts elements such as pitch, tone, rhythm, and emotion as numerical data. The feature extraction unit can also model the physical characteristics of the voice source (e.g., throat, mouth, nose) to extract more precise features. The mapping unit maps the voice features extracted by the feature extraction unit to facial regularities. For example, the mapping unit learns facial features (e.g., eye shape, mouth size) that correspond to specific voice pitches and tones, and generates corresponding facial features from the voice features. The mapping unit can also model subtle changes in facial expressions and muscle movements to generate more realistic facial features. The illustration generation unit generates anime-style illustrations based on the results mapped by the mapping unit. For example, the illustration generation unit determines eye shape, hairstyle, facial expression, etc. based on voice characteristics to draw anime-style characters. The illustration generation unit can also generate character movements and poses in real time to create dynamic animations. The actor face generation unit generates an actor's face based on the results mapped by the mapping unit. For example, the actor face generation unit determines facial contours, facial features, hairstyle, etc. based on voice characteristics to draw a realistic actor's face. The actor face generation unit can also reflect the actor's expressions and emotions in real time to generate facial changes according to emotions. The avatar generation unit generates a virtual avatar based on the illustrations and faces generated by the illustration generation unit and the actor face generation unit. For example, the avatar generation unit utilizes voice characteristics and facial regularity to generate an avatar with a natural appearance while maintaining consistency with the voice. The avatar generation unit can also generate avatar movements and gestures in real time, allowing for more natural movements.As a result, the image generation system according to the embodiment can generate anime-style illustrations or actor's faces from voices and create virtual avatars. For example, a user can generate an avatar with the face of an anime character or actor that resembles them simply by inputting their own voice. This will realize new forms of entertainment and communication that utilize XR technology.

[0058] The voice analysis unit can analyze subtle changes in voice and intonation in real time to extract more detailed features. For example, the voice analysis unit develops a highly accurate voice analysis algorithm to analyze subtle changes in voice and intonation in real time. For example, it divides voice waveform data into small segments and analyzes the frequency components and amplitude fluctuations of each segment. The voice analysis unit also builds a system that analyzes voice intonation and rhythm in real time to extract detailed voice features. For example, it analyzes the pitch and tempo of the audio signal to estimate the emotion and intention of the voice. The voice analysis unit also collects voice data using multiple audio sensors to capture subtle changes in voice and analyzes it in real time. For example, it uses a microphone array to measure the direction and distance of the voice and extract detailed features. This allows for real-time analysis of subtle changes in voice and intonation to extract detailed features.

[0059] The voice analysis unit models the physical characteristics of the voice source, allowing for more precise extraction of voice features. For example, the voice analysis unit models the physical characteristics of the throat, mouth, and nose, which are the voice source, and develops a system that precisely extracts voice features. For example, it simulates the vibration of the vocal cords and the resonance characteristics of the oral cavity. In addition, to analyze the physical characteristics of the voice source, the voice analysis unit reproduces the voice production process using acoustic simulation technology. For example, it models the movement of the vocal cords and the changes in the shape of the oral cavity. In addition, the voice analysis unit develops an algorithm that analyzes voice features in detail based on the physical characteristics of the voice source. For example, it analyzes the vibration pattern of the vocal cords and the resonance frequency of the oral cavity to extract voice features. This allows for modeling the physical characteristics of the voice source and for precise extraction of voice features.

[0060] The voice analysis unit can use the emotion estimation function to analyze the emotional state of the voice and extract features based on that emotion. The voice analysis unit, for example, uses the emotion estimation function to analyze the emotional state of the voice in real time and build a system that extracts features based on that emotion. For example, it analyzes changes in voice tone and rhythm and calculates an emotion score. In addition, to analyze the emotional state of the voice, the voice analysis unit extracts features (e.g., pitch, intensity, speed) of the audio signal and applies an emotion estimation algorithm. For example, it classifies emotions such as joy and sadness. In addition, the voice analysis unit uses the emotion estimation function to develop a system that extracts features based on the emotional state of the voice. For example, it analyzes voice features in detail based on the voice emotion score and extracts features according to the emotion. This makes it possible to analyze the emotional state of the voice and extract features based on that emotion.

[0061] The voice analysis unit can accommodate different languages ​​and dialects, enabling global user support. For example, the voice analysis unit develops a multilingual voice analysis algorithm to accommodate different languages ​​and dialects. For example, it collects voice data for each language and dialect and trains features. In addition, the voice analysis unit analyzes voice data from different languages ​​and dialects to build a system that extracts common features, enabling global user support. For example, it analyzes differences in voice rhythm and intonation. In addition, in order to accommodate different languages ​​and dialects, the voice analysis unit converts voice data into text using voice recognition technology and extracts features based on the text data. For example, it analyzes the content and context of the voice. This allows the system to accommodate different languages ​​and dialects and global users.

[0062] The voice analysis unit can also be applied to music and singing voices and used to generate musical avatars. For example, the voice analysis unit develops an algorithm specialized for analyzing music and singing voices and uses it to generate musical avatars. For example, it analyzes the pitch and rhythm of singing voices and generates the movements of a musical avatar. The voice analysis unit also analyzes the characteristics of music and singing voices and builds a system that generates musical avatars based on those characteristics. For example, it analyzes the emotions and expressions of singing voices and generates the facial expressions and movements of an avatar. The voice analysis unit also optimizes the musical avatar generation process based on the analysis results of music and singing voices. For example, it analyzes the characteristics of singing voices in detail and generates the movements and facial expressions of an avatar in real time. This allows it to be applied to music and singing voices and used to generate musical avatars.

[0063] The voice analysis unit can analyze the emotion of the user when inputting voice in real time and extract features according to the emotion. The voice analysis unit, for example, builds a system that analyzes the emotion of the user when inputting voice in real time. For example, it analyzes the feature amount of the voice signal in real time and calculates an emotion score. The voice analysis unit also develops an algorithm that analyzes the emotional state of the user's voice in real time and extracts features according to the emotion. For example, it analyzes changes in the tone and rhythm of the voice and extracts features based on the emotion. The voice analysis unit also develops a system that analyzes the emotion of the user when inputting voice in real time and extracts features based on the results. For example, it analyzes the voice features in detail based on the emotion score and extracts features according to the emotion. This makes it possible to analyze the emotion of the user when inputting voice in real time and extract features according to the emotion.

[0064] The mapping unit can model subtle changes in facial expression or muscle movements to generate more realistic facial features. For example, the mapping unit develops a highly accurate facial recognition algorithm to model subtle changes in facial expression and muscle movements. For example, it simulates facial muscle movements to generate realistic facial expressions. The mapping unit also analyzes facial expression changes and muscle movements in detail and builds a system that generates facial features based on that data. For example, it models facial muscle movements and skin changes. The mapping unit also analyzes facial movements in real time using multiple cameras to capture subtle changes in facial expression and generates facial features based on that data. For example, it reproduces facial muscle movements in a 3D model. This makes it possible to model subtle changes in facial expression and muscle movements to generate realistic facial features.

[0065] The mapping unit can develop an algorithm that generates a facial expression according to the emotional state of the voice. The mapping unit, for example, develops an algorithm that generates a facial expression according to the emotional state of the voice. For example, it analyzes changes in the tone and rhythm of the voice to generate an expression according to the emotion. The mapping unit also analyzes the emotional state of the voice and builds a system that generates a facial expression based on the results. For example, it generates expressions such as joy and sadness based on the emotional score of the voice. The mapping unit also develops an algorithm that generates a facial expression based on the emotional state of the voice and builds a system that changes the expression in real time. For example, it dynamically generates facial expressions according to emotional changes in the voice. This makes it possible to develop an algorithm that generates a facial expression according to the emotional state of the voice.

[0066] The mapping unit uses the emotion estimation function to generate facial features based on the emotional state of the voice and can reflect facial changes corresponding to the emotion in real time. The mapping unit, for example, uses the emotion estimation function to build a system that generates facial features based on the emotional state of the voice. For example, facial expressions and features are generated in real time based on the emotional score of the voice. The mapping unit also analyzes the emotional state of the voice in real time and develops an algorithm that generates facial features based on the results. For example, facial expressions are dynamically generated in response to changes in the emotional state of the voice. The mapping unit also uses the emotion estimation function to build a system that generates facial features based on the emotional state of the voice and reflects facial changes in real time. For example, facial expressions are dynamically changed based on the emotional score of the voice. This makes it possible to use the emotion estimation function to generate facial features based on the emotional state of the voice and reflect facial changes corresponding to the emotion in real time.

[0067] The mapping unit can also be applied to animals and fantasy characters to generate a variety of avatars. For example, the mapping unit trains a dataset of specific animals or characters to apply the mapping between voice features and facial regularity to animals and fantasy characters. For example, the mapping unit analyzes the facial features of animals and fantasy characters' designs. The mapping unit also analyzes the facial features of animals and fantasy characters and builds a system that generates a variety of avatars based on that data. For example, the mapping unit models the facial expressions of animals and character features. The mapping unit also applies the mapping between voice features and facial regularity to animals and fantasy characters to develop a system that generates avatars in real time. For example, the mapping unit generates the faces of animals and characters based on voice features. This allows the mapping to be applied to animals and fantasy characters to generate a variety of avatars.

[0068] The mapping unit can accommodate facial features of different cultures and ethnicities and support global users. For example, the mapping unit analyzes facial features of different cultures and ethnicities and builds a system that maps voice features and facial regularities based on the data. For example, the mapping unit learns the facial features of each culture and ethnicity. In addition, to accommodate global users, the mapping unit analyzes facial features of different cultures and ethnicities and develops an algorithm that generates facial features based on the data. For example, it models face shape and skin color. In addition, to accommodate facial features of different cultures and ethnicities, the mapping unit integrates voice data and facial features and develops a system that supports global users. For example, it generates faces for different cultures and ethnicities based on voice features. This allows the system to accommodate facial features of different cultures and ethnicities and support global users.

[0069] The mapping unit can analyze the emotion of the user when inputting voice in real time and generate facial features corresponding to the emotion. For example, the mapping unit builds a system that analyzes the emotion of the user when inputting voice in real time and generates facial features corresponding to the emotion. For example, a facial expression is generated based on the emotion score of the voice. The mapping unit also analyzes the emotional state of the voice in real time and develops an algorithm that generates facial features based on the results. For example, a facial expression is dynamically generated according to emotional changes in the voice. The mapping unit also analyzes the emotion of the user when inputting voice in real time and develops a system that generates facial features based on the data. For example, a facial expression is analyzed in detail based on the emotion score and facial features corresponding to the emotion are generated. This makes it possible to analyze the emotion of the user when inputting voice in real time and generate facial features corresponding to the emotion.

[0070] The illustration generation unit can generate character movements and poses in real time to create dynamic animations. For example, the illustration generation unit develops a motion analysis algorithm to generate character movements and poses in real time. For example, it reproduces character movements based on motion capture data. The illustration generation unit also builds a system to generate character poses in real time and create dynamic animations. For example, it dynamically changes character poses in response to user input. The illustration generation unit also uses a machine learning algorithm to generate character movements and poses in real time and create animations. For example, it learns from past animation data and generates movements in real time. This allows character movements and poses to be generated in real time and dynamic animations to be created.

[0071] The illustration generation unit allows customization of the character's clothing and accessories, and can generate illustrations according to the user's preferences. The illustration generation unit, for example, develops a user interface to enable customization of the character's clothing and accessories. For example, it provides a function that allows selection of clothing and accessories by drag and drop. The illustration generation unit also builds a system that generates the character's clothing and accessories according to the user's preferences. For example, it dynamically changes the character's appearance based on the user's selection. The illustration generation unit also develops a system that allows customization of the character's clothing and accessories, and allows the user to generate illustrations according to their preferences. For example, it provides a function that allows free change of colors and designs. This allows customization of the character's clothing and accessories, and can generate illustrations according to the user's preferences.

[0072] The illustration generation unit uses the emotion estimation function to generate a character's facial expression and pose based on the emotional state of the voice, thereby creating an illustration that corresponds to the emotion. The illustration generation unit, for example, uses the emotion estimation function to build a system that generates a character's facial expression and pose based on the emotional state of the voice. For example, the character's facial expression is dynamically changed based on the emotional score of the voice. The illustration generation unit also analyzes the emotional state of the voice in real time and develops an algorithm that generates a character's facial expression and pose based on the results. For example, the character's movements are dynamically generated according to changes in the emotional state of the voice. The illustration generation unit also uses the emotion estimation function to develop a system that generates a character's facial expression and pose based on the emotional state of the voice, thereby creating an illustration that corresponds to the emotion. For example, the character's facial expression is analyzed in detail based on the emotional score, and an illustration that corresponds to the emotion is generated. As a result, the emotion estimation function can be used to generate a character's facial expression and pose based on the emotional state of the voice, thereby creating an illustration that corresponds to the emotion.

[0073] The illustration generation unit can generate a variety of illustrations to accommodate different anime styles. For example, the illustration generation unit trains realistic and deformed datasets to accommodate different anime styles. For example, the unit analyzes the characteristics of each style and reflects them in the illustration generation algorithm. The illustration generation unit also develops an interface that allows users to select a style to accommodate a variety of anime styles. For example, the unit selects a realistic or deformed style and generates an illustration. The illustration generation unit also develops a style conversion algorithm to accommodate different anime styles and generates an illustration according to the user's selection. For example, the unit converts a realistic illustration into a deformed illustration. This allows the unit to generate a variety of illustrations to accommodate different anime styles.

[0074] The illustration generation unit can also be applied to manga and comic characters to generate manga-style illustrations. For example, the illustration generation unit trains a manga-style dataset to apply to manga and comic characters. For example, it analyzes the characteristic line and shadow expressions of manga and reflects this in the illustration generation algorithm. In addition, the illustration generation unit develops an interface that allows a user to select a manga style to generate manga-style illustrations. For example, it selects a manga-style style and generates an illustration. In addition, the illustration generation unit develops a style conversion algorithm to apply to manga and comic characters and generates manga-style illustrations according to the user's selection. For example, it converts an anime-style illustration into a manga style. This allows it to be applied to manga and comic characters to generate manga-style illustrations.

[0075] The illustration generation unit can analyze the emotion a user feels when inputting their voice in real time and generate an illustration corresponding to that emotion. The illustration generation unit, for example, builds a system that analyzes the emotion a user feels when inputting their voice in real time and generates an illustration corresponding to that emotion. For example, it generates a character's facial expression based on the emotion score of the voice. The illustration generation unit also develops an algorithm that analyzes the emotional state of the voice in real time and generates an illustration based on the results. For example, it dynamically generates a character's facial expression and pose according to changes in the emotion of the voice. The illustration generation unit also develops a system that analyzes the emotion a user feels when inputting their voice in real time and generates an illustration based on that data. For example, it analyzes the character's facial expression in detail based on the emotion score and generates an illustration corresponding to the emotion. This makes it possible to analyze the emotion a user feels when inputting their voice in real time and generate an illustration corresponding to the emotion.

[0076] The actor face generation unit generates facial features according to the actor's age and gender, allowing for the creation of a more realistic face. For example, the actor face generation unit learns data sets for each age and gender in order to generate facial features according to the actor's age and gender. For example, it analyzes facial changes due to age and gender and reflects this in the face generation algorithm. The actor face generation unit also analyzes facial features according to the actor's age and gender in detail, and builds a system that generates a realistic face based on that data. For example, it models facial wrinkles due to age and facial contours due to gender. The actor face generation unit also learns facial features using a machine learning algorithm in order to generate facial features according to the actor's age and gender. For example, it analyzes facial features for each age and gender in detail to generate a realistic face. This allows for the generation of facial features according to the actor's age and gender, allowing for the creation of a realistic face.

[0077] The actor face generation unit can reflect the actor's facial expressions and emotions in real time and generate facial changes corresponding to the emotions. The actor face generation unit, for example, develops a facial expression recognition algorithm to reflect the actor's facial expressions and emotions in real time. For example, it analyzes the actor's facial movements in real time and generates facial expressions corresponding to the emotions. The actor face generation unit also builds a system that analyzes the actor's emotional state in real time and generates facial changes based on the results. For example, it dynamically changes facial expressions based on emotion scores. The actor face generation unit also uses a machine learning algorithm to reflect the actor's facial expressions and emotions in real time and generate facial changes corresponding to the emotions. For example, it learns past facial expression data and generates facial expressions in real time. This makes it possible to reflect the actor's facial expressions and emotions in real time and generate facial changes corresponding to the emotions.

[0078] The actor face generation unit uses the emotion estimation function to generate an actor's facial expression based on the emotional state of the voice, and can reflect facial changes corresponding to the emotion in real time. The actor face generation unit, for example, uses the emotion estimation function to build a system that generates an actor's facial expression based on the emotional state of the voice. For example, the actor's facial expression is generated in real time based on the emotional score of the voice. The actor face generation unit also analyzes the emotional state of the voice in real time and develops an algorithm that generates an actor's facial expression based on the results. For example, the actor's facial expression is dynamically generated in response to emotional changes in the voice. The actor face generation unit also uses the emotion estimation function to build a system that generates an actor's facial expression based on the emotional state of the voice and reflects facial changes in real time. For example, the actor's facial expression is dynamically changed based on the emotional score of the voice. This makes it possible to use the emotion estimation function to generate an actor's facial expression based on the emotional state of the voice, and reflect facial changes corresponding to the emotion in real time.

[0079] The actor face generation unit can generate facial features according to different movie genres. For example, to support different movie genres, the actor face generation unit learns datasets for each genre. For example, the facial features of actors in action movies and comedy movies are analyzed and reflected in the face generation algorithm. The actor face generation unit also develops an interface that allows a user to select a genre in order to generate facial features according to the movie genre. For example, the genre of action movies or comedy movies is selected and a face is generated. The actor face generation unit also develops a genre conversion algorithm to support different movie genres and generates facial features according to the user's selection. For example, the face of an action movie actor is converted to look like a comedy movie. This allows facial features to be generated according to different movie genres.

[0080] The actor face generation unit can be applied to historical figures and fictional characters to generate a variety of faces. For example, the actor face generation unit trains a specific dataset to be applied to historical figures and fictional characters. For example, portraits of historical figures and designs of fictional characters are analyzed and reflected in the face generation algorithm. The actor face generation unit also analyzes the facial features of historical figures and fictional characters and builds a system that generates a variety of faces based on that data. For example, the facial features of historical figures and designs of fictional characters are modeled. The actor face generation unit also develops a system that can be applied to historical figures and fictional characters to generate faces in real time. For example, the face of a historical figure or fictional character is generated based on voice characteristics. This allows the system to be applied to historical figures and fictional characters to generate a variety of faces.

[0081] The actor face generation unit can analyze the emotion a user feels when inputting their voice in real time and generate an actor's face according to that emotion. The actor face generation unit, for example, builds a system that analyzes the emotion a user feels when inputting their voice in real time and generates an actor's face according to that emotion. For example, it generates an actor's facial expression based on the emotion score of the voice. The actor face generation unit also develops an algorithm that analyzes the emotional state of the voice in real time and generates an actor's face based on the results. For example, it dynamically generates an actor's facial expression and facial features according to emotional changes in the voice. The actor face generation unit also develops a system that analyzes the emotion a user feels when inputting their voice in real time and generates an actor's face based on that data. For example, it analyzes the actor's facial expression in detail based on the emotion score and generates a face according to the emotion. This makes it possible to analyze the emotion a user feels when inputting their voice in real time and generate an actor's face according to the emotion.

[0082] The avatar generation unit generates avatar movements and gestures in real time, enabling more natural movements. The avatar generation unit, for example, develops a motion analysis algorithm to generate avatar movements and gestures in real time. For example, the avatar generation unit reproduces avatar movements based on motion capture data. The avatar generation unit also builds a system that generates avatar movements in real time and enables natural movements. For example, the avatar generation unit dynamically changes avatar movements in response to user input. The avatar generation unit also uses a machine learning algorithm to generate avatar movements and gestures in real time and enable natural movements. For example, the avatar generation unit learns past movement data and generates movements in real time. This allows avatar movements and gestures to be generated in real time and enable natural movements.

[0083] The avatar generation unit allows the avatar's clothing and accessories to be customized, and can generate an avatar according to the user's preferences. The avatar generation unit, for example, develops a user interface to enable the avatar's clothing and accessories to be customized. For example, it provides a function that allows the user to select clothing and accessories by drag and drop. The avatar generation unit also builds a system that generates the avatar's clothing and accessories according to the user's preferences. For example, it dynamically changes the avatar's appearance based on the user's selection. The avatar generation unit also develops a system that allows the avatar's clothing and accessories to be customized, and allows the user to generate an avatar according to their preferences. For example, it provides a function that allows the user to freely change colors and designs. This allows the avatar's clothing and accessories to be customized, and an avatar can be generated according to the user's preferences.

[0084] The avatar generation unit uses the emotion estimation function to generate avatar facial expressions and movements based on the emotional state of the voice, thereby creating an avatar that corresponds to the emotion. The avatar generation unit, for example, uses the emotion estimation function to build a system that generates avatar facial expressions and movements based on the emotional state of the voice. For example, the avatar generation unit generates avatar facial expressions in real time based on the emotional score of the voice. The avatar generation unit also analyzes the emotional state of the voice in real time and develops an algorithm that generates avatar facial expressions and movements based on the results. For example, the avatar movement is dynamically generated in response to changes in the emotional state of the voice. The avatar generation unit also uses the emotion estimation function to develop a system that generates avatar facial expressions and movements based on the emotional state of the voice, thereby creating an avatar that corresponds to the emotion. For example, the avatar facial expressions are analyzed in detail based on the emotion score, and an avatar that corresponds to the emotion is generated. This makes it possible to use the emotion estimation function to generate avatar facial expressions and movements based on the emotional state of the voice, thereby creating an avatar that corresponds to the emotion.

[0085] The avatar generation unit can support different platforms and make the avatar usable for a variety of purposes. For example, to support different platforms, the avatar generation unit develops avatar generation algorithms tailored to the specifications of each platform. For example, the avatar data format is converted according to the specifications of games and social networking sites. The avatar generation unit also develops an interface that allows users to select a platform to generate avatars that can be used for a variety of purposes. For example, the avatar generation unit selects and generates avatars for games and social networking sites. The avatar generation unit also builds a system that allows avatar data to be shared between platforms to support different platforms. For example, the avatar created in a game can be used on social networking sites. This allows the avatar to be compatible with different platforms and used for a variety of purposes.

[0086] The avatar generation unit can accommodate the characteristics of different cultures and ethnicities and can accommodate global users. The avatar generation unit, for example, analyzes the characteristics of different cultures and ethnicities and builds a system that generates avatars based on that data. For example, it learns the facial features and clothing of each culture and ethnicity. In addition, to accommodate global users, the avatar generation unit analyzes the characteristics of different cultures and ethnicities and develops an algorithm that generates avatar characteristics based on that data. For example, it models facial shapes and skin colors. In addition, to accommodate the characteristics of different cultures and ethnicities, the avatar generation unit integrates voice data and facial features to develop a system that accommodates global users. For example, it generates avatars of different cultures and ethnicities based on voice features. This allows it to accommodate the characteristics of different cultures and ethnicities and accommodate global users.

[0087] The avatar generation unit can analyze the emotion a user feels when inputting their voice in real time, and generate an avatar according to that emotion. For example, the avatar generation unit builds a system that analyzes the emotion a user feels when inputting their voice in real time, and generates an avatar according to that emotion. For example, the avatar generation unit generates an avatar's facial expression based on the emotion score of the voice. The avatar generation unit also develops an algorithm that analyzes the emotional state of the voice in real time, and generates an avatar based on the results. For example, the avatar generation unit dynamically generates the avatar's facial expression and movement according to changes in the emotion of the voice. The avatar generation unit also develops a system that analyzes the emotion a user feels when inputting their voice in real time, and generates an avatar based on that data. For example, the avatar's facial expression is analyzed in detail based on the emotion score, and an avatar according to the emotion is generated. This makes it possible to analyze the emotion a user feels when inputting their voice in real time, and generate an avatar according to the emotion.

[0088] The system according to the embodiment is not limited to the above-described example, and various modifications are possible, for example, as follows.

[0089] The image generation system may further include a voice recognition unit. The voice recognition unit converts the user's voice into text and controls the avatar's movements and facial expressions based on the text data. For example, if the user says "smile," the avatar will smile. The voice recognition unit can also change the avatar's pose according to the user's instructions. For example, if the user says "raise your hand," the avatar will raise its hand. The voice recognition unit can also change the avatar's background or scene based on the content of the user's voice. For example, if the user says "I want to go to the beach," the avatar's background will change to a seaside scene. This makes it possible to dynamically change the avatar's movements and scene based on the user's voice instructions.

[0090] The image generation system may further include a gesture recognition unit. The gesture recognition unit can capture the user's hand and body movements with a camera and reflect those movements in the avatar. For example, when the user waves their hand, the avatar waves their hand in the same way. The gesture recognition unit can also change the pose of the avatar based on the user's body movements. For example, when the user jumps, the avatar also jumps. The gesture recognition unit can also analyze the user's facial expressions and reflect those expressions in the avatar. For example, when the user smiles, the avatar also smiles. This makes it possible to change the avatar's movements and expressions in real time based on the user's gestures and expressions.

[0091] The image generation system may further include an environment recognition unit. The environment recognition unit captures the user's surrounding environment using a camera or sensor and can change the avatar's behavior and background based on that information. For example, if the user is outdoors, the avatar's background can be changed to an outdoor scene. The environment recognition unit can also analyze the sounds around the user and change the avatar's behavior in response to those sounds. For example, if the surroundings are quiet, the avatar will behave in a relaxed manner. The environment recognition unit can also change the avatar's behavior and background based on the user's location information. For example, if the user is in a park, the avatar's background can be changed to a park scene. This allows the avatar's behavior and background to be dynamically changed according to the user's surrounding environment.

[0092] The image generation system may further include a biometrics recognition unit. The biometrics recognition unit measures the user's biometric information (e.g., heart rate, skin temperature, sweat rate) using a sensor and can control the avatar's movements and facial expressions based on that information. For example, if the user's heart rate increases, the avatar will show an excited expression. The biometrics recognition unit can also change the avatar's movements based on the user's biometric information. For example, if the user's skin temperature increases, the avatar will act as if it is sweating. The biometrics recognition unit can also change the avatar's background or scene based on the user's biometric information. For example, if the user is relaxing, the avatar's background will be changed to a landscape with a relaxing atmosphere. This makes it possible to dynamically change the avatar's movements and background according to the user's biometric information.

[0093] The image generation system may further include a context recognition unit. The context recognition unit analyzes the content of a user's conversation and behavioral history, and can control the avatar's behavior and facial expression based on that information. For example, the avatar may show an appropriate facial expression based on what the user has said in the past. The context recognition unit may also change the avatar's behavior based on the user's behavioral history. For example, the avatar's background may be changed based on places the user has visited in the past. The context recognition unit may also analyze the content of a user's conversation and change the avatar's behavior and facial expression according to that content. For example, if the user is having an enjoyable conversation, the avatar may smile. This makes it possible to dynamically change the avatar's behavior and facial expression according to the user's conversation content and behavioral history.

[0094] The image generation system can further use an emotion estimation function to provide audio feedback based on the user's emotions. For example, if the user makes a sad voice, the system will respond with comforting words. If the user makes an excited voice, the system will respond with sympathetic words. Furthermore, the emotion estimation function can be used to play music according to the user's emotions. For example, if the user makes a relaxed voice, the system will play relaxing music. The emotion estimation function can also be used to control the behavior of an avatar based on the user's emotions. For example, if the user makes an angry voice, the avatar will show an angry expression. This makes it possible to provide audio feedback, play music, and change the behavior of the avatar based on the user's emotions.

[0095] The image generation system can further use an emotion estimation function to change the avatar's clothing and accessories based on the user's emotions. For example, if the user uses a happy voice, the avatar will wear brightly colored clothing. If the user uses a sad voice, the avatar will wear subdued clothing. The emotion estimation function can also be used to change the avatar's accessories according to the user's emotions. For example, if the user uses an excited voice, the avatar will wear flashy accessories. The emotion estimation function can also be used to change the avatar's background based on the user's emotions. For example, if the user uses a relaxed voice, the avatar's background will be changed to a natural landscape. This makes it possible to dynamically change the avatar's clothing, accessories, and background based on the user's emotions.

[0096] The image generation system can further use an emotion estimation function to generate avatar movements and gestures based on the user's emotions. For example, if the user makes a voice of joy, the avatar will dance in joy. If the user makes a voice of sadness, the avatar will make a gesture of comfort. Furthermore, the emotion estimation function can be used to change the avatar's facial expression according to the user's emotions. For example, if the user makes a voice of anger, the avatar will show an angry expression. The emotion estimation function can also be used to change the avatar's pose based on the user's emotions. For example, if the user makes a relaxed voice, the avatar will take a relaxed pose. This makes it possible to dynamically generate avatar movements, gestures, facial expressions, and poses based on the user's emotions.

[0097] The image generation system can further use an emotion estimation function to generate an avatar story based on the user's emotions. For example, if the user uses a happy voice, the avatar will tell a fun adventure story. If the user uses a sad voice, the avatar will tell a touching story. Furthermore, the emotion estimation function can be used to generate avatar dialogue based on the user's emotions. For example, if the user uses an excited voice, the avatar will have an excited dialogue. The emotion estimation function can also be used to control the avatar's behavior based on the user's emotions. For example, if the user uses a relaxed voice, the avatar will behave in a relaxed manner. This makes it possible to dynamically generate avatar stories, dialogues, and actions based on the user's emotions.

[0098] The image generation system can further use an emotion estimation function to generate the voice of the avatar based on the user's emotion. For example, if the user makes a voice of joy, the avatar will respond in a voice of joy. Also, if the user makes a voice of sadness, the avatar will respond in a voice of comfort. Furthermore, the emotion estimation function can be used to change the tone and rhythm of the avatar's voice according to the user's emotion. For example, if the user makes a voice of excitement, the avatar will speak in an excited tone. The emotion estimation function can also be used to change the content of the avatar's voice based on the user's emotion. For example, if the user makes a voice of relaxation, the avatar will speak about relaxed content. In this way, the voice, tone, rhythm, and content of the avatar can be dynamically generated based on the user's emotion.

[0099] The processing flow of the second embodiment will be briefly explained below.

[0100] Step 1: The voice analysis unit analyzes the voice. For example, the voice analysis unit analyzes the input voice waveform data and extracts features such as pitch, tone, and rhythm. The voice analysis unit can also analyze the emotional state of the voice. Step 2: The feature extraction unit extracts the voice features analyzed by the voice analysis unit. For example, the feature extraction unit extracts elements such as pitch, tone, rhythm, and emotion as numerical data. The feature extraction unit can also model the physical characteristics of the voice source (e.g., throat, mouth, nose) to extract more precise features. Step 3: The mapping unit maps the vocal features extracted by the feature extraction unit to facial regularities. For example, the mapping unit learns which facial features (eye shape, mouth size, etc.) correspond to a specific vocal pitch or tone, and generates corresponding facial features from the vocal features. The mapping unit can also model subtle changes in facial expressions and muscle movements to generate more realistic facial features. Step 4: The illustration generation unit generates anime-style illustrations based on the results of mapping by the mapping unit. For example, the illustration generation unit determines the eye shape, hairstyle, facial expression, etc. based on the voice characteristics, and draws an anime-style character. The illustration generation unit can also generate character movements and poses in real time to create dynamic animations. Step 5: The actor face generation unit generates the actor's face based on the results of mapping by the mapping unit. For example, the actor face generation unit determines the facial contours, facial features, hairstyle, etc. based on the voice characteristics, and draws a realistic actor's face. The actor face generation unit can also reflect the actor's expressions and emotions in real time and generate facial changes according to the emotions. Step 6: The avatar generation unit generates a virtual avatar based on the illustration and face generated by the illustration generation unit and the actor face generation unit. For example, the avatar generation unit utilizes voice characteristics and facial regularity to generate an avatar with a natural appearance while maintaining consistency with the voice. The avatar generation unit can also generate the avatar's movements and gestures in real time to achieve more natural movements.

[0101] The specific processing unit 290 transmits the result of the specific processing to the smart device 14. In the smart device 14, the control unit 46A causes the output device 40 to output the result of the specific processing. The microphone 38B acquires audio indicating a user input regarding the result of the specific processing. The control unit 46A transmits audio data indicating the user input acquired by the microphone 38B to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the audio data.

[0102] The data generation model 58 is a so-called generative AI (Artificial Intelligence). An example of the data generation model 58 is ChatGPT (Internet Search<URL: https: / / openai.com / blog / chatgpt> Examples of generative AIs include the data generation model 58, such as a neural network model (e.g., a neural network model), and a neural network model (e.g., a neural network model). The data generation model 58 is obtained by performing deep learning on a neural network. A prompt including an instruction is input to the data generation model 58, and inference data such as voice data indicating speech, text data indicating text, and image data indicating an image is also input to the data generation model 58. The data generation model 58 performs inference on the input inference data in accordance with the instruction indicated by the prompt and outputs the inference result in a data format such as voice data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization. The specification processing unit 290 performs the above-mentioned specification processing using the data generation model 58. The data generation model 58 may be a fine-tuned model so as to output an inference result from a prompt that does not include an instruction. In this case, the data generation model 58 can output an inference result from a prompt that does not include an instruction. The data processing device 12 and the like include multiple types of data generation models 58, and the data generation model 58 includes AIs other than the generative AI. The AI ​​other than the generative AI may be, for example, linear regression, logistic regression, decision tree, random forest, support vector machine (SVM), k-means clustering, convolutional neural network (CNN), recurrent neural network (RNN), generative adversarial network (GAN), or naive Bayes, and can perform various processes, but is not limited to these examples. The AI ​​may also be an AI agent. When the processes of each of the above-mentioned parts are performed by AI, the processes may be performed in part or entirely by AI, but are not limited to these examples. The processes performed by AI, including the generative AI, may be replaced with rule-based processes.

[0103] Furthermore, the processing by the data processing system 10 described above is executed by the specific processing unit 290 of the data processing device 12 or the control unit 46A of the smart device 14, but may also be executed by the specific processing unit 290 of the data processing device 12 and the control unit 46A of the smart device 14. Furthermore, the specific processing unit 290 of the data processing device 12 acquires or collects information necessary for processing from the smart device 14 or an external device, and the smart device 14 acquires or collects information necessary for processing from the data processing device 12 or an external device.

[0104] [Second embodiment] FIG. 3 shows an example of the configuration of a data processing system 210 according to the second embodiment.

[0105] 3, the data processing system 210 includes the data processing device 12 and smart glasses 214. An example of the data processing device 12 is a server.

[0106] The data processing device 12 includes a computer 22, a database 24, and a communication I / F 26. The computer 22 includes a processor 28, a RAM 30, and a storage 32. The processor 28, RAM 30, and storage 32 are connected to a bus 34. The database 24 and the communication I / F 26 are also connected to the bus 34. The communication I / F 26 is connected to a network 54. Examples of the network 54 include a WAN and / or a LAN.

[0107] The smart glasses 214 include a computer 36, a microphone 238, a speaker 240, a camera 42, and a communication I / F 44. The computer 36 includes a processor 46, a RAM 48, and a storage 50. The processor 46, the RAM 48, and the storage 50 are connected to a bus 52. The microphone 238, the speaker 240, and the camera 42 are also connected to the bus 52.

[0108] The microphone 238 receives instructions and the like from the user by receiving voice uttered by the user. The microphone 238 captures the voice uttered by the user, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio according to instructions from the processor 46.

[0109] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an imaging element such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, and captures images of the user's surroundings (for example, an imaging range defined by an angle of view equivalent to the field of vision of a typical healthy person).

[0110] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 are responsible for the exchange of various information between the processor 46 and the processor 28 via the network 54. The exchange of various information between the processor 46 and the processor 28 using the communication I / Fs 44 and 26 is carried out in a secure state.

[0111] Fig. 4 shows an example of the main functions of the data processing device 12 and the smart glasses 214. As shown in Fig. 4, in the data processing device 12, a specific process is performed by the processor 28. A specific process program 56 is stored in the storage 32.

[0112] The processor 28 reads the specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific processing is realized by the processor 28 operating as a specific processing unit 290 in accordance with the specific processing program 56 executed on the RAM 30.

[0113] The storage 32 stores a data generation model 58 and an emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290. The identification processing unit 290 can estimate the user's emotion using the emotion identification model 59 and perform identification processing using the user's emotion.

[0114] In the smart glasses 214, the specific processing is performed by the processor 46. A specific processing program 60 is stored in the storage 50. The processor 46 reads the specific processing program 60 from the storage 50 and executes the read specific processing program 60 on the RAM 48. The specific processing is realized by the processor 46 operating as the control unit 46A in accordance with the specific processing program 60 executed on the RAM 48. Note that the smart glasses 214 may have a data generation model and an emotion identification model similar to the data generation model 58 and the emotion identification model 59.

[0115] Note that a device other than the data processing device 12 may have the data generation model 58. For example, a server device may have the data generation model 58. In this case, the data processing device 12 communicates with the server device having the data generation model 58 to obtain a processing result (such as a prediction result) using the data generation model 58. Furthermore, the data processing device 12 may be a server device, or may be a terminal device (for example, a mobile phone, a robot, a home appliance, etc.) owned by a user.

[0116] The specific processing unit 290 transmits the result of the specific processing to the smart glasses 214. In the smart glasses 214, the control unit 46A causes the speaker 240 to output the result of the specific processing. The microphone 238 acquires audio indicating a user input regarding the result of the specific processing. The control unit 46A transmits audio data indicating the user input acquired by the microphone 238 to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the audio data.

[0117] The data generation model 58 is a so-called generative AI. An example of the data generation model 58 is a generative AI such as ChatGPT. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 receives a prompt containing an instruction, as well as inference data such as voice data representing speech, text data representing text, and image data representing an image. The data generation model 58 performs inference on the input inference data in accordance with the instruction indicated by the prompt and outputs the inference result in a data format such as voice data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization. The identification processing unit 290 performs the above-mentioned identification processing using the data generation model 58. The data generation model 58 may be a fine-tuned model so as to output an inference result from a prompt that does not include an instruction. In this case, the data generation model 58 can output an inference result from a prompt that does not include an instruction. The data processing device 12 and the like include multiple types of data generation models 58, and the data generation model 58 includes AIs other than the generative AI. The AI ​​other than the generative AI may be, for example, linear regression, logistic regression, decision tree, random forest, support vector machine (SVM), k-means clustering, convolutional neural network (CNN), recurrent neural network (RNN), generative adversarial network (GAN), or naive Bayes, and can perform various processes, but is not limited to these examples. The AI ​​may also be an AI agent. When the processes of each of the above-mentioned parts are performed by AI, the processes may be performed in part or entirely by AI, but are not limited to these examples. The processes performed by AI, including the generative AI, may be replaced with rule-based processes.

[0118] The data processing system 210 according to the second embodiment performs the same processing as the data processing system 10 according to the first embodiment. The processing by the data processing system 210 is executed by the specific processing unit 290 of the data processing device 12 or the control unit 46A of the smart glasses 214, but may also be executed by the specific processing unit 290 of the data processing device 12 and the control unit 46A of the smart glasses 214. Furthermore, the specific processing unit 290 of the data processing device 12 acquires or collects information required for processing from the smart glasses 214 or an external device, etc., and the smart glasses 214 acquires or collects information required for processing from the data processing device 12 or an external device, etc.

[0119] [Third embodiment] FIG. 5 shows an example of the configuration of a data processing system 310 according to the third embodiment.

[0120] 5, the data processing system 310 includes the data processing device 12 and a headset type terminal 314. An example of the data processing device 12 is a server.

[0121] The data processing device 12 includes a computer 22, a database 24, and a communication I / F 26. The computer 22 includes a processor 28, a RAM 30, and a storage 32. The processor 28, RAM 30, and storage 32 are connected to a bus 34. The database 24 and the communication I / F 26 are also connected to the bus 34. The communication I / F 26 is connected to a network 54. Examples of the network 54 include a WAN and / or a LAN.

[0122] The headset type terminal 314 includes a computer 36, a microphone 238, a speaker 240, a camera 42, a communication I / F 44, and a display 343. The computer 36 includes a processor 46, a RAM 48, and a storage 50. The processor 46, the RAM 48, and the storage 50 are connected to a bus 52. The microphone 238, the speaker 240, the camera 42, and the display 343 are also connected to the bus 52.

[0123] The microphone 238 receives instructions and the like from the user by receiving voice uttered by the user. The microphone 238 captures the voice uttered by the user, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio according to instructions from the processor 46.

[0124] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an imaging element such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, and captures images of the user's surroundings (for example, an imaging range defined by an angle of view equivalent to the field of vision of a typical healthy person).

[0125] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 are responsible for the exchange of various information between the processor 46 and the processor 28 via the network 54. The exchange of various information between the processor 46 and the processor 28 using the communication I / Fs 44 and 26 is carried out in a secure state.

[0126] Fig. 6 shows an example of the main functions of the data processing device 12 and the headset type terminal 314. As shown in Fig. 6, in the data processing device 12, a specific process is performed by the processor 28. A specific process program 56 is stored in the storage 32.

[0127] The processor 28 reads the specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific processing is realized by the processor 28 operating as a specific processing unit 290 in accordance with the specific processing program 56 executed on the RAM 30.

[0128] The storage 32 stores a data generation model 58 and an emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290. The identification processing unit 290 can estimate the user's emotion using the emotion identification model 59 and perform identification processing using the user's emotion.

[0129] In the headset type terminal 314, the identification process is performed by the processor 46. A identification program 60 is stored in the storage 50. The processor 46 reads the identification program 60 from the storage 50 and executes the read identification program 60 on the RAM 48. The identification process is realized by the processor 46 operating as a control unit 46A in accordance with the identification program 60 executed on the RAM 48. Note that the headset type terminal 314 may also have a data generation model and an emotion identification model similar to the data generation model 58 and the emotion identification model 59.

[0130] Note that a device other than the data processing device 12 may have the data generation model 58. For example, a server device may have the data generation model 58. In this case, the data processing device 12 communicates with the server device having the data generation model 58 to obtain a processing result (such as a prediction result) using the data generation model 58. Furthermore, the data processing device 12 may be a server device, or may be a terminal device (for example, a mobile phone, a robot, a home appliance, etc.) owned by a user.

[0131] The specific processing unit 290 transmits the result of the specific processing to the headset type terminal 314. In the headset type terminal 314, the control unit 46A causes the speaker 240 and the display 343 to output the result of the specific processing. The microphone 238 acquires audio indicating a user input regarding the result of the specific processing. The control unit 46A transmits audio data indicating the user input acquired by the microphone 238 to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the audio data.

[0132] The data generation model 58 is a so-called generative AI. An example of the data generation model 58 is a generative AI such as ChatGPT. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 receives a prompt containing an instruction, as well as inference data such as voice data representing speech, text data representing text, and image data representing an image. The data generation model 58 performs inference on the input inference data in accordance with the instruction indicated by the prompt and outputs the inference result in a data format such as voice data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization. The identification processing unit 290 performs the above-mentioned identification processing using the data generation model 58. The data generation model 58 may be a fine-tuned model so as to output an inference result from a prompt that does not include an instruction. In this case, the data generation model 58 can output an inference result from a prompt that does not include an instruction. The data processing device 12 and the like include multiple types of data generation models 58, and the data generation model 58 includes AIs other than the generative AI. The AI ​​other than the generative AI may be, for example, linear regression, logistic regression, decision tree, random forest, support vector machine (SVM), k-means clustering, convolutional neural network (CNN), recurrent neural network (RNN), generative adversarial network (GAN), or naive Bayes, and can perform various processes, but is not limited to these examples. The AI ​​may also be an AI agent. When the processes of each of the above-mentioned parts are performed by AI, the processes may be performed in part or entirely by AI, but are not limited to these examples. The processes performed by AI, including the generative AI, may be replaced with rule-based processes.

[0133] The data processing system 310 according to the third embodiment performs the same processing as the data processing system 10 according to the first embodiment. The processing by the data processing system 310 is executed by the specific processing unit 290 of the data processing device 12 or the control unit 46A of the headset type terminal 314, but may also be executed by the specific processing unit 290 of the data processing device 12 and the control unit 46A of the headset type terminal 314. Furthermore, the specific processing unit 290 of the data processing device 12 acquires or collects information required for processing from the headset type terminal 314 or an external device, etc., and the headset type terminal 314 acquires or collects information required for processing from the data processing device 12 or an external device, etc.

[0134] [Fourth embodiment] FIG. 7 shows an example of the configuration of a data processing system 410 according to the fourth embodiment.

[0135] 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.

[0136] The data processing device 12 includes a computer 22, a database 24, and a communication I / F 26. The computer 22 includes a processor 28, a RAM 30, and a storage 32. The processor 28, RAM 30, and storage 32 are connected to a bus 34. The database 24 and the communication I / F 26 are also connected to the bus 34. The communication I / F 26 is connected to a network 54. Examples of the network 54 include a WAN and / or a LAN.

[0137] The robot 414 includes a computer 36, a microphone 238, a speaker 240, a camera 42, a communication I / F 44, and a control target 443. The computer 36 includes a processor 46, a RAM 48, and a storage 50. The processor 46, the RAM 48, and the storage 50 are connected to a bus 52. The microphone 238, the speaker 240, the camera 42, and the control target 443 are also connected to the bus 52.

[0138] The microphone 238 receives instructions and the like from the user by receiving voice uttered by the user. The microphone 238 captures the voice uttered by the user, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio according to instructions from the processor 46.

[0139] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an imaging element such as a CMOS image sensor or a CCD image sensor, and captures images of the user's surroundings (for example, an imaging range defined by an angle of view equivalent to the field of vision of a typical healthy person).

[0140] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 are responsible for the exchange of various information between the processor 46 and the processor 28 via the network 54. The exchange of various information between the processor 46 and the processor 28 using the communication I / Fs 44 and 26 is carried out in a secure state.

[0141] The control object 443 includes a display device, LEDs in the eyes, and motors that drive the arms, hands, and feet. The posture and gestures of the robot 414 are controlled by controlling the motors of the arms, hands, and feet. Some of the emotions of the robot 414 can be expressed by controlling these motors. In addition, the facial expressions of the robot 414 can also be expressed by controlling the light emission state of the LEDs in the eyes of the robot 414.

[0142] Fig. 8 shows an example of the main functions of the data processing device 12 and the robot 414. As shown in Fig. 8, in the data processing device 12, a specific process is performed by the processor 28. A specific process program 56 is stored in the storage 32.

[0143] The processor 28 reads the specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific processing is realized by the processor 28 operating as a specific processing unit 290 in accordance with the specific processing program 56 executed on the RAM 30.

[0144] The storage 32 stores a data generation model 58 and an emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290. The identification processing unit 290 can estimate the user's emotion using the emotion identification model 59 and perform identification processing using the user's emotion.

[0145] In the robot 414, the processor 46 performs the identification process. A identification program 60 is stored in the storage 50. The processor 46 reads the identification program 60 from the storage 50 and executes the read identification program 60 on the RAM 48. The identification process is realized by the processor 46 operating as a control unit 46A in accordance with the identification program 60 executed on the RAM 48. The robot 414 may have a data generation model and an emotion identification model similar to the data generation model 58 and the emotion identification model 59.

[0146] Note that a device other than the data processing device 12 may have the data generation model 58. For example, a server device may have the data generation model 58. In this case, the data processing device 12 communicates with the server device having the data generation model 58 to obtain a processing result (such as a prediction result) using the data generation model 58. Furthermore, the data processing device 12 may be a server device, or may be a terminal device (for example, a mobile phone, a robot, a home appliance, etc.) owned by a user.

[0147] The specific processing unit 290 transmits the result of the specific processing to the robot 414. In the robot 414, the control unit 46A causes the speaker 240 and the control target 443 to output the result of the specific processing. The microphone 238 acquires voice indicating a user input regarding the result of the specific processing. The control unit 46A transmits voice data indicating the user input acquired by the microphone 238 to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the voice data.

[0148] The data generation model 58 is a so-called generative AI. An example of the data generation model 58 is a generative AI such as ChatGPT. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 receives a prompt containing an instruction, as well as inference data such as voice data representing speech, text data representing text, and image data representing an image. The data generation model 58 performs inference on the input inference data in accordance with the instruction indicated by the prompt and outputs the inference result in a data format such as voice data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization. The identification processing unit 290 performs the above-mentioned identification processing using the data generation model 58. The data generation model 58 may be a fine-tuned model so as to output an inference result from a prompt that does not include an instruction. In this case, the data generation model 58 can output an inference result from a prompt that does not include an instruction. The data processing device 12 and the like include multiple types of data generation models 58, and the data generation model 58 includes AIs other than the generative AI. The AI ​​other than the generative AI may be, for example, linear regression, logistic regression, decision tree, random forest, support vector machine (SVM), k-means clustering, convolutional neural network (CNN), recurrent neural network (RNN), generative adversarial network (GAN), or naive Bayes, and can perform various processes, but is not limited to these examples. The AI ​​may also be an AI agent. When the processes of each of the above-mentioned parts are performed by AI, the processes may be performed in part or entirely by AI, but are not limited to these examples. The processes performed by AI, including the generative AI, may be replaced with rule-based processes.

[0149] The data processing system 410 according to the fourth embodiment performs the same processing as the data processing system 10 according to the first embodiment. The processing by the data processing system 410 is executed by the specific processing unit 290 of the data processing device 12 or the control unit 46A of the robot 414, but may also be executed by the specific processing unit 290 of the data processing device 12 and the control unit 46A of the robot 414. Furthermore, the specific processing unit 290 of the data processing device 12 acquires or collects information required for processing from the robot 414 or an external device, etc., and the robot 414 acquires or collects information required for processing from the data processing device 12 or an external device, etc.

[0150] The emotion identification model 59 as an emotion engine may determine the user's emotion according to a specific mapping. Specifically, the emotion identification model 59 may determine the user's emotion according to an emotion map (see FIG. 9), which is a specific mapping. Similarly, the emotion identification model 59 may determine the robot's emotion, and the identification processing unit 290 may perform identification processing using the robot's emotion.

[0151] FIG. 9 illustrates an emotion map 400 on which multiple emotions are mapped. In the emotion map 400, emotions are arranged in concentric circles radiating from the center. Emotions closer to the center of the concentric circles are more primitive. Emotions representing states and behaviors arising from a state of mind are arranged on the outer edges of the concentric circles. The concept of emotion encompasses both emotions and mental states. Emotions generally generated from reactions occurring in the brain are arranged on the left side of the concentric circles. Emotions generally induced by situational judgment are arranged on the right side of the concentric circles. Emotions generally generated from reactions occurring in the brain and induced by situational judgment are arranged on the upper and lower sides of the concentric circles. Furthermore, the emotion of "pleasure" is arranged on the upper side of the concentric circles, and the emotion of "discomfort" is arranged on the lower side. In this way, in the emotion map 400, multiple emotions are mapped based on the structure by which emotions are generated, and emotions that tend to occur simultaneously are mapped close to each other.

[0152] These emotions are distributed in the 3 o'clock direction on emotion map 400, and typically fluctuate between relief and anxiety. In the right half of emotion map 400, situational awareness dominates over internal sensations, resulting in a sense of calm.

[0153] The inside of emotion map 400 represents what is going on in the mind, and the outside of emotion map 400 represents behavior, so the further you go outside emotion map 400, the more visible the emotions become (the more they are expressed in behavior).

[0154] Human emotions are based on various balances, such as posture and blood sugar levels. When these balances deviate from the ideal, a state of discomfort is expressed, and when they approach the ideal, a state of pleasure is expressed. Emotions can also be created for robots, cars, and motorcycles, based on various balances, such as posture and remaining battery life. When these balances deviate from the ideal, a state of discomfort is expressed, and when they approach the ideal, a state of pleasure is expressed. An emotion map can be generated, for example, based on Dr. Mitsuyoshi's emotion map (Research on speech emotion recognition and brain physiological signal analysis systems for emotions, Tokushima University, doctoral dissertation: https: / / ci.nii.ac.jp / naid / 500000375379). The left half of the emotion map lists emotions belonging to the area called "reaction," where sensation is dominant. The right half of the emotion map lists emotions belonging to the area called "situation," where situational awareness is dominant.

[0155] The emotion map defines two emotions that promote learning. One is a negative emotion on the situation side, around the middle of "repentance" or "reflection." In other words, this occurs when the robot experiences negative emotions such as "I never want to feel this way again" or "I don't want to be scolded again." The other is a positive emotion on the response side, around "desire." In other words, this occurs when the robot experiences positive feelings such as "I want more" or "I want to know more."

[0156] The emotion identification model 59 inputs user input into a pre-trained neural network, obtains emotion values ​​indicating each emotion shown in the emotion map 400, and determines the user's emotion. This neural network is pre-trained based on multiple pieces of training data that are combinations of user input and emotion values ​​indicating each emotion shown in the emotion map 400. Furthermore, this neural network is trained so that emotions that are located close to each other have similar values, as in the emotion map 900 shown in FIG. 10. FIG. 10 shows an example in which multiple emotions, "relieved," "calm," and "reassuring," have similar emotion values.

[0157] In the above embodiment, an example was given in which a specific process is performed by one computer 22, but the technology disclosed herein is not limited to this, and distributed processing of the specific process may be performed by multiple computers including computer 22.

[0158] In the above embodiment, an example in which the specific processing program 56 is stored in the storage 32 has been described, but the technology of the present disclosure is not limited to this. For example, the specific processing program 56 may be stored in a portable, computer-readable, non-transitory storage medium such as a USB (Universal Serial Bus) memory. The specific processing program 56 stored in the non-transitory storage medium is installed in the computer 22 of the data processing device 12. The processor 28 executes the specific processing in accordance with the specific processing program 56.

[0159] 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.

[0160] It is not necessary to store all of the specific processing program 56 in a storage device such as a server connected to the data processing device 12 via the network 54, or to store all of the specific processing program 56 in the storage 32; only a portion of the specific processing program 56 may be stored.

[0161] The hardware resource for executing a specific process can be any of the following types of processors: A processor, for example, is a CPU, which is a general-purpose processor that functions as a hardware resource for executing a specific process by executing software, i.e., a program. A processor also includes a dedicated electrical circuit, such as an FPGA (Field-Programmable Gate Array), a PLD (Programmable Logic Device), or an ASIC (Application Specific Integrated Circuit), which is a processor with a circuit configuration designed specifically for executing a specific process. Each processor has built-in or connected memory, and each processor uses the memory to execute the specific process.

[0162] The hardware resource that executes the specific process may be configured with one of these various processors, or may be configured with a combination of two or more processors of the same or different types (for example, a combination of multiple FPGAs, or a combination of a CPU and an FPGA). Also, the hardware resource that executes the specific process may be a single processor.

[0163] As an example of a system configured with a single processor, first, one processor is configured by combining one or more CPUs and software, and this processor functions as a hardware resource that executes a specific process. Second, there is a system that uses a processor that realizes the functions of an entire system including multiple hardware resources that execute a specific process on a single IC chip, as typified by SoC (System-on-a-chip). In this way, a specific process is realized using one or more of the above-mentioned various processors as hardware resources.

[0164] Furthermore, the hardware structure of these various processors can be, more specifically, an electric circuit that combines circuit elements such as semiconductor devices. The specific processing described above is merely an example. Therefore, it goes without saying that unnecessary steps may be deleted, new steps may be added, or the processing order may be rearranged, without departing from the spirit of the invention.

[0165] In the above example, the first to fourth embodiments have been described separately, but some or all of these embodiments may be combined. The smart device 14, smart glasses 214, headset terminal 314, and robot 414 are merely examples, and they may be combined, or other devices may be used. In the above example, the first and second embodiments have been described separately, but they may be combined.

[0166] The above-described description and illustrations are a detailed explanation of the parts related to the technology of the present disclosure and are merely an example of the technology of the present disclosure. For example, the above description of the configuration, functions, actions, and effects is an explanation of an example of the configuration, functions, actions, and effects of the parts related to the technology of the present disclosure. Therefore, it goes without saying that unnecessary parts may be deleted, new elements may be added, or replacements may be made to the above-described description and illustrations within the scope of the gist of the technology of the present disclosure. Furthermore, to avoid confusion and facilitate understanding of the parts related to the technology of the present disclosure, the above-described description and illustrations omit explanations of common technical knowledge that do not require particular explanation to enable the implementation of the technology of the present disclosure.

[0167] All publications, patent applications, and technical standards mentioned in this specification are herein incorporated by reference to the same extent as if each individual publication, patent application, or technical standard was specifically and individually indicated to be incorporated by reference. [Explanation of symbols]

[0168] 10, 210, 310, 410 Data Processing Systems 12 Data Processing Device 14 Smart Devices 214 Smart Glasses 314 Headset-type terminal 414 Robot

Claims

1. a voice analysis unit that analyzes voices; a feature extraction unit that extracts features of the voice analyzed by the voice analysis unit; a mapping unit that maps the voice features extracted by the feature extraction unit to facial regularities; an illustration generation unit that generates an anime-style illustration based on the mapping result by the mapping unit; an actor face generation unit that generates an actor's face based on the mapping result by the mapping unit; an avatar generation unit that generates a virtual avatar based on the illustration and face generated by the illustration generation unit and the actor face generation unit. A system characterized by:

2. The voice analysis unit Accommodating different languages ​​and dialects to cater to a global audience 2. The system of claim 1.

3. The mapping unit Model subtle facial expressions or muscle movements to generate more realistic facial features 2. The system of claim 1.

4. The illustration generation unit Generate character movements and poses in real time to create dynamic animations 2. The system of claim 1.

5. The actor face generation unit Generate facial features based on the actor's age and gender to create a more realistic face 2. The system of claim 1.

6. The avatar generation unit Generate facial expressions and movements of avatars based on the emotional state of the voice, and create avatars that respond to emotions.

2. The system of claim 1.

7. The voice analysis unit Analyze the emotional state of the voice and extract features based on that emotion 2. The system of claim 1.

Images