System

Abstract

A system according to embodiments is directed to efficiently adding audio and related content to a visual work.SOLUTION: A system according to an embodiment includes a speech-to-text unit, a speech generation unit, a visual generation unit, and a related content search unit. The speech-to-text converter converts speech into text. The speech generation unit generates speech from the text converted by the speech-to-text unit. The visual generator generates new visual content based on the sound generated by the sound generator. The related content search unit searches for text or an image related to the visual content generated by the visual generation unit.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] Previous technology has made the process of adding audio and related content to visual works tedious, time-consuming, and inefficient.

[0005] The system according to the embodiment aims to efficiently add audio and related content to visual works. [Means for solving the problem]

[0006] The system according to the embodiment includes a speech-to-text unit, a speech generation unit, a visual generation unit, and a related content search unit. The speech-to-text unit converts speech into text. The speech generation unit generates speech from the text converted by the speech-to-text unit. The visual generation unit generates new visual content based on the speech generated by the speech generation unit. The related content search unit searches for text or images related to the visual content generated by the visual generation unit. [Effects of the Invention]

[0007] Embodiments of the system allow for efficient addition of audio and related content to visual works. [Brief explanation of the drawings]

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

[0028] (Example 1) An entertainment system according to an embodiment of the present invention converts speech into text, generates speech from text, generates visual content, and searches for related content, thereby bringing manga and anime visual works to life and providing a new form of entertainment experience.

[0029] An entertainment system according to an embodiment includes a speech-to-text unit, a speech generation unit, a visual generation unit, and a related content search unit. The speech-to-text unit converts speech into text. For example, it analyzes speech using speech recognition technology and generates corresponding text. The speech-to-text unit can also analyze the tone and speed of speech to estimate emotions. For example, it analyzes the strength and rhythm of speech to estimate a character's emotions. The speech generation unit generates speech from text. For example, it analyzes text using speech synthesis technology and generates corresponding speech. The speech generation unit can also learn a character's past utterances and behavior patterns to generate consistent speech. For example, it can generate speech with the same tone and rhythm based on the character's past utterance data. The visual generation unit generates new visual content. For example, it generates visual content based on a user's instructions using image generation technology. The visual generation unit can also estimate a character's emotions and adjust the color tone and composition of a scene based on the estimated emotions. For example, if a character is sad, the color tone of the scene can be darkened and the composition can be simplified. The related content search unit searches for related text and images. For example, the related text and images may be searched for using an embedding function and provided to the user. The related content search unit may also preferentially display related content according to the user's emotions. For example, if the user is happy, text and images that empathize with the user's emotions may be preferentially displayed. This enables the entertainment system according to the embodiment to perform mutual conversion between voice and text, generate visual content, and search for related content. For example, a user can automatically convert dialogue from a manga to voice and give characters their own unique voices. Furthermore, new visual content can be created to expand the worldview of the story or characters. Furthermore, related text and images can be searched to provide background information for the story.

[0030] When generating voice from text, the voice generation unit learns the character's past statements and behavioral patterns, allowing it to generate consistent voice. For example, the voice generation unit stores the character's past statements and behavioral patterns in a database, which the generation AI learns from. For example, it records the tone in which Character A has spoken in the past. The voice generation unit also ensures consistency when generating voice from text based on the learned data. For example, if Character A always speaks in a calm tone, the generated voice will also maintain a calm tone. The voice generation unit also builds a system that references past statements and behavioral patterns in real time to generate voice from text. For example, to maintain the character's consistency, it constantly references past data. This makes it possible to generate voice that maintains the character's consistency.

[0031] The voice generation unit can simultaneously convert voice to text and generate voice from the text, generating character conversations in real time. The voice generation unit, for example, builds a system that simultaneously converts voice to text and generates voice from text. For example, voice input is converted to text as it is received, and voice is generated based on that text. The voice generation unit also uses high-speed voice analysis and generation technology to generate character conversations in real time. For example, the processing from voice input to text conversion and voice generation is completed within a few seconds. The voice generation unit also develops a system that processes multiple voice inputs simultaneously to generate character conversations in real time. For example, it can smoothly process scenes in which multiple characters speak at the same time. This makes it possible to generate character conversations in real time.

[0032] The speech-to-text unit and speech generation unit convert speech to text between different languages ​​and generate speech from text, making it possible to create multilingual characters. For example, the speech-to-text unit and speech generation unit build a system that converts speech to text and generates speech from text in different languages. For example, Japanese speech is converted into English text and English speech is generated based on that text. In addition, to create multilingual characters, the speech-to-text unit and speech generation unit prepare a speech database for each language, which the generation AI learns from. For example, speech data for English, French, Chinese, etc. is prepared. The speech-to-text unit and speech generation unit also develop a system that converts speech to text between different languages ​​and generates speech from text in real time. For example, English speech is generated simultaneously with Japanese speech input. This makes it possible to create multilingual characters.

[0033] The speech-to-text unit and speech generation unit convert speech to text and generate speech from the text between different characters, enabling automatic generation of dialogue between the characters. The speech-to-text unit and speech generation unit, for example, build a system that converts speech between different characters to text and generates speech from the text. For example, they automatically generate a conversation between character A and character B. In addition, to automatically generate dialogue between characters, the speech-to-text unit and speech generation unit prepare a voice database for each character, which the generation AI learns from. For example, they prepare voice data for character A and character B. In addition, the speech-to-text unit and speech generation unit develop a system that generates dialogue between different characters in real time. For example, they generate a voice in which character B responds as character A speaks. This allows automatic generation of dialogue between characters.

[0034] The visual generation unit learns past scenes and character behavior patterns when creating visual content, allowing it to generate consistent visuals. For example, the visual generation unit stores past scenes and character behavior patterns in a database, which the generation AI then learns. For example, it records how Character A acted in past scenes. The visual generation unit also ensures consistency when creating visual content based on the learned data. For example, it ensures that Character A always maintains the same pose and facial expression. The visual generation unit also references past scenes and behavior patterns in real time to build a system that generates visual content. For example, it constantly references past data to maintain character consistency. This makes it possible to generate consistent visuals based on past scenes and behavior patterns.

[0035] The visual generation unit can dynamically adjust the creation of visual content based on real-time user feedback. For example, the visual generation unit builds a system that collects real-time user feedback when creating visual content. For example, it uses an online survey or comment function. The visual generation unit also analyzes user feedback in real time and dynamically adjusts the visual content. For example, it changes the color tone or composition of a scene based on user opinions. The visual generation unit also develops a system that continuously improves the visual content based on real-time feedback. For example, it adjusts the visual based on user evaluation scores. This makes it possible to dynamically adjust the visual content based on real-time user feedback.

[0036] The visual generation unit creates visual content using different art styles and techniques, allowing for a variety of visual expressions. For example, the visual generation unit builds a system that uses different art styles and techniques when creating visual content. For example, it allows users to select styles such as hand-drawn, 3D rendering, and anime. The visual generation unit also provides a variety of visual expressions using a generative AI that has learned different art styles and techniques. For example, it generates visual content according to a style selected by a user. The visual generation unit also develops a system that combines multiple art styles and techniques when creating visual content to achieve unique visual expressions. For example, it provides an expression that combines hand-drawn and 3D rendering. This enables a variety of visual expressions.

[0037] The visual generation unit creates visual content with different characters and scenes, allowing multiple storylines to unfold simultaneously. For example, the visual generation unit builds a system that creates visual content with different characters and scenes. For example, it generates a storyline in which Character A and Character B appear simultaneously in different scenes. In addition, to unfold multiple storylines simultaneously, the visual generation unit prepares a database of each character and scene, which the generation AI learns. For example, it records the behavior patterns of Character A and Character B. The visual generation unit also generates visual content with different characters and scenes in real time, developing a system that unfolds multiple storylines simultaneously. For example, it generates visuals according to the storyline selected by the user. This allows multiple storylines to unfold simultaneously.

[0038] The related content search unit uses the embedding function to learn past search history and user behavior patterns, allowing it to provide more accurate related content. For example, the related content search unit uses the embedding function to store past search history and user behavior patterns in a database, which the generation AI then learns. For example, it records keywords that users have previously searched for and content they have viewed. The related content search unit also builds a system that provides more accurate related content based on the learned data. For example, it prioritizes displaying highly relevant text and images based on the user's past behavior patterns. The related content search unit also develops a system that references past search history and behavior patterns in real time to provide related content. For example, each time a user performs a new search, it updates the related content based on past data. This makes it possible to provide more accurate related content based on past search history and behavior patterns.

[0039] The related content search unit can use the embedding function to reflect user feedback in real time and dynamically adjust search results. For example, the related content search unit uses the embedding function to build a system that collects real-time feedback from users. For example, it uses online surveys and comment functions. The related content search unit also analyzes user feedback in real time and dynamically adjusts search results. For example, it prioritizes displaying highly relevant text and images based on user opinions. The related content search unit also develops a system that continuously improves search results based on real-time feedback. For example, it adjusts search results based on user evaluation scores. This makes it possible to dynamically adjust search results based on real-time user feedback.

[0040] The related content search unit can use the embedding function to search for related content from different media (e.g., videos and music) and provide a multimedia experience. The related content search unit, for example, uses the embedding function to build a system that searches for related content from different media. For example, a database of videos and music is prepared and the generation AI learns from it. The related content search unit also searches for related content from different media and provides a multimedia experience. For example, videos and music related to a character's scene are displayed. The related content search unit also develops a system that searches for related content from different media in real time and provides it to the user. For example, each time a user performs a new search, the related content is updated based on the video and music database. This makes it possible to search for related content from different media and provide a multimedia experience.

[0041] The related content search unit uses the embedding function to simultaneously search for content related to different characters and scenes, thereby providing information from multiple perspectives. For example, the related content search unit uses the embedding function to build a system that simultaneously searches for content related to different characters and scenes. For example, related content for character A and character B is displayed simultaneously. Furthermore, to provide information from multiple perspectives, the related content search unit prepares a database for each character and scene, which the generation AI learns. For example, the behavior patterns of character A and character B are recorded. Furthermore, the related content search unit searches for content related to different characters and scenes in real time, thereby developing a system that provides information from multiple perspectives. For example, related content is displayed according to the character or scene selected by the user. This makes it possible to simultaneously search for content related to different characters and scenes, thereby providing information from multiple perspectives.

[0042] The system according to the embodiment is not limited to the above-described example, and various modifications are possible, for example, as follows.

[0043] The entertainment system may further include a biometric information acquisition unit that acquires biometric information of the user. For example, the biometric information acquisition unit may measure the user's heart rate or electrodermal response to estimate the user's level of excitement or relaxation. The biometric information acquisition unit may also adjust the operation of the system based on the user's biometric information. For example, if the user is excited, the system may provide more action scenes, and if the user is relaxed, the system may provide more calm scenes. This enables a personalized entertainment experience based on the user's biometric information.

[0044] The entertainment system may further include an eye-tracking unit that tracks the user's gaze. For example, the system may analyze in real time which part of the screen the user is looking at and identify characters or scenes of interest. The eye-tracking unit may also adjust the system's operation based on the user's gaze. For example, if the user is paying attention to a particular character, the system may prioritize displaying information or scenes related to that character. This enables an interactive entertainment experience based on the user's gaze.

[0045] The entertainment system may further include a gesture recognition unit that recognizes user gestures. For example, a camera may detect a user's gestures, such as waving or pointing, and reflect the detected gestures in the system. The gesture recognition unit may also adjust the system's behavior based on the user's gestures. For example, when a user performs a specific gesture, a character may perform an action corresponding to the gesture. This allows for an interactive entertainment experience based on the user's gestures.

[0046] The entertainment system may further include a voice recognition unit that recognizes user voice commands. For example, when a user issues a voice command such as "go to the next scene" or "change character," the system recognizes the command and performs the corresponding action. The voice recognition unit may also adjust the system's operation based on the user's voice command. For example, when a user calls out the name of a specific character, that character will appear on the screen. This allows for an interactive entertainment experience based on the user's voice commands.

[0047] The processing flow of the first embodiment will be briefly explained below.

[0048] Step 1: The speech-to-text unit converts speech into text. For example, it uses speech recognition technology to analyze the speech and generate corresponding text. The speech-to-text unit can also analyze the tone and speed of the speech to estimate emotions. For example, it can analyze the strength and rhythm of the speech to estimate the character's emotions. Step 2: The voice generation unit generates voice from the text. For example, it analyzes the text using speech synthesis technology and generates corresponding voice. The voice generation unit can also learn the character's past utterances and behavior patterns to generate consistent voice. For example, it can generate voice with the same tone and rhythm based on the character's past utterance data. Step 3: The visual generation unit generates new visual content. For example, it uses image generation technology to generate visual content based on user instructions. The visual generation unit can also estimate the character's emotions and adjust the color tone and composition of the scene based on those emotions. For example, if the character is sad, the scene's color tone can be darkened and the composition simplified. Step 4: The related content search unit searches for related text and images. For example, it uses the embedding function to search for related text and images and provides them to the user. The related content search unit can also prioritize displaying related content according to the user's emotions. For example, if the user is happy, it will prioritize displaying text and images that empathize with that emotion.

[0049] (Example 2) An entertainment system according to an embodiment of the present invention converts speech into text, generates speech from text, generates visual content, and searches for related content, thereby bringing manga and anime visual works to life and providing a new form of entertainment experience.

[0050] An entertainment system according to an embodiment includes a speech-to-text unit, a speech generation unit, a visual generation unit, and a related content search unit. The speech-to-text unit converts speech into text. For example, it analyzes speech using speech recognition technology and generates corresponding text. The speech-to-text unit can also analyze the tone and speed of speech to estimate emotions. For example, it analyzes the strength and rhythm of speech to estimate a character's emotions. The speech generation unit generates speech from text. For example, it analyzes text using speech synthesis technology and generates corresponding speech. The speech generation unit can also learn a character's past utterances and behavior patterns to generate consistent speech. For example, it can generate speech with the same tone and rhythm based on the character's past utterance data. The visual generation unit generates new visual content. For example, it generates visual content based on a user's instructions using image generation technology. The visual generation unit can also estimate a character's emotions and adjust the color tone and composition of a scene based on the estimated emotions. For example, if a character is sad, the color tone of the scene can be darkened and the composition can be simplified. The related content search unit searches for related text and images. For example, the related text and images may be searched for using an embedding function and provided to the user. The related content search unit may also preferentially display related content according to the user's emotions. For example, if the user is happy, text and images that empathize with the user's emotions may be preferentially displayed. This enables the entertainment system according to the embodiment to perform mutual conversion between voice and text, generate visual content, and search for related content. For example, a user can automatically convert dialogue from a manga to voice and give characters their own unique voices. Furthermore, new visual content can be created to expand the worldview of the story or characters. Furthermore, related text and images can be searched to provide background information for the story.

[0051] The speech-to-text unit can estimate the character's emotion when converting speech to text and adjust the text expression based on that emotion. For example, the speech-to-text unit uses speech analysis technology to estimate the character's emotion when converting speech to text. For example, it analyzes the tone, speed, and strength of the speech to estimate whether the character is angry or sad. The speech-to-text unit also adjusts the text expression based on the estimated emotion. For example, if the emotion of anger is strong, exclamation marks or emphasis expressions are added, and if the emotion of sadness is strong, punctuation and expressions are softened. The speech-to-text unit also builds a system that performs emotion estimation and text adjustment in real time. For example, the emotion is estimated at the same time as speech input and reflected in the text. This makes it possible to express text according to the character's emotion.

[0052] When generating voice from text, the voice generation unit learns the character's past statements and behavioral patterns, allowing it to generate consistent voice. For example, the voice generation unit stores the character's past statements and behavioral patterns in a database, which the generation AI learns from. For example, it records the tone in which Character A has spoken in the past. The voice generation unit also ensures consistency when generating voice from text based on the learned data. For example, if Character A always speaks in a calm tone, the generated voice will also maintain a calm tone. The voice generation unit also builds a system that references past statements and behavioral patterns in real time to generate voice from text. For example, to maintain the character's consistency, it constantly references past data. This makes it possible to generate voice that maintains the character's consistency.

[0053] The voice generation unit can simultaneously convert voice to text and generate voice from the text, generating character conversations in real time. The voice generation unit, for example, builds a system that simultaneously converts voice to text and generates voice from text. For example, voice input is converted to text as it is received, and voice is generated based on that text. The voice generation unit also uses high-speed voice analysis and generation technology to generate character conversations in real time. For example, the processing from voice input to text conversion and voice generation is completed within a few seconds. The voice generation unit also develops a system that processes multiple voice inputs simultaneously to generate character conversations in real time. For example, it can smoothly process scenes in which multiple characters speak at the same time. This makes it possible to generate character conversations in real time.

[0054] The speech-to-text unit and speech generation unit convert speech to text between different languages ​​and generate speech from text, making it possible to create multilingual characters. For example, the speech-to-text unit and speech generation unit build a system that converts speech to text and generates speech from text in different languages. For example, Japanese speech is converted into English text and English speech is generated based on that text. In addition, to create multilingual characters, the speech-to-text unit and speech generation unit prepare a speech database for each language, which the generation AI learns from. For example, speech data for English, French, Chinese, etc. is prepared. The speech-to-text unit and speech generation unit also develop a system that converts speech to text between different languages ​​and generates speech from text in real time. For example, English speech is generated simultaneously with Japanese speech input. This makes it possible to create multilingual characters.

[0055] The speech-to-text unit and speech generation unit convert speech to text and generate speech from the text between different characters, enabling automatic generation of dialogue between the characters. The speech-to-text unit and speech generation unit, for example, build a system that converts speech between different characters to text and generates speech from the text. For example, they automatically generate a conversation between character A and character B. In addition, to automatically generate dialogue between characters, the speech-to-text unit and speech generation unit prepare a voice database for each character, which the generation AI learns from. For example, they prepare voice data for character A and character B. In addition, the speech-to-text unit and speech generation unit develop a system that generates dialogue between different characters in real time. For example, they generate a voice in which character B responds as character A speaks. This allows automatic generation of dialogue between characters.

[0056] The voice generation unit uses the emotion estimation function to adjust the tone and speed of the voice according to the character's emotion, thereby enabling more natural conversation. The voice generation unit, for example, uses the emotion estimation function to build a system that adjusts the tone and speed of the voice according to the character's emotion. For example, if the emotion of anger is strong, the voice tone is raised and the speed is increased. The voice generation unit also uses high-speed emotion analysis technology to adjust the tone and speed of the voice according to the character's emotion in real time. For example, the emotion is analyzed simultaneously with voice input and reflected in the voice. The voice generation unit also develops a system that achieves more natural conversation by combining emotion estimation and voice adjustment. For example, the voice is adjusted so that dialogue between characters proceeds smoothly. This enables natural conversation according to the character's emotion.

[0057] The visual generation unit can estimate a character's emotion when creating visual content and adjust the color tone and composition of a scene based on that emotion. For example, the visual generation unit uses emotion analysis technology to estimate a character's emotion when creating visual content. For example, it analyzes the character's facial expression and pose to estimate the emotion. The visual generation unit also adjusts the color tone and composition of a scene based on the estimated emotion. For example, if the emotion of sadness is strong, the color tone of the scene is darkened and the composition is simplified. The visual generation unit also builds a system that performs emotion estimation and scene adjustment in real time. For example, the color tone and composition of a scene are automatically adjusted every time the character's emotion changes. This makes it possible to adjust the color tone and composition of a scene according to the character's emotion.

[0058] The visual generation unit learns past scenes and character behavior patterns when creating visual content, allowing it to generate consistent visuals. For example, the visual generation unit stores past scenes and character behavior patterns in a database, which the generation AI then learns. For example, it records how Character A acted in past scenes. The visual generation unit also ensures consistency when creating visual content based on the learned data. For example, it ensures that Character A always maintains the same pose and facial expression. The visual generation unit also references past scenes and behavior patterns in real time to build a system that generates visual content. For example, it constantly references past data to maintain character consistency. This makes it possible to generate consistent visuals based on past scenes and behavior patterns.

[0059] The visual generation unit can dynamically adjust the creation of visual content based on real-time user feedback. For example, the visual generation unit builds a system that collects real-time user feedback when creating visual content. For example, it uses an online survey or comment function. The visual generation unit also analyzes user feedback in real time and dynamically adjusts the visual content. For example, it changes the color tone or composition of a scene based on user opinions. The visual generation unit also develops a system that continuously improves the visual content based on real-time feedback. For example, it adjusts the visual based on user evaluation scores. This makes it possible to dynamically adjust the visual content based on real-time user feedback.

[0060] The visual generation unit creates visual content using different art styles and techniques, allowing for a variety of visual expressions. For example, the visual generation unit builds a system that uses different art styles and techniques when creating visual content. For example, it allows users to select styles such as hand-drawn, 3D rendering, and anime. The visual generation unit also provides a variety of visual expressions using a generative AI that has learned different art styles and techniques. For example, it generates visual content according to a style selected by a user. The visual generation unit also develops a system that combines multiple art styles and techniques when creating visual content to achieve unique visual expressions. For example, it provides an expression that combines hand-drawn and 3D rendering. This enables a variety of visual expressions.

[0061] The visual generation unit creates visual content with different characters and scenes, allowing multiple storylines to unfold simultaneously. For example, the visual generation unit builds a system that creates visual content with different characters and scenes. For example, it generates a storyline in which Character A and Character B appear simultaneously in different scenes. In addition, to unfold multiple storylines simultaneously, the visual generation unit prepares a database of each character and scene, which the generation AI learns. For example, it records the behavior patterns of Character A and Character B. The visual generation unit also generates visual content with different characters and scenes in real time, developing a system that unfolds multiple storylines simultaneously. For example, it generates visuals according to the storyline selected by the user. This allows multiple storylines to unfold simultaneously.

[0062] The visual generation unit can use the emotion estimation function to add visual effects according to the character's emotion to enhance emotional expression. The visual generation unit, for example, uses the emotion estimation function to build a system that adds visual effects according to the character's emotion. For example, if the emotion of anger is strong, a flame effect is added to the background. The visual generation unit also uses high-speed emotion analysis technology to add visual effects according to the character's emotion in real time. For example, effects are automatically added every time the character's facial expression changes. The visual generation unit also develops a system that enhances emotional expression by combining emotion estimation and visual effects. For example, the background and effects are adjusted every time the character's emotion changes. This makes it possible to add visual effects according to the character's emotion.

[0063] The related content search unit can use the embedding function to estimate a character's emotion and prioritize search for related text and images based on that emotion. The related content search unit, for example, uses the embedding function to build a system that estimates a character's emotion. For example, it analyzes the character's facial expressions and actions to estimate the emotion. The related content search unit also prioritizes search for related text and images based on the estimated emotion. For example, if a character is sad, it prioritizes displaying text and images that express sadness. The related content search unit also develops a system that estimates emotions and searches for related content in real time. For example, it automatically updates related text and images every time a character's emotion changes. This enables prioritized search for related content based on the character's emotion.

[0064] The related content search unit uses the embedding function to learn past search history and user behavior patterns, allowing it to provide more accurate related content. For example, the related content search unit uses the embedding function to store past search history and user behavior patterns in a database, which the generation AI then learns. For example, it records keywords that users have previously searched for and content they have viewed. The related content search unit also builds a system that provides more accurate related content based on the learned data. For example, it prioritizes displaying highly relevant text and images based on the user's past behavior patterns. The related content search unit also develops a system that references past search history and behavior patterns in real time to provide related content. For example, each time a user performs a new search, it updates the related content based on past data. This makes it possible to provide more accurate related content based on past search history and behavior patterns.

[0065] The related content search unit can use the embedding function to reflect user feedback in real time and dynamically adjust search results. For example, the related content search unit uses the embedding function to build a system that collects real-time feedback from users. For example, it uses online surveys and comment functions. The related content search unit also analyzes user feedback in real time and dynamically adjusts search results. For example, it prioritizes displaying highly relevant text and images based on user opinions. The related content search unit also develops a system that continuously improves search results based on real-time feedback. For example, it adjusts search results based on user evaluation scores. This makes it possible to dynamically adjust search results based on real-time user feedback.

[0066] The related content search unit can use the embedding function to search for related content from different media (e.g., videos and music) and provide a multimedia experience. The related content search unit, for example, uses the embedding function to build a system that searches for related content from different media. For example, a database of videos and music is prepared and the generation AI learns from it. The related content search unit also searches for related content from different media and provides a multimedia experience. For example, videos and music related to a character's scene are displayed. The related content search unit also develops a system that searches for related content from different media in real time and provides it to the user. For example, each time a user performs a new search, the related content is updated based on the video and music database. This makes it possible to search for related content from different media and provide a multimedia experience.

[0067] The related content search unit uses the embedding function to simultaneously search for content related to different characters and scenes, thereby providing information from multiple perspectives. For example, the related content search unit uses the embedding function to build a system that simultaneously searches for content related to different characters and scenes. For example, related content for character A and character B is displayed simultaneously. Furthermore, to provide information from multiple perspectives, the related content search unit prepares a database for each character and scene, which the generation AI learns. For example, the behavior patterns of character A and character B are recorded. Furthermore, the related content search unit searches for content related to different characters and scenes in real time, thereby developing a system that provides information from multiple perspectives. For example, related content is displayed according to the character or scene selected by the user. This makes it possible to simultaneously search for content related to different characters and scenes, thereby providing information from multiple perspectives.

[0068] The related content search unit uses an emotion estimation function to preferentially display related content according to the user's emotion, thereby promoting emotional empathy. The related content search unit, for example, uses the emotion estimation function to build a system that preferentially displays related content according to the user's emotion. For example, if the user is sad, text and images that empathize with the emotion are displayed. The related content search unit also uses high-speed emotion analysis technology to display related content according to the user's emotion in real time. For example, the related content is automatically updated every time the user's emotion changes. The related content search unit also develops a system that promotes emotional empathy by combining emotion estimation and display of related content. For example, the content to be displayed is adjusted according to the user's emotion. This makes it possible to preferentially display related content according to the user's emotion, thereby promoting emotional empathy.

[0069] The system according to the embodiment is not limited to the above-described example, and various modifications are possible, for example, as follows.

[0070] The entertainment system may further include a biometric information acquisition unit that acquires biometric information of the user. For example, the biometric information acquisition unit may measure the user's heart rate or electrodermal response to estimate the user's level of excitement or relaxation. The biometric information acquisition unit may also adjust the operation of the system based on the user's biometric information. For example, if the user is excited, the system may provide more action scenes, and if the user is relaxed, the system may provide more calm scenes. This enables a personalized entertainment experience based on the user's biometric information.

[0071] The entertainment system may further include an eye-tracking unit that tracks the user's gaze. For example, the system may analyze in real time which part of the screen the user is looking at and identify characters or scenes of interest. The eye-tracking unit may also adjust the system's operation based on the user's gaze. For example, if the user is paying attention to a particular character, the system may prioritize displaying information or scenes related to that character. This enables an interactive entertainment experience based on the user's gaze.

[0072] The entertainment system may further include a gesture recognition unit that recognizes user gestures. For example, a camera may detect a user's gestures, such as waving or pointing, and reflect the detected gestures in the system. The gesture recognition unit may also adjust the system's behavior based on the user's gestures. For example, when a user performs a specific gesture, a character may perform an action corresponding to the gesture. This allows for an interactive entertainment experience based on the user's gestures.

[0073] The entertainment system may further include a voice recognition unit that recognizes user voice commands. For example, when a user issues a voice command such as "go to the next scene" or "change character," the system recognizes the command and performs the corresponding action. The voice recognition unit may also adjust the system's operation based on the user's voice command. For example, when a user calls out the name of a specific character, that character will appear on the screen. This allows for an interactive entertainment experience based on the user's voice commands.

[0074] The entertainment system may further include an emotion estimation unit that estimates the user's emotion and adjusts the system's operation based on the estimated emotion. For example, the emotion estimation unit may analyze the user's facial expression and tone of voice to estimate emotions such as joy, sadness, and anger. The emotion estimation unit may also adjust the system's operation based on the estimated emotion. For example, if the user is sad, an encouraging message may be displayed, and if the user is happy, a congratulatory message may be displayed. This enables a personalized entertainment experience based on the user's emotion.

[0075] The entertainment system can further estimate the user's emotions and adjust the character's behavior based on those emotions. For example, the system can analyze the user's facial expressions and tone of voice to estimate emotions. The system can also adjust the character's behavior based on the estimated emotions. For example, if the user is angry, the character may take a comforting action, and if the user is happy, the character may take a joyful action to share the user's joy. This enables an interactive entertainment experience based on the user's emotions.

[0076] The entertainment system can further estimate the user's emotion and adjust the music for the scene based on the estimated emotion. For example, the system can analyze the user's facial expression and voice tone to estimate the emotion. The system can also adjust the music for the scene based on the estimated emotion. For example, if the user is sad, soft music can be played, and if the user is excited, fast-paced music can be played. This makes it possible to adjust the music based on the user's emotion.

[0077] The entertainment system can further estimate the user's emotion and adjust the lighting of the scene based on the emotion. For example, the emotion can be estimated by analyzing the user's facial expression and tone of voice. The lighting of the scene can also be adjusted based on the estimated emotion. For example, soft lighting can be used when the user is relaxed, and bright lighting can be used when the user is excited. This makes it possible to adjust the lighting based on the user's emotion.

[0078] The entertainment system can further estimate the user's emotion and adjust the scene effects based on the estimated emotion. For example, the system can analyze the user's facial expression and voice tone to estimate the emotion. The system can also adjust the scene effects based on the estimated emotion. For example, if the user is surprised, the effects can be enhanced, and if the user is calm, the effects can be reduced. This makes it possible to adjust the effects based on the user's emotion.

[0079] The entertainment system can further estimate the user's emotions and adjust the narration of a scene based on the estimated emotions. For example, the system can analyze the user's facial expressions and voice tone to estimate the emotions. The system can also adjust the narration of a scene based on the estimated emotions. For example, if the user is sad, the narration can be performed in a gentle tone, and if the user is excited, the narration can be performed in a powerful tone. This makes it possible to adjust the narration based on the user's emotions.

[0080] The processing flow of the second embodiment will be briefly explained below.

[0081] Step 1: The speech-to-text unit converts speech into text. For example, it uses speech recognition technology to analyze the speech and generate corresponding text. The speech-to-text unit can also analyze the tone and speed of the speech to estimate emotions. For example, it can analyze the strength and rhythm of the speech to estimate the character's emotions. Step 2: The voice generation unit generates voice from the text. For example, it analyzes the text using speech synthesis technology and generates corresponding voice. The voice generation unit can also learn the character's past utterances and behavior patterns to generate consistent voice. For example, it can generate voice with the same tone and rhythm based on the character's past utterance data. Step 3: The visual generation unit generates new visual content. For example, it uses image generation technology to generate visual content based on user instructions. The visual generation unit can also estimate the character's emotions and adjust the color tone and composition of the scene based on those emotions. For example, if the character is sad, the scene's color tone can be darkened and the composition simplified. Step 4: The related content search unit searches for related text and images. For example, it uses the embedding function to search for related text and images and provides them to the user. The related content search unit can also prioritize displaying related content according to the user's emotions. For example, if the user is happy, it will prioritize displaying text and images that empathize with that emotion.

[0082] 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.

[0083] The data generation model 58 is a so-called generative AI (Artificial Intelligence). An example of the data generation model 58 is ChatGPT (registered trademark) (Internet search engine).<URL: https: / / openai.com / blog / chatgpt> Examples of generative AIs include the data generation model 58, such as a neural network model (e.g., a neural network model), and a neural network model (e.g., a neural network model). The data generation model 58 is obtained by performing deep learning on a neural network. A prompt including an instruction is input to the data generation model 58, and inference data such as voice data indicating speech, text data indicating text, and image data indicating an image is also input to the data generation model 58. The data generation model 58 performs inference on the input inference data in accordance with the instruction indicated by the prompt and outputs the inference result in a data format such as voice data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization. The specification processing unit 290 performs the above-mentioned specification processing using the data generation model 58. The data generation model 58 may be a fine-tuned model so as to output an inference result from a prompt that does not include an instruction. In this case, the data generation model 58 can output an inference result from a prompt that does not include an instruction. The data processing device 12 and the like include multiple types of data generation models 58, and the data generation model 58 includes AIs other than the generative AI. The AI ​​other than the generative AI may be, for example, linear regression, logistic regression, decision tree, random forest, support vector machine (SVM), k-means clustering, convolutional neural network (CNN), recurrent neural network (RNN), generative adversarial network (GAN), or naive Bayes, and can perform various processes, but is not limited to these examples. The AI ​​may also be an AI agent. When the processes of each of the above-mentioned parts are performed by AI, the processes may be performed in part or entirely by AI, but are not limited to these examples. The processes performed by AI, including the generative AI, may be replaced with rule-based processes.

[0084] 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.

[0085] [Second embodiment] FIG. 3 shows an example of the configuration of a data processing system 210 according to the second embodiment.

[0086] 3, the data processing system 210 includes a data processing device 12 and smart glasses 214. An example of the data processing device 12 is a server.

[0087] 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.

[0088] 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.

[0089] 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.

[0090] 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).

[0091] 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.

[0092] 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.

[0093] 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.

[0094] The storage 32 stores a data generation model 58 and an emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290. The identification processing unit 290 can estimate a user's emotion using the emotion identification model 59 and perform identification processing using the user's emotion. The emotion estimation function (emotion identification function) using the emotion identification model 59 performs various estimations and predictions regarding the user's emotion, including estimation and prediction of the user's emotion, but is not limited to these examples. Furthermore, the estimation and prediction of emotion also includes, for example, emotion analysis.

[0095] In the smart glasses 214, the specific processing is performed by the processor 46. A specific processing program 60 is stored in the storage 50. The processor 46 reads the specific processing program 60 from the storage 50 and executes the read specific processing program 60 on the RAM 48. The specific processing is realized by the processor 46 operating as the control unit 46A in accordance with the specific processing program 60 executed on the RAM 48. The smart glasses 214 also have a data generation model and an emotion identification model similar to the data generation model 58 and the emotion identification model 59, and can perform processing similar to that of the specific processing unit 290 using these models.

[0096] 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.

[0097] 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.

[0098] 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 AI 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.

[0099] 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.

[0100] [Third embodiment] FIG. 5 shows an example of the configuration of a data processing system 310 according to the third embodiment.

[0101] 5, the data processing system 310 includes the data processing device 12 and a headset terminal 314. An example of the data processing device 12 is a server.

[0102] 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.

[0103] 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.

[0104] 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.

[0105] 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).

[0106] 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.

[0107] Fig. 6 shows an example of the main functions of the data processing device 12 and the headset 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.

[0108] 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.

[0109] The storage 32 stores a data generation model 58 and an emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290. The identification processing unit 290 can estimate a user's emotion using the emotion identification model 59 and perform identification processing using the user's emotion. The emotion estimation function (emotion identification function) using the emotion identification model 59 performs various estimations and predictions regarding the user's emotion, including estimation and prediction of the user's emotion, but is not limited to these examples. Furthermore, the estimation and prediction of emotion also includes, for example, emotion analysis.

[0110] In the headset type terminal 314, 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 headset type terminal 314 has a data generation model and an emotion identification model similar to the data generation model 58 and the emotion identification model 59, and can also perform processing similar to that of the specific processing unit 290 using these models.

[0111] 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.

[0112] 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.

[0113] 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 AI 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.

[0114] 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.

[0115] [Fourth embodiment] FIG. 7 shows an example of the configuration of a data processing system 410 according to the fourth embodiment.

[0116] 7, a 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.

[0117] 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.

[0118] 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.

[0119] 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.

[0120] 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).

[0121] 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.

[0122] 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.

[0123] 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.

[0124] 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.

[0125] The storage 32 stores a data generation model 58 and an emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290. The identification processing unit 290 can estimate a user's emotion using the emotion identification model 59 and perform identification processing using the user's emotion. The emotion estimation function (emotion identification function) using the emotion identification model 59 performs various estimations and predictions regarding the user's emotion, including estimation and prediction of the user's emotion, but is not limited to these examples. Furthermore, the estimation and prediction of emotion also includes, for example, emotion analysis.

[0126] In the robot 414, the specific processing is performed by the processor 46. A specific processing program 60 is stored in the storage 50. The processor 46 reads the specific processing program 60 from the storage 50 and executes the read specific processing program 60 on the RAM 48. The specific processing is realized by the processor 46 operating as the control unit 46A in accordance with the specific processing program 60 executed on the RAM 48. The robot 414 also has a data generation model and an emotion identification model similar to the data generation model 58 and the emotion identification model 59, and can perform processing similar to that of the specific processing unit 290 using these models.

[0127] 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.

[0128] 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.

[0129] 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 AI 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.

[0130] 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.

[0131] 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.

[0132] 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.

[0133] 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.

[0134] 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).

[0135] 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.

[0136] 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."

[0137] 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.

[0138] 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.

[0139] 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.

[0140] 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.

[0141] 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.

[0142] 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.

[0143] 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.

[0144] 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.

[0145] 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.

[0146] 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.

[0147] 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, in order to avoid confusion and to 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.

[0148] 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]

[0149] 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 speech-to-text unit that converts speech into text; a speech generation unit that generates speech from the text converted by the speech-to-text unit; a visual generation unit that generates new visual content based on the audio generated by the audio generation unit; a related content search unit that searches for text or images related to the visual content generated by the visual generation unit. A system characterized by:

2. The speech-to-text unit When converting speech to text, the emotions of the characters are estimated and the expression of the text is adjusted based on those emotions.

2. The system of claim 1.

3. The voice generation unit When generating speech from text, it learns the character's past speech or behavior patterns to generate consistent speech.

2. The system of claim 1.

4. The voice generation unit Simultaneously converts speech to text and generates speech from text to generate character conversations in real time 2. The system of claim 1.

5. The speech-to-text unit and the speech generation unit Create multilingual characters by transcribing speech to text and generating speech from text across different languages 2. The system of claim 1.

Images