System

Abstract

An object of a system according to an embodiment is to efficiently generate and correct a moving image based on a sentence input by a user and a live-action moving image.SOLUTION: A system includes a sentence analysis part, a moving image generation part, an animation part, and a correction part. The sentence analysis unit analyzes a sentence input by a user. The moving image generation unit generates a moving image based on the content analyzed by the text analysis unit. The animation unit animates the live-action video input by the user. The correction unit corrects the generated moving image.SELECTED DRAWING: Figure 1

Description

[Technical Field]

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

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

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

[0004] With conventional technology, the process of generating and modifying videos based on user-entered text and live-action videos was complicated, making it difficult to carry out efficiently.

[0005] The system according to the embodiment aims to efficiently generate and edit videos based on text and live-action videos input by the user. [Means for solving the problem]

[0006] The system according to the embodiment includes a text analysis unit, a video generation unit, an animation unit, and a correction unit. The text analysis unit analyzes text input by a user. The video generation unit generates video based on the content analyzed by the text analysis unit. The animation unit animates live-action video input by the user. The correction unit corrects the generated video. [Effects of the Invention]

[0007] The system according to the embodiment can efficiently generate and edit videos based on text and live-action videos input by the user. [Brief explanation of the drawings]

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

[0028] (Example 1) The video creation support platform according to the embodiment of the present invention is a system that generates a video according to a text-based video that a user wants to create. This allows the video creation support platform to enable users to easily create high-quality videos.

[0029] A video creation support platform according to an embodiment includes a text analysis unit, a video generation unit, an animation unit, and a correction unit. The text analysis unit analyzes text entered by a user. For example, the text analysis unit breaks down a text using morphological analysis and performs grammatical analysis. The text analysis unit can also understand the content of the text using semantic analysis. For example, morphological analysis breaks down a text into words and identifies the part of speech of each word. Grammatical analysis analyzes the structure of the text and clarifies relationships such as between subjects and predicates. Semantic analysis understands the meaning of the text and provides an appropriate interpretation based on the context. The video generation unit generates a video based on the content analyzed by the text analysis unit. For example, the video generation unit uses a generation AI to generate a video that matches the content of the text. The video generation unit can also collect related images and audio from the Internet and incorporate them into the video. For example, the generation AI converts the content of the text into a video using a text generation AI (e.g., LLM). The images and audio collected from the Internet are applied to scenes in the video. The animation unit animates a live-action video entered by a user. For example, the animation unit analyzes the movement of live-action video and improves the smoothness of the movement when animating. The animation unit can also automatically animate the background of the live-action video to enhance the sense of unity between the character and the background. For example, frame interpolation is performed to improve the smoothness of the movement. Background animation reproduces the movement of the background and creates a sense of unity with the character. The correction unit corrects the generated video. For example, the correction unit analyzes a user's correction instructions in real time and immediately reflects them in the video. The correction unit can also automatically generate multiple correction suggestions using the generation AI based on the correction instructions and provide the user with options. For example, real-time analysis instantly updates the video upon receiving the correction instructions. The generation AI automatically generates multiple correction suggestions and presents them to the user. This allows the video creation support platform according to the embodiment to easily create high-quality videos. For example, a user can generate specific scenes using text-based instructions and use the video as reference material to create videos that reflect more specific images.You can also create your own animated videos by animating live-action videos, and the editing function in the UI allows you to fine-tune the generated videos.

[0030] The video generation unit automatically generates multiple scenes based on the content of the text and can perform natural transitions between the scenes. The video generation unit, for example, analyzes the content of the text and automatically generates multiple scenes. For example, it divides scenes according to the progress of the story and generates each scene. The video generation unit can also apply effects such as fade-in and fade-out to perform natural transitions between scenes. For example, it can perform a fade-in when switching scenes, and transition to the next scene naturally. This allows the generation of multiple scenes based on the content of the text and the performance of natural transitions between scenes.

[0031] The video generation unit can automatically collect relevant images and sounds from the internet in response to text-based instructions using the generation AI and incorporate them into the video. For example, the video generation unit automatically collects relevant images from the internet based on the content of the text and incorporates them into the video. For example, when generating a beach scene, images of the ocean are collected. The video generation unit can also automatically collect relevant sounds from the internet based on the content of the text and incorporate them into the video. For example, for a beach scene, the sound of waves is collected and inserted into the video. This makes it possible to automatically collect relevant images and sounds based on text-based instructions and incorporate them into the video.

[0032] The video generation unit can generate video from different viewpoints based on the content of the text, creating a multi-angle video. The video generation unit, for example, analyzes the content of the text and automatically generates video from different viewpoints. For example, it creates video that looks like the same scene was shot from multiple camera angles. The video generation unit can also perform natural transitions between viewpoints to create a multi-angle video. For example, it performs smooth transitions when switching viewpoints, creating a sense of realism. This allows video from different viewpoints to be generated based on the content of the text, creating a multi-angle video.

[0033] The video generation unit can analyze the style and color tone of the reference video and apply the same style and color tone to the new video. For example, the video generation unit uses a generation AI to analyze the style of the reference video and apply the same style to the new video. For example, it can reflect a specific animation style in the new video. The video generation unit can also analyze the color tone of the reference video and apply the same color tone to the new video. For example, it can reflect a specific color palette in the new video. This allows the style and color tone of the reference video to be applied to the new video.

[0034] The video generation unit can analyze the movements and camerawork of the reference video and reproduce similar movements and camerawork in the new video. The video generation unit, for example, analyzes the movements of the reference video and reproduces similar movements in the new video. For example, it imitates the movements of characters or the movements of action scenes. The video generation unit can also analyze the camerawork of the reference video and reproduce similar camerawork in the new video. For example, it applies camerawork such as panning and zooming to the new video. This allows the movements and camerawork of the reference video to be reproduced in the new video.

[0035] The video generation unit can analyze the audio and music of the reference video and apply the same audio and music to the new video. For example, the video generation unit can analyze the audio of the reference video and apply the same audio to the new video. For example, the video generation unit can reflect narration and sound effects in the new video. The video generation unit can also analyze the music of the reference video and apply the same music to the new video. For example, the video generation unit can reflect specific background music in the new video. This allows the audio and music of the reference video to be applied to the new video.

[0036] The video generation unit can reuse scenes by cutting out specific scenes from the reference video and incorporating them into the new video. The video generation unit, for example, cuts out specific scenes from the reference video and incorporates them into the new video. For example, specific action scenes or landscape scenes are reused. The video generation unit can also perform natural scene transitions when reusing scenes. For example, a fade-in or fade-out can be performed when switching scenes to achieve a natural transition. This allows specific scenes from the reference video to be reused in the new video.

[0037] The animation unit can analyze the movement of live-action video and improve the smoothness of the movement when animating. The animation unit can, for example, analyze the movement of live-action video and improve the smoothness of the movement when animating. For example, it can perform interpolation between frames to achieve smooth movement. The animation unit can also fine-tune the movement of a character to maintain naturalness of the movement. For example, it can apply an interpolation algorithm to make the movement of a character's joints natural. This can improve the smoothness of the movement when analyzing the movement of live-action video and animating.

[0038] The animation unit can automatically animate the background of the live-action video to enhance the sense of unity between the character and the background. The animation unit, for example, analyzes the background of the live-action video and automatically animates it. For example, it reproduces the movement of the background to create a sense of unity with the character. The animation unit can also finely adjust the details of the background. For example, it animates the color tone and texture of the background to enhance the sense of unity with the character. In this way, the background of the live-action video can be animated to enhance the sense of unity between the character and the background.

[0039] The animation unit can achieve partial animation by cutting out specific parts of live-action video and animating only those parts. The animation unit can, for example, cut out specific parts of live-action video and animate only those parts. For example, it can animate only the movements of a character and leave the background as live-action. The animation unit can also finely adjust the range of the animation when performing partial animation. For example, it can animate only part of the movements of a character and leave the other parts as live-action. In this way, it is possible to animate specific parts of live-action video and achieve partial animation.

[0040] The animation unit can analyze the audio of live-action video and automatically generate lip sync that matches the audio when animating. The animation unit, for example, analyzes the audio of live-action video and automatically generates lip sync that matches the audio when animating. For example, it reproduces the mouth movements of a character in accordance with the audio. The animation unit can also apply an audio analysis algorithm to improve the accuracy of the lip sync. For example, it analyzes the waveform of the audio and fine-tunes the mouth movements. This makes it possible to automatically generate lip sync that matches the audio of the live-action video.

[0041] The correction unit can analyze the user's correction instructions in real time and instantly reflect them in the video. For example, the correction unit can analyze the user's correction instructions input from the UI in real time and instantly reflect them in the video. For example, upon receiving an instruction to change the position of a character, the correction unit can instantly update the video. The correction unit can also apply an analysis algorithm to improve the accuracy of the real-time analysis. For example, a high-speed analysis algorithm can be used to minimize the delay time of the correction instructions. This allows the user's correction instructions to be analyzed in real time and instantly reflected in the video.

[0042] The correction unit can have the generation AI automatically generate multiple correction suggestions based on the correction instructions and provide the user with options. The correction unit can, for example, have the generation AI automatically generate multiple correction suggestions based on the user's correction instructions and provide the user with options. For example, the correction unit can present multiple suggestions for changing the position of a character. The correction unit can also set evaluation criteria for the correction suggestions and select the optimal one. For example, the evaluation criteria for the correction suggestions can take into account visual beauty and story consistency. This makes it possible to generate multiple correction suggestions based on the correction instructions and provide the user with options.

[0043] When a user selects a part they want to modify, the correction unit can automatically correct other scenes related to that part. For example, when a user selects a part they want to modify, the generation AI automatically corrects other scenes related to that part. For example, when a character's clothing is changed, the same change is applied to other scenes. The correction unit can also set a method for identifying related scenes and fine-tune the scope of correction. For example, the frequency of character appearances and the continuity of scenes can be considered as criteria for scene relevance. This allows when a user selects a part they want to modify, other scenes related to that part can also be automatically corrected.

[0044] The correction unit allows the generation AI to automatically suggest relevant effects and filters based on the correction instructions and apply them to the video. For example, the correction unit may suggest effects that are suitable for a particular scene. The correction unit may also set how effects and filters are applied to improve the quality of the video. For example, the correction unit may fine-tune the strength of an effect or the type of filter. This allows the generation AI to automatically suggest relevant effects and filters based on the correction instructions and apply them to the video.

[0045] The system according to the embodiment is not limited to the above-described example, and various modifications are possible, for example, as follows.

[0046] The video creation support platform can provide interactive feedback on video scenes based on text entered by the user. For example, if a user requests a detailed explanation of a particular scene, the system can provide additional information and background related to that scene. Also, if a user requests a scene change, the system can show in real time how the change will affect other scenes. Furthermore, if a user requests a scene change, the system can visually show how the change will affect the narrative flow. This allows users to more effectively manage video scenes and create optimal videos.

[0047] The video creation support platform can provide audio descriptions for video scenes based on text entered by the user. For example, the system can automatically generate narration for each scene to help users better understand the content of the scene. The system can also automatically select background sounds and sound effects to enhance the scene's atmosphere. Furthermore, if the user requests additional audio descriptions for a particular scene, the system can generate audio descriptions according to the user's request. This allows users to create videos that are both visually and aurally appealing.

[0048] The video creation support platform can add interactive elements to video scenes based on text entered by users. For example, users can add quizzes or surveys to specific scenes to allow viewers to provide feedback on the scene. Users can also add links or buttons to scenes to allow viewers to access related information. Furthermore, users can add comments or notes to scenes to allow viewers to share their opinions or thoughts about the scene. This allows users to increase interaction with viewers and create more engaging videos.

[0049] The video creation support platform can provide real-time feedback on video scenes based on text entered by the user. For example, the system can collect viewer reactions to each scene in real time and provide feedback to the user. The system can also automatically adjust the content of a scene based on the viewer's reactions to keep the viewer engaged. Furthermore, if the user requests a scene change, the system can show in real time how the change will affect viewer reactions. This allows the user to create the optimal video while taking viewer reactions into consideration.

[0050] The video creation support platform can automatically apply visual styles to video scenes based on text entered by the user. For example, the system can apply different art styles to each scene to create a visually appealing video. The system can also automatically select color tones and filters based on the content of a scene to enhance its atmosphere. Furthermore, if a user desires a specific style, the system can generate scenes based on that style. This allows users to easily create visually consistent videos.

[0051] The video creation support platform can provide interactive navigation for video scenes based on text entered by the user. For example, the user can set chapters for specific scenes, allowing viewers to jump directly to those scenes. The user can also add menus and submenus to scenes, allowing viewers to easily move between scenes. Furthermore, the user can add interactive maps to scenes, allowing viewers to visually understand the relative locations of scenes. This allows users to create videos that are easy for viewers to use.

[0052] The processing flow of the first embodiment will be briefly explained below.

[0053] Step 1: The text analysis unit analyzes the text entered by the user. For example, it uses morphological analysis to break down the text and perform grammatical analysis. It can also use semantic analysis to understand the content of the text. Morphological analysis breaks down the text into words and identifies the part of speech of each word. Grammatical analysis analyzes the structure of the text and clarifies relationships such as subject and predicate. Semantic analysis understands the meaning of the text and provides an appropriate interpretation based on the context. Step 2: The video generation unit generates a video based on the content analyzed by the text analysis unit. For example, a generation AI is used to generate a video that matches the content of the text. It can also collect related images and audio from the Internet and incorporate them into the video. The generation AI uses a text generation AI (e.g., LLM) to convert the content of the text into a video. The images and audio collected from the Internet are applied to the video scenes. Step 3: The animation unit animates the live-action video input by the user. For example, it analyzes the movement of the live-action video and improves the smoothness of the movement when animating. It can also automatically animate the background of the live-action video to enhance the sense of unity between the character and the background. Interpolation is performed between frames to improve the smoothness of the movement. The background animation reproduces the movement of the background, creating a sense of unity with the character. Step 4: The correction unit corrects the generated video. For example, it analyzes the user's correction instructions in real time and immediately reflects them in the video. The generation AI can also automatically generate multiple correction suggestions based on the correction instructions and provide the user with options. Real-time analysis updates the video immediately upon receiving the correction instructions. Multiple correction suggestions are automatically generated by the generation AI and presented to the user.

[0054] (Example 2) The video creation support platform according to the embodiment of the present invention is a system that generates a video according to a text-based video that a user wants to create. This allows the video creation support platform to enable users to easily create high-quality videos.

[0055] A video creation support platform according to an embodiment includes a text analysis unit, a video generation unit, an animation unit, and a correction unit. The text analysis unit analyzes text entered by a user. For example, the text analysis unit breaks down a text using morphological analysis and performs grammatical analysis. The text analysis unit can also understand the content of the text using semantic analysis. For example, morphological analysis breaks down a text into words and identifies the part of speech of each word. Grammatical analysis analyzes the structure of the text and clarifies relationships such as between subjects and predicates. Semantic analysis understands the meaning of the text and provides an appropriate interpretation based on the context. The video generation unit generates a video based on the content analyzed by the text analysis unit. For example, the video generation unit uses a generation AI to generate a video that matches the content of the text. The video generation unit can also collect related images and audio from the Internet and incorporate them into the video. For example, the generation AI converts the content of the text into a video using a text generation AI (e.g., LLM). The images and audio collected from the Internet are applied to scenes in the video. The animation unit animates a live-action video entered by a user. For example, the animation unit analyzes the movement of live-action video and improves the smoothness of the movement when animating. The animation unit can also automatically animate the background of the live-action video to enhance the sense of unity between the character and the background. For example, frame interpolation is performed to improve the smoothness of the movement. Background animation reproduces the movement of the background and creates a sense of unity with the character. The correction unit corrects the generated video. For example, the correction unit analyzes a user's correction instructions in real time and immediately reflects them in the video. The correction unit can also automatically generate multiple correction suggestions using the generation AI based on the correction instructions and provide the user with options. For example, real-time analysis instantly updates the video upon receiving the correction instructions. The generation AI automatically generates multiple correction suggestions and presents them to the user. This allows the video creation support platform according to the embodiment to easily create high-quality videos. For example, a user can generate specific scenes using text-based instructions and use the video as reference material to create videos that reflect more specific images.You can also create your own animated videos by animating live-action videos, and the editing function in the UI allows you to fine-tune the generated videos.

[0056] The text analysis unit can analyze the emotional tone of text and automatically add visual effects according to the emotion. The text analysis unit, for example, analyzes the emotional tone of text entered by a user and automatically adjusts the color tone according to the emotion. For example, it applies a bluish color tone to sad scenes and a bright color tone to happy scenes. The text analysis unit can also automatically select music based on the emotional tone and insert it into the video. For example, it applies emotional music to moving scenes and tense music to tense scenes. In this way, visual effects can be automatically added based on the emotional tone of the text.

[0057] The video generation unit automatically generates multiple scenes based on the content of the text and can perform natural transitions between the scenes. The video generation unit, for example, analyzes the content of the text and automatically generates multiple scenes. For example, it divides scenes according to the progress of the story and generates each scene. The video generation unit can also apply effects such as fade-in and fade-out to perform natural transitions between scenes. For example, it can perform a fade-in when switching scenes, and transition to the next scene naturally. This allows the generation of multiple scenes based on the content of the text and the performance of natural transitions between scenes.

[0058] The video generation unit can use the emotion estimation function to analyze the emotion of a sentence and generate a scene that best suits that emotion. For example, the video generation unit uses the emotion estimation function to analyze the emotion of a sentence input by a user and automatically generate a scene that best suits that emotion. For example, it generates an emotional scene for an emotional sentence, and generates a tense scene for a tense sentence. The video generation unit can also use the emotion estimation function to select characters and backgrounds for a scene. For example, it applies emotional characters and backgrounds to an emotional scene. This makes it possible to generate an optimal scene based on the emotion of the sentence.

[0059] The video generation unit can automatically collect relevant images and sounds from the internet in response to text-based instructions using the generation AI and incorporate them into the video. For example, the video generation unit automatically collects relevant images from the internet based on the content of the text and incorporates them into the video. For example, when generating a beach scene, images of the ocean are collected. The video generation unit can also automatically collect relevant sounds from the internet based on the content of the text and incorporate them into the video. For example, for a beach scene, the sound of waves is collected and inserted into the video. This makes it possible to automatically collect relevant images and sounds based on text-based instructions and incorporate them into the video.

[0060] The video generation unit can generate video from different viewpoints based on the content of the text, creating a multi-angle video. The video generation unit, for example, analyzes the content of the text and automatically generates video from different viewpoints. For example, it creates video that looks like the same scene was shot from multiple camera angles. The video generation unit can also perform natural transitions between viewpoints to create a multi-angle video. For example, it performs smooth transitions when switching viewpoints, creating a sense of realism. This allows video from different viewpoints to be generated based on the content of the text, creating a multi-angle video.

[0061] The video generation unit can use the emotion estimation function to generate different variations of emotional tone based on the emotion of the text. For example, the video generation unit uses the emotion estimation function to generate different variations of emotional tone based on the emotion of the text input by the user. For example, the same scene is expressed in different emotional tones. The video generation unit can also change the color tone and music based on the emotional tone. For example, soft color tones and emotional music are applied to an emotional scene, and dark color tones and tense music are applied to a tense scene. In this way, different variations of emotional tone can be generated based on the emotion of the text.

[0062] The video generation unit can analyze the style and color tone of the reference video and apply the same style and color tone to the new video. For example, the video generation unit uses a generation AI to analyze the style of the reference video and apply the same style to the new video. For example, it can reflect a specific animation style in the new video. The video generation unit can also analyze the color tone of the reference video and apply the same color tone to the new video. For example, it can reflect a specific color palette in the new video. This allows the style and color tone of the reference video to be applied to the new video.

[0063] The video generation unit can analyze the movements and camerawork of the reference video and reproduce similar movements and camerawork in the new video. The video generation unit, for example, analyzes the movements of the reference video and reproduces similar movements in the new video. For example, it imitates the movements of characters or the movements of action scenes. The video generation unit can also analyze the camerawork of the reference video and reproduce similar camerawork in the new video. For example, it applies camerawork such as panning and zooming to the new video. This allows the movements and camerawork of the reference video to be reproduced in the new video.

[0064] The video generation unit can use the emotion estimation function to analyze the emotional tone of the reference video and reflect the same emotional tone in the new video. For example, the video generation unit can use the emotion estimation function to analyze the emotional tone of the reference video and reflect the same emotional tone in the new video. For example, based on an emotional reference video, a new video can be generated with an emotional tone. The video generation unit can also change the color tone and music based on the emotional tone. For example, soft color tones and emotional music can be applied to an emotional scene, and dark color tones and tense music can be applied to a tense scene. In this way, the emotional tone of the reference video can be reflected in the new video.

[0065] The video generation unit can analyze the audio and music of the reference video and apply the same audio and music to the new video. For example, the video generation unit can analyze the audio of the reference video and apply the same audio to the new video. For example, the video generation unit can reflect narration and sound effects in the new video. The video generation unit can also analyze the music of the reference video and apply the same music to the new video. For example, the video generation unit can reflect specific background music in the new video. This allows the audio and music of the reference video to be applied to the new video.

[0066] The video generation unit can reuse scenes by cutting out specific scenes from the reference video and incorporating them into the new video. The video generation unit, for example, cuts out specific scenes from the reference video and incorporates them into the new video. For example, specific action scenes or landscape scenes are reused. The video generation unit can also perform natural scene transitions when reusing scenes. For example, a fade-in or fade-out can be performed when switching scenes to achieve a natural transition. This allows specific scenes from the reference video to be reused in the new video.

[0067] The video generation unit can use the emotion estimation function to optimize the scene composition of the new video based on the emotional tone of the reference video. For example, the video generation unit uses the emotion estimation function to analyze the emotional tone of the reference video and optimize the scene composition of the new video. For example, the video generation unit adjusts the order of scenes and transitions to emphasize moving scenes. The video generation unit can also perform natural transitions between scenes based on the emotional tone. For example, the video generation unit applies appropriate transitions before and after moving scenes to smooth the flow of emotions. This allows the scene composition of the new video to be optimized based on the emotional tone of the reference video.

[0068] The animation unit can analyze the movement of live-action video and improve the smoothness of the movement when animating. The animation unit can, for example, analyze the movement of live-action video and improve the smoothness of the movement when animating. For example, it can perform interpolation between frames to achieve smooth movement. The animation unit can also fine-tune the movement of a character to maintain naturalness of the movement. For example, it can apply an interpolation algorithm to make the movement of a character's joints natural. This can improve the smoothness of the movement when analyzing the movement of live-action video and animating.

[0069] The animation unit can automatically animate the background of the live-action video to enhance the sense of unity between the character and the background. The animation unit, for example, analyzes the background of the live-action video and automatically animates it. For example, it reproduces the movement of the background to create a sense of unity with the character. The animation unit can also finely adjust the details of the background. For example, it animates the color tone and texture of the background to enhance the sense of unity with the character. In this way, the background of the live-action video can be animated to enhance the sense of unity between the character and the background.

[0070] The animation unit can use the emotion estimation function to analyze the emotions of a character in a live-action video and emphasize the emotional expression when animating the character. For example, the animation unit can use the emotion estimation function to analyze the emotions of a character in a live-action video and emphasize the emotional expression when animating the character. For example, the animation unit can express emotions by emphasizing the character's facial expressions and movements. The animation unit can also apply color tones and effects to emphasize the emotional expression. For example, soft color tones and emotional effects can be applied to emotional scenes. This allows the animation unit to analyze the emotions of a character in a live-action video and emphasize the emotional expression when animating the character.

[0071] The animation unit can achieve partial animation by cutting out specific parts of live-action video and animating only those parts. The animation unit can, for example, cut out specific parts of live-action video and animate only those parts. For example, it can animate only the movements of a character and leave the background as live-action. The animation unit can also finely adjust the range of the animation when performing partial animation. For example, it can animate only part of the movements of a character and leave the other parts as live-action. In this way, it is possible to animate specific parts of live-action video and achieve partial animation.

[0072] The animation unit can analyze the audio of live-action video and automatically generate lip sync that matches the audio when animating. The animation unit, for example, analyzes the audio of live-action video and automatically generates lip sync that matches the audio when animating. For example, it reproduces the mouth movements of a character in accordance with the audio. The animation unit can also apply an audio analysis algorithm to improve the accuracy of the lip sync. For example, it analyzes the waveform of the audio and fine-tunes the mouth movements. This makes it possible to automatically generate lip sync that matches the audio of the live-action video.

[0073] The animation unit can use the emotion estimation function to change the style and color tone of the animation based on the emotion of the character in the live-action video. For example, the animation unit uses the emotion estimation function to analyze the emotion of the character in the live-action video and change the style of the animation based on the emotion. For example, a soft style is applied to an emotional scene. The animation unit can also change the color tone based on the emotion. For example, soft colors are applied to an emotional scene and dark colors are applied to a tense scene. In this way, the style and color tone of the animation can be changed based on the emotion of the character in the live-action video.

[0074] The correction unit can analyze the user's correction instructions in real time and instantly reflect them in the video. For example, the correction unit can analyze the user's correction instructions input from the UI in real time and instantly reflect them in the video. For example, upon receiving an instruction to change the position of a character, the correction unit can instantly update the video. The correction unit can also apply an analysis algorithm to improve the accuracy of the real-time analysis. For example, a high-speed analysis algorithm can be used to minimize the delay time of the correction instructions. This allows the user's correction instructions to be analyzed in real time and instantly reflected in the video.

[0075] The correction unit can have the generation AI automatically generate multiple correction suggestions based on the correction instructions and provide the user with options. The correction unit can, for example, have the generation AI automatically generate multiple correction suggestions based on the user's correction instructions and provide the user with options. For example, the correction unit can present multiple suggestions for changing the position of a character. The correction unit can also set evaluation criteria for the correction suggestions and select the optimal one. For example, the evaluation criteria for the correction suggestions can take into account visual beauty and story consistency. This makes it possible to generate multiple correction suggestions based on the correction instructions and provide the user with options.

[0076] The correction unit can use the emotion estimation function to analyze the emotion behind the user's correction instruction and make a correction that is most appropriate for that emotion. For example, the correction unit can use the emotion estimation function to analyze the emotion behind the user's correction instruction and make a correction that is most appropriate for that emotion. For example, if the user is feeling dissatisfied, the correction unit makes a correction that resolves that dissatisfaction. The correction unit can also apply an emotion estimation algorithm to improve the accuracy of the emotion analysis. For example, the correction unit can analyze the user's facial expressions and voice to accurately estimate the emotion. This makes it possible to analyze the emotion behind the user's correction instruction and make a correction that is most appropriate for that emotion.

[0077] When a user selects a part they want to modify, the correction unit can automatically correct other scenes related to that part. For example, when a user selects a part they want to modify, the generation AI automatically corrects other scenes related to that part. For example, when a character's clothing is changed, the same change is applied to other scenes. The correction unit can also set a method for identifying related scenes and fine-tune the scope of correction. For example, the frequency of character appearances and the continuity of scenes can be considered as criteria for scene relevance. This allows when a user selects a part they want to modify, other scenes related to that part can also be automatically corrected.

[0078] The correction unit allows the generation AI to automatically suggest relevant effects and filters based on the correction instructions and apply them to the video. For example, the correction unit may suggest effects that are suitable for a particular scene. The correction unit may also set how effects and filters are applied to improve the quality of the video. For example, the correction unit may fine-tune the strength of an effect or the type of filter. This allows the generation AI to automatically suggest relevant effects and filters based on the correction instructions and apply them to the video.

[0079] The modification unit can use the emotion estimation function to adjust the emotional tone of the entire video based on the user's modification instructions. The modification unit, for example, uses the emotion estimation function to adjust the emotional tone of the entire video based on the user's modification instructions. For example, if the user is looking for an emotional tone, the modification unit adjusts the overall color tone and music. The modification unit can also set a method for adjusting the emotional tone to maintain consistency in the video. For example, the modification unit adjusts the emotional tone so that changes occur naturally between scenes. This allows the emotional tone of the entire video to be adjusted based on the user's modification instructions.

[0080] The system according to the embodiment is not limited to the above-described example, and various modifications are possible, for example, as follows.

[0081] The video creation support platform can provide interactive feedback on video scenes based on text entered by the user. For example, if a user requests a detailed explanation of a particular scene, the system can provide additional information and background related to that scene. Also, if a user requests a scene change, the system can show in real time how the change will affect other scenes. Furthermore, if a user requests a scene change, the system can visually show how the change will affect the narrative flow. This allows users to more effectively manage video scenes and create optimal videos.

[0082] The video creation support platform can automatically add visual effects to video scenes based on the emotional tone of the text entered by the user. For example, rain and tear effects can be added to sad scenes, and fireworks and smiley faces can be added to happy scenes. It can also use dark colors and fast cuts for tense scenes and soft colors and slow motion for relaxed scenes. It can also adjust the facial expressions and movements of characters in a scene based on the emotional tone. This allows users to easily create emotionally rich videos.

[0083] The video creation support platform can provide audio descriptions for video scenes based on text entered by the user. For example, the system can automatically generate narration for each scene to help users better understand the content of the scene. The system can also automatically select background sounds and sound effects to enhance the scene's atmosphere. Furthermore, if the user requests additional audio descriptions for a particular scene, the system can generate audio descriptions according to the user's request. This allows users to create videos that are both visually and aurally appealing.

[0084] Using its emotion estimation function, the video creation support platform can automatically adjust the character's movements and facial expressions for video scenes based on the emotions in the text entered by the user. For example, a character can be made to shed tears in a touching scene, or to smile and bounce in a joyful scene. Additionally, a character can display nervous expressions and movements in a tense scene, and calm expressions and movements in a relaxed scene. Furthermore, the tone and speed of a character's voice can be adjusted based on the emotion. This allows users to easily create videos with expressive characters.

[0085] The video creation support platform can add interactive elements to video scenes based on text entered by users. For example, users can add quizzes or surveys to specific scenes to allow viewers to provide feedback on the scene. Users can also add links or buttons to scenes to allow viewers to access related information. Furthermore, users can add comments or notes to scenes to allow viewers to share their opinions or thoughts about the scene. This allows users to increase interaction with viewers and create more engaging videos.

[0086] The video creation support platform can provide real-time feedback on video scenes based on text entered by the user. For example, the system can collect viewer reactions to each scene in real time and provide feedback to the user. The system can also automatically adjust the content of a scene based on the viewer's reactions to keep the viewer engaged. Furthermore, if the user requests a scene change, the system can show in real time how the change will affect viewer reactions. This allows the user to create the optimal video while taking viewer reactions into consideration.

[0087] The video creation support platform uses its emotion estimation function to automatically select background music for video scenes based on the emotion of the text entered by the user. For example, it can apply moving music to moving scenes and tense music to tense scenes. It can also apply calm music to relaxing scenes and cheerful music to happy scenes. It can also adjust the tempo and volume of the music based on the emotion. This allows users to easily create videos with emotionally rich music.

[0088] The video creation support platform can automatically apply visual styles to video scenes based on text entered by the user. For example, the system can apply different art styles to each scene to create a visually appealing video. The system can also automatically select color tones and filters based on the content of a scene to enhance its atmosphere. Furthermore, if a user desires a specific style, the system can generate scenes based on that style. This allows users to easily create visually consistent videos.

[0089] Using its emotion estimation function, the video creation support platform can automatically apply effects to video scenes based on the emotions in the text entered by the user. For example, a soft light effect can be applied to an emotional scene, and a dark shadow effect to a tense scene. It can also apply a bright light effect to a happy scene, and a rain or tear effect to a sad scene. Furthermore, the intensity and duration of the effect can be adjusted based on the emotion. This allows users to easily create videos with richly emotional effects.

[0090] The video creation support platform can provide interactive navigation for video scenes based on text entered by the user. For example, the user can set chapters for specific scenes, allowing viewers to jump directly to those scenes. The user can also add menus and submenus to scenes, allowing viewers to easily move between scenes. Furthermore, the user can add interactive maps to scenes, allowing viewers to visually understand the relative locations of scenes. This allows users to create videos that are easy for viewers to use.

[0091] The processing flow of the second embodiment will be briefly explained below.

[0092] Step 1: The text analysis unit analyzes the text entered by the user. For example, it uses morphological analysis to break down the text and perform grammatical analysis. It can also use semantic analysis to understand the content of the text. Morphological analysis breaks down the text into words and identifies the part of speech of each word. Grammatical analysis analyzes the structure of the text and clarifies relationships such as subject and predicate. Semantic analysis understands the meaning of the text and provides an appropriate interpretation based on the context. Step 2: The video generation unit generates a video based on the content analyzed by the text analysis unit. For example, a generation AI is used to generate a video that matches the content of the text. It can also collect related images and audio from the Internet and incorporate them into the video. The generation AI uses a text generation AI (e.g., LLM) to convert the content of the text into a video. The images and audio collected from the Internet are applied to the video scenes. Step 3: The animation unit animates the live-action video input by the user. For example, it analyzes the movement of the live-action video and improves the smoothness of the movement when animating. It can also automatically animate the background of the live-action video to enhance the sense of unity between the character and the background. Interpolation is performed between frames to improve the smoothness of the movement. The background animation reproduces the movement of the background, creating a sense of unity with the character. Step 4: The correction unit corrects the generated video. For example, it analyzes the user's correction instructions in real time and immediately reflects them in the video. The generation AI can also automatically generate multiple correction suggestions based on the correction instructions and provide the user with options. Real-time analysis updates the video immediately upon receiving the correction instructions. Multiple correction suggestions are automatically generated by the generation AI and presented to the user.

[0093] 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.

[0094] The data generation model 58 is a so-called generative AI (Artificial Intelligence). An example of the data generation model 58 is ChatGPT (Internet Search<URL: https: / / openai.com / blog / chatgpt> Examples of generative AIs include the data generation model 58, such as a neural network model (e.g., a neural network model), and a neural network model (e.g., a neural network model). The data generation model 58 is obtained by performing deep learning on a neural network. A prompt including an instruction is input to the data generation model 58, and inference data such as voice data indicating speech, text data indicating text, and image data indicating an image is also input to the data generation model 58. The data generation model 58 performs inference on the input inference data in accordance with the instruction indicated by the prompt and outputs the inference result in a data format such as voice data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization. The specification processing unit 290 performs the above-mentioned specification processing using the data generation model 58. The data generation model 58 may be a fine-tuned model so as to output an inference result from a prompt that does not include an instruction. In this case, the data generation model 58 can output an inference result from a prompt that does not include an instruction. The data processing device 12 and the like include multiple types of data generation models 58, and the data generation model 58 includes AIs other than the generative AI. The AI ​​other than the generative AI may be, for example, linear regression, logistic regression, decision tree, random forest, support vector machine (SVM), k-means clustering, convolutional neural network (CNN), recurrent neural network (RNN), generative adversarial network (GAN), or naive Bayes, and can perform various processes, but is not limited to these examples. The AI ​​may also be an AI agent. When the processes of each of the above-mentioned parts are performed by AI, the processes may be performed in part or entirely by AI, but are not limited to these examples. The processes performed by AI, including the generative AI, may be replaced with rule-based processes.

[0095] 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.

[0096] [Second embodiment] FIG. 3 shows an example of the configuration of a data processing system 210 according to the second embodiment.

[0097] 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.

[0098] 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.

[0099] 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.

[0100] 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.

[0101] 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).

[0102] 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.

[0103] 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.

[0104] 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.

[0105] The storage 32 stores a data generation model 58 and an emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290. The identification processing unit 290 can estimate the user's emotion using the emotion identification model 59 and perform identification processing using the user's emotion.

[0106] In the smart glasses 214, the specific processing is performed by the processor 46. A specific processing program 60 is stored in the storage 50. The processor 46 reads the specific processing program 60 from the storage 50 and executes the read specific processing program 60 on the RAM 48. The specific processing is realized by the processor 46 operating as the control unit 46A in accordance with the specific processing program 60 executed on the RAM 48. Note that the smart glasses 214 may have a data generation model and an emotion identification model similar to the data generation model 58 and the emotion identification model 59.

[0107] 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.

[0108] 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.

[0109] The data generation model 58 is a so-called generative AI. An example of the data generation model 58 is a generative AI such as ChatGPT. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 receives a prompt containing an instruction, as well as inference data such as voice data representing speech, text data representing text, and image data representing an image. The data generation model 58 performs inference on the input inference data in accordance with the instruction indicated by the prompt and outputs the inference result in a data format such as voice data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization. The identification processing unit 290 performs the above-mentioned identification processing using the data generation model 58. The data generation model 58 may be a fine-tuned model so as to output an inference result from a prompt that does not include an instruction. In this case, the data generation model 58 can output an inference result from a prompt that does not include an instruction. The data processing device 12 and the like include multiple types of data generation models 58, and the data generation model 58 includes AIs other than the generative AI. The AI ​​other than the generative AI may be, for example, linear regression, logistic regression, decision tree, random forest, support vector machine (SVM), k-means clustering, convolutional neural network (CNN), recurrent neural network (RNN), generative adversarial network (GAN), or naive Bayes, and can perform various processes, but is not limited to these examples. The AI ​​may also be an AI agent. When the processes of each of the above-mentioned parts are performed by AI, the processes may be performed in part or entirely by AI, but are not limited to these examples. The processes performed by AI, including the generative AI, may be replaced with rule-based processes.

[0110] 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.

[0111] [Third embodiment] FIG. 5 shows an example of the configuration of a data processing system 310 according to the third embodiment.

[0112] 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.

[0113] 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.

[0114] 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.

[0115] 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.

[0116] 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).

[0117] 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.

[0118] 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.

[0119] 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.

[0120] The storage 32 stores a data generation model 58 and an emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290. The identification processing unit 290 can estimate the user's emotion using the emotion identification model 59 and perform identification processing using the user's emotion.

[0121] In the headset type terminal 314, the identification process is performed by the processor 46. A identification program 60 is stored in the storage 50. The processor 46 reads the identification program 60 from the storage 50 and executes the read identification program 60 on the RAM 48. The identification process is realized by the processor 46 operating as a control unit 46A in accordance with the identification program 60 executed on the RAM 48. Note that the headset type terminal 314 may also have a data generation model and an emotion identification model similar to the data generation model 58 and the emotion identification model 59.

[0122] 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.

[0123] 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.

[0124] The data generation model 58 is a so-called generative AI. An example of the data generation model 58 is a generative AI such as ChatGPT. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 receives a prompt containing an instruction, as well as inference data such as voice data representing speech, text data representing text, and image data representing an image. The data generation model 58 performs inference on the input inference data in accordance with the instruction indicated by the prompt and outputs the inference result in a data format such as voice data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization. The identification processing unit 290 performs the above-mentioned identification processing using the data generation model 58. The data generation model 58 may be a fine-tuned model so as to output an inference result from a prompt that does not include an instruction. In this case, the data generation model 58 can output an inference result from a prompt that does not include an instruction. The data processing device 12 and the like include multiple types of data generation models 58, and the data generation model 58 includes AIs other than the generative AI. The AI ​​other than the generative AI may be, for example, linear regression, logistic regression, decision tree, random forest, support vector machine (SVM), k-means clustering, convolutional neural network (CNN), recurrent neural network (RNN), generative adversarial network (GAN), or naive Bayes, and can perform various processes, but is not limited to these examples. The AI ​​may also be an AI agent. When the processes of each of the above-mentioned parts are performed by AI, the processes may be performed in part or entirely by AI, but are not limited to these examples. The processes performed by AI, including the generative AI, may be replaced with rule-based processes.

[0125] 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.

[0126] [Fourth embodiment] FIG. 7 shows an example of the configuration of a data processing system 410 according to the fourth embodiment.

[0127] 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.

[0128] 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.

[0129] 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.

[0130] 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.

[0131] 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).

[0132] 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.

[0133] 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.

[0134] 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.

[0135] 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.

[0136] The storage 32 stores a data generation model 58 and an emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290. The identification processing unit 290 can estimate the user's emotion using the emotion identification model 59 and perform identification processing using the user's emotion.

[0137] In the robot 414, the processor 46 performs the identification process. A identification program 60 is stored in the storage 50. The processor 46 reads the identification program 60 from the storage 50 and executes the read identification program 60 on the RAM 48. The identification process is realized by the processor 46 operating as a control unit 46A in accordance with the identification program 60 executed on the RAM 48. The robot 414 may have a data generation model and an emotion identification model similar to the data generation model 58 and the emotion identification model 59.

[0138] 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.

[0139] 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.

[0140] The data generation model 58 is a so-called generative AI. An example of the data generation model 58 is a generative AI such as ChatGPT. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 receives a prompt containing an instruction, as well as inference data such as voice data representing speech, text data representing text, and image data representing an image. The data generation model 58 performs inference on the input inference data in accordance with the instruction indicated by the prompt and outputs the inference result in a data format such as voice data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization. The identification processing unit 290 performs the above-mentioned identification processing using the data generation model 58. The data generation model 58 may be a fine-tuned model so as to output an inference result from a prompt that does not include an instruction. In this case, the data generation model 58 can output an inference result from a prompt that does not include an instruction. The data processing device 12 and the like include multiple types of data generation models 58, and the data generation model 58 includes AIs other than the generative AI. The AI ​​other than the generative AI may be, for example, linear regression, logistic regression, decision tree, random forest, support vector machine (SVM), k-means clustering, convolutional neural network (CNN), recurrent neural network (RNN), generative adversarial network (GAN), or naive Bayes, and can perform various processes, but is not limited to these examples. The AI ​​may also be an AI agent. When the processes of each of the above-mentioned parts are performed by AI, the processes may be performed in part or entirely by AI, but are not limited to these examples. The processes performed by AI, including the generative AI, may be replaced with rule-based processes.

[0141] 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.

[0142] 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.

[0143] 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.

[0144] 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.

[0145] 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).

[0146] 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.

[0147] 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."

[0148] 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.

[0149] 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.

[0150] 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.

[0151] 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.

[0152] 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.

[0153] 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.

[0154] 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.

[0155] 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.

[0156] 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.

[0157] 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.

[0158] 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.

[0159] 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]

[0160] 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 text analysis unit that analyzes text entered by a user; a video generation unit that generates a video based on the content analyzed by the text analysis unit; an animation unit that animates live-action video input by a user; a correction unit that corrects the generated video. A system characterized by:

2. The sentence analysis unit Analyze the emotional tone of the text and automatically add visual effects according to the emotion.

2. The system of claim 1.

3. The video generation unit In response to text-based instructions, the generation AI automatically collects relevant images or audio from the internet and incorporates them into the video.

2. The system of claim 1.

4. The video generation unit Analyze the style or color tone of a reference video and apply the same style or color tone to the new video 2. The system of claim 1.

5. The animation unit: The movement of the live-action video is analyzed, and the smoothness of the movement is improved when the live-action video is animated.

2. The system of claim 1.

6. The correction unit Using an emotion estimation function, the emotion behind the user's correction instruction is analyzed, and the correction is made in a way that best suits the emotion.

2. The system of claim 1.

7. The video generation unit Using emotion estimation function, the emotion of the text is analyzed and a scene that best suits the emotion is generated.

2. The system of claim 1.

8. The video generation unit Using emotion estimation function, analyze the emotional tone of the reference video and reflect the same emotional tone in the new video.

2. The system of claim 1.

Images