System

Abstract

A system according to an embodiment aims to streamline the process of media generation and editing in movie production.SOLUTION: A system according to an embodiment includes a speech input unit, a text conversion unit, a text editing unit, a speech generation unit, a visual generation unit, and a relevance analysis unit. The voice input unit acquires voice data. The text conversion unit converts the voice data acquired by the voice input unit into text. The text editing unit edits the text converted by the text conversion unit. The voice generation unit converts the text edited by the text editing unit into voice. The visual generator generates visual content based on the text. The relevance analysis unit analyzes and optimizes relevance between text and visual content.SELECTED DRAWING: Figure 1

Description

[Technical Field]

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

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

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

[0004] Conventional technology has faced the challenge that the media creation and editing processes in film production are complex and difficult to carry out efficiently.

[0005] The system according to the embodiment aims to streamline the media creation and editing process in film production. [Means for solving the problem]

[0006] The system according to the embodiment includes a voice input unit, a text conversion unit, a text editing unit, a voice generation unit, a visual generation unit, and a relevance analysis unit. The voice input unit acquires voice data. The text conversion unit converts the voice data acquired by the voice input unit into text. The text editing unit edits the text converted by the text conversion unit. The voice generation unit converts the text edited by the text editing unit into voice. The visual generation unit generates visual content based on the text. The relevance analysis unit analyzes and optimizes the relevance between the text and the visual content. [Effects of the Invention]

[0007] Systems according to embodiments can streamline the media creation and editing process in film production. [Brief explanation of the drawings]

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

[0028] (Example 1) A media production and editing system according to an embodiment of the present invention allows users to voice-input scripts and ideas, converts them into text, edits them, converts them into audio, generates visual content, and analyzes and optimizes the relevance of the text and images, thereby streamlining idea visualization, pre-visualization, and post-production in the filmmaking process.

[0029] A media production and editing system according to an embodiment includes a voice input unit, a text conversion unit, a text editing unit, a voice generation unit, a visual generation unit, and a relevance analysis unit. The voice input unit acquires voice data. For example, the voice data is collected using a microphone. The voice input unit can also acquire voice data using a microphone on a smartphone or tablet. The voice input unit can also read recorded voice files. For example, the voice input unit can read audio files in WAV or MP3 format. The text conversion unit converts the voice data acquired by the voice input unit into text. For example, the text conversion unit converts the voice data into text using a voice recognition algorithm. The text conversion unit can also convert the voice data into text using generative AI (e.g., text generation AI or multimodal generative AI). For example, the text conversion unit converts the voice data into text using voice recognition software. The text editing unit edits the text converted by the text conversion unit. For example, the text editing unit makes grammatical corrections and style changes. The text editing unit can also add or delete content. For example, the text editing unit performs grammar correction using a grammar check algorithm. The speech generation unit converts the text edited by the text editing unit into speech. For example, the speech generation unit converts text into speech using speech synthesis technology. The speech generation unit can also convert text into speech using generative AI. For example, the speech generation unit converts text into speech using speech synthesis software. The visual generation unit generates visual content based on the text. For example, the visual generation unit generates images based on the text using the DALL-E API. The visual generation unit can also generate visual content based on the text using generative AI. For example, the visual generation unit generates images based on the text using image generation software. The relevance analysis unit analyzes and optimizes the relevance between the text and visual content. For example, the relevance analysis unit analyzes the relevance between the text and visual content using an embedding function.The relevance analysis unit can also use generative AI to optimize the relevance between text and visual content. For example, the relevance analysis unit may analyze the relevance between text and visual content using co-occurrence analysis or semantic analysis. This allows the media production and editing system according to the embodiment to streamline idea visualization, pre-visualization, and post-production in the filmmaking process. For example, the output unit may provide the generated visual and audio content to a user through a web or mobile application. If feedback is desired in paper form, the output unit may print the results using a printer. Sending the results via email provides quick feedback by sending them directly to the user.

[0030] The voice input unit can analyze background sounds or environmental sounds included in the voice data and reflect the atmosphere of the scene in the text. For example, the voice input unit analyzes background sounds or environmental sounds during voice input and reflects the atmosphere of the scene in the text. For example, it analyzes voice data containing birdsong and the sound of wind, and adds a detail such as "in the forest where birdsong can be heard" to text "A scene in which the main character is walking in the forest." The voice input unit also analyzes environmental sounds during voice input and reflects the atmosphere of the scene in the text. For example, it analyzes voice data containing car sounds and people talking, and adds a detail such as "in the city where car sounds and people talking can be heard" to text "A scene in which the main character is walking in the city." The voice input unit also analyzes background sounds during voice input and reflects the atmosphere of the scene in the text. For example, it analyzes voice data containing waves and seabirds singing, and adds a detail such as "A beach where waves and seabirds can be heard" to text "A scene in which the main character is walking on the beach." This allows the atmosphere of the scene to be reflected in more detail.

[0031] The speech input unit can simultaneously analyze the speech of multiple speakers and generate dialogue-style text. For example, the speech input unit simultaneously analyzes the speech of multiple speakers during speech input and generates dialogue-style text. For example, it analyzes speech data of two speakers having a conversation and generates dialogue-style text such as "A: Hello. B: Hello, how are you?" The speech input unit also simultaneously analyzes the speech of multiple speakers during speech input and generates dialogue-style text. For example, it analyzes speech data of three speakers having a conversation and generates dialogue-style text such as "A: What shall we do today? B: Let's go see a movie. C: Sounds good!" The speech input unit also simultaneously analyzes the speech of multiple speakers during speech input and generates dialogue-style text. For example, it analyzes speech data of four speakers having a conversation and generates dialogue-style text such as "A: Hello. B: Hello, how are you? C: What shall we do today? D: Let's go see a movie." This allows a conversation between multiple speakers to be converted into text.

[0032] The voice input unit can automatically translate voice data in different languages ​​and convert it into text. The voice input unit, for example, supports multilingual voice input and automatically translates and converts voice input in different languages ​​into text. For example, it translates voice input in English into Japanese and generates text such as "A scene where the protagonist is walking in the forest." The voice input unit also supports multilingual voice input and automatically translates and converts voice input in different languages ​​into text. For example, it translates voice input in French into English and generates text such as "The protagonist is walking in the forest." The voice input unit also supports multilingual voice input and automatically translates and converts voice input in different languages ​​into text. For example, it translates voice input in Chinese into Japanese and generates text such as "A scene where the protagonist is walking in the forest." This enables multilingual support.

[0033] The voice input unit can combine gesture or facial expression recognition to reflect a more detailed scene description in the text. The voice input unit, for example, combines gesture and facial expression recognition during voice input to reflect a more detailed scene description in the text. For example, if the speaker is smiling while speaking, the voice input unit generates text such as "A scene in which the main character is smiling and walking through the forest." The voice input unit also combines gesture and facial expression recognition during voice input to reflect a more detailed scene description in the text. For example, if the speaker is waving their hands while speaking, the voice input unit generates text such as "A scene in which the main character is waving their hands while walking through the forest." The voice input unit also combines gesture and facial expression recognition during voice input to reflect a more detailed scene description in the text. For example, if the speaker is speaking with a surprised expression, the voice input unit generates text such as "A scene in which the main character is walking through the forest with a surprised expression." This allows the scene description to be reflected in more detail.

[0034] The text editing unit can add an automatic grammar and style correction function to produce professional-looking text. The text editing unit, for example, adds an automatic grammar and style correction function when editing text to produce professional-looking text. For example, the text "A scene in which the protagonist is walking through the forest" is corrected to "A scene in which the protagonist is walking quietly through the forest." The text editing unit also adds an automatic grammar and style correction function when editing text to produce professional-looking text. For example, the text "He is walking through the forest" is corrected to "He is walking quietly through the forest." The text editing unit also adds an automatic grammar and style correction function when editing text to produce professional-looking text. For example, the text "A scene in which the protagonist is walking through the forest" is corrected to "A scene in which the protagonist is walking slowly through the forest." In this way, professional-looking text is generated through automatic grammar and style correction.

[0035] The speech generation unit can customize the tone and accent of a speaker's voice. For example, the speech generation unit can customize the tone and accent of a speaker's voice when converting edited text into speech. For example, the text "A scene where the main character is walking through the forest" is converted into speech in a calm tone. The speech generation unit can also customize the tone and accent of a speaker's voice when converting edited text into speech. For example, the text "A scene where the main character is walking through the forest" is converted into speech in an excited tone. The speech generation unit can also customize the tone and accent of a speaker's voice when converting edited text into speech. For example, the text "A scene where the main character is walking through the forest" is converted into speech in a sad tone. This allows for customizing the tone and accent of a speaker's voice, making it possible to produce a wider variety of speech expressions.

[0036] The text editing unit can add a collaboration function that reflects feedback from other users in real time. The text editing unit adds, for example, a collaboration function that reflects feedback from other users in real time when editing text. For example, a co-editor adds a comment to the text "A scene where the main character is walking through the forest" and modifies the text based on the comment. The text editing unit also adds a collaboration function that reflects feedback from other users in real time when editing text. For example, a co-editor makes a suggested correction to the text "A scene where the main character is walking through the forest" and modifies the text based on the suggestion. The text editing unit also adds a collaboration function that reflects feedback from other users in real time when editing text. For example, a co-editor gives an opinion on the text "A scene where the main character is walking through the forest" and modifies the text based on the opinion. This enables collaboration in real time.

[0037] The audio generation unit can automatically add background sounds and sound effects when converting text to audio, thereby generating more realistic audio content. For example, the audio generation unit automatically adds background sounds and sound effects when converting edited text to audio, thereby generating more realistic audio content. For example, birdsong and the sound of wind are added to the text "A scene in which the main character is walking through a forest." The audio generation unit also automatically adds background sounds and sound effects when converting edited text to audio, thereby generating more realistic audio content. For example, the sound of cars and people talking are added to the text "A scene in which the main character is walking through a city." The audio generation unit also automatically adds background sounds and sound effects when converting edited text to audio, thereby generating more realistic audio content. For example, the sound of waves and the cries of seabirds are added to the text "A scene in which the main character is walking on the beach." In this way, more realistic audio content is generated by adding background sounds and sound effects.

[0038] The visual generation unit can reflect detailed scene settings. The visual generation unit, for example, reflects detailed scene settings when generating visual content. For example, for the text "A scene in which the main character is walking through the forest," the time period is set to evening, and an image of a forest at sunset is generated. The visual generation unit also reflects detailed scene settings when generating visual content. For example, for the text "A scene in which the main character is walking through the forest," the time period is set to rainy weather, and an image of a forest in the rain is generated. The visual generation unit also reflects detailed scene settings when generating visual content. For example, for the text "A scene in which the main character is walking through the forest," the season is set to winter, and an image of a forest covered in snow is generated. In this way, by reflecting detailed scene settings, more realistic visual content is generated.

[0039] The visual generation unit can add a function to automatically correct the visual content based on user feedback. The visual generation unit adds, for example, a function to automatically correct the generated visual content based on user feedback. For example, if the user provides feedback such as "I want a brighter forest," the visual generation unit corrects the image to a brighter forest. The visual generation unit also adds a function to automatically correct the generated visual content based on user feedback. For example, if the user provides feedback such as "I want a more detailed background," the visual generation unit adds detailed elements to the background. The visual generation unit also adds a function to automatically correct the generated visual content based on user feedback. For example, if the user provides feedback such as "I want a character's facial expression changed," the character's facial expression is changed. In this way, by automatically correcting the visual content based on user feedback, visual content that is more in line with the user's intentions is generated.

[0040] The visual generation unit can automatically generate 3D models and animations to provide more dynamic content. The visual generation unit automatically generates 3D models and animations when generating visual content, for example, to provide more dynamic content. For example, for the text "a scene in which the main character is walking through the forest," an animation of a 3D model of the main character walking through the forest is generated. The visual generation unit also automatically generates 3D models and animations when generating visual content, to provide more dynamic content. For example, for the text "a scene in which the main character is walking through a city," an animation of a 3D model of the main character walking through a city is generated. The visual generation unit also automatically generates 3D models and animations when generating visual content, to provide more dynamic content. For example, for the text "a scene in which the main character is walking along the beach," an animation of a 3D model of the main character walking along the beach is generated. In this way, more dynamic visual content is provided by automatically generating 3D models and animations.

[0041] The visual generation unit allows selection of different art styles and can generate visual content according to the user's preferences. For example, the visual generation unit allows selection of different art styles when generating visual content and generates visual content according to the user's preferences. For example, an oil-painting style forest image is generated for the text "a scene in which the main character is walking through the forest." The visual generation unit also allows selection of different art styles when generating visual content and generates visual content according to the user's preferences. For example, a manga-style forest image is generated for the text "a scene in which the main character is walking through the forest." The visual generation unit also allows selection of different art styles when generating visual content and generates visual content according to the user's preferences. For example, a watercolor-style forest image is generated for the text "a scene in which the main character is walking through the forest." In this way, by allowing selection of different art styles, visual content according to the user's preferences is generated.

[0042] The relevance analysis unit can take into account the time flow and storyboard of the scene when analyzing the relevance between text and video. For example, the relevance analysis unit takes into account the time flow and storyboard of the scene when analyzing the relevance between text and video. For example, for the text "a scene in which the main character is walking through a forest," a video showing the passage of time is generated. The relevance analysis unit also takes into account the time flow and storyboard of the scene when analyzing the relevance between text and video. For example, for the text "a scene in which the main character is walking through a city," a video showing the passage of time from morning to night is generated. The relevance analysis unit also takes into account the time flow and storyboard of the scene when analyzing the relevance between text and video. For example, for the text "a scene in which the main character is walking on the beach," a video showing the passage of time from sunrise to sunset is generated. In this way, by taking into account the time flow and storyboard of the scene, more consistent video is generated.

[0043] The relevance analysis unit can add a function to automatically generate scene transitions and cuts based on the relevance analysis results. The relevance analysis unit adds a function to automatically generate scene transitions and cuts based on the relevance analysis results. For example, for the text "a scene in which the main character is walking through a forest," a transition that smoothly switches scenes is generated. The relevance analysis unit also adds a function to automatically generate scene transitions and cuts based on the relevance analysis results. For example, for the text "a scene in which the main character is walking through a city," a cut is automatically generated to smooth the flow of scenes. The relevance analysis unit also adds a function to automatically generate scene transitions and cuts based on the relevance analysis results. For example, for the text "a scene in which the main character is walking on the beach," a transition is generated to smoothly switch scenes. In this way, the flow of video becomes smoother by automatically generating scene transitions and cuts.

[0044] When analyzing the relevance between text and video, the relevance analysis unit can propose new expressions by combining videos of different genres and styles. For example, when analyzing the relevance between text and video, the relevance analysis unit proposes new expressions by combining videos of different genres and styles. For example, for the text "a scene in which the main character is walking through a forest," a video that combines animation and live action is generated. Furthermore, when analyzing the relevance between text and video, the relevance analysis unit proposes new expressions by combining videos of different genres and styles. For example, for the text "a scene in which the main character is walking through a city," a video that combines documentary-style and fiction-style videos is generated. Furthermore, when analyzing the relevance between text and video, the relevance analysis unit proposes new expressions by combining videos of different genres and styles. For example, for the text "a scene in which the main character is walking on the beach," a video that combines monochrome and color is generated. In this way, new expressions can be created by combining videos of different genres and styles.

[0045] The relevance analysis unit can automatically adjust the color tone and music of the video based on the relevance analysis results to optimize the atmosphere of the scene. The relevance analysis unit, for example, automatically adjusts the color tone and music of the video based on the relevance analysis results to optimize the atmosphere of the scene. For example, for the text "A scene in which the main character is walking through a forest," bright colors and light music are added. The relevance analysis unit also automatically adjusts the color tone and music of the video based on the relevance analysis results to optimize the atmosphere of the scene. For example, for the text "A scene in which the main character is walking through a city," monochrome colors and jazz music are added. The relevance analysis unit also automatically adjusts the color tone and music of the video based on the relevance analysis results to optimize the atmosphere of the scene. For example, for the text "A scene in which the main character is walking on the beach," blue colors and the sound of waves are added. In this way, the atmosphere of the scene is optimized by automatically adjusting the color tone and music of the video.

[0046] The system according to the embodiment is not limited to the above-described example, and various modifications are possible, for example, as follows.

[0047] The voice input unit can analyze background or environmental sounds contained in the voice data and reflect the atmosphere of the scene in the text. For example, by analyzing voice data containing the sounds of birds chirping and wind, it can add details such as "in the forest where birds chirping can be heard" to the text "A scene in which the main character is walking in the forest." It can also analyze voice data containing the sounds of cars and people talking and add details such as "in the city where the sounds of cars and people talking can be heard" to the text "A scene in which the main character is walking in the city." It can also analyze voice data containing the sounds of waves and seabirds singing and add details such as "on the beach where the sounds of waves and seabirds can be heard" to the text "A scene in which the main character is walking on the beach." This allows the atmosphere of the scene to be reflected in more detail.

[0048] The speech input unit can simultaneously analyze the speech of multiple speakers and generate dialogue-style text. For example, it can analyze speech data of two speakers conversing and generate dialogue-style text such as "A: Hello. B: Hello, how are you?" It can also analyze speech data of three speakers conversing and generate dialogue-style text such as "A: What are you doing today? B: Let's go to the movies. C: Sounds good!" It can also analyze speech data of four speakers conversing and generate dialogue-style text such as "A: Hello. B: Hello, how are you? C: What are you doing today? D: Let's go to the movies." This makes it possible to convert conversations between multiple speakers into text.

[0049] The voice input unit can automatically translate voice data in different languages ​​and convert it into text. For example, it can translate voice input in English into Japanese and generate the text "A scene where the protagonist is walking in the forest." It can also translate voice input in French into English and generate the text "The protagonist is walking in the forest." It can also translate voice input in Chinese into Japanese and generate the text "A scene where the protagonist is walking in the forest." This makes it possible to support multiple languages.

[0050] The voice input unit can combine gesture or facial expression recognition to reflect more detailed scene descriptions in the text. For example, if the speaker is smiling, it can generate text such as "A scene in which the protagonist is smiling and walking through the forest." If the speaker is waving their hands while speaking, it can also generate text such as "A scene in which the protagonist is waving their hands while walking through the forest." If the speaker is speaking with a surprised expression, it can also generate text such as "A scene in which the protagonist is walking through the forest with a surprised expression." This allows for more detailed scene descriptions to be reflected.

[0051] The visual generation unit can reflect detailed scene settings. For example, for the text "A scene in which the main character is walking through the forest," it can set the time of day to evening and generate an image of a forest at sunset. Also, for the text "A scene in which the main character is walking through the forest," it can set the time to rain and generate an image of a forest in the rain. Furthermore, for the text "A scene in which the main character is walking through the forest," it can set the season to winter and generate an image of a forest covered in snow. In this way, more realistic visual content can be generated by reflecting detailed scene settings.

[0052] The visual generation unit can automatically generate 3D models and animations to provide more dynamic content. For example, for the text "A scene in which the main character is walking through the forest," it can generate an animation of a 3D model of the main character walking through the forest. Also, for the text "A scene in which the main character is walking through a city," it can generate an animation of a 3D model of the main character walking through a city. Furthermore, for the text "A scene in which the main character is walking on the beach," it can generate an animation of a 3D model of the main character walking on the beach. In this way, by automatically generating 3D models and animations, more dynamic visual content can be provided.

[0053] The relevance analysis unit can take into account the time flow and storyboard of a scene when analyzing the relevance between text and video. For example, for the text "A scene in which the main character is walking through the forest," it can generate a video showing the passage of time. Also, for the text "A scene in which the main character is walking through town," it can generate a video showing the passage of time from morning to night. Furthermore, for the text "A scene in which the main character is walking on the beach," it can generate a video showing the passage of time from sunrise to sunset. In this way, by taking into account the time flow and storyboard of a scene, more consistent video can be generated.

[0054] Based on the results of the relevance analysis, the relevance analysis unit can automatically adjust the color tones and music of the video to optimize the atmosphere of the scene. For example, bright colors and upbeat music can be added to the text "A scene in which the main character is walking through the forest." Monochrome colors and jazz music can also be added to the text "A scene in which the main character is walking through town." Furthermore, blue colors and the sound of waves can be added to the text "A scene in which the main character is walking on the beach." In this way, the atmosphere of the scene can be optimized by automatically adjusting the color tones and music of the video.

[0055] The processing flow of the first embodiment will be briefly explained below.

[0056] Step 1: The audio input unit acquires audio data. For example, the audio data is collected using a microphone. The audio input unit can also acquire audio data using a microphone on a smartphone or tablet. Furthermore, the audio input unit can also read a recorded audio file. For example, the audio input unit can read an audio file in WAV format or MP3 format. Step 2: The text conversion unit converts the voice data acquired by the voice input unit into text. For example, the text conversion unit converts the voice data into text using a voice recognition algorithm. The text conversion unit can also convert the voice data into text using generative AI (e.g., text generation AI or multimodal generation AI). For example, the text conversion unit converts the voice data into text using voice recognition software. Step 3: The text editing unit edits the text converted by the text conversion unit. For example, the text editing unit makes grammatical corrections or style changes. The text editing unit can also add or delete content. For example, the text editing unit makes grammatical corrections using a grammar check algorithm. Step 4: The speech generation unit converts the text edited by the text editing unit into speech. For example, the speech generation unit converts the text into speech using speech synthesis technology. The speech generation unit can also convert the text into speech using generative AI. For example, the speech generation unit converts the text into speech using speech synthesis software. Step 5: The visual generation unit generates visual content based on the text. For example, the visual generation unit generates an image based on the text using the DALL-E API. The visual generation unit can also generate visual content based on the text using generative AI. For example, the visual generation unit generates an image based on the text using image generation software. Step 6: The relevance analysis unit analyzes and optimizes the relevance between the text and visual content. For example, the relevance analysis unit may use embedding functions to analyze the relevance between the text and visual content. The relevance analysis unit may also use generative AI to optimize the relevance between the text and visual content. For example, the relevance analysis unit may use co-occurrence analysis or semantic analysis to analyze the relevance between the text and visual content.

[0057] (Example 2) A media production and editing system according to an embodiment of the present invention allows users to voice-input scripts and ideas, converts them into text, edits them, converts them into audio, generates visual content, and analyzes and optimizes the relevance of the text and images, thereby streamlining idea visualization, pre-visualization, and post-production in the filmmaking process.

[0058] A media production and editing system according to an embodiment includes a voice input unit, a text conversion unit, a text editing unit, a voice generation unit, a visual generation unit, and a relevance analysis unit. The voice input unit acquires voice data. For example, the voice data is collected using a microphone. The voice input unit can also acquire voice data using a microphone on a smartphone or tablet. The voice input unit can also read recorded voice files. For example, the voice input unit can read audio files in WAV or MP3 format. The text conversion unit converts the voice data acquired by the voice input unit into text. For example, the text conversion unit converts the voice data into text using a voice recognition algorithm. The text conversion unit can also convert the voice data into text using generative AI (e.g., text generation AI or multimodal generative AI). For example, the text conversion unit converts the voice data into text using voice recognition software. The text editing unit edits the text converted by the text conversion unit. For example, the text editing unit makes grammatical corrections and style changes. The text editing unit can also add or delete content. For example, the text editing unit performs grammar correction using a grammar check algorithm. The speech generation unit converts the text edited by the text editing unit into speech. For example, the speech generation unit converts text into speech using speech synthesis technology. The speech generation unit can also convert text into speech using generative AI. For example, the speech generation unit converts text into speech using speech synthesis software. The visual generation unit generates visual content based on the text. For example, the visual generation unit generates images based on the text using the DALL-E API. The visual generation unit can also generate visual content based on the text using generative AI. For example, the visual generation unit generates images based on the text using image generation software. The relevance analysis unit analyzes and optimizes the relevance between the text and visual content. For example, the relevance analysis unit analyzes the relevance between the text and visual content using an embedding function.The relevance analysis unit can also use generative AI to optimize the relevance between text and visual content. For example, the relevance analysis unit may analyze the relevance between text and visual content using co-occurrence analysis or semantic analysis. This allows the media production and editing system according to the embodiment to streamline idea visualization, pre-visualization, and post-production in the filmmaking process. For example, the output unit may provide the generated visual and audio content to a user through a web or mobile application. If feedback is desired in paper form, the output unit may print the results using a printer. Sending the results via email provides quick feedback by sending them directly to the user.

[0059] The voice input unit can analyze background sounds or environmental sounds included in the voice data and reflect the atmosphere of the scene in the text. For example, the voice input unit analyzes background sounds or environmental sounds during voice input and reflects the atmosphere of the scene in the text. For example, it analyzes voice data containing birdsong and the sound of wind, and adds a detail such as "in the forest where birdsong can be heard" to text "A scene in which the main character is walking in the forest." The voice input unit also analyzes environmental sounds during voice input and reflects the atmosphere of the scene in the text. For example, it analyzes voice data containing car sounds and people talking, and adds a detail such as "in the city where car sounds and people talking can be heard" to text "A scene in which the main character is walking in the city." The voice input unit also analyzes background sounds during voice input and reflects the atmosphere of the scene in the text. For example, it analyzes voice data containing waves and seabirds singing, and adds a detail such as "A beach where waves and seabirds can be heard" to text "A scene in which the main character is walking on the beach." This allows the atmosphere of the scene to be reflected in more detail.

[0060] The speech input unit can use a generation AI to estimate the speaker's emotion contained in the speech data and adjust the tone and expression of the text based on that emotion. For example, the speech input unit uses a generation AI to estimate the speaker's emotion during speech input and adjust the tone and expression of the text based on that emotion. For example, if the speaker is excited, the text "A scene in which the protagonist is walking through the forest" is adjusted to "A scene in which the protagonist is walking through the forest excitedly." The speech input unit also uses a generation AI to estimate the speaker's emotion during speech input and adjust the tone and expression of the text based on that emotion. For example, if the speaker is sad, the text "A scene in which the protagonist is walking through the forest" is adjusted to "A scene in which the protagonist is walking through the forest sadly." The speech input unit also uses a generation AI to estimate the speaker's emotion during speech input and adjust the tone and expression of the text based on that emotion. For example, if the speaker is angry, the text "A scene in which the protagonist is walking through the forest" is adjusted to "A scene in which the protagonist is walking through the forest angry." This makes it possible to generate text that corresponds to the speaker's emotion.

[0061] The speech input unit can simultaneously analyze the speech of multiple speakers and generate dialogue-style text. For example, the speech input unit simultaneously analyzes the speech of multiple speakers during speech input and generates dialogue-style text. For example, it analyzes speech data of two speakers having a conversation and generates dialogue-style text such as "A: Hello. B: Hello, how are you?" The speech input unit also simultaneously analyzes the speech of multiple speakers during speech input and generates dialogue-style text. For example, it analyzes speech data of three speakers having a conversation and generates dialogue-style text such as "A: What shall we do today? B: Let's go see a movie. C: Sounds good!" The speech input unit also simultaneously analyzes the speech of multiple speakers during speech input and generates dialogue-style text. For example, it analyzes speech data of four speakers having a conversation and generates dialogue-style text such as "A: Hello. B: Hello, how are you? C: What shall we do today? D: Let's go see a movie." This allows a conversation between multiple speakers to be converted into text.

[0062] The voice input unit can automatically translate voice data in different languages ​​and convert it into text. The voice input unit, for example, supports multilingual voice input and automatically translates and converts voice input in different languages ​​into text. For example, it translates voice input in English into Japanese and generates text such as "A scene where the protagonist is walking in the forest." The voice input unit also supports multilingual voice input and automatically translates and converts voice input in different languages ​​into text. For example, it translates voice input in French into English and generates text such as "The protagonist is walking in the forest." The voice input unit also supports multilingual voice input and automatically translates and converts voice input in different languages ​​into text. For example, it translates voice input in Chinese into Japanese and generates text such as "A scene where the protagonist is walking in the forest." This enables multilingual support.

[0063] The voice input unit can combine gesture or facial expression recognition to reflect a more detailed scene description in the text. The voice input unit, for example, combines gesture and facial expression recognition during voice input to reflect a more detailed scene description in the text. For example, if the speaker is smiling while speaking, the voice input unit generates text such as "A scene in which the main character is smiling and walking through the forest." The voice input unit also combines gesture and facial expression recognition during voice input to reflect a more detailed scene description in the text. For example, if the speaker is waving their hands while speaking, the voice input unit generates text such as "A scene in which the main character is waving their hands while walking through the forest." The voice input unit also combines gesture and facial expression recognition during voice input to reflect a more detailed scene description in the text. For example, if the speaker is speaking with a surprised expression, the voice input unit generates text such as "A scene in which the main character is walking through the forest with a surprised expression." This allows the scene description to be reflected in more detail.

[0064] The speech input unit can use the emotion estimation function to analyze the emotion of the speaker of the speech data in real time and generate text according to the emotion. The speech input unit, for example, uses the emotion estimation function to analyze the emotion of the speaker at the time of speech input in real time and generate text according to the emotion. For example, if the speaker is happy, the speech input unit generates text such as "A scene in which the main character is walking through the forest feeling happy." The speech input unit also uses the emotion estimation function to analyze the emotion of the speaker at the time of speech input in real time and generate text according to the emotion. For example, if the speaker is sad, the speech input unit generates text such as "A scene in which the main character is walking through the forest feeling sad." The speech input unit also uses the emotion estimation function to analyze the emotion of the speaker at the time of speech input in real time and generate text according to the emotion. For example, if the speaker is angry, the speech input unit generates text such as "A scene in which the main character is walking through the forest feeling angry." This makes it possible to generate text according to the speaker's emotion in real time.

[0065] The text editing unit can add an automatic grammar and style correction function to produce professional-looking text. The text editing unit, for example, adds an automatic grammar and style correction function when editing text to produce professional-looking text. For example, the text "A scene in which the protagonist is walking through the forest" is corrected to "A scene in which the protagonist is walking quietly through the forest." The text editing unit also adds an automatic grammar and style correction function when editing text to produce professional-looking text. For example, the text "He is walking through the forest" is corrected to "He is walking quietly through the forest." The text editing unit also adds an automatic grammar and style correction function when editing text to produce professional-looking text. For example, the text "A scene in which the protagonist is walking through the forest" is corrected to "A scene in which the protagonist is walking slowly through the forest." In this way, professional-looking text is generated through automatic grammar and style correction.

[0066] The speech generation unit can customize the tone and accent of a speaker's voice. For example, the speech generation unit can customize the tone and accent of a speaker's voice when converting edited text into speech. For example, the text "A scene where the main character is walking through the forest" is converted into speech in a calm tone. The speech generation unit can also customize the tone and accent of a speaker's voice when converting edited text into speech. For example, the text "A scene where the main character is walking through the forest" is converted into speech in an excited tone. The speech generation unit can also customize the tone and accent of a speaker's voice when converting edited text into speech. For example, the text "A scene where the main character is walking through the forest" is converted into speech in a sad tone. This allows for customizing the tone and accent of a speaker's voice, making it possible to produce a wider variety of speech expressions.

[0067] The voice generation unit can analyze the emotion of the text using a generation AI and automatically generate a voice expression corresponding to the emotion. For example, the voice generation unit analyzes the emotion of the edited text using a generation AI and automatically generates a voice expression corresponding to the emotion. For example, the text "A scene where the main character is walking through the forest" is vocalized with the emotion of joy. The voice generation unit also analyzes the emotion of the edited text using a generation AI and automatically generates a voice expression corresponding to the emotion. For example, the text "A scene where the main character is walking through the forest" is vocalized with the emotion of sadness. The voice generation unit also analyzes the emotion of the edited text using a generation AI and automatically generates a voice expression corresponding to the emotion. For example, the text "A scene where the main character is walking through the forest" is vocalized with the emotion of anger. In this way, a voice expression corresponding to the emotion of the text is automatically generated.

[0068] The text editing unit can add a collaboration function that reflects feedback from other users in real time. The text editing unit adds, for example, a collaboration function that reflects feedback from other users in real time when editing text. For example, a co-editor adds a comment to the text "A scene where the main character is walking through the forest" and modifies the text based on the comment. The text editing unit also adds a collaboration function that reflects feedback from other users in real time when editing text. For example, a co-editor makes a suggested correction to the text "A scene where the main character is walking through the forest" and modifies the text based on the suggestion. The text editing unit also adds a collaboration function that reflects feedback from other users in real time when editing text. For example, a co-editor gives an opinion on the text "A scene where the main character is walking through the forest" and modifies the text based on the opinion. This enables collaboration in real time.

[0069] The audio generation unit can automatically add background sounds and sound effects when converting text to audio, thereby generating more realistic audio content. For example, the audio generation unit automatically adds background sounds and sound effects when converting edited text to audio, thereby generating more realistic audio content. For example, birdsong and the sound of wind are added to the text "A scene in which the main character is walking through a forest." The audio generation unit also automatically adds background sounds and sound effects when converting edited text to audio, thereby generating more realistic audio content. For example, the sound of cars and people talking are added to the text "A scene in which the main character is walking through a city." The audio generation unit also automatically adds background sounds and sound effects when converting edited text to audio, thereby generating more realistic audio content. For example, the sound of waves and the cries of seabirds are added to the text "A scene in which the main character is walking on the beach." In this way, more realistic audio content is generated by adding background sounds and sound effects.

[0070] The speech generation unit can use the emotion estimation function to analyze the emotion of the text in real time and generate a speech expression corresponding to the emotion. The speech generation unit, for example, uses the emotion estimation function to analyze the emotion of the edited text in real time and generate a speech expression corresponding to the emotion. For example, the text "A scene where the main character is walking through the forest" is vocalized with an emotion of joy. The speech generation unit also uses the emotion estimation function to analyze the emotion of the edited text in real time and generate a speech expression corresponding to the emotion. For example, the text "A scene where the main character is walking through the forest" is vocalized with an emotion of sadness. The speech generation unit also uses the emotion estimation function to analyze the emotion of the edited text in real time and generate a speech expression corresponding to the emotion. For example, the text "A scene where the main character is walking through the forest" is vocalized with an emotion of anger. In this way, a speech expression corresponding to the emotion of the text is generated in real time.

[0071] The visual generation unit can reflect detailed scene settings. The visual generation unit, for example, reflects detailed scene settings when generating visual content. For example, for the text "A scene in which the main character is walking through the forest," the time period is set to evening, and an image of a forest at sunset is generated. The visual generation unit also reflects detailed scene settings when generating visual content. For example, for the text "A scene in which the main character is walking through the forest," the time period is set to rainy weather, and an image of a forest in the rain is generated. The visual generation unit also reflects detailed scene settings when generating visual content. For example, for the text "A scene in which the main character is walking through the forest," the season is set to winter, and an image of a forest covered in snow is generated. In this way, by reflecting detailed scene settings, more realistic visual content is generated.

[0072] The visual generation unit can add a function to automatically correct the visual content based on user feedback. The visual generation unit adds, for example, a function to automatically correct the generated visual content based on user feedback. For example, if the user provides feedback such as "I want a brighter forest," the visual generation unit corrects the image to a brighter forest. The visual generation unit also adds a function to automatically correct the generated visual content based on user feedback. For example, if the user provides feedback such as "I want a more detailed background," the visual generation unit adds detailed elements to the background. The visual generation unit also adds a function to automatically correct the generated visual content based on user feedback. For example, if the user provides feedback such as "I want a character's facial expression changed," the character's facial expression is changed. In this way, by automatically correcting the visual content based on user feedback, visual content that is more in line with the user's intentions is generated.

[0073] The visual generation unit can reflect the emotional atmosphere of a scene using the emotion estimation function. For example, the visual generation unit uses the emotion estimation function to reflect the emotional atmosphere of a scene when generating visual content. For example, for the text "A scene in which the main character is walking through the forest," an image of a bright forest that reflects the emotion of joy is generated. The visual generation unit also uses the emotion estimation function to reflect the emotional atmosphere of a scene when generating visual content. For example, for the text "A scene in which the main character is walking through the forest," an image of a dark forest that reflects the emotion of sadness is generated. The visual generation unit also uses the emotion estimation function to reflect the emotional atmosphere of a scene when generating visual content. For example, for the text "A scene in which the main character is walking through the forest," an image of an eerie forest that reflects the emotion of fear is generated. In this way, by reflecting the emotional atmosphere of a scene, more emotional visual content is generated.

[0074] The visual generation unit can automatically generate 3D models and animations to provide more dynamic content. The visual generation unit automatically generates 3D models and animations when generating visual content, for example, to provide more dynamic content. For example, for the text "a scene in which the main character is walking through the forest," an animation of a 3D model of the main character walking through the forest is generated. The visual generation unit also automatically generates 3D models and animations when generating visual content, to provide more dynamic content. For example, for the text "a scene in which the main character is walking through a city," an animation of a 3D model of the main character walking through a city is generated. The visual generation unit also automatically generates 3D models and animations when generating visual content, to provide more dynamic content. For example, for the text "a scene in which the main character is walking along the beach," an animation of a 3D model of the main character walking along the beach is generated. In this way, more dynamic visual content is provided by automatically generating 3D models and animations.

[0075] The visual generation unit allows selection of different art styles and can generate visual content according to the user's preferences. For example, the visual generation unit allows selection of different art styles when generating visual content and generates visual content according to the user's preferences. For example, an oil-painting style forest image is generated for the text "a scene in which the main character is walking through the forest." The visual generation unit also allows selection of different art styles when generating visual content and generates visual content according to the user's preferences. For example, a manga-style forest image is generated for the text "a scene in which the main character is walking through the forest." The visual generation unit also allows selection of different art styles when generating visual content and generates visual content according to the user's preferences. For example, a watercolor-style forest image is generated for the text "a scene in which the main character is walking through the forest." In this way, by allowing selection of different art styles, visual content according to the user's preferences is generated.

[0076] The visual generation unit can use the emotion estimation function to analyze the emotional impact of the generated visual content and propose an optimal visual representation. For example, the visual generation unit uses the emotion estimation function to analyze the emotional impact of the generated visual content and propose an optimal visual representation. For example, an image of a bright forest reflecting the emotion of joy is proposed. The visual generation unit also uses the emotion estimation function to analyze the emotional impact of the generated visual content and propose an optimal visual representation. For example, an image of a dark forest reflecting the emotion of sadness is proposed. The visual generation unit also uses the emotion estimation function to analyze the emotional impact of the generated visual content and propose an optimal visual representation. For example, an image of an eerie forest reflecting the emotion of fear is proposed. In this way, by analyzing the emotional impact of the visual content and proposing an optimal visual representation, more emotional visual content is generated.

[0077] The relevance analysis unit can take into account the time flow and storyboard of the scene when analyzing the relevance between text and video. For example, the relevance analysis unit takes into account the time flow and storyboard of the scene when analyzing the relevance between text and video. For example, for the text "a scene in which the main character is walking through a forest," a video showing the passage of time is generated. The relevance analysis unit also takes into account the time flow and storyboard of the scene when analyzing the relevance between text and video. For example, for the text "a scene in which the main character is walking through a city," a video showing the passage of time from morning to night is generated. The relevance analysis unit also takes into account the time flow and storyboard of the scene when analyzing the relevance between text and video. For example, for the text "a scene in which the main character is walking on the beach," a video showing the passage of time from sunrise to sunset is generated. In this way, by taking into account the time flow and storyboard of the scene, more consistent video is generated.

[0078] The relevance analysis unit can add a function to automatically generate scene transitions and cuts based on the relevance analysis results. The relevance analysis unit adds a function to automatically generate scene transitions and cuts based on the relevance analysis results. For example, for the text "a scene in which the main character is walking through a forest," a transition that smoothly switches scenes is generated. The relevance analysis unit also adds a function to automatically generate scene transitions and cuts based on the relevance analysis results. For example, for the text "a scene in which the main character is walking through a city," a cut is automatically generated to smooth the flow of scenes. The relevance analysis unit also adds a function to automatically generate scene transitions and cuts based on the relevance analysis results. For example, for the text "a scene in which the main character is walking on the beach," a transition is generated to smoothly switch scenes. In this way, the flow of video becomes smoother by automatically generating scene transitions and cuts.

[0079] The relevance analysis unit can analyze the relevance between text and video using an emotion estimation function and optimize the emotional match. The relevance analysis unit, for example, analyzes the relevance between text and video using the emotion estimation function and optimizes the emotional match. For example, for the text "a scene in which the main character is walking through the forest," a video reflecting the emotion of joy is generated. The relevance analysis unit also analyzes the relevance between text and video using the emotion estimation function and optimizes the emotional match. For example, for the text "a scene in which the main character is walking through the forest," a video reflecting the emotion of sadness is generated. The relevance analysis unit also analyzes the relevance between text and video using the emotion estimation function and optimizes the emotional match. For example, for the text "a scene in which the main character is walking through the forest," a video reflecting the emotion of fear is generated. In this way, by optimizing the emotional match between text and video, a more emotional video is generated.

[0080] When analyzing the relevance between text and video, the relevance analysis unit can propose new expressions by combining videos of different genres and styles. For example, when analyzing the relevance between text and video, the relevance analysis unit proposes new expressions by combining videos of different genres and styles. For example, for the text "a scene in which the main character is walking through a forest," a video that combines animation and live action is generated. Furthermore, when analyzing the relevance between text and video, the relevance analysis unit proposes new expressions by combining videos of different genres and styles. For example, for the text "a scene in which the main character is walking through a city," a video that combines documentary-style and fiction-style videos is generated. Furthermore, when analyzing the relevance between text and video, the relevance analysis unit proposes new expressions by combining videos of different genres and styles. For example, for the text "a scene in which the main character is walking on the beach," a video that combines monochrome and color is generated. In this way, new expressions can be created by combining videos of different genres and styles.

[0081] The relevance analysis unit can automatically adjust the color tone and music of the video based on the relevance analysis results to optimize the atmosphere of the scene. The relevance analysis unit, for example, automatically adjusts the color tone and music of the video based on the relevance analysis results to optimize the atmosphere of the scene. For example, for the text "A scene in which the main character is walking through a forest," bright colors and light music are added. The relevance analysis unit also automatically adjusts the color tone and music of the video based on the relevance analysis results to optimize the atmosphere of the scene. For example, for the text "A scene in which the main character is walking through a city," monochrome colors and jazz music are added. The relevance analysis unit also automatically adjusts the color tone and music of the video based on the relevance analysis results to optimize the atmosphere of the scene. For example, for the text "A scene in which the main character is walking on the beach," blue colors and the sound of waves are added. In this way, the atmosphere of the scene is optimized by automatically adjusting the color tone and music of the video.

[0082] The relevance analysis unit can use the emotion estimation function to analyze the relevance between text and video in real time and make suggestions to increase the emotional match. For example, the relevance analysis unit uses the emotion estimation function to analyze the relevance between text and video in real time and make suggestions to increase the emotional match. For example, for the text "a scene where the main character is walking through the forest," a video that reflects the emotion of joy is suggested. The relevance analysis unit also uses the emotion estimation function to analyze the relevance between text and video in real time and make suggestions to increase the emotional match. For example, for the text "a scene where the main character is walking through the forest," a video that reflects the emotion of sadness is suggested. The relevance analysis unit also uses the emotion estimation function to analyze the relevance between text and video in real time and make suggestions to increase the emotional match. For example, for the text "a scene where the main character is walking through the forest," a video that reflects the emotion of fear is suggested. In this way, by analyzing the emotional match between text and video in real time and making suggestions, more emotional videos are generated.

[0083] The system according to the embodiment is not limited to the above-described example, and various modifications are possible, for example, as follows.

[0084] The speech input unit can estimate the speaker's emotions contained in the speech data and adjust the tone and expression of the text based on those emotions. For example, if the speaker is excited, the text "A scene in which the protagonist is walking through the forest" can be adjusted to "A scene in which the protagonist is walking through the forest excitedly." If the speaker is sad, the text "A scene in which the protagonist is walking through the forest" can be adjusted to "A scene in which the protagonist is walking through the forest sadly." Furthermore, if the speaker is angry, the text "A scene in which the protagonist is walking through the forest" can be adjusted to "A scene in which the protagonist is walking through the forest angry." This makes it possible to generate text that corresponds to the speaker's emotions.

[0085] The voice input unit can analyze background or environmental sounds contained in the voice data and reflect the atmosphere of the scene in the text. For example, by analyzing voice data containing the sounds of birds chirping and wind, it can add details such as "in the forest where birds chirping can be heard" to the text "A scene in which the main character is walking in the forest." It can also analyze voice data containing the sounds of cars and people talking and add details such as "in the city where the sounds of cars and people talking can be heard" to the text "A scene in which the main character is walking in the city." It can also analyze voice data containing the sounds of waves and seabirds singing and add details such as "on the beach where the sounds of waves and seabirds can be heard" to the text "A scene in which the main character is walking on the beach." This allows the atmosphere of the scene to be reflected in more detail.

[0086] The speech input unit can simultaneously analyze the speech of multiple speakers and generate dialogue-style text. For example, it can analyze speech data of two speakers conversing and generate dialogue-style text such as "A: Hello. B: Hello, how are you?" It can also analyze speech data of three speakers conversing and generate dialogue-style text such as "A: What are you doing today? B: Let's go to the movies. C: Sounds good!" It can also analyze speech data of four speakers conversing and generate dialogue-style text such as "A: Hello. B: Hello, how are you? C: What are you doing today? D: Let's go to the movies." This makes it possible to convert conversations between multiple speakers into text.

[0087] The voice input unit can automatically translate voice data in different languages ​​and convert it into text. For example, it can translate voice input in English into Japanese and generate the text "A scene where the protagonist is walking in the forest." It can also translate voice input in French into English and generate the text "The protagonist is walking in the forest." It can also translate voice input in Chinese into Japanese and generate the text "A scene where the protagonist is walking in the forest." This makes it possible to support multiple languages.

[0088] The voice input unit can combine gesture or facial expression recognition to reflect more detailed scene descriptions in the text. For example, if the speaker is smiling, it can generate text such as "A scene in which the protagonist is smiling and walking through the forest." If the speaker is waving their hands while speaking, it can also generate text such as "A scene in which the protagonist is waving their hands while walking through the forest." If the speaker is speaking with a surprised expression, it can also generate text such as "A scene in which the protagonist is walking through the forest with a surprised expression." This allows for more detailed scene descriptions to be reflected.

[0089] The voice generation unit uses generation AI to analyze the emotions in the text and can automatically generate voice expressions that correspond to the emotions. For example, the text "A scene in which the main character is walking through the forest" can be voiced with the emotion of joy. The text "A scene in which the main character is walking through the forest" can also be voiced with the emotion of sadness. Furthermore, the text "A scene in which the main character is walking through the forest" can also be voiced with the emotion of anger. In this way, voice expressions that correspond to the emotions in the text can be automatically generated.

[0090] The visual generation unit can reflect detailed scene settings. For example, for the text "A scene in which the main character is walking through the forest," it can set the time of day to evening and generate an image of a forest at sunset. Also, for the text "A scene in which the main character is walking through the forest," it can set the time to rain and generate an image of a forest in the rain. Furthermore, for the text "A scene in which the main character is walking through the forest," it can set the season to winter and generate an image of a forest covered in snow. In this way, more realistic visual content can be generated by reflecting detailed scene settings.

[0091] The visual generation unit can automatically generate 3D models and animations to provide more dynamic content. For example, for the text "A scene in which the main character is walking through the forest," it can generate an animation of a 3D model of the main character walking through the forest. Also, for the text "A scene in which the main character is walking through a city," it can generate an animation of a 3D model of the main character walking through a city. Furthermore, for the text "A scene in which the main character is walking on the beach," it can generate an animation of a 3D model of the main character walking on the beach. In this way, by automatically generating 3D models and animations, more dynamic visual content can be provided.

[0092] The relevance analysis unit can take into account the time flow and storyboard of a scene when analyzing the relevance between text and video. For example, for the text "A scene in which the main character is walking through the forest," it can generate a video showing the passage of time. Also, for the text "A scene in which the main character is walking through town," it can generate a video showing the passage of time from morning to night. Furthermore, for the text "A scene in which the main character is walking on the beach," it can generate a video showing the passage of time from sunrise to sunset. In this way, by taking into account the time flow and storyboard of a scene, more consistent video can be generated.

[0093] Based on the results of the relevance analysis, the relevance analysis unit can automatically adjust the color tones and music of the video to optimize the atmosphere of the scene. For example, bright colors and upbeat music can be added to the text "A scene in which the main character is walking through the forest." Monochrome colors and jazz music can also be added to the text "A scene in which the main character is walking through town." Furthermore, blue colors and the sound of waves can be added to the text "A scene in which the main character is walking on the beach." In this way, the atmosphere of the scene can be optimized by automatically adjusting the color tones and music of the video.

[0094] The processing flow of the second embodiment will be briefly explained below.

[0095] Step 1: The audio input unit acquires audio data. For example, the audio data is collected using a microphone. The audio input unit can also acquire audio data using a microphone on a smartphone or tablet. Furthermore, the audio input unit can also read a recorded audio file. For example, the audio input unit can read an audio file in WAV format or MP3 format. Step 2: The text conversion unit converts the voice data acquired by the voice input unit into text. For example, the text conversion unit converts the voice data into text using a voice recognition algorithm. The text conversion unit can also convert the voice data into text using generative AI (e.g., text generation AI or multimodal generation AI). For example, the text conversion unit converts the voice data into text using voice recognition software. Step 3: The text editing unit edits the text converted by the text conversion unit. For example, the text editing unit makes grammatical corrections or style changes. The text editing unit can also add or delete content. For example, the text editing unit makes grammatical corrections using a grammar check algorithm. Step 4: The speech generation unit converts the text edited by the text editing unit into speech. For example, the speech generation unit converts the text into speech using speech synthesis technology. The speech generation unit can also convert the text into speech using generative AI. For example, the speech generation unit converts the text into speech using speech synthesis software. Step 5: The visual generation unit generates visual content based on the text. For example, the visual generation unit generates an image based on the text using the DALL-E API. The visual generation unit can also generate visual content based on the text using generative AI. For example, the visual generation unit generates an image based on the text using image generation software. Step 6: The relevance analysis unit analyzes and optimizes the relevance between the text and visual content. For example, the relevance analysis unit may use embedding functions to analyze the relevance between the text and visual content. The relevance analysis unit may also use generative AI to optimize the relevance between the text and visual content. For example, the relevance analysis unit may use co-occurrence analysis or semantic analysis to analyze the relevance between the text and visual content.

[0096] 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.

[0097] The data generation model 58 is a so-called generative AI (Artificial Intelligence). An example of the data generation model 58 is ChatGPT (registered trademark) (Internet search engine).<URL: https: / / openai.com / blog / chatgpt> Examples of generative AIs include the data generation model 58, such as a neural network model (e.g., a neural network model), and a neural network model (e.g., a neural network model). The data generation model 58 is obtained by performing deep learning on a neural network. A prompt including an instruction is input to the data generation model 58, and inference data such as voice data indicating speech, text data indicating text, and image data indicating an image is also input to the data generation model 58. The data generation model 58 performs inference on the input inference data in accordance with the instruction indicated by the prompt and outputs the inference result in a data format such as voice data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization. The specification processing unit 290 performs the above-mentioned specification processing using the data generation model 58. The data generation model 58 may be a fine-tuned model so as to output an inference result from a prompt that does not include an instruction. In this case, the data generation model 58 can output an inference result from a prompt that does not include an instruction. The data processing device 12 and the like include multiple types of data generation models 58, and the data generation model 58 includes AIs other than the generative AI. The AI ​​other than the generative AI may be, for example, linear regression, logistic regression, decision tree, random forest, support vector machine (SVM), k-means clustering, convolutional neural network (CNN), recurrent neural network (RNN), generative adversarial network (GAN), or naive Bayes, and can perform various processes, but is not limited to these examples. The AI ​​may also be an AI agent. When the processes of each of the above-mentioned parts are performed by AI, the processes may be performed in part or entirely by AI, but are not limited to these examples. The processes performed by AI, including the generative AI, may be replaced with rule-based processes.

[0098] 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.

[0099] [Second embodiment] FIG. 3 shows an example of the configuration of a data processing system 210 according to the second embodiment.

[0100] 3, the data processing system 210 includes the data processing device 12 and smart glasses 214. An example of the data processing device 12 is a server.

[0101] 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.

[0102] 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.

[0103] 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.

[0104] 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).

[0105] 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.

[0106] 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.

[0107] 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.

[0108] The storage 32 stores a data generation model 58 and an emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290. The identification processing unit 290 can estimate a user's emotion using the emotion identification model 59 and perform identification processing using the user's emotion. The emotion estimation function (emotion identification function) using the emotion identification model 59 performs various estimations and predictions regarding the user's emotion, including estimation and prediction of the user's emotion, but is not limited to these examples. Furthermore, the estimation and prediction of emotion also includes, for example, emotion analysis.

[0109] In the smart glasses 214, the specific processing is performed by the processor 46. A specific processing program 60 is stored in the storage 50. The processor 46 reads the specific processing program 60 from the storage 50 and executes the read specific processing program 60 on the RAM 48. The specific processing is realized by the processor 46 operating as the control unit 46A in accordance with the specific processing program 60 executed on the RAM 48. The smart glasses 214 also have a data generation model and an emotion identification model similar to the data generation model 58 and the emotion identification model 59, and can perform processing similar to that of the specific processing unit 290 using these models.

[0110] 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.

[0111] 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.

[0112] 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.

[0113] 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.

[0114] [Third embodiment] FIG. 5 shows an example of the configuration of a data processing system 310 according to the third embodiment.

[0115] 5, the data processing system 310 includes the data processing device 12 and a headset type terminal 314. An example of the data processing device 12 is a server.

[0116] 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.

[0117] 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.

[0118] 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.

[0119] 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).

[0120] 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.

[0121] Fig. 6 shows an example of the main functions of the data processing device 12 and the headset type terminal 314. As shown in Fig. 6, in the data processing device 12, a specific process is performed by the processor 28. A specific process program 56 is stored in the storage 32.

[0122] 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.

[0123] The storage 32 stores a data generation model 58 and an emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290. The identification processing unit 290 can estimate a user's emotion using the emotion identification model 59 and perform identification processing using the user's emotion. The emotion estimation function (emotion identification function) using the emotion identification model 59 performs various estimations and predictions regarding the user's emotion, including estimation and prediction of the user's emotion, but is not limited to these examples. Furthermore, the estimation and prediction of emotion also includes, for example, emotion analysis.

[0124] In the headset type terminal 314, the specific processing is performed by the processor 46. A specific processing program 60 is stored in the storage 50. The processor 46 reads the specific processing program 60 from the storage 50 and executes the read specific processing program 60 on the RAM 48. The specific processing is realized by the processor 46 operating as the control unit 46A in accordance with the specific processing program 60 executed on the RAM 48. Note that the headset type terminal 314 has a data generation model and an emotion identification model similar to the data generation model 58 and the emotion identification model 59, and can also perform processing similar to that of the specific processing unit 290 using these models.

[0125] 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.

[0126] 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.

[0127] 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.

[0128] 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.

[0129] [Fourth embodiment] FIG. 7 shows an example of the configuration of a data processing system 410 according to the fourth embodiment.

[0130] 7, the data processing system 410 includes a data processing device 12 and a robot 414. An example of the data processing device 12 is a server.

[0131] 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.

[0132] 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.

[0133] 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.

[0134] 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).

[0135] 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.

[0136] 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.

[0137] 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.

[0138] 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.

[0139] The storage 32 stores a data generation model 58 and an emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290. The identification processing unit 290 can estimate a user's emotion using the emotion identification model 59 and perform identification processing using the user's emotion. The emotion estimation function (emotion identification function) using the emotion identification model 59 performs various estimations and predictions regarding the user's emotion, including estimation and prediction of the user's emotion, but is not limited to these examples. Furthermore, the estimation and prediction of emotion also includes, for example, emotion analysis.

[0140] In the robot 414, the specific processing is performed by the processor 46. A specific processing program 60 is stored in the storage 50. The processor 46 reads the specific processing program 60 from the storage 50 and executes the read specific processing program 60 on the RAM 48. The specific processing is realized by the processor 46 operating as the control unit 46A in accordance with the specific processing program 60 executed on the RAM 48. The robot 414 has a data generation model and an emotion identification model similar to the data generation model 58 and the emotion identification model 59, and can also perform processing similar to that of the specific processing unit 290 using these models.

[0141] 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.

[0142] 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.

[0143] 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.

[0144] 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.

[0145] 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.

[0146] 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.

[0147] 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.

[0148] 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).

[0149] 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.

[0150] 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."

[0151] 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.

[0152] 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.

[0153] 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.

[0154] 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.

[0155] 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.

[0156] 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.

[0157] 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.

[0158] 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.

[0159] 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.

[0160] 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.

[0161] The above-described description and illustrations are a detailed explanation of the parts related to the technology of the present disclosure and are merely an example of the technology of the present disclosure. For example, the above description of the configuration, functions, actions, and effects is an explanation of an example of the configuration, functions, actions, and effects of the parts related to the technology of the present disclosure. Therefore, it goes without saying that unnecessary parts may be deleted, new elements may be added, or replacements may be made to the above-described description and illustrations within the scope of the gist of the technology of the present disclosure. Furthermore, to avoid confusion and facilitate understanding of the parts related to the technology of the present disclosure, the above-described description and illustrations omit explanations of common technical knowledge that do not require particular explanation to enable the implementation of the technology of the present disclosure.

[0162] 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]

[0163] 10, 210, 310, 410 Data Processing Systems 12 Data Processing Device 14 Smart Devices 214 Smart Glasses 314 Headset-type terminal 414 Robot

Claims

1. a voice input unit that acquires voice data; a text conversion unit that converts the voice data acquired by the voice input unit into text; a text editing unit that edits the text converted by the text conversion unit; a voice generating unit that converts the text edited by the text editing unit into voice; a visual generation unit that generates visual content based on the text; a relevance analysis unit that analyzes and optimizes the relevance between the text and the visual content. A system characterized by:

2. The voice input unit Analyzing background or environmental sounds contained in the audio data and reflecting the atmosphere of the scene in the text.

2. The system of claim 1.

3. The voice input unit The generative AI estimates the speaker's emotions contained in the audio data, and adjusts the tone and expression of the text based on those emotions.

2. The system of claim 1.

4. The voice input unit The voices of the multiple speakers included in the voice data are simultaneously analyzed, and the text is generated in a dialogue format.

2. The system of claim 1.

5. The voice input unit Automatically translating the voice data in different languages ​​into the text 2. The system of claim 1.

6. The voice input unit Combine gesture or facial expression recognition to reflect more detailed scene descriptions in the text 2. The system of claim 1.

Images