System

Abstract

An object of the system according to the embodiment is to efficiently store and regenerate high-resolution media while saving a storage space and a communication band.SOLUTION: A system according to an embodiment includes a file conversion unit, a storage unit, a metadata management unit, and a regeneration unit. The file converter converts the file into a text-based prompt. The storage unit stores the text-based prompt converted by the file conversion unit. The metadata management unit adds metadata and version management information to the text-based prompt stored by the storage unit. The regeneration unit regenerates the high-resolution media based on the text-based prompt.SELECTED DRAWING: Figure 1

Description

[Technical Field]

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

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

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

[0004] Conventional technologies have the drawback of requiring a large amount of storage space and communication bandwidth to directly store large media files, resulting in high costs.

[0005] The system according to the embodiment aims to efficiently store and reproduce high-resolution media while conserving storage space and communication bandwidth. [Means for solving the problem]

[0006] The system according to an embodiment includes a file conversion unit, a storage unit, a metadata management unit, and a regeneration unit. The file conversion unit converts a file into a text-based prompt. The storage unit stores the text-based prompt converted by the file conversion unit. The metadata management unit adds metadata and version control information to the text-based prompt stored by the storage unit. The regeneration unit regenerates high-resolution media based on the text-based prompt. [Effects of the Invention]

[0007] Systems according to embodiments can efficiently store and reproduce high-resolution media while conserving storage space and communication bandwidth. [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) In a data management system according to an embodiment of the present invention, a generation AI converts files to be saved into text-based prompts, stores the prompts in storage, and then regenerates high-resolution media when needed. This allows the data management system to significantly reduce storage space and communication bandwidth by storing only small text data instead of directly storing large media files. Furthermore, by utilizing in-house or third-party AI models and focusing on metadata and version management, long-term data access and cost reductions can be achieved.

[0029] A data management system according to an embodiment includes a file conversion unit, a storage unit, a metadata management unit, and a regeneration unit. The file conversion unit converts files into text-based prompts. For example, a generation AI analyzes a high-resolution image file and generates a text prompt such as "A landscape with a blue sky and white clouds." The generation AI can also analyze an audio file and convert its content into a text prompt. The generation AI can also analyze a video file and convert its content into a text prompt. The storage unit stores the text-based prompts converted by the file conversion unit. For example, instead of storing a 1 GB image file, a text prompt of a few KB can be stored. The storage unit can also store the text prompts in cloud storage or local storage. The storage unit can also compress and store the text prompts. The metadata management unit adds metadata and version control information to the text-based prompts stored by the storage unit. For example, the metadata includes information such as the file creation date and time, the creator, and the file type. Version control allows the file's change history to be tracked and the file can be restored to a previous version if necessary. The metadata management unit also records file usage and access frequency, which can be used for future data management. The regeneration unit regenerates high-resolution media based on text-based prompts. For example, if the saved text prompt "A landscape with blue skies and white clouds" is input to the generation AI, the generation AI regenerates a high-resolution landscape image based on the prompt. The regeneration unit can also regenerate audio and video files. Furthermore, the regeneration unit can simultaneously generate media in different formats. This allows the data management system according to the embodiment to efficiently manage large volumes of media files and save storage space and communication bandwidth. For example, if a company stores a large amount of image data, this method can significantly reduce storage costs. Furthermore, metadata and version management enable long-term data access while maintaining data integrity.

[0030] The file conversion unit can refer to related external data when analyzing the contents of a file to generate more detailed text prompts. For example, the generation AI in the file conversion unit analyzes an image file and refers to related news articles to understand the context. For example, it analyzes images of a sporting event and generates a detailed text prompt such as "Scenes from the 2023 Olympics." The file conversion unit also analyzes audio files and refers to related academic papers to understand the context. For example, it analyzes the audio of a scientific lecture and generates a detailed text prompt such as "The latest research presentation by a Nobel Prize winner." The file conversion unit also analyzes video files and refers to related external data to understand the context. For example, it analyzes a historical documentary video and generates a detailed text prompt such as "A documentary depicting battle scenes from World War II." This allows more detailed text prompts to be generated by referencing external data.

[0031] The file conversion unit can analyze the contents of a file from multiple perspectives and generate multiple different text prompts. For example, the file conversion unit uses a generation AI to analyze an image file and generate text prompts from different perspectives. For example, it analyzes a landscape image and generates multiple text prompts such as "a landscape with a blue sky and white clouds" and "a landscape with a range of mountains." The file conversion unit also uses a generation AI to analyze an audio file and generate text prompts from different perspectives. For example, it analyzes an interview audio and generates multiple text prompts such as "the scene where the interviewer is asking a question" and "the scene where the interviewee is answering." The file conversion unit also uses a generation AI to analyze a video file and generate text prompts from different perspectives. For example, it analyzes a video of a sports game and generates multiple text prompts such as "the moment a player scores a goal" and "the moment the audience cheers." This allows for the generation of a variety of text prompts by analyzing from multiple perspectives.

[0032] The file conversion unit can also simultaneously analyze audio or video multimedia data and reflect it in text prompts. For example, the file conversion unit uses a generation AI to simultaneously analyze image and audio files and reflect it in text prompts. For example, it analyzes the images and audio of a presentation and generates a text prompt such as, "The graph displayed on the slide and its explanation." The file conversion unit also uses a generation AI to analyze video files and reflect both the video and audio in text prompts. For example, it analyzes a movie trailer and generates a text prompt such as, "The action scene and its background music." The file conversion unit also uses a generation AI to simultaneously analyze audio and image files and reflect it in text prompts. For example, it analyzes images and audio from a music concert and generates a text prompt such as, "The band on stage and the song being played." This allows multimedia data to be analyzed simultaneously and reflected in text prompts.

[0033] The file conversion unit can simultaneously generate text prompts in different languages, achieving multilingual support. For example, in the file conversion unit, the generation AI analyzes image files and generates text prompts in different languages. For example, it analyzes landscape images and generates multilingual text prompts such as "A landscape with blue sky and white clouds." In addition, in the file conversion unit, the generation AI analyzes audio files and generates text prompts in different languages. For example, it analyzes the audio of a lecture and generates multilingual text prompts such as "A scene where an inspiring speech is being delivered" and "A moving speech is being delivered." In addition, in the file conversion unit, the generation AI analyzes video files and generates text prompts in different languages. For example, it analyzes a documentary video and generates multilingual text prompts such as "A video depicting historical scenes" and "A video depicting historical scenes." This achieves multilingual support and allows the generation of text prompts in different languages.

[0034] The storage unit can improve access speed by optimizing the storage location based on the importance and frequency of use of the prompt when saving the text prompt. For example, the storage unit optimizes the storage location based on the importance of the prompt when saving the text prompt. For example, it saves prompts with high importance in storage that can be accessed quickly. Furthermore, the storage unit optimizes the storage location based on the frequency of use of the prompt when saving the text prompt. For example, it saves prompts with high frequency of use in a cache to improve access speed. Furthermore, the storage unit optimizes the storage location by combining the importance and frequency of use of the prompt when saving the text prompt. For example, it saves prompts with high importance and frequency of use in the fastest storage. In this way, optimizing the storage location improves access speed.

[0035] The storage unit can encrypt the contents of the text prompt when saving it, thereby enhancing security. For example, the storage unit encrypts the contents of the prompt when saving it. For example, the prompt is encrypted using AES encryption to enhance security. The storage unit also encrypts the contents of the prompt when saving it. For example, the prompt is encrypted using RSA encryption to enhance security. The storage unit also encrypts the contents of the prompt when saving it. For example, the prompt is encrypted using hybrid encryption to enhance security. In this way, security can be enhanced by encrypting the contents of the prompt.

[0036] The storage unit can combine cloud storage and local storage to achieve hybrid storage when storing text prompts. For example, the storage unit combines cloud storage and local storage to achieve hybrid storage when storing text prompts. For example, important prompts are stored in the cloud and frequently accessed prompts are stored locally. The storage unit also combines cloud storage and local storage to achieve hybrid storage when storing text prompts. For example, prompts are stored in the cloud for backup and stored locally for working. The storage unit also combines cloud storage and local storage to achieve hybrid storage when storing text prompts. For example, prompts stored in the cloud are cached locally to improve access speed. This allows hybrid storage to be achieved by combining cloud storage and local storage.

[0037] The storage unit can compress the content of the text prompt when saving it, thereby further saving storage space. For example, the storage unit compresses the content of the prompt when saving it. For example, it compresses the prompt using gzip compression to save storage space. The storage unit also compresses the content of the prompt when saving it. For example, it compresses the prompt using LZMA compression to save storage space. The storage unit also compresses the content of the prompt when saving it. For example, it compresses the prompt using Brotli compression to save storage space. Thus, by compressing the content of the prompt, it is possible to further save storage space.

[0038] The metadata management unit records the file usage status and access frequency in the metadata, which can be useful for future data management. The metadata management unit, for example, records the file usage status and access frequency in the metadata, which can be useful for future data management. For example, the number of times a prompt has been accessed and the last access date and time are recorded as metadata. The metadata management unit also records the file usage status and access frequency in the metadata, which can be useful for future data management. For example, the prompt usage frequency and usage time are recorded as metadata. The metadata management unit also records the file usage status and access frequency in the metadata, which can be useful for future data management. For example, the prompt usage history and user information are recorded as metadata. In this way, recording the usage status and access frequency can be useful for future data management.

[0039] The metadata management unit can enable uniform management of metadata and version management across different storage systems. The metadata management unit, for example, enables uniform management of metadata and version management across different storage systems. For example, a system is constructed that uniformly manages metadata for cloud storage and local storage. The metadata management unit also enables uniform management of metadata and version management across different storage systems. For example, a system is constructed that unifies metadata and version management across different cloud services. The metadata management unit also enables uniform management of metadata and version management across different storage systems. For example, a system is constructed that unifies metadata and version management between on-premise and cloud storage systems. This enables uniform management across different storage systems.

[0040] The metadata management unit can add information indicating file relationships and interdependencies to the metadata, thereby visualizing the data relationships. The metadata management unit, for example, adds information indicating file relationships and interdependencies to the metadata, thereby visualizing the data relationships. For example, related prompts are linked together and visually displayed. The metadata management unit also adds information indicating file relationships and interdependencies to the metadata, thereby visualizing the data relationships. For example, prompt dependencies are displayed in a graph, making it easier to understand visually. The metadata management unit also adds information indicating file relationships and interdependencies to the metadata, thereby visualizing the data relationships. For example, prompt relationships are displayed in a treemap, making it easier to understand visually. In this way, visualizing data relationships makes data management easier.

[0041] The regeneration unit can generate more detailed media by referencing related external data to understand the context of the original file when regenerating the high-resolution media. For example, when the generation AI regenerates the high-resolution media, the regeneration unit references related news articles to understand the context of the original file and generates more detailed media. For example, when regenerating images of a sporting event, the regeneration unit references related news articles to generate detailed images. Furthermore, when the generation AI regenerates the high-resolution media, the regeneration unit references related academic papers to understand the context of the original file and generates more detailed media. For example, when regenerating audio of a scientific lecture, the regeneration unit references related academic papers to generate detailed audio. Furthermore, when the generation AI regenerates the high-resolution media, the regeneration unit references related external data to understand the context of the original file and generates more detailed media. For example, when regenerating a historical documentary video, the regeneration unit references related external data to generate detailed video. In this way, by referencing external data, more detailed media can be generated.

[0042] The regeneration unit generates media from multiple different viewpoints when regenerating high-resolution media, providing the user with options. For example, when the generation AI regenerates high-resolution media, the regeneration unit generates media from multiple different viewpoints to provide the user with options. For example, when regenerating a landscape image, the regeneration unit generates multiple images, such as a "landscape with a blue sky and white clouds" and a "landscape with a range of mountains." Furthermore, when the generation AI regenerates high-resolution media, the regeneration unit generates media from multiple different viewpoints to provide the user with options. For example, when regenerating an interview video, the regeneration unit generates multiple videos, such as "a scene where the interviewer is asking a question" and "a scene where the interviewee is answering." Furthermore, when the generation AI regenerates high-resolution media, the regeneration unit generates media from multiple different viewpoints to provide the user with options. For example, when regenerating a video of a sports game, the regeneration unit generates multiple videos, such as "the moment a player scores a goal" and "the moment the spectators cheer." This allows media to be generated from multiple viewpoints, providing the user with options.

[0043] The regeneration unit can simultaneously generate media in different formats when regenerating high-resolution media. For example, the regeneration unit simultaneously generates media in different formats when the generation AI regenerates high-resolution media. For example, when regenerating a landscape image, the regeneration unit simultaneously generates an audio file describing the landscape. The regeneration unit also simultaneously generates media in different formats when the generation AI regenerates high-resolution media. For example, when regenerating a video of a sporting event, the regeneration unit simultaneously generates highlight images of the event. The regeneration unit also simultaneously generates media in different formats when the generation AI regenerates high-resolution media. For example, when regenerating the audio of a lecture, the regeneration unit simultaneously generates slide images of the lecture. This allows media in different formats to be generated simultaneously.

[0044] The regeneration unit can simultaneously generate media in different languages ​​when regenerating high-resolution media, thereby achieving multilingual support. For example, the regeneration unit simultaneously generates media in different languages ​​when the generation AI regenerates high-resolution media. For example, when regenerating a landscape image, the regeneration unit simultaneously generates a description of the landscape in multiple languages. The regeneration unit also simultaneously generates media in different languages ​​when the generation AI regenerates high-resolution media. For example, when regenerating the audio of a lecture, the regeneration unit simultaneously generates the content of the lecture in multiple languages. The regeneration unit also simultaneously generates media in different languages ​​when the generation AI regenerates high-resolution media. For example, when regenerating a documentary video, the regeneration unit simultaneously generates subtitles for the video in multiple languages. This achieves multilingual support and allows media in different languages ​​to be generated simultaneously.

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

[0046] The file conversion unit can refer to related external data when analyzing the contents of a file to generate more detailed text prompts. For example, the generation AI analyzes an image file and refers to related news articles to understand the context. For example, it analyzes images of a sporting event and generates a detailed text prompt such as "Scenes from the 2023 Olympics." The generation AI also analyzes audio files and refers to related academic papers to understand the context. For example, it analyzes the audio of a scientific lecture and generates a detailed text prompt such as "The latest research presentation by a Nobel Prize winner." The generation AI also analyzes video files and refers to related external data to understand the context. For example, it analyzes a historical documentary video and generates a detailed text prompt such as "A documentary depicting battle scenes from World War II." This allows more detailed text prompts to be generated by referencing external data.

[0047] The file conversion unit can analyze the contents of a file from multiple perspectives and generate multiple different text prompts. For example, the generation AI analyzes an image file and generates text prompts from different perspectives. For example, it analyzes a landscape image and generates multiple text prompts such as "a landscape with a blue sky and white clouds" and "a landscape with a range of mountains." The generation AI also analyzes audio files and generates text prompts from different perspectives. For example, it analyzes interview audio and generates multiple text prompts such as "the scene where the interviewer is asking a question" and "the scene where the interviewee is answering." The generation AI also analyzes video files and generates text prompts from different perspectives. For example, it analyzes a video of a sports game and generates multiple text prompts such as "the moment a player scores a goal" and "the moment the audience cheers." This allows for the generation of a variety of text prompts by analyzing from multiple perspectives.

[0048] The file conversion unit can also simultaneously analyze audio or video multimedia data and reflect it in text prompts. For example, the generation AI can simultaneously analyze image and audio files and reflect it in text prompts. For example, it can analyze the images and audio of a presentation and generate a text prompt such as, "The graph displayed on the slide and its explanation." The generation AI can also analyze video files and reflect both the image and audio in the text prompt. For example, it can analyze a movie trailer and generate a text prompt such as, "The action scene and its background music." The generation AI can also simultaneously analyze audio and image files and reflect it in text prompts. For example, it can analyze the images and audio of a music concert and generate a text prompt such as, "The band on stage and the song being played." This allows multimedia data to be analyzed simultaneously and reflected in text prompts.

[0049] The file conversion unit can simultaneously generate text prompts in different languages, achieving multilingual support. For example, the generation AI analyzes image files and generates text prompts in different languages. For example, it analyzes landscape images and generates multilingual text prompts such as "A landscape with blue sky and white clouds." The generation AI also analyzes audio files and generates text prompts in different languages. For example, it analyzes the audio of a lecture and generates multilingual text prompts such as "A scene where an inspiring speech is being delivered" and "A moving speech is being delivered." The generation AI also analyzes video files and generates text prompts in different languages. For example, it analyzes a documentary video and generates multilingual text prompts such as "A video depicting historical scenes." This enables multilingual support and the generation of text prompts in different languages.

[0050] The storage unit can improve access speed by optimizing the storage location based on the importance and frequency of use of the prompt when saving the text prompt. For example, when saving the text prompt, the storage location is optimized based on the importance of the prompt. For example, prompts with high importance are saved in storage that can be accessed quickly. Furthermore, when saving the text prompt, the storage location is optimized based on the frequency of use of the prompt. For example, frequently used prompts are saved in a cache to improve access speed. Furthermore, when saving the text prompt, the storage location is optimized by combining the importance and frequency of use of the prompt. For example, prompts with high importance and high frequency of use are saved in the fastest storage. In this way, optimizing the storage location improves access speed.

[0051] The storage unit can encrypt the contents of the text prompt when saving it, thereby enhancing security. For example, the storage unit encrypts the contents of the prompt when saving it. For example, the storage unit encrypts the contents of the prompt using AES encryption to enhance security. Furthermore, the storage unit encrypts the contents of the prompt when saving it. For example, the storage unit encrypts the prompt using RSA encryption to enhance security. Furthermore, the storage unit encrypts the contents of the prompt when saving it. For example, the storage unit encrypts the prompt using hybrid encryption to enhance security. In this way, security can be enhanced by encrypting the contents of the prompt.

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

[0053] Step 1: The file conversion unit converts the file into a text-based prompt. For example, the generation AI can analyze a high-resolution image file and generate a text prompt such as "A landscape with a blue sky and white clouds." The generation AI can also analyze audio and video files and convert their contents into text prompts. Step 2: The storage unit stores the text-based prompt converted by the file conversion unit. For example, instead of storing a 1GB image file, a text prompt of a few KB can be stored. The storage unit can also store the text prompt in cloud storage or local storage, and can further compress and store it. Step 3: The metadata manager adds metadata and version control information to the text-based prompts saved by the storage unit. For example, metadata includes information such as the file's creation date and time, its creator, and the file type. Version control also allows the file's change history to be tracked and previous versions to be reverted if necessary. Furthermore, the metadata manager records the file's usage and access frequency, which can be used for future data management. Step 4: The regeneration unit regenerates high-resolution media based on a text-based prompt. For example, if the saved text prompt "A landscape with blue skies and white clouds" is input into the generation AI, the AI ​​will regenerate a high-resolution landscape image based on that prompt. The regeneration unit can also regenerate audio and video files, and can simultaneously generate media in different formats.

[0054] (Example 2) In a data management system according to an embodiment of the present invention, a generation AI converts files to be saved into text-based prompts, stores the prompts in storage, and then regenerates high-resolution media when needed. This allows the data management system to significantly reduce storage space and communication bandwidth by storing only small text data instead of directly storing large media files. Furthermore, by utilizing in-house or third-party AI models and focusing on metadata and version management, long-term data access and cost reductions can be achieved.

[0055] A data management system according to an embodiment includes a file conversion unit, a storage unit, a metadata management unit, and a regeneration unit. The file conversion unit converts files into text-based prompts. For example, a generation AI analyzes a high-resolution image file and generates a text prompt such as "A landscape with a blue sky and white clouds." The generation AI can also analyze an audio file and convert its content into a text prompt. The generation AI can also analyze a video file and convert its content into a text prompt. The storage unit stores the text-based prompts converted by the file conversion unit. For example, instead of storing a 1 GB image file, a text prompt of a few KB can be stored. The storage unit can also store the text prompts in cloud storage or local storage. The storage unit can also compress and store the text prompts. The metadata management unit adds metadata and version control information to the text-based prompts stored by the storage unit. For example, the metadata includes information such as the file creation date and time, the creator, and the file type. Version control allows the file's change history to be tracked and the file can be restored to a previous version if necessary. The metadata management unit also records file usage and access frequency, which can be used for future data management. The regeneration unit regenerates high-resolution media based on text-based prompts. For example, if the saved text prompt "A landscape with blue skies and white clouds" is input to the generation AI, the generation AI regenerates a high-resolution landscape image based on the prompt. The regeneration unit can also regenerate audio and video files. Furthermore, the regeneration unit can simultaneously generate media in different formats. This allows the data management system according to the embodiment to efficiently manage large volumes of media files and save storage space and communication bandwidth. For example, if a company stores a large amount of image data, this method can significantly reduce storage costs. Furthermore, metadata and version management enable long-term data access while maintaining data integrity.

[0056] The file conversion unit can use an emotion estimation function to estimate the emotion associated with the file when analyzing the contents of the file and generate a text prompt that reflects that emotion. For example, the file conversion unit uses a generation AI to analyze an image file and estimate the emotion contained in the image. For example, it analyzes an image containing a smiling person and generates a text prompt that reflects the emotion, such as "a scene in which a smiling person is having fun." The file conversion unit also uses a generation AI to analyze an audio file and estimate the emotion contained in the audio. For example, it analyzes an emotional speech and generates a text prompt that reflects the emotion, such as "a scene in which an emotional speech is being delivered." The file conversion unit also uses a generation AI to analyze a video file and estimate the emotion contained in the video. For example, it analyzes a video that contains an emotional scene and generates a text prompt that reflects the emotion, such as "a video in which an emotional scene unfolds." This makes it possible to generate a text prompt that reflects the emotional value of the file.

[0057] The file conversion unit can refer to related external data when analyzing the contents of a file to generate more detailed text prompts. For example, the generation AI in the file conversion unit analyzes an image file and refers to related news articles to understand the context. For example, it analyzes images of a sporting event and generates a detailed text prompt such as "Scenes from the 2023 Olympics." The file conversion unit also analyzes audio files and refers to related academic papers to understand the context. For example, it analyzes the audio of a scientific lecture and generates a detailed text prompt such as "The latest research presentation by a Nobel Prize winner." The file conversion unit also analyzes video files and refers to related external data to understand the context. For example, it analyzes a historical documentary video and generates a detailed text prompt such as "A documentary depicting battle scenes from World War II." This allows more detailed text prompts to be generated by referencing external data.

[0058] The file conversion unit can analyze the contents of a file from multiple perspectives and generate multiple different text prompts. For example, the file conversion unit uses a generation AI to analyze an image file and generate text prompts from different perspectives. For example, it analyzes a landscape image and generates multiple text prompts such as "a landscape with a blue sky and white clouds" and "a landscape with a range of mountains." The file conversion unit also uses a generation AI to analyze an audio file and generate text prompts from different perspectives. For example, it analyzes an interview audio and generates multiple text prompts such as "the scene where the interviewer is asking a question" and "the scene where the interviewee is answering." The file conversion unit also uses a generation AI to analyze a video file and generate text prompts from different perspectives. For example, it analyzes a video of a sports game and generates multiple text prompts such as "the moment a player scores a goal" and "the moment the audience cheers." This allows for the generation of a variety of text prompts by analyzing from multiple perspectives.

[0059] The file conversion unit can also simultaneously analyze audio or video multimedia data and reflect it in text prompts. For example, the file conversion unit uses a generation AI to simultaneously analyze image and audio files and reflect it in text prompts. For example, it analyzes the images and audio of a presentation and generates a text prompt such as, "The graph displayed on the slide and its explanation." The file conversion unit also uses a generation AI to analyze video files and reflect both the video and audio in text prompts. For example, it analyzes a movie trailer and generates a text prompt such as, "The action scene and its background music." The file conversion unit also uses a generation AI to simultaneously analyze audio and image files and reflect it in text prompts. For example, it analyzes images and audio from a music concert and generates a text prompt such as, "The band on stage and the song being played." This allows multimedia data to be analyzed simultaneously and reflected in text prompts.

[0060] The file conversion unit can simultaneously generate text prompts in different languages, achieving multilingual support. For example, in the file conversion unit, the generation AI analyzes image files and generates text prompts in different languages. For example, it analyzes landscape images and generates multilingual text prompts such as "A landscape with blue sky and white clouds." In addition, in the file conversion unit, the generation AI analyzes audio files and generates text prompts in different languages. For example, it analyzes the audio of a lecture and generates multilingual text prompts such as "A scene where an inspiring speech is being delivered" and "A moving speech is being delivered." In addition, in the file conversion unit, the generation AI analyzes video files and generates text prompts in different languages. For example, it analyzes a documentary video and generates multilingual text prompts such as "A video depicting historical scenes" and "A video depicting historical scenes." This achieves multilingual support and allows the generation of text prompts in different languages.

[0061] The file conversion unit can use the emotion estimation function to monitor the user's emotions in real time and generate text prompts according to the user's emotions. For example, the file conversion unit uses a generation AI to analyze image files, monitor the user's emotions in real time, and generate text prompts. For example, if the user is moved, it generates a text prompt such as "an image of an inspiring landscape." The file conversion unit also uses a generation AI to analyze audio files, monitor the user's emotions in real time, and generate text prompts. For example, if the user is excited, it generates a text prompt such as "a scene where an exciting speech is being given." The file conversion unit also uses a generation AI to analyze video files, monitor the user's emotions in real time, and generate text prompts. For example, if the user is surprised, it generates a text prompt such as "a video showing a surprising scene." This makes it possible to generate text prompts according to the user's emotions.

[0062] The storage unit can use the emotion estimation function to add emotional information related to the prompt as metadata when saving the text prompt. For example, when saving the text prompt, the storage unit uses the emotion estimation function to add emotional information related to the prompt as metadata. For example, the storage unit adds emotional information "emotional" to a prompt such as "an image of an inspiring landscape." Furthermore, when saving the text prompt, the storage unit uses the emotion estimation function to add emotional information related to the prompt as metadata. For example, the storage unit adds emotional information "excited" to a prompt such as "a scene in which an exciting speech is being given." Furthermore, when saving the text prompt, the storage unit uses the emotion estimation function to add emotional information related to the prompt as metadata. For example, the storage unit adds emotional information "surprise" to a prompt such as "a video in which a surprising scene unfolds." In this way, by adding emotional information as metadata, the emotional value of the prompt can be managed.

[0063] The storage unit can improve access speed by optimizing the storage location based on the importance and frequency of use of the prompt when saving the text prompt. For example, the storage unit optimizes the storage location based on the importance of the prompt when saving the text prompt. For example, it saves prompts with high importance in storage that can be accessed quickly. Furthermore, the storage unit optimizes the storage location based on the frequency of use of the prompt when saving the text prompt. For example, it saves prompts with high frequency of use in a cache to improve access speed. Furthermore, the storage unit optimizes the storage location by combining the importance and frequency of use of the prompt when saving the text prompt. For example, it saves prompts with high importance and frequency of use in the fastest storage. In this way, optimizing the storage location improves access speed.

[0064] The storage unit can encrypt the contents of the text prompt when saving it, thereby enhancing security. For example, the storage unit encrypts the contents of the prompt when saving it. For example, the prompt is encrypted using AES encryption to enhance security. The storage unit also encrypts the contents of the prompt when saving it. For example, the prompt is encrypted using RSA encryption to enhance security. The storage unit also encrypts the contents of the prompt when saving it. For example, the prompt is encrypted using hybrid encryption to enhance security. In this way, security can be enhanced by encrypting the contents of the prompt.

[0065] The storage unit can combine cloud storage and local storage to achieve hybrid storage when storing text prompts. For example, the storage unit combines cloud storage and local storage to achieve hybrid storage when storing text prompts. For example, important prompts are stored in the cloud and frequently accessed prompts are stored locally. The storage unit also combines cloud storage and local storage to achieve hybrid storage when storing text prompts. For example, prompts are stored in the cloud for backup and stored locally for working. The storage unit also combines cloud storage and local storage to achieve hybrid storage when storing text prompts. For example, prompts stored in the cloud are cached locally to improve access speed. This allows hybrid storage to be achieved by combining cloud storage and local storage.

[0066] The storage unit can compress the content of the text prompt when saving it, thereby further saving storage space. For example, the storage unit compresses the content of the prompt when saving it. For example, it compresses the prompt using gzip compression to save storage space. The storage unit also compresses the content of the prompt when saving it. For example, it compresses the prompt using LZMA compression to save storage space. The storage unit also compresses the content of the prompt when saving it. For example, it compresses the prompt using Brotli compression to save storage space. Thus, by compressing the content of the prompt, it is possible to further save storage space.

[0067] The storage unit can analyze the user's emotions using the emotion estimation function and suggest a saving method based on the emotions. For example, when saving text prompts, the storage unit uses the emotion estimation function to analyze the user's emotions and suggest a saving method based on the emotions. For example, if the user is moved, the storage unit prioritizes saving moving prompts. Furthermore, when saving text prompts, the storage unit uses the emotion estimation function to analyze the user's emotions and suggest a saving method based on the emotions. For example, if the user is excited, the storage unit prioritizes saving prompts that cause excitement. Furthermore, when saving text prompts, the storage unit uses the emotion estimation function to analyze the user's emotions and suggest a saving method based on the emotions. For example, if the user is surprised, the storage unit prioritizes saving prompts that cause surprise. In this way, a saving method based on the user's emotions can be suggested.

[0068] The metadata management unit can add emotion information estimated using the emotion estimation function to the metadata and manage the emotional value of the file. The metadata management unit, for example, adds emotion information estimated using the emotion estimation function to the metadata and manages the emotional value of the file. For example, emotion information "emotional" is added as metadata to a prompt such as "an image of an inspiring landscape." The metadata management unit also adds emotion information estimated using the emotion estimation function to the metadata and manages the emotional value of the file. For example, emotion information "excited" is added as metadata to a prompt such as "a scene in which an exciting speech is being given." The metadata management unit also adds emotion information estimated using the emotion estimation function to the metadata and manages the emotional value of the file. For example, emotion information "surprise" is added as metadata to a prompt such as "a video in which a surprising scene unfolds." In this way, the emotional value of the file can be managed by adding emotion information.

[0069] The metadata management unit can track not only the change history of a file in version control, but also changes in emotion associated with the change. For example, in version control, the metadata management unit tracks not only the change history of a file, but also changes in emotion associated with the change. For example, it records changes in emotion scores associated with changes to prompts and tracks changes in emotion. Furthermore, in version control, the metadata management unit tracks not only the change history of a file, but also changes in emotion associated with the change. For example, it records changes in emotion associated with modifications to prompts and tracks changes in emotion. Furthermore, in version control, the metadata management unit tracks not only the change history of a file, but also changes in emotion associated with the change. For example, it records changes in emotion associated with addition or deletion of prompts and tracks changes in emotion. In this way, the emotional value of a file can be managed by tracking changes in emotion associated with changes.

[0070] The metadata management unit records the file usage status and access frequency in the metadata, which can be useful for future data management. The metadata management unit, for example, records the file usage status and access frequency in the metadata, which can be useful for future data management. For example, the number of times a prompt has been accessed and the last access date and time are recorded as metadata. The metadata management unit also records the file usage status and access frequency in the metadata, which can be useful for future data management. For example, the prompt usage frequency and usage time are recorded as metadata. The metadata management unit also records the file usage status and access frequency in the metadata, which can be useful for future data management. For example, the prompt usage history and user information are recorded as metadata. In this way, recording the usage status and access frequency can be useful for future data management.

[0071] The metadata management unit can enable uniform management of metadata and version management across different storage systems. The metadata management unit, for example, enables uniform management of metadata and version management across different storage systems. For example, a system is constructed that uniformly manages metadata for cloud storage and local storage. The metadata management unit also enables uniform management of metadata and version management across different storage systems. For example, a system is constructed that unifies metadata and version management across different cloud services. The metadata management unit also enables uniform management of metadata and version management across different storage systems. For example, a system is constructed that unifies metadata and version management between on-premise and cloud storage systems. This enables uniform management across different storage systems.

[0072] The metadata management unit can add information indicating file relationships and interdependencies to the metadata, thereby visualizing the data relationships. The metadata management unit, for example, adds information indicating file relationships and interdependencies to the metadata, thereby visualizing the data relationships. For example, related prompts are linked together and visually displayed. The metadata management unit also adds information indicating file relationships and interdependencies to the metadata, thereby visualizing the data relationships. For example, prompt dependencies are displayed in a graph, making it easier to understand visually. The metadata management unit also adds information indicating file relationships and interdependencies to the metadata, thereby visualizing the data relationships. For example, prompt relationships are displayed in a treemap, making it easier to understand visually. In this way, visualizing data relationships makes data management easier.

[0073] The metadata management unit can use the emotion estimation function to propose a version management method based on the user's emotion. For example, the metadata management unit uses the emotion estimation function for metadata and version management to propose a version management method based on the user's emotion. For example, it prioritizes saving a version that moved the user. Also, the metadata management unit uses the emotion estimation function for metadata and version management to propose a version management method based on the user's emotion. For example, it prioritizes saving a version that excited the user. Also, the metadata management unit uses the emotion estimation function for metadata and version management to propose a version management method based on the user's emotion. For example, it prioritizes saving a version that surprised the user. In this way, it is possible to propose a version management method based on the user's emotion.

[0074] The regeneration unit can use the emotion estimation function to generate media that reflects the user's emotions when regenerating high-resolution media. For example, when the generation AI regenerates high-resolution media, the regeneration unit uses the emotion estimation function to generate media that reflects the user's emotions. For example, if the user is moved, the regeneration unit generates an emotional landscape image. Furthermore, when the generation AI regenerates high-resolution media, the regeneration unit uses the emotion estimation function to generate media that reflects the user's emotions. For example, if the user is excited, the regeneration unit generates a video that includes an exciting scene. Furthermore, when the generation AI regenerates high-resolution media, the regeneration unit uses the emotion estimation function to generate media that reflects the user's emotions. For example, if the user is surprised, the regeneration unit generates an image that includes a surprising scene. In this way, media that reflects the user's emotions can be generated.

[0075] The regeneration unit can generate more detailed media by referencing related external data to understand the context of the original file when regenerating the high-resolution media. For example, when the generation AI regenerates the high-resolution media, the regeneration unit references related news articles to understand the context of the original file and generates more detailed media. For example, when regenerating images of a sporting event, the regeneration unit references related news articles to generate detailed images. Furthermore, when the generation AI regenerates the high-resolution media, the regeneration unit references related academic papers to understand the context of the original file and generates more detailed media. For example, when regenerating audio of a scientific lecture, the regeneration unit references related academic papers to generate detailed audio. Furthermore, when the generation AI regenerates the high-resolution media, the regeneration unit references related external data to understand the context of the original file and generates more detailed media. For example, when regenerating a historical documentary video, the regeneration unit references related external data to generate detailed video. In this way, by referencing external data, more detailed media can be generated.

[0076] The regeneration unit generates media from multiple different viewpoints when regenerating high-resolution media, providing the user with options. For example, when the generation AI regenerates high-resolution media, the regeneration unit generates media from multiple different viewpoints to provide the user with options. For example, when regenerating a landscape image, the regeneration unit generates multiple images, such as a "landscape with a blue sky and white clouds" and a "landscape with a range of mountains." Furthermore, when the generation AI regenerates high-resolution media, the regeneration unit generates media from multiple different viewpoints to provide the user with options. For example, when regenerating an interview video, the regeneration unit generates multiple videos, such as "a scene where the interviewer is asking a question" and "a scene where the interviewee is answering." Furthermore, when the generation AI regenerates high-resolution media, the regeneration unit generates media from multiple different viewpoints to provide the user with options. For example, when regenerating a video of a sports game, the regeneration unit generates multiple videos, such as "the moment a player scores a goal" and "the moment the spectators cheer." This allows media to be generated from multiple viewpoints, providing the user with options.

[0077] The regeneration unit can simultaneously generate media in different formats when regenerating high-resolution media. For example, the regeneration unit simultaneously generates media in different formats when the generation AI regenerates high-resolution media. For example, when regenerating a landscape image, the regeneration unit simultaneously generates an audio file describing the landscape. The regeneration unit also simultaneously generates media in different formats when the generation AI regenerates high-resolution media. For example, when regenerating a video of a sporting event, the regeneration unit simultaneously generates highlight images of the event. The regeneration unit also simultaneously generates media in different formats when the generation AI regenerates high-resolution media. For example, when regenerating the audio of a lecture, the regeneration unit simultaneously generates slide images of the lecture. This allows media in different formats to be generated simultaneously.

[0078] The regeneration unit can simultaneously generate media in different languages ​​when regenerating high-resolution media, thereby achieving multilingual support. For example, the regeneration unit simultaneously generates media in different languages ​​when the generation AI regenerates high-resolution media. For example, when regenerating a landscape image, the regeneration unit simultaneously generates a description of the landscape in multiple languages. The regeneration unit also simultaneously generates media in different languages ​​when the generation AI regenerates high-resolution media. For example, when regenerating the audio of a lecture, the regeneration unit simultaneously generates the content of the lecture in multiple languages. The regeneration unit also simultaneously generates media in different languages ​​when the generation AI regenerates high-resolution media. For example, when regenerating a documentary video, the regeneration unit simultaneously generates subtitles for the video in multiple languages. This achieves multilingual support and allows media in different languages ​​to be generated simultaneously.

[0079] The regeneration unit can use the emotion estimation function to monitor the user's emotions in real time when regenerating high-resolution media, and generate media according to the user's emotions. For example, when the generation AI regenerates high-resolution media, the regeneration unit can use the emotion estimation function to monitor the user's emotions in real time, and generate media according to the user's emotions. For example, if the user is moved, the regeneration unit generates an emotional landscape image. The regeneration unit can also use the emotion estimation function to monitor the user's emotions in real time when the generation AI regenerates high-resolution media, and generate media according to the user's emotions. For example, if the user is excited, the regeneration unit generates a video including an exciting scene. The regeneration unit can also use the emotion estimation function to monitor the user's emotions in real time when the generation AI regenerates high-resolution media, and generate media according to the user's emotions. For example, if the user is surprised, the regeneration unit generates an image including a surprising scene. This makes it possible to generate media according to the user's emotions in real time.

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

[0081] The file conversion unit can refer to related external data when analyzing the contents of a file to generate more detailed text prompts. For example, the generation AI analyzes an image file and refers to related news articles to understand the context. For example, it analyzes images of a sporting event and generates a detailed text prompt such as "Scenes from the 2023 Olympics." The generation AI also analyzes audio files and refers to related academic papers to understand the context. For example, it analyzes the audio of a scientific lecture and generates a detailed text prompt such as "The latest research presentation by a Nobel Prize winner." The generation AI also analyzes video files and refers to related external data to understand the context. For example, it analyzes a historical documentary video and generates a detailed text prompt such as "A documentary depicting battle scenes from World War II." This allows more detailed text prompts to be generated by referencing external data.

[0082] The file conversion unit can analyze the contents of a file from multiple perspectives and generate multiple different text prompts. For example, the generation AI analyzes an image file and generates text prompts from different perspectives. For example, it analyzes a landscape image and generates multiple text prompts such as "a landscape with a blue sky and white clouds" and "a landscape with a range of mountains." The generation AI also analyzes audio files and generates text prompts from different perspectives. For example, it analyzes interview audio and generates multiple text prompts such as "the scene where the interviewer is asking a question" and "the scene where the interviewee is answering." The generation AI also analyzes video files and generates text prompts from different perspectives. For example, it analyzes a video of a sports game and generates multiple text prompts such as "the moment a player scores a goal" and "the moment the audience cheers." This allows for the generation of a variety of text prompts by analyzing from multiple perspectives.

[0083] The file conversion unit can also simultaneously analyze audio or video multimedia data and reflect it in text prompts. For example, the generation AI can simultaneously analyze image and audio files and reflect it in text prompts. For example, it can analyze the images and audio of a presentation and generate a text prompt such as, "The graph displayed on the slide and its explanation." The generation AI can also analyze video files and reflect both the image and audio in the text prompt. For example, it can analyze a movie trailer and generate a text prompt such as, "The action scene and its background music." The generation AI can also simultaneously analyze audio and image files and reflect it in text prompts. For example, it can analyze the images and audio of a music concert and generate a text prompt such as, "The band on stage and the song being played." This allows multimedia data to be analyzed simultaneously and reflected in text prompts.

[0084] The file conversion unit can simultaneously generate text prompts in different languages, achieving multilingual support. For example, the generation AI analyzes image files and generates text prompts in different languages. For example, it analyzes landscape images and generates multilingual text prompts such as "A landscape with blue sky and white clouds." The generation AI also analyzes audio files and generates text prompts in different languages. For example, it analyzes the audio of a lecture and generates multilingual text prompts such as "A scene where an inspiring speech is being delivered" and "A moving speech is being delivered." The generation AI also analyzes video files and generates text prompts in different languages. For example, it analyzes a documentary video and generates multilingual text prompts such as "A video depicting historical scenes." This enables multilingual support and the generation of text prompts in different languages.

[0085] The file conversion unit can use its emotion estimation function to monitor the user's emotions in real time and generate text prompts that correspond to the user's emotions. For example, the generation AI analyzes image files, monitors the user's emotions in real time, and generates text prompts. For example, if the user is moved, it generates a text prompt such as "an image of an inspiring landscape." The generation AI can also analyze audio files, monitor the user's emotions in real time, and generate text prompts. For example, if the user is excited, it generates a text prompt such as "a scene where an exciting speech is being given." The generation AI can also analyze video files, monitor the user's emotions in real time, and generate text prompts. For example, if the user is surprised, it generates a text prompt such as "a video showing a surprising scene." This makes it possible to generate text prompts that correspond to the user's emotions.

[0086] The storage unit can use the emotion estimation function to add emotional information related to the prompt as metadata when saving the text prompt. For example, when saving the text prompt, the emotion estimation function is used to add emotional information related to the prompt as metadata. For example, the emotion information "emotional" is added to a prompt such as "an image of an inspiring landscape." Furthermore, when saving the text prompt, the emotion estimation function is used to add emotional information related to the prompt as metadata. For example, the emotion information "excited" is added to a prompt such as "a scene in which an exciting speech is being given." Furthermore, when saving the text prompt, the emotion estimation function is used to add emotional information related to the prompt as metadata. For example, the emotion information "surprise" is added to a prompt such as "a video in which a surprising scene unfolds." In this way, by adding emotional information as metadata, the emotional value of the prompt can be managed.

[0087] The storage unit can improve access speed by optimizing the storage location based on the importance and frequency of use of the prompt when saving the text prompt. For example, when saving the text prompt, the storage location is optimized based on the importance of the prompt. For example, prompts with high importance are saved in storage that can be accessed quickly. Furthermore, when saving the text prompt, the storage location is optimized based on the frequency of use of the prompt. For example, frequently used prompts are saved in a cache to improve access speed. Furthermore, when saving the text prompt, the storage location is optimized by combining the importance and frequency of use of the prompt. For example, prompts with high importance and high frequency of use are saved in the fastest storage. In this way, optimizing the storage location improves access speed.

[0088] The storage unit can encrypt the contents of the text prompt when saving it, thereby enhancing security. For example, the storage unit encrypts the contents of the prompt when saving it. For example, the storage unit encrypts the contents of the prompt using AES encryption to enhance security. Furthermore, the storage unit encrypts the contents of the prompt when saving it. For example, the storage unit encrypts the prompt using RSA encryption to enhance security. Furthermore, the storage unit encrypts the contents of the prompt when saving it. For example, the storage unit encrypts the prompt using hybrid encryption to enhance security. In this way, security can be enhanced by encrypting the contents of the prompt.

[0089] The storage unit can use the emotion estimation function to analyze the user's emotion and suggest a storage method based on the emotion. For example, when saving text prompts, the emotion estimation function is used to analyze the user's emotion and suggest a storage method based on the emotion. For example, if the user is moved, emotional prompts are preferentially saved. Furthermore, when saving text prompts, the emotion estimation function is used to analyze the user's emotion and suggest a storage method based on the emotion. For example, if the user is excited, prompts that cause excitement are preferentially saved. Furthermore, when saving text prompts, the emotion estimation function is used to analyze the user's emotion and suggest a storage method based on the emotion. For example, if the user is surprised, prompts that cause surprise are preferentially saved. In this way, a storage method based on the user's emotion can be suggested.

[0090] The metadata management unit can add emotion information estimated using the emotion estimation function to the metadata and manage the emotional value of the file. For example, the emotional information estimated using the emotion estimation function is added to the metadata to manage the emotional value of the file. For example, emotion information "emotional" is added as metadata to a prompt such as "an image of an inspiring landscape." Furthermore, emotion information estimated using the emotion estimation function is added to the metadata to manage the emotional value of the file. For example, emotion information "excited" is added as metadata to a prompt such as "a scene where an exciting speech is being given." Furthermore, emotion information estimated using the emotion estimation function is added to the metadata to manage the emotional value of the file. For example, emotion information "surprise" is added as metadata to a prompt such as "a video in which a surprising scene unfolds." In this way, the emotional value of the file can be managed by adding emotion information.

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

[0092] Step 1: The file conversion unit converts the file into a text-based prompt. For example, the generation AI can analyze a high-resolution image file and generate a text prompt such as "A landscape with a blue sky and white clouds." The generation AI can also analyze audio and video files and convert their contents into text prompts. Step 2: The storage unit stores the text-based prompt converted by the file conversion unit. For example, instead of storing a 1GB image file, a text prompt of a few KB can be stored. The storage unit can also store the text prompt in cloud storage or local storage, and can further compress and store it. Step 3: The metadata manager adds metadata and version control information to the text-based prompts saved by the storage unit. For example, metadata includes information such as the file's creation date and time, its creator, and the file type. Version control also allows the file's change history to be tracked and previous versions to be reverted if necessary. Furthermore, the metadata manager records the file's usage and access frequency, which can be used for future data management. Step 4: The regeneration unit regenerates high-resolution media based on a text-based prompt. For example, if the saved text prompt "A landscape with blue skies and white clouds" is input into the generation AI, the AI ​​will regenerate a high-resolution landscape image based on that prompt. The regeneration unit can also regenerate audio and video files, and can simultaneously generate media in different formats.

[0093] The specific processing unit 290 transmits the result of the specific processing to the smart device 14. In the smart device 14, the control unit 46A causes the output device 40 to output the result of the specific processing. The microphone 38B acquires audio indicating a user input regarding the result of the specific processing. The control unit 46A transmits audio data indicating the user input acquired by the microphone 38B to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the audio data.

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

[0095] Furthermore, the processing by the data processing system 10 described above is executed by the specific processing unit 290 of the data processing device 12 or the control unit 46A of the smart device 14, but may also be executed by the specific processing unit 290 of the data processing device 12 and the control unit 46A of the smart device 14. Furthermore, the specific processing unit 290 of the data processing device 12 acquires or collects information necessary for processing from the smart device 14 or an external device, and the smart device 14 acquires or collects information necessary for processing from the data processing device 12 or an external device.

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

[0097] 3, the data processing system 210 includes the data processing device 12 and smart glasses 214. An example of the data processing device 12 is a server.

[0098] The data processing device 12 includes a computer 22, a database 24, and a communication I / F 26. The computer 22 includes a processor 28, a RAM 30, and a storage 32. The processor 28, RAM 30, and storage 32 are connected to a bus 34. The database 24 and the communication I / F 26 are also connected to the bus 34. The communication I / F 26 is connected to a network 54. Examples of the network 54 include a WAN and / or a LAN.

[0099] The smart glasses 214 include a computer 36, a microphone 238, a speaker 240, a camera 42, and a communication I / F 44. The computer 36 includes a processor 46, a RAM 48, and a storage 50. The processor 46, the RAM 48, and the storage 50 are connected to a bus 52. The microphone 238, the speaker 240, and the camera 42 are also connected to the bus 52.

[0100] The microphone 238 receives instructions and the like from the user by receiving voice uttered by the user. The microphone 238 captures the voice uttered by the user, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio according to instructions from the processor 46.

[0101] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an imaging element such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, and captures images of the user's surroundings (for example, an imaging range defined by an angle of view equivalent to the field of vision of a typical healthy person).

[0102] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 are responsible for the exchange of various information between the processor 46 and the processor 28 via the network 54. The exchange of various information between the processor 46 and the processor 28 using the communication I / Fs 44 and 26 is carried out in a secure state.

[0103] Fig. 4 shows an example of the main functions of the data processing device 12 and the smart glasses 214. As shown in Fig. 4, in the data processing device 12, a specific process is performed by the processor 28. A specific process program 56 is stored in the storage 32.

[0104] The processor 28 reads the specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific processing is realized by the processor 28 operating as a specific processing unit 290 in accordance with the specific processing program 56 executed on the RAM 30.

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

[0106] In the smart glasses 214, the specific processing is performed by the processor 46. A specific processing program 60 is stored in the storage 50. The processor 46 reads the specific processing program 60 from the storage 50 and executes the read specific processing program 60 on the RAM 48. The specific processing is realized by the processor 46 operating as the control unit 46A in accordance with the specific processing program 60 executed on the RAM 48. 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.

[0107] Note that a device other than the data processing device 12 may have the data generation model 58. For example, a server device may have the data generation model 58. In this case, the data processing device 12 communicates with the server device having the data generation model 58 to obtain a processing result (such as a prediction result) using the data generation model 58. Furthermore, the data processing device 12 may be a server device, or may be a terminal device (for example, a mobile phone, a robot, a home appliance, etc.) owned by a user.

[0108] The specific processing unit 290 transmits the result of the specific processing to the smart glasses 214. In the smart glasses 214, the control unit 46A causes the speaker 240 to output the result of the specific processing. The microphone 238 acquires audio indicating a user input regarding the result of the specific processing. The control unit 46A transmits audio data indicating the user input acquired by the microphone 238 to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the audio data.

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

[0110] The data processing system 210 according to the second embodiment performs the same processing as the data processing system 10 according to the first embodiment. The processing by the data processing system 210 is executed by the specific processing unit 290 of the data processing device 12 or the control unit 46A of the smart glasses 214, but may also be executed by the specific processing unit 290 of the data processing device 12 and the control unit 46A of the smart glasses 214. Furthermore, the specific processing unit 290 of the data processing device 12 acquires or collects information required for processing from the smart glasses 214 or an external device, etc., and the smart glasses 214 acquires or collects information required for processing from the data processing device 12 or an external device, etc.

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

[0112] 5, the data processing system 310 includes the data processing device 12 and a headset type terminal 314. An example of the data processing device 12 is a server.

[0113] The data processing device 12 includes a computer 22, a database 24, and a communication I / F 26. The computer 22 includes a processor 28, a RAM 30, and a storage 32. The processor 28, RAM 30, and storage 32 are connected to a bus 34. The database 24 and the communication I / F 26 are also connected to the bus 34. The communication I / F 26 is connected to a network 54. Examples of the network 54 include a WAN and / or a LAN.

[0114] The headset type terminal 314 includes a computer 36, a microphone 238, a speaker 240, a camera 42, a communication I / F 44, and a display 343. The computer 36 includes a processor 46, a RAM 48, and a storage 50. The processor 46, the RAM 48, and the storage 50 are connected to a bus 52. The microphone 238, the speaker 240, the camera 42, and the display 343 are also connected to the bus 52.

[0115] The microphone 238 receives instructions and the like from the user by receiving voice uttered by the user. The microphone 238 captures the voice uttered by the user, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio according to instructions from the processor 46.

[0116] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an imaging element such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, and captures images of the user's surroundings (for example, an imaging range defined by an angle of view equivalent to the field of vision of a typical healthy person).

[0117] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 are responsible for the exchange of various information between the processor 46 and the processor 28 via the network 54. The exchange of various information between the processor 46 and the processor 28 using the communication I / Fs 44 and 26 is carried out in a secure state.

[0118] Fig. 6 shows an example of the main functions of the data processing device 12 and the headset 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.

[0119] The processor 28 reads the specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific processing is realized by the processor 28 operating as a specific processing unit 290 in accordance with the specific processing program 56 executed on the RAM 30.

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

[0121] 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.

[0122] Note that a device other than the data processing device 12 may have the data generation model 58. For example, a server device may have the data generation model 58. In this case, the data processing device 12 communicates with the server device having the data generation model 58 to obtain a processing result (such as a prediction result) using the data generation model 58. Furthermore, the data processing device 12 may be a server device, or may be a terminal device (for example, a mobile phone, a robot, a home appliance, etc.) owned by a user.

[0123] The specific processing unit 290 transmits the result of the specific processing to the headset type terminal 314. In the headset type terminal 314, the control unit 46A causes the speaker 240 and the display 343 to output the result of the specific processing. The microphone 238 acquires audio indicating a user input regarding the result of the specific processing. The control unit 46A transmits audio data indicating the user input acquired by the microphone 238 to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the audio data.

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

[0125] The data processing system 310 according to the third embodiment performs the same processing as the data processing system 10 according to the first embodiment. The processing by the data processing system 310 is executed by the specific processing unit 290 of the data processing device 12 or the control unit 46A of the headset type terminal 314, but may also be executed by the specific processing unit 290 of the data processing device 12 and the control unit 46A of the headset type terminal 314. Furthermore, the specific processing unit 290 of the data processing device 12 acquires or collects information required for processing from the headset type terminal 314 or an external device, etc., and the headset type terminal 314 acquires or collects information required for processing from the data processing device 12 or an external device, etc.

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

[0127] 7, 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.

[0128] The data processing device 12 includes a computer 22, a database 24, and a communication I / F 26. The computer 22 includes a processor 28, a RAM 30, and a storage 32. The processor 28, RAM 30, and storage 32 are connected to a bus 34. The database 24 and the communication I / F 26 are also connected to the bus 34. The communication I / F 26 is connected to a network 54. Examples of the network 54 include a WAN and / or a LAN.

[0129] The robot 414 includes a computer 36, a microphone 238, a speaker 240, a camera 42, a communication I / F 44, and a control target 443. The computer 36 includes a processor 46, a RAM 48, and a storage 50. The processor 46, the RAM 48, and the storage 50 are connected to a bus 52. The microphone 238, the speaker 240, the camera 42, and the control target 443 are also connected to the bus 52.

[0130] The microphone 238 receives instructions and the like from the user by receiving voice uttered by the user. The microphone 238 captures the voice uttered by the user, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio according to instructions from the processor 46.

[0131] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an imaging element such as a CMOS image sensor or a CCD image sensor, and captures images of the user's surroundings (for example, an imaging range defined by an angle of view equivalent to the field of vision of a typical healthy person).

[0132] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 are responsible for the exchange of various information between the processor 46 and the processor 28 via the network 54. The exchange of various information between the processor 46 and the processor 28 using the communication I / Fs 44 and 26 is carried out in a secure state.

[0133] The control object 443 includes a display device, LEDs in the eyes, and motors that drive the arms, hands, and feet. The posture and gestures of the robot 414 are controlled by controlling the motors of the arms, hands, and feet. Some of the emotions of the robot 414 can be expressed by controlling these motors. In addition, the facial expressions of the robot 414 can also be expressed by controlling the light emission state of the LEDs in the eyes of the robot 414.

[0134] Fig. 8 shows an example of the main functions of the data processing device 12 and the robot 414. As shown in Fig. 8, in the data processing device 12, a specific process is performed by the processor 28. A specific process program 56 is stored in the storage 32.

[0135] The processor 28 reads the specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific processing is realized by the processor 28 operating as a specific processing unit 290 in accordance with the specific processing program 56 executed on the RAM 30.

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

[0137] 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.

[0138] Note that a device other than the data processing device 12 may have the data generation model 58. For example, a server device may have the data generation model 58. In this case, the data processing device 12 communicates with the server device having the data generation model 58 to obtain a processing result (such as a prediction result) using the data generation model 58. Furthermore, the data processing device 12 may be a server device, or may be a terminal device (for example, a mobile phone, a robot, a home appliance, etc.) owned by a user.

[0139] The specific processing unit 290 transmits the result of the specific processing to the robot 414. In the robot 414, the control unit 46A causes the speaker 240 and the control target 443 to output the result of the specific processing. The microphone 238 acquires voice indicating a user input regarding the result of the specific processing. The control unit 46A transmits voice data indicating the user input acquired by the microphone 238 to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the voice data.

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

[0141] The data processing system 410 according to the fourth embodiment performs the same processing as the data processing system 10 according to the first embodiment. The processing by the data processing system 410 is executed by the specific processing unit 290 of the data processing device 12 or the control unit 46A of the robot 414, but may also be executed by the specific processing unit 290 of the data processing device 12 and the control unit 46A of the robot 414. Furthermore, the specific processing unit 290 of the data processing device 12 acquires or collects information required for processing from the robot 414 or an external device, etc., and the robot 414 acquires or collects information required for processing from the data processing device 12 or an external device, etc.

[0142] The emotion identification model 59 as an emotion engine may determine the user's emotion according to a specific mapping. Specifically, the emotion identification model 59 may determine the user's emotion according to an emotion map (see FIG. 9), which is a specific mapping. Similarly, the emotion identification model 59 may determine the robot's emotion, and the identification processing unit 290 may perform identification processing using the robot's emotion.

[0143] FIG. 9 illustrates an emotion map 400 on which multiple emotions are mapped. In the emotion map 400, emotions are arranged in concentric circles radiating from the center. Emotions closer to the center of the concentric circles are more primitive. Emotions representing states and behaviors arising from a state of mind are arranged on the outer edges of the concentric circles. The concept of emotion encompasses both emotions and mental states. Emotions generally generated from reactions occurring in the brain are arranged on the left side of the concentric circles. Emotions generally induced by situational judgment are arranged on the right side of the concentric circles. Emotions generally generated from reactions occurring in the brain and induced by situational judgment are arranged on the upper and lower sides of the concentric circles. Furthermore, the emotion of "pleasure" is arranged on the upper side of the concentric circles, and the emotion of "discomfort" is arranged on the lower side. In this way, in the emotion map 400, multiple emotions are mapped based on the structure by which emotions are generated, and emotions that tend to occur simultaneously are mapped close to each other.

[0144] These emotions are distributed in the 3 o'clock direction on emotion map 400, and typically fluctuate between relief and anxiety. In the right half of emotion map 400, situational awareness dominates over internal sensations, resulting in a sense of calm.

[0145] The inside of emotion map 400 represents what is going on in the mind, and the outside of emotion map 400 represents behavior, so the further you go outside emotion map 400, the more visible the emotions become (the more they are expressed in behavior).

[0146] Human emotions are based on various balances, such as posture and blood sugar levels. When these balances deviate from the ideal, a state of discomfort is expressed, and when they approach the ideal, a state of pleasure is expressed. Emotions can also be created for robots, cars, and motorcycles, based on various balances, such as posture and remaining battery life. When these balances deviate from the ideal, a state of discomfort is expressed, and when they approach the ideal, a state of pleasure is expressed. An emotion map can be generated, for example, based on Dr. Mitsuyoshi's emotion map (Research on speech emotion recognition and brain physiological signal analysis systems for emotions, Tokushima University, doctoral dissertation: https: / / ci.nii.ac.jp / naid / 500000375379). The left half of the emotion map lists emotions belonging to the area called "reaction," where sensation is dominant. The right half of the emotion map lists emotions belonging to the area called "situation," where situational awareness is dominant.

[0147] The emotion map defines two emotions that promote learning. One is a negative emotion on the situation side, around the middle of "repentance" or "reflection." In other words, this occurs when the robot experiences negative emotions such as "I never want to feel this way again" or "I don't want to be scolded again." The other is a positive emotion on the response side, around "desire." In other words, this occurs when the robot experiences positive feelings such as "I want more" or "I want to know more."

[0148] The emotion identification model 59 inputs user input into a pre-trained neural network, obtains emotion values ​​indicating each emotion shown in the emotion map 400, and determines the user's emotion. This neural network is pre-trained based on multiple pieces of training data that are combinations of user input and emotion values ​​indicating each emotion shown in the emotion map 400. Furthermore, this neural network is trained so that emotions that are located close to each other have similar values, as in the emotion map 900 shown in FIG. 10. FIG. 10 shows an example in which multiple emotions, "relieved," "calm," and "reassuring," have similar emotion values.

[0149] In the above embodiment, an example was given in which a specific process is performed by one computer 22, but the technology disclosed herein is not limited to this, and distributed processing of the specific process may be performed by multiple computers including computer 22.

[0150] In the above embodiment, an example in which the specific processing program 56 is stored in the storage 32 has been described, but the technology of the present disclosure is not limited to this. For example, the specific processing program 56 may be stored in a portable, computer-readable, non-transitory storage medium such as a USB (Universal Serial Bus) memory. The specific processing program 56 stored in the non-transitory storage medium is installed in the computer 22 of the data processing device 12. The processor 28 executes the specific processing in accordance with the specific processing program 56.

[0151] Alternatively, the specific processing program 56 may be stored in a storage device such as a server connected to the data processing device 12 via the network 54, and the specific processing program 56 may be downloaded and installed on the computer 22 in response to a request from the data processing device 12.

[0152] It is not necessary to store all of the specific processing program 56 in a storage device such as a server connected to the data processing device 12 via the network 54, or to store all of the specific processing program 56 in the storage 32; only a portion of the specific processing program 56 may be stored.

[0153] The hardware resource for executing a specific process can be any of the following types of processors: A processor, for example, is a CPU, which is a general-purpose processor that functions as a hardware resource for executing a specific process by executing software, i.e., a program. A processor also includes a dedicated electrical circuit, such as an FPGA (Field-Programmable Gate Array), a PLD (Programmable Logic Device), or an ASIC (Application Specific Integrated Circuit), which is a processor with a circuit configuration designed specifically for executing a specific process. Each processor has built-in or connected memory, and each processor uses the memory to execute the specific process.

[0154] The hardware resource that executes the specific process may be configured with one of these various processors, or may be configured with a combination of two or more processors of the same or different types (for example, a combination of multiple FPGAs, or a combination of a CPU and an FPGA). Also, the hardware resource that executes the specific process may be a single processor.

[0155] As an example of a system configured with a single processor, first, one processor is configured by combining one or more CPUs and software, and this processor functions as a hardware resource that executes a specific process. Second, there is a system that uses a processor that realizes the functions of an entire system including multiple hardware resources that execute a specific process on a single IC chip, as typified by SoC (System-on-a-chip). In this way, a specific process is realized using one or more of the above-mentioned various processors as hardware resources.

[0156] Furthermore, the hardware structure of these various processors can be, more specifically, an electric circuit that combines circuit elements such as semiconductor devices. The specific processing described above is merely an example. Therefore, it goes without saying that unnecessary steps may be deleted, new steps may be added, or the processing order may be rearranged, without departing from the spirit of the invention.

[0157] In the above example, the first to fourth embodiments have been described separately, but some or all of these embodiments may be combined. The smart device 14, smart glasses 214, headset terminal 314, and robot 414 are merely examples, and they may be combined, or other devices may be used. In the above example, the first and second embodiments have been described separately, but they may be combined.

[0158] The above-described description and illustrations are a detailed explanation of the parts related to the technology of the present disclosure and are merely an example of the technology of the present disclosure. For example, the above description of the configuration, functions, actions, and effects is an explanation of an example of the configuration, functions, actions, and effects of the parts related to the technology of the present disclosure. Therefore, it goes without saying that unnecessary parts may be deleted, new elements may be added, or replacements may be made to the above-described description and illustrations within the scope of the gist of the technology of the present disclosure. Furthermore, 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.

[0159] All publications, patent applications, and technical standards mentioned in this specification are herein incorporated by reference to the same extent as if each individual publication, patent application, or technical standard was specifically and individually indicated to be incorporated by reference. [Explanation of symbols]

[0160] 10, 210, 310, 410 Data Processing Systems 12 Data Processing Device 14 Smart Devices 214 Smart Glasses 314 Headset-type terminal 414 Robot

Claims

1. a file converter that converts the file into a text-based prompt; a storage unit for storing the text-based prompt converted by the file conversion unit; a metadata manager that adds metadata and version control information to the text-based prompts stored by the storage unit; a regenerator that regenerates high-resolution media based on the text-based prompts. A system characterized by:

2. The file conversion unit Inferring a sentiment associated with the file when analyzing the contents of the file and generating a text prompt reflecting the sentiment.

2. The system of claim 1.

3. The file conversion unit When parsing the contents of the file, relevant external data is referenced to generate a more detailed text prompt.

2. The system of claim 1.

4. The file conversion unit The contents of the file are analyzed from multiple perspectives to generate multiple different text prompts.

2. The system of claim 1.

5. The file conversion unit Audio or video multimedia data is also analyzed and reflected in the text prompts.

2. The system of claim 1.

Images