system

Abstract

An object of the system according to the embodiment is to improve the accessibility and distribution of information by seamlessly linking audio, text, images, and broadcast media.SOLUTION: A system according to an embodiment includes a voice conversion part, a text conversion part, an image generation part, a retrieval classification part, and a broadcast cooperation part. The voice conversion unit converts the voice data into text in real time. The text conversion unit converts the text converted by the voice conversion unit into voice again. The image generation unit generates an associated image from the text or the voice data converted by the text conversion unit. The search / classification unit searches for or classifies the image, text, or audio data generated by the image generation unit using an embedding technique. The broadcast cooperation unit cooperates the data searched or classified by the search and classification unit with the TV broadcast system to expand the broadcast content as rich media.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 make it difficult to seamlessly integrate audio, text, images, and broadcast media, leaving room for improvement in information accessibility and distribution.

[0005] The system according to the embodiment aims to improve the accessibility and distribution of information by seamlessly linking audio, text, images, and broadcast media. [Means for solving the problem]

[0006] The system according to the embodiment includes a speech conversion unit, a text conversion unit, an image generation unit, a search and classification unit, and a broadcast linkage unit. The speech conversion unit converts speech data into text in real time. The text conversion unit converts the text converted by the speech conversion unit back into speech. The image generation unit generates related images from the text or speech data converted by the text conversion unit. The search and classification unit searches or classifies the image, text, or speech data generated by the image generation unit using embedding technology. The broadcast linkage unit links the data searched or classified by the search and classification unit with a TV broadcast system to expand the broadcast content as rich media. [Effects of the Invention]

[0007] The system according to the embodiment can seamlessly integrate audio, text, images, and broadcast media to improve the accessibility and distribution of information. [Brief explanation of the drawings]

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

[0028] (Example 1) A multimodal service platform according to an embodiment of the present invention is a system that seamlessly integrates voice, text, image, and broadcast media. This system can convert voice data into text in real time and then convert the text back into voice. It can also generate related images from text and voice data and use embedding technology to search and classify the content. By linking with TV broadcasting systems, it can enhance broadcast content as rich media, providing a more interactive experience. This allows the multimodal service platform to significantly improve the accessibility and distribution of information in the media industry, educational institutions, and businesses.

[0029] A multimodal service platform according to an embodiment includes a speech conversion unit, a text conversion unit, an image generation unit, a search and classification unit, and a broadcast linkage unit. The speech conversion unit converts speech data into text in real time. For example, speech spoken during a meeting can be transcribed in real time. The speech conversion unit analyzes speech data using a generation AI (e.g., a text generation AI or a multimodal generation AI) to generate text. The text conversion unit converts the text converted by the speech conversion unit back into speech. For example, a news article written in text can be read aloud. The text conversion unit analyzes text data using a generation AI to generate speech. The image generation unit generates related images from text and speech data. For example, a scene described in text can be generated as an image. The image generation unit analyzes text data and speech data using a generation AI to generate an image. The search and classification unit searches and classifies the images, text, and speech data generated by the image generation unit using embedding technology. For example, documents related to a specific keyword can be searched for from a large amount of document data. The search and classification unit uses a generation AI to analyze text data and audio data to be searched and classified, and generates search and classification results. The broadcast linkage unit links the data searched and classified by the search and classification unit with a TV broadcast system to expand the broadcast content as rich media. For example, additional information related to a news program currently being broadcast can be displayed in real time. The broadcast linkage unit uses a generation AI to analyze the broadcast content data and generate the additional information. As a result, the multimodal service platform according to the embodiment can seamlessly link audio, text, images, and broadcast media.

[0030] The speech conversion unit can automatically remove background sounds or noise from the speech data to achieve more accurate text conversion. For example, the speech conversion unit develops an algorithm to automatically remove background sounds and noise from the speech data to achieve more accurate text conversion. For example, noise during a meeting can be removed to clarify what is being said. The speech conversion unit also uses noise removal technology to improve the quality of the speech data. For example, wind noise and traffic noise can be removed to make the speaker's voice clearer. The speech conversion unit also analyzes noise in the speech data in real time and applies a noise removal filter. For example, accurate text conversion can be achieved even in environments with a lot of background noise. This allows for accurate text conversion by removing background sounds and noise.

[0031] The speech conversion unit can translate speech data into multiple languages ​​in real time and generate text in each language simultaneously. The speech conversion unit, for example, builds a system that translates speech data into multiple languages ​​in real time and generates text in each language simultaneously. For example, speech during a conference is translated into English, Japanese, and Chinese simultaneously. The speech conversion unit also uses a translation algorithm to convert speech data into multiple languages ​​in real time. For example, speech at an international conference is displayed in multiple languages. The speech conversion unit also develops a real-time translation system for speech data and generates text in each language simultaneously. For example, the speech of a news program is translated into multiple languages ​​and displayed. This makes it possible to translate into multiple languages ​​in real time and generate text in each language simultaneously.

[0032] The speech conversion unit can summarize speech data in real time and generate summary text. The speech conversion unit, for example, develops an algorithm that summarizes speech data in real time and generates summary text. For example, it summarizes statements made during a meeting and extracts important points. The speech conversion unit also uses a summarization algorithm to extract the main points of speech data in real time and generate summary text. For example, it summarizes the content of a lecture and converts it into text. The speech conversion unit also builds a summarization system for speech data and generates summary text in real time. For example, it summarizes and displays the content of a news program. This makes it possible to summarize speech data in real time and generate summary text.

[0033] The text conversion unit can understand the context of the text and select an appropriate voice character. For example, the text conversion unit builds a system that analyzes the context of the text and selects an appropriate voice character. For example, a child's voice is used for text intended for children. The text conversion unit also uses context analysis to automatically select the voice character best suited to the text. For example, a male voice is used for business documents. The text conversion unit also develops a system that selects a voice character in real time according to the content of the text. For example, a female voice is used for emotional text. This makes it possible to select an appropriate voice character based on the context.

[0034] The text conversion unit can translate text data into multiple languages ​​and simultaneously generate speech in each language. For example, the text conversion unit builds a system that translates text data into multiple languages ​​in real time and simultaneously generates speech in each language. For example, a news article is simultaneously read aloud in English, Japanese, and Chinese. The text conversion unit also uses a translation algorithm to convert text data into multiple languages ​​in real time and generate speech in each language. For example, materials for an international conference are read aloud in multiple languages. The text conversion unit also develops a real-time translation system for text data and simultaneously generates speech in each language. For example, educational content is provided in multiple languages. This allows translation into multiple languages ​​and simultaneous generation of speech in each language.

[0035] The text conversion unit can summarize text data and generate summarized audio. For example, the text conversion unit develops an algorithm that summarizes text data in real time and generates summarized audio. For example, a long news article is summarized and provided as audio. The text conversion unit also uses a summarization algorithm to extract the main points of text data in real time and generate summarized audio. For example, the content of a lecture is summarized and provided as audio. The text conversion unit also builds a summarization system for text data and generates summarized audio in real time. For example, minutes of a meeting are summarized and provided as audio. In this way, text data can be summarized and summarized audio can be generated.

[0036] The image generation unit can understand the context of text or audio data and generate multiple related images. The image generation unit, for example, builds a system that analyzes the context of text or audio data and generates multiple related images. For example, it generates multiple images of tourist spots from the text of a travelogue. The image generation unit also uses context analysis to automatically generate images related to the text or audio data. For example, it generates multiple slide images based on the content of a lecture. The image generation unit also develops a system that understands the context of text or audio data and generates related images in real time. For example, it generates multiple images related to a news article. This makes it possible to generate multiple related images based on the context.

[0037] The image generation unit can generate 3D models or animations based on text or audio data. The image generation unit builds a system that generates 3D models based on text or audio data. For example, it generates a 3D model of a building from the text of an architectural plan. The image generation unit also analyzes text or audio data and automatically generates animations. For example, it generates character animations from the text of a story. The image generation unit also develops a system that generates 3D models and animations in real time based on text or audio data. For example, it generates 3D models and animations from the text of educational content. This makes it possible to generate 3D models and animations based on text or audio data.

[0038] The image generation unit can generate infographics or data visualizations based on text or audio data. The image generation unit, for example, builds a system that generates infographics based on text or audio data. For example, it generates infographics from text in a business report. The image generation unit also analyzes text or audio data to automatically generate data visualizations. For example, it generates data visualizations from text in a research paper. The image generation unit also develops a system that generates infographics or data visualizations in real time based on text or audio data. For example, it generates data visualizations from text in a news article. This makes it possible to generate infographics or data visualizations based on text or audio data.

[0039] The search and classifier can understand the context of text or audio data and automatically link related content. For example, the search and classifier analyzes the context of text or audio data to build a system that automatically links related content. For example, it links related past articles based on the context of a news article. The search and classifier also uses context analysis to automatically link related content to text or audio data. For example, it links related papers based on the context of a research paper. The search and classifier also develops a system that understands the context of text or audio data and links related content in real time. For example, it links related teaching materials based on the context of educational content. This makes it possible to automatically link related content based on context.

[0040] The search and classification unit can search for related video content based on text or audio data. The search and classification unit builds a system for searching for related video content based on text or audio data, for example. For example, related videos are searched for based on the content of a news article. The search and classification unit also uses context analysis to automatically search for video content related to text or audio data. For example, related videos are searched for based on the content of educational content. The search and classification unit also develops a system for searching for related video content in real time based on text or audio data. For example, related videos are searched for based on the content of a lecture. This makes it possible to search for related video content based on text or audio data.

[0041] The search and classification unit can search for related social media posts based on text or audio data. The search and classification unit, for example, builds a system for searching for related social media posts based on text or audio data. For example, it searches for related tweets based on the content of a news article. The search and classification unit also uses context analysis to automatically search for social media posts related to the text or audio data. For example, it searches for related Facebook (registered trademark) posts based on the content of educational content. The search and classification unit also develops a system for searching for related social media posts in real time based on text or audio data. For example, it searches for related Instagram (registered trademark) posts based on the content of a lecture. This makes it possible to search for related social media posts based on text or audio data.

[0042] The broadcast collaboration unit can understand the context of the broadcast content and automatically generate related interactive content. For example, the broadcast collaboration unit builds a system that analyzes the context of the broadcast content and automatically generates related interactive content. For example, an interactive quiz is generated based on the content of a news program. The broadcast collaboration unit also uses context analysis to automatically generate interactive content related to the broadcast content. For example, an interactive storyboard is generated based on the content of a drama. The broadcast collaboration unit also develops a system that understands the context of the broadcast content and generates related interactive content in real time. For example, interactive statistical data is generated based on the content of a sports program. This makes it possible to automatically generate related interactive content based on the context.

[0043] The broadcast collaboration unit can translate broadcast content into multiple languages ​​in real time and display subtitles in each language simultaneously. For example, the broadcast collaboration unit builds a system that translates broadcast content into multiple languages ​​in real time and displays subtitles in each language simultaneously. For example, a news program is subtitled simultaneously in English, Japanese, and Chinese. The broadcast collaboration unit also uses a translation algorithm to convert broadcast content into multiple languages ​​in real time and display subtitles in each language. For example, an international conference broadcast is subtitled in multiple languages. The broadcast collaboration unit also develops a real-time translation system for broadcast content and displays subtitles in each language simultaneously. For example, an educational program is subtitled in multiple languages. This allows broadcast content to be translated into multiple languages ​​in real time and subtitles in each language to be displayed simultaneously.

[0044] The broadcast collaboration unit can summarize broadcast content and display summary information in real time. The broadcast collaboration unit, for example, develops an algorithm that summarizes broadcast content in real time and displays summary information. For example, the content of a news program is summarized and displayed. The broadcast collaboration unit also uses a summarization algorithm to extract the main points of broadcast content in real time and display summary information. For example, the content of a documentary program is summarized and displayed. The broadcast collaboration unit also builds a summary system for broadcast content and displays summary information in real time. For example, the content of a sports program is summarized and displayed. This allows broadcast content to be summarized and summary information to be displayed in real time.

[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 speech conversion unit can automatically remove background sounds or noise from the speech data to enable more accurate text conversion. For example, removing noise during a meeting makes what is being said clearer. The speech conversion unit also uses noise removal technology to improve the quality of the speech data. For example, removing wind noise and traffic noise makes the speaker's voice clearer. The speech conversion unit also analyzes noise in the speech data in real time and applies a noise removal filter. For example, accurate text conversion is possible even in environments with a lot of background noise. This allows for accurate text conversion by removing background sounds and noise.

[0047] The speech conversion unit can translate speech data into multiple languages ​​in real time and generate text in each language simultaneously. For example, speech during a conference can be translated into English, Japanese, and Chinese simultaneously. The speech conversion unit also uses a translation algorithm to convert speech data into multiple languages ​​in real time. For example, speech at an international conference can be displayed in multiple languages. The speech conversion unit has also developed a real-time translation system for speech data and simultaneously generates text in each language. For example, the speech of a news program can be translated into multiple languages ​​and displayed. This makes it possible to translate into multiple languages ​​in real time and generate text in each language simultaneously.

[0048] The speech conversion unit can summarize speech data in real time and generate summary text. For example, it can summarize statements made during a meeting and extract important points. The speech conversion unit also uses a summarization algorithm to extract key points from speech data in real time and generate summary text. For example, it can summarize the content of a lecture and convert it into text. The speech conversion unit also builds a summarization system for speech data and generates summary text in real time. For example, it can summarize and display the content of a news program. This allows speech data to be summarized in real time and summary text to be generated.

[0049] The text conversion unit can understand the context of the text and select an appropriate voice character. For example, a child's voice is used for text intended for children. The text conversion unit also uses contextual analysis to automatically select the voice character best suited to the text. For example, a male voice is used for business documents. The text conversion unit will also develop a system that selects voice characters in real time according to the content of the text. For example, a female voice is used for emotional text. This allows the appropriate voice character to be selected based on the context.

[0050] The image generation unit can understand the context of text or audio data and generate multiple related images. For example, it generates multiple images of tourist spots from the text of a travelogue. The image generation unit also uses context analysis to automatically generate images related to text or audio data. For example, it generates multiple slide images based on the content of a lecture. The image generation unit also develops a system that understands the context of text or audio data and generates related images in real time. For example, it generates multiple images related to a news article. This makes it possible to generate multiple related images based on context.

[0051] The image generation unit can generate 3D models or animations based on text or audio data. For example, it generates a 3D model of a building from the text of an architectural plan. The image generation unit also analyzes text and audio data to automatically generate animations. For example, it generates character animations from the text of a story. The image generation unit also develops a system that generates 3D models and animations in real time based on text and audio data. For example, it generates 3D models and animations from the text of educational content. This makes it possible to generate 3D models and animations based on text and audio data.

[0052] The search and classifier can understand the context of text or audio data and automatically link related content. For example, it links related past articles based on the context of a news article. The search and classifier also uses context analysis to automatically link related content to text or audio data. For example, it links related papers based on the context of a research paper. The search and classifier also develops a system that understands the context of text or audio data and links related content in real time. For example, it links related teaching materials based on the context of educational content. This allows for automatic linking of related content based on context.

[0053] The processing flow of the first embodiment will be briefly explained below.

[0054] Step 1: The speech conversion unit converts the speech data into text in real time. For example, speech spoken during a meeting can be transcribed in real time. The speech conversion unit analyzes the speech data using generative AI (e.g., text generation AI or multimodal generation AI) and generates text. Step 2: The text conversion unit converts the text converted by the speech conversion unit back into speech. For example, a news article written in text can be read aloud. The text conversion unit uses generative AI to analyze the text data and generate speech. Step 3: The image generation unit generates related images from the text and audio data. For example, it can generate an image of a scene described in the text. The image generation unit uses generative AI to analyze the text and audio data and generate an image. Step 4: The search and classification unit uses embedding technology to search and classify the images, text, and audio data generated by the image generation unit. For example, it can search for documents related to specific keywords from a large amount of document data. The search and classification unit uses generation AI to analyze the text and audio data to be searched and classified, and generates search and classification results. Step 5: The broadcasting linkage unit links the data searched and classified by the search and classification unit with the TV broadcasting system to expand the broadcast content as rich media. For example, it can display additional information related to a news program currently being broadcast in real time. The broadcasting linkage unit uses generation AI to analyze the broadcast content data and generate the additional information.

[0055] (Example 2) A multimodal service platform according to an embodiment of the present invention is a system that seamlessly integrates voice, text, image, and broadcast media. This system can convert voice data into text in real time and then convert the text back into voice. It can also generate related images from text and voice data and use embedding technology to search and classify the content. By linking with TV broadcasting systems, it can enhance broadcast content as rich media, providing a more interactive experience. This allows the multimodal service platform to significantly improve the accessibility and distribution of information in the media industry, educational institutions, and businesses.

[0056] A multimodal service platform according to an embodiment includes a speech conversion unit, a text conversion unit, an image generation unit, a search and classification unit, and a broadcast linkage unit. The speech conversion unit converts speech data into text in real time. For example, speech spoken during a meeting can be transcribed in real time. The speech conversion unit analyzes speech data using a generation AI (e.g., a text generation AI or a multimodal generation AI) to generate text. The text conversion unit converts the text converted by the speech conversion unit back into speech. For example, a news article written in text can be read aloud. The text conversion unit analyzes text data using a generation AI to generate speech. The image generation unit generates related images from text and speech data. For example, a scene described in text can be generated as an image. The image generation unit analyzes text data and speech data using a generation AI to generate an image. The search and classification unit searches and classifies the images, text, and speech data generated by the image generation unit using embedding technology. For example, documents related to a specific keyword can be searched for from a large amount of document data. The search and classification unit uses a generation AI to analyze text data and audio data to be searched and classified, and generates search and classification results. The broadcast linkage unit links the data searched and classified by the search and classification unit with a TV broadcast system to expand the broadcast content as rich media. For example, additional information related to a news program currently being broadcast can be displayed in real time. The broadcast linkage unit uses a generation AI to analyze the broadcast content data and generate the additional information. As a result, the multimodal service platform according to the embodiment can seamlessly link audio, text, images, and broadcast media.

[0057] The speech conversion unit can perform emotion analysis of the speech data and adjust the expression of the text based on the emotion. The speech conversion unit, for example, performs emotion analysis of the speech data and adjusts the expression of the text according to the emotion of the speaker. For example, if the emotion of anger is strong, emphasis is added to the text. The speech conversion unit also uses emotion analysis to change the color and font of the text based on the emotion of the speaker. For example, if the emotion of joy is strong, bright colors and large fonts are used. The speech conversion unit also adjusts the context of the text based on the emotion score of the speech data. For example, if the emotion of sadness is strong, an expression that reflects the emotion is added to the text. This makes it possible to adjust the expression of the text based on the emotion.

[0058] The speech conversion unit can automatically remove background sounds or noise from the speech data to achieve more accurate text conversion. For example, the speech conversion unit develops an algorithm to automatically remove background sounds and noise from the speech data to achieve more accurate text conversion. For example, noise during a meeting can be removed to clarify what is being said. The speech conversion unit also uses noise removal technology to improve the quality of the speech data. For example, wind noise and traffic noise can be removed to make the speaker's voice clearer. The speech conversion unit also analyzes noise in the speech data in real time and applies a noise removal filter. For example, accurate text conversion can be achieved even in environments with a lot of background noise. This allows for accurate text conversion by removing background sounds and noise.

[0059] The speech conversion unit can use the emotion estimation function to estimate the speaker's emotion and highlight text according to the emotion. The speech conversion unit, for example, uses the emotion estimation function to analyze the speaker's emotion in real time and highlight text according to the emotion. For example, if the emotion of anger is strong, the text is made bold. The speech conversion unit also changes the color and font of the text based on the speaker's emotion score. For example, if the emotion of joy is strong, the text is displayed in a bright color. The speech conversion unit also adjusts the context of the text based on the emotion estimation data. For example, if the emotion of sadness is strong, an expression that reflects the emotion is added to the text. This makes it possible to highlight text according to the emotion.

[0060] The speech conversion unit can translate speech data into multiple languages ​​in real time and generate text in each language simultaneously. The speech conversion unit, for example, builds a system that translates speech data into multiple languages ​​in real time and generates text in each language simultaneously. For example, speech during a conference is translated into English, Japanese, and Chinese simultaneously. The speech conversion unit also uses a translation algorithm to convert speech data into multiple languages ​​in real time. For example, speech at an international conference is displayed in multiple languages. The speech conversion unit also develops a real-time translation system for speech data and generates text in each language simultaneously. For example, the speech of a news program is translated into multiple languages ​​and displayed. This makes it possible to translate into multiple languages ​​in real time and generate text in each language simultaneously.

[0061] The speech conversion unit can summarize speech data in real time and generate summary text. The speech conversion unit, for example, develops an algorithm that summarizes speech data in real time and generates summary text. For example, it summarizes statements made during a meeting and extracts important points. The speech conversion unit also uses a summarization algorithm to extract the main points of speech data in real time and generate summary text. For example, it summarizes the content of a lecture and converts it into text. The speech conversion unit also builds a summarization system for speech data and generates summary text in real time. For example, it summarizes and displays the content of a news program. This makes it possible to summarize speech data in real time and generate summary text.

[0062] The speech conversion unit can use the emotion estimation function to provide real-time feedback according to the speaker's emotion. The speech conversion unit, for example, uses the emotion estimation function to analyze the speaker's emotion in real time and build a system that provides feedback according to the emotion. For example, if the speaker is nervous, advice to relax is displayed. The speech conversion unit also provides feedback in real time based on the speaker's emotion score. For example, positive feedback is displayed if the speaker is happy. The speech conversion unit also develops a system that provides real-time feedback according to the speaker's emotion based on the emotion estimation data. For example, if the speaker is angry, advice to stay calm is displayed. This makes it possible to provide real-time feedback according to the speaker's emotion.

[0063] The text conversion unit can perform sentiment analysis of the text and adjust the tone and intonation of the voice based on the sentiment. For example, the text conversion unit builds a system that performs sentiment analysis of the text and adjusts the tone and intonation of the voice based on the sentiment. For example, if the sentiment of joy is strong, a bright tone of voice is generated. The text conversion unit also uses sentiment analysis to automatically adjust the tone and intonation of the voice according to the sentiment of the text. For example, if the sentiment of sadness is strong, a calm tone of voice is generated. The text conversion unit also develops a system that adjusts the tone and intonation of the voice in real time based on the sentiment score of the text. For example, if the sentiment of anger is strong, a stressed tone of voice is generated. This makes it possible to adjust the tone and intonation of the voice based on the sentiment.

[0064] The text conversion unit can understand the context of the text and select an appropriate voice character. For example, the text conversion unit builds a system that analyzes the context of the text and selects an appropriate voice character. For example, a child's voice is used for text intended for children. The text conversion unit also uses context analysis to automatically select the voice character best suited to the text. For example, a male voice is used for business documents. The text conversion unit also develops a system that selects a voice character in real time according to the content of the text. For example, a female voice is used for emotional text. This makes it possible to select an appropriate voice character based on the context.

[0065] The text conversion unit can use the emotion estimation function to provide voice feedback according to the user's emotion. For example, the text conversion unit uses the emotion estimation function to analyze the user's emotion in real time and build a system that provides voice feedback according to the emotion. For example, if the user is happy, positive voice feedback is provided. The text conversion unit also adjusts the voice feedback in real time based on the user's emotion score. For example, if the user is sad, comforting voice feedback is provided. The text conversion unit also develops a system that provides voice feedback according to the user's emotion in real time based on the emotion estimation data. For example, if the user is angry, voice feedback to calm down is provided. This makes it possible to provide voice feedback according to the user's emotion.

[0066] The text conversion unit can translate text data into multiple languages ​​and simultaneously generate speech in each language. For example, the text conversion unit builds a system that translates text data into multiple languages ​​in real time and simultaneously generates speech in each language. For example, a news article is simultaneously read aloud in English, Japanese, and Chinese. The text conversion unit also uses a translation algorithm to convert text data into multiple languages ​​in real time and generate speech in each language. For example, materials for an international conference are read aloud in multiple languages. The text conversion unit also develops a real-time translation system for text data and simultaneously generates speech in each language. For example, educational content is provided in multiple languages. This allows translation into multiple languages ​​and simultaneous generation of speech in each language.

[0067] The text conversion unit can summarize text data and generate summarized audio. For example, the text conversion unit develops an algorithm that summarizes text data in real time and generates summarized audio. For example, a long news article is summarized and provided as audio. The text conversion unit also uses a summarization algorithm to extract the main points of text data in real time and generate summarized audio. For example, the content of a lecture is summarized and provided as audio. The text conversion unit also builds a summarization system for text data and generates summarized audio in real time. For example, minutes of a meeting are summarized and provided as audio. In this way, text data can be summarized and summarized audio can be generated.

[0068] The text conversion unit can use the emotion estimation function to provide audio guidance according to the user's emotions. For example, the text conversion unit uses the emotion estimation function to analyze the user's emotions in real time and build a system that provides audio guidance according to the emotions. For example, if the user is nervous, an audio guidance that encourages relaxation is provided. The text conversion unit also adjusts the audio guidance in real time based on the user's emotion score. For example, if the user is happy, a positive audio guidance is provided. The text conversion unit also develops a system that provides audio guidance according to the user's emotions in real time based on the emotion estimation data. For example, if the user is angry, an audio guidance that encourages calmness is provided. This makes it possible to provide audio guidance according to the user's emotions.

[0069] The image generation unit can perform emotion analysis of the text or audio data and adjust the color tone or design of the image based on the emotion. The image generation unit, for example, performs emotion analysis of the text or audio data and builds a system that adjusts the color tone or design of the image based on the emotion. For example, if the emotion of joy is strong, an image with bright color tones is generated. The image generation unit also uses emotion analysis to automatically adjust the color tone or design of the image according to the emotion of the text or audio data. For example, if the emotion of sadness is strong, an image with subdued color tones is generated. The image generation unit also develops a system that adjusts the color tone or design of the image in real time based on the emotion score of the text or audio data. For example, if the emotion of anger is strong, an image with an emphasized design is generated. This makes it possible to adjust the color tone or design of the image based on the emotion.

[0070] The image generation unit can understand the context of text or audio data and generate multiple related images. The image generation unit, for example, builds a system that analyzes the context of text or audio data and generates multiple related images. For example, it generates multiple images of tourist spots from the text of a travelogue. The image generation unit also uses context analysis to automatically generate images related to the text or audio data. For example, it generates multiple slide images based on the content of a lecture. The image generation unit also develops a system that understands the context of text or audio data and generates related images in real time. For example, it generates multiple images related to a news article. This makes it possible to generate multiple related images based on the context.

[0071] The image generation unit can use the emotion estimation function to provide image feedback according to the user's emotion. The image generation unit, for example, uses the emotion estimation function to analyze the user's emotion in real time and build a system that provides image feedback according to the emotion. For example, if the user is happy, a positive image is provided. The image generation unit also adjusts the image feedback in real time based on the user's emotion score. For example, if the user is sad, a comforting image is provided. The image generation unit also develops a system that provides image feedback according to the user's emotion in real time based on the emotion estimation data. For example, if the user is angry, a calming image is provided. This makes it possible to provide image feedback according to the user's emotion.

[0072] The image generation unit can generate 3D models or animations based on text or audio data. The image generation unit builds a system that generates 3D models based on text or audio data. For example, it generates a 3D model of a building from the text of an architectural plan. The image generation unit also analyzes text or audio data and automatically generates animations. For example, it generates character animations from the text of a story. The image generation unit also develops a system that generates 3D models and animations in real time based on text or audio data. For example, it generates 3D models and animations from the text of educational content. This makes it possible to generate 3D models and animations based on text or audio data.

[0073] The image generation unit can generate infographics or data visualizations based on text or audio data. The image generation unit, for example, builds a system that generates infographics based on text or audio data. For example, it generates infographics from text in a business report. The image generation unit also analyzes text or audio data to automatically generate data visualizations. For example, it generates data visualizations from text in a research paper. The image generation unit also develops a system that generates infographics or data visualizations in real time based on text or audio data. For example, it generates data visualizations from text in a news article. This makes it possible to generate infographics or data visualizations based on text or audio data.

[0074] The image generation unit can use the emotion estimation function to customize images according to the user's emotions. The image generation unit, for example, uses the emotion estimation function to analyze the user's emotions in real time and build a system that customizes images according to the emotions. For example, if the user is happy, it provides an image with bright colors. The image generation unit also adjusts the image customization in real time based on the user's emotion score. For example, if the user is sad, it provides an image with calm colors. The image generation unit also develops a system that customizes images according to the user's emotions in real time based on the emotion estimation data. For example, if the user is angry, it provides an image with an emphasized design. This makes it possible to customize images according to the user's emotions.

[0075] The search classification unit can perform sentiment analysis of text or audio data and prioritize search results based on emotion. The search classification unit, for example, performs sentiment analysis of text or audio data and builds a system for prioritizing search results based on emotion. For example, documents with a strong positive emotion are preferentially displayed. The search classification unit also uses sentiment analysis to automatically prioritize search results according to the emotion of the text or audio data. For example, documents with a strong sad emotion are postponed. The search classification unit also develops a system for prioritizing search results in real time based on the sentiment score of the text or audio data. For example, documents with a strong angry emotion are preferentially displayed. This makes it possible to prioritize search results based on emotion.

[0076] The search and classifier can understand the context of text or audio data and automatically link related content. For example, the search and classifier analyzes the context of text or audio data to build a system that automatically links related content. For example, it links related past articles based on the context of a news article. The search and classifier also uses context analysis to automatically link related content to text or audio data. For example, it links related papers based on the context of a research paper. The search and classifier also develops a system that understands the context of text or audio data and links related content in real time. For example, it links related teaching materials based on the context of educational content. This makes it possible to automatically link related content based on context.

[0077] The search categorization unit can use the emotion estimation function to provide search result feedback according to the user's emotions. The search categorization unit, for example, uses the emotion estimation function to analyze the user's emotions in real time and build a system that provides search result feedback according to the emotions. For example, if the user is happy, positive search results are provided. The search categorization unit also adjusts the search result feedback in real time based on the user's emotion score. For example, if the user is sad, comforting search results are provided. The search categorization unit also develops a system that provides search result feedback according to the user's emotions in real time based on the emotion estimation data. For example, if the user is angry, search results that help the user to calm down are provided. This makes it possible to provide search result feedback according to the user's emotions.

[0078] The search and classification unit can search for related video content based on text or audio data. The search and classification unit builds a system for searching for related video content based on text or audio data, for example. For example, related videos are searched for based on the content of a news article. The search and classification unit also uses context analysis to automatically search for video content related to text or audio data. For example, related videos are searched for based on the content of educational content. The search and classification unit also develops a system for searching for related video content in real time based on text or audio data. For example, related videos are searched for based on the content of a lecture. This makes it possible to search for related video content based on text or audio data.

[0079] The search and classification unit can search for related social media posts based on text or audio data. The search and classification unit, for example, builds a system for searching for related social media posts based on text or audio data. For example, it searches for related tweets based on the content of a news article. The search and classification unit also uses context analysis to automatically search for social media posts related to the text or audio data. For example, it searches for related Facebook (registered trademark) posts based on the content of educational content. The search and classification unit also develops a system for searching for related social media posts in real time based on text or audio data. For example, it searches for related Instagram (registered trademark) posts based on the content of a lecture. This makes it possible to search for related social media posts based on text or audio data.

[0080] The search classification unit can use the emotion estimation function to customize search results according to the user's emotions. The search classification unit, for example, uses the emotion estimation function to analyze the user's emotions in real time and build a system that customizes search results according to the emotions. For example, if the user is happy, positive search results are provided. The search classification unit also adjusts the customization of search results in real time based on the user's emotion score. For example, if the user is sad, comforting search results are provided. The search classification unit also develops a system that customizes search results according to the user's emotions in real time based on the emotion estimation data. For example, if the user is angry, calm search results are provided. This makes it possible to customize search results according to the user's emotions.

[0081] The broadcast collaboration unit can perform sentiment analysis of broadcast content and provide additional information based on the sentiment. The broadcast collaboration unit, for example, performs sentiment analysis of broadcast content and builds a system that provides additional information based on the sentiment. For example, it displays related articles based on the sentiment of a news program. The broadcast collaboration unit also uses sentiment analysis to automatically provide additional information based on the sentiment of the broadcast content. For example, it displays related interviews based on the sentiment of a drama. The broadcast collaboration unit also develops a system that provides additional information in real time based on the sentiment score of the broadcast content. For example, it displays related statistical data based on the sentiment of a sports program. This makes it possible to provide additional information based on the sentiment.

[0082] The broadcast collaboration unit can understand the context of the broadcast content and automatically generate related interactive content. For example, the broadcast collaboration unit builds a system that analyzes the context of the broadcast content and automatically generates related interactive content. For example, an interactive quiz is generated based on the content of a news program. The broadcast collaboration unit also uses context analysis to automatically generate interactive content related to the broadcast content. For example, an interactive storyboard is generated based on the content of a drama. The broadcast collaboration unit also develops a system that understands the context of the broadcast content and generates related interactive content in real time. For example, interactive statistical data is generated based on the content of a sports program. This makes it possible to automatically generate related interactive content based on the context.

[0083] The broadcast collaboration unit can use the emotion estimation function to provide real-time feedback according to the viewer's emotions. The broadcast collaboration unit, for example, uses the emotion estimation function to analyze the viewer's emotions in real time and build a system that provides feedback according to the emotions. For example, if the viewer is happy, positive feedback is displayed. The broadcast collaboration unit also provides feedback in real time based on the viewer's emotion score. For example, if the viewer is sad, comforting feedback is displayed. The broadcast collaboration unit also develops a system that provides real-time feedback according to the viewer's emotions based on the emotion estimation data. For example, if the viewer is angry, feedback to calm down is displayed. This makes it possible to provide real-time feedback according to the viewer's emotions.

[0084] The broadcast collaboration unit can translate broadcast content into multiple languages ​​in real time and display subtitles in each language simultaneously. For example, the broadcast collaboration unit builds a system that translates broadcast content into multiple languages ​​in real time and displays subtitles in each language simultaneously. For example, a news program is subtitled simultaneously in English, Japanese, and Chinese. The broadcast collaboration unit also uses a translation algorithm to convert broadcast content into multiple languages ​​in real time and display subtitles in each language. For example, an international conference broadcast is subtitled in multiple languages. The broadcast collaboration unit also develops a real-time translation system for broadcast content and displays subtitles in each language simultaneously. For example, an educational program is subtitled in multiple languages. This allows broadcast content to be translated into multiple languages ​​in real time and subtitles in each language to be displayed simultaneously.

[0085] The broadcast collaboration unit can summarize broadcast content and display summary information in real time. The broadcast collaboration unit, for example, develops an algorithm that summarizes broadcast content in real time and displays summary information. For example, the content of a news program is summarized and displayed. The broadcast collaboration unit also uses a summarization algorithm to extract the main points of broadcast content in real time and display summary information. For example, the content of a documentary program is summarized and displayed. The broadcast collaboration unit also builds a summary system for broadcast content and displays summary information in real time. For example, the content of a sports program is summarized and displayed. This allows broadcast content to be summarized and summary information to be displayed in real time.

[0086] The broadcast collaboration unit can use the emotion estimation function to provide interactive quizzes or questionnaires according to the viewer's emotions. For example, the broadcast collaboration unit uses the emotion estimation function to analyze the viewer's emotions in real time and build a system that provides interactive quizzes and questionnaires according to the emotions. For example, if the viewer is happy, a positive quiz is provided. The broadcast collaboration unit also provides interactive quizzes and questionnaires in real time based on the viewer's emotion score. For example, if the viewer is sad, a comforting questionnaire is provided. The broadcast collaboration unit also develops a system that provides interactive quizzes and questionnaires according to the viewer's emotions in real time based on the emotion estimation data. For example, if the viewer is angry, a quiz to calm the viewer is provided. This makes it possible to provide interactive quizzes and questionnaires according to the viewer's emotions.

[0087] The system according to the embodiment is not limited to the above-described example, and various modifications are possible, for example, as follows.

[0088] The speech conversion unit can automatically remove background sounds or noise from the speech data to enable more accurate text conversion. For example, removing noise during a meeting makes what is being said clearer. The speech conversion unit also uses noise removal technology to improve the quality of the speech data. For example, removing wind noise and traffic noise makes the speaker's voice clearer. The speech conversion unit also analyzes noise in the speech data in real time and applies a noise removal filter. For example, accurate text conversion is possible even in environments with a lot of background noise. This allows for accurate text conversion by removing background sounds and noise.

[0089] The speech conversion unit can translate speech data into multiple languages ​​in real time and generate text in each language simultaneously. For example, speech during a conference can be translated into English, Japanese, and Chinese simultaneously. The speech conversion unit also uses a translation algorithm to convert speech data into multiple languages ​​in real time. For example, speech at an international conference can be displayed in multiple languages. The speech conversion unit has also developed a real-time translation system for speech data and simultaneously generates text in each language. For example, the speech of a news program can be translated into multiple languages ​​and displayed. This makes it possible to translate into multiple languages ​​in real time and generate text in each language simultaneously.

[0090] The speech conversion unit can summarize speech data in real time and generate summary text. For example, it can summarize statements made during a meeting and extract important points. The speech conversion unit also uses a summarization algorithm to extract key points from speech data in real time and generate summary text. For example, it can summarize the content of a lecture and convert it into text. The speech conversion unit also builds a summarization system for speech data and generates summary text in real time. For example, it can summarize and display the content of a news program. This allows speech data to be summarized in real time and summary text to be generated.

[0091] The speech conversion unit can use the emotion estimation function to provide real-time feedback according to the speaker's emotions. For example, if the speaker is nervous, advice to relax is displayed. The speech conversion unit also provides real-time feedback based on the speaker's emotion score. For example, if the speaker is happy, positive feedback is displayed. The speech conversion unit will also develop a system that provides real-time feedback according to the speaker's emotions based on emotion estimation data. For example, if the speaker is angry, advice to stay calm is displayed. This makes it possible to provide real-time feedback according to the speaker's emotions.

[0092] The text conversion unit performs sentiment analysis of the text and can adjust the tone and intonation of the voice based on the emotion. For example, if the emotion of joy is strong, a brighter tone of voice is generated. The text conversion unit also uses sentiment analysis to automatically adjust the tone and intonation of the voice according to the emotion of the text. For example, if the emotion of sadness is strong, a calmer tone of voice is generated. The text conversion unit also develops a system that adjusts the tone and intonation of the voice in real time based on the emotion score of the text. For example, if the emotion of anger is strong, a more emphasized tone of voice is generated. This makes it possible to adjust the tone and intonation of the voice based on the emotion.

[0093] The text conversion unit can understand the context of the text and select an appropriate voice character. For example, a child's voice is used for text intended for children. The text conversion unit also uses contextual analysis to automatically select the voice character best suited to the text. For example, a male voice is used for business documents. The text conversion unit will also develop a system that selects voice characters in real time according to the content of the text. For example, a female voice is used for emotional text. This allows the appropriate voice character to be selected based on the context.

[0094] The text conversion unit can use the emotion estimation function to provide voice feedback according to the user's emotions. For example, if the user is happy, it provides positive voice feedback. The text conversion unit also adjusts the voice feedback in real time based on the user's emotion score. For example, if the user is sad, it provides comforting voice feedback. The text conversion unit also develops a system that provides voice feedback according to the user's emotions in real time based on the emotion estimation data. For example, if the user is angry, it provides voice feedback to calm down. This makes it possible to provide voice feedback according to the user's emotions.

[0095] The image generation unit can understand the context of text or audio data and generate multiple related images. For example, it generates multiple images of tourist spots from the text of a travelogue. The image generation unit also uses context analysis to automatically generate images related to text or audio data. For example, it generates multiple slide images based on the content of a lecture. The image generation unit also develops a system that understands the context of text or audio data and generates related images in real time. For example, it generates multiple images related to a news article. This makes it possible to generate multiple related images based on context.

[0096] The image generation unit can generate 3D models or animations based on text or audio data. For example, it generates a 3D model of a building from the text of an architectural plan. The image generation unit also analyzes text and audio data to automatically generate animations. For example, it generates character animations from the text of a story. The image generation unit also develops a system that generates 3D models and animations in real time based on text and audio data. For example, it generates 3D models and animations from the text of educational content. This makes it possible to generate 3D models and animations based on text and audio data.

[0097] The search and classifier can understand the context of text or audio data and automatically link related content. For example, it links related past articles based on the context of a news article. The search and classifier also uses context analysis to automatically link related content to text or audio data. For example, it links related papers based on the context of a research paper. The search and classifier also develops a system that understands the context of text or audio data and links related content in real time. For example, it links related teaching materials based on the context of educational content. This allows for automatic linking of related content based on context.

[0098] The processing flow of the second embodiment will be briefly explained below.

[0099] Step 1: The speech conversion unit converts the speech data into text in real time. For example, speech spoken during a meeting can be transcribed in real time. The speech conversion unit analyzes the speech data using generative AI (e.g., text generation AI or multimodal generation AI) and generates text. Step 2: The text conversion unit converts the text converted by the speech conversion unit back into speech. For example, a news article written in text can be read aloud. The text conversion unit uses generative AI to analyze the text data and generate speech. Step 3: The image generation unit generates related images from the text and audio data. For example, it can generate an image of a scene described in the text. The image generation unit uses generative AI to analyze the text and audio data and generate an image. Step 4: The search and classification unit uses embedding technology to search and classify the images, text, and audio data generated by the image generation unit. For example, it can search for documents related to specific keywords from a large amount of document data. The search and classification unit uses generation AI to analyze the text and audio data to be searched and classified, and generates search and classification results. Step 5: The broadcasting linkage unit links the data searched and classified by the search and classification unit with the TV broadcasting system to expand the broadcast content as rich media. For example, it can display additional information related to a news program currently being broadcast in real time. The broadcasting linkage unit uses generation AI to analyze the broadcast content data and generate the additional information.

[0100] 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.

[0101] The data generation model 58 is a so-called generative AI (Artificial Intelligence). An example of the data generation model 58 is ChatGPT (registered trademark) (Internet search engine).<URL: https: / / openai.com / blog / chatgpt> Examples of generative AIs include the data generation model 58, such as a neural network model (e.g., a neural network model), and a neural network model (e.g., a neural network model). The data generation model 58 is obtained by performing deep learning on a neural network. A prompt including an instruction is input to the data generation model 58, and inference data such as voice data indicating speech, text data indicating text, and image data indicating an image is also input to the data generation model 58. The data generation model 58 performs inference on the input inference data in accordance with the instruction indicated by the prompt and outputs the inference result in a data format such as voice data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization. The specification processing unit 290 performs the above-mentioned specification processing using the data generation model 58. The data generation model 58 may be a fine-tuned model so as to output an inference result from a prompt that does not include an instruction. In this case, the data generation model 58 can output an inference result from a prompt that does not include an instruction. The data processing device 12 and the like include multiple types of data generation models 58, and the data generation model 58 includes AIs other than the generative AI. The AI ​​other than the generative AI may be, for example, linear regression, logistic regression, decision tree, random forest, support vector machine (SVM), k-means clustering, convolutional neural network (CNN), recurrent neural network (RNN), generative adversarial network (GAN), or naive Bayes, and can perform various processes, but is not limited to these examples. The AI ​​may also be an AI agent. When the processes of each of the above-mentioned parts are performed by AI, the processes may be performed in part or entirely by AI, but are not limited to these examples. The processes performed by AI, including the generative AI, may be replaced with rule-based processes.

[0102] 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.

[0103] [Second embodiment] FIG. 3 shows an example of the configuration of a data processing system 210 according to the second embodiment.

[0104] 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.

[0105] 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.

[0106] 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.

[0107] 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.

[0108] 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).

[0109] 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.

[0110] 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.

[0111] 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.

[0112] 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.

[0113] 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.

[0114] 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.

[0115] 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.

[0116] 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.

[0117] 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.

[0118] [Third embodiment] FIG. 5 shows an example of the configuration of a data processing system 310 according to the third embodiment.

[0119] 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.

[0120] 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.

[0121] 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.

[0122] 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.

[0123] 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).

[0124] 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.

[0125] 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.

[0126] 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.

[0127] 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.

[0128] 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.

[0129] 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.

[0130] 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.

[0131] 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.

[0132] 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.

[0133] [Fourth embodiment] FIG. 7 shows an example of the configuration of a data processing system 410 according to the fourth embodiment.

[0134] 7, a data processing system 410 includes a data processing device 12 and a robot 414. An example of the data processing device 12 is a server.

[0135] 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.

[0136] 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.

[0137] 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.

[0138] 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).

[0139] 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.

[0140] 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.

[0141] 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.

[0142] 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.

[0143] 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.

[0144] 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.

[0145] 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.

[0146] 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.

[0147] 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.

[0148] 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.

[0149] 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.

[0150] 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.

[0151] 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.

[0152] 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).

[0153] 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.

[0154] 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."

[0155] 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.

[0156] 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.

[0157] 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.

[0158] 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.

[0159] 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.

[0160] 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.

[0161] 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.

[0162] 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.

[0163] 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.

[0164] 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.

[0165] 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.

[0166] 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]

[0167] 10, 210, 310, 410 Data Processing Systems 12 Data Processing Device 14 Smart Devices 214 Smart Glasses 314 Headset-type terminal 414 Robot

Claims

1. a speech conversion unit that converts speech data into text in real time; a text conversion unit that converts the text converted by the speech conversion unit back into speech; an image generation unit that generates an associated image from the text or audio data converted by the text conversion unit; a search and classification unit that searches or classifies the image, text, or audio data generated by the image generation unit using an embedding technique; a broadcast linkage unit that links the data searched or classified by the search and classification unit with a TV broadcast system to expand the broadcast content as rich media. A system characterized by:

2. The voice conversion unit performing a sentiment analysis of the audio data and adjusting the wording of the text based on the sentiment; The system of claim 1 .

3. The voice conversion unit Automatically remove background sounds or noise from the audio data to achieve more accurate text conversion. The system of claim 1 .

4. The voice conversion unit Estimating the speaker's emotions and highlighting the text according to the emotions The system of claim 1 .

5. The voice conversion unit translating the voice data into multiple languages ​​in real time and simultaneously generating the text in each language; The system of claim 1 .

6. The voice conversion unit Summarizing the audio data in real time to generate a summary text. The system of claim 1 .

7. The voice conversion unit Providing real-time feedback based on the speaker's emotions The system of claim 1 .

8. The text conversion unit performing a sentiment analysis of the text and adjusting the tone or intonation of the speech based on the sentiment; The system of claim 1 .

Images