System

Abstract

An object of a system according to an embodiment is to improve generation and accessibility of multimedia content.SOLUTION: A system includes a voice conversion unit, a text conversion unit, an image generation unit, and a text analysis unit. The voice conversion unit converts the voice data into text data. The text conversion unit converts the text data converted by the voice conversion unit into voice data. The image generation unit generates a customizable image based on an instruction from a user. The text analysis unit analyzes text data.SELECTED DRAWING: Figure 1

Description

[Technical Field]

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

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

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

[0004] Conventional technologies have not adequately addressed the creation and accessibility of multimedia content, and there is room for improvement.

[0005] A system according to an embodiment aims to improve the creation and accessibility of multimedia content. [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, and a text analysis unit. The speech conversion unit converts speech data into text data. The text conversion unit converts the text data converted by the speech conversion unit into speech data. The image generation unit generates a customizable image based on a user instruction. The text analysis unit analyzes the text data. [Effects of the Invention]

[0007] Systems according to embodiments can improve the creation and accessibility of multimedia content. [Brief explanation of the drawings]

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

[0028] (Example 1) A media conversion hub according to an embodiment of the present invention is a system that converts audio data to text data, converts text data to audio data, generates customizable images, and analyzes text data, thereby enabling the generation and accessibility of multimedia content.

[0029] A media conversion hub according to an embodiment includes a speech conversion unit, a text conversion unit, an image generation unit, and a text analysis unit. The speech conversion unit converts speech data into text data. For example, the speech conversion unit analyzes speech data using a generation AI and outputs text data. The speech conversion unit can also convert speech data into text data in real time. For example, the speech of a news program can be converted into text in real time and displayed as subtitles. The text conversion unit converts the text data converted by the speech conversion unit into speech data. For example, the text conversion unit analyzes text data using a generation AI and outputs speech data. The text conversion unit can also read news articles and educational materials aloud. For example, the generation AI analyzes text data and generates natural-sounding speech. The image generation unit generates customizable images based on user instructions. For example, the image generation unit analyzes prompts containing image generation instructions using a generation AI and outputs image data. The image generation unit can also generate charts and illustrations for use in educational materials. For example, the generation AI generates images based on prompts and customizes them according to user requests. The text analysis unit analyzes text data. For example, the text analysis unit uses a generation AI to analyze the text data and output summaries and keywords. The text analysis unit can also deeply understand the content of the text and perform sentiment analysis. For example, the generation AI analyzes the text data and calculates a sentiment score. This enables the media conversion hub according to the embodiment to generate multimedia content and improve accessibility. For example, it can convert audio content into text and provide it to the hearing impaired, or provide text content as audio to the visually impaired. Furthermore, educational institutions can streamline the creation and distribution of teaching materials and provide content that meets the needs of learners.

[0030] The voice conversion unit can automatically remove background sounds and noise from voice data to enable clear text conversion. For example, the voice conversion unit analyzes voice data and develops algorithms that automatically detect and remove background sounds and noise. For example, it extracts only the speaker's voice from voice data recorded in a noisy environment and converts it into text. The voice conversion unit also uses technology to filter specific frequency bands when removing noise from voice data. For example, it removes low-frequency background sounds and emphasizes the speaker's high-frequency voice. To remove noise, the voice conversion unit also uses multiple microphones to collect voice data and perform spatial noise cancellation. For example, when recording in a conference room, it removes ambient noise to make the speaker's voice clearer. This improves the quality of the voice data and enables accurate text conversion.

[0031] The speech conversion unit can identify speakers of audio data and apply different text styles to each speaker. For example, the speech conversion unit analyzes audio data and develops an algorithm to identify speakers based on their voice characteristics. For example, it can identify each speaker from a meeting recording and apply a different text style to each speaker. To identify speakers, the speech conversion unit also uses technology to analyze characteristics of audio data, such as pitch, tempo, and tone of voice. For example, it can identify male and female voices and apply appropriate text styles to each. To improve the accuracy of speaker identification, the speech conversion unit collects speaker voice samples in advance and trains a machine learning model. For example, it can pre-register the voice of a specific speaker and automatically identify that speaker each time they speak. This improves readability by applying an appropriate text style to each speaker.

[0032] The speech conversion unit can convert speech data into multiple languages ​​simultaneously and generate multilingual subtitles. For example, the speech conversion unit analyzes speech data and develops algorithms for simultaneous conversion into multiple languages. For example, English speech data can be converted into Japanese, French, Chinese, etc. in real time to generate multilingual subtitles. For multilingual conversion, the speech conversion unit pre-trains speech recognition models for each language and uses technology to select an appropriate model when analyzing speech data. For example, the language of the speech data can be automatically identified and the corresponding language model can be applied. To improve the accuracy of multilingual subtitle generation, the speech conversion unit also develops technology to analyze the context of speech data and perform appropriate translations. For example, technical terms and proper nouns can be accurately translated and reflected in multilingual subtitles. This enables multilingual support and can reach a wide range of viewers.

[0033] The speech conversion unit can summarize the content of the speech data and output it as short text. For example, the speech conversion unit develops an algorithm that analyzes speech data and extracts important information to summarize it. For example, it extracts key points from long conference recordings and outputs them as short text. The speech conversion unit also uses technology to analyze the context of speech data and extract important keywords and phrases for summarization. For example, it summarizes key news items from the speech data of a news program. The speech conversion unit also collects speech data with summary labels in advance and trains a machine learning model to improve the accuracy of summaries. For example, it generates summaries of speech data in real time and outputs them as short text. This allows the main points of the speech data to be output as short text.

[0034] The text conversion unit can understand the context of text data and generate speech with appropriate intonation and inflection. The text conversion unit, for example, analyzes text data and develops algorithms to understand the context. For example, it generates speech with appropriate intonation and inflection for questions and exclamations. The text conversion unit also uses techniques for syntactic and semantic analysis of text data to understand the context. For example, it analyzes the structure and meaning of sentences and generates appropriate speech expressions. The text conversion unit also collects text data with audio labels in advance and trains machine learning models to improve the accuracy of speech generation with intonation and inflection. For example, it generates speech expressions according to emotions and context in real time. This enables natural speech generation according to context.

[0035] The text conversion unit can use different speaker voices depending on the content of the text data. For example, the text conversion unit analyzes text data and develops an algorithm to select different speaker voices depending on the content. For example, it uses multiple speaker voices for dialogue-style text. The text conversion unit also uses technology to analyze the context and speaker information of the text data to select speakers. For example, it assigns different voices to different characters. To improve the accuracy of using different speaker voices, the text conversion unit also collects text data with speaker labels in advance and trains a machine learning model. For example, it automatically selects speakers depending on the content of the text. This makes it possible to generate appropriate speaker voices depending on the content of the text.

[0036] The text conversion unit can translate text data into multiple languages ​​and generate speech in each language. For example, the text conversion unit analyzes text data and develops algorithms for translating into multiple languages. For example, it translates English text into Japanese, French, Chinese, etc., and generates speech in each language. For multilingual translation, the text conversion unit pre-trains translation models for each language and uses technology to select an appropriate model when analyzing text data. For example, it automatically identifies the language of the text and applies the corresponding translation model. To improve the accuracy of multilingual speech generation, the text conversion unit pre-collects text data labeled with multilingual labels and trains a machine learning model. For example, it accurately translates technical terms and proper nouns and reflects them in multilingual speech. This enables multilingual support and can reach a wide range of viewers.

[0037] The text conversion unit can summarize the content of text data and output it as short audio. For example, the text conversion unit develops an algorithm that analyzes text data and extracts important information to summarize it. For example, it extracts the main points from a long article and outputs them as short audio. The text conversion unit also uses technology to analyze the context of text data and extract important keywords and phrases for summarization. For example, it summarizes the main points of a news article and outputs them as short audio. The text conversion unit also collects text data with summary labels in advance and trains a machine learning model to improve the accuracy of summaries. For example, it generates a summary of the text data in real time and outputs it as short audio. This allows the main points of the text data to be output as short audio.

[0038] The image generation unit can automatically generate multiple image styles based on user instructions and provide options. For example, the image generation unit develops an algorithm that automatically generates multiple image styles based on user instructions. For example, it generates images of the same theme in different art styles and provides the user with options. The image generation unit also uses technology to analyze the user's instructions and select an appropriate style when generating images. For example, it generates images based on colors and shapes specified by the user. The image generation unit also collects image data with style labels in advance and trains a machine learning model to improve the accuracy of generating multiple image styles. For example, it automatically suggests styles based on the user's preferences. This allows the user to choose from multiple image styles.

[0039] The image generation unit can learn the user's past preferences and suggest optimal images. For example, the image generation unit develops an algorithm that learns the user's past preferences and suggests optimal images. For example, it suggests new images based on image styles selected by the user in the past. The image generation unit also uses technology to analyze the user's selection history to learn past preferences. For example, it extracts the user's favorite colors and shapes and generates images based on them. The image generation unit also collects user preference data in advance and trains a machine learning model to improve the accuracy of suggesting optimal images. For example, it suggests images that match the user's preferences in real time. This makes it possible to suggest optimal images based on the user's past preferences.

[0040] The image generation unit can customize images by incorporating elements from different cultures and regions based on user instructions. For example, the image generation unit develops algorithms to generate images incorporating elements from different cultures and regions. For example, it generates images incorporating traditional Japanese designs or American pop art styles. To incorporate cultural and regional elements, the image generation unit also uses technology to analyze the design elements and colors of each region. For example, it can reflect the traditional patterns and colors of a specific region in an image. To improve the accuracy of image generation that incorporates elements from different cultures and regions, the image generation unit also collects image data with cultural labels in advance and trains a machine learning model. For example, it can automatically incorporate cultural elements according to user specifications. This makes it possible to generate images that incorporate elements from different cultures and regions.

[0041] The image generation unit can animate the generated images and provide them as dynamic content. The image generation unit, for example, develops an algorithm for animating the generated images. For example, the image generation unit generates dynamic content by continuously changing still images. The image generation unit also uses a technique for breaking down each element of an image and adding movement to it for animation. For example, it simulates the movement of joints and muscles to smooth the character's movements. The image generation unit also collects image data with animation labels in advance and trains a machine learning model to improve the accuracy of generating dynamic content. For example, it automatically generates animations according to user instructions. This makes it possible to generate images as dynamic content.

[0042] The text analysis unit can deeply understand the context of text data and automatically link related information. For example, the text analysis unit analyzes text data and develops algorithms that deeply understand context. For example, it analyzes the context of a news article and automatically links related past articles and information. The text analysis unit also uses techniques for syntactic and semantic analysis of text data to understand the context. For example, it analyzes the structure and meaning of sentences and links related information. The text analysis unit also collects text data with link labels in advance and trains a machine learning model to improve the accuracy of links to related information. For example, it automatically suggests related information that the user may be interested in. This makes it possible to understand the context of the text and automatically link related information.

[0043] The text analysis unit can analyze the content of text data and extract potential themes and topics. For example, the text analysis unit analyzes text data and develops algorithms to extract potential themes and topics. For example, it extracts major themes and topics from long articles. The text analysis unit also uses techniques for semantic analysis and topic modeling of text data to extract themes and topics. For example, it analyzes the meaning of sentences and extracts related themes. The text analysis unit also collects text data with theme labels in advance and trains a machine learning model to improve the accuracy of theme and topic extraction. For example, it automatically extracts themes that are likely to interest users. This makes it possible to analyze the content of text and extract potential themes and topics.

[0044] The text analysis unit can visualize the results of text analysis in different formats. For example, the text analysis unit develops algorithms to visualize the results of text analysis in graphs and charts. For example, the text analysis unit displays the sentiment analysis results of text data in a pie chart or bar graph. For visualization, the text analysis unit stores the text analysis results in a database and uses technology to display them in an appropriate format. For example, the text analysis unit displays the frequency of keyword appearances in a heat map. To improve the accuracy of visualization, the text analysis unit collects text data with visualization labels in advance and trains a machine learning model. For example, the text analysis unit displays the analysis results in a format that is easy for users to understand. This makes the results of text analysis easier to understand visually.

[0045] The text analysis unit can integrate the results of text analysis with other datasets to gain new insights. For example, the text analysis unit develops algorithms to integrate the results of text analysis with other datasets. For example, the text analysis unit integrates the results of news article analysis with social media data to analyze trends. The text analysis unit also uses technology to unify the formats of different datasets and link the analysis results for data integration. For example, it integrates text data and image data to analyze relevance. The text analysis unit also collects datasets with integrated labels in advance to train machine learning models to improve the accuracy of data integration. For example, it integrates information from different data sources to gain new insights. This allows the results of text analysis to be integrated with other datasets to gain new insights.

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

[0047] The Media Conversion Hub can also analyze user behavior history to provide content optimized for individual users. For example, it can recommend new related content based on the content a user has previously viewed. To analyze user behavior history, it collects data such as viewing time and number of clicks and uses technology to train machine learning models. For example, if a user prefers content from a specific genre, it can prioritize recommendations for content related to that genre. It can also display advertisements optimized for individual users based on user behavior history. For example, it can display advertisements related to products purchased in the past. This makes it possible to provide personalized content based on a user's behavior history.

[0048] The speech conversion unit can also estimate the age and gender of the speaker of the speech data and incorporate this information into the text conversion. For example, it analyzes speech data and develops an algorithm to estimate age and gender based on the speaker's vocal characteristics. For example, it can distinguish between children's voices and adult voices and apply appropriate text styles to each. The speech conversion unit also uses technology to analyze features such as pitch, tempo, and tone of the speech data to estimate age and gender. For example, it can distinguish between male and female voices and apply appropriate text styles to each. To improve the accuracy of age and gender estimation, the speech conversion unit collects speech data labeled with age and gender in advance and trains a machine learning model. For example, it can pre-register the voices of speakers of a specific age group or gender and automatically identify them each time they speak. This improves readability by applying appropriate text styles according to the speaker's age and gender.

[0049] The speech conversion unit can convert audio data into multiple languages ​​simultaneously and generate multilingual subtitles. For example, it analyzes audio data and develops algorithms for simultaneous conversion into multiple languages. For example, it converts English audio data into Japanese, French, Chinese, etc. in real time to generate multilingual subtitles. For multilingual conversion, the speech conversion unit pre-trains speech recognition models for each language and uses technology to select the appropriate model when analyzing the audio data. For example, it automatically identifies the language of the audio data and applies the corresponding language model. To improve the accuracy of multilingual subtitle generation, the speech conversion unit also develops technology to analyze the context of the audio data and perform appropriate translations. For example, it accurately translates technical terms and proper nouns and reflects them in multilingual subtitles. This enables multilingual support and can reach a wide range of viewers.

[0050] The speech conversion unit can summarize the content of audio data and output it as short text. For example, it develops an algorithm that analyzes audio data, extracts important information, and summarizes it. For example, it extracts key points from long conference recordings and outputs them as short text. The speech conversion unit also uses technology to analyze the context of audio data and extract important keywords and phrases for summarization. For example, it summarizes key news items from audio data of a news program. The speech conversion unit also collects audio data with summary labels in advance and trains a machine learning model to improve the accuracy of summaries. For example, it generates summaries of audio data in real time and outputs them as short text. This allows the main points of the audio data to be output as short text.

[0051] The text conversion unit can understand the context of text data and generate speech with appropriate intonation and inflection. For example, it analyzes text data and develops an algorithm to understand the context. For example, it generates speech with appropriate intonation and inflection for questions and exclamations. The text conversion unit also uses techniques for syntactic and semantic analysis of text data to understand the context. For example, it analyzes the structure and meaning of sentences and generates appropriate speech expressions. The text conversion unit also collects text data with audio labels in advance and trains machine learning models to improve the accuracy of speech generation with intonation and inflection. For example, it generates speech expressions according to emotions and context in real time. This enables natural speech generation according to context.

[0052] The text conversion unit can use different speaker voices depending on the content of the text data. For example, it analyzes text data and develops an algorithm to select different speaker voices depending on the content. For example, it uses multiple speaker voices for dialogue-style text. The text conversion unit also uses technology to analyze the context and speaker information of the text data to select speakers. For example, it assigns different voices to each character. To improve the accuracy of using different speaker voices, the text conversion unit also collects text data with speaker labels in advance and trains a machine learning model. For example, it automatically selects speakers depending on the content of the text. This makes it possible to generate appropriate speaker voices according to the content of the text.

[0053] The text conversion unit can translate text data into multiple languages ​​and generate speech in each language. For example, it analyzes text data and develops algorithms for translating into multiple languages. For example, it translates English text into Japanese, French, Chinese, etc., and generates speech in each language. For multilingual translation, the text conversion unit pre-trains translation models for each language and uses technology to select the appropriate model when analyzing text data. For example, it automatically identifies the language of the text and applies the corresponding translation model. To improve the accuracy of multilingual speech generation, the text conversion unit also collects multilingually labeled text data in advance and trains a machine learning model. For example, it accurately translates technical terms and proper nouns and reflects them in multilingual speech. This enables multilingual support and can reach a wide range of viewers.

[0054] The processing flow of the first embodiment will be briefly explained below.

[0055] Step 1: The speech conversion unit converts the speech data into text data. For example, the speech conversion unit analyzes the speech data using generative AI and outputs text data. The speech conversion unit can also convert speech data into text data in real time. For example, the speech of a news program can be converted into text in real time and displayed as subtitles. Step 2: The text conversion unit converts the text data converted by the speech conversion unit into speech data. For example, the text conversion unit uses generative AI to analyze the text data and output speech data. The text conversion unit can also read out news articles or educational materials aloud. For example, generative AI analyzes the text data and generates natural-sounding speech. Step 3: The image generator generates a customizable image based on the user's instructions. For example, the image generator uses generative AI to analyze prompts containing image generation instructions and output image data. The image generator can also generate charts and illustrations for use in educational materials. For example, the generative AI generates an image based on the prompts and customizes it to meet the user's needs. Step 4: The text analysis unit analyzes the text data. For example, the text analysis unit uses the generation AI to analyze the text data and output summaries and keywords. The text analysis unit can also deeply understand the content of the text and perform sentiment analysis. For example, the generation AI analyzes the text data and calculates a sentiment score.

[0056] (Example 2) A media conversion hub according to an embodiment of the present invention is a system that converts audio data to text data, converts text data to audio data, generates customizable images, and analyzes text data, thereby enabling the generation and accessibility of multimedia content.

[0057] A media conversion hub according to an embodiment includes a speech conversion unit, a text conversion unit, an image generation unit, and a text analysis unit. The speech conversion unit converts speech data into text data. For example, the speech conversion unit analyzes speech data using a generation AI and outputs text data. The speech conversion unit can also convert speech data into text data in real time. For example, the speech of a news program can be converted into text in real time and displayed as subtitles. The text conversion unit converts the text data converted by the speech conversion unit into speech data. For example, the text conversion unit analyzes text data using a generation AI and outputs speech data. The text conversion unit can also read news articles and educational materials aloud. For example, the generation AI analyzes text data and generates natural-sounding speech. The image generation unit generates customizable images based on user instructions. For example, the image generation unit analyzes prompts containing image generation instructions using a generation AI and outputs image data. The image generation unit can also generate charts and illustrations for use in educational materials. For example, the generation AI generates images based on prompts and customizes them according to user requests. The text analysis unit analyzes text data. For example, the text analysis unit uses a generation AI to analyze the text data and output summaries and keywords. The text analysis unit can also deeply understand the content of the text and perform sentiment analysis. For example, the generation AI analyzes the text data and calculates a sentiment score. This enables the media conversion hub according to the embodiment to generate multimedia content and improve accessibility. For example, it can convert audio content into text and provide it to the hearing impaired, or provide text content as audio to the visually impaired. Furthermore, educational institutions can streamline the creation and distribution of teaching materials and provide content that meets the needs of learners.

[0058] The voice conversion unit can automatically remove background sounds and noise from voice data to enable clear text conversion. For example, the voice conversion unit analyzes voice data and develops algorithms that automatically detect and remove background sounds and noise. For example, it extracts only the speaker's voice from voice data recorded in a noisy environment and converts it into text. The voice conversion unit also uses technology to filter specific frequency bands when removing noise from voice data. For example, it removes low-frequency background sounds and emphasizes the speaker's high-frequency voice. To remove noise, the voice conversion unit also uses multiple microphones to collect voice data and perform spatial noise cancellation. For example, when recording in a conference room, it removes ambient noise to make the speaker's voice clearer. This improves the quality of the voice data and enables accurate text conversion.

[0059] The speech conversion unit can identify speakers of audio data and apply different text styles to each speaker. For example, the speech conversion unit analyzes audio data and develops an algorithm to identify speakers based on their voice characteristics. For example, it can identify each speaker from a meeting recording and apply a different text style to each speaker. To identify speakers, the speech conversion unit also uses technology to analyze characteristics of audio data, such as pitch, tempo, and tone of voice. For example, it can identify male and female voices and apply appropriate text styles to each. To improve the accuracy of speaker identification, the speech conversion unit collects speaker voice samples in advance and trains a machine learning model. For example, it can pre-register the voice of a specific speaker and automatically identify that speaker each time they speak. This improves readability by applying an appropriate text style to each speaker.

[0060] The speech conversion unit can use an emotion estimation function to estimate the emotion of a speaker of speech data and generate a text representation corresponding to the emotion. For example, the speech conversion unit analyzes speech data and develops an algorithm to estimate emotion based on features such as the tone, pitch, and tempo of the speaker's voice. For example, if the speaker is angry, a text representation reflecting the emotion is generated. To estimate emotion, the speech conversion unit performs waveform and spectral analysis of speech data and uses technology to extract emotional features. For example, if the speaker's voice is excited, a text representation reflecting a positive emotion is generated. To improve the accuracy of emotion estimation, the speech conversion unit collects speech data with emotion labels in advance and trains a machine learning model. For example, the speech conversion unit estimates the emotion of the speaker's voice in real time and generates a text representation corresponding to the emotion. This enables text representations that reflect the speaker's emotion.

[0061] The speech conversion unit can convert speech data into multiple languages ​​simultaneously and generate multilingual subtitles. For example, the speech conversion unit analyzes speech data and develops algorithms for simultaneous conversion into multiple languages. For example, English speech data can be converted into Japanese, French, Chinese, etc. in real time to generate multilingual subtitles. For multilingual conversion, the speech conversion unit pre-trains speech recognition models for each language and uses technology to select an appropriate model when analyzing speech data. For example, the language of the speech data can be automatically identified and the corresponding language model can be applied. To improve the accuracy of multilingual subtitle generation, the speech conversion unit also develops technology to analyze the context of speech data and perform appropriate translations. For example, technical terms and proper nouns can be accurately translated and reflected in multilingual subtitles. This enables multilingual support and can reach a wide range of viewers.

[0062] The speech conversion unit can summarize the content of the speech data and output it as short text. For example, the speech conversion unit develops an algorithm that analyzes speech data and extracts important information to summarize it. For example, it extracts key points from long conference recordings and outputs them as short text. The speech conversion unit also uses technology to analyze the context of speech data and extract important keywords and phrases for summarization. For example, it summarizes key news items from the speech data of a news program. The speech conversion unit also collects speech data with summary labels in advance and trains a machine learning model to improve the accuracy of summaries. For example, it generates summaries of speech data in real time and outputs them as short text. This allows the main points of the speech data to be output as short text.

[0063] The speech conversion unit can use an emotion estimation function to analyze the emotional tone of speech data and perform text conversion according to the emotion. The speech conversion unit, for example, analyzes speech data and develops an algorithm to estimate the emotional tone. For example, if the speaker's tone of voice is sad, text conversion is performed that reflects the emotion. To analyze the emotional tone, the speech conversion unit performs waveform and spectral analysis of the speech data and uses technology to extract emotional features. For example, if the speaker's voice is excited, text conversion is performed that reflects a positive emotion. To improve the accuracy of text conversion that reflects the emotional tone, the speech conversion unit collects speech data with emotion labels in advance and trains a machine learning model. For example, the speech conversion unit estimates the speaker's emotion in real time and performs text conversion according to the emotion. This enables text conversion that reflects the emotion of speech data.

[0064] The text conversion unit can understand the context of text data and generate speech with appropriate intonation and inflection. The text conversion unit, for example, analyzes text data and develops algorithms to understand the context. For example, it generates speech with appropriate intonation and inflection for questions and exclamations. The text conversion unit also uses techniques for syntactic and semantic analysis of text data to understand the context. For example, it analyzes the structure and meaning of sentences and generates appropriate speech expressions. The text conversion unit also collects text data with audio labels in advance and trains machine learning models to improve the accuracy of speech generation with intonation and inflection. For example, it generates speech expressions according to emotions and context in real time. This enables natural speech generation according to context.

[0065] The text conversion unit can use different speaker voices depending on the content of the text data. For example, the text conversion unit analyzes text data and develops an algorithm to select different speaker voices depending on the content. For example, it uses multiple speaker voices for dialogue-style text. The text conversion unit also uses technology to analyze the context and speaker information of the text data to select speakers. For example, it assigns different voices to different characters. To improve the accuracy of using different speaker voices, the text conversion unit also collects text data with speaker labels in advance and trains a machine learning model. For example, it automatically selects speakers depending on the content of the text. This makes it possible to generate appropriate speaker voices depending on the content of the text.

[0066] The text conversion unit can use the emotion estimation function to estimate the emotion of text data and generate a voice expression corresponding to the emotion. For example, the text conversion unit analyzes text data and develops an algorithm for estimating emotion. For example, it generates a bright-toned voice for text with a positive emotion. The text conversion unit also uses technology to analyze the emotion labels of text data for emotion estimation. For example, it extracts keywords and phrases that express emotions and estimates emotions. The text conversion unit also collects text data with emotion labels in advance and trains a machine learning model to improve the accuracy of the voice expression corresponding to the emotion. For example, it generates a voice expression corresponding to the emotion in real time. This makes it possible to generate a voice expression that reflects the emotion of the text.

[0067] The text conversion unit can translate text data into multiple languages ​​and generate speech in each language. For example, the text conversion unit analyzes text data and develops algorithms for translating into multiple languages. For example, it translates English text into Japanese, French, Chinese, etc., and generates speech in each language. For multilingual translation, the text conversion unit pre-trains translation models for each language and uses technology to select an appropriate model when analyzing text data. For example, it automatically identifies the language of the text and applies the corresponding translation model. To improve the accuracy of multilingual speech generation, the text conversion unit pre-collects text data labeled with multilingual labels and trains a machine learning model. For example, it accurately translates technical terms and proper nouns and reflects them in multilingual speech. This enables multilingual support and can reach a wide range of viewers.

[0068] The text conversion unit can summarize the content of text data and output it as short audio. For example, the text conversion unit develops an algorithm that analyzes text data and extracts important information to summarize it. For example, it extracts the main points from a long article and outputs them as short audio. The text conversion unit also uses technology to analyze the context of text data and extract important keywords and phrases for summarization. For example, it summarizes the main points of a news article and outputs them as short audio. The text conversion unit also collects text data with summary labels in advance and trains a machine learning model to improve the accuracy of summaries. For example, it generates a summary of the text data in real time and outputs it as short audio. This allows the main points of the text data to be output as short audio.

[0069] The text conversion unit can use an emotion estimation function to analyze the emotional tone of text data and perform speech conversion according to the emotion. The text conversion unit, for example, analyzes text data and develops an algorithm to estimate the emotional tone. For example, it generates a bright-toned speech for text with a positive emotion. The text conversion unit also uses technology to analyze the emotion labels of text data to analyze the emotional tone. For example, it extracts keywords and phrases that express emotions and estimates the emotion. The text conversion unit also collects text data with emotion labels in advance and trains a machine learning model to improve the accuracy of speech conversion that reflects the emotional tone. For example, it performs speech conversion according to the emotion in real time. This enables speech conversion that reflects the emotion of the text.

[0070] The image generation unit can automatically generate multiple image styles based on user instructions and provide options. For example, the image generation unit develops an algorithm that automatically generates multiple image styles based on user instructions. For example, it generates images of the same theme in different art styles and provides the user with options. The image generation unit also uses technology to analyze the user's instructions and select an appropriate style when generating images. For example, it generates images based on colors and shapes specified by the user. The image generation unit also collects image data with style labels in advance and trains a machine learning model to improve the accuracy of generating multiple image styles. For example, it automatically suggests styles based on the user's preferences. This allows the user to choose from multiple image styles.

[0071] The image generation unit can learn the user's past preferences and suggest optimal images. For example, the image generation unit develops an algorithm that learns the user's past preferences and suggests optimal images. For example, it suggests new images based on image styles selected by the user in the past. The image generation unit also uses technology to analyze the user's selection history to learn past preferences. For example, it extracts the user's favorite colors and shapes and generates images based on them. The image generation unit also collects user preference data in advance and trains a machine learning model to improve the accuracy of suggesting optimal images. For example, it suggests images that match the user's preferences in real time. This makes it possible to suggest optimal images based on the user's past preferences.

[0072] The image generation unit can use the emotion estimation function to estimate the user's emotion and generate an image corresponding to the emotion. The image generation unit, for example, develops an algorithm to estimate the user's emotion and generate an image corresponding to the emotion. For example, if the user has a positive emotion, it generates an image with bright colors. The image generation unit also uses technology to analyze the user's facial expressions and voice to estimate the emotion. For example, it captures the user's facial expression with a camera and estimates the emotion. The image generation unit also collects image data with emotion labels in advance and trains a machine learning model to improve the accuracy of image generation corresponding to the emotion. For example, it generates an image corresponding to the user's emotion in real time. This makes it possible to generate images corresponding to the user's emotion.

[0073] The image generation unit can customize images by incorporating elements from different cultures and regions based on user instructions. For example, the image generation unit develops algorithms to generate images incorporating elements from different cultures and regions. For example, it generates images incorporating traditional Japanese designs or American pop art styles. To incorporate cultural and regional elements, the image generation unit also uses technology to analyze the design elements and colors of each region. For example, it can reflect the traditional patterns and colors of a specific region in an image. To improve the accuracy of image generation that incorporates elements from different cultures and regions, the image generation unit also collects image data with cultural labels in advance and trains a machine learning model. For example, it can automatically incorporate cultural elements according to user specifications. This makes it possible to generate images that incorporate elements from different cultures and regions.

[0074] The image generation unit can animate the generated images and provide them as dynamic content. The image generation unit, for example, develops an algorithm for animating the generated images. For example, the image generation unit generates dynamic content by continuously changing still images. The image generation unit also uses a technique for breaking down each element of an image and adding movement to it for animation. For example, it simulates the movement of joints and muscles to smooth the character's movements. The image generation unit also collects image data with animation labels in advance and trains a machine learning model to improve the accuracy of generating dynamic content. For example, it automatically generates animations according to user instructions. This makes it possible to generate images as dynamic content.

[0075] The image generation unit can use the emotion estimation function to analyze the user's emotional response and generate an image according to the emotion. For example, the image generation unit develops an algorithm that analyzes the user's emotional response and generates an image according to the emotion. For example, if the user is relaxed, it generates a calm landscape image. The image generation unit also uses technology that analyzes the user's facial expressions and voice to estimate the emotion. For example, it analyzes the tone of the user's voice to estimate the emotion. Furthermore, the image generation unit collects image data with emotion labels in advance and trains a machine learning model to improve the accuracy of image generation according to the emotion. For example, it generates an image according to the user's emotion in real time. This makes it possible to generate images according to the user's emotional response.

[0076] The text analysis unit can deeply understand the context of text data and automatically link related information. For example, the text analysis unit analyzes text data and develops algorithms that deeply understand context. For example, it analyzes the context of a news article and automatically links related past articles and information. The text analysis unit also uses techniques for syntactic and semantic analysis of text data to understand the context. For example, it analyzes the structure and meaning of sentences and links related information. The text analysis unit also collects text data with link labels in advance and trains a machine learning model to improve the accuracy of links to related information. For example, it automatically suggests related information that the user may be interested in. This makes it possible to understand the context of the text and automatically link related information.

[0077] The text analysis unit can analyze the content of text data and extract potential themes and topics. For example, the text analysis unit analyzes text data and develops algorithms to extract potential themes and topics. For example, it extracts major themes and topics from long articles. The text analysis unit also uses techniques for semantic analysis and topic modeling of text data to extract themes and topics. For example, it analyzes the meaning of sentences and extracts related themes. The text analysis unit also collects text data with theme labels in advance and trains a machine learning model to improve the accuracy of theme and topic extraction. For example, it automatically extracts themes that are likely to interest users. This makes it possible to analyze the content of text and extract potential themes and topics.

[0078] The text analysis unit can use the emotion estimation function to analyze the emotional nuances of text data and generate summaries based on the emotions. For example, the text analysis unit analyzes text data and develops an algorithm to estimate emotional nuances. For example, it generates a bright-toned summary for text with positive emotions. To analyze emotional nuances, the text analysis unit also uses technology to analyze the emotion labels of text data. For example, it extracts keywords and phrases that express emotions and estimates the emotions. To improve the accuracy of summaries based on emotions, the text analysis unit also collects emotion-labeled text data in advance and trains a machine learning model. For example, it generates summaries based on emotions in real time. This enables summaries that reflect the emotional nuances of the text.

[0079] The text analysis unit can visualize the results of text analysis in different formats. For example, the text analysis unit develops algorithms to visualize the results of text analysis in graphs and charts. For example, the text analysis unit displays the sentiment analysis results of text data in a pie chart or bar graph. For visualization, the text analysis unit stores the text analysis results in a database and uses technology to display them in an appropriate format. For example, the text analysis unit displays the frequency of keyword appearances in a heat map. To improve the accuracy of visualization, the text analysis unit collects text data with visualization labels in advance and trains a machine learning model. For example, the text analysis unit displays the analysis results in a format that is easy for users to understand. This makes the results of text analysis easier to understand visually.

[0080] The text analysis unit can integrate the results of text analysis with other datasets to gain new insights. For example, the text analysis unit develops algorithms to integrate the results of text analysis with other datasets. For example, the text analysis unit integrates the results of news article analysis with social media data to analyze trends. The text analysis unit also uses technology to unify the formats of different datasets and link the analysis results for data integration. For example, it integrates text data and image data to analyze relevance. The text analysis unit also collects datasets with integrated labels in advance to train machine learning models to improve the accuracy of data integration. For example, it integrates information from different data sources to gain new insights. This allows the results of text analysis to be integrated with other datasets to gain new insights.

[0081] The text analysis unit can use the emotion estimation function to analyze the emotional tone of text data and provide analysis results according to the emotion. The text analysis unit, for example, analyzes text data and develops an algorithm to estimate the emotional tone. For example, it provides analysis results with a bright tone for text with a positive emotion. The text analysis unit also uses technology to analyze the emotion labels of text data to analyze the emotional tone. For example, it extracts keywords and phrases that express emotions and estimates the emotion. The text analysis unit also collects text data with emotion labels in advance and trains a machine learning model to improve the accuracy of the emotion-based analysis results. For example, it provides analysis results according to the emotion in real time. This makes it possible to provide analysis results that reflect the emotional tone of the text.

[0082] The system according to the embodiment is not limited to the above-described example, and various modifications are possible, for example, as follows.

[0083] The Media Conversion Hub can also analyze user behavior history to provide content optimized for individual users. For example, it can recommend new related content based on the content a user has previously viewed. To analyze user behavior history, it collects data such as viewing time and number of clicks and uses technology to train machine learning models. For example, if a user prefers content from a specific genre, it can prioritize recommendations for content related to that genre. It can also display advertisements optimized for individual users based on user behavior history. For example, it can display advertisements related to products purchased in the past. This makes it possible to provide personalized content based on a user's behavior history.

[0084] The speech conversion unit can also estimate the age and gender of the speaker of the speech data and incorporate this information into the text conversion. For example, it analyzes speech data and develops an algorithm to estimate age and gender based on the speaker's vocal characteristics. For example, it can distinguish between children's voices and adult voices and apply appropriate text styles to each. The speech conversion unit also uses technology to analyze features such as pitch, tempo, and tone of the speech data to estimate age and gender. For example, it can distinguish between male and female voices and apply appropriate text styles to each. To improve the accuracy of age and gender estimation, the speech conversion unit collects speech data labeled with age and gender in advance and trains a machine learning model. For example, it can pre-register the voices of speakers of a specific age group or gender and automatically identify them each time they speak. This improves readability by applying appropriate text styles according to the speaker's age and gender.

[0085] The speech conversion unit can use its emotion estimation function to estimate the emotion of a speaker from speech data and generate a text representation corresponding to that emotion. For example, it analyzes speech data and develops an algorithm to estimate emotion based on features such as the tone, pitch, and tempo of the speaker's voice. For example, if the speaker is angry, it generates a text representation that reflects that emotion. The speech conversion unit also uses technology to extract emotional features by performing waveform and spectral analysis of speech data for emotion estimation. For example, if the speaker's voice is excited, it generates a text representation that reflects a positive emotion. To improve the accuracy of emotion estimation, the speech conversion unit also collects speech data with emotion labels in advance and trains a machine learning model. For example, it estimates the emotion of the speaker's voice in real time and generates a text representation corresponding to that emotion. This makes it possible to generate a text representation that reflects the speaker's emotion.

[0086] The speech conversion unit can convert audio data into multiple languages ​​simultaneously and generate multilingual subtitles. For example, it analyzes audio data and develops algorithms for simultaneous conversion into multiple languages. For example, it converts English audio data into Japanese, French, Chinese, etc. in real time to generate multilingual subtitles. For multilingual conversion, the speech conversion unit pre-trains speech recognition models for each language and uses technology to select the appropriate model when analyzing the audio data. For example, it automatically identifies the language of the audio data and applies the corresponding language model. To improve the accuracy of multilingual subtitle generation, the speech conversion unit also develops technology to analyze the context of the audio data and perform appropriate translations. For example, it accurately translates technical terms and proper nouns and reflects them in multilingual subtitles. This enables multilingual support and can reach a wide range of viewers.

[0087] The speech conversion unit can summarize the content of audio data and output it as short text. For example, it develops an algorithm that analyzes audio data, extracts important information, and summarizes it. For example, it extracts key points from long conference recordings and outputs them as short text. The speech conversion unit also uses technology to analyze the context of audio data and extract important keywords and phrases for summarization. For example, it summarizes key news items from audio data of a news program. The speech conversion unit also collects audio data with summary labels in advance and trains a machine learning model to improve the accuracy of summaries. For example, it generates summaries of audio data in real time and outputs them as short text. This allows the main points of the audio data to be output as short text.

[0088] The speech conversion unit can use an emotion estimation function to analyze the emotional tone of speech data and perform text conversion according to the emotion. For example, an algorithm is developed to analyze speech data and estimate the emotional tone. For example, if the speaker's tone of voice is sad, text conversion is performed that reflects the emotion. To analyze the emotional tone, the speech conversion unit also uses technology to perform waveform and spectral analysis of speech data and extract emotional features. For example, if the speaker's voice is excited, text conversion is performed that reflects a positive emotion. To improve the accuracy of text conversion that reflects the emotional tone, the speech conversion unit collects speech data with emotion labels in advance and trains a machine learning model. For example, the speech conversion unit estimates the speaker's emotion in real time and performs text conversion according to the emotion. This enables text conversion that reflects the emotion of speech data.

[0089] The text conversion unit can understand the context of text data and generate speech with appropriate intonation and inflection. For example, it analyzes text data and develops an algorithm to understand the context. For example, it generates speech with appropriate intonation and inflection for questions and exclamations. The text conversion unit also uses techniques for syntactic and semantic analysis of text data to understand the context. For example, it analyzes the structure and meaning of sentences and generates appropriate speech expressions. The text conversion unit also collects text data with audio labels in advance and trains machine learning models to improve the accuracy of speech generation with intonation and inflection. For example, it generates speech expressions according to emotions and context in real time. This enables natural speech generation according to context.

[0090] The text conversion unit can use different speaker voices depending on the content of the text data. For example, it analyzes text data and develops an algorithm to select different speaker voices depending on the content. For example, it uses multiple speaker voices for dialogue-style text. The text conversion unit also uses technology to analyze the context and speaker information of the text data to select speakers. For example, it assigns different voices to each character. To improve the accuracy of using different speaker voices, the text conversion unit also collects text data with speaker labels in advance and trains a machine learning model. For example, it automatically selects speakers depending on the content of the text. This makes it possible to generate appropriate speaker voices according to the content of the text.

[0091] The text conversion unit can use the emotion estimation function to estimate the emotion of text data and generate a voice expression corresponding to the emotion. For example, it analyzes text data and develops an algorithm to estimate the emotion. For example, it generates a bright-toned voice for text with a positive emotion. The text conversion unit also uses technology to analyze the emotion labels of text data for emotion estimation. For example, it extracts keywords and phrases that express emotions and estimates the emotion. The text conversion unit also collects text data with emotion labels in advance and trains a machine learning model to improve the accuracy of the voice expression corresponding to the emotion. For example, it generates a voice expression corresponding to the emotion in real time. This makes it possible to generate a voice expression that reflects the emotion of the text.

[0092] The text conversion unit can translate text data into multiple languages ​​and generate speech in each language. For example, it analyzes text data and develops algorithms for translating into multiple languages. For example, it translates English text into Japanese, French, Chinese, etc., and generates speech in each language. For multilingual translation, the text conversion unit pre-trains translation models for each language and uses technology to select the appropriate model when analyzing text data. For example, it automatically identifies the language of the text and applies the corresponding translation model. To improve the accuracy of multilingual speech generation, the text conversion unit also collects multilingually labeled text data in advance and trains a machine learning model. For example, it accurately translates technical terms and proper nouns and reflects them in multilingual speech. This enables multilingual support and can reach a wide range of viewers.

[0093] The processing flow of the second embodiment will be briefly explained below.

[0094] Step 1: The speech conversion unit converts the speech data into text data. For example, the speech conversion unit analyzes the speech data using generative AI and outputs text data. The speech conversion unit can also convert speech data into text data in real time. For example, the speech of a news program can be converted into text in real time and displayed as subtitles. Step 2: The text conversion unit converts the text data converted by the speech conversion unit into speech data. For example, the text conversion unit uses generative AI to analyze the text data and output speech data. The text conversion unit can also read out news articles or educational materials aloud. For example, generative AI analyzes the text data and generates natural-sounding speech. Step 3: The image generator generates a customizable image based on the user's instructions. For example, the image generator uses generative AI to analyze prompts containing image generation instructions and output image data. The image generator can also generate charts and illustrations for use in educational materials. For example, the generative AI generates an image based on the prompts and customizes it to meet the user's needs. Step 4: The text analysis unit analyzes the text data. For example, the text analysis unit uses the generation AI to analyze the text data and output summaries and keywords. The text analysis unit can also deeply understand the content of the text and perform sentiment analysis. For example, the generation AI analyzes the text data and calculates a sentiment score.

[0095] 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.

[0096] 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.

[0097] 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.

[0098] [Second embodiment] FIG. 3 shows an example of the configuration of a data processing system 210 according to the second embodiment.

[0099] 3, the data processing system 210 includes a data processing device 12 and smart glasses 214. An example of the data processing device 12 is a server.

[0100] 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.

[0101] 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.

[0102] 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.

[0103] 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).

[0104] 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.

[0105] 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.

[0106] 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.

[0107] 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.

[0108] 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.

[0109] 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.

[0110] 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.

[0111] The data generation model 58 is a so-called generative AI. An example of the data generation model 58 is a generative AI such as ChatGPT. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 receives a prompt containing an instruction, as well as inference data such as voice data representing speech, text data representing text, and image data representing an image. The data generation model 58 performs inference on the input inference data in accordance with the instruction indicated by the prompt and outputs the inference result in a data format such as voice data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization. The identification processing unit 290 performs the above-mentioned identification processing using the data generation model 58. The data generation model 58 may be a fine-tuned model so as to output an inference result from a prompt that does not include an instruction. In this case, the data generation model 58 can output an inference result from a prompt that does not include an instruction. The data processing device 12 and the like include multiple types of data generation models 58, and the data generation model 58 includes AI other than the generative AI. The AI ​​other than the generative AI may be, for example, linear regression, logistic regression, decision tree, random forest, support vector machine (SVM), k-means clustering, convolutional neural network (CNN), recurrent neural network (RNN), generative adversarial network (GAN), or naive Bayes, and can perform various processes, but is not limited to these examples. The AI ​​may also be an AI agent. When the processes of each of the above-mentioned parts are performed by AI, the processes may be performed in part or entirely by AI, but are not limited to these examples. The processes performed by AI, including the generative AI, may be replaced with rule-based processes.

[0112] 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.

[0113] [Third embodiment] FIG. 5 shows an example of the configuration of a data processing system 310 according to the third embodiment.

[0114] 5, the data processing system 310 includes the data processing device 12 and a headset terminal 314. An example of the data processing device 12 is a server.

[0115] 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.

[0116] 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.

[0117] 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.

[0118] 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).

[0119] 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.

[0120] Fig. 6 shows an example of the main functions of the data processing device 12 and the headset terminal 314. As shown in Fig. 6, in the data processing device 12, a specific process is performed by the processor 28. A specific process program 56 is stored in the storage 32.

[0121] 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.

[0122] 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.

[0123] 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.

[0124] 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.

[0125] 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.

[0126] The data generation model 58 is a so-called generative AI. An example of the data generation model 58 is a generative AI such as ChatGPT. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 receives a prompt containing an instruction, as well as inference data such as voice data representing speech, text data representing text, and image data representing an image. The data generation model 58 performs inference on the input inference data in accordance with the instruction indicated by the prompt and outputs the inference result in a data format such as voice data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization. The identification processing unit 290 performs the above-mentioned identification processing using the data generation model 58. The data generation model 58 may be a fine-tuned model so as to output an inference result from a prompt that does not include an instruction. In this case, the data generation model 58 can output an inference result from a prompt that does not include an instruction. The data processing device 12 and the like include multiple types of data generation models 58, and the data generation model 58 includes AI other than the generative AI. The AI ​​other than the generative AI may be, for example, linear regression, logistic regression, decision tree, random forest, support vector machine (SVM), k-means clustering, convolutional neural network (CNN), recurrent neural network (RNN), generative adversarial network (GAN), or naive Bayes, and can perform various processes, but is not limited to these examples. The AI ​​may also be an AI agent. When the processes of each of the above-mentioned parts are performed by AI, the processes may be performed in part or entirely by AI, but are not limited to these examples. The processes performed by AI, including the generative AI, may be replaced with rule-based processes.

[0127] 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.

[0128] [Fourth embodiment] FIG. 7 shows an example of the configuration of a data processing system 410 according to the fourth embodiment.

[0129] 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.

[0130] 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.

[0131] 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.

[0132] 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.

[0133] 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).

[0134] 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.

[0135] 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.

[0136] 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.

[0137] 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.

[0138] 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.

[0139] In the robot 414, the specific processing is performed by the processor 46. A specific processing program 60 is stored in the storage 50. The processor 46 reads the specific processing program 60 from the storage 50 and executes the read specific processing program 60 on the RAM 48. The specific processing is realized by the processor 46 operating as the control unit 46A in accordance with the specific processing program 60 executed on the RAM 48. The robot 414 also has a data generation model and an emotion identification model similar to the data generation model 58 and the emotion identification model 59, and can perform processing similar to that of the specific processing unit 290 using these models.

[0140] 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.

[0141] 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.

[0142] The data generation model 58 is a so-called generative AI. An example of the data generation model 58 is a generative AI such as ChatGPT. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 receives a prompt containing an instruction, as well as inference data such as voice data representing speech, text data representing text, and image data representing an image. The data generation model 58 performs inference on the input inference data in accordance with the instruction indicated by the prompt and outputs the inference result in a data format such as voice data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization. The identification processing unit 290 performs the above-mentioned identification processing using the data generation model 58. The data generation model 58 may be a fine-tuned model so as to output an inference result from a prompt that does not include an instruction. In this case, the data generation model 58 can output an inference result from a prompt that does not include an instruction. The data processing device 12 and the like include multiple types of data generation models 58, and the data generation model 58 includes AI other than the generative AI. The AI ​​other than the generative AI may be, for example, linear regression, logistic regression, decision tree, random forest, support vector machine (SVM), k-means clustering, convolutional neural network (CNN), recurrent neural network (RNN), generative adversarial network (GAN), or naive Bayes, and can perform various processes, but is not limited to these examples. The AI ​​may also be an AI agent. When the processes of each of the above-mentioned parts are performed by AI, the processes may be performed in part or entirely by AI, but are not limited to these examples. The processes performed by AI, including the generative AI, may be replaced with rule-based processes.

[0143] 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.

[0144] 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.

[0145] 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.

[0146] 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.

[0147] 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).

[0148] 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.

[0149] 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."

[0150] 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.

[0151] 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.

[0152] 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.

[0153] 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.

[0154] 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.

[0155] 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.

[0156] 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.

[0157] 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.

[0158] 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.

[0159] 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.

[0160] The above-described description and illustrations are a detailed explanation of the parts related to the technology of the present disclosure and are merely an example of the technology of the present disclosure. For example, the above description of the configuration, functions, actions, and effects is an explanation of an example of the configuration, functions, actions, and effects of the parts related to the technology of the present disclosure. Therefore, it goes without saying that unnecessary parts may be deleted, new elements may be added, or replacements may be made to the above-described description and illustrations within the scope of the gist of the technology of the present disclosure. Furthermore, in order to avoid confusion and to facilitate understanding of the parts related to the technology of the present disclosure, the above-described description and illustrations omit explanations of common technical knowledge that do not require particular explanation to enable the implementation of the technology of the present disclosure.

[0161] 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]

[0162] 10, 210, 310, 410 Data Processing Systems 12 Data Processing Device 14 Smart Devices 214 Smart Glasses 314 Headset-type terminal 414 Robot

Claims

1. a voice conversion unit that converts voice data into text data; a text conversion unit that converts the text data converted by the speech conversion unit into speech data; an image generation unit that generates a customizable image based on a user's instruction; a text analysis unit that analyzes text data; A system characterized by:

2. The voice conversion unit Automatically removes background sounds and noise from the audio data to produce clear text conversion The system of claim 1 .

3. The voice conversion unit Identifying speakers of the audio data and applying different text styles to each speaker The system of claim 1 .

4. The voice conversion unit Estimating the emotion of the speaker of the voice data and generating a text expression according to the emotion The system of claim 1 .

5. The voice conversion unit The audio data is simultaneously converted into multiple languages ​​to generate multilingual subtitles. The system of claim 1 .

6. The voice conversion unit The contents of the audio data are summarized and output as a short text. The system of claim 1 .

Images