System

Abstract

An object of the system according to the embodiment is to make conversion of voice data into text, conversion of text data into voice, image generation, and information extraction and classification efficient in an integrated manner.SOLUTION: A system according to an embodiment includes a speech-to-text unit, a speech conversion unit, an image generation unit, and an information extraction unit. The speech-to-text transcriber converts the speech data into text data. The voice conversion unit converts the text data converted by the voice-to-text unit into voice data. The image generation unit generates an image based on the text data. The information extraction unit extracts and classifies information using an embedding technique.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] In conventional technologies, the conversion of voice data to text, the conversion of text data to voice, image generation, and information extraction and classification are carried out separately, and there is room for improvement in terms of integrating and streamlining the processes.

[0005] The system according to the embodiment aims to improve the efficiency of the conversion of voice data to text, the conversion of text data to voice, image generation, and information extraction and classification in an integrated manner. [Means for solving the problem]

[0006] The system according to the embodiment includes a speech-to-text unit, a speech conversion unit, an image generation unit, and an information extraction unit. The speech-to-text unit converts speech data into text data. The speech conversion unit converts the text data converted by the speech-to-text unit back into speech data. The image generation unit generates an image based on the text data. The information extraction unit extracts and classifies information using embedding technology. [Effects of the Invention]

[0007] The system according to the embodiment can comprehensively improve the efficiency of converting voice data to text, converting text data to voice, generating images, and extracting and classifying information. [Brief explanation of the drawings]

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

[0028] (Example 1) A media content production management system according to an embodiment of the present invention is a system that converts voice data to text data, converts text data to voice data, generates images based on text prompts, and extracts and classifies information using embedding technology, thereby enabling the efficient production and management of media content.

[0029] A media content generation management system according to an embodiment includes a speech-to-text unit, a speech conversion unit, an image generation unit, and an information extraction unit. The speech-to-text unit converts speech data into text data. For example, the speech-to-text unit converts speech data in WAV format into text data. The speech-to-text unit can also convert speech data in MP3 format into text data. The speech-to-text unit can also convert real-time speech into text data. For example, the speech-to-text unit converts lecture speech data into text in real time. The speech conversion unit converts the text data converted by the speech-to-text unit into speech data. For example, the speech conversion unit considers character encoding when converting text data into speech data. The speech conversion unit can also consider a format when converting text data into speech data. The speech conversion unit can also select a speech style according to a user's preference when converting text data into speech data. For example, the speech conversion unit selects a formal speech style. The image generation unit generates an image based on the text data. For example, the image generation unit generates an image based on a text prompt using the DALL-E API. The image generation unit may also consider the resolution of the generated image. The image generation unit may also consider the color and design elements of the generated image. For example, the image generation unit generates images suitable for teaching materials. The information extraction unit extracts and classifies information using embedding technology. For example, the information extraction unit may extract and classify information using Word2Vec. The information extraction unit may also extract and classify information using BERT. The information extraction unit may also perform sentiment analysis of text data and classify information based on sentiment. For example, the information extraction unit may preferentially extract information with a strong positive sentiment. This allows the media content generation and management system according to the embodiment to efficiently generate and manage media content. For example, educators can convert lecture content into text and distribute it to provide information to visually impaired people. Business professionals can provide reports as audio data to visually reinforce presentations.In the film industry, script analysis can improve the quality of character development and storytelling.

[0030] The speech-to-text conversion unit performs speaker identification of the speech data, and when there are multiple speakers, can distinguish and convert each utterance into text. The speech-to-text conversion unit, for example, analyzes speech data and performs speaker identification, and when there are multiple speakers, can distinguish and convert each utterance into text. For example, it analyzes recorded data of a meeting and distinguishes between the utterances of each participant. The speech-to-text conversion unit also uses speaker identification technology to extract characteristics of each speaker in the speech data and distinguish between utterances based on the characteristics. For example, it analyzes tone of voice and speaking patterns. The speech-to-text conversion unit also analyzes speech data containing multiple speakers and builds a system that automatically distinguishes and converts each speaker's utterance into text. For example, it analyzes recorded data of an interview and distinguishes between utterances of the questioner and the respondent. This allows utterances of multiple speakers to be distinguished and converted into text.

[0031] The speech-to-text unit can automatically remove background sounds and noise from the speech data to generate clear text data. The speech-to-text unit generates clear text data, for example, by analyzing speech data and using technology that automatically removes background sounds and noise. For example, noise in a conference room and external noise are removed. The speech-to-text unit also uses noise removal technology to improve the quality of the speech data. For example, white noise and echoes that occur during recording are removed. The speech-to-text unit also builds a system that analyzes background sounds and noise from speech data in real time to generate clear speech data. For example, it analyzes recorded data from a live event and removes noise. This allows for the generation of clear text data.

[0032] The speech-to-text unit converts audio data into text in real time, allowing the contents of live events and conferences to be recorded instantly. The speech-to-text unit, for example, builds a system that analyzes audio data in real time and converts it into text instantly. For example, the contents of live events and conferences are recorded in real time. The speech-to-text unit also uses real-time speech recognition technology to convert audio data into text instantly and record the contents of live events and conferences. For example, the contents of lectures and presentations are converted into text in real time. The speech-to-text unit also develops a system that converts audio data into text in real time and records it instantly. For example, the contents of online conferences are converted into text in real time and provided to participants. This allows the contents of live events and conferences to be recorded instantly.

[0033] The speech-to-text unit can automatically translate speech data into different languages ​​and generate multilingual text data. The speech-to-text unit, for example, analyzes speech data and builds a system for automatic translation into different languages. For example, English speech data is translated into Japanese and provided as text data. The speech-to-text unit also uses automatic translation technology to translate speech data into different languages ​​and generate multilingual text data. For example, speech data from an international conference is translated into multiple languages. The speech-to-text unit also develops a system for analyzing speech data in real time and automatically translating it into different languages. For example, speech data from a live event is translated in real time and provided as text data. This makes it possible to generate multilingual text data.

[0034] The voice conversion unit can automatically add appropriate background music and sound effects based on the content of the text data. The voice conversion unit, for example, analyzes text data and builds a system that automatically adds appropriate background music and sound effects based on the content. For example, music and sound effects are added that correspond to scenes in the story. The voice conversion unit also uses automatic music generation technology to generate background music and sound effects based on the content of the text data. For example, music that is suitable for tense scenes is added. The voice conversion unit also develops a system that analyzes the content of the text data in real time and automatically adds appropriate background music and sound effects. For example, music that is suitable for moving scenes is added. This makes it possible to automatically add appropriate background music and sound effects.

[0035] The speech conversion unit takes into account speaker information in the text data and can play back different voices for each speaker when there are multiple speakers. The speech conversion unit, for example, analyzes text data and builds a system that takes speaker information into account and plays back different voices for each speaker when there are multiple speakers. For example, conversational text is played back in different voices. The speech conversion unit also uses speaker identification technology to extract the characteristics of each speaker in the text data and plays back different voices based on that. For example, it uses male and female voices. The speech conversion unit also analyzes speaker information in text data in real time and develops a system that plays back different voices for each speaker when there are multiple speakers. For example, interview-style text is played back in different voices. This allows different voices to be played back for each speaker when there are multiple speakers.

[0036] The speech conversion unit can automatically translate text data into different languages ​​and generate multilingual audio data. The speech conversion unit, for example, analyzes text data and builds a system that automatically translates it into different languages. For example, it translates English text into Japanese and provides the resulting audio data. The speech conversion unit also uses automatic translation technology to translate text data into different languages ​​and generate multilingual audio data. For example, it translates text data from an international conference into multiple languages. The speech conversion unit also develops a system that analyzes text data in real time and automatically translates it into different languages. For example, it translates text data from a live event in real time and provides the resulting audio data. This allows multilingual audio data to be generated.

[0037] The speech conversion unit can enable a user to select a speech style (e.g., formal, casual) according to their preference when converting text data into speech. The speech conversion unit, for example, builds a system that allows a user to select a speech style according to their preference when converting text data into speech. For example, a formal tone or a casual tone is selected. The speech conversion unit also uses a speech style selection function to play back text data in a speech style according to the user's preference. For example, a business report is played back in a formal tone. The speech conversion unit also develops a system that allows a user to select a speech style according to their preference in real time when converting text data into speech. For example, the content of a presentation is played back in a casual tone. This allows a speech style according to the user's preference to be selected.

[0038] The image generation unit can generate multiple image styles (e.g., realistic, cartoon) based on the content of the text prompt and allow the user to select from them. For example, the image generation unit builds a system that analyzes the text prompt and generates multiple image styles based on the content. For example, it generates both a realistic style and a cartoon style. The image generation unit also uses image generation technology to generate multiple image styles based on the content of the text prompt and allow the user to select from them. For example, it provides an interface that allows the user to select their preferred style. The image generation unit also develops a system that analyzes the content of the text prompt in real time and generates multiple image styles. For example, it allows the user to switch between styles in real time. This generates multiple image styles and allows the user to select from them.

[0039] The image generation unit can automatically add related background images and scenes by taking into account background information of the text prompt. The image generation unit, for example, analyzes the text prompt and builds a system that automatically adds related background images and scenes by taking into account the background information. For example, a background image suitable for a story scene is added. The image generation unit also uses background information analysis technology to automatically add related background images and scenes based on the content of the text prompt. For example, natural landscapes and urban landscapes are added. The image generation unit also develops a system that analyzes background information of the text prompt in real time and automatically adds related background images and scenes. For example, an interface is provided that allows a user to select a background image. This allows related background images and scenes to be automatically added.

[0040] The image generation unit can automatically translate text prompts into different languages ​​and generate images that support multiple languages. The image generation unit, for example, analyzes text prompts and builds a system that automatically translates them into different languages. For example, it translates English prompts into Japanese and generates images. The image generation unit also uses automatic translation technology to translate text prompts into different languages ​​and generate images that support multiple languages. For example, it supports international teaching materials and presentations. The image generation unit also develops a system that analyzes text prompts in real time and automatically translates them into different languages. For example, it translates prompts from live events in real time and generates images. This allows for multilingual image generation.

[0041] The image generation unit can provide an interface that allows the generated image to be edited in real time, enabling the user to make instant corrections and adjustments. The image generation unit, for example, builds a system that provides an interface that allows the generated image to be edited in real time. For example, the user can instantly correct the color or design of the image. The image generation unit also uses a real-time editing function to allow the user to instantly correct and adjust the generated image. For example, by cutting out or adding part of the image. The image generation unit also develops an interface that allows the generated image to be edited in real time, providing a system that allows the user to instantly correct and adjust the image. For example, the image can be edited by drag and drop. This allows the generated image to be edited in real time.

[0042] The information extraction unit performs time series analysis of text data, tracks changes in information over time, and can identify trends. For example, the information extraction unit analyzes text data and performs time series analysis to build a system that tracks changes in information over time and identifies trends. For example, it analyzes data from the past few years and identifies trends. The information extraction unit also uses time series analysis technology to analyze changes in text data over time and identify trends. For example, it analyzes the frequency of appearance of specific keywords. The information extraction unit also analyzes the time series of text data in real time, tracks changes in information over time, and develops a system that identifies trends. For example, it identifies the latest trends in real time. This makes it possible to track changes in information over time and identify trends.

[0043] The information extraction unit can generate an interactive map that visualizes the relevance of text data and allows users to intuitively understand it. The information extraction unit, for example, builds a system that analyzes text data and generates an interactive map that visualizes the relevance. For example, related keywords and topics are displayed as nodes. The information extraction unit also uses visualization technology to display the relevance of the text data as an interactive map, allowing users to intuitively understand it. For example, links between nodes can be clicked to access detailed information. The information extraction unit also develops a system that analyzes the relevance of text data in real time and generates an interactive map. For example, it allows users to operate the map to search for related information. This visualizes the relevance of the text data and allows users to intuitively understand it.

[0044] The information extraction unit can integrate with different datasets to extract information to gain new insights. For example, the information extraction unit builds a system that analyzes text data and integrates it with different datasets to extract information to gain new insights. For example, patent data and market data are integrated and analyzed. The information extraction unit also uses data integration technology to integrate text data with different datasets to extract information to gain new insights. For example, academic paper data is integrated with corporate technical reports. The information extraction unit also develops a system that analyzes text data in real time and integrates it with different datasets. For example, market data and patent data collected in real time are integrated and analyzed. This makes it possible to integrate different datasets and extract information to gain new insights.

[0045] The information extraction unit can automatically translate text data into different languages ​​and perform multilingual information extraction and classification. For example, the information extraction unit analyzes text data and builds a system that automatically translates it into different languages. For example, it translates English text data into Japanese and performs information extraction and classification. The information extraction unit also uses automatic translation technology to translate text data into different languages ​​and perform multilingual information extraction and classification. For example, it analyzes international data sets. The information extraction unit also develops a system that analyzes text data in real time and automatically translates it into different languages. For example, it translates text data from a live event in real time and performs information extraction and classification. This enables multilingual information extraction and classification.

[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 content creation and management system can also analyze a user's browsing history and recommend content based on their interests. For example, it can analyze the genres and themes of content a user has previously viewed and recommend similar content. It can also provide content at the optimal time, taking into account the user's viewing time and frequency. It can also collect user feedback to improve the recommendation algorithm. For example, it can prioritize the recommendation of content that users have given high ratings.

[0048] The media content creation and management system can also obtain the user's location information and provide local content based on the location information. For example, if the user is in a specific area, it can provide news and event information related to that area. It can also use the user's location information to provide information on nearby stores and services. It can also analyze the user's movement history and recommend content related to places the user has visited in the past. For example, it can provide a travel guide based on photos the user has taken at their travel destination.

[0049] The media content generation management system can also obtain device information about the user and provide content optimized for that device. For example, if the user is using a smartphone, it can provide content optimized for mobile devices. Also, if the user is using a tablet, it can provide content suitable for large screens. It can also adjust the resolution and format of content according to the performance and settings of the user's device. For example, it can provide lightweight content to devices with low specifications.

[0050] The media content creation and management system can also analyze a user's social media activity and recommend content based on their interests. For example, it can recommend relevant content by analyzing the accounts a user follows and the content they post. It can also provide content at the optimal time, taking into account the user's social media engagement. It can also collect users' social media feedback to improve the recommendation algorithm. For example, it can recommend content based on the posts the user has "liked."

[0051] The media content creation and management system can also acquire a user's health data and provide content based on the user's health condition. For example, it can analyze the user's heart rate and sleep data to provide content that has a relaxing effect. It can also use the user's exercise data to provide fitness-related content. It can also adjust the display time and frequency of content based on the user's health data. For example, if the user is tired, it can provide content that can be enjoyed in a short amount of time.

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

[0053] Step 1: The speech-to-text unit converts the speech data into text data. For example, the speech-to-text unit can convert speech data in WAV or MP3 format into text data. It can also convert real-time speech into text data. For example, it can convert the speech data of a lecture into text in real time. Step 2: The speech conversion unit converts the text data converted by the speech-to-text unit into speech data. For example, the speech conversion unit can take into account character codes and formats when converting text data into speech data. It can also select a speech style according to the user's preferences. For example, a formal speech style can be selected. Step 3: The image generator generates an image based on the text data. For example, the image generator uses the DALL-E API to generate an image based on the text prompt. The image generator can also take into account the resolution, color, and design elements of the generated image. For example, it generates an image suitable for teaching materials. Step 4: The information extraction unit extracts and classifies information using embedding techniques. For example, the information extraction unit can extract and classify information using Word2Vec or BERT. It can also perform sentiment analysis of the text data and classify information based on sentiment. For example, it can preferentially extract information with a strong positive sentiment.

[0054] (Example 2) A media content production management system according to an embodiment of the present invention is a system that converts voice data to text data, converts text data to voice data, generates images based on text prompts, and extracts and classifies information using embedding technology, thereby enabling the efficient production and management of media content.

[0055] A media content generation management system according to an embodiment includes a speech-to-text unit, a speech conversion unit, an image generation unit, and an information extraction unit. The speech-to-text unit converts speech data into text data. For example, the speech-to-text unit converts speech data in WAV format into text data. The speech-to-text unit can also convert speech data in MP3 format into text data. The speech-to-text unit can also convert real-time speech into text data. For example, the speech-to-text unit converts lecture speech data into text in real time. The speech conversion unit converts the text data converted by the speech-to-text unit into speech data. For example, the speech conversion unit considers character encoding when converting text data into speech data. The speech conversion unit can also consider a format when converting text data into speech data. The speech conversion unit can also select a speech style according to a user's preference when converting text data into speech data. For example, the speech conversion unit selects a formal speech style. The image generation unit generates an image based on the text data. For example, the image generation unit generates an image based on a text prompt using the DALL-E API. The image generation unit may also consider the resolution of the generated image. The image generation unit may also consider the color and design elements of the generated image. For example, the image generation unit generates images suitable for teaching materials. The information extraction unit extracts and classifies information using embedding technology. For example, the information extraction unit may extract and classify information using Word2Vec. The information extraction unit may also extract and classify information using BERT. The information extraction unit may also perform sentiment analysis of text data and classify information based on sentiment. For example, the information extraction unit may preferentially extract information with a strong positive sentiment. This allows the media content generation and management system according to the embodiment to efficiently generate and manage media content. For example, educators can convert lecture content into text and distribute it to provide information to visually impaired people. Business professionals can provide reports as audio data to visually reinforce presentations.In the film industry, script analysis can improve the quality of character development and storytelling.

[0056] The speech-to-text unit can perform emotion analysis of the speech data and tag the intensity and type of emotion in the converted text. The speech-to-text unit, for example, analyzes the speech data and performs emotion analysis to identify the intensity and type of the speaker's emotion. For example, emotions such as joy, sadness, and anger are quantified and tagged in the converted text. The speech-to-text unit also performs emotion analysis of the speech data and tracks changes in emotion over time. For example, if a speaker's emotion changes mid-speech, the change is reflected in the text. The speech-to-text unit also uses emotion analysis to reflect the emotional nuances of the speech data in the text. For example, it identifies emphasized parts and parts with heightened emotions and tags them in the text. This allows the intensity and type of emotion to be reflected in the converted text.

[0057] The speech-to-text conversion unit performs speaker identification of the speech data, and when there are multiple speakers, can distinguish and convert each utterance into text. The speech-to-text conversion unit, for example, analyzes speech data and performs speaker identification, and when there are multiple speakers, can distinguish and convert each utterance into text. For example, it analyzes recorded data of a meeting and distinguishes between the utterances of each participant. The speech-to-text conversion unit also uses speaker identification technology to extract characteristics of each speaker in the speech data and distinguish between utterances based on the characteristics. For example, it analyzes tone of voice and speaking patterns. The speech-to-text conversion unit also analyzes speech data containing multiple speakers and builds a system that automatically distinguishes and converts each speaker's utterance into text. For example, it analyzes recorded data of an interview and distinguishes between utterances of the questioner and the respondent. This allows utterances of multiple speakers to be distinguished and converted into text.

[0058] The speech-to-text unit can automatically remove background sounds and noise from the speech data to generate clear text data. The speech-to-text unit generates clear text data, for example, by analyzing speech data and using technology that automatically removes background sounds and noise. For example, noise in a conference room and external noise are removed. The speech-to-text unit also uses noise removal technology to improve the quality of the speech data. For example, white noise and echoes that occur during recording are removed. The speech-to-text unit also builds a system that analyzes background sounds and noise from speech data in real time to generate clear speech data. For example, it analyzes recorded data from a live event and removes noise. This allows for the generation of clear text data.

[0059] The speech-to-text unit converts audio data into text in real time, allowing the contents of live events and conferences to be recorded instantly. The speech-to-text unit, for example, builds a system that analyzes audio data in real time and converts it into text instantly. For example, the contents of live events and conferences are recorded in real time. The speech-to-text unit also uses real-time speech recognition technology to convert audio data into text instantly and record the contents of live events and conferences. For example, the contents of lectures and presentations are converted into text in real time. The speech-to-text unit also develops a system that converts audio data into text in real time and records it instantly. For example, the contents of online conferences are converted into text in real time and provided to participants. This allows the contents of live events and conferences to be recorded instantly.

[0060] The speech-to-text unit can automatically translate speech data into different languages ​​and generate multilingual text data. The speech-to-text unit, for example, analyzes speech data and builds a system for automatic translation into different languages. For example, English speech data is translated into Japanese and provided as text data. The speech-to-text unit also uses automatic translation technology to translate speech data into different languages ​​and generate multilingual text data. For example, speech data from an international conference is translated into multiple languages. The speech-to-text unit also develops a system for analyzing speech data in real time and automatically translating it into different languages. For example, speech data from a live event is translated in real time and provided as text data. This makes it possible to generate multilingual text data.

[0061] The speech-to-text conversion unit can use the emotion estimation function to analyze the emotion of the speech data in real time and convert the speech data into text according to the emotion. For example, the speech-to-text conversion unit uses the emotion estimation function to build a system that analyzes the emotion of the speech data in real time and converts the speech data into text according to the emotion. For example, parts where the speaker's emotion is heightened are emphasized when converted into text. The speech-to-text conversion unit also analyzes the emotion of the speech data in real time and converts the speech data into text according to the emotion. For example, the font or color of the text is changed depending on the intensity of the emotion. The speech-to-text conversion unit also uses the emotion estimation function to develop a system that analyzes the emotion of the speech data in real time and converts the speech data into text according to the emotion. For example, changes in emotion are reflected in the text. This allows for text conversion according to the emotion in real time.

[0062] The speech conversion unit performs emotional analysis of the text data and can automatically adjust the tone and intonation of the voice according to the emotion. The speech conversion unit, for example, analyzes the text data and performs emotional analysis to build a system that automatically adjusts the tone and intonation of the voice according to the emotion. For example, parts with a strong emotion of joy are reproduced in a brighter tone. The speech conversion unit also uses emotion analysis technology to analyze the emotion of the text data and adjusts the tone and intonation of the voice according to the emotion. For example, parts with a strong emotion of sadness are reproduced in a calmer tone. The speech conversion unit also analyzes the emotion of the text data in real time to develop a system that automatically adjusts the tone and intonation of the voice according to the emotion. For example, parts with a strong emotion of anger are reproduced with emphasis. This makes it possible to automatically adjust the tone and intonation of the voice according to the emotion.

[0063] The voice conversion unit can automatically add appropriate background music and sound effects based on the content of the text data. The voice conversion unit, for example, analyzes text data and builds a system that automatically adds appropriate background music and sound effects based on the content. For example, music and sound effects are added that correspond to scenes in the story. The voice conversion unit also uses automatic music generation technology to generate background music and sound effects based on the content of the text data. For example, music that is suitable for tense scenes is added. The voice conversion unit also develops a system that analyzes the content of the text data in real time and automatically adds appropriate background music and sound effects. For example, music that is suitable for moving scenes is added. This makes it possible to automatically add appropriate background music and sound effects.

[0064] The speech conversion unit takes into account speaker information in the text data and can play back different voices for each speaker when there are multiple speakers. The speech conversion unit, for example, analyzes text data and builds a system that takes speaker information into account and plays back different voices for each speaker when there are multiple speakers. For example, conversational text is played back in different voices. The speech conversion unit also uses speaker identification technology to extract the characteristics of each speaker in the text data and plays back different voices based on that. For example, it uses male and female voices. The speech conversion unit also analyzes speaker information in text data in real time and develops a system that plays back different voices for each speaker when there are multiple speakers. For example, interview-style text is played back in different voices. This allows different voices to be played back for each speaker when there are multiple speakers.

[0065] The speech conversion unit can automatically translate text data into different languages ​​and generate multilingual audio data. The speech conversion unit, for example, analyzes text data and builds a system that automatically translates it into different languages. For example, it translates English text into Japanese and provides the resulting audio data. The speech conversion unit also uses automatic translation technology to translate text data into different languages ​​and generate multilingual audio data. For example, it translates text data from an international conference into multiple languages. The speech conversion unit also develops a system that analyzes text data in real time and automatically translates it into different languages. For example, it translates text data from a live event in real time and provides the resulting audio data. This allows multilingual audio data to be generated.

[0066] The speech conversion unit can enable a user to select a speech style (e.g., formal, casual) according to their preference when converting text data into speech. The speech conversion unit, for example, builds a system that allows a user to select a speech style according to their preference when converting text data into speech. For example, a formal tone or a casual tone is selected. The speech conversion unit also uses a speech style selection function to play back text data in a speech style according to the user's preference. For example, a business report is played back in a formal tone. The speech conversion unit also develops a system that allows a user to select a speech style according to their preference in real time when converting text data into speech. For example, the content of a presentation is played back in a casual tone. This allows a speech style according to the user's preference to be selected.

[0067] The voice conversion unit can use the emotion estimation function to analyze the emotion of the text data and play it back with an audio tone that corresponds to the emotion. For example, the voice conversion unit uses the emotion estimation function to build a system that analyzes the emotion of the text data and plays it back with an audio tone that corresponds to the emotion. For example, parts with a strong emotion of joy are played back with a brighter tone. The voice conversion unit also analyzes the emotion of the text data in real time and plays it back with an audio tone that corresponds to the emotion. For example, parts with a strong emotion of sadness are played back with a calmer tone. The voice conversion unit also uses the emotion estimation function to develop a system that analyzes the emotion of the text data in real time and plays it back with an audio tone that corresponds to the emotion. For example, parts with a strong emotion of anger are played back with emphasis. This makes it possible to play back with an audio tone that corresponds to the emotion.

[0068] The image generation unit can perform emotion analysis of the text prompt and automatically adjust colors and design elements according to the emotion. The image generation unit, for example, analyzes the text prompt and performs emotion analysis to build a system that automatically adjusts colors and design elements according to the emotion. For example, if the emotion of joy is strong, bright colors are used. The image generation unit also uses emotion analysis technology to analyze the emotion of the text prompt and adjusts colors and design elements according to the emotion. For example, if the emotion of sadness is strong, calm colors are used. The image generation unit also analyzes the emotion of the text prompt in real time to develop a system that automatically adjusts colors and design elements according to the emotion. For example, if the emotion of anger is strong, emphasized design elements are used. This makes it possible to automatically adjust colors and design elements according to the emotion.

[0069] The image generation unit can generate multiple image styles (e.g., realistic, cartoon) based on the content of the text prompt and allow the user to select from them. For example, the image generation unit builds a system that analyzes the text prompt and generates multiple image styles based on the content. For example, it generates both a realistic style and a cartoon style. The image generation unit also uses image generation technology to generate multiple image styles based on the content of the text prompt and allow the user to select from them. For example, it provides an interface that allows the user to select their preferred style. The image generation unit also develops a system that analyzes the content of the text prompt in real time and generates multiple image styles. For example, it allows the user to switch between styles in real time. This generates multiple image styles and allows the user to select from them.

[0070] The image generation unit can automatically add related background images and scenes by taking into account background information of the text prompt. The image generation unit, for example, analyzes the text prompt and builds a system that automatically adds related background images and scenes by taking into account the background information. For example, a background image suitable for a story scene is added. The image generation unit also uses background information analysis technology to automatically add related background images and scenes based on the content of the text prompt. For example, natural landscapes and urban landscapes are added. The image generation unit also develops a system that analyzes background information of the text prompt in real time and automatically adds related background images and scenes. For example, an interface is provided that allows a user to select a background image. This allows related background images and scenes to be automatically added.

[0071] The image generation unit can automatically translate text prompts into different languages ​​and generate images that support multiple languages. The image generation unit, for example, analyzes text prompts and builds a system that automatically translates them into different languages. For example, it translates English prompts into Japanese and generates images. The image generation unit also uses automatic translation technology to translate text prompts into different languages ​​and generate images that support multiple languages. For example, it supports international teaching materials and presentations. The image generation unit also develops a system that analyzes text prompts in real time and automatically translates them into different languages. For example, it translates prompts from live events in real time and generates images. This allows for multilingual image generation.

[0072] The image generation unit can provide an interface that allows the generated image to be edited in real time, enabling the user to make instant corrections and adjustments. The image generation unit, for example, builds a system that provides an interface that allows the generated image to be edited in real time. For example, the user can instantly correct the color or design of the image. The image generation unit also uses a real-time editing function to allow the user to instantly correct and adjust the generated image. For example, by cutting out or adding part of the image. The image generation unit also develops an interface that allows the generated image to be edited in real time, providing a system that allows the user to instantly correct and adjust the image. For example, the image can be edited by drag and drop. This allows the generated image to be edited in real time.

[0073] The image generation unit can use the emotion estimation function to analyze the emotion of the text prompt and generate an image style according to the emotion. For example, the image generation unit uses the emotion estimation function to analyze the emotion of the text prompt and build a system to generate an image style according to the emotion. For example, if the emotion of joy is strong, an image with bright colors is generated. The image generation unit also analyzes the emotion of the text prompt in real time and generates an image style according to the emotion. For example, if the emotion of sadness is strong, an image with calm colors is generated. The image generation unit also uses the emotion estimation function to develop a system to analyze the emotion of the text prompt in real time and generate an image style according to the emotion. For example, if the emotion of anger is strong, emphasized design elements are used. This makes it possible to generate an image style according to the emotion.

[0074] The information extraction unit performs sentiment analysis of the text data, classifies information based on the sentiment, and can preferentially extract information with high emotional value. For example, the information extraction unit analyzes the text data and performs sentiment analysis to classify information based on the sentiment and build a system that preferentially extracts information with high emotional value. For example, information with strong positive sentiment is preferentially extracted. The information extraction unit also uses sentiment analysis technology to analyze the sentiment of the text data and classify information based on the sentiment. For example, information with strong negative sentiment is classified into a separate category. The information extraction unit also analyzes the sentiment of the text data in real time, classifies information based on the sentiment, and develops a system that preferentially extracts information with high emotional value. For example, the priority of information is determined according to the intensity of the sentiment. This allows information with high emotional value to be preferentially extracted.

[0075] The information extraction unit performs time series analysis of text data, tracks changes in information over time, and can identify trends. For example, the information extraction unit analyzes text data and performs time series analysis to build a system that tracks changes in information over time and identifies trends. For example, it analyzes data from the past few years and identifies trends. The information extraction unit also uses time series analysis technology to analyze changes in text data over time and identify trends. For example, it analyzes the frequency of appearance of specific keywords. The information extraction unit also analyzes the time series of text data in real time, tracks changes in information over time, and develops a system that identifies trends. For example, it identifies the latest trends in real time. This makes it possible to track changes in information over time and identify trends.

[0076] The information extraction unit can generate an interactive map that visualizes the relevance of text data and allows users to intuitively understand it. The information extraction unit, for example, builds a system that analyzes text data and generates an interactive map that visualizes the relevance. For example, related keywords and topics are displayed as nodes. The information extraction unit also uses visualization technology to display the relevance of the text data as an interactive map, allowing users to intuitively understand it. For example, links between nodes can be clicked to access detailed information. The information extraction unit also develops a system that analyzes the relevance of text data in real time and generates an interactive map. For example, it allows users to operate the map to search for related information. This visualizes the relevance of the text data and allows users to intuitively understand it.

[0077] The information extraction unit can integrate with different datasets to extract information to gain new insights. For example, the information extraction unit builds a system that analyzes text data and integrates it with different datasets to extract information to gain new insights. For example, patent data and market data are integrated and analyzed. The information extraction unit also uses data integration technology to integrate text data with different datasets to extract information to gain new insights. For example, academic paper data is integrated with corporate technical reports. The information extraction unit also develops a system that analyzes text data in real time and integrates it with different datasets. For example, market data and patent data collected in real time are integrated and analyzed. This makes it possible to integrate different datasets and extract information to gain new insights.

[0078] The information extraction unit can automatically translate text data into different languages ​​and perform multilingual information extraction and classification. For example, the information extraction unit analyzes text data and builds a system that automatically translates it into different languages. For example, it translates English text data into Japanese and performs information extraction and classification. The information extraction unit also uses automatic translation technology to translate text data into different languages ​​and perform multilingual information extraction and classification. For example, it analyzes international data sets. The information extraction unit also develops a system that analyzes text data in real time and automatically translates it into different languages. For example, it translates text data from a live event in real time and performs information extraction and classification. This enables multilingual information extraction and classification.

[0079] The information extraction unit can use the emotion estimation function to analyze the emotions in the text data and extract and classify information based on the emotions. For example, the information extraction unit can use the emotion estimation function to analyze the emotions in the text data and build a system that extracts and classifies information based on emotions. For example, it can prioritize and extract information with a strong positive emotion. The information extraction unit can also analyze the emotions in the text data in real time and extract and classify information based on emotions. For example, it can classify information with a strong negative emotion into a separate category. The information extraction unit can also use the emotion estimation function to analyze the emotions in the text data in real time and develop a system that extracts and classifies information based on emotions. For example, it can determine the priority of information according to the intensity of the emotion. This allows information to be extracted and classified based on emotions.

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

[0081] The media content creation and management system can further estimate the user's emotions and adjust the display order of content based on the estimated emotions. For example, if the user is feeling stressed, it can prioritize displaying relaxing content. Alternatively, if the user is excited, it can display energetic content. Furthermore, it can change the color and design of content depending on the user's emotions. For example, if the user is sad, it can display content with calming colors.

[0082] The media content creation and management system can also analyze a user's browsing history and recommend content based on their interests. For example, it can analyze the genres and themes of content a user has previously viewed and recommend similar content. It can also provide content at the optimal time, taking into account the user's viewing time and frequency. It can also collect user feedback to improve the recommendation algorithm. For example, it can prioritize the recommendation of content that users have given high ratings.

[0083] The media content generation management system can further estimate the user's emotions and adjust the content of advertisements to be displayed based on the estimated emotions. For example, if the user is relaxed, an advertisement for a product with a relaxing effect can be displayed. Alternatively, if the user is excited, an advertisement for an energetic product can be displayed. Furthermore, the design and message of the advertisement can be changed depending on the user's emotions. For example, if the user is sad, an advertisement containing an encouraging message can be displayed.

[0084] The media content creation and management system can also obtain the user's location information and provide local content based on the location information. For example, if the user is in a specific area, it can provide news and event information related to that area. It can also use the user's location information to provide information on nearby stores and services. It can also analyze the user's movement history and recommend content related to places the user has visited in the past. For example, it can provide a travel guide based on photos the user has taken at their travel destination.

[0085] The media content creation and management system can further estimate a user's emotions and generate a music playlist based on the estimated emotions. For example, if a user wants to relax, relaxing music can be added to the playlist. Alternatively, if a user is feeling energetic, upbeat music can be added to the playlist. Furthermore, music genres and artists can be selected according to the user's emotions. For example, if a user is sad, soothing music can be added to the playlist.

[0086] The media content generation management system can also obtain device information about the user and provide content optimized for that device. For example, if the user is using a smartphone, it can provide content optimized for mobile devices. Also, if the user is using a tablet, it can provide content suitable for large screens. It can also adjust the resolution and format of content according to the performance and settings of the user's device. For example, it can provide lightweight content to devices with low specifications.

[0087] The media content generation and management system can further estimate the user's emotions and adjust the timing of notifications based on the estimated emotions. For example, if the user is concentrating, the system can refrain from sending notifications. Alternatively, if the user is relaxed, the system can send notifications. Furthermore, the system can change the content and format of notifications depending on the user's emotions. For example, if the user is feeling stressed, the system can send notifications that have a relaxing effect.

[0088] The media content creation and management system can also analyze a user's social media activity and recommend content based on their interests. For example, it can recommend relevant content by analyzing the accounts a user follows and the content they post. It can also provide content at the optimal time, taking into account the user's social media engagement. It can also collect users' social media feedback to improve the recommendation algorithm. For example, it can recommend content based on the posts the user has "liked."

[0089] The media content generation management system can further estimate the user's emotions and adjust the difficulty of the content based on the estimated emotions. For example, if the user is relaxed, more difficult content can be provided. Alternatively, if the user is stressed, less difficult content can be provided. Furthermore, the content progression speed and volume can be adjusted according to the user's emotions. For example, if the user is concentrating, the progression speed can be increased.

[0090] The media content creation and management system can also acquire a user's health data and provide content based on the user's health condition. For example, it can analyze the user's heart rate and sleep data to provide content that has a relaxing effect. It can also use the user's exercise data to provide fitness-related content. It can also adjust the display time and frequency of content based on the user's health data. For example, if the user is tired, it can provide content that can be enjoyed in a short amount of time.

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

[0092] Step 1: The speech-to-text unit converts the speech data into text data. For example, the speech-to-text unit can convert speech data in WAV or MP3 format into text data. It can also convert real-time speech into text data. For example, it can convert the speech data of a lecture into text in real time. Step 2: The speech conversion unit converts the text data converted by the speech-to-text unit into speech data. For example, the speech conversion unit can take into account character codes and formats when converting text data into speech data. It can also select a speech style according to the user's preferences. For example, a formal speech style can be selected. Step 3: The image generator generates an image based on the text data. For example, the image generator uses the DALL-E API to generate an image based on the text prompt. The image generator can also take into account the resolution, color, and design elements of the generated image. For example, it generates an image suitable for teaching materials. Step 4: The information extraction unit extracts and classifies information using embedding techniques. For example, the information extraction unit can extract and classify information using Word2Vec or BERT. It can also perform sentiment analysis of the text data and classify information based on sentiment. For example, it can preferentially extract information with a strong positive sentiment.

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

[0094] The data generation model 58 is a so-called generative AI (Artificial Intelligence). An example of the data generation model 58 is ChatGPT (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.

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

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

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

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

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

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

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

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

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

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

[0105] The storage 32 stores a data generation model 58 and an emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290. The identification processing unit 290 can estimate a user's emotion using the emotion identification model 59 and perform identification processing using the user's emotion. The emotion estimation function (emotion identification function) using the emotion identification model 59 performs various estimations and predictions regarding the user's emotion, including estimation and prediction of the user's emotion, but is not limited to these examples. Furthermore, the estimation and prediction of emotion also includes, for example, emotion analysis.

[0106] In the smart glasses 214, the specific processing is performed by the processor 46. A specific processing program 60 is stored in the storage 50. The processor 46 reads the specific processing program 60 from the storage 50 and executes the read specific processing program 60 on the RAM 48. The specific processing is realized by the processor 46 operating as the control unit 46A in accordance with the specific processing program 60 executed on the RAM 48. The smart glasses 214 also have a data generation model and an emotion identification model similar to the data generation model 58 and the emotion identification model 59, and can perform processing similar to that of the specific processing unit 290 using these models.

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

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

[0109] The data generation model 58 is a so-called generative AI. An example of the data generation model 58 is a generative AI such as ChatGPT. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 receives a prompt containing an instruction, as well as inference data such as voice data representing speech, text data representing text, and image data representing an image. The data generation model 58 performs inference on the input inference data in accordance with the instruction indicated by the prompt and outputs the inference result in a data format such as voice data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization. The identification processing unit 290 performs the above-mentioned identification processing using the data generation model 58. The data generation model 58 may be a fine-tuned model so as to output an inference result from a prompt that does not include an instruction. In this case, the data generation model 58 can output an inference result from a prompt that does not include an instruction. The data processing device 12 and the like include multiple types of data generation models 58, and the data generation model 58 includes 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.

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

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

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

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

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

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

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

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

[0118] Fig. 6 shows an example of the main functions of the data processing device 12 and the headset terminal 314. As shown in Fig. 6, in the data processing device 12, a specific process is performed by the processor 28. A specific process program 56 is stored in the storage 32.

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

[0120] The storage 32 stores a data generation model 58 and an emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290. The identification processing unit 290 can estimate a user's emotion using the emotion identification model 59 and perform identification processing using the user's emotion. The emotion estimation function (emotion identification function) using the emotion identification model 59 performs various estimations and predictions regarding the user's emotion, including estimation and prediction of the user's emotion, but is not limited to these examples. Furthermore, the estimation and prediction of emotion also includes, for example, emotion analysis.

[0121] In the headset type terminal 314, the specific processing is performed by the processor 46. A specific processing program 60 is stored in the storage 50. The processor 46 reads the specific processing program 60 from the storage 50 and executes the read specific processing program 60 on the RAM 48. The specific processing is realized by the processor 46 operating as the control unit 46A in accordance with the specific processing program 60 executed on the RAM 48. Note that the headset type terminal 314 has a data generation model and an emotion identification model similar to the data generation model 58 and the emotion identification model 59, and can also perform processing similar to that of the specific processing unit 290 using these models.

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

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

[0124] The data generation model 58 is a so-called generative AI. An example of the data generation model 58 is a generative AI such as ChatGPT. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 receives a prompt containing an instruction, as well as inference data such as voice data representing speech, text data representing text, and image data representing an image. The data generation model 58 performs inference on the input inference data in accordance with the instruction indicated by the prompt and outputs the inference result in a data format such as voice data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization. The identification processing unit 290 performs the above-mentioned identification processing using the data generation model 58. The data generation model 58 may be a fine-tuned model so as to output an inference result from a prompt that does not include an instruction. In this case, the data generation model 58 can output an inference result from a prompt that does not include an instruction. The data processing device 12 and the like include multiple types of data generation models 58, and the data generation model 58 includes 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.

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

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

[0127] 7, a data processing system 410 includes a data processing device 12 and a robot 414. An example of the data processing device 12 is a server.

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

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

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

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

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

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

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

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

[0136] The storage 32 stores a data generation model 58 and an emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290. The identification processing unit 290 can estimate a user's emotion using the emotion identification model 59 and perform identification processing using the user's emotion. The emotion estimation function (emotion identification function) using the emotion identification model 59 performs various estimations and predictions regarding the user's emotion, including estimation and prediction of the user's emotion, but is not limited to these examples. Furthermore, the estimation and prediction of emotion also includes, for example, emotion analysis.

[0137] In the robot 414, the specific processing is performed by the processor 46. A specific processing program 60 is stored in the storage 50. The processor 46 reads the specific processing program 60 from the storage 50 and executes the read specific processing program 60 on the RAM 48. The specific processing is realized by the processor 46 operating as the control unit 46A in accordance with the specific processing program 60 executed on the RAM 48. The robot 414 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.

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

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

[0140] The data generation model 58 is a so-called generative AI. An example of the data generation model 58 is a generative AI such as ChatGPT. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 receives a prompt containing an instruction, as well as inference data such as voice data representing speech, text data representing text, and image data representing an image. The data generation model 58 performs inference on the input inference data in accordance with the instruction indicated by the prompt and outputs the inference result in a data format such as voice data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization. The identification processing unit 290 performs the above-mentioned identification processing using the data generation model 58. The data generation model 58 may be a fine-tuned model so as to output an inference result from a prompt that does not include an instruction. In this case, the data generation model 58 can output an inference result from a prompt that does not include an instruction. The data processing device 12 and the like include multiple types of data generation models 58, and the data generation model 58 includes 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.

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

[0158] The above-described description and illustrations are a detailed explanation of the parts related to the technology of the present disclosure and are merely an example of the technology of the present disclosure. For example, the above description of the configuration, functions, actions, and effects is an explanation of an example of the configuration, functions, actions, and effects of the parts related to the technology of the present disclosure. Therefore, it goes without saying that unnecessary parts may be deleted, new elements may be added, or replacements may be made to the above-described description and illustrations within the scope of the gist of the technology of the present disclosure. Furthermore, in order to avoid confusion and to facilitate understanding of the parts related to the technology of the present disclosure, the above-described description and illustrations omit explanations of common technical knowledge that do not require particular explanation to enable the implementation of the technology of the present disclosure.

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

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

Claims

1. a speech-to-text unit that converts speech data into text data; a voice conversion unit that converts the text data converted by the voice-to-text unit into voice data; an image generation unit that generates an image based on the text data; An information extraction unit that extracts and classifies information using embedding technology. A system characterized by:

2. The speech-to-text unit Sentiment analysis of the audio data is performed, and the intensity and type of emotion are tagged into the textual content.

2. The system of claim 1.

3. The speech-to-text unit Speaker identification is performed on the audio data, and if there are multiple speakers, each statement is distinguished and converted into text.

2. The system of claim 1.

4. The speech-to-text unit Automatically remove background sounds and noise from the audio data to generate clear text data 2. The system of claim 1.

5. The speech-to-text unit Converts the audio data into text in real time to instantly record the contents of live events and meetings 2. The system of claim 1.

Images