System

Abstract

An object of a system according to an embodiment is to facilitate production of multimedia content through integrated processing of audio, text, and images.SOLUTION: A system according to an embodiment includes a speech-to-text transcriber, a speech re-transcriber, an image generator, and a text analyzer. The speech-to-text converter converts speech into text. The re-vocalization unit re-converts the text converted by the speech-to-text unit into speech. The image generation unit generates an image based on the voice converted by the voice re-output unit. The text analysis unit performs text embedding analysis based on the image generated by the image generation unit.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] With conventional technology, it has been difficult to process audio, text, and images in an integrated manner when producing multimedia content, making efficient production difficult.

[0005] The system according to the embodiment aims to facilitate the creation of multimedia content through integrated processing of audio, text, and images. [Means for solving the problem]

[0006] The system according to the embodiment includes a speech-to-text unit, a re-speech unit, an image generation unit, and a text analysis unit. The speech-to-text unit converts speech into text. The re-speech unit converts the text converted by the speech-to-text unit back into speech. The image generation unit generates an image based on the speech converted by the re-speech unit. The text analysis unit performs embedding analysis of the text based on the image generated by the image generation unit. [Effects of the Invention]

[0007] Systems according to embodiments can facilitate the creation of multimedia content through integrated processing of audio, text, and images. [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) The integrated platform according to an embodiment of the present invention is a system that converts speech to text, converts it back to speech, and combines image generation with text embedding analysis, making it suitable for a wide range of applications, including filmmaking, educational material creation, and digital marketing content development.

[0029] The integrated platform according to the embodiment includes a speech-to-text unit, a re-speech unit, an image generation unit, and a text analysis unit. The speech-to-text unit converts speech to text. For example, it converts speech to text using a speech recognition algorithm. The speech-to-text unit can also convert speech to text by specifying software to be used. The speech-to-text unit can also analyze the tone and pitch of the speech and reflect this in the text. The re-speech unit converts the text converted by the speech-to-text unit back into speech. For example, it converts text to speech using speech synthesis technology. The re-speech unit can also convert text to speech by specifying software to be used. The re-speech unit can also analyze the emotion of the text and reflect this in the speech. The image generation unit generates an image based on the speech converted by the re-speech unit. For example, it generates an image based on the speech using a generation algorithm. The image generation unit can also generate an image by specifying software to be used. The image generation unit can also analyze the content of the speech and generate an appropriate visual. The text analysis unit performs embedding analysis of the text based on the image generated by the image generation unit. For example, a model to be used can be specified to perform text embedding analysis. The text analysis unit can also specify an analysis method to perform text embedding analysis. The text analysis unit can also analyze the content of an image and reflect the results in the text embedding analysis. This allows the integrated platform according to the embodiment to perform voice-to-text conversion, re-voice conversion, image generation, and text analysis in an integrated manner. For example, in film production, dialogue editing, subtitle generation, and visual suggestions appropriate for a scene can be quickly performed. In the creation of educational materials, easy-to-understand expressions and structures can be suggested, and in the development of digital marketing content, customizable visual content can be instantly provided.

[0030] The speech-to-text unit can automatically remove background noise from speech and generate clear speech data. The speech-to-text unit, for example, analyzes speech data and uses an algorithm that automatically detects background noise. For example, noise reduction technology is used to remove noise components from speech signals. The speech-to-text unit then converts the noise-removed speech data into text and generates clear text data. For example, high-precision speech recognition is performed based on speech data with little noise. The speech-to-text unit also generates speech using the clear speech data from which noise has been removed during re-speech. For example, natural speech is reproduced based on speech data with little noise. This allows background noise to be removed and clear speech data to be generated.

[0031] The speech-to-text unit adds a speaker identification function to the speech, enabling it to convert speech from multiple speakers into text and re-speech individually. The speech-to-text unit, for example, analyzes speech data and identifies multiple speakers using a speaker identification algorithm. For example, it identifies speakers based on speech features. The speech-to-text unit also converts speech from multiple speakers into text individually and generates different text data for each speaker. For example, it converts the speech of speaker A and speaker B into separate text data. The speech-to-text unit also reproduces different speech tones for each speaker when re-speech is performed. For example, speaker A's speech is reproduced in a low tone and speaker B's speech in a high tone. This allows the speech from multiple speakers to be converted into text and re-speech individually.

[0032] The re-audio unit can combine audio data with music and sound effects to generate richer multimedia content. The re-audio unit, for example, analyzes audio data and uses an algorithm to automatically select appropriate music and sound effects. For example, it selects music and sound effects according to emotions. The re-audio unit then combines the audio data with the selected music and sound effects to generate multimedia content. For example, it adds music to the background of the audio. The re-audio unit then re-audio-izes the combined multimedia content and provides it to the user. For example, it generates content in which audio and music are in harmony. This allows audio data to be combined with music and sound effects to generate richer multimedia content.

[0033] The re-speech unit can convert speech to text and re-speech to accommodate different accents and dialects. The re-speech unit, for example, analyzes speech data and uses an algorithm to identify different accents and dialects. For example, it identifies accents and dialects based on regional speech characteristics. The re-speech unit also reflects the identified accents and dialects when converting speech to text. For example, it converts speech in Kansai dialect into text in Kansai dialect. The re-speech unit also generates speech that reproduces the accent or dialect when re-speech is performed. For example, it reproduces text in Kansai dialect as speech in Kansai dialect. This makes it possible to convert speech to text and re-speech to accommodate different accents and dialects.

[0034] The text analysis unit can evaluate the readability of text data and make improvement suggestions. The text analysis unit, for example, analyzes text data and uses an algorithm to evaluate readability. For example, it evaluates readability based on the length and structure of sentences and the difficulty of vocabulary. The text analysis unit also automatically generates improvement suggestions based on the readability evaluation results. For example, it makes suggestions to shorten long sentences or change difficult vocabulary to simpler vocabulary. The text analysis unit also generates readability improvement suggestions in real time and provides them to the user. For example, it immediately provides specific correction points to improve readability. This makes it possible to evaluate the readability of text data and make improvement suggestions.

[0035] The text analysis unit can automatically summarize the content of text data and make improvement suggestions based on the summary. The text analysis unit, for example, analyzes text data and automatically summarizes the content using a summarization algorithm. For example, it extracts important points and keywords to generate a summary. The text analysis unit also automatically generates improvement suggestions for the content based on the summary results. For example, it makes suggestions to delete redundant parts or highlight important information based on the summary. The text analysis unit also generates improvement suggestions based on the summary in real time and provides them to the user. For example, it immediately provides specific correction points based on the summary results. This makes it possible to summarize the content of text data and make improvement suggestions based on the summary.

[0036] The text analysis unit can visualize the analysis results of the text data and display them in graphs and charts. The text analysis unit, for example, uses an algorithm to visualize the analysis results of the text data. For example, it displays the emotion analysis results in graphs and charts. The text analysis unit also provides the visualized analysis results to the user to enable intuitive understanding. For example, it displays emotional fluctuations in a line graph. The text analysis unit also visualizes the analysis results in real time and provides them to the user. For example, it displays emotional fluctuations in the text data in real time. In this way, the analysis results of the text data are visualized to enable intuitive understanding.

[0037] The text analysis unit can translate the analysis results of the text data into different languages ​​and make multilingual improvement suggestions. The text analysis unit, for example, uses an algorithm that automatically translates the analysis results of the text data into different languages. For example, it translates English analysis results into Japanese or French. The text analysis unit also makes multilingual improvement suggestions based on the translated analysis results. For example, it provides improvement suggestions for expressions and structures in different languages. The text analysis unit also generates multilingual improvement suggestions in real time and provides them to the user. For example, it immediately provides specific correction points based on the translated analysis results. This makes it possible to provide the analysis results of the text data in multiple languages ​​and make improvement suggestions.

[0038] The image generation unit can analyze the storytelling elements of the scenario and make suggestions to improve the story structure. The image generation unit, for example, analyzes the scenario text and uses an algorithm to identify storytelling elements. For example, it analyzes the plot development and character relationships. The image generation unit also makes suggestions to improve the story structure based on the analysis results of the storytelling elements. For example, it makes suggestions to make the plot development smoother. The image generation unit also generates suggestions to improve the story structure in real time and provides them to the user. For example, it immediately provides specific points to be corrected based on the analysis results of the storytelling elements. This makes it possible to analyze the storytelling elements of the scenario and make suggestions to improve the story structure.

[0039] The image generation unit can analyze characters in a scenario and propose visuals and ideas that are suitable for the characters. The image generation unit, for example, analyzes the scenario text and identifies the characteristics of the characters using a character analysis algorithm. For example, it analyzes the character's personality and role. The image generation unit also proposes visuals and ideas that are suitable for the characters based on the results of the character analysis. For example, it proposes a visual design that matches the character's personality. The image generation unit also generates visuals and ideas that are suitable for the characters in real time and provides them to the user. For example, it instantly generates visuals that match the character's characteristics. This makes it possible to propose visuals and ideas that are suitable for the characters based on the character analysis of the scenario.

[0040] The image generation unit can convert the scenario text into a different media format and make visual proposals. The image generation unit, for example, uses an algorithm to convert the scenario text into a different media format. For example, it converts the scenario into a manga format or a novel format. The image generation unit also makes visual proposals based on the scenario converted into a different media format. For example, it proposes a visual design suitable for a manga-format scenario. The image generation unit also generates the scenario converted into a different media format and visual proposals in real time and provides them to the user. For example, it instantly generates visuals based on a manga-format scenario. This allows the scenario text to be converted into a different media format and make visual proposals.

[0041] The image generation unit can implement a visual proposal for a scenario as a prototype and improve it based on feedback. The image generation unit, for example, uses an algorithm to implement a visual proposal for a scenario as a prototype. For example, it generates a visual design based on the scenario as a prototype. The image generation unit also collects user feedback on the visual proposal for the prototype and makes improvements. For example, it adjusts the visual design based on user opinions. The image generation unit also generates an improved visual proposal based on the feedback in real time and provides it to the user. For example, it instantly generates a visual that reflects user feedback. This allows the visual proposal for a scenario to be implemented as a prototype and improved based on feedback.

[0042] The system according to the embodiment is not limited to the above-described example, and various modifications are possible, for example, as follows.

[0043] The speech-to-text unit can automatically remove background noise from speech and generate clear speech data. For example, it uses an algorithm that analyzes speech data and automatically detects background noise. It can also use noise reduction technology to remove noise components from speech signals. The speech-to-text unit can also convert the noise-removed speech data into text and generate clear text data. High-precision speech recognition can be performed based on speech data with little noise. The speech-to-text unit can also generate speech using clear speech data from which noise has been removed during re-speech. It can reproduce natural speech based on speech data with little noise. This allows background noise to be removed and clear speech data to be generated.

[0044] The re-audio unit can combine audio data with music and sound effects to generate richer multimedia content. For example, it uses an algorithm that analyzes audio data and automatically selects appropriate music and sound effects. It can also select music and sound effects according to emotions. The re-audio unit can also combine audio data with the selected music and sound effects to generate multimedia content. It can also add music to the background of the audio. The re-audio unit can also re-audio the combined multimedia content and provide it to the user. Content in which audio and music are in harmony can be generated. This makes it possible to generate rich multimedia content by combining audio data with music and sound effects.

[0045] The re-speech unit can convert speech to text and re-speech to accommodate different accents and dialects. For example, it can use an algorithm that analyzes speech data and identifies different accents and dialects. It can also identify accents and dialects based on regional speech characteristics. The re-speech unit can also reflect the identified accents and dialects when converting speech to text. It can also convert Kansai dialect speech to Kansai dialect text. The re-speech unit can also generate speech that reproduces the accent or dialect when re-speech, and it can also reproduce Kansai dialect text as Kansai dialect speech. This makes it possible to convert speech to text and re-speech to accommodate different accents and dialects.

[0046] The text analysis unit can evaluate the readability of text data and make suggestions for improvement. For example, it uses an algorithm that analyzes text data and evaluates readability. It can also evaluate readability based on the length and structure of sentences and the difficulty of vocabulary. The text analysis unit can also automatically generate improvement suggestions based on the readability evaluation results. It can make suggestions to shorten long sentences or change difficult vocabulary to easier vocabulary. The text analysis unit can also generate readability improvement suggestions in real time and provide them to the user. It can also immediately provide specific corrections to improve readability. In this way, it is possible to evaluate the readability of text data and make improvement suggestions.

[0047] The text analysis unit can automatically summarize the content of text data and make improvement suggestions based on the summary. For example, it analyzes text data and automatically summarizes the content using a summarization algorithm. It can also extract important points and keywords to generate summaries. The text analysis unit can also automatically generate improvement suggestions for the content based on the summary results. It can also make suggestions to remove redundant parts and highlight important information based on the summary. The text analysis unit can also generate improvement suggestions based on the summary in real time and provide them to the user. It can also immediately provide specific points to be corrected based on the summary results. This makes it possible to summarize the content of text data and make improvement suggestions based on the summary.

[0048] The processing flow of the first embodiment will be briefly explained below.

[0049] Step 1: The speech-to-text unit converts speech to text. For example, it uses a speech recognition algorithm to convert speech to text. The speech-to-text unit can also specify the software to use to convert speech to text. It can also analyze the tone and pitch of the speech and reflect this in the text. Step 2: The re-speech unit converts the text converted by the speech-to-text unit back into speech. For example, it converts text into speech using speech synthesis technology. The re-speech unit can also specify software to use to convert text into speech. It can also analyze the sentiment of the text and reflect it in the speech. Step 3: The image generator generates an image based on the audio converted by the audio conversion unit. For example, it uses a generation algorithm to generate an image based on the audio. The image generator can also specify software to use to generate the image. It can also analyze the content of the audio and generate an appropriate visual. Step 4: The text analysis unit performs text embedding analysis based on the image generated by the image generation unit. For example, the text analysis unit performs text embedding analysis by specifying the model to be used. The text analysis unit can also perform text embedding analysis by specifying an analysis method. Furthermore, the content of the image can be analyzed and reflected in the text embedding analysis.

[0050] (Example 2) The integrated platform according to an embodiment of the present invention is a system that converts speech to text, converts it back to speech, and combines image generation with text embedding analysis, making it suitable for a wide range of applications, including filmmaking, educational material creation, and digital marketing content development.

[0051] The integrated platform according to the embodiment includes a speech-to-text unit, a re-speech unit, an image generation unit, and a text analysis unit. The speech-to-text unit converts speech to text. For example, it converts speech to text using a speech recognition algorithm. The speech-to-text unit can also convert speech to text by specifying software to be used. The speech-to-text unit can also analyze the tone and pitch of the speech and reflect this in the text. The re-speech unit converts the text converted by the speech-to-text unit back into speech. For example, it converts text to speech using speech synthesis technology. The re-speech unit can also convert text to speech by specifying software to be used. The re-speech unit can also analyze the emotion of the text and reflect this in the speech. The image generation unit generates an image based on the speech converted by the re-speech unit. For example, it generates an image based on the speech using a generation algorithm. The image generation unit can also generate an image by specifying software to be used. The image generation unit can also analyze the content of the speech and generate an appropriate visual. The text analysis unit performs embedding analysis of the text based on the image generated by the image generation unit. For example, a model to be used can be specified to perform text embedding analysis. The text analysis unit can also specify an analysis method to perform text embedding analysis. The text analysis unit can also analyze the content of an image and reflect the results in the text embedding analysis. This allows the integrated platform according to the embodiment to perform voice-to-text conversion, re-voice conversion, image generation, and text analysis in an integrated manner. For example, in film production, dialogue editing, subtitle generation, and visual suggestions appropriate for a scene can be quickly performed. In the creation of educational materials, easy-to-understand expressions and structures can be suggested, and in the development of digital marketing content, customizable visual content can be instantly provided.

[0052] The speech-to-text unit can estimate the emotion of the speech and perform text conversion according to the emotion. The speech-to-text unit, for example, analyzes speech data and estimates the user's emotion using an emotion engine. For example, it identifies the emotion based on the tone, pitch, speed, etc. of the speech and performs text conversion according to that emotion. The speech-to-text unit also reflects the emotion during text conversion based on the emotion estimation result. For example, if the emotion of anger is included, an emphasized expression is used. The speech-to-text unit also reproduces a speech tone according to the emotion during re-speech. For example, if the emotion of joy is included, speech is generated with a bright tone. This makes it possible to convert text according to the emotion of the speech.

[0053] The speech-to-text unit can automatically remove background noise from speech and generate clear speech data. The speech-to-text unit, for example, analyzes speech data and uses an algorithm that automatically detects background noise. For example, noise reduction technology is used to remove noise components from speech signals. The speech-to-text unit then converts the noise-removed speech data into text and generates clear text data. For example, high-precision speech recognition is performed based on speech data with little noise. The speech-to-text unit also generates speech using the clear speech data from which noise has been removed during re-speech. For example, natural speech is reproduced based on speech data with little noise. This allows background noise to be removed and clear speech data to be generated.

[0054] The speech-to-text unit adds a speaker identification function to the speech, enabling it to convert speech from multiple speakers into text and re-speech individually. The speech-to-text unit, for example, analyzes speech data and identifies multiple speakers using a speaker identification algorithm. For example, it identifies speakers based on speech features. The speech-to-text unit also converts speech from multiple speakers into text individually and generates different text data for each speaker. For example, it converts the speech of speaker A and speaker B into separate text data. The speech-to-text unit also reproduces different speech tones for each speaker when re-speech is performed. For example, speaker A's speech is reproduced in a low tone and speaker B's speech in a high tone. This allows the speech from multiple speakers to be converted into text and re-speech individually.

[0055] The re-audio unit can combine audio data with music and sound effects to generate richer multimedia content. The re-audio unit, for example, analyzes audio data and uses an algorithm to automatically select appropriate music and sound effects. For example, it selects music and sound effects according to emotions. The re-audio unit then combines the audio data with the selected music and sound effects to generate multimedia content. For example, it adds music to the background of the audio. The re-audio unit then re-audio-izes the combined multimedia content and provides it to the user. For example, it generates content in which audio and music are in harmony. This allows audio data to be combined with music and sound effects to generate richer multimedia content.

[0056] The re-speech unit can convert speech to text and re-speech to accommodate different accents and dialects. The re-speech unit, for example, analyzes speech data and uses an algorithm to identify different accents and dialects. For example, it identifies accents and dialects based on regional speech characteristics. The re-speech unit also reflects the identified accents and dialects when converting speech to text. For example, it converts speech in Kansai dialect into text in Kansai dialect. The re-speech unit also generates speech that reproduces the accent or dialect when re-speech is performed. For example, it reproduces text in Kansai dialect as speech in Kansai dialect. This makes it possible to convert speech to text and re-speech to accommodate different accents and dialects.

[0057] The re-voice unit can provide voice feedback according to the user's emotion using the emotion estimation function. The re-voice unit, for example, analyzes voice data and identifies the user's emotion using an emotion estimation algorithm. For example, the emotion is estimated based on the tone, pitch, speed, etc. of the voice. The re-voice unit also generates voice feedback according to the user's emotion based on the emotion estimation result. For example, encouraging voice feedback is provided for positive emotions. The re-voice unit also provides voice feedback in real time and responds according to the user's emotion. For example, comforting voice feedback is provided for negative emotions. This makes it possible to provide voice feedback according to the user's emotion.

[0058] The text analysis unit can perform sentiment analysis of text data and automatically generate improvement suggestions according to the sentiment. The text analysis unit, for example, analyzes text data and identifies sentiment using a sentiment analysis algorithm. For example, it estimates sentiment based on expressions and vocabulary in the text. The text analysis unit also automatically generates improvement suggestions according to the sentiment based on the sentiment analysis results. For example, if negative sentiment is included, it makes a suggestion to change the expression to a more positive one. The text analysis unit also generates improvement suggestions according to the sentiment in real time and provides them to the user. For example, it immediately provides improvement suggestions based on expressions and structure according to the sentiment. This makes it possible to automatically generate improvement suggestions based on sentiment analysis of text data.

[0059] The text analysis unit can evaluate the readability of text data and make improvement suggestions. The text analysis unit, for example, analyzes text data and uses an algorithm to evaluate readability. For example, it evaluates readability based on the length and structure of sentences and the difficulty of vocabulary. The text analysis unit also automatically generates improvement suggestions based on the readability evaluation results. For example, it makes suggestions to shorten long sentences or change difficult vocabulary to simpler vocabulary. The text analysis unit also generates readability improvement suggestions in real time and provides them to the user. For example, it immediately provides specific correction points to improve readability. This makes it possible to evaluate the readability of text data and make improvement suggestions.

[0060] The text analysis unit can automatically summarize the content of text data and make improvement suggestions based on the summary. The text analysis unit, for example, analyzes text data and automatically summarizes the content using a summarization algorithm. For example, it extracts important points and keywords to generate a summary. The text analysis unit also automatically generates improvement suggestions for the content based on the summary results. For example, it makes suggestions to delete redundant parts or highlight important information based on the summary. The text analysis unit also generates improvement suggestions based on the summary in real time and provides them to the user. For example, it immediately provides specific correction points based on the summary results. This makes it possible to summarize the content of text data and make improvement suggestions based on the summary.

[0061] The text analysis unit can visualize the analysis results of the text data and display them in graphs and charts. The text analysis unit, for example, uses an algorithm to visualize the analysis results of the text data. For example, it displays the emotion analysis results in graphs and charts. The text analysis unit also provides the visualized analysis results to the user to enable intuitive understanding. For example, it displays emotional fluctuations in a line graph. The text analysis unit also visualizes the analysis results in real time and provides them to the user. For example, it displays emotional fluctuations in the text data in real time. In this way, the analysis results of the text data are visualized to enable intuitive understanding.

[0062] The text analysis unit can translate the analysis results of the text data into different languages ​​and make multilingual improvement suggestions. The text analysis unit, for example, uses an algorithm that automatically translates the analysis results of the text data into different languages. For example, it translates English analysis results into Japanese or French. The text analysis unit also makes multilingual improvement suggestions based on the translated analysis results. For example, it provides improvement suggestions for expressions and structures in different languages. The text analysis unit also generates multilingual improvement suggestions in real time and provides them to the user. For example, it immediately provides specific correction points based on the translated analysis results. This makes it possible to provide the analysis results of the text data in multiple languages ​​and make improvement suggestions.

[0063] The text analysis unit can use the emotion estimation function to make suggestions for improving text according to the user's emotions. The text analysis unit, for example, analyzes text data and identifies the user's emotions using an emotion estimation algorithm. For example, it estimates emotions based on the expressions and vocabulary in the text. The text analysis unit also makes suggestions for improving text according to the user's emotions based on the emotion estimation results. For example, if negative emotions are included, it makes a suggestion to change the expression to a more positive one. The text analysis unit also generates suggestions for improving text according to the emotions in real time and provides them to the user. For example, it immediately provides suggestions for improving expressions and structure according to the emotions. This makes it possible to make suggestions for improving text according to the user's emotions.

[0064] The image generation unit can perform sentiment analysis of the scenario text and automatically generate visual suggestions corresponding to the sentiment. The image generation unit, for example, analyzes the scenario text and identifies the sentiment using a sentiment analysis algorithm. For example, the sentiment is estimated based on the expressions and vocabulary of the text. The image generation unit also automatically generates visual suggestions corresponding to the sentiment based on the sentiment analysis results. For example, for the sentiment of joy, visuals with bright colors and positive designs are proposed. The image generation unit also generates visual suggestions corresponding to the sentiment in real time and provides them to the user. For example, visuals with colors and designs corresponding to the sentiment are instantly generated. This makes it possible to automatically generate visual suggestions based on sentiment analysis of the scenario text.

[0065] The image generation unit can analyze the storytelling elements of the scenario and make suggestions to improve the story structure. The image generation unit, for example, analyzes the scenario text and uses an algorithm to identify storytelling elements. For example, it analyzes the plot development and character relationships. The image generation unit also makes suggestions to improve the story structure based on the analysis results of the storytelling elements. For example, it makes suggestions to make the plot development smoother. The image generation unit also generates suggestions to improve the story structure in real time and provides them to the user. For example, it immediately provides specific points to be corrected based on the analysis results of the storytelling elements. This makes it possible to analyze the storytelling elements of the scenario and make suggestions to improve the story structure.

[0066] The image generation unit can analyze characters in a scenario and propose visuals and ideas that are suitable for the characters. The image generation unit, for example, analyzes the scenario text and identifies the characteristics of the characters using a character analysis algorithm. For example, it analyzes the character's personality and role. The image generation unit also proposes visuals and ideas that are suitable for the characters based on the results of the character analysis. For example, it proposes a visual design that matches the character's personality. The image generation unit also generates visuals and ideas that are suitable for the characters in real time and provides them to the user. For example, it instantly generates visuals that match the character's characteristics. This makes it possible to propose visuals and ideas that are suitable for the characters based on the character analysis of the scenario.

[0067] The image generation unit can convert the scenario text into a different media format and make visual proposals. The image generation unit, for example, uses an algorithm to convert the scenario text into a different media format. For example, it converts the scenario into a manga format or a novel format. The image generation unit also makes visual proposals based on the scenario converted into a different media format. For example, it proposes a visual design suitable for a manga-format scenario. The image generation unit also generates the scenario converted into a different media format and visual proposals in real time and provides them to the user. For example, it instantly generates visuals based on a manga-format scenario. This allows the scenario text to be converted into a different media format and make visual proposals.

[0068] The image generation unit can implement a visual proposal for a scenario as a prototype and improve it based on feedback. The image generation unit, for example, uses an algorithm to implement a visual proposal for a scenario as a prototype. For example, it generates a visual design based on the scenario as a prototype. The image generation unit also collects user feedback on the visual proposal for the prototype and makes improvements. For example, it adjusts the visual design based on user opinions. The image generation unit also generates an improved visual proposal based on the feedback in real time and provides it to the user. For example, it instantly generates a visual that reflects user feedback. This allows the visual proposal for a scenario to be implemented as a prototype and improved based on feedback.

[0069] The image generation unit can use the emotion estimation function to make visual suggestions for a scenario that correspond to the user's emotions. The image generation unit, for example, analyzes the scenario text and identifies the user's emotions using an emotion estimation algorithm. For example, it estimates emotions based on the expressions and vocabulary of the scenario. The image generation unit also makes visual suggestions for a scenario that correspond to the user's emotions based on the emotion estimation results. For example, it suggests visuals with bright colors and designs for positive emotions. The image generation unit also generates visual suggestions for a scenario that correspond to emotions in real time and provides them to the user. For example, it instantly generates visuals with colors and designs that correspond to emotions. This makes it possible to make visual suggestions for a scenario that correspond to the user's emotions.

[0070] The system according to the embodiment is not limited to the above-described example, and various modifications are possible, for example, as follows.

[0071] The speech-to-text unit can automatically remove background noise from speech and generate clear speech data. For example, it uses an algorithm that analyzes speech data and automatically detects background noise. It can also use noise reduction technology to remove noise components from speech signals. The speech-to-text unit can also convert the noise-removed speech data into text and generate clear text data. High-precision speech recognition can be performed based on speech data with little noise. The speech-to-text unit can also generate speech using clear speech data from which noise has been removed during re-speech. It can reproduce natural speech based on speech data with little noise. This allows background noise to be removed and clear speech data to be generated.

[0072] The re-audio unit can combine audio data with music and sound effects to generate richer multimedia content. For example, it uses an algorithm that analyzes audio data and automatically selects appropriate music and sound effects. It can also select music and sound effects according to emotions. The re-audio unit can also combine audio data with the selected music and sound effects to generate multimedia content. It can also add music to the background of the audio. The re-audio unit can also re-audio the combined multimedia content and provide it to the user. Content in which audio and music are in harmony can be generated. This makes it possible to generate rich multimedia content by combining audio data with music and sound effects.

[0073] The re-speech unit can convert speech to text and re-speech to accommodate different accents and dialects. For example, it can use an algorithm that analyzes speech data and identifies different accents and dialects. It can also identify accents and dialects based on regional speech characteristics. The re-speech unit can also reflect the identified accents and dialects when converting speech to text. It can also convert Kansai dialect speech to Kansai dialect text. The re-speech unit can also generate speech that reproduces the accent or dialect when re-speech, and it can also reproduce Kansai dialect text as Kansai dialect speech. This makes it possible to convert speech to text and re-speech to accommodate different accents and dialects.

[0074] The text analysis unit can evaluate the readability of text data and make suggestions for improvement. For example, it uses an algorithm that analyzes text data and evaluates readability. It can also evaluate readability based on the length and structure of sentences and the difficulty of vocabulary. The text analysis unit can also automatically generate improvement suggestions based on the readability evaluation results. It can make suggestions to shorten long sentences or change difficult vocabulary to easier vocabulary. The text analysis unit can also generate readability improvement suggestions in real time and provide them to the user. It can also immediately provide specific corrections to improve readability. In this way, it is possible to evaluate the readability of text data and make improvement suggestions.

[0075] The text analysis unit can automatically summarize the content of text data and make improvement suggestions based on the summary. For example, it analyzes text data and automatically summarizes the content using a summarization algorithm. It can also extract important points and keywords to generate summaries. The text analysis unit can also automatically generate improvement suggestions for the content based on the summary results. It can also make suggestions to remove redundant parts and highlight important information based on the summary. The text analysis unit can also generate improvement suggestions based on the summary in real time and provide them to the user. It can also immediately provide specific points to be corrected based on the summary results. This makes it possible to summarize the content of text data and make improvement suggestions based on the summary.

[0076] The speech-to-text unit can estimate the emotion of the speech and perform text conversion according to the emotion. For example, it analyzes speech data and estimates the user's emotion using an emotion engine. It can also identify the emotion based on the tone, pitch, speed, etc. of the speech and perform text conversion according to that emotion. The speech-to-text unit can also reflect the emotion during text conversion based on the emotion estimation result. If the emotion of anger is included, it can use emphasized expressions. The speech-to-text unit can also reproduce a speech tone according to the emotion during re-speech. If the emotion of joy is included, it can generate speech with a bright tone. This makes it possible to convert text according to the emotion of the speech.

[0077] The re-voice unit can use the emotion estimation function to provide voice feedback according to the user's emotion. For example, the voice data can be analyzed and the user's emotion can be identified using an emotion estimation algorithm. The emotion can also be estimated based on the tone, pitch, speed, etc. of the voice. The re-voice unit can also generate voice feedback according to the user's emotion based on the emotion estimation result. Encouraging voice feedback can be provided for positive emotions. The re-voice unit can also provide voice feedback in real time and take action according to the user's emotion. Comforting voice feedback can be provided for negative emotions. In this way, voice feedback according to the user's emotion can be provided.

[0078] The text analysis unit can perform sentiment analysis of text data and automatically generate improvement suggestions based on the sentiment. For example, it analyzes text data and identifies sentiment using a sentiment analysis algorithm. It can also estimate sentiment based on the expressions and vocabulary in the text. The text analysis unit can also automatically generate improvement suggestions based on the sentiment based on the sentiment analysis results. If negative sentiment is included, it can make a suggestion to change the expression to a more positive one. The text analysis unit can also generate improvement suggestions based on the sentiment in real time and provide them to the user. It can also immediately provide improvement suggestions for expressions and structure based on the sentiment. This makes it possible to automatically generate improvement suggestions based on the sentiment analysis of text data.

[0079] The image generation unit can perform sentiment analysis of the scenario text and automatically generate visual suggestions according to the sentiment. For example, the scenario text is analyzed and sentiment is identified using a sentiment analysis algorithm. The sentiment can also be estimated based on the expressions and vocabulary in the text. The image generation unit can also automatically generate visual suggestions according to the sentiment based on the sentiment analysis results. For the sentiment of joy, visuals with bright colors and positive designs can be suggested. The image generation unit can also generate visual suggestions according to the sentiment in real time and provide them to the user. Visuals with colors and designs according to the sentiment can also be instantly generated. This makes it possible to automatically generate visual suggestions based on sentiment analysis of the scenario text.

[0080] The image generation unit can use the emotion estimation function to make visual suggestions for the scenario according to the user's emotions. For example, the scenario text can be analyzed and the user's emotions identified using an emotion estimation algorithm. Emotions can also be estimated based on the expressions and vocabulary of the scenario. The image generation unit can also make visual suggestions for the scenario according to the user's emotions based on the emotion estimation results. Visuals with bright colors and designs can be suggested for positive emotions. The image generation unit can also generate visual suggestions for the scenario according to emotions in real time and provide them to the user. Visuals with colors and designs according to emotions can also be generated instantly. This makes it possible to make visual suggestions for the scenario according to the user's emotions.

[0081] The processing flow of the second embodiment will be briefly explained below.

[0082] Step 1: The speech-to-text unit converts speech to text. For example, it uses a speech recognition algorithm to convert speech to text. The speech-to-text unit can also specify the software to use to convert speech to text. It can also analyze the tone and pitch of the speech and reflect this in the text. Step 2: The re-speech unit converts the text converted by the speech-to-text unit back into speech. For example, it converts text into speech using speech synthesis technology. The re-speech unit can also specify software to use to convert text into speech. It can also analyze the sentiment of the text and reflect it in the speech. Step 3: The image generator generates an image based on the audio converted by the audio conversion unit. For example, it uses a generation algorithm to generate an image based on the audio. The image generator can also specify software to use to generate the image. It can also analyze the content of the audio and generate an appropriate visual. Step 4: The text analysis unit performs text embedding analysis based on the image generated by the image generation unit. For example, the text analysis unit performs text embedding analysis by specifying the model to be used. The text analysis unit can also perform text embedding analysis by specifying an analysis method. Furthermore, the content of the image can be analyzed and reflected in the text embedding analysis.

[0083] 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.

[0084] 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.

[0085] 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.

[0086] [Second embodiment] FIG. 3 shows an example of the configuration of a data processing system 210 according to the second embodiment.

[0087] 3, the data processing system 210 includes the data processing device 12 and smart glasses 214. An example of the data processing device 12 is a server.

[0088] 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.

[0089] 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.

[0090] 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.

[0091] 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).

[0092] 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.

[0093] 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.

[0094] 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.

[0095] 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.

[0096] 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.

[0097] 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.

[0098] 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.

[0099] 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.

[0100] 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.

[0101] [Third embodiment] FIG. 5 shows an example of the configuration of a data processing system 310 according to the third embodiment.

[0102] 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.

[0103] 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.

[0104] 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.

[0105] 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.

[0106] 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).

[0107] 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.

[0108] Fig. 6 shows an example of the main functions of the data processing device 12 and the headset type terminal 314. As shown in Fig. 6, in the data processing device 12, a specific process is performed by the processor 28. A specific process program 56 is stored in the storage 32.

[0109] 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.

[0110] 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.

[0111] 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.

[0112] 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.

[0113] 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.

[0114] 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.

[0115] 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.

[0116] [Fourth embodiment] FIG. 7 shows an example of the configuration of a data processing system 410 according to the fourth embodiment.

[0117] 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.

[0118] 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.

[0119] 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.

[0120] 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.

[0121] 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).

[0122] 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.

[0123] 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.

[0124] 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.

[0125] 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.

[0126] 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.

[0127] 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.

[0128] 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.

[0129] 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.

[0130] 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.

[0131] 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.

[0132] 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.

[0133] 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.

[0134] 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.

[0135] 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).

[0136] 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 "reaction" domain, where sensation is dominant. The right half of the emotion map lists emotions belonging to the "situation" domain, where situational awareness is dominant.

[0137] 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."

[0138] 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.

[0139] 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.

[0140] 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.

[0141] 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.

[0142] 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.

[0143] 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.

[0144] 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.

[0145] 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.

[0146] 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.

[0147] 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.

[0148] The above-described description and illustrations are a detailed explanation of the parts related to the technology of the present disclosure and are merely an example of the technology of the present disclosure. For example, the above description of the configuration, functions, actions, and effects is an explanation of an example of the configuration, functions, actions, and effects of the parts related to the technology of the present disclosure. Therefore, it goes without saying that unnecessary parts may be deleted, new elements may be added, or replacements may be made to the above-described description and illustrations within the scope of the gist of the technology of the present disclosure. Furthermore, to avoid confusion and facilitate understanding of the parts related to the technology of the present disclosure, the above-described description and illustrations omit explanations of common technical knowledge that do not require particular explanation to enable the implementation of the technology of the present disclosure.

[0149] 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]

[0150] 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 into text; a re-speech conversion unit that converts the text converted by the speech-to-text conversion unit back into speech; an image generating unit that generates an image based on the audio converted by the re-audio converting unit; a text analysis unit that performs an embedding analysis of text based on the image generated by the image generation unit. A system characterized by:

2. The speech-to-text unit Estimate the emotion of the voice and convert it into text according to the emotion.

2. The system of claim 1.

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

4. The speech-to-text unit Add speaker identification to the audio, and convert and re-audio the audio of multiple speakers individually.

2. The system of claim 1.

5. The re-voice conversion unit Combining audio data with music and sound effects to create richer multimedia content 2. The system of claim 1.

Images