system

Abstract

The system according to this embodiment aims to enable multilingual communication while maintaining privacy using silent speech. [Solution] The system according to the embodiment comprises a collection unit, a generation unit, a translation unit, and a delivery unit. The collection unit reads the user's silent utterances. The generation unit converts the data read by the collection unit into text. The translation unit translates the text generated by the generation unit. The delivery unit converts the text translated by the translation unit into audio data and delivers it to the conversation partner.

Description

Technical Field

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

Background Art

[0002] Patent Document 1 discloses a method for controlling a persona chatbot, which is performed by at least one processor, and includes steps of receiving a user utterance, adding the user utterance to a prompt including an instruction sentence related to an explanation of a character of the chatbot, encoding the prompt, and inputting the encoded prompt into a language model to generate a chatbot utterance as a response to the user utterance.

Prior Art Documents

Patent Documents

[0003]

Patent Document 1

Summary of the Invention

Problems to be Solved by the Invention

[0004] In the conventional technology, communication using voiceless utterances has not been fully realized, and there is room for improvement.

[0005] The system according to the embodiment aims to realize multilingual communication while maintaining privacy by using voiceless utterances.

Means for Solving the Problems

[0006] The system according to this embodiment comprises a collection unit, a generation unit, a translation unit, and a delivery unit. The collection unit reads the user's silent utterances. The generation unit converts the data read by the collection unit into text. The translation unit translates the text generated by the generation unit. The delivery unit converts the text translated by the translation unit into audio data and delivers it to the conversation partner. [Effects of the Invention]

[0007] The system according to this embodiment can achieve multilingual communication while maintaining privacy using silent speech. [Brief explanation of the drawing]

[0008] [Figure 1] This is a conceptual diagram showing an example of the configuration of a data processing system according to the first embodiment. [Figure 2] This is a conceptual diagram showing an example of the essential functions of a data processing device and a smart device according to the first embodiment. [Figure 3] This is a conceptual diagram showing an example of the configuration of a data processing system according to the second embodiment. [Figure 4] This is a conceptual diagram showing an example of the main functions of a data processing device and smart glasses according to the second embodiment. [Figure 5] This is a conceptual diagram showing an example of the configuration of a data processing system according to the third embodiment. [Figure 6] This is a conceptual diagram showing an example of the main functions of a data processing device and a headset-type terminal according to the third embodiment. [Figure 7] This is a conceptual diagram showing an example of the configuration of a data processing system according to the fourth embodiment. [Figure 8] This is a conceptual diagram showing an example of the main functions of a data processing device and a robot according to the fourth embodiment. [Figure 9] This shows an emotion map where multiple emotions are mapped. [Figure 10] This shows an emotion map where multiple emotions are mapped. [Modes for carrying out the invention]

[0009] Hereinafter, an example of an embodiment of the system relating to the technology of this disclosure will be described with reference to the attached drawings.

[0010] First, let's explain the terminology used in the following explanation.

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

[0012] In the following embodiments, signed RAM (Random Access Memory) is a memory that temporarily stores information and is used as work memory by the processor.

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

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

[0015] In the following embodiments, "A and / or B" is synonymous with "at least one of A and B". That is, "A and / or B" means that it may be only A, only B, or a combination of A and B. Also, in this specification, when expressing three or more matters connected by "and / or", the same concept as "A and / or B" is applied.

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

[0017] As shown in FIG. 1, the 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, the RAM 30, and the storage 32 are connected to a bus 34. Also, the database 24 and the communication I / F 26 are 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 comprises a computer 36, a receiving device 38, an output device 40, a camera 42, and a communication interface 44. The computer 36 comprises a processor 46, RAM 48, and storage 50. The processor 46, RAM 48, and storage 50 are connected to a bus 52. The receiving device 38, output device 40, and camera 42 are also connected to the bus 52.

[0020] The reception device 38 is equipped with a touch panel 38A and a microphone 38B, and accepts user input. The touch panel 38A accepts user input via touch by detecting contact with an object (e.g., a pen or finger). The microphone 38B accepts user input via voice by detecting the user's voice. The control unit 46A transmits data indicating the user input received by the touch panel 38A and microphone 38B to the data processing unit 12. In the data processing unit 12, the specific processing unit 290 (see Figure 2) acquires the data indicating the user input.

[0021] The output device 40 includes a display 40A and a speaker 40B, and presents data to the user by outputting the data in a form perceptible to the user (e.g., audio and / or text). The display 40A displays visible information such as text and images according to instructions from the processor 46. The speaker 40B outputs audio according to instructions from the processor 46. The camera 42 is a small digital camera equipped with an optical system such as a lens, aperture, and shutter, and an image sensor such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor.

[0022] Communication interface 44 is connected to network 54. Communication interfaces 44 and 26 are responsible for the exchange of various types of information between processor 46 and processor 28 via network 54.

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

[0024] As shown in Figure 2, in the data processing device 12, a specific processing 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" related to the technology of this 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 processing is realized by the processor 28 operating as a specific processing unit 290 according to the specific processing program 56 executed on the RAM 30.

[0025] Storage 32 stores the data generation model 58 and the 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 the user's emotions using the emotion identification model 59 and perform identification processing using the user's emotions. The emotion estimation function (emotion identification function) using the emotion identification model 59 performs various estimations and predictions regarding the user's emotions, including but not limited to these examples. Furthermore, emotion estimation and prediction also include, for example, emotion analysis.

[0026] In the smart device 14, specific processing is performed by the processor 46. The storage 50 stores a specific processing program 60. The specific processing program 60 is used in conjunction 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 a control unit 46A according to the specific processing program 60 executed on the RAM 48. The smart device 14 also has a data generation model 58 and an emotion identification model 59, similar to the data generation model and emotion identification model 59, and can perform processing similar to that of the specific processing unit 290 using these models.

[0027] Furthermore, other devices besides the data processing device 12 may also 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 processing results (such as prediction results) using the data generation model 58 by communicating with the server device having the data generation model 58. The data processing device 12 may also be a server device or a terminal device owned by a user (e.g., a mobile phone, robot, home appliance, etc.). Next, an example of processing by the data processing system 10 according to the first embodiment will be described.

[0028] (Example of form 1) The communication system according to an embodiment of the present invention is a system that transcribes a user's silent speech into text in the language of the conversation partner and generates audio data that mimics the user's voice quality. In an era where remote work and free-address offices are becoming commonplace, this communication system allows communication outside the company while protecting confidential company information, privacy, and the surrounding quietness. It also enables communication with foreigners and online meetings with overseas companies, providing an experience that feels like speaking in the other person's native language. The communication system uses multimodal AI to read the movements of the lips and tongue and transcribe them into text. Then, a generation AI captures the flow of the conversation, generates multiple candidate statements, and compares them to improve the accuracy of the transcription. Furthermore, if the conversation partner speaks a different language, it generates audio data after translation and delivers it to the conversation partner. For example, in the communication system, the user speaks silently, and the multimodal AI reads the movements of the lips and tongue and transcribes them into text. Next, the generation AI captures the flow of the conversation, generates multiple candidate statements, and compares them to select the most appropriate text. Furthermore, if the conversation partner speaks a different language, the AI-generating system translates the text and generates audio data that mimics the user's voice. Finally, the generated audio data is delivered to the conversation partner. This system allows users to have a conversation-like experience in their native language with anyone, anywhere, while protecting confidential company information and privacy. For example, even when working remotely in a cafe, important conversations can be held while maintaining the quietness of the surroundings. Also, communication with foreigners or online meetings with overseas companies can proceed smoothly in the other party's native language, improving business efficiency. In this way, the call system enables multilingual communication while protecting privacy by transcribing the user's silent speech into text, translating it, and converting it into audio data.

[0029] The communication system according to the embodiment comprises a collection unit, a generation unit, a translation unit, and a provision unit. The collection unit reads the user's non-verbal utterances. The collection unit can read lip and tongue movements using, for example, camera technology. The collection unit can also detect lip and tongue movements using sensor technology. Furthermore, the collection unit can read lip and tongue movements using infrared technology. For example, the collection unit uses a camera to capture the user's lip movements in high resolution and analyzes the video data. Sensor technology detects minute lip and tongue movements with high precision and collects them as data. Infrared technology can accurately read lip and tongue movements even in dark places. The generation unit converts the data read by the collection unit into text. The generation unit can improve the accuracy of text conversion using, for example, generation AI. The generation unit captures the flow of the conversation, generates multiple candidate statements, and compares them to select the most appropriate text. The generation unit, for example, uses generation AI to analyze the context of the conversation and generate appropriate candidate statements. Furthermore, the generation unit can have the generating AI refer to past conversation history and select the most suitable utterances. In addition, the generation unit can generate text considering the user's expertise and industry jargon. For example, the generating AI considers the context of the conversation to generate utterances that flow naturally. The generating AI prioritizes generating frequently used phrases from past conversation history. The generating AI prioritizes generating terminology related to the user's profession. The translation unit translates the text generated by the generation unit. The translation unit can translate the text using, for example, machine translation technology. The translation unit translates the text into the language of the conversation partner. The translation unit can translate the text using, for example, a translation algorithm. The translation unit can also estimate the user's emotions and adjust the translation's expression based on the estimated emotions. Furthermore, the translation unit can analyze the context of the conversation to provide a more natural translation. For example, if the user is nervous, the translation unit will provide a concise and clear translation. The translation unit considers the context of the conversation to provide an appropriate translation. The translation department refers to the user's past translation history and selects the most suitable translation method. The delivery department converts the text translated by the translation department into audio data and delivers it to the conversation partner.The service provider can generate voice data using, for example, speech synthesis technology. The service provider generates voice data that mimics the user's voice quality. The service provider generates voice that closely matches the user's voice quality using, for example, speech synthesis technology. The service provider can also estimate the user's emotions and adjust the voice data generation method based on the estimated emotions. Furthermore, the service provider can analyze the context of the conversation and generate more natural-sounding voice. For example, the service provider generates natural-sounding voice data when the user is relaxed. The service provider considers the context of the conversation and generates appropriate voice. The service provider refers to the user's past voice data and generates optimal voice. As a result, the call system according to this embodiment enables multilingual communication while protecting privacy by transcribing the user's silent speech into text, translating it, and converting it into voice data.

[0030] The data collection unit reads the user's non-verbal speech. The data collection unit can read lip and tongue movements using, for example, camera technology. It can also detect lip and tongue movements using sensor technology. Furthermore, the data collection unit can read lip and tongue movements using infrared technology. For example, the data collection unit uses a camera to capture the user's lip movements in high resolution and analyzes the video data. Sensor technology detects minute lip and tongue movements with high precision and collects them as data. Infrared technology can accurately read lip and tongue movements even in dark places. Specifically, camera technology can be used in combination with a wide-angle lens that captures the user's entire face and a zoom lens that captures lip and tongue movements in detail. This makes it possible to analyze the user's speech actions from multiple angles and collect more accurate data. Sensor technology, for example, uses pressure sensors and acceleration sensors to detect minute lip and tongue movements in real time. This makes it possible to capture the user's speech actions with high precision and improve the accuracy of the data. Infrared technology can accurately read lip and tongue movements even in dark or low-light environments, making it usable in various settings such as at night or indoors. This allows the data collection unit to capture the user's speech movements from multiple angles and collect accurate and highly precise data. Furthermore, the data collection unit can analyze this data in real time and provide it to the generation and translation units, thereby improving the overall system performance.

[0031] The generation unit converts the data read by the collection unit into text. The generation unit can improve the accuracy of text conversion, for example, by using a generation AI. The generation unit captures the flow of conversation, generates multiple utterance candidates, and compares them to select the most appropriate text. For example, the generation unit can use a generation AI to analyze the context of the conversation and generate appropriate utterance candidates. The generation unit can also use a generation AI to refer to past conversation history and select the optimal utterance candidate. Furthermore, the generation unit can use a generation AI to generate text while considering the user's expertise and industry jargon. For example, the generation AI considers the context of the conversation and generates utterance candidates that flow naturally. The generation AI prioritizes generating frequently used phrases from past conversation history. The generation AI prioritizes generating terms related to the user's occupation. Specifically, the generation AI uses natural language processing techniques to analyze data obtained from the user's speech actions and generate contextually appropriate text. The generation AI uses, for example, a recurrent neural network (RNN) or a transformer model to capture the flow of conversation and generate multiple utterance candidates. This allows the generation unit to accurately transcribe user speech actions into text, resulting in natural-sounding conversations. Furthermore, the generation unit's AI can learn the user's speech style and preferences, enabling the generation unit to produce more personalized text. This allows the generation unit to transcribe user speech actions with high accuracy, improving the overall system performance.

[0032] The translation unit translates the text generated by the generation unit. The translation unit can translate the text using, for example, machine translation technology. The translation unit translates the text into the language of the conversation partner. The translation unit can translate the text using, for example, a translation algorithm. The translation unit can also estimate the user's emotions and adjust the expression of the translation based on the estimated user emotions. Furthermore, the translation unit can analyze the context of the conversation and provide a more natural translation. For example, if the user is nervous, the translation unit will provide a concise and clear translation. The translation unit will consider the context of the conversation and provide an appropriate translation. The translation unit will refer to the user's past translation history and select the optimal translation method. Specifically, the translation unit uses neural machine translation (NMT) technology to translate the generated text with high accuracy. NMT technology can provide contextually natural translations using deep learning. The translation unit uses, for example, an encoder-decoder model to encode the input text and decode it into the target language. This allows the translation unit to accurately translate the user's utterances and achieve natural conversation. Furthermore, the translation unit can use sentiment analysis technology to estimate the user's emotions. Sentiment analysis technology can analyze the sentiment of the text and provide an appropriate translation that reflects the user's emotions. This allows the translation unit to provide natural translations that take the user's emotions into consideration, thereby improving the overall system performance.

[0033] The delivery unit converts the text translated by the translation unit into audio data and delivers it to the conversation partner. The delivery unit can generate audio data using, for example, speech synthesis technology. The delivery unit generates audio data that mimics the user's voice quality. The delivery unit generates voice that closely matches the user's voice quality using, for example, speech synthesis technology. The delivery unit can also estimate the user's emotions and adjust the method of generating audio data based on the estimated emotions. Furthermore, the delivery unit can analyze the context of the conversation and generate more natural-sounding voices. For example, the delivery unit generates natural-sounding voice data when the user is relaxed. The delivery unit considers the context of the conversation and generates appropriate voices. The delivery unit refers to the user's past voice data and generates the optimal voice. Specifically, the delivery unit can use deep learning-based speech synthesis models as speech synthesis technology. For example, it can use models such as WaveNet or Tacotron to generate high-quality audio data. This allows the delivery unit to generate natural-sounding voices that closely match the user's voice quality and deliver them to the conversation partner. Furthermore, the service provider can generate voice data that corresponds to the user's emotions using emotion analysis technology. This emotion analysis technology analyzes the user's emotions and generates voice data that includes appropriate emotional expressions. As a result, the service provider can provide natural-sounding voice that takes the user's emotions into consideration, improving the overall system performance.

[0034] The data collection unit can read the movements of the lips and tongue. The data collection unit can read the movements of the lips and tongue using, for example, camera technology. The data collection unit can also detect the movements of the lips and tongue using, for example, sensor technology. The data collection unit can also read the movements of the lips and tongue using, for example, infrared technology. By reading the movements of the lips and tongue, the accuracy of silent speech is improved. Some or all of the above processing in the data collection unit may be performed using, for example, AI, or not using AI. For example, the data collection unit can input lip and tongue movement data acquired by the camera into a generating AI, and the generating AI can perform movement analysis.

[0035] The generation unit can capture the flow of a conversation, generate multiple potential statements, and compare them to select the most appropriate text. For example, the generation unit can use a generation AI to analyze the context of the conversation and generate appropriate statement candidates. The generation unit can also use a generation AI to refer to past conversation history and select the optimal statement candidate. The generation unit can also use a generation AI to generate text while considering the user's expertise and industry jargon. This improves the accuracy of the text transcription by capturing the flow of the conversation and generating multiple statement candidates. Some or all of the above-described processes in the generation unit may be performed using a generation AI, or they may be performed without a generation AI. For example, the generation unit can input conversation data into a generation AI to analyze the context of the conversation, and the generation AI can generate statement candidates.

[0036] The translation unit can translate text into the language of the conversation partner. The translation unit can translate text using, for example, machine translation technology. The translation unit can also translate text using, for example, a translation algorithm. This enables multilingual communication by translating text into the language of the conversation partner. Some or all of the above-described processes in the translation unit may be performed using, for example, AI, or not using AI. For example, the translation unit can input text data into a generating AI, and the generating AI can perform the translation.

[0037] The service provider can generate voice data that mimics the user's voice and deliver it to the conversation partner. The service provider generates voice data using, for example, speech synthesis technology. The service provider can also generate voice that closely resembles the user's voice using, for example, speech synthesis technology. This enables natural conversation by generating voice data that mimics the user's voice. Some or all of the above processing in the service provider may be performed using, for example, AI, or without AI. For example, the service provider can input text data into a generation AI, and the generation AI can generate voice data.

[0038] The generation unit can improve the accuracy of text conversion using a generation AI. For example, the generation unit improves the accuracy of text conversion by using a generation AI. The generation unit can also, for example, have the generation AI analyze the context of the conversation and generate appropriate utterance candidates. This improves the accuracy of text conversion by using a generation AI. Some or all of the above-described processes in the generation unit may be performed using a generation AI, or they may be performed without a generation AI. For example, the generation unit can input conversation data into a generation AI and improve the accuracy of text conversion using the generation AI.

[0039] The data collection unit can analyze the user's past speech patterns and select the optimal reading method. For example, the data collection unit can use AI to select the optimal reading method based on speech patterns the user has frequently used in the past. The data collection unit can also prioritize the analysis of specific pronunciations or movements from the user's past speech patterns. The data collection unit can also analyze the user's past speech patterns and customize the process to improve reading accuracy. This allows the optimal reading method to be selected by analyzing past speech patterns. Some or all of the above processing in the data collection unit may be performed using AI, or without AI. For example, the data collection unit can input past speech data into a generating AI, which can then select the optimal reading method.

[0040] The data collection unit can improve accuracy by simultaneously analyzing the user's facial expressions and eye movements when reading silent speech. For example, the data collection unit can analyze the user's facial expressions to more accurately interpret the intent of the speech. For example, the data collection unit can track the user's eye movements to analyze the timing and emphasis of speech. For example, the data collection unit can analyze the movement of the user's entire face to improve the accuracy of reading silent speech. As a result, the accuracy of silent speech is improved by analyzing facial expressions and eye movements. Some or all of the above processing in the data collection unit may be performed using AI, for example, or without AI. For example, the data collection unit can input facial expression and eye movement data acquired by the camera into a generating AI, and the generating AI can perform the analysis.

[0041] The data collection unit can filter out ambient noise from the user when reading silent speech. For example, the data collection unit can filter out ambient noise to improve the accuracy of reading silent speech. The data collection unit can also analyze ambient noise in real time and remove noise. For example, the data collection unit can automatically detect and filter out ambient noise that affects the user's speech. This improves the accuracy of silent speech by filtering out ambient noise. Some or all of the above processing in the data collection unit may be performed using AI, for example, or without AI. For example, the data collection unit can input ambient sound data into a generating AI, and the generating AI can perform noise removal.

[0042] The data collection unit can analyze the user's gestures to obtain supplementary information when reading silent speech. For example, the data collection unit can analyze the user's hand movements to supplement the intent of the speech. The data collection unit can also analyze the user's body movements to supplement the emphasis of the speech. The data collection unit can also analyze the user's gestures to supplement the content of the speech. By analyzing gestures, the accuracy of silent speech is improved. Some or all of the above processing in the data collection unit may be performed using AI, for example, or without AI. For example, the data collection unit can input gesture data into a generating AI and have the generating AI perform the analysis.

[0043] The generation unit can generate optimal utterance candidates by referring to the user's past conversation history. For example, the generation unit can use the user's past conversation history as a basis for generating the optimal utterance candidate using a generation AI. The generation unit can also analyze the user's past conversation patterns, for example, and the generation AI can generate appropriate utterance candidates. For example, the generation unit can use the user's past conversation history to preferentially generate frequently used phrases using the generation AI. This allows the generation unit to generate optimal utterance candidates by referring to past conversation history. Some or all of the above-described processes in the generation unit may be performed using the generation AI, for example, or without using the generation AI. For example, the generation unit can input past conversation data into the generation AI, and the generation AI can generate the optimal utterance candidate.

[0044] The generation unit can generate more natural text by analyzing the context of the conversation when generating utterance candidates. For example, the generation unit can analyze the context of the conversation, and the generation AI can generate utterance candidates that flow naturally. The generation unit can also consider the context of the conversation, and the generation AI can generate appropriate utterance candidates. The generation unit can also analyze the topic of the conversation, and the generation AI can generate highly relevant utterance candidates. In this way, more natural text can be generated by analyzing the context of the conversation. Some or all of the above processing in the generation unit may be performed using the generation AI, or without using the generation AI. For example, the generation unit can input conversation data into the generation AI, and the generation AI can perform contextual analysis to generate natural text.

[0045] The generation unit can generate text considering the user's expertise and industry jargon when generating utterance candidates. For example, the generation unit can consider the user's expertise and have the generation AI generate utterance candidates that include appropriate industry jargon. The generation unit can also, for example, prioritize the generation of terms related to the user's occupation. The generation unit can also, for example, prioritize the generation of frequently used technical terms from the user's past conversation history. This allows for the generation of more appropriate text by considering expertise and industry jargon. Some or all of the above processing in the generation unit may be performed using, for example, the generation AI, or without the generation AI. For example, the generation unit can input technical terminology data into the generation AI, and the generation AI can generate utterance candidates.

[0046] The generation unit can select appropriate expressions when generating utterance candidates, taking into account the user's cultural background. For example, the generation unit considers the user's cultural background, and the generation AI selects appropriate expressions. The generation unit can also, for example, prioritize generating expressions specific to the user's country or region. The generation unit can also, for example, prioritize generating culturally appropriate expressions from the user's past conversation history. This allows for the selection of more appropriate expressions by considering the cultural background. Some or all of the above-described processes in the generation unit may be performed using, for example, a generation AI, or without using a generation AI. For example, the generation unit can input cultural background data into the generation AI, and the generation AI can generate utterance candidates.

[0047] The translation unit can provide a more natural translation by analyzing the context of the conversation during translation. For example, the translation unit can analyze the context of the conversation and provide a translation with a natural flow. For example, the translation unit can also consider the context of the conversation and provide an appropriate translation. For example, the translation unit can analyze the topic of the conversation and provide a highly relevant translation. In this way, by analyzing the context of the conversation, a more natural translation can be provided. Some or all of the above processes in the translation unit may be performed using AI, for example, or not using AI. For example, the translation unit can input conversation data into a generating AI, have the generating AI perform contextual analysis, and provide a natural translation.

[0048] The translation unit can select the optimal translation method by referring to the user's past translation history during translation. For example, the translation unit can select the optimal translation method based on the user's past translation history. The translation unit can also select an appropriate translation method by analyzing the user's past translation patterns. For example, the translation unit can prioritize the translation of frequently used expressions from the user's past translation history. This allows the optimal translation method to be selected by referring to past translation history. Some or all of the above processes in the translation unit may be performed using AI, for example, or without AI. For example, the translation unit can input past translation data into a generating AI, and the generating AI can select the optimal translation method.

[0049] The translation unit can select appropriate expressions while considering the cultural background of the conversation partner during translation. For example, the translation unit can select appropriate expressions considering the cultural background of the conversation partner. The translation unit can also, for example, prioritize the translation of expressions specific to the conversation partner's country or region. The translation unit can also, for example, prioritize the translation of culturally appropriate expressions based on the conversation partner's past conversation history. This allows for the provision of more appropriate translations by considering cultural background. Some or all of the above processing in the translation unit may be performed using AI, for example, or without AI. For example, the translation unit can input cultural background data into a generating AI and have the generating AI perform the translation.

[0050] The translation unit can improve accuracy by considering specialized terminology and industry jargon during translation. For example, the translation unit can consider specialized terminology and provide appropriate translations. The translation unit can also, for example, prioritize the translation of industry jargon. The translation unit can also, for example, consider terminology related to the user's occupation to improve accuracy. This improves the accuracy of translation by considering specialized terminology and industry jargon. Some or all of the above processes in the translation unit may be performed using AI, for example, or not using AI. For example, the translation unit can input specialized terminology data into a generating AI and have the generating AI perform the translation.

[0051] The service provider can generate optimal speech by referencing the user's past speech data when generating speech data. For example, the service provider can generate optimal speech based on the user's past speech data. The service provider can also analyze the user's past speech patterns and generate appropriate speech. For example, the service provider can prioritize the generation of frequently used tones and rhythms from the user's past speech data. This allows the service provider to generate optimal speech by referencing past speech data. Some or all of the above processing in the service provider may be performed using AI, for example, or without AI. For example, the service provider can input past speech data into a generation AI, and the generation AI can generate optimal speech.

[0052] The output unit can generate more natural speech by analyzing the context of a conversation when generating audio data. For example, the output unit can analyze the context of a conversation and generate naturally flowing speech. For example, the output unit can also consider the context of a conversation and generate appropriate speech. For example, the output unit can analyze the topic of a conversation and generate highly relevant speech. In this way, more natural speech can be generated by analyzing the context of a conversation. Some or all of the above processing in the output unit may be performed using AI, for example, or without AI. For example, the output unit can input conversation data into a generation AI, have the generation AI perform contextual analysis, and generate natural speech.

[0053] The service provider can generate natural-sounding speech by considering the tone and rhythm of the user's voice when generating speech data. For example, the service provider can generate natural-sounding speech by considering the tone of the user's voice. The service provider can also generate appropriate speech by considering the rhythm of the user's speech. For example, the service provider can prioritize the generation of frequently used tones and rhythms from the user's past speech data. This allows for the generation of more natural-sounding speech by considering the tone and rhythm of the voice. Some or all of the above-described processes in the service provider may be performed using AI, for example, or without AI. For example, the service provider can input voice tone and rhythm data into a generating AI, and the generating AI can generate speech data.

[0054] The service provider can generate speech while considering the accent and intonation of the conversation partner's language. For example, the service provider can consider the accent of the conversation partner's language and generate appropriate speech. For example, the service provider can also consider the intonation of the conversation partner's language and generate natural-sounding speech. For example, the service provider can prioritize the generation of frequently used accents and intonations from the conversation partner's past conversation history. This allows for the generation of more natural-sounding speech by considering the accent and intonation of the conversation partner's language. Some or all of the above processing in the service provider may be performed using AI, for example, or without AI. For example, the service provider can input the conversation partner's language data into a generating AI, and the generating AI can generate speech data.

[0055] The system according to the embodiment is not limited to the example described above, and various modifications are possible, for example, as follows.

[0056] The communication system can also be equipped with a gesture analysis unit that analyzes the user's gestures. The gesture analysis unit can analyze the user's hand and body movements and use them as supplementary information for silent speech. For example, if the user waves their hand, the system can analyze that the gesture means "goodbye" and add it as supplementary information when transcribing the message. Similarly, if the user points their finger, the system can analyze that the gesture means "here" and add it as supplementary information when transcribing the message. Furthermore, if the user nods their head, the system can analyze that the gesture means "yes" and add it as supplementary information when transcribing the message. As a result, using the gesture analysis unit improves the accuracy of silent speech and enables more natural communication.

[0057] The call system can also be equipped with an ambient sound analysis unit that analyzes the user's surrounding sounds. The ambient sound analysis unit can analyze the sounds around the user in real time and remove noise. For example, if a user is making a call in a cafe, the ambient sound analysis unit can filter out the cafe's background noise, improving the accuracy of reading silent speech. Also, if a user is making a call while out and about, the ambient sound analysis unit can filter out wind noise and car noises, improving the accuracy of reading silent speech. Furthermore, if a user is making a call at home, the ambient sound analysis unit can filter out household appliance sounds and pet noises, improving the accuracy of reading silent speech. As a result, using the ambient sound analysis unit improves the accuracy of silent speech, enabling clearer communication.

[0058] The call system may also include a history analysis unit that generates utterance suggestions by referencing the user's past conversation history. The history analysis unit can analyze the user's past conversation data and extract frequently used phrases and patterns. For example, based on phrases the user has frequently used in the past, the generation unit can generate optimal utterance suggestions. The generation unit can also analyze the user's past conversation patterns and generate appropriate utterance suggestions. Furthermore, from the user's past conversation history, the generation unit can prioritize the generation of frequently used technical terms and industry jargon. As a result, by using the history analysis unit, appropriate utterance suggestions based on the user's past conversation history can be generated, enabling more natural communication.

[0059] The call system may also include a cultural analysis unit that generates utterance suggestions while considering the user's cultural background. The cultural analysis unit can analyze expressions and cultural backgrounds specific to the user's country or region and generate appropriate utterance suggestions. For example, if the user is from Japan, the cultural analysis unit can prioritize generating expressions specific to Japan. Similarly, if the user is from the United States, the cultural analysis unit can prioritize generating expressions specific to the United States. Furthermore, it can also prioritize generating culturally appropriate expressions based on the user's past conversation history. As a result, by using the cultural analysis unit, appropriate utterance suggestions based on the user's cultural background can be generated, enabling more natural communication.

[0060] The communication system can also include a specialized terminology translation unit that takes into account the user's expertise and industry jargon. This unit can analyze terminology and expertise related to the user's profession and provide appropriate translations. For example, if the user is a medical professional, the unit can prioritize translating medical terminology. Similarly, if the user is a legal professional, the unit can prioritize translating legal terminology. Furthermore, it can prioritize frequently used specialized terms based on the user's past translation history. This allows for more natural communication by providing appropriate translations based on the user's expertise and industry jargon.

[0061] The call system may also include a voice history unit that generates voice data by referencing the user's past voice data. The voice history unit can analyze the user's past voice data and generate optimal voice. For example, based on the user's past voice data, the voice history unit can generate optimal voice. It can also analyze the user's past speech patterns and generate appropriate voice. Furthermore, it can prioritize the generation of frequently used tones and rhythms from the user's past voice data. As a result, by using the voice history unit, it becomes possible to generate appropriate voice based on the user's past voice data, enabling more natural communication.

[0062] The call system may also include an accent analysis unit that generates speech while considering the accent and intonation of the conversation partner's language. The accent analysis unit can analyze the accent and intonation of the conversation partner's language and generate appropriate speech. For example, if the conversation partner speaks English, the accent analysis unit can generate speech while considering the English accent. Similarly, if the conversation partner speaks French, the accent analysis unit can generate speech while considering the French intonation. Furthermore, it can prioritize the generation of frequently used accents and intonations based on the conversation partner's past conversation history. As a result, by using the accent analysis unit, it is possible to generate appropriate speech based on the accent and intonation of the conversation partner's language, enabling more natural communication.

[0063] The following briefly describes the processing flow for example form 1.

[0064] Step 1: The data collection unit reads the user's non-verbal speech. The data collection unit can, for example, read lip and tongue movements using camera technology. It can also detect lip and tongue movements using sensor technology. Furthermore, the data collection unit can read lip and tongue movements using infrared technology. For example, the data collection unit uses a camera to capture the user's lip movements in high resolution and analyzes the video data. Sensor technology detects minute lip and tongue movements with high precision and collects them as data. Infrared technology can accurately read lip and tongue movements even in dark places. Step 2: The generation unit converts the data read by the collection unit into text. The generation unit can improve the accuracy of the text conversion, for example, by using a generation AI. The generation unit captures the flow of the conversation, generates multiple utterance candidates, and compares them to select the most appropriate text. For example, the generation unit can use a generation AI to analyze the context of the conversation and generate appropriate utterance candidates. The generation unit can also use a generation AI to refer to past conversation history and select the best utterance candidate. Furthermore, the generation unit can use a generation AI to generate text while considering the user's expertise and industry terminology. For example, the generation AI considers the context of the conversation and generates utterance candidates that flow naturally. The generation AI prioritizes generating frequently used phrases from past conversation history. The generation AI prioritizes generating terms related to the user's profession. Step 3: The translation unit translates the text generated by the generation unit. The translation unit can translate the text using, for example, machine translation technology. The translation unit translates the text into the language of the conversation partner. The translation unit translates the text using, for example, a translation algorithm. The translation unit can also estimate the user's emotions and adjust the expression of the translation based on the estimated user emotions. Furthermore, the translation unit can analyze the context of the conversation and provide a more natural translation. For example, if the user is nervous, the translation unit will provide a concise and clear translation. The translation unit will consider the context of the conversation and provide an appropriate translation. The translation unit will refer to the user's past translation history and select the best translation method. Step 4: The delivery unit converts the text translated by the translation unit into audio data and delivers it to the conversation partner. The delivery unit can generate audio data using, for example, speech synthesis technology. The delivery unit generates audio data that mimics the user's voice quality. The delivery unit generates voice that closely matches the user's voice quality using, for example, speech synthesis technology. The delivery unit can also estimate the user's emotions and adjust the method of generating audio data based on the estimated user emotions. Furthermore, the delivery unit can analyze the context of the conversation and generate more natural-sounding voice. For example, the delivery unit generates natural-sounding voice data when the user is relaxed. The delivery unit considers the context of the conversation and generates appropriate voice. The delivery unit refers to the user's past audio data and generates the optimal voice.

[0065] (Example of form 2) The communication system according to an embodiment of the present invention is a system that transcribes a user's silent speech into text in the language of the conversation partner and generates audio data that mimics the user's voice quality. In an era where remote work and free-address offices are becoming commonplace, this communication system allows communication outside the company while protecting confidential company information, privacy, and the surrounding quietness. It also enables communication with foreigners and online meetings with overseas companies, providing an experience that feels like speaking in the other person's native language. The communication system uses multimodal AI to read the movements of the lips and tongue and transcribe them into text. Then, a generation AI captures the flow of the conversation, generates multiple candidate statements, and compares them to improve the accuracy of the transcription. Furthermore, if the conversation partner speaks a different language, it generates audio data after translation and delivers it to the conversation partner. For example, in the communication system, the user speaks silently, and the multimodal AI reads the movements of the lips and tongue and transcribes them into text. Next, the generation AI captures the flow of the conversation, generates multiple candidate statements, and compares them to select the most appropriate text. Furthermore, if the conversation partner speaks a different language, the AI-generating system translates the text and generates audio data that mimics the user's voice. Finally, the generated audio data is delivered to the conversation partner. This system allows users to have a conversation-like experience in their native language with anyone, anywhere, while protecting confidential company information and privacy. For example, even when working remotely in a cafe, important conversations can be held while maintaining the quietness of the surroundings. Also, communication with foreigners or online meetings with overseas companies can proceed smoothly in the other party's native language, improving business efficiency. In this way, the call system enables multilingual communication while protecting privacy by transcribing the user's silent speech into text, translating it, and converting it into audio data.

[0066] The communication system according to the embodiment comprises a collection unit, a generation unit, a translation unit, and a provision unit. The collection unit reads the user's non-verbal utterances. The collection unit can read lip and tongue movements using, for example, camera technology. The collection unit can also detect lip and tongue movements using sensor technology. Furthermore, the collection unit can read lip and tongue movements using infrared technology. For example, the collection unit uses a camera to capture the user's lip movements in high resolution and analyzes the video data. Sensor technology detects minute lip and tongue movements with high precision and collects them as data. Infrared technology can accurately read lip and tongue movements even in dark places. The generation unit converts the data read by the collection unit into text. The generation unit can improve the accuracy of text conversion using, for example, generation AI. The generation unit captures the flow of the conversation, generates multiple candidate statements, and compares them to select the most appropriate text. The generation unit, for example, uses generation AI to analyze the context of the conversation and generate appropriate candidate statements. Furthermore, the generation unit can have the generating AI refer to past conversation history and select the most suitable utterances. In addition, the generation unit can generate text considering the user's expertise and industry jargon. For example, the generating AI considers the context of the conversation to generate utterances that flow naturally. The generating AI prioritizes generating frequently used phrases from past conversation history. The generating AI prioritizes generating terminology related to the user's profession. The translation unit translates the text generated by the generation unit. The translation unit can translate the text using, for example, machine translation technology. The translation unit translates the text into the language of the conversation partner. The translation unit can translate the text using, for example, a translation algorithm. The translation unit can also estimate the user's emotions and adjust the translation's expression based on the estimated emotions. Furthermore, the translation unit can analyze the context of the conversation to provide a more natural translation. For example, if the user is nervous, the translation unit will provide a concise and clear translation. The translation unit considers the context of the conversation to provide an appropriate translation. The translation department refers to the user's past translation history and selects the most suitable translation method. The delivery department converts the text translated by the translation department into audio data and delivers it to the conversation partner.The service provider can generate voice data using, for example, speech synthesis technology. The service provider generates voice data that mimics the user's voice quality. The service provider generates voice that closely matches the user's voice quality using, for example, speech synthesis technology. The service provider can also estimate the user's emotions and adjust the voice data generation method based on the estimated emotions. Furthermore, the service provider can analyze the context of the conversation and generate more natural-sounding voice. For example, the service provider generates natural-sounding voice data when the user is relaxed. The service provider considers the context of the conversation and generates appropriate voice. The service provider refers to the user's past voice data and generates optimal voice. As a result, the call system according to this embodiment enables multilingual communication while protecting privacy by transcribing the user's silent speech into text, translating it, and converting it into voice data.

[0067] The data collection unit reads the user's non-verbal speech. The data collection unit can read lip and tongue movements using, for example, camera technology. It can also detect lip and tongue movements using sensor technology. Furthermore, the data collection unit can read lip and tongue movements using infrared technology. For example, the data collection unit uses a camera to capture the user's lip movements in high resolution and analyzes the video data. Sensor technology detects minute lip and tongue movements with high precision and collects them as data. Infrared technology can accurately read lip and tongue movements even in dark places. Specifically, camera technology can be used in combination with a wide-angle lens that captures the user's entire face and a zoom lens that captures lip and tongue movements in detail. This makes it possible to analyze the user's speech actions from multiple angles and collect more accurate data. Sensor technology, for example, uses pressure sensors and acceleration sensors to detect minute lip and tongue movements in real time. This makes it possible to capture the user's speech actions with high precision and improve the accuracy of the data. Infrared technology can accurately read lip and tongue movements even in dark or low-light environments, making it usable in various settings such as at night or indoors. This allows the data collection unit to capture the user's speech movements from multiple angles and collect accurate and highly precise data. Furthermore, the data collection unit can analyze this data in real time and provide it to the generation and translation units, thereby improving the overall system performance.

[0068] The generation unit converts the data read by the collection unit into text. The generation unit can improve the accuracy of text conversion, for example, by using a generation AI. The generation unit captures the flow of conversation, generates multiple utterance candidates, and compares them to select the most appropriate text. For example, the generation unit can use a generation AI to analyze the context of the conversation and generate appropriate utterance candidates. The generation unit can also use a generation AI to refer to past conversation history and select the optimal utterance candidate. Furthermore, the generation unit can use a generation AI to generate text while considering the user's expertise and industry jargon. For example, the generation AI considers the context of the conversation and generates utterance candidates that flow naturally. The generation AI prioritizes generating frequently used phrases from past conversation history. The generation AI prioritizes generating terms related to the user's occupation. Specifically, the generation AI uses natural language processing techniques to analyze data obtained from the user's speech actions and generate contextually appropriate text. The generation AI uses, for example, a recurrent neural network (RNN) or a transformer model to capture the flow of conversation and generate multiple utterance candidates. This allows the generation unit to accurately transcribe user speech actions into text, resulting in natural-sounding conversations. Furthermore, the generation unit's AI can learn the user's speech style and preferences, enabling the generation unit to produce more personalized text. This allows the generation unit to transcribe user speech actions with high accuracy, improving the overall system performance.

[0069] The translation unit translates the text generated by the generation unit. The translation unit can translate the text using, for example, machine translation technology. The translation unit translates the text into the language of the conversation partner. The translation unit can translate the text using, for example, a translation algorithm. The translation unit can also estimate the user's emotions and adjust the expression of the translation based on the estimated user emotions. Furthermore, the translation unit can analyze the context of the conversation and provide a more natural translation. For example, if the user is nervous, the translation unit will provide a concise and clear translation. The translation unit will consider the context of the conversation and provide an appropriate translation. The translation unit will refer to the user's past translation history and select the optimal translation method. Specifically, the translation unit uses neural machine translation (NMT) technology to translate the generated text with high accuracy. NMT technology can provide contextually natural translations using deep learning. The translation unit uses, for example, an encoder-decoder model to encode the input text and decode it into the target language. This allows the translation unit to accurately translate the user's utterances and achieve natural conversation. Furthermore, the translation unit can use sentiment analysis technology to estimate the user's emotions. Sentiment analysis technology can analyze the sentiment of the text and provide an appropriate translation that reflects the user's emotions. This allows the translation unit to provide natural translations that take the user's emotions into consideration, thereby improving the overall system performance.

[0070] The delivery unit converts the text translated by the translation unit into audio data and delivers it to the conversation partner. The delivery unit can generate audio data using, for example, speech synthesis technology. The delivery unit generates audio data that mimics the user's voice quality. The delivery unit generates voice that closely matches the user's voice quality using, for example, speech synthesis technology. The delivery unit can also estimate the user's emotions and adjust the method of generating audio data based on the estimated emotions. Furthermore, the delivery unit can analyze the context of the conversation and generate more natural-sounding voices. For example, the delivery unit generates natural-sounding voice data when the user is relaxed. The delivery unit considers the context of the conversation and generates appropriate voices. The delivery unit refers to the user's past voice data and generates the optimal voice. Specifically, the delivery unit can use deep learning-based speech synthesis models as speech synthesis technology. For example, it can use models such as WaveNet or Tacotron to generate high-quality audio data. This allows the delivery unit to generate natural-sounding voices that closely match the user's voice quality and deliver them to the conversation partner. Furthermore, the service provider can generate voice data that corresponds to the user's emotions using emotion analysis technology. This emotion analysis technology analyzes the user's emotions and generates voice data that includes appropriate emotional expressions. As a result, the service provider can provide natural-sounding voice that takes the user's emotions into consideration, improving the overall system performance.

[0071] The data collection unit can read the movements of the lips and tongue. The data collection unit can read the movements of the lips and tongue using, for example, camera technology. The data collection unit can also detect the movements of the lips and tongue using, for example, sensor technology. The data collection unit can also read the movements of the lips and tongue using, for example, infrared technology. By reading the movements of the lips and tongue, the accuracy of silent speech is improved. Some or all of the above processing in the data collection unit may be performed using, for example, AI, or not using AI. For example, the data collection unit can input lip and tongue movement data acquired by the camera into a generating AI, and the generating AI can perform movement analysis.

[0072] The generation unit can capture the flow of a conversation, generate multiple potential statements, and compare them to select the most appropriate text. For example, the generation unit can use a generation AI to analyze the context of the conversation and generate appropriate statement candidates. The generation unit can also use a generation AI to refer to past conversation history and select the optimal statement candidate. The generation unit can also use a generation AI to generate text while considering the user's expertise and industry jargon. This improves the accuracy of the text transcription by capturing the flow of the conversation and generating multiple statement candidates. Some or all of the above-described processes in the generation unit may be performed using a generation AI, or they may be performed without a generation AI. For example, the generation unit can input conversation data into a generation AI to analyze the context of the conversation, and the generation AI can generate statement candidates.

[0073] The translation unit can translate text into the language of the conversation partner. The translation unit can translate text using, for example, machine translation technology. The translation unit can also translate text using, for example, a translation algorithm. This enables multilingual communication by translating text into the language of the conversation partner. Some or all of the above-described processes in the translation unit may be performed using, for example, AI, or not using AI. For example, the translation unit can input text data into a generating AI, and the generating AI can perform the translation.

[0074] The service provider can generate voice data that mimics the user's voice and deliver it to the conversation partner. The service provider generates voice data using, for example, speech synthesis technology. The service provider can also generate voice that closely resembles the user's voice using, for example, speech synthesis technology. This enables natural conversation by generating voice data that mimics the user's voice. Some or all of the above processing in the service provider may be performed using, for example, AI, or without AI. For example, the service provider can input text data into a generation AI, and the generation AI can generate voice data.

[0075] The generation unit can improve the accuracy of text conversion using a generation AI. For example, the generation unit improves the accuracy of text conversion by using a generation AI. The generation unit can also, for example, have the generation AI analyze the context of the conversation and generate appropriate utterance candidates. This improves the accuracy of text conversion by using a generation AI. Some or all of the above-described processes in the generation unit may be performed using a generation AI, or they may be performed without a generation AI. For example, the generation unit can input conversation data into a generation AI and improve the accuracy of text conversion using the generation AI.

[0076] The data collection unit can estimate the user's emotions and adjust the accuracy of reading silent speech based on the estimated emotions. For example, if the user is nervous, the AI ​​may analyze lip and tongue movements in more detail to improve reading accuracy. If the user is relaxed, the AI ​​may revert the reading accuracy to the normal setting and prioritize natural speech. If the user is in a hurry, the AI ​​may prioritize reading speed and quickly transcribe the speech. This improves the accuracy of silent speech by adjusting the reading accuracy based on the user's emotions. Emotion estimation is achieved using an emotion estimation function, such as an emotion engine or a generative AI. The generative AI may be, but is not limited to, a text generation AI (e.g., LLM) or a multimodal generation AI. Some or all of the above processing in the data collection unit may be performed using or without AI. For example, the data collection unit can input user facial expression data acquired by a camera into a generative AI, which can then perform emotion estimation.

[0077] The data collection unit can analyze the user's past speech patterns and select the optimal reading method. For example, the data collection unit can use AI to select the optimal reading method based on speech patterns the user has frequently used in the past. The data collection unit can also prioritize the analysis of specific pronunciations or movements from the user's past speech patterns. The data collection unit can also analyze the user's past speech patterns and customize the process to improve reading accuracy. This allows the optimal reading method to be selected by analyzing past speech patterns. Some or all of the above processing in the data collection unit may be performed using AI, or without AI. For example, the data collection unit can input past speech data into a generating AI, which can then select the optimal reading method.

[0078] The data collection unit can improve accuracy by simultaneously analyzing the user's facial expressions and eye movements when reading silent speech. For example, the data collection unit can analyze the user's facial expressions to more accurately interpret the intent of the speech. For example, the data collection unit can track the user's eye movements to analyze the timing and emphasis of speech. For example, the data collection unit can analyze the movement of the user's entire face to improve the accuracy of reading silent speech. As a result, the accuracy of silent speech is improved by analyzing facial expressions and eye movements. Some or all of the above processing in the data collection unit may be performed using AI, for example, or without AI. For example, the data collection unit can input facial expression and eye movement data acquired by the camera into a generating AI, and the generating AI can perform the analysis.

[0079] The data collection unit can estimate the user's emotions and determine the priority of utterances to read based on the estimated emotions. For example, if the user is nervous, the data collection unit may prioritize reading important utterances. If the user is relaxed, the data collection unit may also read all utterances equally. If the user is in a hurry, the data collection unit may also prioritize reading short utterances. This allows for the priority of important utterances to be read by determining the priority of utterances based on the user's emotions. Emotion estimation is achieved using an emotion estimation function, such as an emotion engine or generative AI. Generative AI may be, but is not limited to, text generation AI (e.g., LLM) or multimodal generation AI. Some or all of the above processing in the data collection unit may be performed using AI or not using AI. For example, the data collection unit can input user facial expression data acquired by a camera into a generative AI, which can then perform emotion estimation.

[0080] The data collection unit can filter out ambient noise from the user when reading silent speech. For example, the data collection unit can filter out ambient noise to improve the accuracy of reading silent speech. The data collection unit can also analyze ambient noise in real time and remove noise. For example, the data collection unit can automatically detect and filter out ambient noise that affects the user's speech. This improves the accuracy of silent speech by filtering out ambient noise. Some or all of the above processing in the data collection unit may be performed using AI, for example, or without AI. For example, the data collection unit can input ambient sound data into a generating AI, and the generating AI can perform noise removal.

[0081] The data collection unit can analyze the user's gestures to obtain supplementary information when reading silent speech. For example, the data collection unit can analyze the user's hand movements to supplement the intent of the speech. The data collection unit can also analyze the user's body movements to supplement the emphasis of the speech. The data collection unit can also analyze the user's gestures to supplement the content of the speech. By analyzing gestures, the accuracy of silent speech is improved. Some or all of the above processing in the data collection unit may be performed using AI, for example, or without AI. For example, the data collection unit can input gesture data into a generating AI and have the generating AI perform the analysis.

[0082] The generation unit can estimate the user's emotions and adjust the method of generating speech candidates based on the estimated user emotions. For example, if the user is relaxed, the generation AI will generate natural speech candidates. If the user is tense, the generation unit can also generate concise and clear speech candidates. If the user is in a hurry, the generation unit can also generate speech candidates quickly. By adjusting the method of generating speech candidates based on the user's emotions, more appropriate speech candidates can be generated. Emotion estimation is achieved using an emotion estimation function, for example, using an emotion engine or a generation AI. The generation AI is, but is not limited to, a text generation AI (e.g., LLM) or a multimodal generation AI. Some or all of the above processing in the generation unit may be performed using a generation AI, or not using a generation AI. For example, the generation unit can input emotion data into a generation AI, and the generation AI can adjust the method of generating speech candidates.

[0083] The generation unit can generate optimal utterance candidates by referring to the user's past conversation history. For example, the generation unit can use the user's past conversation history as a basis for generating the optimal utterance candidate using a generation AI. The generation unit can also analyze the user's past conversation patterns, for example, and the generation AI can generate appropriate utterance candidates. For example, the generation unit can use the user's past conversation history to preferentially generate frequently used phrases using the generation AI. This allows the generation unit to generate optimal utterance candidates by referring to past conversation history. Some or all of the above-described processes in the generation unit may be performed using the generation AI, for example, or without using the generation AI. For example, the generation unit can input past conversation data into the generation AI, and the generation AI can generate the optimal utterance candidate.

[0084] The generation unit can generate more natural text by analyzing the context of the conversation when generating utterance candidates. For example, the generation unit can analyze the context of the conversation, and the generation AI can generate utterance candidates that flow naturally. The generation unit can also consider the context of the conversation, and the generation AI can generate appropriate utterance candidates. The generation unit can also analyze the topic of the conversation, and the generation AI can generate highly relevant utterance candidates. In this way, more natural text can be generated by analyzing the context of the conversation. Some or all of the above processing in the generation unit may be performed using the generation AI, or without using the generation AI. For example, the generation unit can input conversation data into the generation AI, and the generation AI can perform contextual analysis to generate natural text.

[0085] The generation unit can estimate the user's emotions and determine the priority of potential statements based on the estimated emotions. For example, if the user is nervous, the generation AI will prioritize concise and clear statements. If the user is relaxed, the generation AI may also prioritize detailed statements. If the user is in a hurry, the generation AI may also prioritize quick statements. This allows for the priority generation of important statements by determining the priority of statements based on the user's emotions. Emotion estimation is achieved using an emotion estimation function, such as an emotion engine or a generation AI. The generation AI is, but is not limited to, a text generation AI (e.g., LLM) or a multimodal generation AI. Some or all of the above-described processes in the generation unit may be performed using a generation AI, or not. For example, the generation unit can input emotion data into a generation AI, which can then determine the priority of potential statements.

[0086] The generation unit can generate text considering the user's expertise and industry jargon when generating utterance candidates. For example, the generation unit can consider the user's expertise and have the generation AI generate utterance candidates that include appropriate industry jargon. The generation unit can also, for example, prioritize the generation of terms related to the user's occupation. The generation unit can also, for example, prioritize the generation of frequently used technical terms from the user's past conversation history. This allows for the generation of more appropriate text by considering expertise and industry jargon. Some or all of the above processing in the generation unit may be performed using, for example, the generation AI, or without the generation AI. For example, the generation unit can input technical terminology data into the generation AI, and the generation AI can generate utterance candidates.

[0087] The generation unit can select appropriate expressions when generating utterance candidates, taking into account the user's cultural background. For example, the generation unit considers the user's cultural background, and the generation AI selects appropriate expressions. The generation unit can also, for example, prioritize generating expressions specific to the user's country or region. The generation unit can also, for example, prioritize generating culturally appropriate expressions from the user's past conversation history. This allows for the selection of more appropriate expressions by considering the cultural background. Some or all of the above-described processes in the generation unit may be performed using, for example, a generation AI, or without using a generation AI. For example, the generation unit can input cultural background data into the generation AI, and the generation AI can generate utterance candidates.

[0088] The translation unit can estimate the user's emotions and adjust the translation's expression based on the estimated emotions. For example, if the user is nervous, the translation unit can provide a concise and clear translation. If the user is relaxed, the translation unit can also provide a detailed and polite translation. If the user is in a hurry, the translation unit can also provide a quick translation. This allows for more appropriate translations by adjusting the translation's expression based on the user's emotions. Emotion estimation is achieved using an emotion estimation function, such as an emotion engine or generative AI. Generative AI includes, but is not limited to, text generation AI (e.g., LLM) or multimodal generation AI. Some or all of the above processing in the translation unit may be performed using AI, or not using AI. For example, the translation unit can input emotion data into a generative AI, and the generative AI can adjust the translation's expression.

[0089] The translation unit can provide a more natural translation by analyzing the context of the conversation during translation. For example, the translation unit can analyze the context of the conversation and provide a translation with a natural flow. For example, the translation unit can also consider the context of the conversation and provide an appropriate translation. For example, the translation unit can analyze the topic of the conversation and provide a highly relevant translation. In this way, by analyzing the context of the conversation, a more natural translation can be provided. Some or all of the above processes in the translation unit may be performed using AI, for example, or not using AI. For example, the translation unit can input conversation data into a generating AI, have the generating AI perform contextual analysis, and provide a natural translation.

[0090] The translation unit can select the optimal translation method by referring to the user's past translation history during translation. For example, the translation unit can select the optimal translation method based on the user's past translation history. The translation unit can also select an appropriate translation method by analyzing the user's past translation patterns. For example, the translation unit can prioritize the translation of frequently used expressions from the user's past translation history. This allows the optimal translation method to be selected by referring to past translation history. Some or all of the above processes in the translation unit may be performed using AI, for example, or without AI. For example, the translation unit can input past translation data into a generating AI, and the generating AI can select the optimal translation method.

[0091] The translation unit can estimate the user's emotions and determine translation priorities based on the estimated emotions. For example, if the user is nervous, the translation unit may prioritize translating important parts. If the user is relaxed, the translation unit may also translate all parts equally. If the user is in a hurry, the translation unit may also prioritize translating shorter sections. This allows for prioritizing the translation of important parts by determining translation priorities based on the user's emotions. Emotion estimation is achieved using an emotion estimation function, such as an emotion engine or generative AI. Generative AI may be, but is not limited to, text generation AI (e.g., LLM) or multimodal generation AI. Some or all of the above processing in the translation unit may be performed using AI or not. For example, the translation unit can input emotion data into a generative AI, which can then determine translation priorities.

[0092] The translation unit can select appropriate expressions while considering the cultural background of the conversation partner during translation. For example, the translation unit can select appropriate expressions considering the cultural background of the conversation partner. The translation unit can also, for example, prioritize the translation of expressions specific to the conversation partner's country or region. The translation unit can also, for example, prioritize the translation of culturally appropriate expressions based on the conversation partner's past conversation history. This allows for the provision of more appropriate translations by considering cultural background. Some or all of the above processing in the translation unit may be performed using AI, for example, or without AI. For example, the translation unit can input cultural background data into a generating AI and have the generating AI perform the translation.

[0093] The translation unit can improve accuracy by considering specialized terminology and industry jargon during translation. For example, the translation unit can consider specialized terminology and provide appropriate translations. The translation unit can also, for example, prioritize the translation of industry jargon. The translation unit can also, for example, consider terminology related to the user's occupation to improve accuracy. This improves the accuracy of translation by considering specialized terminology and industry jargon. Some or all of the above processes in the translation unit may be performed using AI, for example, or not using AI. For example, the translation unit can input specialized terminology data into a generating AI and have the generating AI perform the translation.

[0094] The service provider can estimate the user's emotions and adjust the method of generating audio data based on the estimated user emotions. For example, if the user is relaxed, the service provider can generate natural-sounding audio data. For example, if the user is tense, the service provider can also generate audio data in a calm tone. For example, if the user is in a hurry, the service provider can also generate fast and clear audio data. This allows for the generation of more appropriate audio data by adjusting the method of generating audio data based on the user's emotions. Emotion estimation is achieved using an emotion estimation function, for example, using an emotion engine or a generative AI. The generative AI is, but is not limited to, text generation AI (e.g., LLM) or multimodal generation AI. Some or all of the above processing in the service provider may be performed using AI, for example, or without AI. For example, the service provider can input emotion data into a generative AI, and the generative AI can adjust the method of generating audio data.

[0095] The service provider can generate optimal speech by referencing the user's past speech data when generating speech data. For example, the service provider can generate optimal speech based on the user's past speech data. The service provider can also analyze the user's past speech patterns and generate appropriate speech. For example, the service provider can prioritize the generation of frequently used tones and rhythms from the user's past speech data. This allows the service provider to generate optimal speech by referencing past speech data. Some or all of the above processing in the service provider may be performed using AI, for example, or without AI. For example, the service provider can input past speech data into a generation AI, and the generation AI can generate optimal speech.

[0096] The output unit can generate more natural speech by analyzing the context of a conversation when generating audio data. For example, the output unit can analyze the context of a conversation and generate naturally flowing speech. For example, the output unit can also consider the context of a conversation and generate appropriate speech. For example, the output unit can analyze the topic of a conversation and generate highly relevant speech. In this way, more natural speech can be generated by analyzing the context of a conversation. Some or all of the above processing in the output unit may be performed using AI, for example, or without AI. For example, the output unit can input conversation data into a generation AI, have the generation AI perform contextual analysis, and generate natural speech.

[0097] The delivery unit can estimate the user's emotions and prioritize audio data based on the estimated emotions. For example, if the user is nervous, the delivery unit will prioritize vocalizing important parts. For example, if the user is relaxed, the delivery unit can also vocalize all parts equally. For example, if the user is in a hurry, the delivery unit can also prioritize vocalizing shorter parts. This allows for prioritizing important parts by prioritizing audio data based on the user's emotions. Emotion estimation is achieved using an emotion estimation function, such as an emotion engine or generative AI. Generative AI is, but is not limited to, text generation AI (e.g., LLM) or multimodal generation AI. Some or all of the above processing in the delivery unit may be performed using AI or not using AI. For example, the delivery unit can input emotion data into a generative AI, and the generative AI can determine the priority of the audio data.

[0098] The service provider can generate natural-sounding speech by considering the tone and rhythm of the user's voice when generating speech data. For example, the service provider can generate natural-sounding speech by considering the tone of the user's voice. The service provider can also generate appropriate speech by considering the rhythm of the user's speech. For example, the service provider can prioritize the generation of frequently used tones and rhythms from the user's past speech data. This allows for the generation of more natural-sounding speech by considering the tone and rhythm of the voice. Some or all of the above-described processes in the service provider may be performed using AI, for example, or without AI. For example, the service provider can input voice tone and rhythm data into a generating AI, and the generating AI can generate speech data.

[0099] The service provider can generate speech while considering the accent and intonation of the conversation partner's language. For example, the service provider can consider the accent of the conversation partner's language and generate appropriate speech. For example, the service provider can also consider the intonation of the conversation partner's language and generate natural-sounding speech. For example, the service provider can prioritize the generation of frequently used accents and intonations from the conversation partner's past conversation history. This allows for the generation of more natural-sounding speech by considering the accent and intonation of the conversation partner's language. Some or all of the above processing in the service provider may be performed using AI, for example, or without AI. For example, the service provider can input the conversation partner's language data into a generating AI, and the generating AI can generate speech data.

[0100] The system according to the embodiment is not limited to the example described above, and various modifications are possible, for example, as follows.

[0101] The communication system can also be equipped with a gesture analysis unit that analyzes the user's gestures. The gesture analysis unit can analyze the user's hand and body movements and use them as supplementary information for silent speech. For example, if the user waves their hand, the system can analyze that the gesture means "goodbye" and add it as supplementary information when transcribing the message. Similarly, if the user points their finger, the system can analyze that the gesture means "here" and add it as supplementary information when transcribing the message. Furthermore, if the user nods their head, the system can analyze that the gesture means "yes" and add it as supplementary information when transcribing the message. As a result, using the gesture analysis unit improves the accuracy of silent speech and enables more natural communication.

[0102] The call system can also be equipped with an ambient sound analysis unit that analyzes the user's surrounding sounds. The ambient sound analysis unit can analyze the sounds around the user in real time and remove noise. For example, if a user is making a call in a cafe, the ambient sound analysis unit can filter out the cafe's background noise, improving the accuracy of reading silent speech. Also, if a user is making a call while out and about, the ambient sound analysis unit can filter out wind noise and car noises, improving the accuracy of reading silent speech. Furthermore, if a user is making a call at home, the ambient sound analysis unit can filter out household appliance sounds and pet noises, improving the accuracy of reading silent speech. As a result, using the ambient sound analysis unit improves the accuracy of silent speech, enabling clearer communication.

[0103] The call system may also include an emotion analysis unit that estimates the user's emotions and generates suggested phrases based on those estimates. The emotion analysis unit can analyze the user's facial expressions and tone of voice to estimate their emotions. For example, if the user is smiling while speaking, the emotion analysis unit can estimate that the user is relaxed, and the generation unit can generate natural phrase suggestions. Similarly, if the user is frowning, the emotion analysis unit can estimate that the user is tense, and the generation unit can generate concise and clear phrase suggestions. Furthermore, if the user appears to be in a hurry, the emotion analysis unit can estimate that the user is in a hurry, and the generation unit can quickly generate phrase suggestions. By using the emotion analysis unit, it becomes possible to generate appropriate phrase suggestions based on the user's emotions, enabling more natural communication.

[0104] The call system may also include a history analysis unit that generates utterance suggestions by referencing the user's past conversation history. The history analysis unit can analyze the user's past conversation data and extract frequently used phrases and patterns. For example, based on phrases the user has frequently used in the past, the generation unit can generate optimal utterance suggestions. The generation unit can also analyze the user's past conversation patterns and generate appropriate utterance suggestions. Furthermore, from the user's past conversation history, the generation unit can prioritize the generation of frequently used technical terms and industry jargon. As a result, by using the history analysis unit, appropriate utterance suggestions based on the user's past conversation history can be generated, enabling more natural communication.

[0105] The call system may also include a cultural analysis unit that generates utterance suggestions while considering the user's cultural background. The cultural analysis unit can analyze expressions and cultural backgrounds specific to the user's country or region and generate appropriate utterance suggestions. For example, if the user is from Japan, the cultural analysis unit can prioritize generating expressions specific to Japan. Similarly, if the user is from the United States, the cultural analysis unit can prioritize generating expressions specific to the United States. Furthermore, it can also prioritize generating culturally appropriate expressions based on the user's past conversation history. As a result, by using the cultural analysis unit, appropriate utterance suggestions based on the user's cultural background can be generated, enabling more natural communication.

[0106] The call system may also include a translation adjustment unit that estimates the user's emotions and adjusts the translation's expression based on those emotions. The translation adjustment unit can analyze the user's emotions and adjust the translation's expression accordingly. For example, if the user is nervous, the unit can provide a concise and clear translation. If the user is relaxed, the unit can provide a detailed and polite translation. Furthermore, if the user is in a hurry, the unit can provide a quick translation. This allows for more natural communication by providing appropriate translations based on the user's emotions.

[0107] The communication system can also include a specialized terminology translation unit that takes into account the user's expertise and industry jargon. This unit can analyze terminology and expertise related to the user's profession and provide appropriate translations. For example, if the user is a medical professional, the unit can prioritize translating medical terminology. Similarly, if the user is a legal professional, the unit can prioritize translating legal terminology. Furthermore, it can prioritize frequently used specialized terms based on the user's past translation history. This allows for more natural communication by providing appropriate translations based on the user's expertise and industry jargon.

[0108] The call system may also include a voice adjustment unit that estimates the user's emotions and adjusts the method of generating voice data based on the estimated emotions. The voice adjustment unit can analyze the user's emotions and adjust the method of generating voice data. For example, if the user is relaxed, the voice adjustment unit can generate natural voice data. If the user is tense, the voice adjustment unit can also generate voice data in a calm tone. Furthermore, if the user is in a hurry, the voice adjustment unit can also generate fast and clear voice data. In this way, by using the voice adjustment unit, appropriate voice data based on the user's emotions can be generated, enabling more natural communication.

[0109] The call system may also include a voice history unit that generates voice data by referencing the user's past voice data. The voice history unit can analyze the user's past voice data and generate optimal voice. For example, based on the user's past voice data, the voice history unit can generate optimal voice. It can also analyze the user's past speech patterns and generate appropriate voice. Furthermore, it can prioritize the generation of frequently used tones and rhythms from the user's past voice data. As a result, by using the voice history unit, it becomes possible to generate appropriate voice based on the user's past voice data, enabling more natural communication.

[0110] The call system may also include an accent analysis unit that generates speech while considering the accent and intonation of the conversation partner's language. The accent analysis unit can analyze the accent and intonation of the conversation partner's language and generate appropriate speech. For example, if the conversation partner speaks English, the accent analysis unit can generate speech while considering the English accent. Similarly, if the conversation partner speaks French, the accent analysis unit can generate speech while considering the French intonation. Furthermore, it can prioritize the generation of frequently used accents and intonations based on the conversation partner's past conversation history. As a result, by using the accent analysis unit, it is possible to generate appropriate speech based on the accent and intonation of the conversation partner's language, enabling more natural communication.

[0111] The following briefly describes the processing flow for example form 2.

[0112] Step 1: The data collection unit reads the user's non-verbal speech. The data collection unit can, for example, read lip and tongue movements using camera technology. It can also detect lip and tongue movements using sensor technology. Furthermore, the data collection unit can read lip and tongue movements using infrared technology. For example, the data collection unit uses a camera to capture the user's lip movements in high resolution and analyzes the video data. Sensor technology detects minute lip and tongue movements with high precision and collects them as data. Infrared technology can accurately read lip and tongue movements even in dark places. Step 2: The generation unit converts the data read by the collection unit into text. The generation unit can improve the accuracy of the text conversion, for example, by using a generation AI. The generation unit captures the flow of the conversation, generates multiple utterance candidates, and compares them to select the most appropriate text. For example, the generation unit can use a generation AI to analyze the context of the conversation and generate appropriate utterance candidates. The generation unit can also use a generation AI to refer to past conversation history and select the best utterance candidate. Furthermore, the generation unit can use a generation AI to generate text while considering the user's expertise and industry terminology. For example, the generation AI considers the context of the conversation and generates utterance candidates that flow naturally. The generation AI prioritizes generating frequently used phrases from past conversation history. The generation AI prioritizes generating terms related to the user's profession. Step 3: The translation unit translates the text generated by the generation unit. The translation unit can translate the text using, for example, machine translation technology. The translation unit translates the text into the language of the conversation partner. The translation unit translates the text using, for example, a translation algorithm. The translation unit can also estimate the user's emotions and adjust the expression of the translation based on the estimated user emotions. Furthermore, the translation unit can analyze the context of the conversation and provide a more natural translation. For example, if the user is nervous, the translation unit will provide a concise and clear translation. The translation unit will consider the context of the conversation and provide an appropriate translation. The translation unit will refer to the user's past translation history and select the best translation method. Step 4: The delivery unit converts the text translated by the translation unit into audio data and delivers it to the conversation partner. The delivery unit can generate audio data using, for example, speech synthesis technology. The delivery unit generates audio data that mimics the user's voice quality. The delivery unit generates voice that closely matches the user's voice quality using, for example, speech synthesis technology. The delivery unit can also estimate the user's emotions and adjust the method of generating audio data based on the estimated user emotions. Furthermore, the delivery unit can analyze the context of the conversation and generate more natural-sounding voice. For example, the delivery unit generates natural-sounding voice data when the user is relaxed. The delivery unit considers the context of the conversation and generates appropriate voice. The delivery unit refers to the user's past audio data and generates the optimal voice.

[0113] 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 user input for the result of the specific processing. The control unit 46A transmits the audio data indicating 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.

[0114] Data generation model 58 is a form of so-called generative AI (Artificial Intelligence). An example of data generation model 58 is ChatGPT (registered trademark) (Internet search).<URL: https: / / openai.com / blog / chatgpt> Examples of generative AI include text generation AI, image generation AI, and multimodal generation AI. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 is input with prompts containing instructions, and with inference data such as audio data representing speech, text data representing text, and image data representing images (e.g., still image data or video data). The data generation model 58 infers from the input inference data according to the instructions indicated by the prompts, and outputs the inference result in one or more data formats from audio data, text data, and image data. The data generation model 58 includes, for example, text generation AI, image generation AI, and multimodal generation AI. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization. The specific processing unit 290 performs the specific processing described above using the data generation model 58. The data generation model 58 may be a fine-tuned model that outputs inference results from prompts that do not contain instructions, in which case the data generation model 58 can output inference results from prompts that do not contain instructions. In the data processing device 12, etc., there are multiple types of data generation models 58, and the data generation model 58 includes AI other than generative AI. AI other than generative AI includes, for example, linear regression, logistic regression, decision trees, random forests, support vector machines (SVMs), k-means clustering, convolutional neural networks (CNNs), recurrent neural networks (RNNs), generative adversarial networks (GANs), or naive Bayes, and can perform various processes, but is not limited to these examples. Also, the AI ​​may be an AI agent. Furthermore, when the processing of each of the above parts is performed by the AI, the processing may be performed by the AI ​​in part or in whole, but is not limited to this example.Furthermore, processing performed by AI, including generative AI, may be replaced with rule-based processing, and rule-based processing may be replaced with processing performed by AI, including generative AI.

[0115] Furthermore, the processing performed by the data processing system 10 described above is carried out by the specific processing unit 290 of the data processing device 12 or the control unit 46A of the smart device 14, but it may also be carried out by the specific processing unit 290 of the data processing device 12 and the control unit 46A of the smart device 14. In addition, 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.

[0116] Each of the multiple elements described above, including the collection unit, generation unit, translation unit, and delivery unit, is implemented in at least one of the smart device 14 and the data processing device 12. For example, the collection unit can read lip and tongue movements using the camera 42 and sensor technology of the smart device 14. The generation unit is implemented in the specific processing unit 290 of the data processing device 12 and converts the data from the collection unit into text. The translation unit is implemented in the specific processing unit 290 of the data processing device 12 and translates the generated text into the language of the conversation partner. The delivery unit is implemented in the control unit 46A of the smart device 14 and converts the translated text into voice data and delivers it to the conversation partner. The correspondence between each unit and the device or control unit is not limited to the example described above and can be modified in various ways.

[0117] [Second Embodiment] Figure 3 shows an example of the configuration of the data processing system 210 according to the second embodiment.

[0118] As shown in Figure 3, the data processing system 210 includes a data processing device 12 and smart glasses 214. An example of the data processing device 12 is a server.

[0119] The data processing device 12 comprises a computer 22, a database 24, and a communication interface 26. The computer 22 comprises a processor 28, RAM 30, and storage 32. The processor 28, RAM 30, and storage 32 are connected to a bus 34. The database 24 and the communication interface 26 are also connected to the bus 34. The communication interface 26 is connected to a network 54. An example of the network 54 is a WAN and / or LAN.

[0120] The smart glasses 214 include a computer 36, a microphone 238, a speaker 240, a camera 42, and a communication interface 44. The computer 36 includes a processor 46, RAM 48, and storage 50. The processor 46, RAM 48, and storage 50 are connected to a bus 52. The microphone 238, speaker 240, and camera 42 are also connected to the bus 52.

[0121] The microphone 238 receives voice signals from the user and accepts instructions from the user. The microphone 238 captures the voice signals from the user, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio according to the instructions from the processor 46.

[0122] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an image sensor such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, which captures images of the area around the user (for example, an imaging range defined by a field of view equivalent to the field of vision of a typical healthy person).

[0123] Communication interface 44 is connected to network 54. Communication interfaces 44 and 26 are responsible for the exchange of various information between processor 46 and processor 28 via network 54. The exchange of various information between processor 46 and processor 28 using communication interfaces 44 and 26 is performed in a secure manner.

[0124] Figure 4 shows an example of the main functions of the data processing device 12 and the smart glasses 214. As shown in Figure 4, the data processing device 12 performs specific processing by the processor 28. The storage 32 stores the specific processing program 56.

[0125] The processor 28 reads a 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 acting as a specific processing unit 290 according to the specific processing program 56 executed on the RAM 30.

[0126] Storage 32 stores the data generation model 58 and the 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 the user's emotions using the emotion identification model 59 and perform identification processing using the user's emotions. The emotion estimation function (emotion identification function) using the emotion identification model 59 performs various estimations and predictions regarding the user's emotions, including but not limited to these examples. Furthermore, emotion estimation and prediction also include, for example, emotion analysis.

[0127] In the smart glasses 214, specific processing is performed by the processor 46. The storage 50 stores a specific processing program 60. 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 acting as a control unit 46A according to the specific processing program 60 executed on the RAM 48. The smart glasses 214 also have a data generation model 58 and an emotion identification model 59, similar to the data generation model and emotion identification model 59, and can perform processing similar to that of the specific processing unit 290 using these models.

[0128] Furthermore, other devices besides the data processing device 12 may also 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 obtains processing results (such as prediction results) using the data generation model 58 by communicating with the server device that has the data generation model 58. Also, the data processing device 12 may be a server device or a terminal device owned by the user (for example, a mobile phone, robot, home appliance, etc.).

[0129] 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 user input for the result of the specific processing. The control unit 46A transmits the audio data indicating user input acquired by the microphone 238 to the data processing unit 12. In the data processing unit 12, the specific processing unit 290 acquires the audio data.

[0130] The data generation model 58 is a so-called generative AI. An example of a 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 is input with prompts containing instructions, and inference data such as audio data representing speech, text data representing text, and image data representing images (e.g., still image data or video data). The data generation model 58 infers from the input inference data according to the instructions indicated by the prompts, and outputs the inference result in one or more data formats such as audio data, text data, and image data. The data generation model 58 includes, for example, text generation AI, image generation AI, and multimodal generation AI. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization. The specific processing unit 290 performs the specific processing described above using the data generation model 58. The data generation model 58 may be a fine-tuned model that outputs inference results from prompts that do not contain instructions, in which case the data generation model 58 can output inference results from prompts that do not contain instructions. In the data processing device 12, etc., there are multiple types of data generation models 58, and the data generation model 58 includes AI other than generative AI. AI other than generative AI includes, for example, linear regression, logistic regression, decision trees, random forests, support vector machines (SVM), k-means clustering, convolutional neural networks (CNN), recurrent neural networks (RNN), generative adversarial networks (GAN), or naive Bayes, and can perform various processes, but is not limited to these examples. Also, the AI ​​may be an AI agent. Furthermore, when the processing of each part described above is performed by the AI, the processing may be performed by the AI ​​in part or in whole, but is not limited to this example. Also, processing performed by an AI including a generative AI may be replaced by rule-based processing, and rule-based processing may be replaced by processing performed by an AI including a generative AI.

[0131] 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 performed by the specific processing unit 290 of the data processing device 12 or the control unit 46A of the smart glasses 214, but it may also be performed by the specific processing unit 290 of the data processing device 12 and the control unit 46A of the smart glasses 214. In addition, the specific processing unit 290 of the data processing device 12 acquires or collects information necessary for processing from the smart glasses 214 or an external device, and the smart glasses 214 acquires or collects information necessary for processing from the data processing device 12 or an external device.

[0132] Each of the multiple elements described above, including the collection unit, generation unit, translation unit, and delivery unit, is implemented in at least one of the smart glasses 214 and the data processing unit 12. For example, the collection unit can read lip and tongue movements using the camera 42 and sensor technology of the smart glasses 214. The generation unit is implemented in the specific processing unit 290 of the data processing unit 12 and converts the data from the collection unit into text. The translation unit is implemented in the specific processing unit 290 of the data processing unit 12 and translates the generated text into the language of the person being spoken to. The delivery unit is implemented in the control unit 46A of the smart glasses 214 and converts the translated text into audio data and delivers it to the person being spoken to. The correspondence between each unit and the device or control unit is not limited to the example described above and can be modified in various ways.

[0133] [Third Embodiment] Figure 5 shows an example of the configuration of the data processing system 310 according to the third embodiment.

[0134] As shown in Figure 5, the data processing system 310 includes a data processing device 12 and a headset terminal 314. An example of the data processing device 12 is a server.

[0135] The data processing device 12 comprises a computer 22, a database 24, and a communication interface 26. The computer 22 comprises a processor 28, RAM 30, and storage 32. The processor 28, RAM 30, and storage 32 are connected to a bus 34. The database 24 and the communication interface 26 are also connected to the bus 34. The communication interface 26 is connected to a network 54. An example of the network 54 is a WAN and / or LAN.

[0136] The headset terminal 314 includes a computer 36, a microphone 238, a speaker 240, a camera 42, a communication interface 44, and a display 343. The computer 36 includes a processor 46, RAM 48, and storage 50. The processor 46, RAM 48, and storage 50 are connected to a bus 52. The microphone 238, speaker 240, camera 42, and display 343 are also connected to the bus 52.

[0137] The microphone 238 receives voice signals from the user and accepts instructions from the user. The microphone 238 captures the voice signals from the user, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio according to the instructions from the processor 46.

[0138] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an image sensor such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, which captures images of the area around the user (for example, an imaging range defined by a field of view equivalent to the field of vision of a typical healthy person).

[0139] Communication interface 44 is connected to network 54. Communication interfaces 44 and 26 are responsible for the exchange of various information between processor 46 and processor 28 via network 54. The exchange of various information between processor 46 and processor 28 using communication interfaces 44 and 26 is performed in a secure manner.

[0140] Figure 6 shows an example of the main functions of the data processing device 12 and the headset terminal 314. As shown in Figure 6, the data processing device 12 performs specific processing using the processor 28. The storage 32 stores the specific processing program 56.

[0141] The processor 28 reads a 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 acting as a specific processing unit 290 according to the specific processing program 56 executed on the RAM 30.

[0142] Storage 32 stores the data generation model 58 and the 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 the user's emotions using the emotion identification model 59 and perform identification processing using the user's emotions. The emotion estimation function (emotion identification function) using the emotion identification model 59 performs various estimations and predictions regarding the user's emotions, including but not limited to these examples. Furthermore, emotion estimation and prediction also include, for example, emotion analysis.

[0143] In the headset terminal 314, specific processing is performed by the processor 46. The storage 50 stores a specific program 60. The processor 46 reads the specific program 60 from the storage 50 and executes the read specific program 60 on the RAM 48. The specific processing is realized by the processor 46 acting as a control unit 46A according to the specific program 60 executed on the RAM 48. The headset terminal 314 also has a data generation model 58 and an emotion identification model 59, similar to the data generation model and emotion identification model 59, and can perform processing similar to that of the specific processing unit 290 using these models.

[0144] Furthermore, other devices besides the data processing device 12 may also 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 obtains processing results (such as prediction results) using the data generation model 58 by communicating with the server device that has the data generation model 58. Also, the data processing device 12 may be a server device or a terminal device owned by the user (for example, a mobile phone, robot, home appliance, etc.).

[0145] The specific processing unit 290 transmits the result of the specific processing to the headset terminal 314. In the headset terminal 314, the control unit 46A causes the speaker 240 and display 343 to output the result of the specific processing. The microphone 238 acquires audio indicating user input for the result of the specific processing. The control unit 46A transmits the audio data indicating user input acquired by the microphone 238 to the data processing unit 12. In the data processing unit 12, the specific processing unit 290 acquires the audio data.

[0146] The data generation model 58 is a so-called generative AI. An example of a 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 is input with prompts containing instructions, and inference data such as audio data representing speech, text data representing text, and image data representing images (e.g., still image data or video data). The data generation model 58 infers from the input inference data according to the instructions indicated by the prompts, and outputs the inference result in one or more data formats such as audio data, text data, and image data. The data generation model 58 includes, for example, text generation AI, image generation AI, and multimodal generation AI. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization. The specific processing unit 290 performs the specific processing described above using the data generation model 58. The data generation model 58 may be a fine-tuned model that outputs inference results from prompts that do not contain instructions, in which case the data generation model 58 can output inference results from prompts that do not contain instructions. In the data processing device 12, etc., there are multiple types of data generation models 58, and the data generation model 58 includes AI other than generative AI. AI other than generative AI includes, for example, linear regression, logistic regression, decision trees, random forests, support vector machines (SVM), k-means clustering, convolutional neural networks (CNN), recurrent neural networks (RNN), generative adversarial networks (GAN), or naive Bayes, and can perform various processes, but is not limited to these examples. Also, the AI ​​may be an AI agent. Furthermore, when the processing of each part described above is performed by the AI, the processing may be performed by the AI ​​in part or in whole, but is not limited to this example. Also, processing performed by an AI including a generative AI may be replaced by rule-based processing, and rule-based processing may be replaced by processing performed by an AI including a generative AI.

[0147] 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 performed by the specific processing unit 290 of the data processing device 12 or the control unit 46A of the headset terminal 314, but may also be performed by the specific processing unit 290 of the data processing device 12 and the control unit 46A of the headset terminal 314. In addition, the specific processing unit 290 of the data processing device 12 acquires or collects information necessary for processing from the headset terminal 314 or an external device, and the headset terminal 314 acquires or collects information necessary for processing from the data processing device 12 or an external device.

[0148] Each of the multiple elements described above, including the collection unit, generation unit, translation unit, and delivery unit, is implemented in at least one of the headset terminal 314 and the data processing unit 12. For example, the collection unit can read lip and tongue movements using the camera 42 and sensor technology of the headset terminal 314. The generation unit is implemented in the specific processing unit 290 of the data processing unit 12 and converts the data from the collection unit into text. The translation unit is implemented in the specific processing unit 290 of the data processing unit 12 and translates the generated text into the language of the conversation partner. The delivery unit is implemented in the control unit 46A of the headset terminal 314 and converts the translated text into audio data and delivers it to the conversation partner. The correspondence between each unit and the device or control unit is not limited to the example described above and can be modified in various ways.

[0149] [Fourth Embodiment] Figure 7 shows an example of the configuration of the data processing system 410 according to the fourth embodiment.

[0150] As shown in Figure 7, the data processing system 410 includes a data processing device 12 and a robot 414. An example of the data processing device 12 is a server.

[0151] The data processing device 12 comprises a computer 22, a database 24, and a communication interface 26. The computer 22 comprises a processor 28, RAM 30, and storage 32. The processor 28, RAM 30, and storage 32 are connected to a bus 34. The database 24 and the communication interface 26 are also connected to the bus 34. The communication interface 26 is connected to a network 54. An example of the network 54 is a WAN and / or LAN.

[0152] The robot 414 includes a computer 36, a microphone 238, a speaker 240, a camera 42, a communication interface 44, and a controlled object 443. The computer 36 includes a processor 46, RAM 48, and storage 50. The processor 46, RAM 48, and storage 50 are connected to a bus 52. The microphone 238, speaker 240, camera 42, and controlled object 443 are also connected to the bus 52.

[0153] The microphone 238 receives voice signals from the user and accepts instructions from the user. The microphone 238 captures the voice signals from the user, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio according to the instructions from the processor 46.

[0154] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an image sensor such as a CMOS image sensor or CCD image sensor, which captures images of the area around the user (for example, an imaging range defined by a field of view equivalent to the field of vision of a typical healthy person).

[0155] Communication interface 44 is connected to network 54. Communication interfaces 44 and 26 are responsible for the exchange of various information between processor 46 and processor 28 via network 54. The exchange of various information between processor 46 and processor 28 using communication interfaces 44 and 26 is performed in a secure manner.

[0156] The controlled 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 robot 414's emotions can be expressed by controlling these motors. The robot 414's facial expressions can also be expressed by controlling the illumination state of the LEDs in its eyes.

[0157] Figure 8 shows an example of the main functions of the data processing device 12 and the robot 414. As shown in Figure 8, the data processing device 12 performs specific processing using the processor 28. The storage 32 stores the specific processing program 56.

[0158] The processor 28 reads a 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 acting as a specific processing unit 290 according to the specific processing program 56 executed on the RAM 30.

[0159] Storage 32 stores the data generation model 58 and the 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 the user's emotions using the emotion identification model 59 and perform identification processing using the user's emotions. The emotion estimation function (emotion identification function) using the emotion identification model 59 performs various estimations and predictions regarding the user's emotions, including but not limited to these examples. Furthermore, emotion estimation and prediction also include, for example, emotion analysis.

[0160] In robot 414, specific processing is performed by processor 46. A specific program 60 is stored in storage 50. Processor 46 reads the specific program 60 from storage 50 and executes it on RAM 48. The specific processing is achieved by processor 46 acting as a control unit 46A according to the specific program 60 executed on RAM 48. Robot 414 also has data generation model 58 and emotion identification model 59, similar to those of the robot, and can perform processing similar to that of the specific processing unit 290 using these models.

[0161] Furthermore, other devices besides the data processing device 12 may also 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 obtains processing results (such as prediction results) using the data generation model 58 by communicating with the server device that has the data generation model 58. Also, the data processing device 12 may be a server device or a terminal device owned by the user (for example, a mobile phone, robot, home appliance, etc.).

[0162] 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 controlled object 443 to output the result of the specific processing. The microphone 238 acquires audio indicating user input for the result of the specific processing. The control unit 46A transmits the audio data indicating user input acquired by the microphone 238 to the data processing unit 12. In the data processing unit 12, the specific processing unit 290 acquires the audio data.

[0163] The data generation model 58 is a so-called generative AI. An example of a 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 is input with prompts containing instructions, and inference data such as audio data representing speech, text data representing text, and image data representing images (e.g., still image data or video data). The data generation model 58 infers from the input inference data according to the instructions indicated by the prompts, and outputs the inference result in one or more data formats such as audio data, text data, and image data. The data generation model 58 includes, for example, text generation AI, image generation AI, and multimodal generation AI. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization. The specific processing unit 290 performs the specific processing described above using the data generation model 58. The data generation model 58 may be a fine-tuned model that outputs inference results from prompts that do not contain instructions, in which case the data generation model 58 can output inference results from prompts that do not contain instructions. In the data processing device 12, etc., there are multiple types of data generation models 58, and the data generation model 58 includes AI other than generative AI. AI other than generative AI includes, for example, linear regression, logistic regression, decision trees, random forests, support vector machines (SVM), k-means clustering, convolutional neural networks (CNN), recurrent neural networks (RNN), generative adversarial networks (GAN), or naive Bayes, and can perform various processes, but is not limited to these examples. Also, the AI ​​may be an AI agent. Furthermore, when the processing of each part described above is performed by the AI, the processing may be performed by the AI ​​in part or in whole, but is not limited to this example. Also, processing performed by an AI including a generative AI may be replaced by rule-based processing, and rule-based processing may be replaced by processing performed by an AI including a generative AI.

[0164] 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 performed by the specific processing unit 290 of the data processing device 12 or the control unit 46A of the robot 414, but it may also be performed by the specific processing unit 290 of the data processing device 12 and the control unit 46A of the robot 414. In addition, the specific processing unit 290 of the data processing device 12 acquires or collects information necessary for processing from the robot 414 or an external device, and the robot 414 acquires or collects information necessary for processing from the data processing device 12 or an external device.

[0165] Each of the multiple elements described above, including the collection unit, generation unit, translation unit, and delivery unit, is implemented, for example, in at least one of the robot 414 and the data processing unit 12. For example, the collection unit can read lip and tongue movements using the camera 42 and sensor technology of the robot 414. The generation unit is implemented, for example, by the specific processing unit 290 of the data processing unit 12, which converts the data from the collection unit into text. The translation unit is implemented, for example, by the specific processing unit 290 of the data processing unit 12, which translates the generated text into the language of the conversation partner. The delivery unit is implemented, for example, by the control unit 46A of the robot 414, which converts the translated text into audio data and delivers it to the conversation partner. The correspondence between each unit and the device or control unit is not limited to the example described above, and various modifications are possible.

[0166] Furthermore, the emotion identification model 59, acting 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 a specific mapping, which is an emotion map (see Figure 9). Similarly, the emotion identification model 59 may also determine the robot's emotion, and the identification processing unit 290 may perform identification processing using the robot's emotion.

[0167] Figure 9 shows the emotion map 400, in which multiple emotions are mapped. In the emotion map 400, emotions are arranged in concentric circles radiating from the center. The closer to the center of the concentric circles, the more primitive the emotions are located. Further out of the concentric circles, emotions representing states and actions arising from mental states are located. Emotion is a concept that includes feelings and mental states. On the left side of the concentric circles, emotions that are generally generated from reactions occurring in the brain are located. On the right side of the concentric circles, emotions that are generally induced by situational judgment are located. Above and below the concentric circles, emotions that are generally generated from reactions occurring in the brain and induced by situational judgment are located. In addition, the emotion of "pleasure" is located on the upper side of the concentric circles, and the emotion of "displeasure" is located on the lower side. Thus, in the emotion map 400, multiple emotions are mapped based on the structure in which emotions arise, and emotions that are likely to occur simultaneously are mapped close together.

[0168] These emotions are distributed at the 3 o'clock position on the Emotion Map 400, and usually fluctuate between feelings of security and anxiety. In the right half of the Emotion Map 400, situational awareness takes precedence over internal feelings, resulting in a calm impression.

[0169] The inside of the Emotion Map 400 represents inner thoughts, while the outside represents actions. Therefore, the further you go from the outside of the Emotion Map 400, the more visible (expressed in actions) your emotions become.

[0170] Here, human emotions are based on various balances, such as posture and blood sugar levels. When these balances deviate from the ideal, it results in discomfort, and when they approach the ideal, it results in pleasure. Similarly, in robots, cars, and motorcycles, emotions can be created based on various balances, such as posture and battery level. When these balances deviate from the ideal, it results in discomfort, and when they approach the ideal, it results in pleasure. The emotion map can be generated based, for example, on Dr. Mitsuyoshi's emotion map (Research on a system for analyzing brain physiological signals of speech emotion recognition and emotion, Tokushima University, doctoral dissertation: https: / / ci.nii.ac.jp / naid / 500000375379). The left half of the emotion map contains emotions belonging to a region called "response," where sensation is dominant. The right half of the emotion map contains emotions belonging to a region called "situation," where situational awareness is dominant.

[0171] The emotion map defines two emotions that promote learning. One is the emotion around the middle of the negative "repentance" and "reflection" on the situation side. In other words, it is 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 the emotion around the positive "desire" on the reaction side. In other words, it is when the robot has positive feelings such as "I want more" or "I want to know more."

[0172] The emotion identification model 59 inputs user input into a pre-trained neural network, obtains emotion values ​​representing each emotion shown in the emotion map 400, and determines the user's emotion. This neural network is pre-trained based on multiple training data sets, which are combinations of user input and emotion values ​​representing each emotion shown in the emotion map 400. Furthermore, this neural network is trained so that emotions located close together have similar values, as shown in the emotion map 900 in Figure 10. Figure 10 shows an example where multiple emotions such as "reassured," "calm," and "confident" have similar emotion values.

[0173] In the above embodiment, an example was given in which a specific process is performed by a single computer 22. However, the technology of this disclosure is not limited thereto, and a distributed processing method for the specific process may be used, which includes computer 22 and multiple other computers.

[0174] In the above embodiment, an example was given in which the specific processing program 56 is stored in the storage 32, but the technology of this disclosure is not limited thereto. For example, the specific processing program 56 may be stored in a portable, computer-readable, non-temporary storage medium such as a USB (Universal Serial Bus) memory. The specific processing program 56 stored in the non-temporary storage medium is installed in the computer 22 of the data processing device 12. The processor 28 executes specific processing according to the specific processing program 56.

[0175] 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.

[0176] Furthermore, it is not necessary to store the entirety 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 the entirety of the specific processing program 56 in the storage 32; it is acceptable to store only a portion of the specific processing program 56.

[0177] The following types of processors can be used as hardware resources to perform specific processing. Examples of processors include a CPU, a general-purpose processor that functions as a hardware resource to perform specific processing by executing software, i.e., a program. Other examples of processors include dedicated electrical circuits, such as FPGAs (Field-Programmable Gate Arrays), PLDs (Programmable Logic Devices), or ASICs (Application Specific Integrated Circuits), which have circuit configurations specifically designed to perform specific processing. All of these processors have built-in or connected memory, and all of them perform specific processing by using memory.

[0178] The hardware resource that performs a specific process may consist of one of these various processors, or it may consist of 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). Alternatively, the hardware resource that performs a specific process may consist of a single processor.

[0179] Examples of configurations using a single processor include, firstly, a configuration in which one or more CPUs and software are combined to form a single processor, and this processor functions as a hardware resource that performs a specific process. Secondly, there is a configuration using a processor that realizes the functions of the entire system, including multiple hardware resources that perform a specific process, on a single IC chip, as exemplified by SoCs (System-on-a-chip). In this way, a specific process is realized using one or more of the above types of processors as hardware resources.

[0180] Furthermore, the hardware structure of these various processors can more specifically utilize electrical circuits that combine circuit elements such as semiconductor devices. Also, the specific processing described above is merely an example. Therefore, it goes without saying that unnecessary steps can be deleted, new steps added, or the processing order rearranged, as long as it does not deviate from the main purpose.

[0181] Furthermore, although the above-described examples were divided into four embodiments, some or all of these embodiments may be combined. Also, the smart device 14, smart glasses 214, headset terminal 314, and robot 414 are just examples, and they may be combined, or other devices may be used. Also, although the above-described examples were divided into two embodiments, Embodiment 1 and Embodiment 2, these may be combined.

[0182] The descriptions and illustrations presented above are detailed explanations of the technical aspects of this disclosure and are merely examples of the technical aspects. For example, the above descriptions of the structure, function, operation, and effect are examples of the structure, function, operation, and effect of the technical aspects of this disclosure. Therefore, it goes without saying that you may delete unnecessary parts, add new elements, or replace elements in the descriptions and illustrations presented above, as long as you do not deviate from the essence of the technical aspects of this disclosure. Furthermore, in order to avoid confusion and facilitate understanding of the technical aspects of this disclosure, explanations of common technical knowledge and other things that do not require special explanation to enable the implementation of the technical aspects of this disclosure have been omitted from the descriptions and illustrations presented above.

[0183] All documents, patent applications, and technical standards described herein are incorporated by reference to the same extent as if each individual document, patent application, and technical standard were specifically and individually noted to be incorporated by reference.

[0184] (Note 1) A collection unit that reads the user's non-verbal speech, A generation unit that converts the data read by the collection unit into text, A translation unit that translates the text generated by the generation unit, The system includes a delivery unit that converts the text translated by the translation unit into audio data and delivers it to the conversation partner. A system characterized by the following features. (Note 2) The aforementioned collection unit is Read the movements of the lips and tongue The system described in Appendix 1, characterized by the features described herein. (Note 3) The generating unit is It captures the flow of the conversation, generates multiple possible statements, and compares them to select the most appropriate text. The system described in Appendix 1, characterized by the features described herein. (Note 4) The aforementioned translation department, Translate text into the language of the person you are talking to. The system described in Appendix 1, characterized by the features described herein. (Note 5) The aforementioned supply unit is, It generates voice data that mimics the user's voice and delivers it to the person it's talking to. The system described in Appendix 1, characterized by the features described herein. (Note 6) The generating unit is Improve the accuracy of text generation using AI. The system described in Appendix 1, characterized by the features described herein. (Note 7) The aforementioned collection unit is It estimates the user's emotions and adjusts the accuracy of reading silent speech based on the estimated user emotions. The system described in Appendix 1, characterized by the features described herein. (Note 8) The aforementioned collection unit is Analyze the user's past speech patterns and select the optimal reading method. The system described in Appendix 1, characterized by the features described herein. (Note 9) The aforementioned collection unit is When reading silent speech, the system simultaneously analyzes the user's facial expressions and eye movements to improve accuracy. The system described in Appendix 1, characterized by the features described herein. (Note 10) The aforementioned collection unit is It estimates the user's emotions and determines the priority of utterances to read based on the estimated user emotions. The system described in Appendix 1, characterized by the features described herein. (Note 11) The aforementioned collection unit is When reading silent speech, the system filters out user ambient noise to remove noise. The system described in Appendix 1, characterized by the features described herein. (Note 12) The aforementioned collection unit is When reading silent speech, the system analyzes user gestures to obtain supplementary information. The system described in Appendix 1, characterized by the features described herein. (Note 13) The generating unit is The system estimates the user's emotions and adjusts the method of generating suggested responses based on those emotions. The system described in Appendix 1, characterized by the features described herein. (Note 14) The generating unit is When generating suggested phrases, the system refers to the user's past conversation history to generate the most suitable suggestions. The system described in Appendix 1, characterized by the features described herein. (Note 15) The generating unit is When generating suggested speech, the context of the conversation is analyzed to produce more natural-sounding text. The system described in Appendix 1, characterized by the features described herein. (Note 16) The generating unit is The system estimates the user's emotions and prioritizes potential comments based on those emotions. The system described in Appendix 1, characterized by the features described herein. (Note 17) The generating unit is When generating suggested speech, the system takes into account the user's expertise and industry jargon to create the text. The system described in Appendix 1, characterized by the features described herein. (Note 18) The generating unit is When generating potential utterances, the system selects appropriate expressions by considering the user's cultural background. The system described in Appendix 1, characterized by the features described herein. (Note 19) The aforementioned translation department, It estimates the user's emotions and adjusts the translation's expression based on those estimated emotions. The system described in Appendix 1, characterized by the features described herein. (Note 20) The aforementioned translation department, During translation, the context of the conversation is analyzed to provide a more natural translation. The system described in Appendix 1, characterized by the features described herein. (Note 21) The aforementioned translation department, During translation, the system selects the optimal translation method by referring to the user's past translation history. The system described in Appendix 1, characterized by the features described herein. (Note 22) The aforementioned translation department, It estimates the user's emotions and determines translation priorities based on those estimated emotions. The system described in Appendix 1, characterized by the features described herein. (Note 23) The aforementioned translation department, When translating, select appropriate expressions while considering the cultural background of the person you are speaking to. The system described in Appendix 1, characterized by the features described herein. (Note 24) The aforementioned translation department, When translating, we take into account specialized terminology and industry jargon to improve accuracy. The system described in Appendix 1, characterized by the features described herein. (Note 25) The aforementioned supply unit is, It estimates the user's emotions and adjusts the method of generating audio data based on the estimated user emotions. The system described in Appendix 1, characterized by the features described herein. (Note 26) The aforementioned supply unit is, When generating voice data, the system references the user's past voice data to generate the optimal voice. The system described in Appendix 1, characterized by the features described herein. (Note 27) The aforementioned supply unit is, When generating audio data, the context of the conversation is analyzed to produce more natural-sounding audio. The system described in Appendix 1, characterized by the features described herein. (Note 28) The aforementioned supply unit is, It estimates the user's emotions and prioritizes voice data based on the estimated emotions. The system described in Appendix 1, characterized by the features described herein. (Note 29) The aforementioned supply unit is, When generating audio data, the system takes into account the user's voice tone and rhythm to produce natural-sounding audio. The system described in Appendix 1, characterized by the features described herein. (Note 30) The aforementioned supply unit is, When generating audio data, the system takes into account the accent and intonation of the person you are speaking with. The system described in Appendix 1, characterized by the features described herein. [Explanation of symbols]

[0185] 10, 210, 310, 410 Data Processing Systems 12 Data Processing Devices 14 Smart Devices 214 Smart Glasses 314 Headset-type terminal 414 Robots

Claims

1. A collection unit that reads the user's non-verbal speech, A generation unit that converts the data read by the collection unit into text, A translation unit that translates the text generated by the generation unit, The system comprises a delivery unit that converts the text translated by the translation unit into audio data and delivers it to the conversation partner. A system characterized by the following features.

2. The aforementioned collection unit is Read the movements of the lips and tongue The system according to feature 1.

3. The generating unit is It captures the flow of the conversation, generates multiple possible statements, and compares them to select the most appropriate text. The system according to feature 1.

4. The aforementioned translation department, Translate text into the language of the person you are talking to. The system according to feature 1.

5. The aforementioned supply unit is, It generates voice data that mimics the user's voice and delivers it to the person it's talking to. The system according to feature 1.

6. The generating unit is Improve the accuracy of text generation using AI. The system according to feature 1.

7. The aforementioned collection unit is It estimates the user's emotions and adjusts the accuracy of reading silent speech based on the estimated user emotions. The system according to feature 1.

8. The aforementioned collection unit is Analyze the user's past speech patterns and select the optimal reading method. The system according to feature 1.

Images