System

Abstract

An object of the system according to the embodiment is to provide highly accurate translation and background information in real time and to smooth communication.SOLUTION: A system according to an embodiment includes a capture unit, a translation unit, an output unit, a provision unit, and a learning unit. The capturing unit captures a sound. The translation unit translates the voice captured by the capture unit. The output unit outputs the speech translated by the translation unit. The providing unit provides the background information based on the voice output by the output unit. The learning unit learns the feedback of the user based on the background information provided by the providing unit.SELECTED DRAWING: Figure 1

Description

[Technical Field]

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

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

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

[0004] Conventional technologies lack real-time translation accuracy and the ability to provide background information, posing challenges to facilitating communication.

[0005] The system according to the embodiment aims to facilitate smooth communication by providing highly accurate translation and background information in real time. [Means for solving the problem]

[0006] The system according to the embodiment includes a capture unit, a translation unit, an output unit, a provision unit, and a learning unit. The capture unit captures audio. The translation unit translates the audio captured by the capture unit. The output unit outputs the audio translated by the translation unit. The provision unit provides background information based on the audio output by the output unit. The learning unit learns user feedback based on the background information provided by the provision unit. [Effects of the Invention]

[0007] The system according to the embodiment can provide highly accurate translation and background information in real time, facilitating smooth communication. [Brief explanation of the drawings]

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

[0028] (Example 1) A translation support system according to an embodiment of the present invention is a system for converting a language spoken by a user into another language in real time. The translation support system has a function for converting a language spoken by a user into another language in real time, thereby facilitating communication between people who speak different languages. For example, the translation support system can accurately capture expressions and nuances unique to a region or culture and translate appropriately. The translation support system also incorporates sign language and body language as part of the translation to support communication with the hearing impaired and the visually impaired. The translation support system also has a function for providing background information in real time to facilitate communication. For example, the translation support system can improve the accuracy of the translation based on the user's habits, frequency of use, and feedback. This allows the translation support system to convert a language spoken by a user into another language in real time, thereby facilitating communication between people who speak different languages. This allows the translation support system to convert a language spoken by a user into another language in real time, thereby facilitating communication between people who speak different languages. For example, the translation support system can accurately capture expressions and nuances unique to a region or culture and translate appropriately. The translation support system also incorporates sign language and body language as part of the translation to support communication with the hearing impaired and the visually impaired. Additionally, it can provide context in real time to facilitate communication, allowing translation accuracy to be improved based on user habits, usage, and feedback.

[0029] A translation support system according to an embodiment includes a capture unit, a translation unit, an output unit, a provision unit, and a learning unit. The capture unit captures a user's voice. For example, the capture unit captures the user's voice using a microphone. The capture unit can also filter environmental sounds using noise canceling technology to capture clear voice. For example, the capture unit detects ambient noise in real time and captures the voice clearly using noise canceling technology. The translation unit translates the voice captured by the capture unit using a generation AI. The translation unit translates the voice into another language using, for example, a text generation AI (e.g., LLM). The translation unit can also understand expressions and nuances specific to a region or culture and translate appropriately. For example, the translation unit appropriately translates regional slang and cultural idioms. The output unit outputs the voice translated by the translation unit. For example, the output unit outputs the translated voice using a speaker. The output unit can also estimate the user's emotions and adjust the audio output method based on the estimated user's emotions. For example, if the user is nervous, the output unit outputs audio in a calm voice. The providing unit provides background information based on the audio output by the output unit. For example, the providing unit provides background information related to the content of the conversation in real time. For example, if a specific place name or historical event comes up in the conversation, the providing unit immediately provides that information. The learning unit learns user feedback based on the background information provided by the providing unit. The learning unit learns, for example, the user's usage history and feedback to improve translation accuracy. For example, if a specific expression is frequently used, the learning unit prioritizes learning that expression and provides a more natural translation. As a result, the translation support system according to the embodiment can consistently perform processes from audio capture to translation, output, provision of background information, and learning.

[0030] The translation support system includes a recognition unit that recognizes sign language or body language. The recognition unit recognizes sign language or body language. The recognition unit recognizes sign language or body language using, for example, a camera or a sensor. For example, the recognition unit analyzes sign language movements using a camera and converts them into speech or text. The recognition unit can also analyze body language movements using a sensor and convert them into speech or text. For example, the recognition unit uses a sensor to track body movements and recognize sign language or body language. This makes it possible to support communication with the hearing impaired and the visually impaired by recognizing sign language or body language. Some or all of the above-described processing in the recognition unit may be performed using, for example, AI, or may be performed without AI. For example, the recognition unit can input sign language movement data acquired by a camera to a generation AI and have the generation AI convert the sign language movements into speech or text.

[0031] The recognition unit can recognize sign language or body language using a camera or a sensor. The recognition unit, for example, analyzes sign language movements using a camera and converts them into speech or text. For example, the recognition unit can capture sign language movements in real time using a camera, analyze the sign language movements using a generation AI, and convert them into speech or text. The recognition unit can also analyze body language movements using a sensor and convert them into speech or text. For example, the recognition unit can track body movements using a sensor, analyze the body language movements using a generation AI, and convert them into speech or text. In this way, the use of a camera or a sensor improves the accuracy of recognition of sign language or body language. Some or all of the above-mentioned processing in the recognition unit may be performed using, for example, AI, or may be performed without AI. For example, the recognition unit can input sign language movement data captured by a camera to a generation AI and have the generation AI convert the sign language movements into speech or text.

[0032] The translation unit can understand and translate expressions or nuances specific to a region or culture. The translation unit, for example, uses generation AI to understand expressions and nuances specific to a region or culture and translate them appropriately. For example, the translation unit appropriately translates slang and cultural idioms specific to a region. The translation unit can also use generation AI to provide an appropriate translation according to the context. For example, when translating a specific expression, the translation unit provides an appropriate translation according to the situation. This enables a more natural translation by understanding expressions and nuances specific to a region or culture. Some or all of the above-mentioned processing in the translation unit may be performed using, for example, AI, or may be performed without using AI. For example, the translation unit can input data on slang and cultural idioms specific to a region into generation AI and have the generation AI perform an appropriate translation.

[0033] The providing unit can provide background information related to the content of the conversation. For example, the providing unit provides background information related to the content of the conversation in real time. For example, if a specific place name or historical event comes up in the conversation, the providing unit immediately provides that information. The providing unit can also automatically collect and provide background information related to the content of the conversation using the generation AI. For example, the providing unit collects the latest news articles and social media posts from the Internet and provides them as background information related to the content of the conversation. This allows for a deeper understanding of the conversation by providing background information related to the content of the conversation in real time. Some or all of the above-described processing by the providing unit may be performed using, for example, AI, or may be performed without using AI. For example, the providing unit can input background information related to the content of the conversation to the generation AI and cause the generation AI to provide the background information.

[0034] The learning unit can learn the user's usage history or feedback and improve the accuracy of the translation. The learning unit, for example, learns the user's usage history or feedback and improves the accuracy of the translation. For example, if a specific expression is frequently used, the learning unit prioritizes learning that expression and provides a more natural translation. The learning unit can also use a generation AI to learn the user's feedback and improve the translation algorithm. For example, the learning unit updates the translation algorithm based on the user's feedback and improves the accuracy of the translation. In this way, the accuracy of the translation is improved by learning the user's usage history and feedback. Some or all of the above-mentioned processing in the learning unit may be performed using an AI, for example, or may be performed without using an AI. For example, the learning unit can input data on the user's usage history and feedback into the generation AI and cause the generation AI to improve the translation algorithm.

[0035] The capture unit can analyze the user's past voice capture history and select the optimal capture method. The capture unit, for example, analyzes the user's past voice capture history and selects the optimal capture method. For example, the capture unit prioritizes and suggests capture methods (voice, text, etc.) that the user has used in the past. The capture unit can also predict and suggest a capture method to be used in a specific time period based on the user's past capture history. The capture unit can also analyze the user's past capture history and suggest the most efficient capture method. In this way, the optimal capture method can be selected by analyzing the user's past voice capture history. Some or all of the above-described processing in the capture unit may be performed using, for example, AI, or may be performed without using AI. For example, the capture unit can input the user's past capture history data to a generation AI and have the generation AI select the optimal capture method.

[0036] The capture unit can filter the user's current environmental sound to remove noise when capturing audio. For example, the capture unit can filter the user's current environmental sound to remove noise when capturing audio. For example, the capture unit can detect ambient noise in real time and use noise canceling technology to clearly capture audio. The capture unit can also filter noise in a specific frequency band and capture only the user's audio. The capture unit can also analyze the environmental sound and automatically apply optimal noise filtering settings. This enables clear audio capture by filtering the environmental sound and removing noise. Some or all of the above-described processing in the capture unit can be performed using, for example, AI, or without AI. For example, the capture unit can input environmental sound data to a generation AI and have the generation AI execute noise filtering settings.

[0037] The capture unit can automatically adjust capture settings according to the user's speaking speed and tone when capturing audio. For example, the capture unit automatically adjusts capture settings according to the user's speaking speed and tone when capturing audio. For example, if the user speaks quickly, the capture unit adjusts the capture settings to a high speed to accurately capture the audio. Furthermore, if the user speaks softly, the capture unit can increase the sensitivity to capture the audio. Furthermore, the capture unit can automatically apply optimal capture settings according to the user's speaking speed and tone. This enables accurate audio capture by automatically adjusting the capture settings according to the user's speaking speed and tone. Some or all of the above-described processing in the capture unit may be performed using, for example, AI, or may be performed without using AI. For example, the capture unit can input data on the user's speaking speed and tone to a generation AI and cause the generation AI to adjust the capture settings.

[0038] The capture unit can prioritize capturing highly relevant audio by taking into account the user's geographical location information when capturing audio. For example, the capture unit prioritizes capturing highly relevant audio by taking into account the user's geographical location information when capturing audio. For example, when the user is in a specific location, the capture unit prioritizes capturing audio related to that location. The capture unit can also filter and capture relevant audio based on the user's current location. The capture unit can also update the user's geographical location information in real time and capture optimal audio. This allows highly relevant audio to be prioritized by taking the geographical location information into account. Some or all of the above-described processing in the capture unit may be performed using AI, for example, or may be performed without using AI. For example, the capture unit can input the user's geographical location information data to the generation AI and cause the generation AI to capture highly relevant audio.

[0039] The capture unit can analyze the user's social media activity and capture related audio when capturing audio. For example, the capture unit analyzes the user's social media activity and captures related audio when capturing audio. For example, the capture unit analyzes the content of the user's social media posts and captures related audio. The capture unit can also capture related audio by referring to the activity of the user's friends on social media. The capture unit can also capture related audio based on the user's check-in information on social media. In this way, related audio can be captured by analyzing social media activity. Some or all of the above-described processing in the capture unit may be performed using AI, for example, or may be performed without using AI. For example, the capture unit can input the user's social media activity data to a generation AI and cause the generation AI to capture related audio.

[0040] The capture unit can customize the capture method by reflecting the user's past feedback when capturing audio. For example, the capture unit customizes the capture method by reflecting the user's past feedback when capturing audio. For example, the capture unit automatically applies optimal capture settings based on the user's past feedback. The capture unit can also analyze the user's past feedback and customize the capture method. The capture unit can also improve the capture method by referring to the user's past feedback. In this way, the capture method can be customized by reflecting the past feedback. Some or all of the above-described processing in the capture unit may be performed using, for example, AI, or may be performed without using AI. For example, the capture unit can input the user's past feedback data into a generation AI and cause the generation AI to customize the capture method.

[0041] The translation unit can adjust the level of detail of the translation based on the importance of the audio during translation. The translation unit, for example, adjusts the level of detail of the translation based on the importance of the audio during translation. For example, the translation unit provides a detailed translation for important audio. The translation unit can also provide a concise translation for general audio. The translation unit can also automatically adjust the level of detail of the translation according to the importance of the audio. In this way, by adjusting the level of detail of the translation based on the importance of the audio, a detailed translation can be provided for important audio. Some or all of the above-described processing in the translation unit may be performed using, or without, AI, for example. For example, the translation unit can input audio importance data to a generation AI and have the generation AI adjust the level of detail of the translation.

[0042] The translation unit can apply different translation algorithms depending on the category of the audio during translation. For example, the translation unit applies different translation algorithms depending on the category of the audio during translation. For example, the translation unit applies a translation algorithm including technical terms to business conversations. The translation unit can also apply a casual translation algorithm to everyday conversations. The translation unit can also automatically select the optimal translation algorithm depending on the category of the audio. This enables more appropriate translation by applying the optimal translation algorithm depending on the category of the audio. Some or all of the above-mentioned processing in the translation unit may be performed using, for example, AI, or may be performed without using AI. For example, the translation unit can input audio category data to a generation AI and have the generation AI select the optimal translation algorithm.

[0043] The translation unit can improve the accuracy of the translation by referring to the user's past translation results during translation. The translation unit can improve the accuracy of the translation by referring to the user's past translation results during translation, for example. For example, the translation unit provides an optimal translation based on the user's past translation results. The translation unit can also analyze the user's past translation results and improve the translation algorithm. The translation unit can also improve the accuracy of the translation by referring to the user's past translation results. In this way, the accuracy of the translation is improved by referring to the past translation results. Some or all of the above-mentioned processing in the translation unit can be performed using, for example, AI, or can be performed without using AI. For example, the translation unit can input the user's past translation result data into the generation AI and have the generation AI improve the translation algorithm.

[0044] The translation unit can determine the priority of translation based on the time of submission of the audio during translation. The translation unit, for example, determines the priority of translation based on the time of submission of the audio during translation. For example, the translation unit prioritizes translating the most recent audio. The translation unit can also postpone translating audio that was submitted earlier. The translation unit can also automatically determine the priority of translation based on the time of submission of the audio. In this way, by determining the priority of translation based on the time of submission of the audio, the most recent audio can be translated preferentially. Some or all of the above-mentioned processing in the translation unit may be performed using, for example, AI, or may be performed without using AI. For example, the translation unit can input audio submission time data into a generation AI and have the generation AI determine the priority of translation.

[0045] The translation unit can adjust the order of translation based on the relevance of the speech during translation. The translation unit, for example, adjusts the order of translation based on the relevance of the speech during translation. For example, the translation unit prioritizes translating speech that is highly relevant. The translation unit can also postpone translating speech that is less relevant. The translation unit can also automatically adjust the order of translation based on the relevance of the speech. In this way, by adjusting the order of translation based on the relevance of the speech, highly relevant speech can be translated with priority. Some or all of the above-mentioned processing in the translation unit may be performed using AI, for example, or may be performed without using AI. For example, the translation unit can input speech relevance data to a generation AI and have the generation AI adjust the order of translation.

[0046] The translation unit can adjust the use of technical terms in the translation according to the user's level of expertise during translation. For example, the translation unit can adjust the use of technical terms in the translation according to the user's level of expertise during translation. For example, if the user has technical expertise, the translation unit can provide a translation that uses a lot of technical terms. Alternatively, if the user does not have technical expertise, the translation unit can provide a translation that uses simple language. The translation unit can also automatically adjust the use of technical terms in the translation according to the user's level of expertise. This enables more appropriate translation by adjusting the use of technical terms in the translation according to the user's level of expertise. Some or all of the above-described processing in the translation unit can be performed using AI, for example, or without AI. For example, the translation unit can input the user's level of expertise data into a generation AI and have the generation AI execute the use of technical terms.

[0047] The output unit can adjust the level of detail of the output based on the importance of the audio at the time of output. For example, the output unit adjusts the level of detail of the output based on the importance of the audio at the time of output. For example, the output unit provides detailed output for important audio. The output unit can also provide concise output for general audio. The output unit can also automatically adjust the level of detail of the output according to the importance of the audio. In this way, by adjusting the level of detail of the output based on the importance of the audio, detailed output can be provided for important audio. Some or all of the above-described processing in the output unit may be performed using, or without, AI, for example. For example, the output unit can input audio importance data to a generation AI and cause the generation AI to adjust the level of detail of the output.

[0048] The output unit can apply different output algorithms depending on the category of the audio during output. For example, the output unit can apply different output algorithms depending on the category of the audio during output. For example, the output unit can apply an output algorithm including technical terms to business conversations. The output unit can also apply a casual output algorithm to everyday conversations. The output unit can also automatically select the optimal output algorithm depending on the category of the audio. This enables more appropriate audio output by applying the optimal output algorithm depending on the category of the audio. Some or all of the above-mentioned processing in the output unit can be performed using, for example, AI, or can be performed without using AI. For example, the output unit can input audio category data to a generation AI and have the generation AI select the optimal output algorithm.

[0049] The output unit can improve the accuracy of the output by referring to the user's past output results at the time of output. For example, the output unit can improve the accuracy of the output by referring to the user's past output results at the time of output. For example, the output unit provides an optimal output based on the user's past output results. The output unit can also analyze the user's past output results and improve the output algorithm. The output unit can also improve the accuracy of the output by referring to the user's past output results. In this way, the accuracy of the output is improved by referring to the past output results. Some or all of the above-described processing in the output unit can be performed using, for example, AI, or can be performed without using AI. For example, the output unit can input the user's past output result data to the generation AI and cause the generation AI to improve the output algorithm.

[0050] The output unit can determine the output priority based on the time of submission of the audio at the time of output. The output unit, for example, determines the output priority based on the time of submission of the audio at the time of output. For example, the output unit prioritizes output of the most recent audio. The output unit can also postpone audio that has been submitted earlier. The output unit can also automatically determine the output priority based on the time of submission of the audio. In this way, by determining the output priority based on the time of submission of the audio, the most recent audio can be output preferentially. Some or all of the above-mentioned processing in the output unit may be performed using, for example, AI, or may be performed without using AI. For example, the output unit can input audio submission time data to a generation AI and have the generation AI determine the output priority.

[0051] The output unit can adjust the output order based on the relevance of the audio at the time of output. The output unit, for example, adjusts the output order based on the relevance of the audio at the time of output. For example, the output unit prioritizes output of highly relevant audio. The output unit can also postpone output of less relevant audio. The output unit can also automatically adjust the output order based on the relevance of the audio. In this way, by adjusting the output order based on the relevance of the audio, highly relevant audio can be output preferentially. Some or all of the above-described processing in the output unit may be performed using, for example, AI, or may be performed without using AI. For example, the output unit can input audio relevance data to a generation AI and cause the generation AI to adjust the output order.

[0052] The output unit can adjust the use of technical terminology in the output according to the user's level of expertise at the time of output. For example, the output unit can adjust the use of technical terminology in the output according to the user's level of expertise at the time of output. For example, if the user has technical expertise, the output unit can provide output that uses a lot of technical terminology. Alternatively, if the user does not have technical expertise, the output unit can provide output that uses simple language. The output unit can also automatically adjust the use of technical terminology in the output according to the user's level of expertise. This enables more appropriate audio output by adjusting the use of technical terminology in the output according to the user's level of expertise. Some or all of the above-described processing in the output unit can be performed using, for example, AI, or can be performed without AI. For example, the output unit can input the user's level of expertise data to a generation AI and have the generation AI execute the use of technical terminology.

[0053] The providing unit can adjust the level of detail of the background information based on the importance of the conversation when providing the background information. For example, the providing unit adjusts the level of detail of the background information based on the importance of the conversation when providing the background information. For example, the providing unit provides detailed background information for an important conversation. The providing unit can also provide concise background information for a general conversation. The providing unit can also automatically adjust the level of detail of the background information according to the importance of the conversation. In this way, by adjusting the level of detail of the background information based on the importance of the conversation, detailed background information can be provided for an important conversation. Some or all of the above-described processing in the providing unit may be performed using, for example, AI, or may be performed without using AI. For example, the providing unit can input conversation importance data to a generating AI and cause the generating AI to adjust the level of detail of the background information.

[0054] The providing unit can apply different background information provision algorithms depending on the category of the conversation when providing the background information. For example, the providing unit can apply different background information provision algorithms depending on the category of the conversation when providing the background information. For example, the providing unit can apply an algorithm that provides specialized background information to a business conversation. The providing unit can also apply an algorithm that provides casual background information to an everyday conversation. The providing unit can also automatically select an optimal background information provision algorithm depending on the category of the conversation. This allows more appropriate background information to be provided by applying the optimal background information provision algorithm depending on the category of the conversation. Some or all of the above-described processing in the providing unit can be performed using, for example, AI, or can be performed without using AI. For example, the providing unit can input conversation category data to the generation AI and cause the generation AI to select the optimal background information provision algorithm.

[0055] The providing unit can improve the accuracy of the background information provided by the user by referring to the user's past background information provision results when providing the background information. For example, the providing unit can improve the accuracy of the background information provided by the user by referring to the user's past background information provision results when providing the background information. For example, the providing unit provides optimal background information based on the user's past background information provision results. The providing unit can also analyze the user's past background information provision results and improve the provision algorithm. The providing unit can also improve the accuracy of the provision by referring to the user's past background information provision results. In this way, the accuracy of the provision is improved by referring to the past background information provision results. Some or all of the above-described processing by the providing unit can be performed using, for example, AI, or can be performed without using AI. For example, the providing unit can input the user's past background information provision result data into the generation AI and cause the generation AI to improve the provision algorithm.

[0056] The providing unit can determine the priority of the background information based on the submission time of the conversation at the time of providing. The providing unit, for example, determines the priority of the background information based on the submission time of the conversation at the time of providing. For example, the providing unit prioritizes providing background information related to the most recent conversation. The providing unit can also postpone background information related to conversations that were submitted earlier. The providing unit can also automatically determine the priority of the background information based on the submission time of the conversation. In this way, by determining the priority of the background information based on the submission time of the conversation, it is possible to prioritize providing background information related to the most recent conversation. Some or all of the above-mentioned processing in the providing unit may be performed using, for example, AI, or may be performed without using AI. For example, the providing unit can input conversation submission time data to the generation AI and cause the generation AI to determine the priority of the background information.

[0057] The providing unit can adjust the order of background information based on the relevance of the conversation when providing the background information. For example, the providing unit adjusts the order of background information based on the relevance of the conversation when providing the background information. For example, the providing unit prioritizes providing background information related to a highly relevant conversation. The providing unit can also postpone background information related to a less relevant conversation. The providing unit can also automatically adjust the order of background information based on the relevance of the conversation. In this way, by adjusting the order of background information based on the relevance of the conversation, highly relevant background information can be prioritized for provision. Some or all of the above-described processing in the providing unit may be performed using AI, for example, or may be performed without using AI. For example, the providing unit can input conversation relevance data to a generation AI and cause the generation AI to adjust the order of the background information.

[0058] The providing unit can adjust the use of technical terms in the background information according to the user's level of expertise when providing the information. For example, the providing unit can adjust the use of technical terms in the background information according to the user's level of expertise when providing the information. For example, if the user has technical knowledge, the providing unit can provide background information that uses a lot of technical terms. Also, if the user does not have technical knowledge, the providing unit can provide background information that uses simple language. The providing unit can also automatically adjust the use of technical terms in the background information according to the user's level of expertise. This allows more appropriate background information to be provided by adjusting the use of technical terms in the background information according to the user's level of expertise. Some or all of the above-described processing in the providing unit can be performed using AI, for example, or without AI. For example, the providing unit can input the user's level of expertise data into the generation AI and cause the generation AI to use technical terms.

[0059] The learning unit can optimize the learning algorithm by referring to past learning data during learning. The learning unit, for example, optimizes the learning algorithm by referring to past learning data during learning. For example, the learning unit selects an optimal learning algorithm based on past learning data. The learning unit can also analyze past learning data and improve the learning algorithm. The learning unit can also optimize the learning algorithm by referring to past learning data. In this way, the learning algorithm can be optimized by referring to past learning data. Some or all of the above-mentioned processing in the learning unit may be performed using, for example, AI, or may be performed without using AI. For example, the learning unit can input past learning data to a generation AI and cause the generation AI to optimize the learning algorithm.

[0060] The learning unit can update the learning data by reflecting user feedback during learning. For example, the learning unit updates the learning data by reflecting user feedback during learning. For example, the learning unit updates the learning data based on user feedback. The learning unit can also analyze user feedback and improve the learning data. The learning unit can also update the learning data by referring to user feedback. In this way, the learning data can be updated by reflecting user feedback. Some or all of the above-mentioned processing in the learning unit may be performed using AI, for example, or may be performed without using AI. For example, the learning unit can input user feedback data into the generation AI and cause the generation AI to update the learning data.

[0061] The learning unit can weight the learning data based on the time of submission of the audio during learning. The learning unit, for example, weights the learning data based on the time of submission of the audio during learning. For example, the learning unit weights the most recent audio data and prioritizes learning. The learning unit can also weight older audio data lightly. The learning unit can also automatically adjust the weighting of the learning data based on the time of submission of the audio. In this way, by weighting the learning data based on the time of submission of the audio, the most recent audio data can be prioritized for learning. Some or all of the above-described processing in the learning unit may be performed using, for example, AI, or may be performed without using AI. For example, the learning unit can input audio submission time data to a generation AI and have the generation AI perform weighting of the learning data.

[0062] The learning unit can integrate information from different data sources to enrich the training data during learning. For example, the learning unit integrates information from different data sources to enrich the training data during learning. For example, the learning unit integrates information from multiple data sources to enrich the training data. The learning unit can also analyze information from different data sources and select optimal training data. The learning unit can also integrate information from different data sources in real time to update the training data. In this way, the training data can be enriched by integrating information from different data sources. Some or all of the above-described processing in the learning unit may be performed using, for example, AI, or may be performed without using AI. For example, the learning unit can input information from different data sources into a generation AI and cause the generation AI to integrate the information.

[0063] The recognition unit can adjust the level of detail of recognition based on the importance of the sign language or body language during recognition. For example, the recognition unit adjusts the level of detail of recognition based on the importance of the sign language or body language during recognition. For example, the recognition unit provides detailed recognition for important sign language or body language. The recognition unit can also provide concise recognition for general sign language or body language. The recognition unit can also automatically adjust the level of detail of recognition according to the importance of the sign language or body language. In this way, by adjusting the level of detail of recognition based on the importance of the sign language or body language, detailed recognition can be provided for important sign language or body language. Some or all of the above-mentioned processing in the recognition unit may be performed using, for example, AI, or may be performed without using AI. For example, the recognition unit can input importance data of the sign language or body language to the generation AI and cause the generation AI to adjust the level of detail of recognition.

[0064] The recognition unit can apply different recognition algorithms depending on the category of sign language or body language during recognition. For example, the recognition unit can apply different recognition algorithms depending on the category of sign language or body language during recognition. For example, the recognition unit can apply a specialized sign language or body language recognition algorithm to business conversations. The recognition unit can also apply a casual sign language or body language recognition algorithm to everyday conversations. The recognition unit can also automatically select the optimal recognition algorithm depending on the category of sign language or body language. This enables more appropriate recognition by applying the optimal recognition algorithm depending on the category of sign language or body language. Some or all of the above-mentioned processing in the recognition unit can be performed using, for example, AI, or without AI. For example, the recognition unit can input sign language or body language category data to a generation AI and cause the generation AI to select the optimal recognition algorithm.

[0065] The recognition unit can improve the accuracy of recognition by referring to the user's past recognition results during recognition. For example, the recognition unit can improve the accuracy of recognition by referring to the user's past recognition results during recognition. For example, the recognition unit provides optimal recognition based on the user's past recognition results. The recognition unit can also analyze the user's past recognition results and improve the recognition algorithm. The recognition unit can also improve the accuracy of recognition by referring to the user's past recognition results. In this way, the accuracy of recognition is improved by referring to the past recognition results. Some or all of the above-mentioned processing in the recognition unit may be performed using, for example, AI, or may be performed without using AI. For example, the recognition unit can input the user's past recognition result data into the generation AI and cause the generation AI to improve the recognition algorithm.

[0066] The recognition unit can determine the recognition priority based on the time when the sign language or body language was submitted during recognition. The recognition unit, for example, determines the recognition priority based on the time when the sign language or body language was submitted during recognition. For example, the recognition unit prioritizes recognition of the most recent sign language or body language. The recognition unit can also postpone recognition of sign language or body language that was submitted earlier. The recognition unit can also automatically determine the recognition priority based on the time when the sign language or body language was submitted. In this way, by determining the recognition priority based on the time when the sign language or body language was submitted, the most recent sign language or body language can be recognized preferentially. Some or all of the above-mentioned processing in the recognition unit may be performed using, for example, AI, or may be performed without using AI. For example, the recognition unit can input data on the time when the sign language or body language was submitted to the generation AI and cause the generation AI to determine the recognition priority.

[0067] The recognition unit can adjust the order of recognition based on the relevance of the sign languages ​​and body languages ​​during recognition. The recognition unit, for example, adjusts the order of recognition based on the relevance of the sign languages ​​and body languages ​​during recognition. For example, the recognition unit prioritizes recognition of highly relevant sign languages ​​and body languages. The recognition unit can also postpone recognition of less relevant sign languages ​​and body languages. The recognition unit can also automatically adjust the order of recognition based on the relevance of the sign languages ​​and body languages. In this way, by adjusting the order of recognition based on the relevance of the sign languages ​​and body languages, highly relevant sign languages ​​and body languages ​​can be recognized preferentially. Some or all of the above-described processing in the recognition unit may be performed using, for example, AI, or may be performed without using AI. For example, the recognition unit can input relevance data of sign languages ​​and body languages ​​to the generation AI and cause the generation AI to adjust the order of recognition.

[0068] The recognition unit can adjust the use of technical terminology during recognition according to the user's level of expertise. For example, the recognition unit can adjust the use of technical terminology during recognition according to the user's level of expertise. For example, if the user has technical expertise, the recognition unit can provide recognition that uses a lot of technical terminology. Alternatively, if the user does not have technical expertise, the recognition unit can provide recognition that uses simple language. The recognition unit can also automatically adjust the use of technical terminology during recognition according to the user's level of expertise. This enables more appropriate recognition by adjusting the use of technical terminology during recognition according to the user's level of expertise. Some or all of the above-described processing in the recognition unit can be performed using AI, for example, or without AI. For example, the recognition unit can input the user's level of expertise data into a generation AI and have the generation AI execute the use of technical terminology.

[0069] The system according to the embodiment is not limited to the above-described example, and various modifications are possible, for example, as follows.

[0070] The translation support system can also be equipped with a history analysis unit that analyzes the user's past translation history and prioritizes the translation of specific phrases and expressions. For example, work efficiency can be improved by prioritizing the translation of business terms frequently used by the user. Also, if the user has a specific cultural background, expressions specific to that culture can be prioritized for translation. Furthermore, if the user is engaged in a specific specialized field, technical terms related to that field can be prioritized for translation. In this way, by utilizing the user's past translation history, more accurate translations can be provided.

[0071] The translation support system can also include a location information linking unit that acquires the user's real-time location information and reflects information related to that location in the translation. For example, if the user is in a specific country, the system can provide a translation based on the culture and customs of that country. Also, if the user is attending a specific event, the system can prioritize translation of terms and phrases related to that event. Furthermore, if the user is in a tourist spot, the system can also include tourist information related to that location in the translation. In this way, by utilizing the user's location information, the system can provide a translation that is more appropriate to the context.

[0072] The translation support system can also include a social media integration unit that analyzes a user's social media activity and incorporates related information into the translation. For example, if a user frequently posts about a specific topic on social media, terms and phrases related to that topic can be prioritized in the translation. The system can also incorporate related information into the translation based on the activity of the user's friends and followers. Furthermore, location-related information can be incorporated into the translation based on the user's social media check-in information. This allows for more personalized translations by utilizing the user's social media activity.

[0073] The translation support system may further include a feedback analysis unit that analyzes past user feedback to improve translation accuracy. For example, the translation of specific expressions or terms may be improved based on feedback previously provided by the user. The translation support system may also analyze user feedback to optimize the translation algorithm. Furthermore, the translation priority may be adjusted based on user feedback. In this way, more accurate translations may be provided by utilizing user feedback.

[0074] The translation support system may further include a terminology adjustment unit that estimates the user's level of expertise and adjusts the use of terminology in the translation based on the estimated level of expertise. For example, if the user has expertise, a translation that uses a lot of terminology may be provided. On the other hand, if the user does not have expertise, a translation that uses simple language may be provided. Furthermore, the use of terminology in the translation may be automatically adjusted according to the user's level of expertise. This allows the system to provide a translation that matches the user's level of expertise.

[0075] The processing flow of the first embodiment will be briefly explained below.

[0076] Step 1: The capture unit captures the user's voice. The capture unit may use, for example, a microphone to capture the user's voice. The capture unit may also use noise canceling technology to filter out ambient sounds and capture clear voice. For example, the capture unit may detect ambient noise in real time and use noise canceling technology to capture clear voice. Step 2: The translation unit uses a generation AI to translate the audio captured by the capture unit. For example, the translation unit uses a text generation AI (e.g., LLM) to translate the audio into another language. The translation unit can also understand and appropriately translate expressions and nuances specific to a region or culture. For example, the translation unit appropriately translates regional slang and cultural idioms. Step 3: The output unit outputs the speech translated by the translation unit. The output unit outputs the speech translated using, for example, a speaker. The output unit can also estimate the user's emotions and adjust the speech output method based on the estimated user's emotions. For example, if the user is nervous, the output unit outputs speech in a calm voice. Step 4: The providing unit provides background information based on the audio output by the output unit. For example, the providing unit provides background information related to the content of the conversation in real time. For example, if a specific place name or historical event is mentioned in the conversation, the providing unit immediately provides that information. Step 5: The learning unit learns user feedback based on the background information provided by the providing unit. The learning unit learns, for example, user usage history and feedback to improve translation accuracy. For example, if a particular expression is frequently used, the learning unit will prioritize learning that expression to provide a more natural translation.

[0077] (Example 2) A translation support system according to an embodiment of the present invention is a system for converting a language spoken by a user into another language in real time. The translation support system has a function for converting a language spoken by a user into another language in real time, thereby facilitating communication between people who speak different languages. For example, the translation support system can accurately capture expressions and nuances unique to a region or culture and translate appropriately. The translation support system also incorporates sign language and body language as part of the translation to support communication with the hearing impaired and the visually impaired. The translation support system also has a function for providing background information in real time to facilitate communication. For example, the translation support system can improve the accuracy of the translation based on the user's habits, frequency of use, and feedback. This allows the translation support system to convert a language spoken by a user into another language in real time, thereby facilitating communication between people who speak different languages. This allows the translation support system to convert a language spoken by a user into another language in real time, thereby facilitating communication between people who speak different languages. For example, the translation support system can accurately capture expressions and nuances unique to a region or culture and translate appropriately. The translation support system also incorporates sign language and body language as part of the translation to support communication with the hearing impaired and the visually impaired. Additionally, it can provide context in real time to facilitate communication, allowing translation accuracy to be improved based on user habits, usage, and feedback.

[0078] A translation support system according to an embodiment includes a capture unit, a translation unit, an output unit, a provision unit, and a learning unit. The capture unit captures a user's voice. For example, the capture unit captures the user's voice using a microphone. The capture unit can also filter environmental sounds using noise canceling technology to capture clear voice. For example, the capture unit detects ambient noise in real time and captures the voice clearly using noise canceling technology. The translation unit translates the voice captured by the capture unit using a generation AI. The translation unit translates the voice into another language using, for example, a text generation AI (e.g., LLM). The translation unit can also understand expressions and nuances specific to a region or culture and translate appropriately. For example, the translation unit appropriately translates regional slang and cultural idioms. The output unit outputs the voice translated by the translation unit. For example, the output unit outputs the translated voice using a speaker. The output unit can also estimate the user's emotions and adjust the audio output method based on the estimated user's emotions. For example, if the user is nervous, the output unit outputs audio in a calm voice. The providing unit provides background information based on the audio output by the output unit. For example, the providing unit provides background information related to the content of the conversation in real time. For example, if a specific place name or historical event comes up in the conversation, the providing unit immediately provides that information. The learning unit learns user feedback based on the background information provided by the providing unit. The learning unit learns, for example, the user's usage history and feedback to improve translation accuracy. For example, if a specific expression is frequently used, the learning unit prioritizes learning that expression and provides a more natural translation. As a result, the translation support system according to the embodiment can consistently perform processes from audio capture to translation, output, provision of background information, and learning.

[0079] The translation support system includes a recognition unit that recognizes sign language or body language. The recognition unit recognizes sign language or body language. The recognition unit recognizes sign language or body language using, for example, a camera or a sensor. For example, the recognition unit analyzes sign language movements using a camera and converts them into speech or text. The recognition unit can also analyze body language movements using a sensor and convert them into speech or text. For example, the recognition unit uses a sensor to track body movements and recognize sign language or body language. This makes it possible to support communication with the hearing impaired and the visually impaired by recognizing sign language or body language. Some or all of the above-described processing in the recognition unit may be performed using, for example, AI, or may be performed without AI. For example, the recognition unit can input sign language movement data acquired by a camera to a generation AI and have the generation AI convert the sign language movements into speech or text.

[0080] The recognition unit can recognize sign language or body language using a camera or a sensor. The recognition unit, for example, analyzes sign language movements using a camera and converts them into speech or text. For example, the recognition unit can capture sign language movements in real time using a camera, analyze the sign language movements using a generation AI, and convert them into speech or text. The recognition unit can also analyze body language movements using a sensor and convert them into speech or text. For example, the recognition unit can track body movements using a sensor, analyze the body language movements using a generation AI, and convert them into speech or text. In this way, the use of a camera or a sensor improves the accuracy of recognition of sign language or body language. Some or all of the above-mentioned processing in the recognition unit may be performed using, for example, AI, or may be performed without AI. For example, the recognition unit can input sign language movement data captured by a camera to a generation AI and have the generation AI convert the sign language movements into speech or text.

[0081] The translation unit can understand and translate expressions or nuances specific to a region or culture. The translation unit, for example, uses generation AI to understand expressions and nuances specific to a region or culture and translate them appropriately. For example, the translation unit appropriately translates slang and cultural idioms specific to a region. The translation unit can also use generation AI to provide an appropriate translation according to the context. For example, when translating a specific expression, the translation unit provides an appropriate translation according to the situation. This enables a more natural translation by understanding expressions and nuances specific to a region or culture. Some or all of the above-mentioned processing in the translation unit may be performed using, for example, AI, or may be performed without using AI. For example, the translation unit can input data on slang and cultural idioms specific to a region into generation AI and have the generation AI perform an appropriate translation.

[0082] The providing unit can provide background information related to the content of the conversation. For example, the providing unit provides background information related to the content of the conversation in real time. For example, if a specific place name or historical event comes up in the conversation, the providing unit immediately provides that information. The providing unit can also automatically collect and provide background information related to the content of the conversation using the generation AI. For example, the providing unit collects the latest news articles and social media posts from the Internet and provides them as background information related to the content of the conversation. This allows for a deeper understanding of the conversation by providing background information related to the content of the conversation in real time. Some or all of the above-described processing by the providing unit may be performed using, for example, AI, or may be performed without using AI. For example, the providing unit can input background information related to the content of the conversation to the generation AI and cause the generation AI to provide the background information.

[0083] The learning unit can learn the user's usage history or feedback and improve the accuracy of the translation. The learning unit, for example, learns the user's usage history or feedback and improves the accuracy of the translation. For example, if a specific expression is frequently used, the learning unit prioritizes learning that expression and provides a more natural translation. The learning unit can also use a generation AI to learn the user's feedback and improve the translation algorithm. For example, the learning unit updates the translation algorithm based on the user's feedback and improves the accuracy of the translation. In this way, the accuracy of the translation is improved by learning the user's usage history and feedback. Some or all of the above-mentioned processing in the learning unit may be performed using an AI, for example, or may be performed without using an AI. For example, the learning unit can input data on the user's usage history and feedback into the generation AI and cause the generation AI to improve the translation algorithm.

[0084] The capture unit can estimate the user's emotion and adjust the timing of voice capture based on the estimated user emotion. The capture unit, for example, estimates the user's emotion and adjusts the timing of voice capture based on the estimated user emotion. For example, if the user is nervous, the capture unit delays the timing of voice capture and waits until the user relaxes. Furthermore, if the user is relaxed, the capture unit can immediately capture the voice and perform smooth translation. Furthermore, if the user is in a hurry, the capture unit can advance the timing of voice capture and start translation quickly. This enables more appropriate voice capture by adjusting the timing of voice capture according to the user's emotion. Emotion estimation is realized using an emotion estimation function, for example, an emotion engine or a generation AI. The generation AI can be, but is not limited to, a text generation AI (e.g., LLM) or a multimodal generation AI. Some or all of the above-described processing in the capture unit may be performed using, for example, an AI. For example, the capture unit can input user emotion data into the generation AI and cause the generation AI to adjust the capture timing based on the emotion.

[0085] The capture unit can analyze the user's past voice capture history and select the optimal capture method. The capture unit, for example, analyzes the user's past voice capture history and selects the optimal capture method. For example, the capture unit prioritizes and suggests capture methods (voice, text, etc.) that the user has used in the past. The capture unit can also predict and suggest a capture method to be used in a specific time period based on the user's past capture history. The capture unit can also analyze the user's past capture history and suggest the most efficient capture method. In this way, the optimal capture method can be selected by analyzing the user's past voice capture history. Some or all of the above-described processing in the capture unit may be performed using, for example, AI, or may be performed without using AI. For example, the capture unit can input the user's past capture history data to a generation AI and have the generation AI select the optimal capture method.

[0086] The capture unit can filter the user's current environmental sound to remove noise when capturing audio. For example, the capture unit can filter the user's current environmental sound to remove noise when capturing audio. For example, the capture unit can detect ambient noise in real time and use noise canceling technology to clearly capture audio. The capture unit can also filter noise in a specific frequency band and capture only the user's audio. The capture unit can also analyze the environmental sound and automatically apply optimal noise filtering settings. This enables clear audio capture by filtering the environmental sound and removing noise. Some or all of the above-described processing in the capture unit can be performed using, for example, AI, or without AI. For example, the capture unit can input environmental sound data to a generation AI and have the generation AI execute noise filtering settings.

[0087] The capture unit can automatically adjust capture settings according to the user's speaking speed and tone when capturing audio. For example, the capture unit automatically adjusts capture settings according to the user's speaking speed and tone when capturing audio. For example, if the user speaks quickly, the capture unit adjusts the capture settings to a high speed to accurately capture the audio. Furthermore, if the user speaks softly, the capture unit can increase the sensitivity to capture the audio. Furthermore, the capture unit can automatically apply optimal capture settings according to the user's speaking speed and tone. This enables accurate audio capture by automatically adjusting the capture settings according to the user's speaking speed and tone. Some or all of the above-described processing in the capture unit may be performed using, for example, AI, or may be performed without using AI. For example, the capture unit can input data on the user's speaking speed and tone to a generation AI and cause the generation AI to adjust the capture settings.

[0088] The capture unit can estimate the user's emotions and determine the priority of the audio to be captured based on the estimated user emotions. The capture unit, for example, estimates the user's emotions and determines the priority of the audio to be captured based on the estimated user emotions. For example, when the user is nervous, the capture unit prioritizes capturing important audio. When the user is relaxed, the capture unit can also capture all audio evenly. When the user is in a hurry, the capture unit can also capture important audio in a short time. This allows important audio to be prioritized by determining the priority of the audio based on the user's emotions. Emotion estimation is realized using an emotion estimation function, for example, an emotion engine or a generation AI. The generation AI can be a text generation AI (e.g., LLM) or a multimodal generation AI, but is not limited to such examples. Some or all of the above-described processing in the capture unit may be performed using AI, for example, or without AI. For example, the capture unit can input user emotion data to the generation AI and cause the generation AI to determine the priority of the audio based on the emotion.

[0089] The capture unit can prioritize capturing highly relevant audio by taking into account the user's geographical location information when capturing audio. For example, the capture unit prioritizes capturing highly relevant audio by taking into account the user's geographical location information when capturing audio. For example, when the user is in a specific location, the capture unit prioritizes capturing audio related to that location. The capture unit can also filter and capture relevant audio based on the user's current location. The capture unit can also update the user's geographical location information in real time and capture optimal audio. This allows highly relevant audio to be prioritized by taking the geographical location information into account. Some or all of the above-described processing in the capture unit may be performed using AI, for example, or may be performed without using AI. For example, the capture unit can input the user's geographical location information data to the generation AI and cause the generation AI to capture highly relevant audio.

[0090] The capture unit can analyze the user's social media activity and capture related audio when capturing audio. For example, the capture unit analyzes the user's social media activity and captures related audio when capturing audio. For example, the capture unit analyzes the content of the user's social media posts and captures related audio. The capture unit can also capture related audio by referring to the activity of the user's friends on social media. The capture unit can also capture related audio based on the user's check-in information on social media. In this way, related audio can be captured by analyzing social media activity. Some or all of the above-described processing in the capture unit may be performed using AI, for example, or may be performed without using AI. For example, the capture unit can input the user's social media activity data to a generation AI and cause the generation AI to capture related audio.

[0091] The capture unit can customize the capture method by reflecting the user's past feedback when capturing audio. For example, the capture unit customizes the capture method by reflecting the user's past feedback when capturing audio. For example, the capture unit automatically applies optimal capture settings based on the user's past feedback. The capture unit can also analyze the user's past feedback and customize the capture method. The capture unit can also improve the capture method by referring to the user's past feedback. In this way, the capture method can be customized by reflecting the past feedback. Some or all of the above-described processing in the capture unit may be performed using, for example, AI, or may be performed without using AI. For example, the capture unit can input the user's past feedback data into a generation AI and cause the generation AI to customize the capture method.

[0092] The translation unit can estimate the user's emotions and adjust the translation expression based on the estimated user emotions. For example, the translation unit can estimate the user's emotions and adjust the translation expression based on the estimated user emotions. For example, if the user is nervous, the translation unit can use simple and easy-to-understand expressions. If the user is relaxed, the translation unit can use detailed expressions. If the user is in a hurry, the translation unit can use short and to-the-point expressions. This allows for more appropriate translation by adjusting the translation expression based on the user's emotions. Emotion estimation is achieved using an emotion estimation function, for example, an emotion engine or a generation AI. The generation AI can be a text generation AI (e.g., LLM) or a multimodal generation AI, but is not limited to such examples. Some or all of the above-mentioned processing in the translation unit can be performed using AI, for example, or without AI. For example, the translation unit can input user emotion data into the generation AI and cause the generation AI to adjust the translation expression based on the emotion.

[0093] The translation unit can adjust the level of detail of the translation based on the importance of the audio during translation. The translation unit, for example, adjusts the level of detail of the translation based on the importance of the audio during translation. For example, the translation unit provides a detailed translation for important audio. The translation unit can also provide a concise translation for general audio. The translation unit can also automatically adjust the level of detail of the translation according to the importance of the audio. In this way, by adjusting the level of detail of the translation based on the importance of the audio, a detailed translation can be provided for important audio. Some or all of the above-described processing in the translation unit may be performed using, or without, AI, for example. For example, the translation unit can input audio importance data to a generation AI and have the generation AI adjust the level of detail of the translation.

[0094] The translation unit can apply different translation algorithms depending on the category of the audio during translation. For example, the translation unit applies different translation algorithms depending on the category of the audio during translation. For example, the translation unit applies a translation algorithm including technical terms to business conversations. The translation unit can also apply a casual translation algorithm to everyday conversations. The translation unit can also automatically select the optimal translation algorithm depending on the category of the audio. This enables more appropriate translation by applying the optimal translation algorithm depending on the category of the audio. Some or all of the above-mentioned processing in the translation unit may be performed using, for example, AI, or may be performed without using AI. For example, the translation unit can input audio category data to a generation AI and have the generation AI select the optimal translation algorithm.

[0095] The translation unit can improve the accuracy of the translation by referring to the user's past translation results during translation. The translation unit can improve the accuracy of the translation by referring to the user's past translation results during translation, for example. For example, the translation unit provides an optimal translation based on the user's past translation results. The translation unit can also analyze the user's past translation results and improve the translation algorithm. The translation unit can also improve the accuracy of the translation by referring to the user's past translation results. In this way, the accuracy of the translation is improved by referring to the past translation results. Some or all of the above-mentioned processing in the translation unit can be performed using, for example, AI, or can be performed without using AI. For example, the translation unit can input the user's past translation result data into the generation AI and have the generation AI improve the translation algorithm.

[0096] The translation unit can estimate the user's emotions and adjust the length of the translation based on the estimated user emotions. For example, the translation unit can estimate the user's emotions and adjust the length of the translation based on the estimated user emotions. For example, if the user is nervous, the translation unit can provide a short, concise translation. If the user is relaxed, the translation unit can provide a detailed translation. If the user is in a hurry, the translation unit can provide a short, concise translation. This allows for more appropriate translation by adjusting the length of the translation based on the user's emotions. Emotion estimation is achieved using an emotion estimation function, for example, an emotion engine or a generation AI. The generation AI can be a text generation AI (e.g., LLM) or a multimodal generation AI, but is not limited to such examples. Some or all of the above-described processing in the translation unit can be performed using AI, for example, or without AI. For example, the translation unit can input user emotion data into the generation AI and cause the generation AI to adjust the length of the translation based on the emotion.

[0097] The translation unit can determine the priority of translation based on the time of submission of the audio during translation. The translation unit, for example, determines the priority of translation based on the time of submission of the audio during translation. For example, the translation unit prioritizes translating the most recent audio. The translation unit can also postpone translating audio that was submitted earlier. The translation unit can also automatically determine the priority of translation based on the time of submission of the audio. In this way, by determining the priority of translation based on the time of submission of the audio, the most recent audio can be translated preferentially. Some or all of the above-mentioned processing in the translation unit may be performed using, for example, AI, or may be performed without using AI. For example, the translation unit can input audio submission time data into a generation AI and have the generation AI determine the priority of translation.

[0098] The translation unit can adjust the order of translation based on the relevance of the speech during translation. The translation unit, for example, adjusts the order of translation based on the relevance of the speech during translation. For example, the translation unit prioritizes translating speech that is highly relevant. The translation unit can also postpone translating speech that is less relevant. The translation unit can also automatically adjust the order of translation based on the relevance of the speech. In this way, by adjusting the order of translation based on the relevance of the speech, highly relevant speech can be translated with priority. Some or all of the above-mentioned processing in the translation unit may be performed using AI, for example, or may be performed without using AI. For example, the translation unit can input speech relevance data to a generation AI and have the generation AI adjust the order of translation.

[0099] The translation unit can adjust the use of technical terms in the translation according to the user's level of expertise during translation. For example, the translation unit can adjust the use of technical terms in the translation according to the user's level of expertise during translation. For example, if the user has technical expertise, the translation unit can provide a translation that uses a lot of technical terms. Alternatively, if the user does not have technical expertise, the translation unit can provide a translation that uses simple language. The translation unit can also automatically adjust the use of technical terms in the translation according to the user's level of expertise. This enables more appropriate translation by adjusting the use of technical terms in the translation according to the user's level of expertise. Some or all of the above-described processing in the translation unit can be performed using AI, for example, or without AI. For example, the translation unit can input the user's level of expertise data into a generation AI and have the generation AI execute the use of technical terms.

[0100] The output unit can estimate the user's emotion and adjust the audio output method based on the estimated user's emotion. For example, the output unit can estimate the user's emotion and adjust the audio output method based on the estimated user's emotion. For example, if the user is nervous, the output unit can output audio in a calm voice. If the user is relaxed, the output unit can also output audio in a cheerful voice. If the user is in a hurry, the output unit can also output quick and concise audio. This enables more appropriate audio output by adjusting the audio output method based on the user's emotion. Emotion estimation is realized using an emotion estimation function, for example, using an emotion engine or a generation AI. The generation AI can be a text generation AI (e.g., LLM) or a multimodal generation AI, but is not limited to such examples. Some or all of the above-mentioned processing in the output unit can be performed using, for example, an AI. For example, the output unit can input user's emotion data to the generation AI and cause the generation AI to adjust the audio output method based on the emotion.

[0101] The output unit can adjust the level of detail of the output based on the importance of the audio at the time of output. For example, the output unit adjusts the level of detail of the output based on the importance of the audio at the time of output. For example, the output unit provides detailed output for important audio. The output unit can also provide concise output for general audio. The output unit can also automatically adjust the level of detail of the output according to the importance of the audio. In this way, by adjusting the level of detail of the output based on the importance of the audio, detailed output can be provided for important audio. Some or all of the above-described processing in the output unit may be performed using, or without, AI, for example. For example, the output unit can input audio importance data to a generation AI and cause the generation AI to adjust the level of detail of the output.

[0102] The output unit can apply different output algorithms depending on the category of the audio during output. For example, the output unit can apply different output algorithms depending on the category of the audio during output. For example, the output unit can apply an output algorithm including technical terms to business conversations. The output unit can also apply a casual output algorithm to everyday conversations. The output unit can also automatically select the optimal output algorithm depending on the category of the audio. This enables more appropriate audio output by applying the optimal output algorithm depending on the category of the audio. Some or all of the above-mentioned processing in the output unit can be performed using, for example, AI, or can be performed without using AI. For example, the output unit can input audio category data to a generation AI and have the generation AI select the optimal output algorithm.

[0103] The output unit can improve the accuracy of the output by referring to the user's past output results at the time of output. For example, the output unit can improve the accuracy of the output by referring to the user's past output results at the time of output. For example, the output unit provides an optimal output based on the user's past output results. The output unit can also analyze the user's past output results and improve the output algorithm. The output unit can also improve the accuracy of the output by referring to the user's past output results. In this way, the accuracy of the output is improved by referring to the past output results. Some or all of the above-described processing in the output unit can be performed using, for example, AI, or can be performed without using AI. For example, the output unit can input the user's past output result data to the generation AI and cause the generation AI to improve the output algorithm.

[0104] The output unit can estimate the user's emotion and adjust the length of the audio output based on the estimated user emotion. For example, the output unit can estimate the user's emotion and adjust the length of the audio output based on the estimated user emotion. For example, if the user is nervous, the output unit can provide short, concise audio. If the user is relaxed, the output unit can also provide detailed audio. If the user is in a hurry, the output unit can also provide short, concise audio. This allows for more appropriate audio output by adjusting the length of the audio output based on the user's emotion. The emotion estimation is achieved using an emotion estimation function, for example, an emotion engine or a generation AI. The generation AI can be a text generation AI (e.g., LLM) or a multimodal generation AI, but is not limited to such examples. Some or all of the above-described processing in the output unit can be performed using, for example, an AI, or can be performed without using an AI. For example, the output unit can input user emotion data to the generation AI and cause the generation AI to adjust the length of the audio output based on the emotion.

[0105] The output unit can determine the output priority based on the time of submission of the audio at the time of output. The output unit, for example, determines the output priority based on the time of submission of the audio at the time of output. For example, the output unit prioritizes output of the most recent audio. The output unit can also postpone audio that has been submitted earlier. The output unit can also automatically determine the output priority based on the time of submission of the audio. In this way, by determining the output priority based on the time of submission of the audio, the most recent audio can be output preferentially. Some or all of the above-mentioned processing in the output unit may be performed using, for example, AI, or may be performed without using AI. For example, the output unit can input audio submission time data to a generation AI and have the generation AI determine the output priority.

[0106] The output unit can adjust the output order based on the relevance of the audio at the time of output. The output unit, for example, adjusts the output order based on the relevance of the audio at the time of output. For example, the output unit prioritizes output of highly relevant audio. The output unit can also postpone output of less relevant audio. The output unit can also automatically adjust the output order based on the relevance of the audio. In this way, by adjusting the output order based on the relevance of the audio, highly relevant audio can be output preferentially. Some or all of the above-described processing in the output unit may be performed using, for example, AI, or may be performed without using AI. For example, the output unit can input audio relevance data to a generation AI and cause the generation AI to adjust the output order.

[0107] The output unit can adjust the use of technical terminology in the output according to the user's level of expertise at the time of output. For example, the output unit can adjust the use of technical terminology in the output according to the user's level of expertise at the time of output. For example, if the user has technical expertise, the output unit can provide output that uses a lot of technical terminology. Alternatively, if the user does not have technical expertise, the output unit can provide output that uses simple language. The output unit can also automatically adjust the use of technical terminology in the output according to the user's level of expertise. This enables more appropriate audio output by adjusting the use of technical terminology in the output according to the user's level of expertise. Some or all of the above-described processing in the output unit can be performed using, for example, AI, or can be performed without AI. For example, the output unit can input the user's level of expertise data to a generation AI and have the generation AI execute the use of technical terminology.

[0108] The providing unit can estimate the user's emotion and adjust the method of providing background information based on the estimated user's emotion. For example, the providing unit can estimate the user's emotion and adjust the method of providing background information based on the estimated user's emotion. For example, if the user is nervous, the providing unit can provide simple and easy-to-understand background information. Furthermore, if the user is relaxed, the providing unit can provide detailed background information. Furthermore, if the user is in a hurry, the providing unit can provide short and concise background information. This allows for more appropriate background information to be provided by adjusting the method of providing background information based on the user's emotion. Emotion estimation is achieved using an emotion estimation function, for example, an emotion engine or a generation AI. The generation AI can be a text generation AI (e.g., LLM) or a multimodal generation AI, but is not limited to such examples. Some or all of the above-described processing in the providing unit can be performed using, for example, an AI, or can be performed without using an AI. For example, the providing unit can input user emotion data into the generation AI and cause the generation AI to adjust the method of providing background information based on the emotion.

[0109] The providing unit can adjust the level of detail of the background information based on the importance of the conversation when providing the background information. For example, the providing unit adjusts the level of detail of the background information based on the importance of the conversation when providing the background information. For example, the providing unit provides detailed background information for an important conversation. The providing unit can also provide concise background information for a general conversation. The providing unit can also automatically adjust the level of detail of the background information according to the importance of the conversation. In this way, by adjusting the level of detail of the background information based on the importance of the conversation, detailed background information can be provided for an important conversation. Some or all of the above-described processing in the providing unit may be performed using, for example, AI, or may be performed without using AI. For example, the providing unit can input conversation importance data to a generating AI and cause the generating AI to adjust the level of detail of the background information.

[0110] The providing unit can apply different background information provision algorithms depending on the category of the conversation when providing the background information. For example, the providing unit can apply different background information provision algorithms depending on the category of the conversation when providing the background information. For example, the providing unit can apply an algorithm that provides specialized background information to a business conversation. The providing unit can also apply an algorithm that provides casual background information to an everyday conversation. The providing unit can also automatically select an optimal background information provision algorithm depending on the category of the conversation. This allows more appropriate background information to be provided by applying the optimal background information provision algorithm depending on the category of the conversation. Some or all of the above-described processing in the providing unit can be performed using, for example, AI, or can be performed without using AI. For example, the providing unit can input conversation category data to the generation AI and cause the generation AI to select the optimal background information provision algorithm.

[0111] The providing unit can improve the accuracy of the background information provided by the user by referring to the user's past background information provision results when providing the background information. For example, the providing unit can improve the accuracy of the background information provided by the user by referring to the user's past background information provision results when providing the background information. For example, the providing unit provides optimal background information based on the user's past background information provision results. The providing unit can also analyze the user's past background information provision results and improve the provision algorithm. The providing unit can also improve the accuracy of the provision by referring to the user's past background information provision results. In this way, the accuracy of the provision is improved by referring to the past background information provision results. Some or all of the above-described processing by the providing unit can be performed using, for example, AI, or can be performed without using AI. For example, the providing unit can input the user's past background information provision result data into the generation AI and cause the generation AI to improve the provision algorithm.

[0112] The providing unit can estimate the user's emotion and adjust the length of the background information provided based on the estimated user's emotion. The providing unit, for example, estimates the user's emotion and adjusts the length of the background information provided based on the estimated user's emotion. For example, if the user is nervous, the providing unit can provide short, concise background information. If the user is relaxed, the providing unit can also provide detailed background information. If the user is in a hurry, the providing unit can also provide short, concise background information. This allows for adjusting the length of the background information provided based on the user's emotion, thereby providing more appropriate background information. The emotion estimation is achieved using an emotion estimation function, for example, an emotion engine or a generation AI. The generation AI can be a text generation AI (e.g., LLM) or a multimodal generation AI, but is not limited to such examples. Some or all of the above-described processing in the providing unit can be performed using, for example, an AI, or without an AI. For example, the providing unit can input the user's emotion data into the generation AI and cause the generation AI to adjust the length of the background information provided based on the emotion.

[0113] The providing unit can determine the priority of the background information based on the submission time of the conversation at the time of providing. The providing unit, for example, determines the priority of the background information based on the submission time of the conversation at the time of providing. For example, the providing unit prioritizes providing background information related to the most recent conversation. The providing unit can also postpone background information related to conversations that were submitted earlier. The providing unit can also automatically determine the priority of the background information based on the submission time of the conversation. In this way, by determining the priority of the background information based on the submission time of the conversation, it is possible to prioritize providing background information related to the most recent conversation. Some or all of the above-mentioned processing in the providing unit may be performed using, for example, AI, or may be performed without using AI. For example, the providing unit can input conversation submission time data to the generation AI and cause the generation AI to determine the priority of the background information.

[0114] The providing unit can adjust the order of background information based on the relevance of the conversation when providing the background information. For example, the providing unit adjusts the order of background information based on the relevance of the conversation when providing the background information. For example, the providing unit prioritizes providing background information related to a highly relevant conversation. The providing unit can also postpone background information related to a less relevant conversation. The providing unit can also automatically adjust the order of background information based on the relevance of the conversation. In this way, by adjusting the order of background information based on the relevance of the conversation, highly relevant background information can be prioritized for provision. Some or all of the above-described processing in the providing unit may be performed using AI, for example, or may be performed without using AI. For example, the providing unit can input conversation relevance data to a generation AI and cause the generation AI to adjust the order of the background information.

[0115] The providing unit can adjust the use of technical terms in the background information according to the user's level of expertise when providing the information. For example, the providing unit can adjust the use of technical terms in the background information according to the user's level of expertise when providing the information. For example, if the user has technical knowledge, the providing unit can provide background information that uses a lot of technical terms. Also, if the user does not have technical knowledge, the providing unit can provide background information that uses simple language. The providing unit can also automatically adjust the use of technical terms in the background information according to the user's level of expertise. This allows more appropriate background information to be provided by adjusting the use of technical terms in the background information according to the user's level of expertise. Some or all of the above-described processing in the providing unit can be performed using AI, for example, or without AI. For example, the providing unit can input the user's level of expertise data into the generation AI and cause the generation AI to use technical terms.

[0116] The learning unit can estimate the user's emotions and select training data based on the estimated user emotions. The learning unit, for example, estimates the user's emotions and selects training data based on the estimated user emotions. For example, if the user is nervous, the learning unit selects simple and easy-to-understand training data. Furthermore, if the user is relaxed, the learning unit can select detailed training data. Furthermore, if the user is in a hurry, the learning unit can select short, to-the-point training data. This enables more appropriate training by selecting training data based on the user's emotions. The emotion estimation is realized using an emotion estimation function, for example, an emotion engine or a generation AI. The generation AI can be, but is not limited to, a text generation AI (e.g., LLM) or a multimodal generation AI. Some or all of the above-described processing in the learning unit may be performed using, for example, an AI, or may be performed without using an AI. For example, the learning unit can input the user's emotion data into the generation AI and cause the generation AI to select training data based on the emotion.

[0117] The learning unit can optimize the learning algorithm by referring to past learning data during learning. The learning unit, for example, optimizes the learning algorithm by referring to past learning data during learning. For example, the learning unit selects an optimal learning algorithm based on past learning data. The learning unit can also analyze past learning data and improve the learning algorithm. The learning unit can also optimize the learning algorithm by referring to past learning data. In this way, the learning algorithm can be optimized by referring to past learning data. Some or all of the above-mentioned processing in the learning unit may be performed using, for example, AI, or may be performed without using AI. For example, the learning unit can input past learning data to a generation AI and cause the generation AI to optimize the learning algorithm.

[0118] The learning unit can update the learning data by reflecting user feedback during learning. For example, the learning unit updates the learning data by reflecting user feedback during learning. For example, the learning unit updates the learning data based on user feedback. The learning unit can also analyze user feedback and improve the learning data. The learning unit can also update the learning data by referring to user feedback. In this way, the learning data can be updated by reflecting user feedback. Some or all of the above-mentioned processing in the learning unit may be performed using AI, for example, or may be performed without using AI. For example, the learning unit can input user feedback data into the generation AI and cause the generation AI to update the learning data.

[0119] The learning unit can estimate the user's emotions and adjust the frequency of learning based on the estimated user emotions. The learning unit, for example, estimates the user's emotions and adjusts the frequency of learning based on the estimated user emotions. For example, if the user is nervous, the learning unit reduces the frequency of learning to reduce the user's burden. The learning unit can also increase the frequency of learning to promote efficient learning when the user is relaxed. The learning unit can also adjust the frequency of learning to enable effective learning in a short period of time when the user is in a hurry. This enables more appropriate learning by adjusting the frequency of learning based on the user's emotions. The emotion estimation is realized using an emotion estimation function, for example, an emotion engine or a generation AI. The generation 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-described processing in the learning unit may be performed using, for example, an AI, or without an AI. For example, the learning unit can input the user's emotion data into the generation AI and cause the generation AI to adjust the learning frequency based on the emotion.

[0120] The learning unit can weight the learning data based on the time of submission of the audio during learning. The learning unit, for example, weights the learning data based on the time of submission of the audio during learning. For example, the learning unit weights the most recent audio data and prioritizes learning. The learning unit can also weight older audio data lightly. The learning unit can also automatically adjust the weighting of the learning data based on the time of submission of the audio. In this way, by weighting the learning data based on the time of submission of the audio, the most recent audio data can be prioritized for learning. Some or all of the above-described processing in the learning unit may be performed using, for example, AI, or may be performed without using AI. For example, the learning unit can input audio submission time data to a generation AI and have the generation AI perform weighting of the learning data.

[0121] The learning unit can integrate information from different data sources to enrich the training data during learning. For example, the learning unit integrates information from different data sources to enrich the training data during learning. For example, the learning unit integrates information from multiple data sources to enrich the training data. The learning unit can also analyze information from different data sources and select optimal training data. The learning unit can also integrate information from different data sources in real time to update the training data. In this way, the training data can be enriched by integrating information from different data sources. Some or all of the above-described processing in the learning unit may be performed using, for example, AI, or may be performed without using AI. For example, the learning unit can input information from different data sources into a generation AI and cause the generation AI to integrate the information.

[0122] The recognition unit can estimate the user's emotion and adjust the sign language and body language recognition method based on the estimated user emotion. For example, the recognition unit can estimate the user's emotion and adjust the sign language and body language recognition method based on the estimated user emotion. For example, if the user is nervous, the recognition unit can use a simple and easy-to-understand sign language and body language recognition method. Alternatively, if the user is relaxed, the recognition unit can use a detailed sign language and body language recognition method. Alternatively, if the user is in a hurry, the recognition unit can use a short and concise sign language and body language recognition method. This allows for more appropriate recognition by adjusting the sign language and body language recognition method based on the user's emotion. The emotion estimation is achieved using an emotion estimation function, for example, an emotion engine or a generation AI. The generation AI can be a text generation AI (e.g., LLM) or a multimodal generation AI, but is not limited to these examples. Some or all of the above-described processing in the recognition unit can be performed using, for example, AI, or without AI. For example, the recognition unit can input user emotion data into the generation AI and cause the generation AI to adjust the recognition method based on the emotion.

[0123] The recognition unit can adjust the level of detail of recognition based on the importance of the sign language or body language during recognition. For example, the recognition unit adjusts the level of detail of recognition based on the importance of the sign language or body language during recognition. For example, the recognition unit provides detailed recognition for important sign language or body language. The recognition unit can also provide concise recognition for general sign language or body language. The recognition unit can also automatically adjust the level of detail of recognition according to the importance of the sign language or body language. In this way, by adjusting the level of detail of recognition based on the importance of the sign language or body language, detailed recognition can be provided for important sign language or body language. Some or all of the above-mentioned processing in the recognition unit may be performed using, for example, AI, or may be performed without using AI. For example, the recognition unit can input importance data of the sign language or body language to the generation AI and cause the generation AI to adjust the level of detail of recognition.

[0124] The recognition unit can apply different recognition algorithms depending on the category of sign language or body language during recognition. For example, the recognition unit can apply different recognition algorithms depending on the category of sign language or body language during recognition. For example, the recognition unit can apply a specialized sign language or body language recognition algorithm to business conversations. The recognition unit can also apply a casual sign language or body language recognition algorithm to everyday conversations. The recognition unit can also automatically select the optimal recognition algorithm depending on the category of sign language or body language. This enables more appropriate recognition by applying the optimal recognition algorithm depending on the category of sign language or body language. Some or all of the above-mentioned processing in the recognition unit can be performed using, for example, AI, or without AI. For example, the recognition unit can input sign language or body language category data to a generation AI and cause the generation AI to select the optimal recognition algorithm.

[0125] The recognition unit can improve the accuracy of recognition by referring to the user's past recognition results during recognition. For example, the recognition unit can improve the accuracy of recognition by referring to the user's past recognition results during recognition. For example, the recognition unit provides optimal recognition based on the user's past recognition results. The recognition unit can also analyze the user's past recognition results and improve the recognition algorithm. The recognition unit can also improve the accuracy of recognition by referring to the user's past recognition results. In this way, the accuracy of recognition is improved by referring to the past recognition results. Some or all of the above-mentioned processing in the recognition unit may be performed using, for example, AI, or may be performed without using AI. For example, the recognition unit can input the user's past recognition result data into the generation AI and cause the generation AI to improve the recognition algorithm.

[0126] The recognition unit can estimate the user's emotion and adjust the length of sign language and body language recognition based on the estimated user's emotion. For example, the recognition unit can estimate the user's emotion and adjust the length of sign language and body language recognition based on the estimated user's emotion. For example, if the user is nervous, the recognition unit can provide short and concise sign language and body language recognition. Also, if the user is relaxed, the recognition unit can provide detailed sign language and body language recognition. Also, if the user is in a hurry, the recognition unit can provide short and concise sign language and body language recognition. This allows for more appropriate recognition by adjusting the length of sign language and body language recognition based on the user's emotion. The emotion estimation is achieved using an emotion estimation function, for example, an emotion engine or a generation AI. The generation AI can be a text generation AI (e.g., LLM) or a multimodal generation AI, but is not limited to these examples. Some or all of the above-described processing in the recognition unit can be performed using, for example, AI, or without AI. For example, the recognition unit can input user emotion data to the generation AI and cause the generation AI to adjust the length of recognition based on the emotion.

[0127] The recognition unit can determine the recognition priority based on the time when the sign language or body language was submitted during recognition. The recognition unit, for example, determines the recognition priority based on the time when the sign language or body language was submitted during recognition. For example, the recognition unit prioritizes recognition of the most recent sign language or body language. The recognition unit can also postpone recognition of sign language or body language that was submitted earlier. The recognition unit can also automatically determine the recognition priority based on the time when the sign language or body language was submitted. In this way, by determining the recognition priority based on the time when the sign language or body language was submitted, the most recent sign language or body language can be recognized preferentially. Some or all of the above-mentioned processing in the recognition unit may be performed using, for example, AI, or may be performed without using AI. For example, the recognition unit can input data on the time when the sign language or body language was submitted to the generation AI and cause the generation AI to determine the recognition priority.

[0128] The recognition unit can adjust the order of recognition based on the relevance of the sign languages ​​and body languages ​​during recognition. The recognition unit, for example, adjusts the order of recognition based on the relevance of the sign languages ​​and body languages ​​during recognition. For example, the recognition unit prioritizes recognition of highly relevant sign languages ​​and body languages. The recognition unit can also postpone recognition of less relevant sign languages ​​and body languages. The recognition unit can also automatically adjust the order of recognition based on the relevance of the sign languages ​​and body languages. In this way, by adjusting the order of recognition based on the relevance of the sign languages ​​and body languages, highly relevant sign languages ​​and body languages ​​can be recognized preferentially. Some or all of the above-described processing in the recognition unit may be performed using, for example, AI, or may be performed without using AI. For example, the recognition unit can input relevance data of sign languages ​​and body languages ​​to the generation AI and cause the generation AI to adjust the order of recognition.

[0129] The recognition unit can adjust the use of technical terminology during recognition according to the user's level of expertise. For example, the recognition unit can adjust the use of technical terminology during recognition according to the user's level of expertise. For example, if the user has technical expertise, the recognition unit can provide recognition that uses a lot of technical terminology. Alternatively, if the user does not have technical expertise, the recognition unit can provide recognition that uses simple language. The recognition unit can also automatically adjust the use of technical terminology during recognition according to the user's level of expertise. This enables more appropriate recognition by adjusting the use of technical terminology during recognition according to the user's level of expertise. Some or all of the above-described processing in the recognition unit can be performed using AI, for example, or without AI. For example, the recognition unit can input the user's level of expertise data into a generation AI and have the generation AI execute the use of technical terminology. === Hard Collateral 1-1 === Each of the multiple elements, including the capture unit, translation unit, output unit, provision unit, learning unit, and recognition unit, described above, is implemented, for example, in at least one of the smart device 14 and the data processing device 12. For example, the capture unit captures the user's voice using the microphone 38B of the smart device 14 and obtains clear audio using noise cancellation technology. The translation unit is implemented by the specific processing unit 290 of the data processing device 12 and translates the voice into another language using a generative AI. The output unit outputs the translated voice using the speaker 40B of the smart device 14. The provision unit is implemented by the specific processing unit 290 of the data processing device 12 and provides background information related to the content of the conversation in real time. The learning unit is implemented by the specific processing unit 290 of the data processing device 12 and learns from user feedback to improve the accuracy of the translation. The recognition unit recognizes sign language and body language using the camera 42 of the smart device 14 and converts it into voice or text. The capture unit estimates the user's emotions and adjusts the timing of voice capture based on the emotions. === Hard Collateral 1-2 === Each of the multiple elements, including the capture unit, translation unit, output unit, provision unit, learning unit, and recognition unit, described above, is implemented, for example, in at least one of the smart glasses 214 and the data processing device 12. For example, the capture unit captures the user's voice using the microphone 238 of the smart glasses 214 and obtains clear voice using noise-canceling technology. The translation unit is implemented by the specific processing unit 290 of the data processing device 12 and translates the voice into another language using generative AI. The output unit outputs the translated voice using the speaker 240 of the smart glasses 214. The provision unit is implemented by the specific processing unit 290 of the data processing device 12 and provides background information related to the content of the conversation in real time. The learning unit is implemented by the specific processing unit 290 of the data processing device 12 and learns from user feedback to improve the accuracy of the translation. The recognition unit recognizes sign language and body language using the camera 42 of the smart glasses 214 and converts it into voice or text. The capture unit estimates the user's emotions and adjusts the timing of voice capture based on the emotions. === Hard Collateral 1-3 === Each of the multiple elements, including the capture unit, translation unit, output unit, provision unit, learning unit, and recognition unit, described above, is implemented, for example, in at least one of the headset-type terminal 314 and the data processing device 12. For example, the capture unit captures the user's voice using the microphone 238 of the headset-type terminal 314 and obtains clear voice using noise-canceling technology. The translation unit is implemented by the specific processing unit 290 of the data processing device 12 and translates the voice into another language using a generative AI. The output unit outputs the translated voice using the speaker 240 of the headset-type terminal 314. The provision unit is implemented by the specific processing unit 290 of the data processing device 12 and provides background information related to the content of the conversation in real time. The learning unit is implemented by the specific processing unit 290 of the data processing device 12 and learns from user feedback to improve the accuracy of the translation. The recognition unit recognizes sign language and body language using the camera 42 of the headset-type terminal 314 and converts it into voice or text. The capture unit estimates the user's emotions and adjusts the timing of voice capture based on the emotions. === Hard Collateral 1-4 === Each of the multiple elements, including the capture unit, translation unit, output unit, provision unit, learning unit, and recognition unit, described above, is implemented, for example, by at least one of the robot 414 and the data processing device 12. For example, the capture unit captures the user's voice using the microphone 238 of the robot 414 and obtains clear audio using noise cancellation technology. The translation unit is implemented by the specific processing unit 290 of the data processing device 12 and translates the voice into another language using generative AI. The output unit outputs the translated voice using the speaker 240 of the robot 414. The provision unit is implemented by the specific processing unit 290 of the data processing device 12 and provides background information related to the content of the conversation in real time. The learning unit is implemented by the specific processing unit 290 of the data processing device 12 and learns from user feedback to improve the accuracy of the translation. The recognition unit recognizes sign language and body language using the camera 42 of the robot 414 and converts it into voice or text. The capture unit estimates the user's emotions and adjusts the timing of voice capture based on the emotions.

[0130] The system according to the embodiment is not limited to the above-described example, and various modifications are possible, for example, as follows.

[0131] The translation support system can further include a tone adjustment unit that estimates the user's emotions and adjusts the tone of the translation based on the estimated emotions. For example, if the user is angry, the tone of the translation can be made gentler to ease tension in the conversation. Similarly, if the user is sad, the tone of the translation can be made gentler to achieve communication that is sensitive to the user's emotions. Furthermore, if the user is excited, the tone of the translation can be made calmer to promote a calm conversation. This makes it possible to adjust the tone according to the user's emotions, resulting in more appropriate communication.

[0132] The translation support system can also be equipped with a history analysis unit that analyzes the user's past translation history and prioritizes the translation of specific phrases and expressions. For example, work efficiency can be improved by prioritizing the translation of business terms frequently used by the user. Also, if the user has a specific cultural background, expressions specific to that culture can be prioritized for translation. Furthermore, if the user is engaged in a specific specialized field, technical terms related to that field can be prioritized for translation. In this way, by utilizing the user's past translation history, more accurate translations can be provided.

[0133] The translation support system can also include a location information linking unit that acquires the user's real-time location information and reflects information related to that location in the translation. For example, if the user is in a specific country, the system can provide a translation based on the culture and customs of that country. Also, if the user is attending a specific event, the system can prioritize translation of terms and phrases related to that event. Furthermore, if the user is in a tourist spot, the system can also include tourist information related to that location in the translation. In this way, by utilizing the user's location information, the system can provide a translation that is more appropriate to the context.

[0134] The translation support system can further include a detail level adjustment unit that estimates the user's emotions and adjusts the level of detail of the translation based on the estimated emotions. For example, if the user is relaxed, providing a detailed translation can promote deep understanding. If the user is in a hurry, providing a concise translation can support quick communication. Furthermore, if the user is nervous, providing a translation that focuses on the main points can reduce stress. This makes it possible to adjust the level of detail of the translation according to the user's emotions, resulting in a more appropriate translation.

[0135] The translation support system can also include a social media integration unit that analyzes a user's social media activity and incorporates related information into the translation. For example, if a user frequently posts about a specific topic on social media, terms and phrases related to that topic can be prioritized in the translation. The system can also incorporate related information into the translation based on the activity of the user's friends and followers. Furthermore, location-related information can be incorporated into the translation based on the user's social media check-in information. This allows for more personalized translations by utilizing the user's social media activity.

[0136] The translation support system may further include an expression adjustment unit that estimates the user's emotions and adjusts the translation expression method based on the estimated emotions. For example, if the user is nervous, simple and easy-to-understand expressions may be used. If the user is relaxed, detailed expressions may be used. If the user is in a hurry, short and to the point expressions may be used. In this way, by adjusting the translation expression method based on the user's emotions, a more appropriate translation may be provided.

[0137] The translation support system may further include a feedback analysis unit that analyzes past user feedback to improve translation accuracy. For example, the translation of specific expressions or terms may be improved based on feedback previously provided by the user. The translation support system may also analyze user feedback to optimize the translation algorithm. Furthermore, the translation priority may be adjusted based on user feedback. In this way, more accurate translations may be provided by utilizing user feedback.

[0138] The translation support system may further include a length adjustment unit that estimates the user's emotions and adjusts the length of the translation based on the estimated emotions. For example, if the user is nervous, a short, concise translation may be provided. If the user is relaxed, a detailed translation may be provided. Furthermore, if the user is in a hurry, a short, concise translation may be provided. In this way, by adjusting the length of the translation based on the user's emotions, a more appropriate translation may be provided.

[0139] The translation support system may further include a terminology adjustment unit that estimates the user's level of expertise and adjusts the use of terminology in the translation based on the estimated level of expertise. For example, if the user has expertise, a translation that uses a lot of terminology may be provided. On the other hand, if the user does not have expertise, a translation that uses simple language may be provided. Furthermore, the use of terminology in the translation may be automatically adjusted according to the user's level of expertise. This allows the system to provide a translation that matches the user's level of expertise.

[0140] The translation support system can further include a priority determination unit that estimates the user's emotions and determines the priority of translations based on the estimated emotions. For example, if the user is nervous, important translations can be provided with priority. If the user is relaxed, all translations can be provided equally. Furthermore, if the user is in a hurry, important translations can be provided in a short amount of time. In this way, by determining the priority of translations based on the user's emotions, important translations can be provided with priority.

[0141] The processing flow of the second embodiment will be briefly explained below.

[0142] Step 1: The capture unit captures the user's voice. The capture unit may use, for example, a microphone to capture the user's voice. The capture unit may also use noise canceling technology to filter out ambient sounds and capture clear voice. For example, the capture unit may detect ambient noise in real time and use noise canceling technology to capture clear voice. Step 2: The translation unit uses a generation AI to translate the audio captured by the capture unit. For example, the translation unit uses a text generation AI (e.g., LLM) to translate the audio into another language. The translation unit can also understand and appropriately translate expressions and nuances specific to a region or culture. For example, the translation unit appropriately translates regional slang and cultural idioms. Step 3: The output unit outputs the speech translated by the translation unit. The output unit outputs the speech translated using, for example, a speaker. The output unit can also estimate the user's emotions and adjust the speech output method based on the estimated user's emotions. For example, if the user is nervous, the output unit outputs speech in a calm voice. Step 4: The providing unit provides background information based on the audio output by the output unit. For example, the providing unit provides background information related to the content of the conversation in real time. For example, if a specific place name or historical event is mentioned in the conversation, the providing unit immediately provides that information. Step 5: The learning unit learns user feedback based on the background information provided by the providing unit. The learning unit learns, for example, user usage history and feedback to improve translation accuracy. For example, if a particular expression is frequently used, the learning unit will prioritize learning that expression to provide a more natural translation.

[0143] The specific processing unit 290 transmits the result of the specific processing to the smart device 14. In the smart device 14, the control unit 46A causes the output device 40 to output the result of the specific processing. The microphone 38B acquires audio indicating a user input regarding the result of the specific processing. The control unit 46A transmits audio data indicating the user input acquired by the microphone 38B to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the audio data.

[0144] The data generation model 58 is a so-called generative AI (Artificial Intelligence). An example of the data generation model 58 is ChatGPT (registered trademark) (Internet search engine).<URL: https: / / openai.com / blog / chatgpt> Examples of generative AIs include the data generation model 58, such as a neural network model (e.g., a neural network model), and a neural network model (e.g., a neural network model). The data generation model 58 is obtained by performing deep learning on a neural network. A prompt including an instruction is input to the data generation model 58, and inference data such as voice data indicating speech, text data indicating text, and image data indicating an image is also input to the data generation model 58. The data generation model 58 performs inference on the input inference data in accordance with the instruction indicated by the prompt and outputs the inference result in a data format such as voice data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization. The specification processing unit 290 performs the above-mentioned specification processing using the data generation model 58. The data generation model 58 may be a fine-tuned model so as to output an inference result from a prompt that does not include an instruction. In this case, the data generation model 58 can output an inference result from a prompt that does not include an instruction. The data processing device 12 and the like include multiple types of data generation models 58, and the data generation model 58 includes AIs other than the generative AI. The AI ​​other than the generative AI may be, for example, linear regression, logistic regression, decision tree, random forest, support vector machine (SVM), k-means clustering, convolutional neural network (CNN), recurrent neural network (RNN), generative adversarial network (GAN), or naive Bayes, and can perform various processes, but is not limited to these examples. The AI ​​may also be an AI agent. When the processes of each of the above-mentioned parts are performed by AI, the processes may be performed in part or entirely by AI, but are not limited to these examples. The processes performed by AI, including the generative AI, may be replaced with rule-based processes.

[0145] Furthermore, the processing by the data processing system 10 described above is executed by the specific processing unit 290 of the data processing device 12 or the control unit 46A of the smart device 14, but may also be executed by the specific processing unit 290 of the data processing device 12 and the control unit 46A of the smart device 14. Furthermore, the specific processing unit 290 of the data processing device 12 acquires or collects information necessary for processing from the smart device 14 or an external device, and the smart device 14 acquires or collects information necessary for processing from the data processing device 12 or an external device.

[0146] The correspondence between each part and the device or control part is not limited to the example described above, and various modifications are possible.

[0147] [Second embodiment] FIG. 3 shows an example of the configuration of a data processing system 210 according to the second embodiment.

[0148] 3, the data processing system 210 includes the data processing device 12 and smart glasses 214. An example of the data processing device 12 is a server.

[0149] The data processing device 12 includes a computer 22, a database 24, and a communication I / F 26. The computer 22 includes a processor 28, a RAM 30, and a storage 32. The processor 28, RAM 30, and storage 32 are connected to a bus 34. The database 24 and the communication I / F 26 are also connected to the bus 34. The communication I / F 26 is connected to a network 54. Examples of the network 54 include a WAN and / or a LAN.

[0150] The smart glasses 214 include a computer 36, a microphone 238, a speaker 240, a camera 42, and a communication I / F 44. The computer 36 includes a processor 46, a RAM 48, and a storage 50. The processor 46, the RAM 48, and the storage 50 are connected to a bus 52. The microphone 238, the speaker 240, and the camera 42 are also connected to the bus 52.

[0151] The microphone 238 receives instructions and the like from the user by receiving voice uttered by the user. The microphone 238 captures the voice uttered by the user, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio according to instructions from the processor 46.

[0152] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an imaging element such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, and captures images of the user's surroundings (for example, an imaging range defined by an angle of view equivalent to the field of vision of a typical healthy person).

[0153] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 are responsible for the exchange of various information between the processor 46 and the processor 28 via the network 54. The exchange of various information between the processor 46 and the processor 28 using the communication I / Fs 44 and 26 is carried out in a secure state.

[0154] Fig. 4 shows an example of the main functions of the data processing device 12 and the smart glasses 214. As shown in Fig. 4, in the data processing device 12, a specific process is performed by the processor 28. A specific process program 56 is stored in the storage 32.

[0155] The processor 28 reads the specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific processing is realized by the processor 28 operating as a specific processing unit 290 in accordance with the specific processing program 56 executed on the RAM 30.

[0156] The storage 32 stores a data generation model 58 and an emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290. The identification processing unit 290 can estimate a user's emotion using the emotion identification model 59 and perform identification processing using the user's emotion. The emotion estimation function (emotion identification function) using the emotion identification model 59 performs various estimations and predictions regarding the user's emotion, including estimation and prediction of the user's emotion, but is not limited to these examples. Furthermore, the estimation and prediction of emotion also includes, for example, emotion analysis.

[0157] In the smart glasses 214, the specific processing is performed by the processor 46. A specific processing program 60 is stored in the storage 50. The processor 46 reads the specific processing program 60 from the storage 50 and executes the read specific processing program 60 on the RAM 48. The specific processing is realized by the processor 46 operating as the control unit 46A in accordance with the specific processing program 60 executed on the RAM 48. The smart glasses 214 also have a data generation model and an emotion identification model similar to the data generation model 58 and the emotion identification model 59, and can perform processing similar to that of the specific processing unit 290 using these models.

[0158] Note that a device other than the data processing device 12 may have the data generation model 58. For example, a server device may have the data generation model 58. In this case, the data processing device 12 communicates with the server device having the data generation model 58 to obtain a processing result (such as a prediction result) using the data generation model 58. Furthermore, the data processing device 12 may be a server device, or may be a terminal device (for example, a mobile phone, a robot, a home appliance, etc.) owned by a user.

[0159] The specific processing unit 290 transmits the result of the specific processing to the smart glasses 214. In the smart glasses 214, the control unit 46A causes the speaker 240 to output the result of the specific processing. The microphone 238 acquires audio indicating a user input regarding the result of the specific processing. The control unit 46A transmits audio data indicating the user input acquired by the microphone 238 to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the audio data.

[0160] The data generation model 58 is a so-called generative AI. An example of the data generation model 58 is a generative AI such as ChatGPT. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 receives a prompt containing an instruction, as well as inference data such as voice data representing speech, text data representing text, and image data representing an image. The data generation model 58 performs inference on the input inference data in accordance with the instruction indicated by the prompt and outputs the inference result in a data format such as voice data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization. The identification processing unit 290 performs the above-mentioned identification processing using the data generation model 58. The data generation model 58 may be a fine-tuned model so as to output an inference result from a prompt that does not include an instruction. In this case, the data generation model 58 can output an inference result from a prompt that does not include an instruction. The data processing device 12 and the like include multiple types of data generation models 58, and the data generation model 58 includes AIs other than the generative AI. The AI ​​other than the generative AI may be, for example, linear regression, logistic regression, decision tree, random forest, support vector machine (SVM), k-means clustering, convolutional neural network (CNN), recurrent neural network (RNN), generative adversarial network (GAN), or naive Bayes, and can perform various processes, but is not limited to these examples. The AI ​​may also be an AI agent. When the processes of each of the above-mentioned parts are performed by AI, the processes may be performed in part or entirely by AI, but are not limited to these examples. The processes performed by AI, including the generative AI, may be replaced with rule-based processes.

[0161] The data processing system 210 according to the second embodiment performs the same processing as the data processing system 10 according to the first embodiment. The processing by the data processing system 210 is executed by the specific processing unit 290 of the data processing device 12 or the control unit 46A of the smart glasses 214, but may also be executed by the specific processing unit 290 of the data processing device 12 and the control unit 46A of the smart glasses 214. Furthermore, the specific processing unit 290 of the data processing device 12 acquires or collects information required for processing from the smart glasses 214 or an external device, etc., and the smart glasses 214 acquires or collects information required for processing from the data processing device 12 or an external device, etc.

[0162] The correspondence between each part and the device or control part is not limited to the example described above, and various modifications are possible.

[0163] [Third embodiment] FIG. 5 shows an example of the configuration of a data processing system 310 according to the third embodiment.

[0164] 5, the data processing system 310 includes the data processing device 12 and a headset terminal 314. An example of the data processing device 12 is a server.

[0165] The data processing device 12 includes a computer 22, a database 24, and a communication I / F 26. The computer 22 includes a processor 28, a RAM 30, and a storage 32. The processor 28, RAM 30, and storage 32 are connected to a bus 34. The database 24 and the communication I / F 26 are also connected to the bus 34. The communication I / F 26 is connected to a network 54. Examples of the network 54 include a WAN and / or a LAN.

[0166] The headset type terminal 314 includes a computer 36, a microphone 238, a speaker 240, a camera 42, a communication I / F 44, and a display 343. The computer 36 includes a processor 46, a RAM 48, and a storage 50. The processor 46, the RAM 48, and the storage 50 are connected to a bus 52. The microphone 238, the speaker 240, the camera 42, and the display 343 are also connected to the bus 52.

[0167] The microphone 238 receives instructions and the like from the user by receiving voice uttered by the user. The microphone 238 captures the voice uttered by the user, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio according to instructions from the processor 46.

[0168] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an imaging element such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, and captures images of the user's surroundings (for example, an imaging range defined by an angle of view equivalent to the field of vision of a typical healthy person).

[0169] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 are responsible for the exchange of various information between the processor 46 and the processor 28 via the network 54. The exchange of various information between the processor 46 and the processor 28 using the communication I / Fs 44 and 26 is carried out in a secure state.

[0170] Fig. 6 shows an example of the main functions of the data processing device 12 and the headset type terminal 314. As shown in Fig. 6, in the data processing device 12, a specific process is performed by the processor 28. A specific process program 56 is stored in the storage 32.

[0171] The processor 28 reads the specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific processing is realized by the processor 28 operating as a specific processing unit 290 in accordance with the specific processing program 56 executed on the RAM 30.

[0172] The storage 32 stores a data generation model 58 and an emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290. The identification processing unit 290 can estimate a user's emotion using the emotion identification model 59 and perform identification processing using the user's emotion. The emotion estimation function (emotion identification function) using the emotion identification model 59 performs various estimations and predictions regarding the user's emotion, including estimation and prediction of the user's emotion, but is not limited to these examples. Furthermore, the estimation and prediction of emotion also includes, for example, emotion analysis.

[0173] In the headset type terminal 314, the identification process is performed by the processor 46. A identification program 60 is stored in the storage 50. The processor 46 reads the identification program 60 from the storage 50 and executes the read identification program 60 on the RAM 48. The identification process is realized by the processor 46 operating as a control unit 46A in accordance with the identification program 60 executed on the RAM 48. Note that the headset type terminal 314 has a data generation model and an emotion identification model similar to the data generation model 58 and the emotion identification model 59, and can also perform processing similar to that of the identification processing unit 290 using these models.

[0174] Note that a device other than the data processing device 12 may have the data generation model 58. For example, a server device may have the data generation model 58. In this case, the data processing device 12 communicates with the server device having the data generation model 58 to obtain a processing result (such as a prediction result) using the data generation model 58. Furthermore, the data processing device 12 may be a server device, or may be a terminal device (for example, a mobile phone, a robot, a home appliance, etc.) owned by a user.

[0175] The specific processing unit 290 transmits the result of the specific processing to the headset type terminal 314. In the headset type terminal 314, the control unit 46A causes the speaker 240 and the display 343 to output the result of the specific processing. The microphone 238 acquires audio indicating a user input regarding the result of the specific processing. The control unit 46A transmits audio data indicating the user input acquired by the microphone 238 to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the audio data.

[0176] The data generation model 58 is a so-called generative AI. An example of the data generation model 58 is a generative AI such as ChatGPT. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 receives a prompt containing an instruction, as well as inference data such as voice data representing speech, text data representing text, and image data representing an image. The data generation model 58 performs inference on the input inference data in accordance with the instruction indicated by the prompt and outputs the inference result in a data format such as voice data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization. The identification processing unit 290 performs the above-mentioned identification processing using the data generation model 58. The data generation model 58 may be a fine-tuned model so as to output an inference result from a prompt that does not include an instruction. In this case, the data generation model 58 can output an inference result from a prompt that does not include an instruction. The data processing device 12 and the like include multiple types of data generation models 58, and the data generation model 58 includes AIs other than the generative AI. The AI ​​other than the generative AI may be, for example, linear regression, logistic regression, decision tree, random forest, support vector machine (SVM), k-means clustering, convolutional neural network (CNN), recurrent neural network (RNN), generative adversarial network (GAN), or naive Bayes, and can perform various processes, but is not limited to these examples. The AI ​​may also be an AI agent. When the processes of each of the above-mentioned parts are performed by AI, the processes may be performed in part or entirely by AI, but are not limited to these examples. The processes performed by AI, including the generative AI, may be replaced with rule-based processes.

[0177] The data processing system 310 according to the third embodiment performs the same processing as the data processing system 10 according to the first embodiment. The processing by the data processing system 310 is executed by the specific processing unit 290 of the data processing device 12 or the control unit 46A of the headset type terminal 314, but may also be executed by the specific processing unit 290 of the data processing device 12 and the control unit 46A of the headset type terminal 314. Furthermore, the specific processing unit 290 of the data processing device 12 acquires or collects information required for processing from the headset type terminal 314 or an external device, etc., and the headset type terminal 314 acquires or collects information required for processing from the data processing device 12 or an external device, etc.

[0178] The correspondence between each part and the device or control part is not limited to the example described above, and various modifications are possible.

[0179] [Fourth embodiment] FIG. 7 shows an example of the configuration of a data processing system 410 according to the fourth embodiment.

[0180] 7, a data processing system 410 includes a data processing device 12 and a robot 414. An example of the data processing device 12 is a server.

[0181] The data processing device 12 includes a computer 22, a database 24, and a communication I / F 26. The computer 22 includes a processor 28, a RAM 30, and a storage 32. The processor 28, RAM 30, and storage 32 are connected to a bus 34. The database 24 and the communication I / F 26 are also connected to the bus 34. The communication I / F 26 is connected to a network 54. Examples of the network 54 include a WAN and / or a LAN.

[0182] The robot 414 includes a computer 36, a microphone 238, a speaker 240, a camera 42, a communication I / F 44, and a control target 443. The computer 36 includes a processor 46, a RAM 48, and a storage 50. The processor 46, the RAM 48, and the storage 50 are connected to a bus 52. The microphone 238, the speaker 240, the camera 42, and the control target 443 are also connected to the bus 52.

[0183] The microphone 238 receives instructions and the like from the user by receiving voice uttered by the user. The microphone 238 captures the voice uttered by the user, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio according to instructions from the processor 46.

[0184] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an imaging element such as a CMOS image sensor or a CCD image sensor, and captures images of the user's surroundings (for example, an imaging range defined by an angle of view equivalent to the field of vision of a typical healthy person).

[0185] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 are responsible for the exchange of various information between the processor 46 and the processor 28 via the network 54. The exchange of various information between the processor 46 and the processor 28 using the communication I / Fs 44 and 26 is carried out in a secure state.

[0186] The control object 443 includes a display device, LEDs in the eyes, and motors that drive the arms, hands, and feet. The posture and gestures of the robot 414 are controlled by controlling the motors of the arms, hands, and feet. Some of the emotions of the robot 414 can be expressed by controlling these motors. In addition, the facial expressions of the robot 414 can also be expressed by controlling the light emission state of the LEDs in the eyes of the robot 414.

[0187] Fig. 8 shows an example of the main functions of the data processing device 12 and the robot 414. As shown in Fig. 8, in the data processing device 12, a specific process is performed by the processor 28. A specific process program 56 is stored in the storage 32.

[0188] The processor 28 reads the specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific processing is realized by the processor 28 operating as a specific processing unit 290 in accordance with the specific processing program 56 executed on the RAM 30.

[0189] The storage 32 stores a data generation model 58 and an emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290. The identification processing unit 290 can estimate a user's emotion using the emotion identification model 59 and perform identification processing using the user's emotion. The emotion estimation function (emotion identification function) using the emotion identification model 59 performs various estimations and predictions regarding the user's emotion, including estimation and prediction of the user's emotion, but is not limited to these examples. Furthermore, the estimation and prediction of emotion also includes, for example, emotion analysis.

[0190] In the robot 414, the processor 46 performs the identification process. The storage 50 stores the identification program 60. The processor 46 reads the identification program 60 from the storage 50 and executes the read identification program 60 on the RAM 48. The identification process is realized by the processor 46 operating as the control unit 46A in accordance with the identification program 60 executed on the RAM 48. The robot 414 also has a data generation model and an emotion identification model similar to the data generation model 58 and the emotion identification model 59, and can perform the same process as the identification processing unit 290 using these models.

[0191] Note that a device other than the data processing device 12 may have the data generation model 58. For example, a server device may have the data generation model 58. In this case, the data processing device 12 communicates with the server device having the data generation model 58 to obtain a processing result (such as a prediction result) using the data generation model 58. Furthermore, the data processing device 12 may be a server device, or may be a terminal device (for example, a mobile phone, a robot, a home appliance, etc.) owned by a user.

[0192] The specific processing unit 290 transmits the result of the specific processing to the robot 414. In the robot 414, the control unit 46A causes the speaker 240 and the control target 443 to output the result of the specific processing. The microphone 238 acquires voice indicating a user input regarding the result of the specific processing. The control unit 46A transmits voice data indicating the user input acquired by the microphone 238 to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the voice data.

[0193] The data generation model 58 is a so-called generative AI. An example of the data generation model 58 is a generative AI such as ChatGPT. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 receives a prompt containing an instruction, as well as inference data such as voice data representing speech, text data representing text, and image data representing an image. The data generation model 58 performs inference on the input inference data in accordance with the instruction indicated by the prompt and outputs the inference result in a data format such as voice data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization. The identification processing unit 290 performs the above-mentioned identification processing using the data generation model 58. The data generation model 58 may be a fine-tuned model so as to output an inference result from a prompt that does not include an instruction. In this case, the data generation model 58 can output an inference result from a prompt that does not include an instruction. The data processing device 12 and the like include multiple types of data generation models 58, and the data generation model 58 includes AIs other than the generative AI. The AI ​​other than the generative AI may be, for example, linear regression, logistic regression, decision tree, random forest, support vector machine (SVM), k-means clustering, convolutional neural network (CNN), recurrent neural network (RNN), generative adversarial network (GAN), or naive Bayes, and can perform various processes, but is not limited to these examples. The AI ​​may also be an AI agent. When the processes of each of the above-mentioned parts are performed by AI, the processes may be performed in part or entirely by AI, but are not limited to these examples. The processes performed by AI, including the generative AI, may be replaced with rule-based processes.

[0194] The data processing system 410 according to the fourth embodiment performs the same processing as the data processing system 10 according to the first embodiment. The processing by the data processing system 410 is executed by the specific processing unit 290 of the data processing device 12 or the control unit 46A of the robot 414, but may also be executed by the specific processing unit 290 of the data processing device 12 and the control unit 46A of the robot 414. Furthermore, the specific processing unit 290 of the data processing device 12 acquires or collects information required for processing from the robot 414 or an external device, etc., and the robot 414 acquires or collects information required for processing from the data processing device 12 or an external device, etc.

[0195] The correspondence between each part and the device or control part is not limited to the example described above, and various modifications are possible.

[0196] The emotion identification model 59 as an emotion engine may determine the user's emotion according to a specific mapping. Specifically, the emotion identification model 59 may determine the user's emotion according to an emotion map (see FIG. 9), which is a specific mapping. Similarly, the emotion identification model 59 may determine the robot's emotion, and the identification processing unit 290 may perform identification processing using the robot's emotion.

[0197] FIG. 9 illustrates an emotion map 400 on which multiple emotions are mapped. In the emotion map 400, emotions are arranged in concentric circles radiating from the center. Emotions closer to the center of the concentric circles are more primitive. Emotions representing states and behaviors arising from a state of mind are arranged on the outer edges of the concentric circles. The concept of emotion encompasses both emotions and mental states. Emotions generally generated from reactions occurring in the brain are arranged on the left side of the concentric circles. Emotions generally induced by situational judgment are arranged on the right side of the concentric circles. Emotions generally generated from reactions occurring in the brain and induced by situational judgment are arranged on the upper and lower sides of the concentric circles. Furthermore, the emotion of "pleasure" is arranged on the upper side of the concentric circles, and the emotion of "discomfort" is arranged on the lower side. In this way, in the emotion map 400, multiple emotions are mapped based on the structure by which emotions are generated, and emotions that tend to occur simultaneously are mapped close to each other.

[0198] These emotions are distributed in the 3 o'clock direction on emotion map 400, and typically fluctuate between relief and anxiety. In the right half of emotion map 400, situational awareness dominates over internal sensations, resulting in a sense of calm.

[0199] The inside of emotion map 400 represents what is going on in the mind, and the outside of emotion map 400 represents behavior, so the further you go outside emotion map 400, the more visible the emotions become (the more they are expressed in behavior).

[0200] Human emotions are based on various balances, such as posture and blood sugar levels. When these balances deviate from the ideal, a state of discomfort is expressed, and when they approach the ideal, a state of pleasure is expressed. Emotions can also be created for robots, cars, and motorcycles, based on various balances, such as posture and remaining battery life. When these balances deviate from the ideal, a state of discomfort is expressed, and when they approach the ideal, a state of pleasure is expressed. An emotion map can be generated, for example, based on Dr. Mitsuyoshi's emotion map (Research on speech emotion recognition and brain physiological signal analysis systems for emotions, Tokushima University, doctoral dissertation: https: / / ci.nii.ac.jp / naid / 500000375379). The left half of the emotion map lists emotions belonging to the area called "reaction," where sensation is dominant. The right half of the emotion map lists emotions belonging to the area called "situation," where situational awareness is dominant.

[0201] The emotion map defines two emotions that promote learning. One is a negative emotion on the situation side, around the middle of "repentance" or "reflection." In other words, this occurs when the robot experiences negative emotions such as "I never want to feel this way again" or "I don't want to be scolded again." The other is a positive emotion on the response side, around "desire." In other words, this occurs when the robot experiences positive feelings such as "I want more" or "I want to know more."

[0202] The emotion identification model 59 inputs user input into a pre-trained neural network, obtains emotion values ​​indicating each emotion shown in the emotion map 400, and determines the user's emotion. This neural network is pre-trained based on multiple pieces of training data that are combinations of user input and emotion values ​​indicating each emotion shown in the emotion map 400. Furthermore, this neural network is trained so that emotions that are located close to each other have similar values, as in the emotion map 900 shown in FIG. 10. FIG. 10 shows an example in which multiple emotions, "relieved," "calm," and "reassuring," have similar emotion values.

[0203] In the above embodiment, an example was given in which a specific process is performed by one computer 22, but the technology disclosed herein is not limited to this, and distributed processing of the specific process may be performed by multiple computers including computer 22.

[0204] In the above embodiment, an example in which the specific processing program 56 is stored in the storage 32 has been described, but the technology of the present disclosure is not limited to this. For example, the specific processing program 56 may be stored in a portable, computer-readable, non-transitory storage medium such as a USB (Universal Serial Bus) memory. The specific processing program 56 stored in the non-transitory storage medium is installed in the computer 22 of the data processing device 12. The processor 28 executes the specific processing in accordance with the specific processing program 56.

[0205] 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.

[0206] It is not necessary to store all of the specific processing program 56 in a storage device such as a server connected to the data processing device 12 via the network 54, or to store all of the specific processing program 56 in the storage 32; only a portion of the specific processing program 56 may be stored.

[0207] The hardware resource for executing a specific process can be any of the following types of processors: A processor, for example, is a CPU, which is a general-purpose processor that functions as a hardware resource for executing a specific process by executing software, i.e., a program. A processor also includes a dedicated electrical circuit, such as an FPGA (Field-Programmable Gate Array), a PLD (Programmable Logic Device), or an ASIC (Application Specific Integrated Circuit), which is a processor with a circuit configuration designed specifically for executing a specific process. Each processor has built-in or connected memory, and each processor uses the memory to execute the specific process.

[0208] The hardware resource that executes the specific process may be configured with one of these various processors, or may be configured with a combination of two or more processors of the same or different types (for example, a combination of multiple FPGAs, or a combination of a CPU and an FPGA). Also, the hardware resource that executes the specific process may be a single processor.

[0209] As an example of a system configured with a single processor, first, one processor is configured by combining one or more CPUs and software, and this processor functions as a hardware resource that executes a specific process. Second, there is a system that uses a processor that realizes the functions of an entire system including multiple hardware resources that execute a specific process on a single IC chip, as typified by SoC (System-on-a-chip). In this way, a specific process is realized using one or more of the above-mentioned various processors as hardware resources.

[0210] Furthermore, the hardware structure of these various processors can be, more specifically, an electric circuit that combines circuit elements such as semiconductor devices. The specific processing described above is merely an example. Therefore, it goes without saying that unnecessary steps may be deleted, new steps may be added, or the processing order may be rearranged, without departing from the spirit of the invention.

[0211] In the above example, the first to fourth embodiments have been described separately, but some or all of these embodiments may be combined. The smart device 14, smart glasses 214, headset terminal 314, and robot 414 are merely examples, and they may be combined, or other devices may be used. In the above example, the first and second embodiments have been described separately, but they may be combined.

[0212] The above-described description and illustrations are a detailed explanation of the parts related to the technology of the present disclosure and are merely an example of the technology of the present disclosure. For example, the above description of the configuration, functions, actions, and effects is an explanation of an example of the configuration, functions, actions, and effects of the parts related to the technology of the present disclosure. Therefore, it goes without saying that unnecessary parts may be deleted, new elements may be added, or replacements may be made to the above-described description and illustrations within the scope of the gist of the technology of the present disclosure. Furthermore, to avoid confusion and facilitate understanding of the parts related to the technology of the present disclosure, the above-described description and illustrations omit explanations of common technical knowledge that do not require particular explanation to enable the implementation of the technology of the present disclosure.

[0213] All publications, patent applications, and technical standards mentioned in this specification are herein incorporated by reference to the same extent as if each individual publication, patent application, or technical standard was specifically and individually indicated to be incorporated by reference.

[0214] [Explanation of symbols]

[0215] 10, 210, 310, 410 Data Processing Systems 12 Data Processing Device 14 Smart Devices 214 Smart Glasses 314 Headset-type terminal 414 Robot

Claims

1. a capture unit for capturing audio; a translation unit that translates the voice captured by the capture unit; an output unit that outputs the speech translated by the translation unit; a providing unit that provides background information based on the audio output by the output unit; a learning unit that learns user feedback based on the background information provided by the providing unit. A system characterized by:

2. Equipped with a recognition unit that recognizes sign language or body language 2. The system of claim 1.

3. The recognition unit Recognize sign language or body language using cameras or sensors 3. The system of claim 2.

4. The translation unit Understand and translate regional or culturally specific expressions or nuances 2. The system of claim 1.

5. The providing unit Provide context related to the content of the conversation 2. The system of claim 1.

6. The learning unit Learn from your usage history or feedback to improve translation accuracy 2. The system of claim 1.

7. The capture unit Estimate the user's emotion and adjust the timing of voice capture based on the estimated user emotion.

2. The system of claim 1.

8. The capture unit Analyze the user's past voice capture history and select the optimal capture method 2. The system of claim 1.

9. The capture unit Filters the user's current ambient sounds to remove noise when capturing audio 2. The system of claim 1.

Images