system

Abstract

The system according to the embodiment aims to provide opportunities for daily exposure to foreign languages ​​and to support the acquisition of foreign languages. [Solution] A system according to an embodiment includes a receiving unit, a conversion unit, a reply unit, a reply conversion unit, a speaking unit, a speech conversion unit, a recognition unit, and a recognition conversion unit. The receiving unit receives email. The conversion unit converts the email received by the receiving unit into a foreign language. The reply unit replies based on the email converted by the conversion unit. The reply conversion unit converts the email returned by the reply unit into Japanese. The speaking unit speaks voice. The speech conversion unit converts the voice spoken by the speaking unit into a foreign language. The recognition unit recognizes the voice converted by the speech conversion unit. The recognition conversion unit converts the voice recognized by the recognition unit into Japanese.

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 technology has had the problem that there are few opportunities to come into contact with foreign languages ​​on a daily basis, making it difficult to learn foreign languages.

[0005] The system according to the embodiment aims to provide opportunities for daily exposure to foreign languages ​​and to support the acquisition of foreign languages. [Means for solving the problem]

[0006] The system according to the embodiment includes a receiving unit, a converting unit, a replying unit, a reply conversion unit, a speaking unit, a speech conversion unit, a recognition unit, and a recognition conversion unit. The receiving unit receives email. The conversion unit converts the email received by the receiving unit into a foreign language. The replying unit replies based on the email converted by the conversion unit. The reply conversion unit converts the email returned by the replying unit into Japanese. The speaking unit speaks voice. The speech conversion unit converts the voice spoken by the speaking unit into a foreign language. The recognition unit recognizes the voice converted by the speech conversion unit. The recognition conversion unit converts the voice recognized by the recognition unit into Japanese. [Effects of the Invention]

[0007] The system according to the embodiment can provide opportunities for daily exposure to a foreign language and support the acquisition of the foreign language. [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 foreign language acquisition assistance system according to an embodiment of the present invention provides an environment in which a user is forced to come into contact with a foreign language on a daily basis. When a user receives an email, the email is automatically converted into a foreign language and displayed. When the user replies in the foreign language, the reply is automatically converted into Japanese and sent to the recipient. Furthermore, the system can improve the user's conversational skills by using speech utterances and speech recognition functions. For example, when a user speaks a foreign language, the speech is automatically recognized and displayed as text in the foreign language. Furthermore, when a user listens to foreign language speech, the speech is automatically converted into Japanese and displayed. In this way, the user can be exposed to a foreign language on a daily basis and can naturally acquire the foreign language. For example, when a user receives an email, the email is automatically converted into the foreign language and displayed. When the user replies in the foreign language, the reply is automatically converted into Japanese and sent to the recipient. Furthermore, the system can improve the user's conversational skills by using speech utterances and speech recognition functions. For example, when a user speaks a foreign language, the speech is automatically recognized and displayed as text in the foreign language. Furthermore, when a user listens to foreign language speech, the speech is automatically converted into Japanese and displayed. In this way, the user can be exposed to a foreign language on a daily basis and can naturally acquire the foreign language.In this way, the foreign language acquisition support system allows the user to be exposed to a foreign language on a daily basis and can naturally acquire the foreign language.

[0029] A foreign language learning assistance system according to an embodiment includes a receiving unit, a converting unit, a replying unit, a reply conversion unit, a speaking unit, a speech conversion unit, a recognition unit, and a recognition conversion unit. The receiving unit receives emails received by a user. The receiving unit can, for example, acquire emails from an email server. The conversion unit converts the emails received by the receiving unit into a foreign language. The conversion unit can, for example, convert the content of the email into the foreign language using a text translation engine. The replying unit replies based on the email converted by the conversion unit. The replying unit can, for example, send a reply content entered by the user. The reply conversion unit converts the email replied by the replying unit into Japanese. The reply conversion unit can convert the reply content into Japanese using, for example, a text translation engine. The speech unit allows the user to speak. The speech unit can acquire the user's voice using, for example, a microphone. The speech conversion unit converts the voice spoken by the speaking unit into a foreign language. The speech conversion unit can convert the voice spoken by the speaking unit into a foreign language using, for example, a speech translation engine. The recognition unit recognizes the speech converted by the speech conversion unit. The recognition unit can convert the speech into text using, for example, a speech recognition engine. The recognition conversion unit converts the speech recognized by the recognition unit into Japanese. The recognition conversion unit can convert the text into Japanese using, for example, a text translation engine. As a result, the foreign language acquisition assistance system according to the embodiment allows the user to come into contact with a foreign language on a daily basis and naturally acquire the foreign language.

[0030] The foreign language acquisition assistance system includes a progress management unit that manages the user's learning progress. The progress management unit can, for example, record and manage the content and progress of the user's learning. The progress management unit evaluates the user's learning progress and supports efficient learning. For example, the progress management unit can suggest the next content to study based on the content the user has studied. The progress management unit can also visually display the user's learning progress as a graph or chart. This allows the user to grasp their learning progress at a glance. Furthermore, the progress management unit can synchronize the user's learning progress with other devices. For example, the progress management unit can synchronize with the user's smartphone or tablet and update the learning progress in real time. This allows the user to check the learning progress from any device. In this way, the foreign language acquisition assistance system manages the user's learning progress, enabling efficient learning.

[0031] The foreign language learning assistance system includes a speech feedback unit for improving the accuracy of speech. The speech feedback unit provides feedback to improve the accuracy of the user's speech. For example, the speech feedback unit can evaluate the user's pronunciation and intonation and point out areas for improvement. The speech feedback unit can record the user's speech and play it back for later confirmation. For example, the speech feedback unit can record the user's speech and play back the audio to check the accuracy of the pronunciation. The speech feedback unit can also provide real-time feedback on the user's speech. For example, the speech feedback unit can evaluate the accuracy of the pronunciation and the naturalness of the intonation while the user is speaking and provide instant feedback. Furthermore, the speech feedback unit can provide a training program for improving the accuracy of the user's speech. For example, the speech feedback unit can provide a training program for the user to practice pronunciation, thereby improving the accuracy of the pronunciation and the naturalness of the intonation. As a result, the foreign language learning assistance system improves the accuracy of speech, enabling more natural conversations.

[0032] The conversion unit can convert emails into foreign languages ​​using a generation AI. The generation AI converts email content into foreign languages ​​using advanced natural language processing technologies such as GPT-4 (registered trademark) and Gemini. The generation AI has learned from large amounts of text data and has advanced translation capabilities. For example, the generation AI can understand the context of emails and provide appropriate translations. The generation AI can analyze the content of emails and select natural expressions based on the context. For example, the generation AI can select appropriate business terms for business emails and appropriate slang for casual emails. This improves the accuracy of email foreign language conversion using the generation AI. The generation AI can generate multiple translation candidates based on the content of the email and present them to the user. For example, the generation AI can generate multiple translation candidates based on the content of the email and allow the user to select the optimal translation. This allows the user to select the translation that best suits their preferences. Furthermore, the generation AI can automatically refer to related literature and materials based on the content of the email to improve the accuracy of the translation. For example, the generation AI can automatically search for literature related to the content of the email and incorporate it into the translation. This will improve the accuracy of foreign language translation of emails by using generative AI.

[0033] The conversion unit can convert speech into a foreign language using a generation AI. The generation AI converts speech content into a foreign language using advanced natural language processing technologies such as GPT-4 and Gemini. The generation AI has trained on large amounts of speech data and has advanced translation capabilities. For example, the generation AI can understand the context of the speech and provide appropriate translations. The generation AI can analyze the speech content and select natural expressions based on the context. For example, the generation AI can select appropriate business terms for business conversations and appropriate slang for casual conversations. This improves the accuracy of speech-to-foreign-language conversion. The generation AI can generate multiple translation candidates based on the speech content and present them to the user. For example, the generation AI can generate multiple translation candidates based on the speech content and allow the user to select the optimal translation. This allows the user to select the translation that best suits their preferences. Furthermore, the generation AI can automatically refer to related literature and materials based on the speech content to improve the accuracy of the translation. For example, the generation AI can automatically search for literature related to the speech content and incorporate it into the translation. This will improve the accuracy of converting speech into foreign languages ​​by using generative AI.

[0034] The recognition unit can recognize speech using a generative AI. The generative AI recognizes speech using advanced natural language processing technologies, such as GPT-4 and Gemini. Generative AI has trained on large amounts of speech data and has advanced speech recognition capabilities. For example, the generative AI can understand the context of speech and perform appropriate recognition. It can analyze speech content and select natural expressions based on the context. For example, the generative AI can select appropriate business terms for business conversations and appropriate slang for casual conversations. This improves the accuracy of speech recognition. The generative AI can generate multiple recognition candidates based on the speech content and present them to the user. For example, the generative AI can generate multiple recognition candidates based on the speech content and allow the user to select the most appropriate recognition result. This allows the user to select the recognition result that best suits their preferences. Furthermore, the generative AI can automatically refer to related literature and materials based on the speech content to improve recognition accuracy. For example, the generative AI can automatically search for literature related to the speech content and incorporate it into recognition. This will improve the accuracy of voice recognition by using generative AI.

[0035] The receiving unit can analyze the content of received emails and change the method of notification depending on their importance. For example, the receiving unit can analyze the content of emails using keyword extraction technology and evaluate their importance. For example, the receiving unit can notify emails containing important keywords with a voice notification and other emails with a vibration. The receiving unit can also analyze the context of emails and evaluate their importance. For example, the receiving unit can display business-related emails as a pop-up notification and casual emails in a notification bar. Furthermore, the receiving unit can evaluate the importance based on the email sender information and change the method of notification. For example, the receiving unit can notify emails from important business partners immediately and notify other emails collectively after a certain period of time. This enables efficient email management by prioritizing important emails. Some or all of the above-described processing in the receiving unit can be performed using, or without, AI. For example, the receiving unit can input the content of emails into a generation AI and have the generation AI evaluate their importance.

[0036] The receiving unit can set priorities and adjust the receiving order based on sender information of the received emails. The receiving unit, for example, analyzes the sender information of the emails and sets the priorities. For example, the receiving unit can prioritize receiving emails from important business partners and postpone other emails. The receiving unit can also prioritize receiving emails from family and friends and postpone work-related emails. Furthermore, the receiving unit can prioritize receiving emails from superiors and postpone emails from colleagues. This enables efficient email management by prioritizing receiving emails from important senders. Some or all of the above-mentioned processing in the receiving unit may be performed using, for example, AI, or may be performed without using AI. For example, the receiving unit can input email sender information to a generation AI and have the generation AI set the priorities.

[0037] The receiving unit can analyze the content of received emails and automatically display related past emails. The receiving unit can, for example, analyze the content of the email using keyword extraction technology and search for related past emails. For example, the receiving unit can automatically search for and display past emails related to the content of the received email. The receiving unit can also search for related past emails based on email sender information. For example, the receiving unit can automatically display past emails related to the sender of the received email. Furthermore, the receiving unit can analyze the topic of the email and search for related past emails. For example, the receiving unit can automatically display past emails related to the topic of the received email. This enables efficient email management by automatically displaying related past emails. Some or all of the above-mentioned processing in the receiving unit can be performed using, for example, AI, or can be performed without using AI. For example, the receiving unit can input the content of the email into a generation AI and have the generation AI search for related past emails.

[0038] The receiving unit can automatically generate related tasks based on the content of the received email. For example, the receiving unit analyzes the content of the email using keyword extraction technology and generates related tasks. For example, the receiving unit automatically generates related tasks based on the content of the received email and adds them to a task list. The receiving unit can also generate related tasks based on email sender information. For example, the receiving unit automatically generates tasks related to the sender of the received email. Furthermore, the receiving unit can analyze the topic of the email and generate related tasks. For example, the receiving unit automatically generates tasks related to the topic of the received email. This enables efficient task management by automatically generating related tasks. Some or all of the above-mentioned processing in the receiving unit may be performed using, for example, AI, or may be performed without using AI. For example, the receiving unit can input the content of the email into a generation AI and have the generation AI generate related tasks.

[0039] The conversion unit can appropriately convert technical terms and slang depending on the content of the email. The conversion unit, for example, analyzes the content of the email using keyword extraction technology and appropriately converts technical terms and slang. For example, the conversion unit appropriately converts technical terms in the case of a business email. The conversion unit can also appropriately convert slang in the case of a casual email. Furthermore, the conversion unit can also appropriately convert technical terms in the case of a technical email. This improves the accuracy of the translation by performing appropriate conversion depending on the content of the email. Some or all of the above-mentioned processing in the conversion unit may be performed using, for example, AI, or may be performed without using AI. For example, the conversion unit can input the content of the email into a generation AI and have the generation AI convert technical terms and slang.

[0040] The conversion unit can apply an algorithm for performing a natural translation by taking into account the context of the email. The conversion unit, for example, analyzes the content of the email using context analysis technology and applies an algorithm for performing a natural translation. For example, the conversion unit analyzes the context of the email and performs an appropriate translation. The conversion unit can also select natural expressions based on the context of the email. Furthermore, the conversion unit can also select appropriate vocabulary by taking into account the context of the email. This improves the accuracy of the translation by performing a natural translation that takes into account the context of the email. Some or all of the above-mentioned processing in the conversion unit may be performed using, for example, AI, or may be performed without using AI. For example, the conversion unit can input the content of the email into a generation AI and have the generation AI perform a translation that takes the context into account.

[0041] The conversion unit can present multiple translation candidates depending on the content of the email and allow the user to select one. The conversion unit, for example, analyzes the content of the email using keyword extraction technology and generates multiple translation candidates. For example, the conversion unit generates multiple translation candidates based on the content of the email and presents them to the user. The conversion unit can also perform a final translation based on the translation candidate selected by the user. Furthermore, the conversion unit can present appropriate translation candidates depending on the content of the email. This allows the user to select the optimal translation by presenting multiple translation candidates. Some or all of the above-mentioned processing in the conversion unit may be performed using, for example, AI, or may be performed without using AI. For example, the conversion unit can input the content of the email into a generation AI and have the generation AI generate multiple translation candidates.

[0042] The conversion unit can analyze the content of the email and automatically refer to related literature and materials to improve the accuracy of the translation. For example, the conversion unit can analyze the content of the email using keyword extraction technology and search for related literature and materials. For example, the conversion unit can automatically search for literature related to the content of the email and reflect that in the translation. The conversion unit can also automatically refer to materials related to the content of the email to improve the accuracy of the translation. Furthermore, the conversion unit can refer to appropriate literature and materials based on the content of the email. This improves the accuracy of the translation by referring to related literature and materials. Some or all of the above-mentioned processing in the conversion unit can be performed using, for example, AI, or can be performed without using AI. For example, the conversion unit can input the content of the email into a generation AI and have the generation AI search for related literature and materials.

[0043] The reply unit can adjust the level of detail in the reply depending on the importance of the reply content. For example, the reply unit can analyze the reply content using keyword extraction technology and evaluate the importance. For example, the reply unit can write important replies in detail and other replies in a concise manner. The reply unit can also analyze the context of the reply content and evaluate the importance. For example, the reply unit can write important replies in detail and other replies in a concise manner. Furthermore, the reply unit can evaluate the importance based on sender information of the reply content and adjust the level of detail in the reply. For example, the reply unit can include detailed information in important replies and write only the main points in other replies. This enables efficient communication by writing important replies in detail. Some or all of the above-mentioned processing in the reply unit can be performed using, for example, AI, or without AI. For example, the reply unit can input the reply content to a generation AI and have the generation AI evaluate the importance.

[0044] The reply unit can automatically select an appropriate template depending on the reply content. The reply unit, for example, analyzes the reply content using keyword extraction technology and selects an appropriate template. For example, the reply unit selects an appropriate business template for a business email. The reply unit can also select an appropriate casual template for a casual email. Furthermore, the reply unit can also select an appropriate technical template for a technical email. This enables efficient replies by selecting an appropriate template. Some or all of the above-mentioned processing in the reply unit may be performed using, for example, AI, or may be performed without using AI. For example, the reply unit can input the reply content to a generation AI and have the generation AI select an appropriate template.

[0045] The reply unit can analyze the reply content and automatically display related past replies. The reply unit can, for example, analyze the reply content using keyword extraction technology and search for related past replies. For example, the reply unit can automatically search for and display past replies related to the reply content. The reply unit can also search for related past replies based on sender information of the reply content. For example, the reply unit can automatically display past emails related to the reply content. Furthermore, the reply unit can analyze the topic of the reply content and search for related past replies. For example, the reply unit can automatically display past topics related to the reply content. This enables efficient replies by automatically displaying related past replies. Some or all of the above-mentioned processing in the reply unit can be performed using, for example, AI, or can be performed without using AI. For example, the reply unit can input the reply content to a generation AI and cause the generation AI to search for related past replies.

[0046] The reply unit can automatically generate related tasks according to the reply content. For example, the reply unit analyzes the reply content using keyword extraction technology and generates related tasks. For example, the reply unit automatically generates related tasks based on the reply content and adds them to a task list. The reply unit can also generate related tasks based on sender information of the reply content. For example, the reply unit automatically generates tasks related to the reply content. Furthermore, the reply unit can analyze the topic of the reply content and generate related tasks. For example, the reply unit automatically generates tasks based on topics related to the reply content. This enables efficient task management by automatically generating related tasks. Some or all of the above-described processing in the reply unit may be performed using, for example, AI, or may be performed without using AI. For example, the reply unit can input the reply content to a generation AI and cause the generation AI to generate related tasks.

[0047] The conversion unit can apply an algorithm for performing a natural translation by taking into account the context of the reply content. The conversion unit, for example, analyzes the reply content using context analysis technology and applies an algorithm for performing a natural translation. For example, the conversion unit analyzes the context of the reply content and performs an appropriate translation. The conversion unit can also select natural expressions based on the context of the reply content. Furthermore, the conversion unit can also select appropriate vocabulary by taking into account the context of the reply content. This improves the accuracy of the translation by performing a natural translation that takes into account the context of the reply content. Some or all of the above-mentioned processing in the conversion unit may be performed using, for example, AI, or may be performed without using AI. For example, the conversion unit can input the reply content to a generation AI and have the generation AI perform a translation that takes the context into account.

[0048] The conversion unit can appropriately convert technical terms and slang depending on the reply content. The conversion unit, for example, analyzes the reply content using keyword extraction technology and appropriately converts technical terms and slang. For example, the conversion unit appropriately converts technical terms in the case of a business email. The conversion unit can also appropriately convert slang in the case of a casual email. Furthermore, the conversion unit can also appropriately convert technical terms in the case of a technical email. This improves the accuracy of the translation by performing appropriate conversion depending on the reply content. Some or all of the above-mentioned processing in the conversion unit may be performed using, for example, AI, or may be performed without using AI. For example, the conversion unit can input the reply content to a generation AI and have the generation AI convert technical terms and slang.

[0049] The conversion unit can present multiple translation candidates depending on the reply content, allowing the user to select from them. The conversion unit, for example, analyzes the reply content using keyword extraction technology and generates multiple translation candidates. For example, the conversion unit generates multiple translation candidates based on the reply content and presents them to the user. The conversion unit can also perform a final translation based on the translation candidate selected by the user. Furthermore, the conversion unit can present appropriate translation candidates depending on the reply content. This allows the user to select the optimal translation by presenting multiple translation candidates. Some or all of the above-mentioned processing in the conversion unit may be performed using, for example, AI, or may be performed without using AI. For example, the conversion unit can input the reply content to a generation AI and have the generation AI generate multiple translation candidates.

[0050] The conversion unit can analyze the reply content and automatically refer to related literature and materials to improve the accuracy of the translation. The conversion unit can, for example, analyze the reply content using keyword extraction technology and search for related literature and materials. For example, the conversion unit can automatically search for literature related to the reply content and reflect it in the translation. The conversion unit can also automatically refer to materials related to the reply content to improve the accuracy of the translation. Furthermore, the conversion unit can refer to appropriate literature and materials based on the reply content. This improves the accuracy of the translation by referring to related literature and materials. Some or all of the above-mentioned processing in the conversion unit can be performed using, for example, AI, or can be performed without using AI. For example, the conversion unit can input the reply content to a generation AI and cause the generation AI to search for related literature and materials.

[0051] The speech unit can adjust the level of detail of the speech depending on the importance of the speech content. For example, the speech unit can analyze the speech content using keyword extraction technology and evaluate the importance. For example, the speech unit can describe important speech in detail and other speeches briefly. The speech unit can also analyze the context of the speech content and evaluate the importance. For example, the speech unit can describe important speech in detail and other speeches briefly. Furthermore, the speech unit can evaluate the importance based on sender information of the speech content and adjust the level of detail of the speech. For example, the speech unit can include detailed information for important speech and describe only the main points for other speech. This enables efficient communication by describing important speech in detail. Some or all of the above-mentioned processing in the speech unit can be performed using, for example, AI, or without AI. For example, the speech unit can input the speech content to a generation AI and have the generation AI evaluate the importance.

[0052] The speech unit can automatically select an appropriate template depending on the content of the utterance. For example, the speech unit analyzes the content of the utterance using keyword extraction technology and selects an appropriate template. For example, the speech unit selects an appropriate business template for a business conversation. The speech unit can also select an appropriate casual template for a casual conversation. Furthermore, the speech unit can also select an appropriate technical template for a technical conversation. By selecting an appropriate template, efficient speech is possible. Some or all of the above-mentioned processing in the speech unit may be performed using, for example, AI, or may be performed without using AI. For example, the speech unit can input the content of the utterance to a generation AI and have the generation AI select an appropriate template.

[0053] The speech unit can analyze the content of the utterance and automatically display related past utterances. The speech unit can, for example, analyze the content of the utterance using keyword extraction technology and search for related past utterances. For example, the speech unit can automatically search for and display past utterances related to the content of the utterance. The speech unit can also search for related past utterances based on sender information of the content of the utterance. For example, the speech unit can automatically display past conversations related to the content of the utterance. Furthermore, the speech unit can analyze the topic of the content of the utterance and search for related past utterances. For example, the speech unit can automatically display past topics related to the content of the utterance. This enables efficient speech by automatically displaying related past utterances. Some or all of the above-mentioned processing in the speech unit can be performed using, for example, AI, or can be performed without using AI. For example, the speech unit can input the content of the utterance to a generation AI and cause the generation AI to search for related past utterances.

[0054] The speech unit can automatically generate related tasks according to the content of the utterance. For example, the speech unit can analyze the content of the utterance using keyword extraction technology and generate related tasks. For example, the speech unit can automatically generate related tasks based on the content of the utterance and add them to a task list. The speech unit can also generate related tasks based on sender information of the content of the utterance. For example, the speech unit can automatically generate tasks related to the content of the utterance. Furthermore, the speech unit can analyze the topic of the content of the utterance and generate related tasks. For example, the speech unit can automatically generate tasks based on topics related to the content of the utterance. This enables efficient task management by automatically generating related tasks. Some or all of the above-described processing in the speech unit may be performed using, for example, AI, or may be performed without using AI. For example, the speech unit can input the content of the utterance to a generation AI and cause the generation AI to generate related tasks.

[0055] The conversion unit can apply an algorithm for performing a natural translation by taking into account the context of the utterance content. The conversion unit, for example, analyzes the utterance content using context analysis technology and applies an algorithm for performing a natural translation. For example, the conversion unit analyzes the context of the utterance content and performs an appropriate translation. The conversion unit can also select natural expressions based on the context of the utterance content. Furthermore, the conversion unit can also select appropriate vocabulary by taking into account the context of the utterance content. This improves the accuracy of the translation by performing a natural translation that takes into account the context of the utterance content. Some or all of the above-mentioned processing in the conversion unit may be performed using, for example, AI, or may be performed without using AI. For example, the conversion unit can input the utterance content to a generation AI and have the generation AI perform a translation that takes the context into account.

[0056] The conversion unit can appropriately convert technical terms and slang depending on the content of the utterance. For example, the conversion unit analyzes the content of the utterance using keyword extraction technology and appropriately converts technical terms and slang. For example, the conversion unit appropriately converts technical terms in business conversations. The conversion unit can also appropriately convert slang in casual conversations. Furthermore, the conversion unit can also appropriately convert technical terms in technical conversations. This improves the accuracy of translation by performing appropriate conversion depending on the content of the utterance. Some or all of the above-mentioned processing in the conversion unit may be performed using, for example, AI, or may be performed without using AI. For example, the conversion unit can input the content of the utterance to a generation AI and have the generation AI convert technical terms and slang.

[0057] The conversion unit can present multiple translation candidates according to the content of the utterance, allowing the user to select one. The conversion unit, for example, analyzes the content of the utterance using keyword extraction technology and generates multiple translation candidates. For example, the conversion unit generates multiple translation candidates based on the content of the utterance and presents them to the user. The conversion unit can also perform a final translation based on the translation candidate selected by the user. Furthermore, the conversion unit can present appropriate translation candidates according to the content of the utterance. As a result, by presenting multiple translation candidates, the user can select the optimal translation. Some or all of the above-mentioned processing in the conversion unit may be performed using, for example, AI, or may be performed without using AI. For example, the conversion unit can input the content of the utterance to a generation AI and cause the generation AI to generate multiple translation candidates.

[0058] The conversion unit can analyze the content of the utterance and automatically refer to related literature and materials to improve the accuracy of the translation. The conversion unit, for example, analyzes the content of the utterance using keyword extraction technology and searches for related literature and materials. For example, the conversion unit automatically searches for literature related to the content of the utterance and reflects it in the translation. The conversion unit can also automatically refer to materials related to the content of the utterance to improve the accuracy of the translation. Furthermore, the conversion unit can refer to appropriate literature and materials based on the content of the utterance. This improves the accuracy of the translation by referring to related literature and materials. Some or all of the above-mentioned processing in the conversion unit may be performed using, for example, AI, or may be performed without using AI. For example, the conversion unit can input the content of the utterance to a generation AI and cause the generation AI to search for related literature and materials.

[0059] The recognition unit can appropriately recognize technical terms and slang depending on the content of the speech to be recognized. The recognition unit, for example, analyzes the speech content using keyword extraction technology and appropriately recognizes technical terms and slang. For example, the recognition unit appropriately recognizes technical terms in business conversations. The recognition unit can also appropriately recognize slang in casual conversations. Furthermore, the recognition unit can also appropriately recognize technical terms in technical conversations. This improves recognition accuracy by performing appropriate recognition depending on the speech content. 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 speech content to a generation AI and have the generation AI recognize technical terms and slang.

[0060] The recognition unit can apply an algorithm for natural recognition by taking into account the context of the speech to be recognized. The recognition unit, for example, analyzes the speech content using context analysis technology and applies an algorithm for natural recognition. For example, the recognition unit analyzes the speech context and performs appropriate recognition. The recognition unit can also select natural expressions based on the speech context. Furthermore, the recognition unit can also select appropriate vocabulary by taking into account the speech context. This improves recognition accuracy by performing natural recognition that takes into account the speech context. 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 the speech content to a generation AI and cause the generation AI to perform recognition that takes the context into account.

[0061] The recognition unit can present multiple recognition candidates depending on the content of the speech to be recognized, allowing the user to select one. The recognition unit, for example, analyzes the speech content using keyword extraction technology and generates multiple recognition candidates. For example, the recognition unit generates multiple recognition candidates based on the speech content and presents them to the user. The recognition unit can also display a final recognition result based on the recognition candidate selected by the user. Furthermore, the recognition unit can present appropriate recognition candidates depending on the speech content. As a result, by presenting multiple recognition candidates, the user can select the optimal recognition result. 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 speech content to a generation AI and cause the generation AI to generate multiple recognition candidates.

[0062] The recognition unit can analyze the content of the speech to be recognized and automatically refer to related literature and materials to improve the accuracy of the recognition. For example, the recognition unit can analyze the speech content using keyword extraction technology and search for related literature and materials. For example, the recognition unit can automatically search for literature related to the speech content and reflect it in the recognition. The recognition unit can also automatically refer to materials related to the speech content to improve the accuracy of the recognition. Furthermore, the recognition unit can refer to appropriate literature and materials based on the speech content. This improves the accuracy of the recognition by referring to related literature and materials. 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 speech content to a generation AI and cause the generation AI to search for related literature and materials.

[0063] The conversion unit can apply an algorithm for performing a natural translation by taking into account the context of the recognition result. The conversion unit, for example, analyzes the recognition result using context analysis technology and applies an algorithm for performing a natural translation. For example, the conversion unit analyzes the context of the recognition result and performs an appropriate translation. The conversion unit can also select natural expressions based on the context of the recognition result. Furthermore, the conversion unit can also select appropriate vocabulary by taking into account the context of the recognition result. This improves the accuracy of the translation by performing a natural translation that takes into account the context of the recognition result. Some or all of the above-mentioned processing in the conversion unit may be performed using, for example, AI, or may be performed without using AI. For example, the conversion unit can input the recognition result to a generation AI and cause the generation AI to perform a translation that takes the context into account.

[0064] The conversion unit can appropriately convert technical terms and slang depending on the recognition result. The conversion unit, for example, analyzes the recognition result using keyword extraction technology and appropriately converts technical terms and slang. For example, the conversion unit appropriately converts technical terms in business conversations. The conversion unit can also appropriately convert slang in casual conversations. Furthermore, the conversion unit can also appropriately convert technical terms in technical conversations. This improves translation accuracy by performing appropriate conversion depending on the recognition result. Some or all of the above-mentioned processing in the conversion unit may be performed using, for example, AI, or may be performed without using AI. For example, the conversion unit can input the recognition result to a generation AI and have the generation AI convert technical terms and slang.

[0065] The conversion unit can present multiple translation candidates depending on the recognition result, allowing the user to select one. The conversion unit, for example, analyzes the recognition result using keyword extraction technology and generates multiple translation candidates. For example, the conversion unit generates multiple translation candidates based on the recognition result and presents them to the user. The conversion unit can also perform a final translation based on the translation candidate selected by the user. Furthermore, the conversion unit can present appropriate translation candidates depending on the recognition result. This allows the user to select the optimal translation by presenting multiple translation candidates. Some or all of the above-mentioned processing in the conversion unit may be performed using, for example, AI, or may be performed without using AI. For example, the conversion unit can input the recognition result to a generation AI and cause the generation AI to generate multiple translation candidates.

[0066] The conversion unit can analyze the recognition results and automatically refer to related literature and materials to improve the accuracy of the translation. The conversion unit can, for example, analyze the recognition results using keyword extraction technology and search for related literature and materials. For example, the conversion unit can automatically search for literature related to the recognition results and reflect the results in the translation. The conversion unit can also automatically refer to materials related to the recognition results to improve the accuracy of the translation. Furthermore, the conversion unit can refer to appropriate literature and materials based on the recognition results. This improves the accuracy of the translation by referring to related literature and materials. Some or all of the above-mentioned processing in the conversion unit can be performed using, for example, AI, or can be performed without using AI. For example, the conversion unit can input the recognition results to a generation AI and cause the generation AI to search for related literature and materials.

[0067] The management unit can analyze the learning progress, identify the user's weaknesses, and focus the learning on them. The management unit, for example, analyzes the learning progress using keyword extraction technology to identify the user's weaknesses. For example, the management unit can analyze the learning progress and identify the user's weaknesses. The management unit can also focus the learning on the user's weaknesses. Furthermore, the management unit can analyze the learning progress and propose a learning plan that makes use of the user's strengths. This improves the learning effect by identifying the user's weaknesses and focusing the learning on them. Some or all of the above-mentioned processing in the management unit may be performed using, for example, AI, or may be performed without using AI. For example, the management unit can input the learning progress into a generation AI and have the generation AI identify the user's weaknesses.

[0068] The management unit can automatically generate an appropriate study plan according to the learning progress. For example, the management unit analyzes the learning progress using keyword extraction technology and generates an appropriate study plan. For example, the management unit automatically generates an appropriate study plan based on the learning progress. The management unit can also analyze the user's learning progress and propose an optimal study plan. Furthermore, the management unit can automatically update the study plan according to the learning progress. This enables efficient study by automatically generating a study plan according to the learning progress. Some or all of the above-mentioned processing in the management unit may be performed using, for example, AI, or may be performed without using AI. For example, the management unit can input the learning progress into a generation AI and cause the generation AI to generate an appropriate study plan.

[0069] The management unit can analyze the learning progress and automatically present relevant learning materials. For example, the management unit can analyze the learning progress using keyword extraction technology and search for relevant learning materials. For example, the management unit can analyze the learning progress and automatically search for and present relevant learning materials. The management unit can also present appropriate learning materials based on the learning progress. Furthermore, the management unit can analyze the learning progress and present learning materials that address the user's weaknesses. This automatically presents relevant learning materials, thereby improving learning effectiveness. Some or all of the above-mentioned processing in the management unit may be performed using AI, for example, or may be performed without using AI. For example, the management unit can input the learning progress into a generation AI and cause the generation AI to search for relevant learning materials.

[0070] The management unit can automatically generate related tasks according to the learning progress. For example, the management unit analyzes the learning progress using keyword extraction technology and generates related tasks. For example, the management unit automatically generates related tasks based on the learning progress and adds them to a task list. The management unit can also automatically generate appropriate tasks according to the learning progress. Furthermore, the management unit can analyze the learning progress and generate tasks that address the user's weaknesses. This enables efficient task management by automatically generating related tasks. Some or all of the above-mentioned processing in the management unit may be performed using, for example, AI, or may be performed without using AI. For example, the management unit can input the learning progress into a generation AI and cause the generation AI to generate related tasks.

[0071] The feedback unit can analyze the feedback content, identify the user's weaknesses, and provide focused feedback. The feedback unit can, for example, analyze the feedback content using keyword extraction technology to identify the user's weaknesses. For example, the feedback unit can analyze the feedback content and identify the user's weaknesses. The feedback unit can also provide focused feedback based on the user's weaknesses. Furthermore, the feedback unit can analyze the feedback content and provide feedback that makes use of the user's strengths. This improves learning effectiveness by identifying the user's weaknesses and providing focused feedback. Some or all of the above-described processing in the feedback unit can be performed using, for example, AI, or can be performed without using AI. For example, the feedback unit can input the feedback content to a generation AI and cause the generation AI to identify the user's weaknesses.

[0072] The feedback unit can automatically generate an appropriate improvement plan according to the feedback content. The feedback unit, for example, analyzes the feedback content using keyword extraction technology and generates an appropriate improvement plan. For example, the feedback unit automatically generates an appropriate improvement plan based on the feedback content. The feedback unit can also analyze the user's feedback content and propose an optimal improvement plan. Furthermore, the feedback unit can automatically update the improvement plan according to the feedback content. This enables efficient learning by automatically generating an appropriate improvement plan. Some or all of the above-mentioned processing in the feedback unit may be performed using, for example, AI, or may be performed without using AI. For example, the feedback unit can input the feedback content to a generation AI and cause the generation AI to generate an appropriate improvement plan.

[0073] The feedback unit can analyze the feedback content and automatically present relevant study materials. For example, the feedback unit can analyze the feedback content using keyword extraction technology and search for relevant study materials. For example, the feedback unit can analyze the feedback content and automatically search for and present relevant study materials. The feedback unit can also present appropriate study materials based on the feedback content. Furthermore, the feedback unit can analyze the feedback content and present study materials that address the user's weaknesses. This automatically presents relevant study materials, thereby improving learning effectiveness. Some or all of the above-described processing in the feedback unit can be performed using, or without, AI. For example, the feedback unit can input the feedback content to a generation AI and cause the generation AI to search for relevant study materials.

[0074] The feedback unit can automatically generate related tasks according to the feedback content. For example, the feedback unit analyzes the feedback content using keyword extraction technology and generates related tasks. For example, the feedback unit automatically generates related tasks based on the feedback content and adds them to a task list. The feedback unit can also automatically generate appropriate tasks according to the feedback content. Furthermore, the feedback unit can analyze the feedback content and generate tasks that address the user's weaknesses. This enables efficient task management by automatically generating related tasks. Some or all of the above-described processing in the feedback unit may be performed using, for example, AI, or may be performed without using AI. For example, the feedback unit can input the feedback content to a generation AI and cause the generation AI to generate related tasks.

[0075] The system according to the embodiment is not limited to the above-described example, and various modifications are possible, for example, as follows.

[0076] The foreign language acquisition support system may also include a learning style analysis unit that analyzes the user's learning style and suggests the optimal learning method. The learning style analysis unit may, for example, analyze the user's learning history and learning speed, and suggest video materials if the user prefers visual learning, or audio materials if the user prefers auditory learning. The learning style analysis unit may also analyze the user's study time period and concentration span to suggest the optimal study schedule. Furthermore, the learning style analysis unit may adjust the learning method based on the user's feedback to support efficient learning. This improves learning effectiveness by providing the optimal learning method according to the user's learning style.

[0077] The foreign language acquisition assistance system may also include a progress prediction unit that predicts the user's learning progress based on the user's learning history. The progress prediction unit, for example, analyzes the content and learning speed of the user's past learning to predict the user's future learning progress. The progress prediction unit can also predict the time required to achieve the user's learning goals and propose a learning plan based on the user's learning goals. Furthermore, the progress prediction unit can evaluate the effectiveness of learning based on the user's learning history and propose an efficient learning method. This improves the learning effectiveness by predicting the user's learning progress and providing an efficient learning plan.

[0078] The foreign language acquisition support system may also include an environment optimization unit for optimizing the user's learning environment. The environment optimization unit may, for example, analyze the user's learning location and time period and propose an optimal learning environment. The environment optimization unit may also propose appropriate learning tools and learning materials depending on the user's learning environment. Furthermore, the environment optimization unit may monitor the user's learning environment in real time and adjust the learning method in response to changes in the environment. This may improve learning effectiveness by optimizing the user's learning environment.

[0079] The foreign language acquisition assistance system may also include an effect evaluation unit that evaluates the effectiveness of learning based on the user's learning data. The effect evaluation unit, for example, analyzes the user's learning history and test results to evaluate the effectiveness of learning. The effect evaluation unit can also evaluate the user's achievement level and adjust the learning plan based on the user's learning goals. Furthermore, the effect evaluation unit can suggest efficient learning methods based on the user's learning data. This improves learning effectiveness by evaluating the user's learning effectiveness and providing efficient learning methods.

[0080] The foreign language acquisition assistance system may also include a learning optimization unit that maximizes learning effectiveness based on the user's learning data. The learning optimization unit may analyze, for example, the user's learning history and test results to propose an optimal learning method. The learning optimization unit may also propose an efficient learning plan based on the user's learning goals. Furthermore, the learning optimization unit may monitor learning progress in real time based on the user's learning data and adjust the learning method as necessary. This improves learning effectiveness by providing an optimal learning method that maximizes the user's learning effectiveness.

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

[0082] Step 1: The receiving unit receives emails received by the user. For example, the emails can be obtained from an email server. Step 2: The conversion unit converts the email received by the receiving unit into a foreign language. For example, the content of the email can be converted into a foreign language using a text translation engine. Step 3: The reply unit replies based on the email converted by the conversion unit. For example, it can send a reply that the user entered. Step 4: The reply conversion unit converts the email returned by the reply unit into Japanese. For example, the reply content can be converted into Japanese using a text translation engine. Step 5: The user speaks in the speech unit. For example, the user's voice can be acquired using a microphone. Step 6: The speech conversion unit converts the speech uttered by the speech unit into a foreign language. For example, a speech translation engine can be used to convert the speech into the foreign language. Step 7: The recognition unit recognizes the speech converted by the speech conversion unit. For example, a speech recognition engine can be used to convert the speech into text. Step 8: The recognition conversion unit converts the speech recognized by the recognition unit into Japanese. For example, a text translation engine can be used to convert the text into Japanese.

[0083] (Example 2) A foreign language acquisition assistance system according to an embodiment of the present invention provides an environment in which a user is forced to come into contact with a foreign language on a daily basis. When a user receives an email, the email is automatically converted into a foreign language and displayed. When the user replies in the foreign language, the reply is automatically converted into Japanese and sent to the recipient. Furthermore, the system can improve the user's conversational skills by using speech utterances and speech recognition functions. For example, when a user speaks a foreign language, the speech is automatically recognized and displayed as text in the foreign language. Furthermore, when a user listens to foreign language speech, the speech is automatically converted into Japanese and displayed. In this way, the user can be exposed to a foreign language on a daily basis and can naturally acquire the foreign language. For example, when a user receives an email, the email is automatically converted into the foreign language and displayed. When the user replies in the foreign language, the reply is automatically converted into Japanese and sent to the recipient. Furthermore, the system can improve the user's conversational skills by using speech utterances and speech recognition functions. For example, when a user speaks a foreign language, the speech is automatically recognized and displayed as text in the foreign language. Furthermore, when a user listens to foreign language speech, the speech is automatically converted into Japanese and displayed. In this way, the user can be exposed to a foreign language on a daily basis and can naturally acquire the foreign language.In this way, the foreign language acquisition support system allows the user to be exposed to a foreign language on a daily basis and can naturally acquire the foreign language.

[0084] A foreign language learning assistance system according to an embodiment includes a receiving unit, a converting unit, a replying unit, a reply conversion unit, a speaking unit, a speech conversion unit, a recognition unit, and a recognition conversion unit. The receiving unit receives emails received by a user. The receiving unit can, for example, acquire emails from an email server. The conversion unit converts the emails received by the receiving unit into a foreign language. The conversion unit can, for example, convert the content of the email into the foreign language using a text translation engine. The replying unit replies based on the email converted by the conversion unit. The replying unit can, for example, send a reply content entered by the user. The reply conversion unit converts the email replied by the replying unit into Japanese. The reply conversion unit can convert the reply content into Japanese using, for example, a text translation engine. The speech unit allows the user to speak. The speech unit can acquire the user's voice using, for example, a microphone. The speech conversion unit converts the voice spoken by the speaking unit into a foreign language. The speech conversion unit can convert the voice spoken by the speaking unit into a foreign language using, for example, a speech translation engine. The recognition unit recognizes the speech converted by the speech conversion unit. The recognition unit can convert the speech into text using, for example, a speech recognition engine. The recognition conversion unit converts the speech recognized by the recognition unit into Japanese. The recognition conversion unit can convert the text into Japanese using, for example, a text translation engine. As a result, the foreign language acquisition assistance system according to the embodiment allows the user to come into contact with a foreign language on a daily basis and naturally acquire the foreign language.

[0085] The foreign language acquisition assistance system includes a progress management unit that manages the user's learning progress. The progress management unit can, for example, record and manage the content and progress of the user's learning. The progress management unit evaluates the user's learning progress and supports efficient learning. For example, the progress management unit can suggest the next content to study based on the content the user has studied. The progress management unit can also visually display the user's learning progress as a graph or chart. This allows the user to grasp their learning progress at a glance. Furthermore, the progress management unit can synchronize the user's learning progress with other devices. For example, the progress management unit can synchronize with the user's smartphone or tablet and update the learning progress in real time. This allows the user to check the learning progress from any device. In this way, the foreign language acquisition assistance system manages the user's learning progress, enabling efficient learning.

[0086] The foreign language learning assistance system includes a speech feedback unit for improving the accuracy of speech. The speech feedback unit provides feedback to improve the accuracy of the user's speech. For example, the speech feedback unit can evaluate the user's pronunciation and intonation and point out areas for improvement. The speech feedback unit can record the user's speech and play it back for later confirmation. For example, the speech feedback unit can record the user's speech and play back the audio to check the accuracy of the pronunciation. The speech feedback unit can also provide real-time feedback on the user's speech. For example, the speech feedback unit can evaluate the accuracy of the pronunciation and the naturalness of the intonation while the user is speaking and provide instant feedback. Furthermore, the speech feedback unit can provide a training program for improving the accuracy of the user's speech. For example, the speech feedback unit can provide a training program for the user to practice pronunciation, thereby improving the accuracy of the pronunciation and the naturalness of the intonation. As a result, the foreign language learning assistance system improves the accuracy of speech, enabling more natural conversations.

[0087] The conversion unit can convert emails into foreign languages ​​using a generation AI. The generation AI converts email content into foreign languages ​​using advanced natural language processing technologies such as GPT-4 and Gemini. The generation AI has trained on large amounts of text data and has advanced translation capabilities. For example, the generation AI can understand the context of emails and provide appropriate translations. The generation AI can analyze the content of emails and select natural expressions based on the context. For example, the generation AI can select appropriate business terms for business emails and appropriate slang for casual emails. This improves the accuracy of email foreign language conversion. The generation AI can generate multiple translation candidates based on the content of the email and present them to the user. For example, the generation AI can generate multiple translation candidates based on the content of the email and allow the user to select the optimal translation. This allows the user to select the translation that best suits their preferences. Furthermore, the generation AI can automatically refer to related literature and materials based on the content of the email to improve the accuracy of the translation. For example, the generation AI can automatically search for literature related to the content of the email and incorporate it into the translation. This will improve the accuracy of foreign language translation of emails by using generative AI.

[0088] The conversion unit can convert speech into a foreign language using a generation AI. The generation AI converts speech content into a foreign language using advanced natural language processing technologies such as GPT-4 and Gemini. The generation AI has trained on large amounts of speech data and has advanced translation capabilities. For example, the generation AI can understand the context of the speech and provide appropriate translations. The generation AI can analyze the speech content and select natural expressions based on the context. For example, the generation AI can select appropriate business terms for business conversations and appropriate slang for casual conversations. This improves the accuracy of speech-to-foreign-language conversion. The generation AI can generate multiple translation candidates based on the speech content and present them to the user. For example, the generation AI can generate multiple translation candidates based on the speech content and allow the user to select the optimal translation. This allows the user to select the translation that best suits their preferences. Furthermore, the generation AI can automatically refer to related literature and materials based on the speech content to improve the accuracy of the translation. For example, the generation AI can automatically search for literature related to the speech content and incorporate it into the translation. This will improve the accuracy of converting speech into foreign languages ​​by using generative AI.

[0089] The recognition unit can recognize speech using a generative AI. The generative AI recognizes speech using advanced natural language processing technologies, such as GPT-4 and Gemini. Generative AI has trained on large amounts of speech data and has advanced speech recognition capabilities. For example, the generative AI can understand the context of speech and perform appropriate recognition. It can analyze speech content and select natural expressions based on the context. For example, the generative AI can select appropriate business terms for business conversations and appropriate slang for casual conversations. This improves the accuracy of speech recognition. The generative AI can generate multiple recognition candidates based on the speech content and present them to the user. For example, the generative AI can generate multiple recognition candidates based on the speech content and allow the user to select the most appropriate recognition result. This allows the user to select the recognition result that best suits their preferences. Furthermore, the generative AI can automatically refer to related literature and materials based on the speech content to improve recognition accuracy. For example, the generative AI can automatically search for literature related to the speech content and incorporate it into recognition. This will improve the accuracy of voice recognition by using generative AI.

[0090] The receiving unit can estimate the user's emotions and adjust the timing of email reception based on the estimated user emotions. For example, the receiving unit captures the user's facial expression with a camera and estimates the emotion using an emotion estimation algorithm. For example, the receiving unit calculates an emotion score based on changes in facial expression, and if the user is feeling stressed, delays email reception and notifies the user when they are relaxed. The receiving unit can also record the user's voice and estimate the emotion using voice analysis technology. For example, the receiving unit can analyze the tone and speed of the voice to calculate an emotion score, and if the user is concentrating, immediately notify only important emails and later notify other emails. Furthermore, the receiving unit can collect the user's biometric data (heart rate and electrodermal activity) with a sensor and estimate the emotion using an emotion estimation algorithm. For example, the receiving unit can calculate an emotion score based on heart rate fluctuations, and if the user is relaxed, immediately notify all emails. This allows stress to be reduced by adjusting the timing of email reception according to the user's emotions. Emotion estimation is achieved using an emotion estimation function, for example, an emotion engine or generative 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 receiving unit may be performed using AI, or may be performed without using AI. For example, the receiving unit may input image data of a user captured by a camera into the generation AI and cause the generation AI to estimate the user's emotions.

[0091] The receiving unit can analyze the content of received emails and change the method of notification depending on their importance. For example, the receiving unit can analyze the content of emails using keyword extraction technology and evaluate their importance. For example, the receiving unit can notify emails containing important keywords with a voice notification and other emails with a vibration. The receiving unit can also analyze the context of emails and evaluate their importance. For example, the receiving unit can display business-related emails as a pop-up notification and casual emails in a notification bar. Furthermore, the receiving unit can evaluate the importance based on the email sender information and change the method of notification. For example, the receiving unit can notify emails from important business partners immediately and notify other emails collectively after a certain period of time. This enables efficient email management by prioritizing important emails. Some or all of the above-described processing in the receiving unit can be performed using, or without, AI. For example, the receiving unit can input the content of emails into a generation AI and have the generation AI evaluate their importance.

[0092] The receiving unit can set priorities and adjust the receiving order based on sender information of the received emails. The receiving unit, for example, analyzes the sender information of the emails and sets the priorities. For example, the receiving unit can prioritize receiving emails from important business partners and postpone other emails. The receiving unit can also prioritize receiving emails from family and friends and postpone work-related emails. Furthermore, the receiving unit can prioritize receiving emails from superiors and postpone emails from colleagues. This enables efficient email management by prioritizing receiving emails from important senders. Some or all of the above-mentioned processing in the receiving unit may be performed using, for example, AI, or may be performed without using AI. For example, the receiving unit can input email sender information to a generation AI and have the generation AI set the priorities.

[0093] The receiving unit can estimate the user's emotions and adjust the display method of received emails based on the estimated user emotions. For example, the receiving unit captures the user's facial expression with a camera and estimates the emotions using an emotion estimation algorithm. For example, the receiving unit calculates an emotion score based on changes in facial expression, and displays emails in a simple display format if the user is feeling stressed. The receiving unit can also record the user's voice and estimate emotions using voice analysis technology. For example, the receiving unit can analyze the tone and speed of the voice to calculate an emotion score, and display emails in a display format that includes detailed information if the user is relaxed. Furthermore, the receiving unit can collect the user's biometric data (heart rate and electrodermal activity) using a sensor and estimate emotions using an emotion estimation algorithm. For example, the receiving unit can calculate an emotion score based on heart rate fluctuations and highlight important information when the user is concentrating. This allows stress to be reduced by adjusting the display method of emails according to the user's emotions. Emotion estimation is achieved using an emotion estimation function, for example, an emotion engine or generative AI. The generative 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 receiving unit may be performed using, for example, AI, or may be performed without using AI. For example, the receiving unit may input image data of a user taken with a camera to the generating AI and cause the generating AI to estimate the user's emotions.

[0094] The receiving unit can analyze the content of received emails and automatically display related past emails. The receiving unit can, for example, analyze the content of the email using keyword extraction technology and search for related past emails. For example, the receiving unit can automatically search for and display past emails related to the content of the received email. The receiving unit can also search for related past emails based on email sender information. For example, the receiving unit can automatically display past emails related to the sender of the received email. Furthermore, the receiving unit can analyze the topic of the email and search for related past emails. For example, the receiving unit can automatically display past emails related to the topic of the received email. This enables efficient email management by automatically displaying related past emails. Some or all of the above-mentioned processing in the receiving unit can be performed using, for example, AI, or can be performed without using AI. For example, the receiving unit can input the content of the email into a generation AI and have the generation AI search for related past emails.

[0095] The receiving unit can automatically generate related tasks based on the content of the received email. For example, the receiving unit analyzes the content of the email using keyword extraction technology and generates related tasks. For example, the receiving unit automatically generates related tasks based on the content of the received email and adds them to a task list. The receiving unit can also generate related tasks based on email sender information. For example, the receiving unit automatically generates tasks related to the sender of the received email. Furthermore, the receiving unit can analyze the topic of the email and generate related tasks. For example, the receiving unit automatically generates tasks related to the topic of the received email. This enables efficient task management by automatically generating related tasks. Some or all of the above-mentioned processing in the receiving unit may be performed using, for example, AI, or may be performed without using AI. For example, the receiving unit can input the content of the email into a generation AI and have the generation AI generate related tasks.

[0096] The conversion unit can estimate the user's emotions and select a foreign language to convert based on the estimated user emotions. For example, the conversion unit captures the user's facial expressions with a camera and estimates the emotions using an emotion estimation algorithm. For example, the conversion unit calculates an emotion score based on changes in facial expressions, and prioritizes selecting a foreign language the user is learning if the user is relaxed. The conversion unit can also record the user's voice and estimate emotions using voice analysis technology. For example, the conversion unit can analyze the tone and speed of the voice to calculate an emotion score, and select an easier foreign language if the user is stressed. Furthermore, the conversion unit can collect the user's biometric data (heart rate and electrodermal activity) using a sensor and estimate emotions using an emotion estimation algorithm. For example, the conversion unit can calculate an emotion score based on heart rate fluctuations and select a more difficult foreign language if the user is concentrating. This improves learning effectiveness by selecting a foreign language based on the user's emotions. Emotion estimation is achieved using an emotion estimation function, such as an emotion engine or generative 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 conversion unit may be performed using AI, or may be performed without using AI. For example, the conversion unit may input image data of a user captured by a camera into the generation AI and cause the generation AI to estimate the user's emotions.

[0097] The conversion unit can appropriately convert technical terms and slang depending on the content of the email. The conversion unit, for example, analyzes the content of the email using keyword extraction technology and appropriately converts technical terms and slang. For example, the conversion unit appropriately converts technical terms in the case of a business email. The conversion unit can also appropriately convert slang in the case of a casual email. Furthermore, the conversion unit can also appropriately convert technical terms in the case of a technical email. This improves the accuracy of the translation by performing appropriate conversion depending on the content of the email. Some or all of the above-mentioned processing in the conversion unit may be performed using, for example, AI, or may be performed without using AI. For example, the conversion unit can input the content of the email into a generation AI and have the generation AI convert technical terms and slang.

[0098] The conversion unit can apply an algorithm for performing a natural translation by taking into account the context of the email. The conversion unit, for example, analyzes the content of the email using context analysis technology and applies an algorithm for performing a natural translation. For example, the conversion unit analyzes the context of the email and performs an appropriate translation. The conversion unit can also select natural expressions based on the context of the email. Furthermore, the conversion unit can also select appropriate vocabulary by taking into account the context of the email. This improves the accuracy of the translation by performing a natural translation that takes into account the context of the email. Some or all of the above-mentioned processing in the conversion unit may be performed using, for example, AI, or may be performed without using AI. For example, the conversion unit can input the content of the email into a generation AI and have the generation AI perform a translation that takes the context into account.

[0099] The conversion unit can estimate the user's emotions and adjust the expression style of the converted email based on the estimated user emotions. For example, the conversion unit captures the user's facial expression with a camera and estimates the emotion using an emotion estimation algorithm. For example, the conversion unit calculates an emotion score based on changes in facial expression, and uses polite expressions when the user is relaxed. The conversion unit can also record the user's voice and estimate the emotion using voice analysis technology. For example, the conversion unit can analyze the tone and speed of the voice to calculate an emotion score, and use concise expressions when the user is stressed. Furthermore, the conversion unit can collect the user's biometric data (heart rate and electrodermal activity) with a sensor and estimate the emotion using an emotion estimation algorithm. For example, the conversion unit can calculate an emotion score based on heart rate fluctuations and use detailed expressions when the user is concentrating. This improves the quality of communication by adjusting the expression style of the email according to the user's emotions. Emotion estimation is achieved using an emotion estimation function, for example, an emotion engine or a generative AI. The generative 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 conversion unit may be performed using, for example, AI, or may be performed without using AI. For example, the conversion unit may input image data of a user taken with a camera to the generation AI and cause the generation AI to estimate the user's emotions.

[0100] The conversion unit can present multiple translation candidates depending on the content of the email and allow the user to select one. The conversion unit, for example, analyzes the content of the email using keyword extraction technology and generates multiple translation candidates. For example, the conversion unit generates multiple translation candidates based on the content of the email and presents them to the user. The conversion unit can also perform a final translation based on the translation candidate selected by the user. Furthermore, the conversion unit can present appropriate translation candidates depending on the content of the email. This allows the user to select the optimal translation by presenting multiple translation candidates. Some or all of the above-mentioned processing in the conversion unit may be performed using, for example, AI, or may be performed without using AI. For example, the conversion unit can input the content of the email into a generation AI and have the generation AI generate multiple translation candidates.

[0101] The conversion unit can analyze the content of the email and automatically refer to related literature and materials to improve the accuracy of the translation. For example, the conversion unit can analyze the content of the email using keyword extraction technology and search for related literature and materials. For example, the conversion unit can automatically search for literature related to the content of the email and reflect that in the translation. The conversion unit can also automatically refer to materials related to the content of the email to improve the accuracy of the translation. Furthermore, the conversion unit can refer to appropriate literature and materials based on the content of the email. This improves the accuracy of the translation by referring to related literature and materials. Some or all of the above-mentioned processing in the conversion unit may be performed using, for example, AI, or may be performed without using AI. For example, the conversion unit can input the content of the email into a generation AI and have the generation AI search for related literature and materials.

[0102] The reply unit can estimate the user's emotions and adjust the timing of replies based on the estimated user emotions. For example, the reply unit captures the user's facial expression with a camera and estimates the emotions using an emotion estimation algorithm. For example, the reply unit calculates an emotion score based on changes in facial expression and prompts the user to reply immediately if the user is relaxed. The reply unit can also record the user's voice and estimate the emotions using voice analysis technology. For example, the reply unit can analyze the tone and speed of the voice to calculate an emotion score and prompt the user to reply after a certain period of time if the user is feeling stressed. Furthermore, the reply unit can collect the user's biometric data (heart rate and electrodermal activity) using a sensor and estimate the emotions using an emotion estimation algorithm. For example, the reply unit can calculate an emotion score based on heart rate fluctuations and prompt the user to reply immediately only to important messages if the user is concentrating. This allows the user's stress to be reduced by adjusting the timing of replies according to the user's emotions. Emotion estimation is achieved using an emotion estimation function, such as an emotion engine or a generative AI. The generative AI 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 reply unit may be performed using, for example, AI, or may be performed without using AI. For example, the reply unit may input image data of the user taken with a camera to the generation AI and cause the generation AI to estimate the user's emotions.

[0103] The reply unit can adjust the level of detail in the reply depending on the importance of the reply content. For example, the reply unit can analyze the reply content using keyword extraction technology and evaluate the importance. For example, the reply unit can write important replies in detail and other replies in a concise manner. The reply unit can also analyze the context of the reply content and evaluate the importance. For example, the reply unit can write important replies in detail and other replies in a concise manner. Furthermore, the reply unit can evaluate the importance based on sender information of the reply content and adjust the level of detail in the reply. For example, the reply unit can include detailed information in important replies and write only the main points in other replies. This enables efficient communication by writing important replies in detail. Some or all of the above-mentioned processing in the reply unit can be performed using, for example, AI, or without AI. For example, the reply unit can input the reply content to a generation AI and have the generation AI evaluate the importance.

[0104] The reply unit can automatically select an appropriate template depending on the reply content. The reply unit, for example, analyzes the reply content using keyword extraction technology and selects an appropriate template. For example, the reply unit selects an appropriate business template for a business email. The reply unit can also select an appropriate casual template for a casual email. Furthermore, the reply unit can also select an appropriate technical template for a technical email. This enables efficient replies by selecting an appropriate template. Some or all of the above-mentioned processing in the reply unit may be performed using, for example, AI, or may be performed without using AI. For example, the reply unit can input the reply content to a generation AI and have the generation AI select an appropriate template.

[0105] The reply unit can estimate the user's emotions and adjust the way a reply is expressed based on the estimated user's emotions. For example, the reply unit captures the user's facial expression with a camera and estimates the emotion using an emotion estimation algorithm. For example, the reply unit calculates an emotion score based on changes in facial expression, and uses polite expressions when the user is relaxed. The reply unit can also record the user's voice and estimate the emotion using voice analysis technology. For example, the reply unit can analyze the tone and speed of voice to calculate an emotion score, and use concise expressions when the user is stressed. Furthermore, the reply unit can collect the user's biometric data (heart rate and electrodermal activity) with a sensor and estimate the emotion using an emotion estimation algorithm. For example, the reply unit can calculate an emotion score based on heart rate fluctuations and use detailed expressions when the user is concentrating. This improves the quality of communication by adjusting the way a reply is expressed 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, 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 reply unit may be performed using, for example, AI, or may be performed without using AI. For example, the reply unit may input image data of the user taken with a camera to the generation AI and cause the generation AI to estimate the user's emotions.

[0106] The reply unit can analyze the reply content and automatically display related past replies. The reply unit can, for example, analyze the reply content using keyword extraction technology and search for related past replies. For example, the reply unit can automatically search for and display past replies related to the reply content. The reply unit can also search for related past replies based on sender information of the reply content. For example, the reply unit can automatically display past emails related to the reply content. Furthermore, the reply unit can analyze the topic of the reply content and search for related past replies. For example, the reply unit can automatically display past topics related to the reply content. This enables efficient replies by automatically displaying related past replies. Some or all of the above-mentioned processing in the reply unit can be performed using, for example, AI, or can be performed without using AI. For example, the reply unit can input the reply content to a generation AI and cause the generation AI to search for related past replies.

[0107] The reply unit can automatically generate related tasks according to the reply content. For example, the reply unit analyzes the reply content using keyword extraction technology and generates related tasks. For example, the reply unit automatically generates related tasks based on the reply content and adds them to a task list. The reply unit can also generate related tasks based on sender information of the reply content. For example, the reply unit automatically generates tasks related to the reply content. Furthermore, the reply unit can analyze the topic of the reply content and generate related tasks. For example, the reply unit automatically generates tasks based on topics related to the reply content. This enables efficient task management by automatically generating related tasks. Some or all of the above-described processing in the reply unit may be performed using, for example, AI, or may be performed without using AI. For example, the reply unit can input the reply content to a generation AI and cause the generation AI to generate related tasks.

[0108] The conversion unit can estimate the user's emotions and adjust the translation method of the reply based on the estimated user emotions. For example, the conversion unit captures the user's facial expression with a camera and estimates the emotions using an emotion estimation algorithm. For example, the conversion unit calculates an emotion score based on changes in facial expression and performs a detailed translation if the user is relaxed. The conversion unit can also record the user's voice and estimate the emotions using voice analysis technology. For example, the conversion unit can analyze the tone and speed of the voice to calculate an emotion score and perform a concise translation if the user is stressed. Furthermore, the conversion unit can collect the user's biometric data (heart rate and electrodermal activity) using a sensor and estimate the emotions using an emotion estimation algorithm. For example, the conversion unit can calculate an emotion score based on heart rate fluctuations and perform a detailed translation if the user is concentrating. This improves the quality of communication by adjusting the translation method according to the user's emotions. Emotion estimation is achieved using an emotion estimation function, for example, an emotion engine or a generative AI. The generative AI can be, but is not limited to, a text generation AI (e.g., LLM) or a multimodal generative AI. Some or all of the above-described processing in the conversion unit may be performed using, for example, AI, or may be performed without using AI. For example, the conversion unit may input image data of a user taken with a camera to the generation AI and cause the generation AI to estimate the user's emotions.

[0109] The conversion unit can apply an algorithm for performing a natural translation by taking into account the context of the reply content. The conversion unit, for example, analyzes the reply content using context analysis technology and applies an algorithm for performing a natural translation. For example, the conversion unit analyzes the context of the reply content and performs an appropriate translation. The conversion unit can also select natural expressions based on the context of the reply content. Furthermore, the conversion unit can also select appropriate vocabulary by taking into account the context of the reply content. This improves the accuracy of the translation by performing a natural translation that takes into account the context of the reply content. Some or all of the above-mentioned processing in the conversion unit may be performed using, for example, AI, or may be performed without using AI. For example, the conversion unit can input the reply content to a generation AI and have the generation AI perform a translation that takes the context into account.

[0110] The conversion unit can appropriately convert technical terms and slang depending on the reply content. The conversion unit, for example, analyzes the reply content using keyword extraction technology and appropriately converts technical terms and slang. For example, the conversion unit appropriately converts technical terms in the case of a business email. The conversion unit can also appropriately convert slang in the case of a casual email. Furthermore, the conversion unit can also appropriately convert technical terms in the case of a technical email. This improves the accuracy of the translation by performing appropriate conversion depending on the reply content. Some or all of the above-mentioned processing in the conversion unit may be performed using, for example, AI, or may be performed without using AI. For example, the conversion unit can input the reply content to a generation AI and have the generation AI convert technical terms and slang.

[0111] The conversion unit can estimate the user's emotions and adjust the expression style of the translated reply based on the estimated user emotions. For example, the conversion unit captures the user's facial expression with a camera and estimates the emotion using an emotion estimation algorithm. For example, the conversion unit calculates an emotion score based on changes in facial expression, and uses polite expressions when the user is relaxed. The conversion unit can also record the user's voice and estimate the emotion using voice analysis technology. For example, the conversion unit can analyze the tone and speed of voice to calculate an emotion score, and use concise expressions when the user is stressed. Furthermore, the conversion unit can collect the user's biometric data (heart rate and electrodermal activity) with a sensor and estimate the emotion using an emotion estimation algorithm. For example, the conversion unit can calculate an emotion score based on heart rate fluctuations and use detailed expressions when the user is concentrating. This improves the quality of communication by adjusting the expression style after translation according to 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, 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 conversion unit may be performed using, for example, AI, or may be performed without using AI. For example, the conversion unit may input image data of a user taken with a camera to the generation AI and cause the generation AI to estimate the user's emotions.

[0112] The conversion unit can present multiple translation candidates depending on the reply content, allowing the user to select from them. The conversion unit, for example, analyzes the reply content using keyword extraction technology and generates multiple translation candidates. For example, the conversion unit generates multiple translation candidates based on the reply content and presents them to the user. The conversion unit can also perform a final translation based on the translation candidate selected by the user. Furthermore, the conversion unit can present appropriate translation candidates depending on the reply content. This allows the user to select the optimal translation by presenting multiple translation candidates. Some or all of the above-mentioned processing in the conversion unit may be performed using, for example, AI, or may be performed without using AI. For example, the conversion unit can input the reply content to a generation AI and have the generation AI generate multiple translation candidates.

[0113] The conversion unit can analyze the reply content and automatically refer to related literature and materials to improve the accuracy of the translation. The conversion unit can, for example, analyze the reply content using keyword extraction technology and search for related literature and materials. For example, the conversion unit can automatically search for literature related to the reply content and reflect it in the translation. The conversion unit can also automatically refer to materials related to the reply content to improve the accuracy of the translation. Furthermore, the conversion unit can refer to appropriate literature and materials based on the reply content. This improves the accuracy of the translation by referring to related literature and materials. Some or all of the above-mentioned processing in the conversion unit can be performed using, for example, AI, or can be performed without using AI. For example, the conversion unit can input the reply content to a generation AI and cause the generation AI to search for related literature and materials.

[0114] The speech unit can estimate the user's emotions and adjust the timing of speech based on the estimated user emotions. For example, the speech unit captures the user's facial expressions with a camera and estimates their emotions using an emotion estimation algorithm. For example, it calculates an emotion score based on changes in facial expressions and prompts the user to speak immediately if the user is relaxed. The speech unit can also record the user's voice and estimate their emotions using voice analysis technology. For example, it can analyze the tone and speed of the voice to calculate an emotion score and prompt the user to speak after a certain period of time if the user is feeling stressed. Furthermore, the speech unit can collect the user's biometric data (heart rate and electrodermal activity) using a sensor and estimate their emotions using an emotion estimation algorithm. For example, it can calculate an emotion score based on heart rate fluctuations and prompt the user to speak only important parts immediately if the user is concentrating. This allows the timing of speech to be adjusted according to the user's emotions, thereby reducing stress. Emotion estimation is achieved using an emotion estimation function, for example, an emotion engine or generative 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 speech unit may be performed using AI, or may be performed without using AI. For example, the speech unit may input image data of a user captured by a camera into the generation AI and cause the generation AI to estimate the user's emotions.

[0115] The speech unit can adjust the level of detail of the speech depending on the importance of the speech content. For example, the speech unit can analyze the speech content using keyword extraction technology and evaluate the importance. For example, the speech unit can describe important speech in detail and other speeches briefly. The speech unit can also analyze the context of the speech content and evaluate the importance. For example, the speech unit can describe important speech in detail and other speeches briefly. Furthermore, the speech unit can evaluate the importance based on sender information of the speech content and adjust the level of detail of the speech. For example, the speech unit can include detailed information for important speech and describe only the main points for other speech. This enables efficient communication by describing important speech in detail. Some or all of the above-mentioned processing in the speech unit can be performed using, for example, AI, or without AI. For example, the speech unit can input the speech content to a generation AI and have the generation AI evaluate the importance.

[0116] The speech unit can automatically select an appropriate template depending on the content of the utterance. For example, the speech unit analyzes the content of the utterance using keyword extraction technology and selects an appropriate template. For example, the speech unit selects an appropriate business template for a business conversation. The speech unit can also select an appropriate casual template for a casual conversation. Furthermore, the speech unit can also select an appropriate technical template for a technical conversation. By selecting an appropriate template, efficient speech is possible. Some or all of the above-mentioned processing in the speech unit may be performed using, for example, AI, or may be performed without using AI. For example, the speech unit can input the content of the utterance to a generation AI and have the generation AI select an appropriate template.

[0117] The speech unit can estimate the user's emotions and adjust the way the speech is expressed based on the estimated user's emotions. For example, the speech unit captures the user's facial expressions with a camera and estimates the emotions using an emotion estimation algorithm. For example, the speech unit calculates an emotion score based on changes in facial expressions and uses polite expressions when the user is relaxed. The speech unit can also record the user's voice and estimate the emotions using voice analysis technology. For example, the speech unit can analyze the tone and speed of the voice to calculate an emotion score and use concise expressions when the user is stressed. Furthermore, the speech unit can collect the user's biometric data (heart rate and electrodermal activity) using a sensor and estimate the emotions using an emotion estimation algorithm. For example, the speech unit can calculate an emotion score based on heart rate fluctuations and use detailed expressions when the user is concentrating. This improves the quality of communication by adjusting the way the speech is expressed based on the user's emotions. Emotion estimation is achieved using an emotion estimation function, for example, an emotion engine or generative 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 speech unit may be performed using AI, or may be performed without using AI. For example, the speech unit may input image data of a user captured by a camera into the generation AI and cause the generation AI to estimate the user's emotions.

[0118] The speech unit can analyze the content of the utterance and automatically display related past utterances. The speech unit can, for example, analyze the content of the utterance using keyword extraction technology and search for related past utterances. For example, the speech unit can automatically search for and display past utterances related to the content of the utterance. The speech unit can also search for related past utterances based on sender information of the content of the utterance. For example, the speech unit can automatically display past conversations related to the content of the utterance. Furthermore, the speech unit can analyze the topic of the content of the utterance and search for related past utterances. For example, the speech unit can automatically display past topics related to the content of the utterance. This enables efficient speech by automatically displaying related past utterances. Some or all of the above-mentioned processing in the speech unit can be performed using, for example, AI, or can be performed without using AI. For example, the speech unit can input the content of the utterance to a generation AI and cause the generation AI to search for related past utterances.

[0119] The speech unit can automatically generate related tasks according to the content of the utterance. For example, the speech unit can analyze the content of the utterance using keyword extraction technology and generate related tasks. For example, the speech unit can automatically generate related tasks based on the content of the utterance and add them to a task list. The speech unit can also generate related tasks based on sender information of the content of the utterance. For example, the speech unit can automatically generate tasks related to the content of the utterance. Furthermore, the speech unit can analyze the topic of the content of the utterance and generate related tasks. For example, the speech unit can automatically generate tasks based on topics related to the content of the utterance. This enables efficient task management by automatically generating related tasks. Some or all of the above-described processing in the speech unit may be performed using, for example, AI, or may be performed without using AI. For example, the speech unit can input the content of the utterance to a generation AI and cause the generation AI to generate related tasks.

[0120] The conversion unit can estimate the user's emotions and adjust the translation method of the speech based on the estimated user emotions. For example, the conversion unit captures the user's facial expressions with a camera and estimates the emotions using an emotion estimation algorithm. For example, the conversion unit calculates an emotion score based on changes in facial expressions and performs a detailed translation if the user is relaxed. The conversion unit can also record the user's voice and estimate the emotions using voice analysis technology. For example, the conversion unit can analyze the tone and speed of the voice to calculate an emotion score and perform a concise translation if the user is stressed. Furthermore, the conversion unit can collect the user's biometric data (heart rate and electrodermal activity) using a sensor and estimate the emotions using an emotion estimation algorithm. For example, the conversion unit can calculate an emotion score based on heart rate fluctuations and perform a detailed translation if the user is concentrating. This improves the quality of communication by adjusting the translation method according to the user's emotions. Emotion estimation is achieved using an emotion estimation function, for example, an emotion engine or a generative AI. The generative AI can be, but is not limited to, a text generation AI (e.g., LLM) or a multimodal generative AI. Some or all of the above-described processing in the conversion unit may be performed using, for example, AI, or may be performed without using AI. For example, the conversion unit may input image data of a user taken with a camera to the generation AI and cause the generation AI to estimate the user's emotions.

[0121] The conversion unit can apply an algorithm for performing a natural translation by taking into account the context of the utterance content. The conversion unit, for example, analyzes the utterance content using context analysis technology and applies an algorithm for performing a natural translation. For example, the conversion unit analyzes the context of the utterance content and performs an appropriate translation. The conversion unit can also select natural expressions based on the context of the utterance content. Furthermore, the conversion unit can also select appropriate vocabulary by taking into account the context of the utterance content. This improves the accuracy of the translation by performing a natural translation that takes into account the context of the utterance content. Some or all of the above-mentioned processing in the conversion unit may be performed using, for example, AI, or may be performed without using AI. For example, the conversion unit can input the utterance content to a generation AI and have the generation AI perform a translation that takes the context into account.

[0122] The conversion unit can appropriately convert technical terms and slang depending on the content of the utterance. For example, the conversion unit analyzes the content of the utterance using keyword extraction technology and appropriately converts technical terms and slang. For example, the conversion unit appropriately converts technical terms in business conversations. The conversion unit can also appropriately convert slang in casual conversations. Furthermore, the conversion unit can also appropriately convert technical terms in technical conversations. This improves the accuracy of translation by performing appropriate conversion depending on the content of the utterance. Some or all of the above-mentioned processing in the conversion unit may be performed using, for example, AI, or may be performed without using AI. For example, the conversion unit can input the content of the utterance to a generation AI and have the generation AI convert technical terms and slang.

[0123] The conversion unit can estimate the user's emotions and adjust the expression style after translation of the utterance based on the estimated user emotions. For example, the conversion unit captures the user's facial expressions with a camera and estimates the emotions using an emotion estimation algorithm. For example, the conversion unit calculates an emotion score based on changes in facial expressions and uses polite expressions when the user is relaxed. The conversion unit can also record the user's voice and estimate the emotions using voice analysis technology. For example, the conversion unit can analyze the tone and speed of the voice to calculate an emotion score and use concise expressions when the user is stressed. Furthermore, the conversion unit can collect the user's biometric data (heart rate and electrodermal activity) using a sensor and estimate the emotions using an emotion estimation algorithm. For example, the conversion unit can calculate an emotion score based on heart rate fluctuations and use detailed expressions when the user is concentrating. This improves the quality of communication by adjusting the expression style after translation according to the user's emotions. Emotion estimation is realized using an emotion estimation function, for example, an emotion engine or a generative AI. The generative 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 conversion unit may be performed using, for example, AI, or may be performed without using AI. For example, the conversion unit may input image data of a user taken with a camera to the generation AI and cause the generation AI to estimate the user's emotions.

[0124] The conversion unit can present multiple translation candidates according to the content of the utterance, allowing the user to select one. The conversion unit, for example, analyzes the content of the utterance using keyword extraction technology and generates multiple translation candidates. For example, the conversion unit generates multiple translation candidates based on the content of the utterance and presents them to the user. The conversion unit can also perform a final translation based on the translation candidate selected by the user. Furthermore, the conversion unit can present appropriate translation candidates according to the content of the utterance. As a result, by presenting multiple translation candidates, the user can select the optimal translation. Some or all of the above-mentioned processing in the conversion unit may be performed using, for example, AI, or may be performed without using AI. For example, the conversion unit can input the content of the utterance to a generation AI and cause the generation AI to generate multiple translation candidates.

[0125] The conversion unit can analyze the content of the utterance and automatically refer to related literature and materials to improve the accuracy of the translation. The conversion unit, for example, analyzes the content of the utterance using keyword extraction technology and searches for related literature and materials. For example, the conversion unit automatically searches for literature related to the content of the utterance and reflects it in the translation. The conversion unit can also automatically refer to materials related to the content of the utterance to improve the accuracy of the translation. Furthermore, the conversion unit can refer to appropriate literature and materials based on the content of the utterance. This improves the accuracy of the translation by referring to related literature and materials. Some or all of the above-mentioned processing in the conversion unit may be performed using, for example, AI, or may be performed without using AI. For example, the conversion unit can input the content of the utterance to a generation AI and cause the generation AI to search for related literature and materials.

[0126] The recognition unit can estimate the user's emotions and adjust the accuracy of speech recognition based on the estimated user emotions. For example, the recognition unit captures the user's facial expressions with a camera and estimates the emotions using an emotion estimation algorithm. For example, the recognition unit calculates an emotion score based on changes in facial expressions, and uses normal speech recognition accuracy when the user is relaxed. The recognition unit can also record the user's voice and estimate the emotions using speech analysis technology. For example, the recognition unit can analyze the tone and speed of the voice to calculate an emotion score and improve the speech recognition accuracy when the user is stressed. Furthermore, the recognition unit can collect the user's biometric data (heart rate and electrodermal activity) using a sensor and estimate the emotions using an emotion estimation algorithm. For example, the recognition unit can calculate an emotion score based on heart rate fluctuations and optimize the speech recognition accuracy when the user is concentrating. This improves the recognition accuracy by adjusting the speech recognition accuracy according to the user's emotions. Emotion estimation is realized using an emotion estimation function, for example, using an emotion engine or generative AI. The generative 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 recognition unit may be performed using, for example, AI, or may be performed without using AI. For example, the recognition unit may input image data of a user taken by a camera to the generation AI and cause the generation AI to estimate the user's emotions.

[0127] The recognition unit can appropriately recognize technical terms and slang depending on the content of the speech to be recognized. The recognition unit, for example, analyzes the speech content using keyword extraction technology and appropriately recognizes technical terms and slang. For example, the recognition unit appropriately recognizes technical terms in business conversations. The recognition unit can also appropriately recognize slang in casual conversations. Furthermore, the recognition unit can also appropriately recognize technical terms in technical conversations. This improves recognition accuracy by performing appropriate recognition depending on the speech content. 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 speech content to a generation AI and have the generation AI recognize technical terms and slang.

[0128] The recognition unit can apply an algorithm for natural recognition by taking into account the context of the speech to be recognized. The recognition unit, for example, analyzes the speech content using context analysis technology and applies an algorithm for natural recognition. For example, the recognition unit analyzes the speech context and performs appropriate recognition. The recognition unit can also select natural expressions based on the speech context. Furthermore, the recognition unit can also select appropriate vocabulary by taking into account the speech context. This improves recognition accuracy by performing natural recognition that takes into account the speech context. 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 the speech content to a generation AI and cause the generation AI to perform recognition that takes the context into account.

[0129] The recognition unit can estimate the user's emotions and adjust the display method of the recognition results based on the estimated user emotions. For example, the recognition unit captures the user's facial expressions with a camera and estimates the emotions using an emotion estimation algorithm. For example, the recognition unit calculates an emotion score based on changes in facial expressions and displays detailed recognition results if the user is relaxed. The recognition unit can also record the user's voice and estimate emotions using voice analysis technology. For example, the recognition unit can analyze the tone and speed of the voice to calculate an emotion score and display a concise recognition result if the user is stressed. Furthermore, the recognition unit can collect the user's biometric data (heart rate and electrodermal activity) using a sensor and estimate emotions using an emotion estimation algorithm. For example, the recognition unit can calculate an emotion score based on heart rate fluctuations and highlight important information if the user is concentrating. This allows the display method of the recognition results to be adjusted according to the user's emotions, improving understanding of the recognition results. Emotion estimation is achieved using an emotion estimation function, for example, an emotion engine or generative 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 recognition unit may be performed using AI, or may be performed without using AI. For example, the recognition unit may input image data of a user captured by a camera into the generation AI and cause the generation AI to estimate the user's emotions.

[0130] The recognition unit can present multiple recognition candidates depending on the content of the speech to be recognized, allowing the user to select one. The recognition unit, for example, analyzes the speech content using keyword extraction technology and generates multiple recognition candidates. For example, the recognition unit generates multiple recognition candidates based on the speech content and presents them to the user. The recognition unit can also display a final recognition result based on the recognition candidate selected by the user. Furthermore, the recognition unit can present appropriate recognition candidates depending on the speech content. As a result, by presenting multiple recognition candidates, the user can select the optimal recognition result. 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 speech content to a generation AI and cause the generation AI to generate multiple recognition candidates.

[0131] The recognition unit can analyze the content of the speech to be recognized and automatically refer to related literature and materials to improve the accuracy of the recognition. For example, the recognition unit can analyze the speech content using keyword extraction technology and search for related literature and materials. For example, the recognition unit can automatically search for literature related to the speech content and reflect it in the recognition. The recognition unit can also automatically refer to materials related to the speech content to improve the accuracy of the recognition. Furthermore, the recognition unit can refer to appropriate literature and materials based on the speech content. This improves the accuracy of the recognition by referring to related literature and materials. 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 speech content to a generation AI and cause the generation AI to search for related literature and materials.

[0132] The conversion unit can estimate the user's emotions and adjust the translation method of the recognition results based on the estimated user emotions. For example, the conversion unit captures the user's facial expressions with a camera and estimates the emotions using an emotion estimation algorithm. For example, the conversion unit calculates an emotion score based on changes in facial expressions and performs a detailed translation if the user is relaxed. The conversion unit can also record the user's voice and estimate the emotions using voice analysis technology. For example, the conversion unit can analyze the tone and speed of the voice to calculate an emotion score and perform a concise translation if the user is stressed. Furthermore, the conversion unit can collect the user's biometric data (heart rate and electrodermal activity) using a sensor and estimate the emotions using an emotion estimation algorithm. For example, the conversion unit can calculate an emotion score based on heart rate fluctuations and perform a detailed translation if the user is concentrating. This improves the accuracy of the translation by adjusting the translation method according to the user's emotions. Emotion estimation is achieved using an emotion estimation function, for example, an emotion engine or a generative AI. The generative AI can be, but is not limited to, a text generation AI (e.g., LLM) or a multimodal generative AI. Some or all of the above-described processing in the conversion unit may be performed using, for example, AI, or may be performed without using AI. For example, the conversion unit may input image data of a user taken with a camera to the generation AI and cause the generation AI to estimate the user's emotions.

[0133] The conversion unit can apply an algorithm for performing a natural translation by taking into account the context of the recognition result. The conversion unit, for example, analyzes the recognition result using context analysis technology and applies an algorithm for performing a natural translation. For example, the conversion unit analyzes the context of the recognition result and performs an appropriate translation. The conversion unit can also select natural expressions based on the context of the recognition result. Furthermore, the conversion unit can also select appropriate vocabulary by taking into account the context of the recognition result. This improves the accuracy of the translation by performing a natural translation that takes into account the context of the recognition result. Some or all of the above-mentioned processing in the conversion unit may be performed using, for example, AI, or may be performed without using AI. For example, the conversion unit can input the recognition result to a generation AI and cause the generation AI to perform a translation that takes the context into account.

[0134] The conversion unit can appropriately convert technical terms and slang depending on the recognition result. The conversion unit, for example, analyzes the recognition result using keyword extraction technology and appropriately converts technical terms and slang. For example, the conversion unit appropriately converts technical terms in business conversations. The conversion unit can also appropriately convert slang in casual conversations. Furthermore, the conversion unit can also appropriately convert technical terms in technical conversations. This improves translation accuracy by performing appropriate conversion depending on the recognition result. Some or all of the above-mentioned processing in the conversion unit may be performed using, for example, AI, or may be performed without using AI. For example, the conversion unit can input the recognition result to a generation AI and have the generation AI convert technical terms and slang.

[0135] The conversion unit can estimate the user's emotions and adjust the post-translation expression of the recognition result based on the estimated user emotions. For example, the conversion unit captures the user's facial expressions with a camera and estimates the emotions using an emotion estimation algorithm. For example, the conversion unit calculates an emotion score based on changes in facial expressions and uses polite expressions when the user is relaxed. The conversion unit can also record the user's voice and estimate the emotions using voice analysis technology. For example, the conversion unit can analyze the tone and speed of the voice to calculate an emotion score and use concise expressions when the user is stressed. Furthermore, the conversion unit can collect the user's biometric data (heart rate and electrodermal activity) using a sensor and estimate the emotions using an emotion estimation algorithm. For example, the conversion unit can calculate an emotion score based on heart rate fluctuations and use detailed expressions when the user is concentrating. This improves translation accuracy by adjusting the post-translation expression according to the user's emotions. Emotion estimation is achieved using an emotion estimation function, for example, an emotion engine or generative 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 conversion unit may be performed using AI, or may be performed without using AI. For example, the conversion unit may input image data of a user captured by a camera into the generation AI and cause the generation AI to estimate the user's emotions.

[0136] The conversion unit can present multiple translation candidates depending on the recognition result, allowing the user to select one. The conversion unit, for example, analyzes the recognition result using keyword extraction technology and generates multiple translation candidates. For example, the conversion unit generates multiple translation candidates based on the recognition result and presents them to the user. The conversion unit can also perform a final translation based on the translation candidate selected by the user. Furthermore, the conversion unit can present appropriate translation candidates depending on the recognition result. This allows the user to select the optimal translation by presenting multiple translation candidates. Some or all of the above-mentioned processing in the conversion unit may be performed using, for example, AI, or may be performed without using AI. For example, the conversion unit can input the recognition result to a generation AI and cause the generation AI to generate multiple translation candidates.

[0137] The conversion unit can analyze the recognition results and automatically refer to related literature and materials to improve the accuracy of the translation. The conversion unit can, for example, analyze the recognition results using keyword extraction technology and search for related literature and materials. For example, the conversion unit can automatically search for literature related to the recognition results and reflect the results in the translation. The conversion unit can also automatically refer to materials related to the recognition results to improve the accuracy of the translation. Furthermore, the conversion unit can refer to appropriate literature and materials based on the recognition results. This improves the accuracy of the translation by referring to related literature and materials. Some or all of the above-mentioned processing in the conversion unit can be performed using, for example, AI, or can be performed without using AI. For example, the conversion unit can input the recognition results to a generation AI and cause the generation AI to search for related literature and materials.

[0138] The management unit can estimate the user's emotions and adjust the learning progress management method based on the estimated user emotions. For example, the management unit captures the user's facial expressions with a camera and estimates the emotions using an emotion estimation algorithm. For example, the management unit calculates an emotion score based on changes in facial expressions and uses a standard learning progress management method if the user is relaxed. The management unit can also record the user's voice and estimate the emotions using voice analysis technology. For example, the management unit can analyze the tone and speed of the voice to calculate an emotion score and simplify the learning progress management method if the user is feeling stressed. Furthermore, the management unit can collect the user's biometric data (heart rate and electrodermal activity) with a sensor and estimate the emotions using an emotion estimation algorithm. For example, the management unit can calculate an emotion score based on heart rate fluctuations and use a detailed learning progress management method if the user is concentrating. This improves learning effectiveness by adjusting the learning progress management method according to the user's emotions. Emotion estimation is achieved using an emotion estimation function, for example, an emotion engine or generative AI. The generation AI may 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 management unit may be performed using AI, for example, or may be performed without using AI. For example, the management unit may input image data of a user taken with a camera into the generation AI and cause the generation AI to estimate the user's emotions.

[0139] The management unit can analyze the learning progress, identify the user's weaknesses, and focus the learning on them. The management unit, for example, analyzes the learning progress using keyword extraction technology to identify the user's weaknesses. For example, the management unit can analyze the learning progress and identify the user's weaknesses. The management unit can also focus the learning on the user's weaknesses. Furthermore, the management unit can analyze the learning progress and propose a learning plan that makes use of the user's strengths. This improves the learning effect by identifying the user's weaknesses and focusing the learning on them. Some or all of the above-mentioned processing in the management unit may be performed using, for example, AI, or may be performed without using AI. For example, the management unit can input the learning progress into a generation AI and have the generation AI identify the user's weaknesses.

[0140] The management unit can automatically generate an appropriate study plan according to the learning progress. For example, the management unit analyzes the learning progress using keyword extraction technology and generates an appropriate study plan. For example, the management unit automatically generates an appropriate study plan based on the learning progress. The management unit can also analyze the user's learning progress and propose an optimal study plan. Furthermore, the management unit can automatically update the study plan according to the learning progress. This enables efficient study by automatically generating a study plan according to the learning progress. Some or all of the above-mentioned processing in the management unit may be performed using, for example, AI, or may be performed without using AI. For example, the management unit can input the learning progress into a generation AI and cause the generation AI to generate an appropriate study plan.

[0141] The management unit can estimate the user's emotions and adjust the display method of the learning progress based on the estimated user emotions. For example, the management unit captures the user's facial expressions with a camera and estimates the emotions using an emotion estimation algorithm. For example, the management unit calculates an emotion score based on changes in facial expressions and displays detailed learning progress if the user is relaxed. The management unit can also record the user's voice and estimate emotions using voice analysis technology. For example, the management unit can analyze the tone and speed of the voice to calculate an emotion score and display a concise learning progress if the user is stressed. Furthermore, the management unit can collect the user's biometric data (heart rate and electrodermal activity) using a sensor and estimate emotions using an emotion estimation algorithm. For example, the management unit can calculate an emotion score based on heart rate fluctuations and highlight important information if the user is concentrating. This improves learning effectiveness by adjusting the display method of the learning progress according to the user's emotions. Emotion estimation is achieved using an emotion estimation function, for example, an emotion engine or a generative AI. The generative 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 management unit may be performed using, for example, AI, or may be performed without using AI. For example, the management unit may input image data of a user taken with a camera into the generation AI and cause the generation AI to estimate the user's emotions.

[0142] The management unit can analyze the learning progress and automatically present relevant learning materials. For example, the management unit can analyze the learning progress using keyword extraction technology and search for relevant learning materials. For example, the management unit can analyze the learning progress and automatically search for and present relevant learning materials. The management unit can also present appropriate learning materials based on the learning progress. Furthermore, the management unit can analyze the learning progress and present learning materials that address the user's weaknesses. This automatically presents relevant learning materials, thereby improving learning effectiveness. Some or all of the above-mentioned processing in the management unit may be performed using AI, for example, or may be performed without using AI. For example, the management unit can input the learning progress into a generation AI and cause the generation AI to search for relevant learning materials.

[0143] The management unit can automatically generate related tasks according to the learning progress. For example, the management unit analyzes the learning progress using keyword extraction technology and generates related tasks. For example, the management unit automatically generates related tasks based on the learning progress and adds them to a task list. The management unit can also automatically generate appropriate tasks according to the learning progress. Furthermore, the management unit can analyze the learning progress and generate tasks that address the user's weaknesses. This enables efficient task management by automatically generating related tasks. Some or all of the above-mentioned processing in the management unit may be performed using, for example, AI, or may be performed without using AI. For example, the management unit can input the learning progress into a generation AI and cause the generation AI to generate related tasks.

[0144] The feedback unit can estimate the user's emotions and adjust the feedback method based on the estimated user emotions. For example, the feedback unit captures the user's facial expressions with a camera and estimates the emotions using an emotion estimation algorithm. For example, the feedback unit calculates an emotion score based on changes in facial expressions and provides detailed feedback if the user is relaxed. The feedback unit can also record the user's voice and estimate the emotions using voice analysis technology. For example, the feedback unit can analyze the tone and speed of the voice to calculate an emotion score and provide concise feedback if the user is stressed. Furthermore, the feedback unit can collect the user's biometric data (heart rate and electrodermal activity) using a sensor and estimate the emotions using an emotion estimation algorithm. For example, the feedback unit can calculate an emotion score based on heart rate fluctuations and provide feedback that emphasizes important information if the user is concentrating. This improves learning effectiveness by adjusting the feedback method according to the user's emotions. Emotion estimation is achieved using an emotion estimation function, for example, an emotion engine or a generative AI. The generative 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 feedback unit may be performed using, for example, AI, or may be performed without using AI. For example, the feedback unit may input image data of the user taken by a camera to the generation AI and cause the generation AI to estimate the user's emotions.

[0145] The feedback unit can analyze the feedback content, identify the user's weaknesses, and provide focused feedback. The feedback unit can, for example, analyze the feedback content using keyword extraction technology to identify the user's weaknesses. For example, the feedback unit can analyze the feedback content and identify the user's weaknesses. The feedback unit can also provide focused feedback based on the user's weaknesses. Furthermore, the feedback unit can analyze the feedback content and provide feedback that makes use of the user's strengths. This improves learning effectiveness by identifying the user's weaknesses and providing focused feedback. Some or all of the above-described processing in the feedback unit can be performed using, for example, AI, or can be performed without using AI. For example, the feedback unit can input the feedback content to a generation AI and cause the generation AI to identify the user's weaknesses.

[0146] The feedback unit can automatically generate an appropriate improvement plan according to the feedback content. The feedback unit, for example, analyzes the feedback content using keyword extraction technology and generates an appropriate improvement plan. For example, the feedback unit automatically generates an appropriate improvement plan based on the feedback content. The feedback unit can also analyze the user's feedback content and propose an optimal improvement plan. Furthermore, the feedback unit can automatically update the improvement plan according to the feedback content. This enables efficient learning by automatically generating an appropriate improvement plan. Some or all of the above-mentioned processing in the feedback unit may be performed using, for example, AI, or may be performed without using AI. For example, the feedback unit can input the feedback content to a generation AI and cause the generation AI to generate an appropriate improvement plan.

[0147] The feedback unit can estimate the user's emotions and adjust the feedback display method based on the estimated user emotions. For example, the feedback unit captures the user's facial expressions with a camera and estimates the emotions using an emotion estimation algorithm. For example, the feedback unit calculates an emotion score based on changes in facial expressions and displays detailed feedback if the user is relaxed. The feedback unit can also record the user's voice and estimate the emotions using voice analysis technology. For example, the feedback unit can analyze the tone and speed of the voice to calculate an emotion score and display brief feedback if the user is stressed. Furthermore, the feedback unit can collect the user's biometric data (heart rate and electrodermal activity) using a sensor and estimate the emotions using an emotion estimation algorithm. For example, the feedback unit can calculate an emotion score based on heart rate fluctuations and highlight important information when the user is concentrating. This improves learning effectiveness by adjusting the feedback display method according to the user's emotions. Emotion estimation is achieved using an emotion estimation function, for example, an emotion engine or a generative AI. The generative 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 feedback unit may be performed using, for example, AI, or may be performed without using AI. For example, the feedback unit may input image data of the user taken by a camera to the generation AI and cause the generation AI to estimate the user's emotions.

[0148] The feedback unit can analyze the feedback content and automatically present relevant study materials. For example, the feedback unit can analyze the feedback content using keyword extraction technology and search for relevant study materials. For example, the feedback unit can analyze the feedback content and automatically search for and present relevant study materials. The feedback unit can also present appropriate study materials based on the feedback content. Furthermore, the feedback unit can analyze the feedback content and present study materials that address the user's weaknesses. This automatically presents relevant study materials, thereby improving learning effectiveness. Some or all of the above-described processing in the feedback unit can be performed using, or without, AI. For example, the feedback unit can input the feedback content to a generation AI and cause the generation AI to search for relevant study materials.

[0149] The feedback unit can automatically generate related tasks according to the feedback content. For example, the feedback unit analyzes the feedback content using keyword extraction technology and generates related tasks. For example, the feedback unit automatically generates related tasks based on the feedback content and adds them to a task list. The feedback unit can also automatically generate appropriate tasks according to the feedback content. Furthermore, the feedback unit can analyze the feedback content and generate tasks that address the user's weaknesses. This enables efficient task management by automatically generating related tasks. Some or all of the above-described processing in the feedback unit may be performed using, for example, AI, or may be performed without using AI. For example, the feedback unit can input the feedback content to a generation AI and cause the generation AI to generate related tasks. === Hard Collateral 1-1 === Each of the multiple elements including the above-mentioned receiving unit, converting unit, replying unit, reply conversion unit, speaking unit, speech conversion unit, recognition unit, recognition conversion unit, progress management unit, speech feedback unit, and emotion estimation function is realized, for example, by at least one of the smart device 14 and the data processing device 12. For example, the receiving unit receives an email via the communication I / F 44 of the smart device 14, and the email is processed by the specific processing unit 290 of the data processing device 12. The converting unit is realized by the specific processing unit 290 of the data processing device 12 and converts the content of the email into a foreign language. The replying unit is realized by the control unit 46A of the smart device 14 and transmits a reply content entered by the user. The reply conversion unit is realized by the specific processing unit 290 of the data processing device 12 and converts the reply content into Japanese. The speaking unit acquires the user's voice using the microphone 38B of the smart device 14. The speech conversion unit is realized by the specific processing unit 290 of the data processing device 12 and converts the voice into a foreign language. The recognition unit is realized by the specific processing unit 290 of the data processing device 12 and converts speech into text. The recognition conversion unit is realized by the specific processing unit 290 of the data processing device 12 and converts text into Japanese. The progress management unit is realized by the specific processing unit 290 of the data processing device 12 and manages the user's learning progress. The speech feedback unit is realized by the control unit 46A of the smart device 14 and provides feedback to improve the accuracy of the user's speech. The emotion estimation function is realized by the specific processing unit 290 of the data processing device 12 and estimates the user's emotion. === Hard Collateral 1-2 === Each of the multiple elements including the above-mentioned receiving unit, converting unit, replying unit, reply converting unit, speaking unit, speech converting unit, recognition unit, recognition converting unit, progress management unit, speech feedback unit, and emotion estimation function is realized, for example, by at least one of the smart glasses 214 and the data processing device 12. For example, the receiving unit receives an email via the communication I / F 44 of the smart glasses 214, and the email is processed by the specific processing unit 290 of the data processing device 12. The converting unit is realized by the specific processing unit 290 of the data processing device 12 and converts the content of the email into a foreign language. The replying unit is realized by the control unit 46A of the smart glasses 214 and transmits the reply content entered by the user. The reply converting unit is realized by the specific processing unit 290 of the data processing device 12 and converts the reply content into Japanese. The speaking unit acquires the user's voice using the microphone 238 of the smart glasses 214. The speech converting unit is realized by the specific processing unit 290 of the data processing device 12 and converts the voice into a foreign language. The recognition unit is realized by the specific processing unit 290 of the data processing device 12 and converts speech into text. The recognition conversion unit is realized by the specific processing unit 290 of the data processing device 12 and converts text into Japanese. The progress management unit is realized by the specific processing unit 290 of the data processing device 12 and manages the user's learning progress. The speech feedback unit is realized by the control unit 46A of the smart glasses 214 and provides feedback to improve the accuracy of the user's speech. The emotion estimation function is realized by the specific processing unit 290 of the data processing device 12 and estimates the user's emotion. === Hard Collateral 1-3 === Each of the multiple elements including the above-mentioned receiving unit, converting unit, replying unit, reply conversion unit, speaking unit, speech conversion unit, recognition unit, recognition conversion unit, progress management unit, speech feedback unit, and emotion estimation function is realized, for example, by at least one of the headset type terminal 314 and the data processing device 12. For example, the receiving unit receives an email via the communication I / F 44 of the headset type terminal 314, and the email is processed by the specific processing unit 290 of the data processing device 12. The converting unit is realized by the specific processing unit 290 of the data processing device 12 and converts the content of the email into a foreign language. The replying unit is realized by the control unit 46A of the headset type terminal 314 and transmits the reply content entered by the user. The reply conversion unit is realized by the specific processing unit 290 of the data processing device 12 and converts the reply content into Japanese. The speaking unit acquires the user's voice using the microphone 238 of the headset type terminal 314. The speech conversion unit is realized by the specific processing unit 290 of the data processing device 12 and converts the voice into a foreign language. The recognition unit is realized by the specific processing unit 290 of the data processing device 12 and converts speech into text. The recognition conversion unit is realized by the specific processing unit 290 of the data processing device 12 and converts text into Japanese. The progress management unit is realized by the specific processing unit 290 of the data processing device 12 and manages the user's learning progress. The speech feedback unit is realized by the control unit 46A of the headset terminal 314 and provides feedback to improve the accuracy of the user's speech. The emotion estimation function is realized by the specific processing unit 290 of the data processing device 12 and estimates the user's emotion. === Hard Collateral 1-4 === Each of the multiple elements including the above-mentioned receiving unit, converting unit, replying unit, reply converting unit, speaking unit, speech converting unit, recognition unit, recognition converting unit, progress managing unit, speech feedback unit, and emotion estimation function is realized, for example, by at least one of the robot 414 and the data processing device 12. For example, the receiving unit receives an email via the communication I / F 44 of the robot 414, and the email is processed by the specific processing unit 290 of the data processing device 12. The converting unit is realized by the specific processing unit 290 of the data processing device 12 and converts the content of the email into a foreign language. The replying unit is realized by the control unit 46A of the robot 414 and transmits the reply content entered by the user. The reply converting unit is realized by the specific processing unit 290 of the data processing device 12 and converts the reply content into Japanese. The speaking unit acquires the user's voice using the microphone 238 of the robot 414. The speech converting unit is realized by the specific processing unit 290 of the data processing device 12 and converts the voice into a foreign language. The recognition unit is realized by the specific processing unit 290 of the data processing device 12 and converts speech into text. The recognition conversion unit is realized by the specific processing unit 290 of the data processing device 12 and converts text into Japanese. The progress management unit is realized by the specific processing unit 290 of the data processing device 12 and manages the user's learning progress. The speech feedback unit is realized by the control unit 46A of the robot 414 and provides feedback to improve the accuracy of the user's speech. The emotion estimation function is realized by the specific processing unit 290 of the data processing device 12 and estimates the user's emotion.

[0150] The system according to the embodiment is not limited to the above-described example, and various modifications are possible, for example, as follows.

[0151] The foreign language acquisition support system may also include a learning style analysis unit that analyzes the user's learning style and suggests the optimal learning method. The learning style analysis unit may, for example, analyze the user's learning history and learning speed, and suggest video materials if the user prefers visual learning, or audio materials if the user prefers auditory learning. The learning style analysis unit may also analyze the user's study time period and concentration span to suggest the optimal study schedule. Furthermore, the learning style analysis unit may adjust the learning method based on the user's feedback to support efficient learning. This improves learning effectiveness by providing the optimal learning method according to the user's learning style.

[0152] The foreign language learning assistance system may also include an emotion-adaptive learning unit that estimates the user's emotions and adjusts the learning content based on the estimated emotions. For example, the emotion-adaptive learning unit provides relaxing content when the user is feeling stressed, and provides more difficult content when the user is concentrating. The emotion-adaptive learning unit can also adjust the learning pace according to the user's emotions, shortening the learning time when the user is tired and extending the learning time when the user is in good spirits. Furthermore, the emotion-adaptive learning unit can adjust learning feedback based on the user's emotions, providing detailed feedback when the user has positive emotions and brief feedback when the user has negative emotions. This improves learning effectiveness by adjusting the learning content according to the user's emotions.

[0153] The foreign language acquisition assistance system may also include a progress prediction unit that predicts the user's learning progress based on the user's learning history. The progress prediction unit, for example, analyzes the content and learning speed of the user's past learning to predict the user's future learning progress. The progress prediction unit can also predict the time required to achieve the user's learning goals and propose a learning plan based on the user's learning goals. Furthermore, the progress prediction unit can evaluate the effectiveness of learning based on the user's learning history and propose an efficient learning method. This improves the learning effectiveness by predicting the user's learning progress and providing an efficient learning plan.

[0154] The foreign language learning assistance system may also include a motivation management unit that estimates the user's emotions and maintains the user's motivation for learning based on the estimated emotions. For example, the motivation management unit displays a praising message when the user has positive emotions toward learning, and an encouraging message when the user has negative emotions. The motivation management unit may also adjust learning goals according to the user's emotions, setting lower goals when the user is feeling stressed and higher goals when the user is relaxed. Furthermore, the motivation management unit may provide learning rewards based on the user's emotions, increasing the rewards when the user has positive emotions and decreasing the rewards when the user has negative emotions. This improves learning effectiveness by managing motivation according to the user's emotions.

[0155] The foreign language acquisition support system may also include an environment optimization unit for optimizing the user's learning environment. The environment optimization unit may, for example, analyze the user's learning location and time period and propose an optimal learning environment. The environment optimization unit may also propose appropriate learning tools and learning materials depending on the user's learning environment. Furthermore, the environment optimization unit may monitor the user's learning environment in real time and adjust the learning method in response to changes in the environment. This may improve learning effectiveness by optimizing the user's learning environment.

[0156] The foreign language learning assistance system may also include a feedback adjustment unit that estimates the user's emotions and adjusts learning feedback based on the estimated emotions. For example, the feedback adjustment unit provides detailed feedback when the user has positive emotions and provides brief feedback when the user has negative emotions. The feedback adjustment unit may also adjust the timing of feedback according to the user's emotions, providing immediate feedback when the user is relaxed and providing delayed feedback when the user is stressed. Furthermore, the feedback adjustment unit may adjust the content of the feedback based on the user's emotions, providing detailed suggestions for improvement when the user is concentrating and simple suggestions for improvement when the user is tired. This improves learning effectiveness by adjusting feedback according to the user's emotions.

[0157] The foreign language acquisition assistance system may also include an effect evaluation unit that evaluates the effectiveness of learning based on the user's learning data. The effect evaluation unit, for example, analyzes the user's learning history and test results to evaluate the effectiveness of learning. The effect evaluation unit can also evaluate the user's achievement level and adjust the learning plan based on the user's learning goals. Furthermore, the effect evaluation unit can suggest efficient learning methods based on the user's learning data. This improves learning effectiveness by evaluating the user's learning effectiveness and providing efficient learning methods.

[0158] The foreign language learning assistance system may also include an emotion-adaptive progress management unit that estimates the user's emotions and manages learning progress based on the estimated emotions. For example, the emotion-adaptive progress management unit displays detailed progress when the user has positive emotions and displays brief progress when the user has negative emotions. The emotion-adaptive progress management unit may also adjust progress evaluation criteria according to the user's emotions, relaxing the evaluation criteria when the user is stressed and tightening the evaluation criteria when the user is relaxed. Furthermore, the emotion-adaptive progress management unit may adjust progress feedback based on the user's emotions, providing detailed feedback when the user is concentrating and simple feedback when the user is tired. This improves learning effectiveness by managing progress according to the user's emotions.

[0159] The foreign language acquisition assistance system may also include a learning optimization unit that maximizes learning effectiveness based on the user's learning data. The learning optimization unit may analyze, for example, the user's learning history and test results to propose an optimal learning method. The learning optimization unit may also propose an efficient learning plan based on the user's learning goals. Furthermore, the learning optimization unit may monitor learning progress in real time based on the user's learning data and adjust the learning method as necessary. This improves learning effectiveness by providing an optimal learning method that maximizes the user's learning effectiveness.

[0160] The foreign language learning assistance system may also include an emotion-adaptive reward unit that estimates the user's emotion and provides a learning reward based on the estimated emotion. For example, the emotion-adaptive reward unit increases the reward when the user has a positive emotion and decreases the reward when the user has a negative emotion. The emotion-adaptive reward unit may also adjust the type of reward according to the user's emotion, providing a physical reward when the user is relaxed and a mental reward when the user is stressed. Furthermore, the emotion-adaptive reward unit may adjust the timing of the reward based on the user's emotion, providing an immediate reward when the user is concentrating and a later reward when the user is tired. This improves learning effectiveness by providing rewards according to the user's emotion.

[0161] The processing flow of the second embodiment will be briefly explained below.

[0162] Step 1: The receiving unit receives emails received by the user. For example, the emails can be obtained from an email server. Step 2: The conversion unit converts the email received by the receiving unit into a foreign language. For example, the content of the email can be converted into a foreign language using a text translation engine. Step 3: The reply unit replies based on the email converted by the conversion unit. For example, it can send a reply that the user entered. Step 4: The reply conversion unit converts the email returned by the reply unit into Japanese. For example, the reply content can be converted into Japanese using a text translation engine. Step 5: The user speaks in the speech unit. For example, the user's voice can be acquired using a microphone. Step 6: The speech conversion unit converts the speech uttered by the speech unit into a foreign language. For example, a speech translation engine can be used to convert the speech into the foreign language. Step 7: The recognition unit recognizes the speech converted by the speech conversion unit. For example, a speech recognition engine can be used to convert the speech into text. Step 8: The recognition conversion unit converts the speech recognized by the recognition unit into Japanese. For example, a text translation engine can be used to convert the text into Japanese.

[0163] 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.

[0164] 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 the generative AI include a neural network (NN) and a neural network (NN). 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 (e.g., still image data or video data). 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 one or more data formats of voice data, text data, image data, etc. 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 may perform various processes, but is not limited to these examples. The AI ​​may also be an AI agent. When the processing of each of the above-mentioned parts is performed by an AI, the processing may be performed in part or entirely by the AI, but is not limited to these examples. The processing performed by an AI including the generative AI may be replaced with rule-based processing, and rule-based processing may be replaced with processing performed by an AI including the generative AI.

[0165] 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.

[0166] The correspondence between each part and the device or control part is not limited to the example described above, and various modifications are possible.

[0167] [Second embodiment] FIG. 3 shows an example of the configuration of a data processing system 210 according to the second embodiment.

[0168] 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.

[0169] 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.

[0170] 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.

[0171] 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.

[0172] 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).

[0173] 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.

[0174] 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.

[0175] 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.

[0176] 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.

[0177] 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.

[0178] 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.

[0179] 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.

[0180] 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 including an instruction, as well as inference data such as audio data indicating speech, text data indicating text, and image data indicating an image (e.g., still image data or video data). 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 one or more data formats, such as audio data, text data, and image 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 models 58 include AIs other than the generation AI. Examples of AIs other than the generation AI include, but are not limited to, linear regression, logistic regression, decision trees, random forests, support vector machines (SVMs), k-means clustering, convolutional neural networks (CNNs), recurrent neural networks (RNNs), generative adversarial networks (GANs), and naive Bayes. These AIs can perform various types of processing, but are not limited to these examples. The AI ​​may also be an AI agent. When the processing of each of the above-described parts is performed by an AI, the processing may be performed in part or entirely by the AI, but is not limited to these examples. Processing performed by an AI, including the generation AI, may be replaced with rule-based processing, and rule-based processing may be replaced with processing performed by an AI, including the generation AI.

[0181] 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.

[0182] The correspondence between each part and the device or control part is not limited to the example described above, and various modifications are possible.

[0183] [Third embodiment] FIG. 5 shows an example of the configuration of a data processing system 310 according to the third embodiment.

[0184] 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.

[0185] 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.

[0186] 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.

[0187] 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.

[0188] 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).

[0189] 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.

[0190] 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.

[0191] 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.

[0192] 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.

[0193] 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.

[0194] 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.

[0195] 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.

[0196] 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 including an instruction, as well as inference data such as audio data indicating speech, text data indicating text, and image data indicating an image (e.g., still image data or video data). 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 one or more data formats, such as audio data, text data, and image 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 models 58 include AIs other than the generation AI. Examples of AIs other than the generation AI include, but are not limited to, linear regression, logistic regression, decision trees, random forests, support vector machines (SVMs), k-means clustering, convolutional neural networks (CNNs), recurrent neural networks (RNNs), generative adversarial networks (GANs), and naive Bayes. These AIs can perform various types of processing, but are not limited to these examples. The AI ​​may also be an AI agent. When the processing of each of the above-described parts is performed by an AI, the processing may be performed in part or entirely by the AI, but is not limited to these examples. Processing performed by an AI, including the generation AI, may be replaced with rule-based processing, and rule-based processing may be replaced with processing performed by an AI, including the generation AI.

[0197] 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.

[0198] The correspondence between each part and the device or control part is not limited to the example described above, and various modifications are possible.

[0199] [Fourth embodiment] FIG. 7 shows an example of the configuration of a data processing system 410 according to the fourth embodiment.

[0200] 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.

[0201] 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.

[0202] 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.

[0203] 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.

[0204] 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).

[0205] 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.

[0206] 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.

[0207] 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.

[0208] 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.

[0209] 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.

[0210] 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.

[0211] 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.

[0212] 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.

[0213] 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 including an instruction, as well as inference data such as audio data indicating speech, text data indicating text, and image data indicating an image (e.g., still image data or video data). 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 one or more data formats, such as audio data, text data, and image 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 models 58 include AIs other than the generation AI. Examples of AIs other than the generation AI include, but are not limited to, linear regression, logistic regression, decision trees, random forests, support vector machines (SVMs), k-means clustering, convolutional neural networks (CNNs), recurrent neural networks (RNNs), generative adversarial networks (GANs), and naive Bayes. These AIs can perform various types of processing, but are not limited to these examples. The AI ​​may also be an AI agent. When the processing of each of the above-described parts is performed by an AI, the processing may be performed in part or entirely by the AI, but is not limited to these examples. Processing performed by an AI, including the generation AI, may be replaced with rule-based processing, and rule-based processing may be replaced with processing performed by an AI, including the generation AI.

[0214] 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.

[0215] The correspondence between each part and the device or control part is not limited to the example described above, and various modifications are possible.

[0216] 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.

[0217] 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.

[0218] 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.

[0219] 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).

[0220] Human emotions are based on various balances, such as posture and blood sugar levels. When these balances deviate from the ideal, a state of discomfort is expressed, and when they approach the ideal, a state of pleasure is expressed. Emotions can also be created for robots, cars, and motorcycles, based on various balances, such as posture and remaining battery life. When these balances deviate from the ideal, a state of discomfort is expressed, and when they approach the ideal, a state of pleasure is expressed. An emotion map can be generated, for example, based on Dr. Mitsuyoshi's emotion map (Research on speech emotion recognition and brain physiological signal analysis systems for emotions, Tokushima University, doctoral dissertation: https: / / ci.nii.ac.jp / naid / 500000375379). The left half of the emotion map lists emotions belonging to the "reaction" domain, where sensation is dominant. The right half of the emotion map lists emotions belonging to the "situation" domain, where situational awareness is dominant.

[0221] 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."

[0222] 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.

[0223] 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.

[0224] 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.

[0225] 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.

[0226] 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.

[0227] 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.

[0228] 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.

[0229] 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.

[0230] 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.

[0231] 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.

[0232] The above-described description and illustrations are a detailed explanation of the parts related to the technology of the present disclosure and are merely an example of the technology of the present disclosure. For example, the above description of the configuration, functions, actions, and effects is an explanation of an example of the configuration, functions, actions, and effects of the parts related to the technology of the present disclosure. Therefore, it goes without saying that unnecessary parts may be deleted, new elements may be added, or replacements may be made to the above-described description and illustrations within the scope of the gist of the technology of the present disclosure. Furthermore, in order to avoid confusion and to facilitate understanding of the parts related to the technology of the present disclosure, the above-described description and illustrations omit explanations of common technical knowledge that do not require particular explanation to enable the implementation of the technology of the present disclosure.

[0233] 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.

[0234] [Explanation of symbols]

[0235] 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 receiving unit for receiving emails; a conversion unit that converts the email received by the receiving unit into a foreign language; a reply unit that replies based on the email converted by the conversion unit; a reply conversion unit that converts the email returned by the reply unit into Japanese; a speech unit that produces speech; a speech conversion unit that converts the voice uttered by the speech unit into a foreign language; a recognition unit that recognizes the speech converted by the speech conversion unit; a recognition conversion unit that converts the speech recognized by the recognition unit into Japanese; Equipped with A system characterized by:

2. Equipped with a progress management unit that manages the user's learning progress The system of claim 1 .

3. Equipped with a speech feedback unit to improve speech accuracy The system of claim 1 .

4. The conversion unit Converting emails into foreign languages ​​using generative AI The system of claim 1 .

5. The conversion unit Converting speech into a foreign language using generative AI The system of claim 1 .

6. The recognition unit Recognizing speech using generative AI The system of claim 1 .

7. The receiving unit Estimate the user's emotions and adjust the timing of receiving emails based on the estimated user emotions The system of claim 1 .

8. The receiving unit Analyze the content of incoming emails and change the notification method depending on their importance The system of claim 1 .

9. The receiving unit Set priorities and adjust the order of receipt based on the sender information of the emails you receive. The system of claim 1 .

Images