System

Abstract

An object of a system according to an embodiment is to provide an environment in which a user can naturally acquire a second native language.SOLUTION: A system includes a translation unit, a conversation unit, a training unit, and a scenario unit. The translation unit has a multilingual conversation function of translating a user's utterance in real time and responding in a designated language. The conversation component comprises a multi-party conversation algorithm that allows multiple users to converse in different languages at the same time. The training unit includes an English 4-technique approach function that provides training for evenly learning four techniques of listening, speaking, reading, and writing. The scenario unit includes a native language acquisition program that generates a scenario using the second native language in daily life and provides the scenario to the user.SELECTED DRAWING: Figure 1

Description

[Technical Field]

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

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

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

[0004] Conventional technology has made it difficult to provide an environment for natural acquisition of a second native language, and there has been a lack of effective means for bilingual education.

[0005] The system according to the embodiment aims to provide an environment in which a user can naturally acquire a second native language. [Means for solving the problem]

[0006] The system according to the embodiment includes a translation unit, a conversation unit, a training unit, and a scenario unit. The translation unit includes a multilingual conversation function that translates a user's speech in real time and responds in a specified language. The conversation unit includes a multi-party conversation algorithm that enables multiple users to converse simultaneously in different languages. The training unit includes an English four-technique approach function that provides training to equally master the four skills of listening, speaking, reading, and writing. The scenario unit includes a native language acquisition program that generates scenarios for using a second native language in daily life and provides them to the user. [Effects of the Invention]

[0007] The system according to the embodiment can provide an environment in which a user can naturally acquire a second native 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 bilingual development and language acquisition support system according to an embodiment of the present invention uses generative AI to help users naturally acquire multiple languages. The bilingual development and language acquisition support system includes a translation unit with a multilingual conversation function that translates a user's speech in real time and responds in a specified language; a conversation unit with a multi-party conversation algorithm that enables multiple users to converse simultaneously in different languages; a training unit with an English four-technique approach function that provides training for equally mastering the four skills of listening, speaking, reading, and writing; and a scenario unit with a native language acquisition program that generates and provides scenarios for using a second native language in daily life. For example, the bilingual development and language acquisition support system helps users naturally use multiple languages ​​in their daily lives. For example, if a user wants to learn Japanese and English simultaneously, using this system allows them to use both languages ​​naturally in everyday conversation. This allows users to become bilingual unconsciously. The bilingual development and language acquisition support system also allows multiple users to converse simultaneously in different languages. For example, if a family has a father who speaks English and a mother who speaks Japanese, and a child who speaks both languages, using this system allows all family members to communicate smoothly. This allows the child to naturally acquire both languages. Furthermore, the bilingual development and language consolidation support system helps users acquire the four skills of listening, speaking, reading, and writing in a balanced manner. For example, if a user wants to improve their English listening skills, they can use this system to receive training specifically focused on listening. Similarly, they can receive balanced training in the skills of speaking, reading, and writing. Finally, the bilingual development and language consolidation support system helps users naturally acquire a second native language. For example, if a user wants to acquire English as a second native language, using this system allows them to use English naturally in their daily lives.This allows users to unconsciously acquire English as a second native language. This allows the bilingual development and language consolidation support system to help users naturally acquire multiple languages. For example, users can naturally use multiple languages ​​in their daily lives and become bilingual. Furthermore, multiple users can simultaneously converse in different languages, enabling smooth communication. Furthermore, users can acquire the four skills of listening, speaking, reading, and writing in a balanced manner, naturally acquiring a second native language.

[0029] A bilingual development and language acquisition support system according to an embodiment includes a translation unit, a conversation unit, a training unit, and a scenario unit. The translation unit translates a user's speech in real time and responds in a specified language. For example, the translation unit uses a generation AI to translate the user's speech in real time and respond in an appropriate language. The translation unit can also estimate the user's emotions and adjust the tone and expression of the translation based on the estimated user's emotions. For example, if the user is nervous, the generation AI can translate in a gentler tone and use expressions that create a sense of security. The translation unit can also improve the accuracy of the translation by referring to the user's past speech history. For example, the generation AI can memorize specific phrases and expressions used by the user in the past and reuse them in similar contexts. Furthermore, the translation unit can automatically select technical terms according to the user's field of expertise. For example, if the user works in the medical field, the generation AI can prioritize medical terminology when translating. The conversation unit enables multiple users to converse simultaneously in different languages. For example, the conversation unit enables multiple users to converse simultaneously in different languages ​​using the generation AI. The conversation unit can also estimate the user's emotions and adjust the way the conversation proceeds based on the estimated user's emotions. For example, if the user is nervous, the generation AI can proceed with the conversation at a slower pace. The conversation unit can also optimize the flow of the conversation by referring to the user's past conversation history. For example, the generation AI can memorize topics the user has previously discussed and incorporate related topics into the conversation. The conversation unit can also select conversation topics based on the user's areas of interest. For example, the generation AI can select conversation topics based on the user's areas of interest (sports, music, etc.). The training unit provides training to help the user acquire the four skills of listening, speaking, reading, and writing in a balanced manner. For example, the training unit uses the generation AI to provide training to help the user acquire the four skills of listening, speaking, reading, and writing in a balanced manner.The training unit can also estimate the user's emotions and adjust the difficulty of the training based on the estimated user's emotions. For example, if the user is nervous, the generation AI can provide easy training and gradually increase the difficulty. The training unit can also optimize the training content by referring to the user's past learning history. For example, the generation AI can memorize what the user has learned in the past and provide related training. The training unit can also select a training method according to the user's learning style. For example, if the user is a visual learner, the generation AI can provide training using visual materials. The scenario unit can generate scenarios using the second native language in daily life and provide them to the user. For example, the scenario unit can use the generation AI to generate scenarios using the second native language in daily life and provide them to the user. The scenario unit can also estimate the user's emotions and adjust the content of the scenario based on the estimated user's emotions. For example, if the user is nervous, the generation AI can provide a scenario that helps the user relax. The scenario unit can also improve the accuracy of the scenario by referring to the user's past scenario history. For example, the generation AI can memorize scenarios the user has used in the past and provide related scenarios. The scenario unit can also select scenarios according to the user's lifestyle. For example, if a user has a busy lifestyle, the generation AI can provide a scenario that can be completed in a short time. This allows the bilingual development and language consolidation support system according to the embodiment to support the user in naturally acquiring multiple languages.

[0030] The translation unit can use a generation AI to translate a user's utterance in real time and respond in an appropriate language. The generation AI is realized, for example, using a specific AI model or algorithm. For example, the generation AI can translate a user's utterance in real time and respond in an appropriate language. For example, the generation AI inputs the user's utterance as text data and outputs the translation result as text data. The generation AI can also input the user's utterance as audio data and output the translation result as audio data. Furthermore, the generation AI can analyze the user's utterance and provide an appropriate translation according to the context. For example, the generation AI understands the intent of the user's utterance and provides an appropriate translation. As a result, the use of the generation AI improves the accuracy and speed of translation. Some or all of the above-mentioned processing in the translation unit may be performed, for example, using the generation AI, or may be performed without using the generation AI. For example, the translation unit can perform translation using a generation AI that inputs the user's utterance as text data and outputs the translation result as text data.

[0031] The conversation unit can use a generation AI to enable multiple users to converse simultaneously in different languages. The generation AI is realized, for example, using a specific AI model or algorithm. For example, the generation AI enables multiple users to converse simultaneously in different languages. For example, the generation AI translates each user's utterance in real time and responds to other users in an appropriate language. The generation AI can also analyze each user's utterance and provide an appropriate translation based on the context. For example, the generation AI understands the intent of each user's utterance and provides an appropriate translation. This enables smooth communication between users who speak different languages ​​by using the generation AI. Some or all of the above-described processing in the conversation unit can be performed, for example, using the generation AI, or can be performed without using the generation AI. For example, the conversation unit can conduct a conversation using a generation AI that inputs each user's utterance as text data and outputs the translation result as text data.

[0032] The training unit can use a generation AI to provide training for balanced acquisition of the four techniques of listening, speaking, reading, and writing. The generation AI is realized, for example, using a specific AI model or algorithm. For example, the generation AI provides training for balanced acquisition of the four techniques of listening, speaking, reading, and writing. For example, the generation AI provides training for improving a user's listening ability. For example, the generation AI can also provide training for improving a user's speaking ability. For example, the generation AI can also provide training for improving a user's reading ability. For example, the generation AI can also provide training for improving a user's writing ability. In this way, the generation AI can be used to acquire the four techniques in a balanced manner. Some or all of the above-described processing in the training unit may be performed, for example, using the generation AI, or may be performed without using the generation AI. For example, the training unit can perform training using a generation AI that provides training for improving a user's listening ability.

[0033] The scenario unit can use the generation AI to generate scenarios in which the second native language is used in daily life and provide them to the user. The generation AI is realized, for example, using a specific AI model or algorithm. For example, the generation AI can generate scenarios in which the second native language is used in daily life and provide them to the user. For example, the generation AI can analyze the user's daily life situation and generate an appropriate scenario. For example, the generation AI can also generate scenarios that match the user's lifestyle. For example, the generation AI can estimate the user's emotions and adjust the content of the scenario based on the estimated user's emotions. In this way, the generation AI can enable the user to naturally acquire the second native language. Some or all of the above-mentioned processing in the scenario unit can be performed, for example, using the generation AI, or can be performed without using the generation AI. For example, the scenario unit can provide a scenario using a generation AI that analyzes the user's daily life situation and generates an appropriate scenario.

[0034] The translation unit can improve the accuracy of the translation by referring to the user's past speech history during translation. The translation unit, for example, improves the accuracy of the translation by referring to the user's past speech history. For example, the translation unit uses a generation AI to memorize specific phrases and expressions used by the user in the past and reuse them in similar contexts. The translation unit can also prioritize frequently used words and phrases from the user's past speech history in the translation. Furthermore, the translation unit can analyze the user's past speech history to understand grammatical and vocabulary trends and improve the accuracy of the translation. Thus, by referring to the past speech history, the accuracy of the translation is improved. The speech history is stored, for example, as text data or audio data. Some or all of the above-described processing in the translation unit may be performed using, for example, the generation AI, or may be performed without using the generation AI. For example, the translation unit can perform translation using a generation AI that improves the accuracy of the translation by referring to the user's past speech history.

[0035] The translation unit can automatically select technical terms according to the user's field of expertise during translation. For example, the translation unit automatically selects technical terms according to the user's field of expertise. For example, if the user is in the medical field, the translation unit may have the generation AI prioritize medical terminology during translation. Furthermore, if the user is in the technical field, the translation unit may have the generation AI appropriately incorporate technical terminology into the translation. Furthermore, the translation unit may automatically select relevant technical terms based on the user's field of expertise to improve the accuracy of the translation. This allows translations to be performed using appropriate terminology according to the field of expertise. The specific type of field of expertise, such as medical, legal, or technical, and the selection method, must be clearly defined. Some or all of the above-described processing in the translation unit may be performed using, for example, the generation AI, or may be performed without the generation AI. For example, the translation unit may perform translations using a generation AI that automatically selects technical terms according to the user's field of expertise.

[0036] The translation unit can adjust the translation speed during translation according to the user's speaking speed. The translation unit adjusts the translation speed according to, for example, the user's speaking speed. For example, if the user speaks quickly, the generation AI can quickly translate and provide a real-time response. Alternatively, if the user speaks slowly, the generation AI can carefully translate and provide an accurate response. Furthermore, the translation unit can automatically adjust the translation speed according to the user's speaking speed, enabling smooth conversation. This allows translation to be performed at an appropriate speed according to the user's speaking speed. It is necessary to clearly define a specific measurement method or standard for the speaking speed, such as the number of words per unit time. Some or all of the above-described processing in the translation unit may be performed using, for example, the generation AI, or may be performed without using the generation AI. For example, the translation unit can perform translation using a generation AI that adjusts the translation speed according to the user's speaking speed.

[0037] The translation unit can use region-specific expressions during translation, taking into account the user's geographical location information. The translation unit can use region-specific expressions, for example, taking into account the user's geographical location information. For example, if the user is in the United States, the translation unit can have the generation AI use American English expressions to translate. Also, if the user is in the United Kingdom, the translation unit can have the generation AI use British English expressions to translate. Furthermore, the translation unit can appropriately incorporate region-specific slang and expressions into the translation based on the user's geographical location information. This allows translation to be performed using appropriate region-specific expressions. It is necessary to clarify the specific acquisition and usage methods of geographical location information, such as GPS data or IP address. Some or all of the above-described processing in the translation unit can be performed using, for example, the generation AI, or can be performed without using the generation AI. For example, the translation unit can perform translation using a generation AI that uses region-specific expressions while taking into account the user's geographical location information.

[0038] The translation unit can analyze the user's social media activity and use relevant expressions during translation. For example, the translation unit can analyze the user's social media activity and use relevant expressions. For example, the translation unit can incorporate phrases and expressions frequently used by the user on social media into the translation using a generation AI. The translation unit can also identify the user's interests and concerns from their social media activity and use relevant expressions in the translation. Furthermore, the translation unit can analyze the content of the user's social media posts and translate them with an appropriate tone and style. This allows the translation to be performed with appropriate expressions based on the social media activity. The specific content of the social media activity, such as the content of the posts and the number of likes, and the analysis method, need to be clearly defined. Some or all of the above-described processing in the translation unit can be performed using, for example, a generation AI, or can be performed without using a generation AI. For example, the translation unit can analyze the user's social media activity and use a generation AI that uses relevant expressions to perform the translation.

[0039] The translation unit can customize the translation method by reflecting the user's past feedback during translation. For example, the translation unit customizes the translation method by reflecting the user's past feedback. For example, the translation unit allows the generation AI to adjust the tone and style of the translation based on feedback provided by the user in the past. The translation unit can also learn and apply preferred translation methods from the user's past feedback. Furthermore, the translation unit can also allow the generation AI to improve the accuracy and naturalness of the translation by reflecting the user's feedback. This allows translation to be performed in an appropriate manner based on the past feedback. The specific content and acquisition method of the feedback, such as user surveys or evaluation comments, need to be clarified. Some or all of the above-described processing in the translation unit may be performed using, for example, the generation AI, or may be performed without using the generation AI. For example, the translation unit can perform translation using a generation AI that customizes the translation method by reflecting the user's past feedback.

[0040] During a conversation, the conversation unit can optimize the flow of the conversation by referring to the user's past conversation history. The conversation unit, for example, optimizes the flow of the conversation by referring to the user's past conversation history. For example, the conversation unit uses a generation AI to store topics that the user has previously discussed and incorporate related topics into the conversation. The conversation unit can also prioritize preferred topics from the user's past conversation history. Furthermore, the conversation unit can analyze the user's past conversation history to achieve a smooth conversation flow. This allows the conversation to have an appropriate flow based on the past conversation history. The conversation history is stored, for example, as text data or audio data. Some or all of the above-described processing in the conversation unit may be performed, for example, using the generation AI, or may be performed without using the generation AI. For example, the conversation unit can conduct a conversation using a generation AI that optimizes the flow of the conversation by referring to the user's past conversation history.

[0041] During a conversation, the conversation unit can select a conversation topic based on the user's field of interest. The conversation unit, for example, selects a conversation topic based on the user's field of interest. For example, the conversation unit uses a generation AI to select a conversation topic based on the user's field of interest (sports, music, etc.). The conversation unit can also incorporate topics of interest from the user's past search history into the conversation. Furthermore, the conversation unit can analyze the user's social media activity and reflect related topics in the conversation. This allows the conversation to be conducted on an appropriate topic based on the user's field of interest. The specific type and selection method of the field of interest, such as hobbies or occupation, need to be clearly defined. Some or all of the above-mentioned processing in the conversation unit may be performed using, for example, a generation AI, or may be performed without using a generation AI. For example, the conversation unit can conduct a conversation using a generation AI that selects a conversation topic based on the user's field of interest.

[0042] The conversation unit can adjust the tempo of the conversation during a conversation depending on the frequency of the user's speech. The conversation unit, for example, adjusts the tempo of the conversation depending on the frequency of the user's speech. For example, if the user speaks frequently, the conversation unit causes the generation AI to conduct the conversation at a fast tempo. Also, if the user speaks slowly, the conversation unit can cause the generation AI to conduct the conversation at a slower tempo. Furthermore, the conversation unit can automatically adjust the tempo of the conversation depending on the frequency of the user's speech. This allows the conversation to be conducted at an appropriate tempo based on the frequency of the speech. For the frequency of speech, it is necessary to clarify a specific measurement method or standard, such as the number of speeches per unit time. Some or all of the above-mentioned processing in the conversation unit may be performed using, for example, the generation AI, or may be performed without using the generation AI. For example, the conversation unit can conduct a conversation using a generation AI that adjusts the tempo of the conversation depending on the frequency of the user's speech.

[0043] During a conversation, the conversation unit can select a region-specific topic by taking into account the user's geographic location information. For example, the conversation unit selects a region-specific topic by taking into account the user's geographic location information. For example, if the user is in the United States, the generation AI can select a topic related to American culture or news. Furthermore, if the user is in Japan, the generation AI can incorporate a region-specific topic into the conversation based on the user's geographic location information. This allows the conversation to be conducted on an appropriate topic based on the geographic location information. It is necessary to clarify the specific acquisition and usage methods of the geographic location information, such as GPS data or IP address. Some or all of the above-described processing in the conversation unit may be performed using, for example, the generation AI, or may be performed without using the generation AI. For example, the conversation unit can conduct a conversation using a generation AI that selects a region-specific topic by taking into account the user's geographic location information.

[0044] The conversation unit can analyze the user's social media activity and select related topics during a conversation. For example, the conversation unit analyzes the user's social media activity and selects related topics. For example, the conversation unit uses a generation AI to reflect topics that the user frequently discusses on social media in the conversation. The conversation unit can also understand the user's interests and concerns from their social media activity and incorporate related topics into the conversation. Furthermore, the conversation unit can analyze the content of the user's social media posts and conduct the conversation on appropriate topics. This allows the conversation to be conducted on appropriate topics based on the social media activity. The specific content of the social media activity, such as the content of the posts and the number of likes, and the analysis method, need to be clarified. Some or all of the above-mentioned processing in the conversation unit may be performed using, for example, a generation AI, or may be performed without using a generation AI. For example, the conversation unit can conduct a conversation using a generation AI that analyzes the user's social media activity and selects related topics.

[0045] The conversation unit can customize the conversation method by reflecting the user's past feedback during the conversation. For example, the conversation unit customizes the conversation method by reflecting the user's past feedback. For example, the conversation unit uses a generation AI to adjust the tone and style of the conversation based on feedback provided by the user in the past. The conversation unit can also learn and apply preferred conversation methods from the user's past feedback. Furthermore, the conversation unit can optimize the flow and content of the conversation by reflecting the user's feedback. This allows the conversation to be conducted in an appropriate manner based on the past feedback. The specific content and acquisition method of the feedback, such as user surveys or evaluation comments, need to be clarified. Some or all of the above-mentioned processing in the conversation unit may be performed, for example, using the generation AI, or may be performed without using the generation AI. For example, the conversation unit can conduct a conversation using a generation AI that customizes the conversation method by reflecting the user's past feedback.

[0046] During training, the training unit can optimize the training content by referring to the user's past learning history. The training unit, for example, optimizes the training content by referring to the user's past learning history. For example, the training unit uses a generation AI to memorize content the user has previously studied and provide related training. The training unit can also identify weak areas from the user's past learning history and provide focused training. Furthermore, the training unit can analyze the user's past learning history and use the generation AI to propose an effective training plan. This allows training with appropriate content based on the user's past learning history. The learning history must clearly state specific content, such as study time and learning content, and how it is saved. Some or all of the above-described processing in the training unit may be performed using, for example, the generation AI, or may be performed without using the generation AI. For example, the training unit can perform training using a generation AI that optimizes the training content by referring to the user's past learning history.

[0047] The training unit can select a training method that corresponds to the user's learning style during training. The training unit selects a training method that corresponds to the user's learning style, for example. For example, if the user is a visual learner, the training unit can provide training using visual materials via the generation AI. Furthermore, if the user is an auditory learner, the training unit can also provide training using audio materials via the generation AI. Furthermore, the training unit can support effective learning by having the generation AI select an optimal training method based on the user's learning style. This allows training to be conducted in an appropriate manner based on the learning style. It is necessary to clarify the specific type of learning style, such as visual, auditory, or experiential, and the selection method. Some or all of the above-described processing in the training unit may be performed using, for example, the generation AI, or may be performed without using the generation AI. For example, the training unit can conduct training using a generation AI that selects a training method that corresponds to the user's learning style.

[0048] The training unit can adjust the pace of training according to the user's progress during training. For example, the training unit adjusts the pace of training according to the user's progress. For example, if the user is progressing at a fast pace, the generation AI can increase the difficulty of the training. Furthermore, if the user is progressing at a slow pace, the generation AI can also slow down the pace of training. Furthermore, the training unit can automatically adjust the pace of training according to the user's progress to provide an optimal learning environment. This allows training to be performed at an appropriate pace based on the user's progress. It is necessary to clearly define specific measurement methods and criteria for the progress, such as the degree of achievement or completion rate. Some or all of the above-described processing in the training unit may be performed using, for example, the generation AI, or may be performed without using the generation AI. For example, the training unit can perform training using a generation AI that adjusts the pace of training according to the user's progress.

[0049] During training, the training unit can use region-specific teaching materials taking into account the user's geographic location information. For example, the training unit can use region-specific teaching materials taking into account the user's geographic location information. For example, if the user is in the United States, the generation AI can use teaching materials related to American culture and history. Furthermore, if the user is in Japan, the generation AI can select region-specific teaching materials based on the user's geographic location information and reflect the selected region in the training. This allows training to be performed with appropriate teaching materials based on the geographic location information. It is necessary to clarify the specific methods for obtaining and using geographic location information, such as GPS data or IP addresses. Some or all of the above-described processing in the training unit can be performed using, for example, the generation AI, or can be performed without using the generation AI. For example, the training unit can perform training using a generation AI that uses region-specific teaching materials taking into account the user's geographic location information.

[0050] The training unit can analyze the user's social media activities and use relevant teaching materials during training. For example, the training unit can analyze the user's social media activities and use relevant teaching materials. For example, the training unit can use a generation AI to reflect topics frequently discussed by the user on social media in the teaching materials. The training unit can also identify the user's interests from their social media activities and use relevant teaching materials for training. Furthermore, the training unit can analyze the content of the user's social media posts and conduct training with appropriate teaching materials. This allows training to be conducted with appropriate teaching materials based on social media activities. The specific content and analysis method of social media activities, such as the content of posts and the number of likes, need to be clarified. Some or all of the above-described processing in the training unit can be performed, for example, using a generation AI, or can be performed without using a generation AI. For example, the training unit can conduct training using a generation AI that analyzes the user's social media activities and uses relevant teaching materials.

[0051] The training unit can customize the training method by reflecting the user's past feedback during training. The training unit customizes the training method by reflecting, for example, the user's past feedback. For example, the training unit uses a generation AI to adjust the tone and style of the training based on feedback provided by the user in the past. The training unit can also learn and apply preferred training methods from the user's past feedback. Furthermore, the training unit can use the generation AI to optimize the content and progress of the training by reflecting the user's feedback. This allows training to be performed in an appropriate manner based on past feedback. The specific content and acquisition method of the feedback, such as user surveys and evaluation comments, need to be clarified. Some or all of the above-mentioned processing in the training unit may be performed using, for example, the generation AI, or may be performed without using the generation AI. For example, the training unit can perform training using a generation AI that customizes the training method by reflecting the user's past feedback.

[0052] When generating a scenario, the scenario unit can improve the accuracy of the scenario by referring to the user's past scenario history. The scenario unit, for example, improves the accuracy of the scenario by referring to the user's past scenario history. For example, the scenario unit may have a generation AI store scenarios used by the user in the past and provide related scenarios. The scenario unit may also prioritize preferred scenarios from the user's past scenario history. Furthermore, the scenario unit may analyze the user's past scenario history and have the generation AI provide highly accurate scenarios. This allows scenarios to be provided with appropriate content based on the past scenario history. The scenario history must clearly state specific content, such as past scenario content and frequency of use, and a storage method. Some or all of the above-described processing in the scenario unit may be performed, for example, using the generation AI, or may be performed without using the generation AI. For example, the scenario unit may provide a scenario using a generation AI that improves the accuracy of the scenario by referring to the user's past scenario history.

[0053] When generating a scenario, the scenario unit can select a scenario that corresponds to the user's lifestyle. The scenario unit selects a scenario that corresponds to the user's lifestyle, for example. For example, if the user leads a busy lifestyle, the scenario unit can provide a scenario that the generation AI can complete in a short time. Also, if the user leads a relaxed lifestyle, the scenario unit can provide a scenario that the generation AI can enjoy for a long time. Furthermore, the scenario unit can select and provide an optimal scenario based on the user's lifestyle. This allows scenarios to be provided with appropriate content based on the lifestyle. The specific type of lifestyle, such as urban, rural, or family structure, and the selection method, need to be clarified. Some or all of the above-mentioned processing in the scenario unit may be performed, for example, using the generation AI, or may be performed without using the generation AI. For example, the scenario unit can provide a scenario using a generation AI that selects a scenario that corresponds to the user's lifestyle.

[0054] When generating a scenario, the scenario unit can improve the content of the scenario by reflecting user feedback. For example, the scenario unit improves the content of the scenario by reflecting user feedback. For example, the scenario unit adjusts the content of the scenario using a generation AI based on feedback previously provided by the user. The scenario unit can also learn and apply preferred scenario elements from user feedback. Furthermore, the scenario unit can improve the accuracy and naturalness of the scenario by reflecting user feedback. This allows a scenario to be provided with appropriate content based on past feedback. The specific content and acquisition method of the feedback, such as user surveys and evaluation comments, must be clearly defined. Some or all of the above-described processing in the scenario unit may be performed using, for example, a generation AI, or may be performed without using a generation AI. For example, the scenario unit can provide a scenario using a generation AI that improves the content of the scenario by reflecting user feedback.

[0055] When generating a scenario, the scenario unit can generate a region-specific scenario by taking into account the user's geographical location information. The scenario unit, for example, generates a region-specific scenario by taking into account the user's geographical location information. For example, if the user is in the United States, the scenario unit's generation AI can provide a scenario related to American culture and history. Furthermore, if the user is in Japan, the scenario unit's generation AI can select and provide a region-specific scenario based on the user's geographical location information. This allows scenarios to be provided with appropriate content based on the geographical location information. It is necessary to clarify the specific methods for obtaining and using geographical location information, such as GPS data or IP addresses. Some or all of the above-described processing in the scenario unit may be performed, for example, using the generation AI, or may be performed without using the generation AI. For example, the scenario unit can provide a scenario by using a generation AI that generates a region-specific scenario by taking into account the user's geographical location information.

[0056] When generating a scenario, the scenario unit can analyze the user's social media activities and generate a related scenario. For example, the scenario unit analyzes the user's social media activities and generates a related scenario. For example, the scenario unit uses a generation AI to reflect topics frequently discussed by the user on social media in the scenario. The scenario unit can also understand the user's interests and concerns from the user's social media activities and generate a related scenario. Furthermore, the scenario unit can analyze the content posted by the user on social media and provide an appropriate scenario. This makes it possible to provide a scenario with appropriate content based on the social media activities. The specific content of the social media activities, such as the content of posts and the number of likes, and the analysis method, need to be clarified. Some or all of the above-mentioned processing in the scenario unit may be performed, for example, using a generation AI, or may be performed without using a generation AI. For example, the scenario unit can provide a scenario using a generation AI that analyzes the user's social media activities and generates a related scenario.

[0057] When generating a scenario, the scenario unit can customize the content of the scenario by reflecting the user's past feedback. For example, the scenario unit customizes the content of the scenario by reflecting the user's past feedback. For example, the scenario unit allows the generation AI to adjust the tone and style of the scenario based on feedback provided by the user in the past. The scenario unit can also learn and apply preferred scenario elements from the user's past feedback. Furthermore, the scenario unit can allow the generation AI to optimize the content and progression of the scenario by reflecting the user's feedback. This allows a scenario to be provided with appropriate content based on the past feedback. The specific content and acquisition method of the feedback, such as user surveys or evaluation comments, must be clearly defined. Some or all of the above-described processing in the scenario unit may be performed, for example, using the generation AI, or may be performed without using the generation AI. For example, the scenario unit can provide a scenario using a generation AI that customizes the content of the scenario by reflecting the user's past feedback.

[0058] The system according to the embodiment is not limited to the above-described example, and various modifications are possible, for example, as follows.

[0059] The bilingual development and language consolidation support system may further include a progress display unit that visualizes the user's learning progress. The progress display unit displays the user's progress in graphs or charts. For example, progress may be displayed for each technique of listening, speaking, reading, and writing, allowing the user to see at a glance which areas require particular effort. The progress display unit may also display the user's achievement level toward goals set by the user in real time. Furthermore, the progress display unit may provide motivational messages and advice based on the user's progress. This allows the user to understand their own learning situation and effectively advance their studies.

[0060] The translation unit can translate based on the user's speech, taking cultural background into account. For example, when a user speaks about a topic related to a specific culture, the generative AI translates using expressions and examples appropriate to that culture. The translation unit can also provide supplementary information to help users avoid cultural misunderstandings when communicating with people from different cultures. Furthermore, the translation unit can provide resources and links to help users deepen their knowledge of a specific culture. This allows users to learn a language while deepening their understanding of different cultures.

[0061] The training unit can customize the training method according to the user's learning style. For example, if the user is a visual learner, the generation AI can provide training using visual materials. If the user is an auditory learner, the generation AI can provide training using audio materials. Furthermore, if the user is an experiential learner, the generation AI can provide training using interactive simulations. This allows users to effectively learn in the way that best suits them.

[0062] The translation unit can provide expert advice based on the user's speech. For example, if a user talks about a medical topic, the generation AI can appropriately translate medical terminology and provide relevant medical knowledge. If a user talks about a technical topic, the generation AI can appropriately translate technical terminology and provide relevant technical information. If a user talks about a legal topic, the generation AI can appropriately translate legal terminology and provide relevant legal knowledge. This allows users to learn a language while deepening their specialized knowledge.

[0063] The conversation unit can optimize the flow of the conversation by referring to the past conversation history of the user's conversation partner. For example, the conversation unit uses a generation AI to memorize topics that the conversation partner has previously discussed and incorporates related topics into the conversation. The conversation unit can also prioritize preferred topics from the conversation partner's past conversation history. Furthermore, the conversation unit can analyze the conversation partner's past conversation history to ensure a smooth conversation flow. This allows the conversation to flow appropriately based on the past conversation history.

[0064] The training unit can adjust the pace of training according to the user's progress. For example, if the user is progressing at a fast pace, the generation AI can increase the difficulty of the training. Conversely, if the user is progressing at a slow pace, the generation AI can also ease the pace of training. Furthermore, the generation AI can automatically adjust the pace of training according to the user's progress, providing an optimal learning environment. This allows training to be performed at an appropriate pace based on the user's progress.

[0065] The scenario unit can customize the content of the scenario according to the user's lifestyle. For example, if the user leads a busy life, the generation AI can provide a scenario that can be completed in a short time. On the other hand, if the user leads a relaxed life, the generation AI can provide a scenario that can be enjoyed for a long time. Furthermore, the generation AI can select and provide the optimal scenario based on the user's lifestyle. This makes it possible to provide a scenario with appropriate content based on the user's lifestyle.

[0066] The processing flow of the first embodiment will be briefly explained below.

[0067] Step 1: The translation unit translates the user's speech in real time and responds in the specified language. For example, generative AI can be used to translate the user's speech and respond in the appropriate language. It can also estimate the user's emotions and adjust the tone and expression of the translation based on the estimated emotions. Furthermore, it can improve the accuracy of the translation by referring to the user's past speech history, and it can also automatically select technical terms according to the field of expertise. Step 2: The conversation part allows multiple users to converse simultaneously in different languages. For example, it can use generative AI to enable multiple users to converse simultaneously in different languages, estimate users' emotions, and adjust the way the conversation progresses. It can also refer to users' past conversation history to optimize the flow of the conversation and select conversation topics based on their areas of interest. Step 3: The training department provides training to help users master the four skills of listening, speaking, reading, and writing in a balanced way. For example, generative AI can be used to provide training to help users master the four skills in a balanced way, and the difficulty of the training can be adjusted by estimating the user's emotions. It can also optimize the training content by referring to the user's past learning history and select a training method that suits their learning style. Step 4: The scenario unit generates scenarios in which the second native language is used in daily life and provides them to the user. For example, the generation AI can be used to generate scenarios in which the second native language is used in daily life, and the content of the scenario can be adjusted by estimating the user's emotions. It can also improve the accuracy of the scenario by referring to the user's past scenario history and select scenarios that suit their lifestyle.

[0068] (Example 2) A bilingual development and language acquisition support system according to an embodiment of the present invention uses generative AI to help users naturally acquire multiple languages. The bilingual development and language acquisition support system includes a translation unit with a multilingual conversation function that translates a user's speech in real time and responds in a specified language; a conversation unit with a multi-party conversation algorithm that enables multiple users to converse simultaneously in different languages; a training unit with an English four-technique approach function that provides training for equally mastering the four skills of listening, speaking, reading, and writing; and a scenario unit with a native language acquisition program that generates and provides scenarios for using a second native language in daily life. For example, the bilingual development and language acquisition support system helps users naturally use multiple languages ​​in their daily lives. For example, if a user wants to learn Japanese and English simultaneously, using this system allows them to use both languages ​​naturally in everyday conversation. This allows users to become bilingual unconsciously. The bilingual development and language acquisition support system also allows multiple users to converse simultaneously in different languages. For example, if a family has a father who speaks English and a mother who speaks Japanese, and a child who speaks both languages, using this system allows all family members to communicate smoothly. This allows the child to naturally acquire both languages. Furthermore, the bilingual development and language consolidation support system helps users acquire the four skills of listening, speaking, reading, and writing in a balanced manner. For example, if a user wants to improve their English listening skills, they can use this system to receive training specifically focused on listening. Similarly, they can receive balanced training in the skills of speaking, reading, and writing. Finally, the bilingual development and language consolidation support system helps users naturally acquire a second native language. For example, if a user wants to acquire English as a second native language, using this system allows them to use English naturally in their daily lives.This allows users to unconsciously acquire English as a second native language. This allows the bilingual development and language consolidation support system to help users naturally acquire multiple languages. For example, users can naturally use multiple languages ​​in their daily lives and become bilingual. Furthermore, multiple users can simultaneously converse in different languages, enabling smooth communication. Furthermore, users can acquire the four skills of listening, speaking, reading, and writing in a balanced manner, naturally acquiring a second native language.

[0069] A bilingual development and language acquisition support system according to an embodiment includes a translation unit, a conversation unit, a training unit, and a scenario unit. The translation unit translates a user's speech in real time and responds in a specified language. For example, the translation unit uses a generation AI to translate the user's speech in real time and respond in an appropriate language. The translation unit can also estimate the user's emotions and adjust the tone and expression of the translation based on the estimated user's emotions. For example, if the user is nervous, the generation AI can translate in a gentler tone and use expressions that create a sense of security. The translation unit can also improve the accuracy of the translation by referring to the user's past speech history. For example, the generation AI can memorize specific phrases and expressions used by the user in the past and reuse them in similar contexts. Furthermore, the translation unit can automatically select technical terms according to the user's field of expertise. For example, if the user works in the medical field, the generation AI can prioritize medical terminology when translating. The conversation unit enables multiple users to converse simultaneously in different languages. For example, the conversation unit enables multiple users to converse simultaneously in different languages ​​using the generation AI. The conversation unit can also estimate the user's emotions and adjust the way the conversation proceeds based on the estimated user's emotions. For example, if the user is nervous, the generation AI can proceed with the conversation at a slower pace. The conversation unit can also optimize the flow of the conversation by referring to the user's past conversation history. For example, the generation AI can memorize topics the user has previously discussed and incorporate related topics into the conversation. The conversation unit can also select conversation topics based on the user's areas of interest. For example, the generation AI can select conversation topics based on the user's areas of interest (sports, music, etc.). The training unit provides training to help the user acquire the four skills of listening, speaking, reading, and writing in a balanced manner. For example, the training unit uses the generation AI to provide training to help the user acquire the four skills of listening, speaking, reading, and writing in a balanced manner.The training unit can also estimate the user's emotions and adjust the difficulty of the training based on the estimated user's emotions. For example, if the user is nervous, the generation AI can provide easy training and gradually increase the difficulty. The training unit can also optimize the training content by referring to the user's past learning history. For example, the generation AI can memorize what the user has learned in the past and provide related training. The training unit can also select a training method according to the user's learning style. For example, if the user is a visual learner, the generation AI can provide training using visual materials. The scenario unit can generate scenarios using the second native language in daily life and provide them to the user. For example, the scenario unit can use the generation AI to generate scenarios using the second native language in daily life and provide them to the user. The scenario unit can also estimate the user's emotions and adjust the content of the scenario based on the estimated user's emotions. For example, if the user is nervous, the generation AI can provide a scenario that helps the user relax. The scenario unit can also improve the accuracy of the scenario by referring to the user's past scenario history. For example, the generation AI can memorize scenarios the user has used in the past and provide related scenarios. The scenario unit can also select scenarios according to the user's lifestyle. For example, if a user has a busy lifestyle, the generation AI can provide a scenario that can be completed in a short time. This allows the bilingual development and language consolidation support system according to the embodiment to support the user in naturally acquiring multiple languages.

[0070] The translation unit can use a generation AI to translate a user's utterance in real time and respond in an appropriate language. The generation AI is realized, for example, using a specific AI model or algorithm. For example, the generation AI can translate a user's utterance in real time and respond in an appropriate language. For example, the generation AI inputs the user's utterance as text data and outputs the translation result as text data. The generation AI can also input the user's utterance as audio data and output the translation result as audio data. Furthermore, the generation AI can analyze the user's utterance and provide an appropriate translation according to the context. For example, the generation AI understands the intent of the user's utterance and provides an appropriate translation. As a result, the use of the generation AI improves the accuracy and speed of translation. Some or all of the above-mentioned processing in the translation unit may be performed, for example, using the generation AI, or may be performed without using the generation AI. For example, the translation unit can perform translation using a generation AI that inputs the user's utterance as text data and outputs the translation result as text data.

[0071] The conversation unit can use a generation AI to enable multiple users to converse simultaneously in different languages. The generation AI is realized, for example, using a specific AI model or algorithm. For example, the generation AI enables multiple users to converse simultaneously in different languages. For example, the generation AI translates each user's utterance in real time and responds to other users in an appropriate language. The generation AI can also analyze each user's utterance and provide an appropriate translation based on the context. For example, the generation AI understands the intent of each user's utterance and provides an appropriate translation. This enables smooth communication between users who speak different languages ​​by using the generation AI. Some or all of the above-described processing in the conversation unit can be performed, for example, using the generation AI, or can be performed without using the generation AI. For example, the conversation unit can conduct a conversation using a generation AI that inputs each user's utterance as text data and outputs the translation result as text data.

[0072] The training unit can use a generation AI to provide training for balanced acquisition of the four techniques of listening, speaking, reading, and writing. The generation AI is realized, for example, using a specific AI model or algorithm. For example, the generation AI provides training for balanced acquisition of the four techniques of listening, speaking, reading, and writing. For example, the generation AI provides training for improving a user's listening ability. For example, the generation AI can also provide training for improving a user's speaking ability. For example, the generation AI can also provide training for improving a user's reading ability. For example, the generation AI can also provide training for improving a user's writing ability. In this way, the generation AI can be used to acquire the four techniques in a balanced manner. Some or all of the above-described processing in the training unit may be performed, for example, using the generation AI, or may be performed without using the generation AI. For example, the training unit can perform training using a generation AI that provides training for improving a user's listening ability.

[0073] The scenario unit can use the generation AI to generate scenarios in which the second native language is used in daily life and provide them to the user. The generation AI is realized, for example, using a specific AI model or algorithm. For example, the generation AI can generate scenarios in which the second native language is used in daily life and provide them to the user. For example, the generation AI can analyze the user's daily life situation and generate an appropriate scenario. For example, the generation AI can also generate scenarios that match the user's lifestyle. For example, the generation AI can estimate the user's emotions and adjust the content of the scenario based on the estimated user's emotions. In this way, the generation AI can enable the user to naturally acquire the second native language. Some or all of the above-mentioned processing in the scenario unit can be performed, for example, using the generation AI, or can be performed without using the generation AI. For example, the scenario unit can provide a scenario using a generation AI that analyzes the user's daily life situation and generates an appropriate scenario.

[0074] The translation unit can estimate the user's emotions and adjust the tone and expression of the translation based on the estimated user's emotions. For example, the translation unit estimates the user's emotions and adjusts the tone and expression of the translation based on the estimated user's emotions. For example, if the user is nervous, the translation unit may have the generation AI translate in a gentle tone and use expressions that convey a sense of security. Alternatively, if the user is excited, the translation unit may have the generation AI translate in an energetic tone and use lively expressions. Furthermore, if the user is tired, the translation unit may have the generation AI translate in a calm tone and use expressions that convey relaxation. This allows translation to be performed with an appropriate tone and expression according to the user's emotions. Emotion estimation is achieved using an emotion estimation function, for example, using an emotion engine or generation AI. The generation AI may be a text generation AI (e.g., LLM) or a multimodal generation AI, but is not limited to these examples. Some or all of the above-described processing in the translation unit may be performed using, for example, the generation AI, or without the generation AI. For example, the translation unit can perform translation using generative AI that estimates the user's emotions and adjusts the tone and expression of the translation based on the estimated user emotions.

[0075] The translation unit can improve the accuracy of the translation by referring to the user's past speech history during translation. The translation unit, for example, improves the accuracy of the translation by referring to the user's past speech history. For example, the translation unit uses a generation AI to memorize specific phrases and expressions used by the user in the past and reuse them in similar contexts. The translation unit can also prioritize frequently used words and phrases from the user's past speech history in the translation. Furthermore, the translation unit can analyze the user's past speech history to understand grammatical and vocabulary trends and improve the accuracy of the translation. Thus, by referring to the past speech history, the accuracy of the translation is improved. The speech history is stored, for example, as text data or audio data. Some or all of the above-described processing in the translation unit may be performed using, for example, the generation AI, or may be performed without using the generation AI. For example, the translation unit can perform translation using a generation AI that improves the accuracy of the translation by referring to the user's past speech history.

[0076] The translation unit can automatically select technical terms according to the user's field of expertise during translation. For example, the translation unit automatically selects technical terms according to the user's field of expertise. For example, if the user is in the medical field, the translation unit may have the generation AI prioritize medical terminology during translation. Furthermore, if the user is in the technical field, the translation unit may have the generation AI appropriately incorporate technical terminology into the translation. Furthermore, the translation unit may automatically select relevant technical terms based on the user's field of expertise to improve the accuracy of the translation. This allows translations to be performed using appropriate terminology according to the field of expertise. The specific type of field of expertise, such as medical, legal, or technical, and the selection method, must be clearly defined. Some or all of the above-described processing in the translation unit may be performed using, for example, the generation AI, or may be performed without the generation AI. For example, the translation unit may perform translations using a generation AI that automatically selects technical terms according to the user's field of expertise.

[0077] The translation unit can adjust the translation speed during translation according to the user's speaking speed. The translation unit adjusts the translation speed according to, for example, the user's speaking speed. For example, if the user speaks quickly, the generation AI can quickly translate and provide a real-time response. Alternatively, if the user speaks slowly, the generation AI can carefully translate and provide an accurate response. Furthermore, the translation unit can automatically adjust the translation speed according to the user's speaking speed, enabling smooth conversation. This allows translation to be performed at an appropriate speed according to the user's speaking speed. It is necessary to clearly define a specific measurement method or standard for the speaking speed, such as the number of words per unit time. Some or all of the above-described processing in the translation unit may be performed using, for example, the generation AI, or may be performed without using the generation AI. For example, the translation unit can perform translation using a generation AI that adjusts the translation speed according to the user's speaking speed.

[0078] The translation unit can estimate the user's emotions and determine translation priorities based on the estimated user emotions. The translation unit, for example, estimates the user's emotions and determines translation priorities based on the estimated user emotions. For example, when the user is in an emergency, the translation unit allows the generation AI to prioritize translating important messages. Furthermore, when the user is relaxed, the translation unit can also allow the generation AI to translate taking the overall context into consideration. Furthermore, when the user is stressed, the translation unit can also allow the generation AI to prioritize providing concise and clear translations. This allows translation to be performed with appropriate priorities according to the user's emotions. The emotion estimation is achieved using an emotion estimation function, for example, an emotion engine or a generation AI. The generation AI can be a text generation AI (e.g., LLM) or a multimodal generation AI, but is not limited to these examples. Some or all of the above-described processing in the translation unit may be performed using, for example, the generation AI. For example, the translation unit can perform translation using a generation AI that estimates the user's emotions and determines translation priorities based on the estimated user emotions.

[0079] The translation unit can use region-specific expressions during translation, taking into account the user's geographical location information. The translation unit can use region-specific expressions, for example, taking into account the user's geographical location information. For example, if the user is in the United States, the translation unit can have the generation AI use American English expressions to translate. Also, if the user is in the United Kingdom, the translation unit can have the generation AI use British English expressions to translate. Furthermore, the translation unit can appropriately incorporate region-specific slang and expressions into the translation based on the user's geographical location information. This allows translation to be performed using appropriate region-specific expressions. It is necessary to clarify the specific acquisition and usage methods of geographical location information, such as GPS data or IP address. Some or all of the above-described processing in the translation unit can be performed using, for example, the generation AI, or can be performed without using the generation AI. For example, the translation unit can perform translation using a generation AI that uses region-specific expressions while taking into account the user's geographical location information.

[0080] The translation unit can analyze the user's social media activity and use relevant expressions during translation. For example, the translation unit can analyze the user's social media activity and use relevant expressions. For example, the translation unit can incorporate phrases and expressions frequently used by the user on social media into the translation using a generation AI. The translation unit can also identify the user's interests and concerns from their social media activity and use relevant expressions in the translation. Furthermore, the translation unit can analyze the content of the user's social media posts and translate them with an appropriate tone and style. This allows the translation to be performed with appropriate expressions based on the social media activity. The specific content of the social media activity, such as the content of the posts and the number of likes, and the analysis method, need to be clearly defined. Some or all of the above-described processing in the translation unit can be performed using, for example, a generation AI, or can be performed without using a generation AI. For example, the translation unit can analyze the user's social media activity and use a generation AI that uses relevant expressions to perform the translation.

[0081] The translation unit can customize the translation method by reflecting the user's past feedback during translation. For example, the translation unit customizes the translation method by reflecting the user's past feedback. For example, the translation unit allows the generation AI to adjust the tone and style of the translation based on feedback provided by the user in the past. The translation unit can also learn and apply preferred translation methods from the user's past feedback. Furthermore, the translation unit can also allow the generation AI to improve the accuracy and naturalness of the translation by reflecting the user's feedback. This allows translation to be performed in an appropriate manner based on the past feedback. The specific content and acquisition method of the feedback, such as user surveys or evaluation comments, need to be clarified. Some or all of the above-described processing in the translation unit may be performed using, for example, the generation AI, or may be performed without using the generation AI. For example, the translation unit can perform translation using a generation AI that customizes the translation method by reflecting the user's past feedback.

[0082] The conversation unit can estimate the user's emotions and adjust the conversation progression method based on the estimated user emotions. The conversation unit, for example, estimates the user's emotions and adjusts the conversation progression method based on the estimated user emotions. For example, if the user is nervous, the conversation unit causes the generation AI to proceed with the conversation at a slow pace. Also, if the user is relaxed, the conversation unit can cause the generation AI to proceed with the conversation at a natural pace. Furthermore, if the user is excited, the conversation unit can cause the generation AI to proceed with the conversation at a lively pace. This allows the conversation to proceed in an appropriate manner according to the user's emotions. Emotion estimation is realized using an emotion estimation function, for example, with an emotion engine or a generation 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-mentioned processing in the conversation unit may be performed using, for example, the generation AI, or may be performed without using the generation AI. For example, the conversation unit can conduct a conversation using a generation AI that estimates the user's emotions and adjusts the conversation progression method based on the estimated user emotions.

[0083] During a conversation, the conversation unit can optimize the flow of the conversation by referring to the user's past conversation history. The conversation unit, for example, optimizes the flow of the conversation by referring to the user's past conversation history. For example, the conversation unit uses a generation AI to store topics that the user has previously discussed and incorporate related topics into the conversation. The conversation unit can also prioritize preferred topics from the user's past conversation history. Furthermore, the conversation unit can analyze the user's past conversation history to achieve a smooth conversation flow. This allows the conversation to have an appropriate flow based on the past conversation history. The conversation history is stored, for example, as text data or audio data. Some or all of the above-described processing in the conversation unit may be performed, for example, using the generation AI, or may be performed without using the generation AI. For example, the conversation unit can conduct a conversation using a generation AI that optimizes the flow of the conversation by referring to the user's past conversation history.

[0084] During a conversation, the conversation unit can select a conversation topic based on the user's field of interest. The conversation unit, for example, selects a conversation topic based on the user's field of interest. For example, the conversation unit uses a generation AI to select a conversation topic based on the user's field of interest (sports, music, etc.). The conversation unit can also incorporate topics of interest from the user's past search history into the conversation. Furthermore, the conversation unit can analyze the user's social media activity and reflect related topics in the conversation. This allows the conversation to be conducted on an appropriate topic based on the user's field of interest. The specific type and selection method of the field of interest, such as hobbies or occupation, need to be clearly defined. Some or all of the above-mentioned processing in the conversation unit may be performed using, for example, a generation AI, or may be performed without using a generation AI. For example, the conversation unit can conduct a conversation using a generation AI that selects a conversation topic based on the user's field of interest.

[0085] The conversation unit can adjust the tempo of the conversation during a conversation depending on the frequency of the user's speech. The conversation unit, for example, adjusts the tempo of the conversation depending on the frequency of the user's speech. For example, if the user speaks frequently, the conversation unit causes the generation AI to conduct the conversation at a fast tempo. Also, if the user speaks slowly, the conversation unit can cause the generation AI to conduct the conversation at a slower tempo. Furthermore, the conversation unit can automatically adjust the tempo of the conversation depending on the frequency of the user's speech. This allows the conversation to be conducted at an appropriate tempo based on the frequency of the speech. For the frequency of speech, it is necessary to clarify a specific measurement method or standard, such as the number of speeches per unit time. Some or all of the above-mentioned processing in the conversation unit may be performed using, for example, the generation AI, or may be performed without using the generation AI. For example, the conversation unit can conduct a conversation using a generation AI that adjusts the tempo of the conversation depending on the frequency of the user's speech.

[0086] The conversation unit can estimate the user's emotions and determine conversation priorities based on the estimated user emotions. For example, the conversation unit can estimate the user's emotions and determine conversation priorities based on the estimated user emotions. For example, when the user is in an emergency, the conversation unit allows the generation AI to prioritize important topics into the conversation. Furthermore, when the user is relaxed, the conversation unit can also allow the generation AI to proceed with the conversation while taking into account the overall context. Furthermore, when the user is stressed, the conversation unit can also allow the generation AI to prioritize concise and clear conversations. This allows the conversation to be conducted with appropriate priorities according to the user's emotions. The emotion estimation is realized using an emotion estimation function, for example, an emotion engine or a generation AI. The generation AI can be 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 conversation unit can be performed using, for example, the generation AI, or can be performed without using the generation AI. For example, the conversation unit can conduct a conversation using a generation AI that estimates the user's emotions and determines conversation priorities based on the estimated user emotions.

[0087] During a conversation, the conversation unit can select a region-specific topic by taking into account the user's geographic location information. For example, the conversation unit selects a region-specific topic by taking into account the user's geographic location information. For example, if the user is in the United States, the generation AI can select a topic related to American culture or news. Furthermore, if the user is in Japan, the generation AI can incorporate a region-specific topic into the conversation based on the user's geographic location information. This allows the conversation to be conducted on an appropriate topic based on the geographic location information. It is necessary to clarify the specific acquisition and usage methods of the geographic location information, such as GPS data or IP address. Some or all of the above-described processing in the conversation unit may be performed using, for example, the generation AI, or may be performed without using the generation AI. For example, the conversation unit can conduct a conversation using a generation AI that selects a region-specific topic by taking into account the user's geographic location information.

[0088] The conversation unit can analyze the user's social media activity and select related topics during a conversation. For example, the conversation unit analyzes the user's social media activity and selects related topics. For example, the conversation unit uses a generation AI to reflect topics that the user frequently discusses on social media in the conversation. The conversation unit can also understand the user's interests and concerns from their social media activity and incorporate related topics into the conversation. Furthermore, the conversation unit can analyze the content of the user's social media posts and conduct the conversation on appropriate topics. This allows the conversation to be conducted on appropriate topics based on the social media activity. The specific content of the social media activity, such as the content of the posts and the number of likes, and the analysis method, need to be clarified. Some or all of the above-mentioned processing in the conversation unit may be performed using, for example, a generation AI, or may be performed without using a generation AI. For example, the conversation unit can conduct a conversation using a generation AI that analyzes the user's social media activity and selects related topics.

[0089] The conversation unit can customize the conversation method by reflecting the user's past feedback during the conversation. For example, the conversation unit customizes the conversation method by reflecting the user's past feedback. For example, the conversation unit uses a generation AI to adjust the tone and style of the conversation based on feedback provided by the user in the past. The conversation unit can also learn and apply preferred conversation methods from the user's past feedback. Furthermore, the conversation unit can optimize the flow and content of the conversation by reflecting the user's feedback. This allows the conversation to be conducted in an appropriate manner based on the past feedback. The specific content and acquisition method of the feedback, such as user surveys or evaluation comments, need to be clarified. Some or all of the above-mentioned processing in the conversation unit may be performed, for example, using the generation AI, or may be performed without using the generation AI. For example, the conversation unit can conduct a conversation using a generation AI that customizes the conversation method by reflecting the user's past feedback.

[0090] The training unit can estimate the user's emotions and adjust the difficulty of the training based on the estimated user's emotions. The training unit, for example, estimates the user's emotions and adjusts the difficulty of the training based on the estimated user's emotions. For example, if the user is nervous, the generation AI can provide easy training and gradually increase the difficulty. Furthermore, if the user is relaxed, the training unit can provide training of moderate difficulty. Furthermore, if the user is excited, the generation AI can provide challenging training. This allows training to be performed at an appropriate difficulty level according to the user's emotions. The emotion estimation is realized using an emotion estimation function, for example, an emotion engine or a generation AI. The generation AI can be 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 training unit may be performed using, for example, the generation AI, or may be performed without using the generation AI. For example, the training unit can perform training using a generation AI that estimates the user's emotions and adjusts the difficulty of the training based on the estimated user's emotions.

[0091] During training, the training unit can optimize the training content by referring to the user's past learning history. The training unit, for example, optimizes the training content by referring to the user's past learning history. For example, the training unit uses a generation AI to memorize content the user has previously studied and provide related training. The training unit can also identify weak areas from the user's past learning history and provide focused training. Furthermore, the training unit can analyze the user's past learning history and use the generation AI to propose an effective training plan. This allows training with appropriate content based on the user's past learning history. The learning history must clearly state specific content, such as study time and learning content, and how it is saved. Some or all of the above-described processing in the training unit may be performed using, for example, the generation AI, or may be performed without using the generation AI. For example, the training unit can perform training using a generation AI that optimizes the training content by referring to the user's past learning history.

[0092] The training unit can select a training method that corresponds to the user's learning style during training. The training unit selects a training method that corresponds to the user's learning style, for example. For example, if the user is a visual learner, the training unit can provide training using visual materials via the generation AI. Furthermore, if the user is an auditory learner, the training unit can also provide training using audio materials via the generation AI. Furthermore, the training unit can support effective learning by having the generation AI select an optimal training method based on the user's learning style. This allows training to be conducted in an appropriate manner based on the learning style. It is necessary to clarify the specific type of learning style, such as visual, auditory, or experiential, and the selection method. Some or all of the above-described processing in the training unit may be performed using, for example, the generation AI, or may be performed without using the generation AI. For example, the training unit can conduct training using a generation AI that selects a training method that corresponds to the user's learning style.

[0093] The training unit can adjust the pace of training according to the user's progress during training. For example, the training unit adjusts the pace of training according to the user's progress. For example, if the user is progressing at a fast pace, the generation AI can increase the difficulty of the training. Furthermore, if the user is progressing at a slow pace, the generation AI can also slow down the pace of training. Furthermore, the training unit can automatically adjust the pace of training according to the user's progress to provide an optimal learning environment. This allows training to be performed at an appropriate pace based on the user's progress. It is necessary to clearly define specific measurement methods and criteria for the progress, such as the degree of achievement or completion rate. Some or all of the above-described processing in the training unit may be performed using, for example, the generation AI, or may be performed without using the generation AI. For example, the training unit can perform training using a generation AI that adjusts the pace of training according to the user's progress.

[0094] The training unit can estimate the user's emotions and determine the priority of training based on the estimated user emotions. The training unit, for example, estimates the user's emotions and determines the priority of training based on the estimated user emotions. For example, when the user is in an emergency situation, the training unit causes the generation AI to prioritize important training. Furthermore, when the user is relaxed, the training unit can also cause the generation AI to proceed with training taking into account the overall context. Furthermore, when the user is feeling stressed, the training unit can cause the generation AI to prioritize concise and clear training. This allows training to be performed with appropriate priorities according to the user's emotions. The emotion estimation is realized using an emotion estimation function, for example, an emotion engine or a generation AI. The generation AI can be a text generation AI (e.g., LLM) or a multimodal generation AI, but is not limited to such examples. Some or all of the above-mentioned processing in the training unit may be performed using, for example, the generation AI, or may be performed without using the generation AI. For example, the training unit can perform training using a generation AI that estimates the user's emotions and determines the priority of training based on the estimated user emotions.

[0095] During training, the training unit can use region-specific teaching materials taking into account the user's geographic location information. For example, the training unit can use region-specific teaching materials taking into account the user's geographic location information. For example, if the user is in the United States, the generation AI can use teaching materials related to American culture and history. Furthermore, if the user is in Japan, the generation AI can select region-specific teaching materials based on the user's geographic location information and reflect the selected region in the training. This allows training to be performed with appropriate teaching materials based on the geographic location information. It is necessary to clarify the specific methods for obtaining and using geographic location information, such as GPS data or IP addresses. Some or all of the above-described processing in the training unit can be performed using, for example, the generation AI, or can be performed without using the generation AI. For example, the training unit can perform training using a generation AI that uses region-specific teaching materials taking into account the user's geographic location information.

[0096] The training unit can analyze the user's social media activities and use relevant teaching materials during training. For example, the training unit can analyze the user's social media activities and use relevant teaching materials. For example, the training unit can use a generation AI to reflect topics frequently discussed by the user on social media in the teaching materials. The training unit can also identify the user's interests from their social media activities and use relevant teaching materials for training. Furthermore, the training unit can analyze the content of the user's social media posts and conduct training with appropriate teaching materials. This allows training to be conducted with appropriate teaching materials based on social media activities. The specific content and analysis method of social media activities, such as the content of posts and the number of likes, need to be clarified. Some or all of the above-described processing in the training unit can be performed, for example, using a generation AI, or can be performed without using a generation AI. For example, the training unit can conduct training using a generation AI that analyzes the user's social media activities and uses relevant teaching materials.

[0097] The training unit can customize the training method by reflecting the user's past feedback during training. The training unit customizes the training method by reflecting, for example, the user's past feedback. For example, the training unit uses a generation AI to adjust the tone and style of the training based on feedback provided by the user in the past. The training unit can also learn and apply preferred training methods from the user's past feedback. Furthermore, the training unit can use the generation AI to optimize the content and progress of the training by reflecting the user's feedback. This allows training to be performed in an appropriate manner based on past feedback. The specific content and acquisition method of the feedback, such as user surveys and evaluation comments, need to be clarified. Some or all of the above-mentioned processing in the training unit may be performed using, for example, the generation AI, or may be performed without using the generation AI. For example, the training unit can perform training using a generation AI that customizes the training method by reflecting the user's past feedback.

[0098] The scenario unit can estimate the user's emotions and adjust the content of the scenario based on the estimated user emotions. For example, the scenario unit can estimate the user's emotions and adjust the content of the scenario based on the estimated user emotions. For example, if the user is nervous, the scenario unit can provide a scenario that allows the generation AI to relax. Furthermore, if the user is relaxed, the scenario unit can provide a challenging scenario. Furthermore, if the user is excited, the scenario unit can provide an energetic scenario. This makes it possible to provide a scenario with appropriate content according to the user's emotions. Emotion estimation is achieved using an emotion estimation function, for example, using an emotion engine or a generation AI. The generation AI can be a text generation AI (e.g., LLM) or a multimodal generation AI, but is not limited to such examples. Some or all of the above-mentioned processing in the scenario unit can be performed using, for example, the generation AI, or can be performed without using the generation AI. For example, the scenario unit can provide a scenario using a generation AI that estimates the user's emotions and adjusts the content of the scenario based on the estimated user emotions.

[0099] When generating a scenario, the scenario unit can improve the accuracy of the scenario by referring to the user's past scenario history. The scenario unit, for example, improves the accuracy of the scenario by referring to the user's past scenario history. For example, the scenario unit may have a generation AI store scenarios used by the user in the past and provide related scenarios. The scenario unit may also prioritize preferred scenarios from the user's past scenario history. Furthermore, the scenario unit may analyze the user's past scenario history and have the generation AI provide highly accurate scenarios. This allows scenarios to be provided with appropriate content based on the past scenario history. The scenario history must clearly state specific content, such as past scenario content and frequency of use, and a storage method. Some or all of the above-described processing in the scenario unit may be performed, for example, using the generation AI, or may be performed without using the generation AI. For example, the scenario unit may provide a scenario using a generation AI that improves the accuracy of the scenario by referring to the user's past scenario history.

[0100] When generating a scenario, the scenario unit can select a scenario that corresponds to the user's lifestyle. The scenario unit selects a scenario that corresponds to the user's lifestyle, for example. For example, if the user leads a busy lifestyle, the scenario unit can provide a scenario that the generation AI can complete in a short time. Also, if the user leads a relaxed lifestyle, the scenario unit can provide a scenario that the generation AI can enjoy for a long time. Furthermore, the scenario unit can select and provide an optimal scenario based on the user's lifestyle. This allows scenarios to be provided with appropriate content based on the lifestyle. The specific type of lifestyle, such as urban, rural, or family structure, and the selection method, need to be clarified. Some or all of the above-mentioned processing in the scenario unit may be performed, for example, using the generation AI, or may be performed without using the generation AI. For example, the scenario unit can provide a scenario using a generation AI that selects a scenario that corresponds to the user's lifestyle.

[0101] When generating a scenario, the scenario unit can improve the content of the scenario by reflecting user feedback. For example, the scenario unit improves the content of the scenario by reflecting user feedback. For example, the scenario unit adjusts the content of the scenario using a generation AI based on feedback previously provided by the user. The scenario unit can also learn and apply preferred scenario elements from user feedback. Furthermore, the scenario unit can improve the accuracy and naturalness of the scenario by reflecting user feedback. This allows a scenario to be provided with appropriate content based on past feedback. The specific content and acquisition method of the feedback, such as user surveys and evaluation comments, must be clearly defined. Some or all of the above-described processing in the scenario unit may be performed using, for example, a generation AI, or may be performed without using a generation AI. For example, the scenario unit can provide a scenario using a generation AI that improves the content of the scenario by reflecting user feedback.

[0102] The scenario unit can estimate the user's emotions and prioritize scenarios based on the estimated user emotions. For example, the scenario unit can estimate the user's emotions and prioritize scenarios based on the estimated user emotions. For example, when the user is in an emergency, the scenario unit can cause the generation AI to prioritize important scenarios. Furthermore, when the user is relaxed, the scenario unit can also cause the generation AI to proceed with the scenario taking the overall context into consideration. Furthermore, when the user is feeling stressed, the scenario unit can also cause the generation AI to prioritize concise and clear scenarios. This allows scenarios to be provided in an appropriate priority order according to the user's emotions. The emotion estimation is realized using an emotion estimation function, for example, an emotion engine or a generation AI. The generation AI can be 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 scenario unit can be performed using, for example, the generation AI, or can be performed without using the generation AI. For example, the scenario unit can provide scenarios using a generation AI that estimates the user's emotions and prioritizes scenarios based on the estimated user emotions.

[0103] When generating a scenario, the scenario unit can generate a region-specific scenario by taking into account the user's geographical location information. The scenario unit, for example, generates a region-specific scenario by taking into account the user's geographical location information. For example, if the user is in the United States, the scenario unit's generation AI can provide a scenario related to American culture and history. Furthermore, if the user is in Japan, the scenario unit's generation AI can select and provide a region-specific scenario based on the user's geographical location information. This allows scenarios to be provided with appropriate content based on the geographical location information. It is necessary to clarify the specific methods for obtaining and using geographical location information, such as GPS data or IP addresses. Some or all of the above-described processing in the scenario unit may be performed, for example, using the generation AI, or may be performed without using the generation AI. For example, the scenario unit can provide a scenario by using a generation AI that generates a region-specific scenario by taking into account the user's geographical location information.

[0104] When generating a scenario, the scenario unit can analyze the user's social media activities and generate a related scenario. For example, the scenario unit analyzes the user's social media activities and generates a related scenario. For example, the scenario unit uses a generation AI to reflect topics frequently discussed by the user on social media in the scenario. The scenario unit can also understand the user's interests and concerns from the user's social media activities and generate a related scenario. Furthermore, the scenario unit can analyze the content posted by the user on social media and provide an appropriate scenario. This makes it possible to provide a scenario with appropriate content based on the social media activities. The specific content of the social media activities, such as the content of posts and the number of likes, and the analysis method, need to be clarified. Some or all of the above-mentioned processing in the scenario unit may be performed, for example, using a generation AI, or may be performed without using a generation AI. For example, the scenario unit can provide a scenario using a generation AI that analyzes the user's social media activities and generates a related scenario.

[0105] When generating a scenario, the scenario unit can customize the content of the scenario by reflecting the user's past feedback. For example, the scenario unit customizes the content of the scenario by reflecting the user's past feedback. For example, the scenario unit allows the generation AI to adjust the tone and style of the scenario based on feedback provided by the user in the past. The scenario unit can also learn and apply preferred scenario elements from the user's past feedback. Furthermore, the scenario unit can allow the generation AI to optimize the content and progression of the scenario by reflecting the user's feedback. This allows a scenario to be provided with appropriate content based on the past feedback. The specific content and acquisition method of the feedback, such as user surveys or evaluation comments, must be clearly defined. Some or all of the above-described processing in the scenario unit may be performed, for example, using the generation AI, or may be performed without using the generation AI. For example, the scenario unit can provide a scenario using a generation AI that customizes the content of the scenario by reflecting the user's past feedback. === Hard Collateral 1-1 === Each of the multiple elements, including the translation unit, conversation unit, training unit, and scenario unit, described above, is implemented, for example, by at least one of the smart device 14 and the data processing device 12. For example, the translation unit is implemented by the control unit 46A of the smart device 14 and translates a user's speech in real time and responds in a specified language. The conversation unit is implemented by the control unit 46A of the smart device 14 and enables multiple users to converse simultaneously in different languages. The training unit is implemented by the control unit 46A of the smart device 14 and provides training for balanced acquisition of the four skills of listening, speaking, reading, and writing. The scenario unit is implemented by the control unit 46A of the smart device 14 and generates scenarios for using a second native language in daily life and provides them to the user. The translation unit, conversation unit, training unit, and scenario unit are also implemented by the specific processing unit 290 of the data processing device 12. === Hard Collateral 1-2 === Each of the multiple elements, including the translation unit, conversation unit, training unit, and scenario unit, described above, is realized, for example, by at least one of the smart glasses 214 and the data processing device 12. For example, the translation unit is realized by the control unit 46A of the smart glasses 214 and translates a user's speech in real time and responds in a specified language. The conversation unit is realized by the control unit 46A of the smart glasses 214 and enables multiple users to converse simultaneously in different languages. The training unit is realized by the control unit 46A of the smart glasses 214 and provides training for balanced acquisition of the four skills of listening, speaking, reading, and writing. The scenario unit is realized by the control unit 46A of the smart glasses 214 and generates scenarios for using a second native language in daily life and provides them to the user. The translation unit, conversation unit, training unit, and scenario unit are also realized by the specific processing unit 290 of the data processing device 12. === Hard Collateral 1-3 === Each of the multiple elements, including the translation unit, conversation unit, training unit, and scenario unit, described above, is realized, for example, by at least one of the headset-type terminal 314 and the data processing device 12. For example, the translation unit is realized by the control unit 46A of the headset-type terminal 314 and translates a user's speech in real time and responds in a specified language. The conversation unit is realized by the control unit 46A of the headset-type terminal 314 and enables multiple users to converse simultaneously in different languages. The training unit is realized by the control unit 46A of the headset-type terminal 314 and provides training for balanced acquisition of the four skills of listening, speaking, reading, and writing. The scenario unit is realized by the control unit 46A of the headset-type terminal 314 and generates scenarios for using the second native language in daily life and provides them to the user. The translation unit, conversation unit, training unit, and scenario unit are also realized by the specific processing unit 290 of the data processing device 12. === Hard Collateral 1-4 === Each of the multiple elements, including the translation unit, conversation unit, training unit, and scenario unit, described above, is realized, for example, by at least one of the robot 414 and the data processing device 12. For example, the translation unit is realized by the control unit 46A of the robot 414 and translates a user's utterance in real time and responds in a specified language. The conversation unit is realized by the control unit 46A of the robot 414 and enables multiple users to converse simultaneously in different languages. The training unit is realized by the control unit 46A of the robot 414 and provides training for balanced acquisition of the four skills of listening, speaking, reading, and writing. The scenario unit is realized by the control unit 46A of the robot 414 and generates scenarios for using a second native language in daily life and provides them to the user. The translation unit, conversation unit, training unit, and scenario unit are also realized by the specific processing unit 290 of the data processing device 12.

[0106] The system according to the embodiment is not limited to the above-described example, and various modifications are possible, for example, as follows.

[0107] The bilingual development and language consolidation support system may further include a progress display unit that visualizes the user's learning progress. The progress display unit displays the user's progress in graphs or charts. For example, progress may be displayed for each technique of listening, speaking, reading, and writing, allowing the user to see at a glance which areas require particular effort. The progress display unit may also display the user's achievement level toward goals set by the user in real time. Furthermore, the progress display unit may provide motivational messages and advice based on the user's progress. This allows the user to understand their own learning situation and effectively advance their studies.

[0108] The translation unit can translate based on the user's speech, taking cultural background into account. For example, when a user speaks about a topic related to a specific culture, the generative AI translates using expressions and examples appropriate to that culture. The translation unit can also provide supplementary information to help users avoid cultural misunderstandings when communicating with people from different cultures. Furthermore, the translation unit can provide resources and links to help users deepen their knowledge of a specific culture. This allows users to learn a language while deepening their understanding of different cultures.

[0109] The conversation unit can also estimate the emotions of the user's conversation partner and adjust the way the conversation proceeds based on the estimated emotions. For example, if the user's conversation partner is nervous, the conversation unit can select a topic that will help the generation AI relax. Also, if the conversation partner is excited, the conversation unit can provide a lively topic that will maintain the excitement. Furthermore, if the conversation partner is tired, the conversation unit can select a calming topic and proceed with a relaxing conversation. This allows both the user and the conversation partner to communicate comfortably.

[0110] The training unit can customize the training method according to the user's learning style. For example, if the user is a visual learner, the generation AI can provide training using visual materials. If the user is an auditory learner, the generation AI can provide training using audio materials. Furthermore, if the user is an experiential learner, the generation AI can provide training using interactive simulations. This allows users to effectively learn in the way that best suits them.

[0111] The scenario unit can estimate the user's emotions and adjust the difficulty of the scenario based on the estimated emotions. For example, if the user is nervous, the generation AI can provide an easy scenario and gradually increase the difficulty. Alternatively, if the user is relaxed, the generation AI can provide a scenario with a moderate level of difficulty. Furthermore, if the user is excited, the generation AI can provide a challenging scenario. This makes it possible to provide a scenario with an appropriate level of difficulty according to the user's emotions.

[0112] The translation unit can provide expert advice based on the user's speech. For example, if a user talks about a medical topic, the generation AI can appropriately translate medical terminology and provide relevant medical knowledge. If a user talks about a technical topic, the generation AI can appropriately translate technical terminology and provide relevant technical information. If a user talks about a legal topic, the generation AI can appropriately translate legal terminology and provide relevant legal knowledge. This allows users to learn a language while deepening their specialized knowledge.

[0113] The conversation unit can optimize the flow of the conversation by referring to the past conversation history of the user's conversation partner. For example, the conversation unit uses a generation AI to memorize topics that the conversation partner has previously discussed and incorporates related topics into the conversation. The conversation unit can also prioritize preferred topics from the conversation partner's past conversation history. Furthermore, the conversation unit can analyze the conversation partner's past conversation history to ensure a smooth conversation flow. This allows the conversation to flow appropriately based on the past conversation history.

[0114] The training unit can adjust the pace of training according to the user's progress. For example, if the user is progressing at a fast pace, the generation AI can increase the difficulty of the training. Conversely, if the user is progressing at a slow pace, the generation AI can also ease the pace of training. Furthermore, the generation AI can automatically adjust the pace of training according to the user's progress, providing an optimal learning environment. This allows training to be performed at an appropriate pace based on the user's progress.

[0115] The scenario unit can estimate the user's emotions and prioritize scenarios based on the estimated emotions. For example, if the user is in an emergency, the generation AI can prioritize important scenarios. Also, if the user is relaxed, the generation AI can proceed with the scenario taking into account the overall context. Furthermore, if the user is feeling stressed, the generation AI can prioritize concise and clear scenarios. This makes it possible to provide scenarios with appropriate priorities according to the user's emotions.

[0116] The scenario unit can customize the content of the scenario according to the user's lifestyle. For example, if the user leads a busy life, the generation AI can provide a scenario that can be completed in a short time. On the other hand, if the user leads a relaxed life, the generation AI can provide a scenario that can be enjoyed for a long time. Furthermore, the generation AI can select and provide the optimal scenario based on the user's lifestyle. This makes it possible to provide a scenario with appropriate content based on the user's lifestyle.

[0117] The processing flow of the second embodiment will be briefly explained below.

[0118] Step 1: The translation unit translates the user's speech in real time and responds in the specified language. For example, generative AI can be used to translate the user's speech and respond in the appropriate language. It can also estimate the user's emotions and adjust the tone and expression of the translation based on the estimated emotions. Furthermore, it can improve the accuracy of the translation by referring to the user's past speech history, and it can also automatically select technical terms according to the field of expertise. Step 2: The conversation part allows multiple users to converse simultaneously in different languages. For example, it can use generative AI to enable multiple users to converse simultaneously in different languages, estimate users' emotions, and adjust the way the conversation progresses. It can also refer to users' past conversation history to optimize the flow of the conversation and select conversation topics based on their areas of interest. Step 3: The training department provides training to help users master the four skills of listening, speaking, reading, and writing in a balanced way. For example, generative AI can be used to provide training to help users master the four skills in a balanced way, and the difficulty of the training can be adjusted by estimating the user's emotions. It can also optimize the training content by referring to the user's past learning history and select a training method that suits their learning style. Step 4: The scenario unit generates scenarios in which the second native language is used in daily life and provides them to the user. For example, the generation AI can be used to generate scenarios in which the second native language is used in daily life, and the content of the scenario can be adjusted by estimating the user's emotions. It can also improve the accuracy of the scenario by referring to the user's past scenario history and select scenarios that suit their lifestyle.

[0119] 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.

[0120] The data generation model 58 is a so-called generative AI (Artificial Intelligence). An example of the data generation model 58 is ChatGPT (registered trademark) (Internet search engine).<URL: https: / / openai.com / blog / chatgpt> Examples of generative AIs include the data generation model 58, such as a neural network model (e.g., a neural network model), and a neural network model (e.g., a neural network model). The data generation model 58 is obtained by performing deep learning on a neural network. A prompt including an instruction is input to the data generation model 58, and inference data such as voice data indicating speech, text data indicating text, and image data indicating an image is also input to the data generation model 58. The data generation model 58 performs inference on the input inference data in accordance with the instruction indicated by the prompt and outputs the inference result in a data format such as voice data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization. The specification processing unit 290 performs the above-mentioned specification processing using the data generation model 58. The data generation model 58 may be a fine-tuned model so as to output an inference result from a prompt that does not include an instruction. In this case, the data generation model 58 can output an inference result from a prompt that does not include an instruction. The data processing device 12 and the like include multiple types of data generation models 58, and the data generation model 58 includes AIs other than the generative AI. The AI ​​other than the generative AI may be, for example, linear regression, logistic regression, decision tree, random forest, support vector machine (SVM), k-means clustering, convolutional neural network (CNN), recurrent neural network (RNN), generative adversarial network (GAN), or naive Bayes, and can perform various processes, but is not limited to these examples. The AI ​​may also be an AI agent. When the processes of each of the above-mentioned parts are performed by AI, the processes may be performed in part or entirely by AI, but are not limited to these examples. The processes performed by AI, including the generative AI, may be replaced with rule-based processes.

[0121] 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.

[0122] The correspondence between each part and the device or control part is not limited to the example described above, and various modifications are possible.

[0123] [Second embodiment] FIG. 3 shows an example of the configuration of a data processing system 210 according to the second embodiment.

[0124] 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.

[0125] 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.

[0126] 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.

[0127] 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.

[0128] 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).

[0129] 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.

[0130] 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.

[0131] 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.

[0132] 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.

[0133] 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.

[0134] 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.

[0135] 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.

[0136] The data generation model 58 is a so-called generative AI. An example of the data generation model 58 is a generative AI such as ChatGPT. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 receives a prompt containing an instruction, as well as inference data such as voice data representing speech, text data representing text, and image data representing an image. The data generation model 58 performs inference on the input inference data in accordance with the instruction indicated by the prompt and outputs the inference result in a data format such as voice data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization. The identification processing unit 290 performs the above-mentioned identification processing using the data generation model 58. The data generation model 58 may be a fine-tuned model so as to output an inference result from a prompt that does not include an instruction. In this case, the data generation model 58 can output an inference result from a prompt that does not include an instruction. The data processing device 12 and the like include multiple types of data generation models 58, and the data generation model 58 includes AI other than the generative AI. The AI ​​other than the generative AI may be, for example, linear regression, logistic regression, decision tree, random forest, support vector machine (SVM), k-means clustering, convolutional neural network (CNN), recurrent neural network (RNN), generative adversarial network (GAN), or naive Bayes, and can perform various processes, but is not limited to these examples. The AI ​​may also be an AI agent. When the processes of each of the above-mentioned parts are performed by AI, the processes may be performed in part or entirely by AI, but are not limited to these examples. The processes performed by AI, including the generative AI, may be replaced with rule-based processes.

[0137] 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.

[0138] The correspondence between each part and the device or control part is not limited to the example described above, and various modifications are possible.

[0139] [Third embodiment] FIG. 5 shows an example of the configuration of a data processing system 310 according to the third embodiment.

[0140] 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.

[0141] 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.

[0142] 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.

[0143] 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.

[0144] 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).

[0145] 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.

[0146] 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.

[0147] 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.

[0148] 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.

[0149] 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.

[0150] 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.

[0151] 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.

[0152] The data generation model 58 is a so-called generative AI. An example of the data generation model 58 is a generative AI such as ChatGPT. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 receives a prompt containing an instruction, as well as inference data such as voice data representing speech, text data representing text, and image data representing an image. The data generation model 58 performs inference on the input inference data in accordance with the instruction indicated by the prompt and outputs the inference result in a data format such as voice data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization. The identification processing unit 290 performs the above-mentioned identification processing using the data generation model 58. The data generation model 58 may be a fine-tuned model so as to output an inference result from a prompt that does not include an instruction. In this case, the data generation model 58 can output an inference result from a prompt that does not include an instruction. The data processing device 12 and the like include multiple types of data generation models 58, and the data generation model 58 includes AI other than the generative AI. The AI ​​other than the generative AI may be, for example, linear regression, logistic regression, decision tree, random forest, support vector machine (SVM), k-means clustering, convolutional neural network (CNN), recurrent neural network (RNN), generative adversarial network (GAN), or naive Bayes, and can perform various processes, but is not limited to these examples. The AI ​​may also be an AI agent. When the processes of each of the above-mentioned parts are performed by AI, the processes may be performed in part or entirely by AI, but are not limited to these examples. The processes performed by AI, including the generative AI, may be replaced with rule-based processes.

[0153] 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.

[0154] The correspondence between each part and the device or control part is not limited to the example described above, and various modifications are possible.

[0155] [Fourth embodiment] FIG. 7 shows an example of the configuration of a data processing system 410 according to the fourth embodiment.

[0156] 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.

[0157] 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.

[0158] 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.

[0159] 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.

[0160] 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).

[0161] 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.

[0162] 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.

[0163] 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.

[0164] 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.

[0165] 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.

[0166] 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.

[0167] 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.

[0168] 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.

[0169] The data generation model 58 is a so-called generative AI. An example of the data generation model 58 is a generative AI such as ChatGPT. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 receives a prompt containing an instruction, as well as inference data such as voice data representing speech, text data representing text, and image data representing an image. The data generation model 58 performs inference on the input inference data in accordance with the instruction indicated by the prompt and outputs the inference result in a data format such as voice data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization. The identification processing unit 290 performs the above-mentioned identification processing using the data generation model 58. The data generation model 58 may be a fine-tuned model so as to output an inference result from a prompt that does not include an instruction. In this case, the data generation model 58 can output an inference result from a prompt that does not include an instruction. The data processing device 12 and the like include multiple types of data generation models 58, and the data generation model 58 includes AI other than the generative AI. The AI ​​other than the generative AI may be, for example, linear regression, logistic regression, decision tree, random forest, support vector machine (SVM), k-means clustering, convolutional neural network (CNN), recurrent neural network (RNN), generative adversarial network (GAN), or naive Bayes, and can perform various processes, but is not limited to these examples. The AI ​​may also be an AI agent. When the processes of each of the above-mentioned parts are performed by AI, the processes may be performed in part or entirely by AI, but are not limited to these examples. The processes performed by AI, including the generative AI, may be replaced with rule-based processes.

[0170] 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.

[0171] The correspondence between each part and the device or control part is not limited to the example described above, and various modifications are possible.

[0172] 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.

[0173] 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.

[0174] 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.

[0175] 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).

[0176] 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.

[0177] 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."

[0178] 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.

[0179] 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.

[0180] 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.

[0181] 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.

[0182] 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.

[0183] 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.

[0184] 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.

[0185] 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.

[0186] 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.

[0187] 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.

[0188] The above-described description and illustrations are a detailed explanation of the parts related to the technology of the present disclosure and are merely an example of the technology of the present disclosure. For example, the above description of the configuration, functions, actions, and effects is an explanation of an example of the configuration, functions, actions, and effects of the parts related to the technology of the present disclosure. Therefore, it goes without saying that unnecessary parts may be deleted, new elements may be added, or replacements may be made to the above-described description and illustrations within the scope of the gist of the technology of the present disclosure. Furthermore, to avoid confusion and facilitate understanding of the parts related to the technology of the present disclosure, the above-described description and illustrations omit explanations of common technical knowledge that do not require particular explanation to enable the implementation of the technology of the present disclosure.

[0189] 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.

[0190] [Explanation of symbols]

[0191] 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 translation unit having a multilingual conversation function that translates user utterances in real time and responds in a specified language; a conversation unit having a multi-party conversation algorithm that allows multiple users to converse simultaneously in different languages; The training department has a 4-technique approach that provides training to equip students with the four skills of listening, speaking, reading, and writing. a scenario unit having a native language acquisition program that generates scenarios for using the second native language in daily life and provides the scenarios to the user; A system characterized by:

2. The translation unit Using generative AI to translate user utterances in real time and respond in the appropriate language 2. The system of claim 1.

3. The conversation unit is Using generative AI to enable multiple users to converse simultaneously in different languages 2. The system of claim 1.

4. The training section Using generative AI, we provide training to help students master the four skills of listening, speaking, reading, and writing in a balanced manner.

2. The system of claim 1.

5. The scenario section Using generative AI to generate scenarios for using a second native language in daily life and provide them to users 2. The system of claim 1.

6. The translation unit Inferring user sentiment and adjusting the tone and expression of the translation based on the estimated sentiment 2. The system of claim 1.

7. The translation unit When translating, the accuracy of the translation is improved by referring to the user's past speech history.

2. The system of claim 1.

8. The translation unit During translation, technical terms are automatically selected according to the user's field of expertise.

2. The system of claim 1.

9. The translation unit When translating, adjust the translation speed according to the user's speaking rate 2. The system of claim 1.

10. The translation unit Estimate user sentiment and prioritize translations based on the estimated sentiment 2. The system of claim 1.

Images