System

Abstract

An object of the system according to the embodiment is to provide an effective English learning environment to a user who has few opportunities to speak English or a user who does not have time to go to an English conversation class.SOLUTION: A system includes a conversation unit, a learning unit, and a feedback unit. The conversation unit analyzes the user's speech and makes a reply. The learning component detects user pronunciation and grammar errors and provides feedback. The feedback unit records the user's conversation and provides detailed feedback.SELECTED DRAWING: Figure 1

Description

[Technical Field]

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

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

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

[0004] Conventional technologies have had the problem that it is difficult to provide an effective English learning environment for users who have few opportunities to speak English or who do not have time to attend English conversation classes.

[0005] The system according to the embodiment aims to provide an effective English learning environment for users who have few opportunities to speak English or who do not have time to attend English conversation classes. [Means for solving the problem]

[0006] The system according to the embodiment includes a conversation unit, a learning unit, and a feedback unit. The conversation unit analyzes what the user says and provides a response. The learning unit detects the user's pronunciation and grammar errors and provides feedback. The feedback unit records the user's conversation and provides detailed feedback. [Effects of the Invention]

[0007] The system according to the embodiment can provide an effective English learning environment to users who have few opportunities to speak English or who do not have time to attend English conversation classes. [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) An English learning system according to an embodiment of the present invention automatically analyzes a user's utterances, generates appropriate responses from a generation AI, detects pronunciation and grammatical errors, and provides detailed feedback. The English learning system analyzes the user's utterances and generates appropriate responses from a generation AI, allowing the user to enjoy English conversations anytime, anywhere. The English learning system also detects the user's pronunciation and grammatical errors and provides real-time feedback. Furthermore, the English learning system records the user's conversations and provides detailed feedback. For example, when a user says, "The weather is nice today," the generation AI replies, "Yes, it's sunny today." The English learning system then detects the user's pronunciation and grammatical errors and provides real-time feedback. For example, when a user says, "I went to the store," the generation AI provides feedback such as, "'goed' is incorrect. The correct word is 'went.'" The English learning system then records the user's conversations and provides detailed feedback. For example, if a user says, "I am very happy today," the generation AI will provide feedback such as, "Your pronunciation is good, but you could emphasize the pronunciation of 'very' a little more." This allows the English learning system to analyze the user's utterances, detect pronunciation and grammar errors, and provide detailed feedback. This allows the English learning system to effectively support the user's English learning. For example, the user can immediately correct their pronunciation and grammar errors and improve their English conversation skills. In addition, the detailed feedback allows the user to improve their pronunciation and expression.

[0029] The English language learning system according to the embodiment includes a conversation unit, a learning unit, and a feedback unit. The conversation unit analyzes user utterances and provides a response. The user utterances include, but are not limited to, everyday conversations, questions, and opinions. The conversation unit converts the user utterances into text data using, for example, speech recognition technology and analyzes the content of the utterances using natural language processing technology. The conversation unit can also generate appropriate responses using a machine learning model. For example, when the user says, "The weather is nice today," the generation AI can respond with, "Yes, it's sunny today." When the user says, "I'm hungry," the generation AI can respond with, "Is there anything you'd like to eat?" When the user asks, "What are your plans for tomorrow?" the generation AI can respond with, "I have a meeting tomorrow." The learning unit detects the user's pronunciation and grammar errors and provides feedback. For example, the learning unit analyzes the user's pronunciation using speech recognition technology and detects grammar errors using a grammar analysis algorithm. The learning unit can also provide real-time feedback. For example, if a user says, "I went to the store," the generation AI can provide feedback such as, "'goed' is incorrect. The correct answer is 'went'." If a user says, "She don't like apples," the learning unit can provide feedback such as, "'don't' is incorrect. The correct answer is 'doesn't'." If a user says, "He is more taller than me," the generation AI can provide feedback such as, "'more taller' is incorrect. The correct answer is 'taller'." The feedback unit can record a user's conversation and provide detailed feedback later. For example, if a user says, "I am very happy today," the generation AI can provide feedback such as, "Your pronunciation is good, but you could emphasize the pronunciation of 'very' a little more."Furthermore, when a user says, "I think this is a good idea," the feedback unit can cause the generation AI to provide feedback such as, "Your pronunciation is good, but you should practice pronouncing 'think' a little more." When a user says, "I want to go to the park," the feedback unit can cause the generation AI to provide feedback such as, "Your pronunciation is good, but you should practice pronouncing 'want' a little more." This enables the English language learning system according to the embodiment to analyze user utterances, detect pronunciation and grammatical errors, and provide detailed feedback.

[0030] The English learning system further includes a support unit that provides information in English to support the user's daily life. The support unit provides information in English to support the user's daily life. For example, when the user enters a restaurant, the generation AI can ask in English, "What are the recommended menu items at this restaurant?" When the user goes shopping, the support unit can also ask in English, "Where is this item?" When the user gets lost, the support unit can also ask in English, "How do I get to this place?" This allows the user to use English naturally in their daily lives. Some or all of the above-described processing in the support unit may be performed using AI, for example, or may be performed without AI. For example, the support unit can input the user's utterances into the generation AI, which can then generate appropriate English questions.

[0031] The English learning system further includes an analysis unit that analyzes the user's utterances and generates an appropriate response. The analysis unit analyzes the user's utterances and generates an appropriate response. For example, the analysis unit converts the user's utterances into text data using speech recognition technology and analyzes the content of the utterances using natural language processing technology. The analysis unit can also generate an appropriate response using a machine learning model. For example, when the user says, "The weather is nice today," the analysis unit can cause the generation AI to respond, "Yes, it's sunny today." When the user says, "I'm hungry," the analysis unit can cause the generation AI to respond, "Is there anything you'd like to eat?" When the user asks, "What are your plans for tomorrow?" the analysis unit can cause the generation AI to respond, "I have a meeting tomorrow." This makes it possible to analyze the user's utterances and generate an appropriate response. Some or all of the above-described processing in the analysis unit may be performed using, for example, AI, or may be performed without AI. For example, the analysis unit can input the user's utterances into the generation AI, which can then generate an appropriate response.

[0032] The English learning system further includes a protection unit that encrypts or anonymizes data to protect the user's data. The protection unit encrypts or anonymizes data to protect the user's data. The protection unit can encrypt the user's data using, for example, AES encryption technology. The protection unit can also anonymize the user's data using data masking technology. For example, the protection unit encrypts the user's personal information to prevent third parties from accessing it. The protection unit can also anonymize the user's speech data to protect privacy. This makes it possible to protect the user's data. Some or all of the above-mentioned processing in the protection unit may be performed using, for example, AI, or may be performed without using AI. For example, the protection unit can input the user's data to a generation AI, which can then perform appropriate encryption or anonymization.

[0033] The conversation unit can analyze the user's interests during a conversation and select a conversation topic based on that. For example, if the user is interested in sports, the generation AI can provide topics related to sports. If the user is talking about travel, the generation AI can provide information about travel destinations and recommended spots. If the user is interested in music, the generation AI can provide topics about the latest music trends and artists. This enables conversations based on the user's interests. Some or all of the above-mentioned processing in the conversation unit can be performed using, or without, AI. For example, the conversation unit can input the user's utterances into the generation AI, which can then select an appropriate conversation topic.

[0034] The conversation unit can refer to the user's past conversation history and generate a customized response. For example, the conversation unit allows the generation AI to provide related topics based on what the user has previously said. The conversation unit can also allow the generation AI to provide new information based on topics in which the user has previously shown interest. The conversation unit can also allow the generation AI to provide additional information or answers based on what the user has previously asked. This makes it possible to provide a customized response based on the user's past conversation history. Some or all of the above-mentioned processing in the conversation unit may be performed using AI, for example, or may be performed without using AI. For example, the conversation unit can input the user's past conversation history into the generation AI, which then generates a customized response.

[0035] The conversation unit can analyze the context of the conversation and switch the conversation at an appropriate time. For example, if the user shows signs of getting bored with the topic, the generation AI can provide a new topic. Furthermore, after the user asks a question, the conversation unit can provide an answer at an appropriate time. Furthermore, if the user indicates that they want to change the topic, the generation AI can smoothly switch the topic. This makes it possible to switch the conversation at an appropriate time according to the context of the conversation. Some or all of the above-mentioned processing in the conversation unit may be performed using AI, for example, or may be performed without using AI. For example, the conversation unit can input the user's utterances into the generation AI, and the generation AI can switch the conversation at an appropriate time.

[0036] The conversation unit can analyze the user's gestures and facial expressions during the conversation and adjust the response based on the analysis. For example, if the user smiles, the generation AI can provide a humorous response. If the user looks confused, the generation AI can add an explanation. If the user nods, the generation AI can continue the conversation. This enables responses based on the user's gestures and facial expressions. Some or all of the above-described processing in the conversation unit may be performed using AI, for example, or may be performed without using AI. For example, the conversation unit can input the user's gestures and facial expressions into the generation AI, which can then generate an appropriate response.

[0037] The conversation unit can provide relevant information and suggestions to the user based on the content of the conversation. For example, if the user is talking about traveling, the generation AI can suggest recommended travel destinations. Also, if the user is talking about cooking, the generation AI can provide recipes. Also, if the user is talking about movies, the generation AI can provide information about related movies. This makes it possible to provide relevant information and suggestions based on the content of the conversation. Some or all of the above-mentioned processing in the conversation unit may be performed using AI, for example, or may be performed without using AI. For example, the conversation unit can input the user's utterances into the generation AI, which can then generate appropriate information and suggestions.

[0038] The conversation unit can translate what the user says during the conversation and generate a response in a different language. For example, if the user speaks in English, the generation AI can respond in Japanese. Also, if the user speaks in French, the generation AI can respond in English. Also, if the user speaks in Spanish, the generation AI can respond in German. This makes it possible to translate the user's utterances and respond in other languages. Some or all of the above-mentioned processing in the conversation unit may be performed using AI, for example, or may be performed without using AI. For example, the conversation unit can input the user's utterances into the generation AI, which can then generate an appropriate translation and response.

[0039] The learning unit can analyze the user's learning progress and provide a study plan. For example, if the user is struggling with a particular grammar point, the generation AI can provide a study plan focusing on that point. Furthermore, if the user is struggling with pronunciation, the generation AI can provide a study plan that emphasizes pronunciation practice. Furthermore, if the user wants to improve their vocabulary, the generation AI can provide a study plan specialized for vocabulary learning. This makes it possible to provide an optimal study plan based on the user's learning progress. Some or all of the above-described processing in the learning unit may be performed using, or without, AI. For example, the learning unit can input the user's learning data into the generation AI, which can then generate an appropriate study plan.

[0040] The learning unit can analyze the user's pronunciation and grammar errors in detail and suggest specific ways to improve them. For example, if the user says, "I went to the store," the generation AI can provide feedback such as, "'goed' is incorrect. The correct word is 'went'." Alternatively, if the user says, "She don't like apples," the generation AI can provide feedback such as, "'don't' is incorrect. The correct word is 'doesn't'." Alternatively, if the user says, "He is more taller than me," the generation AI can provide feedback such as, "'more taller' is incorrect. The correct word is 'taller'." This allows the generation AI to suggest specific ways to improve the user's pronunciation and grammar errors. Some or all of the above-described processing in the learning unit may be performed using, or without, AI. For example, the learning unit can input the user's utterances into the generation AI, which can then generate appropriate ways to improve the pronunciation and grammar.

[0041] The learning unit can refer to the user's learning history and provide individually customized feedback. For example, the learning unit can have the generation AI provide feedback on a grammar item that the user made a mistake on in the past. The learning unit can also have the generation AI provide feedback for review based on content that the user has previously studied. The learning unit can also have the generation AI provide related feedback based on topics that the user has previously shown interest in. This makes it possible to provide customized feedback based on the user's learning history. Some or all of the above-described processing in the learning unit may be performed using, or without, AI. For example, the learning unit can input the user's learning history into the generation AI, which then generates customized feedback.

[0042] The learning unit can provide different feedback formats (text, audio, video, etc.) depending on the user's learning style. For example, if the user is a visual learner, the generation AI can provide video-format feedback. If the user is an auditory learner, the learning unit can also provide audio-format feedback. If the user is a text-based learner, the learning unit can also provide text-format feedback. This makes it possible to provide feedback formats according to the user's learning style. Some or all of the above-mentioned processing in the learning unit may be performed using AI, for example, or may be performed without using AI. For example, the learning unit can input the user's learning style into the generation AI, which can then generate an appropriate feedback format.

[0043] The learning unit can provide feedback focused on specific skills based on the user's learning goals. For example, if the user wants to improve their pronunciation, the generation AI can provide feedback on pronunciation. Furthermore, if the user wants to strengthen their grammar, the generation AI can provide feedback on grammar. Furthermore, if the user wants to improve their vocabulary, the generation AI can provide feedback on vocabulary. This makes it possible to provide feedback focused on specific skills based on the user's learning goals. Some or all of the above-described processing in the learning unit may be performed using AI, or may be performed without AI. For example, the learning unit can input the user's learning goals into the generation AI, which can then generate appropriate feedback.

[0044] The learning unit can provide optimal feedback depending on the user's learning environment (location, time of day, etc.). For example, if the user is studying in a quiet place, the generation AI can provide detailed feedback. Furthermore, if the user is studying while on the move, the learning unit can provide concise feedback. Furthermore, if the user is studying at night, the generation AI can provide feedback in a relaxed tone. This makes it possible to provide optimal feedback depending on the user's learning environment. Some or all of the above-mentioned processing in the learning unit may be performed using AI, for example, or may be performed without using AI. For example, the learning unit can input the user's learning environment into the generation AI, which can then generate appropriate feedback.

[0045] The feedback unit can analyze the user's conversation history in detail and suggest specific improvements. For example, the feedback unit allows the generation AI to provide feedback on grammar items that the user made mistakes on in the past. The feedback unit can also allow the generation AI to provide feedback for review based on content the user has previously studied. The feedback unit can also allow the generation AI to provide related feedback based on topics the user has previously shown interest in. This makes it possible to suggest specific improvements based on the user's conversation history. Some or all of the above-mentioned processing in the feedback unit may be performed using, or without, AI. For example, the feedback unit can input the user's conversation history into the generation AI, which then generates appropriate improvements.

[0046] The feedback unit can customize the content of the feedback to match the user's learning goals. For example, if the user wants to improve their pronunciation, the generation AI can provide feedback on their pronunciation. Furthermore, if the user wants to strengthen their grammar, the feedback unit can provide feedback on their grammar. Furthermore, if the user wants to improve their vocabulary, the feedback unit can provide feedback on their vocabulary. This makes it possible to provide customized feedback based on the user's learning goals. Some or all of the above-described processing in the feedback unit may be performed using, or without, AI. For example, the feedback unit can input the user's learning goals into the generation AI, which can then generate appropriate feedback.

[0047] The feedback unit can adjust the timing of feedback to match the user's learning rhythm. For example, if the user is concentrating, the generation AI can increase the frequency of feedback. Also, if the user is tired, the feedback unit can reduce the frequency of feedback. Also, if the user is taking a break, the feedback unit can pause feedback and provide it when the user resumes. This makes it possible to adjust the timing of feedback according to the user's learning rhythm. Some or all of the above-mentioned processing in the feedback unit may be performed using AI, for example, or may be performed without using AI. For example, the feedback unit can input the user's learning rhythm into the generation AI, which can then generate appropriate feedback timing.

[0048] The feedback unit can adjust the content of the feedback based on the user's interests. For example, if the user is interested in sports, the generation AI can provide feedback related to sports. If the user is talking about travel, the feedback unit can also provide information about travel destinations and recommended spots. If the user is interested in music, the feedback unit can also provide topics about the latest music trends and artists. This makes it possible to adjust the content of the feedback based on the user's interests. Some or all of the above-described processing in the feedback unit may be performed using AI, for example, or may be performed without using AI. For example, the feedback unit can input the user's interests into the generation AI, which can then generate appropriate feedback content.

[0049] The feedback unit can link the content of the feedback with other learning resources (books, videos, etc.). For example, if the user is struggling with a particular grammar point, the generation AI can suggest books or videos related to that point. Also, if the user is struggling with pronunciation, the feedback unit can suggest videos that are useful for pronunciation practice. Also, if the user wants to improve their vocabulary, the feedback unit can suggest books that are useful for vocabulary learning. This makes it possible to provide feedback linked to other learning resources. Some or all of the above-mentioned processing in the feedback unit may be performed, for example, using AI, or may be performed without using AI. For example, the feedback unit can input the user's learning data into the generation AI, which can then suggest appropriate learning resources.

[0050] The feedback unit can provide feedback content in stages according to the user's learning progress. For example, if the user is at a beginner's level, the generation AI can provide basic feedback. Furthermore, if the user is at an intermediate level, the feedback unit can also provide intermediate-level feedback. Furthermore, if the user is at an advanced level, the generation AI can also provide advanced feedback. This makes it possible to provide feedback in stages according to the user's learning progress. Some or all of the above-mentioned processing in the feedback unit may be performed using AI, for example, or may be performed without using AI. For example, the feedback unit can input the user's learning progress into the generation AI, which can then generate appropriate feedback.

[0051] The support unit can analyze the user's current situation and environment in real time and provide optimal support. For example, if the user is at a restaurant, the generation AI can provide a translation of the menu. If the user is at an airport, the generation AI can also provide support for checking flight information. If the user is at a hotel, the generation AI can also provide support for check-in procedures. This makes it possible to provide optimal support based on the user's current situation and environment. Some or all of the above-mentioned processing in the support unit may be performed using AI, for example, or may be performed without using AI. For example, the support unit can input the user's current situation and environment into the generation AI, which can then generate appropriate support.

[0052] The assistance unit can refer to the user's past assistance history and provide individually customized assistance. For example, the assistance unit allows the generation AI to provide relevant assistance based on assistance content that the user has used in the past. The assistance unit can also allow the generation AI to provide relevant assistance based on topics in which the user has shown interest in the past. The assistance unit can also allow the generation AI to provide relevant assistance based on places the user has visited in the past. This makes it possible to provide customized assistance based on the user's past assistance history. Some or all of the above-described processing in the assistance unit may be performed using AI, for example, or may be performed without using AI. For example, the assistance unit can input the user's past assistance history into the generation AI, which can then generate appropriate assistance.

[0053] The support unit can adjust the support content to match the user's learning goals. For example, if the user wants to improve their pronunciation, the generation AI can provide support regarding pronunciation. Furthermore, if the user wants to strengthen their grammar, the support unit can provide support regarding grammar. Furthermore, if the user wants to improve their vocabulary, the support unit can provide support regarding vocabulary. This makes it possible to adjust the support content based on the user's learning goals. Some or all of the above-mentioned processing in the support unit may be performed using AI, for example, or may be performed without using AI. For example, the support unit can input the user's learning goals into the generation AI, which can then generate appropriate support.

[0054] The support unit can adjust the support content based on the user's interests and concerns. For example, if the user is interested in sports, the generation AI can provide support related to sports. Furthermore, if the user is talking about travel, the generation AI can provide information about travel destinations and recommended spots. Furthermore, if the user is interested in music, the generation AI can provide topics about the latest music trends and artists. This makes it possible to adjust the support content based on the user's interests and concerns. Some or all of the above-mentioned processing in the support unit may be performed using AI, for example, or may be performed without using AI. For example, the support unit can input the user's interests and concerns into the generation AI, which can then generate appropriate support content.

[0055] The support unit can link the support content with other learning resources (books, videos, etc.). For example, if the user is struggling with a particular grammar point, the generation AI can suggest books or videos related to that point. Also, if the user is struggling with pronunciation, the generation AI can suggest videos that are useful for pronunciation practice. Also, if the user wants to improve their vocabulary, the generation AI can suggest books that are useful for vocabulary learning. This makes it possible to provide support content that is linked with other learning resources. Some or all of the above-mentioned processing in the support unit may be performed, for example, using AI, or may be performed without using AI. For example, the support unit can input the user's learning data into the generation AI, which can then suggest appropriate learning resources.

[0056] The support unit can provide support content in stages according to the user's learning progress. For example, if the user is at a beginner's level, the generation AI can provide basic support. Furthermore, if the user is at an intermediate level, the support unit can also provide intermediate-level support. Furthermore, if the user is at an advanced level, the generation AI can also provide advanced support. This makes it possible to provide support content in stages according to the user's learning progress. Some or all of the above-mentioned processing in the support unit may be performed using AI, for example, or may be performed without using AI. For example, the support unit can input the user's learning progress into the generation AI, which can then generate appropriate support.

[0057] The analysis unit can analyze the user's utterances in detail and suggest specific improvements. For example, if the user says, "I went to the store," the generation AI can provide feedback such as, "'goed' is incorrect. The correct word is 'went'." Alternatively, if the user says, "She doesn't like apples," the generation AI can provide feedback such as, "'don't' is incorrect. The correct word is 'doesn't'." Alternatively, if the user says, "He is more taller than me," the generation AI can provide feedback such as, "'more taller' is incorrect. The correct word is 'taller'." This allows specific improvements to be suggested based on the user's utterances. Some or all of the above-described processing in the analysis unit may be performed using, or without, AI. For example, the analysis unit can input the user's utterances into the generation AI, which can then generate appropriate improvements.

[0058] The analysis unit can customize the analysis results to suit the user's learning goals. For example, if the user wants to improve their pronunciation, the generation AI can provide analysis results related to pronunciation. Furthermore, if the user wants to strengthen their grammar, the analysis unit can provide analysis results related to grammar. Furthermore, if the user wants to improve their vocabulary, the analysis unit can provide analysis results related to vocabulary. This makes it possible to provide customized analysis results based on the user's learning goals. Some or all of the above-mentioned processing in the analysis unit may be performed using, or without, AI. For example, the analysis unit can input the user's learning goals into the generation AI, which can then generate appropriate analysis results.

[0059] The analysis unit can adjust the timing of the analysis results to match the user's learning rhythm. For example, if the user is concentrating, the analysis unit causes the generation AI to increase the frequency of the analysis results. Also, if the user is tired, the analysis unit can cause the generation AI to decrease the frequency of the analysis results. Also, if the user is taking a break, the analysis unit can cause the generation AI to pause the analysis results and provide them when the user resumes. This makes it possible to adjust the timing of the analysis results according to the user's learning rhythm. Some or all of the above-mentioned processing in the analysis unit may be performed using, or without, AI. For example, the analysis unit can input the user's learning rhythm into the generation AI, and the generation AI can generate appropriate timing for the analysis results.

[0060] The analysis unit can adjust the analysis results based on the user's interests. For example, if the user is interested in sports, the generation AI can provide analysis results related to sports. If the user is talking about travel, the analysis unit can also provide information about travel destinations and recommended spots. If the user is interested in music, the analysis unit can also provide topics about the latest music trends and artists. This makes it possible to adjust the analysis results based on the user's interests. Some or all of the above-mentioned processing in the analysis unit may be performed using AI, for example, or may be performed without using AI. For example, the analysis unit can input the user's interests into the generation AI, which can then generate appropriate analysis results.

[0061] The analysis unit can link the analysis results with other learning resources (books, videos, etc.). For example, if the user is struggling with a particular grammar point, the generation AI can suggest books or videos related to that point. Also, if the user is struggling with pronunciation, the analysis unit can suggest videos that are useful for pronunciation practice. Also, if the user wants to improve their vocabulary, the generation AI can suggest books that are useful for vocabulary learning. This makes it possible to provide analysis results that are linked with other learning resources. Some or all of the above-mentioned processing in the analysis unit may be performed, for example, using AI, or may be performed without using AI. For example, the analysis unit can input the user's learning data into the generation AI, which can then suggest appropriate learning resources.

[0062] The analysis unit can provide analysis results in stages according to the user's learning progress. For example, if the user is at a beginner's level, the generation AI can provide basic analysis results. Furthermore, if the user is at an intermediate level, the analysis unit can also provide intermediate-level analysis results. Furthermore, if the user is at an advanced level, the generation AI can also provide advanced analysis results. This makes it possible to provide analysis results in stages according to the user's learning progress. Some or all of the above-mentioned processing in the analysis unit may be performed using AI, for example, or may be performed without using AI. For example, the analysis unit can input the user's learning progress into the generation AI, and the generation AI can generate appropriate analysis results.

[0063] The protection unit can analyze the user's data in detail and select an encryption method. For example, if the user's data has high confidentiality, the generation AI can select a strong encryption method. If the user's data has medium confidentiality, the protection unit can also select a moderate encryption method. If the user's data has low confidentiality, the protection unit can also select a basic encryption method. This makes it possible to select the optimal encryption method based on the user's data. Some or all of the above-mentioned processing in the protection unit can be performed using AI, for example, or can be performed without using AI. For example, the protection unit can input the user's data into the generation AI, and the generation AI can generate an appropriate encryption method.

[0064] The protection unit can customize the content of data protection to match the user's privacy settings. For example, if the user selects a high privacy setting, the generation AI can provide strict data protection. Alternatively, if the user selects a medium privacy setting, the protection unit can provide moderate data protection. Alternatively, if the user selects a low privacy setting, the generation AI can provide basic data protection. This makes it possible to provide customized data protection based on the user's privacy settings. Some or all of the above-mentioned processing in the protection unit may be performed using AI, for example, or may be performed without using AI. For example, the protection unit can input the user's privacy settings into the generation AI, which can then generate appropriate data protection content.

[0065] The protection unit can adjust the timing of data protection according to the user's usage status. For example, if the user frequently uses data, the generation AI can provide data protection in real time. Alternatively, if the user occasionally uses data, the protection unit can cause the generation AI to provide data protection periodically. Alternatively, if the user rarely uses data, the protection unit can cause the generation AI to provide data protection as needed. This makes it possible to adjust the timing of data protection according to the user's usage status. Some or all of the above-mentioned processing in the protection unit may be performed using AI, for example, or may be performed without using AI. For example, the protection unit can input the user's usage status to the generation AI, which can then generate an appropriate timing for data protection.

[0066] The protection unit can adjust the content of data protection based on the user's interests and concerns. For example, if the user is interested in high security, the generation AI can provide strong data protection. Alternatively, if the user is interested in medium security, the protection unit can provide moderate data protection. Alternatively, if the user is interested in low security, the generation AI can provide basic data protection. This makes it possible to adjust the content of data protection based on the user's interests and concerns. Some or all of the above-mentioned processing in the protection unit may be performed using AI, for example, or may be performed without using AI. For example, the protection unit can input the user's interests and concerns into the generation AI, which can then generate appropriate data protection content.

[0067] The protection unit can link the data protection content with other security resources (firewalls, antivirus software, etc.). For example, the generation AI of the protection unit can link with a firewall to strengthen data protection. The protection unit can also link with antivirus software to strengthen data protection. The protection unit can also link with other security resources to provide comprehensive data protection. This makes it possible to provide data protection in cooperation with other security resources. Some or all of the above-mentioned processing in the protection unit may be performed using AI, for example, or may be performed without using AI. For example, the protection unit can input other security resources into the generation AI, which can then generate appropriate data protection content.

[0068] The protection unit can provide data protection content in stages according to the user's usage status. For example, if the user frequently uses data, the generation AI can provide data protection in real time. Alternatively, if the user occasionally uses data, the protection unit can provide data protection periodically. Alternatively, if the user rarely uses data, the protection unit can provide data protection as needed. This makes it possible to provide data protection in stages according to the user's usage status. Some or all of the above-mentioned processing in the protection unit may be performed using AI, for example, or may be performed without using AI. For example, the protection unit can input the user's usage status to the generation AI, which can then generate appropriate data protection content.

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

[0070] In addition to analyzing user utterances, English learning systems can also provide customized learning plans based on the user's learning style. For example, visual learners can receive feedback using visual aids and infographics. Auditory learners can receive audio feedback and podcast-style learning materials. Furthermore, users who prefer hands-on learning can progress through interactive simulations and role-playing. This makes it possible to provide the optimal learning experience based on the user's learning style.

[0071] The English learning system can not only analyze a user's utterances but also provide feedback that takes into account the background and context of the user's utterances. For example, if a user is practicing business English conversation, the system can provide feedback focusing on business vocabulary and formal expressions. If a user is practicing travel conversation, the system can provide feedback that takes into account travel-related phrases and cultural background. Furthermore, if a user is practicing everyday conversation, the system can provide feedback on casual expressions and slang. This allows for specific feedback tailored to the user's learning goals.

[0072] The English learning system not only analyzes the user's utterances, but also analyzes the frequency and patterns of the user's utterances to visualize learning progress. For example, if the user frequently makes mistakes on a particular grammar point, the system can provide additional practice questions on that point. Also, if the user struggles with a particular pronunciation, the system can provide special pronunciation practice sessions. Furthermore, if the user shows interest in a particular topic, the system can provide learning materials related to that topic. This allows for a personalized learning plan based on the user's learning progress.

[0073] In addition to analyzing user utterances, the English learning system can provide personalized study reminders based on the user's learning history. For example, it can send reminders to periodically review what the user has learned in the past. If the user has set a specific goal, it can track the user's progress toward that goal and provide reminders based on the level of achievement. Furthermore, if the user has stopped studying, the system can send reminders to encourage them to resume. This can support the user's study habits and encourage continuous learning.

[0074] The English learning system not only analyzes the user's speech, but also the tone and rhythm of the user's speech and can provide feedback to help improve pronunciation. For example, if the user uses the wrong accent for a particular word, the system can provide feedback indicating the correct accent for that word. Also, if the user speaks too fast, the system can suggest an appropriate speaking speed. Furthermore, if the user uses the wrong rhythm, the system can suggest ways to practice rhythm. This makes it possible to comprehensively improve the user's pronunciation skills.

[0075] The English language learning system can not only analyze a user's utterances, but also provide relevant cultural background and knowledge based on the content of the user's utterances. For example, if a user uses a particular English expression, the system can explain the expression's cultural background and historical meaning. Also, if a user is talking about a specific topic, the system can provide cultural information and facts related to that topic. Furthermore, the system can provide information about manners and customs that are useful when users communicate with people from different cultures. This allows users to deepen not only their language skills but also their cultural understanding.

[0076] The processing flow of the first embodiment will be briefly explained below.

[0077] Step 1: The conversation unit analyzes the user's utterances and replies. User utterances include everyday conversations, questions, opinions, etc. The conversation unit converts the user's utterances into text data using speech recognition technology and analyzes the content of the utterances using natural language processing technology. The conversation unit also uses a machine learning model to generate an appropriate response. For example, if a user says, "The weather is nice today," the generation AI replies, "Yes, it's sunny today." If a user says, "I'm hungry," the generation AI can also reply, "Is there anything you'd like to eat?" Furthermore, if a user asks, "What are your plans for tomorrow?" the generation AI can reply, "I have a meeting tomorrow." Step 2: The learning unit detects the user's pronunciation and grammar errors and provides feedback. The learning unit uses speech recognition technology to analyze the user's pronunciation and a grammar analysis algorithm to detect grammatical errors. The learning unit also provides real-time feedback. For example, if the user says, "I went to the store," the generation AI can provide feedback such as, "'goed' is incorrect. The correct word is 'went'." If the user says, "She don't like apples," the generation AI can also provide feedback such as, "'don't' is incorrect. The correct word is 'doesn't'." If the user says, "He is more taller than me," the generation AI can also provide feedback such as, "'more taller' is incorrect. The correct word is 'taller'." Step 3: The feedback unit records the user's conversation and provides detailed feedback. The feedback unit can record the user's conversation and provide detailed feedback later. For example, if the user says, "I am very happy today," the generation AI can provide feedback such as, "Your pronunciation is good, but you should emphasize the pronunciation of 'very' a little more." If the user says, "I think this is a good idea," the generation AI can provide feedback such as, "Your pronunciation is good, but you should practice the pronunciation of 'think' a little more." If the user says, "I want to go to the park," the generation AI can provide feedback such as, "Your pronunciation is good, but you should practice the pronunciation of 'want' a little more."

[0078] (Example 2) An English learning system according to an embodiment of the present invention automatically analyzes a user's utterances, generates appropriate responses from a generation AI, detects pronunciation and grammatical errors, and provides detailed feedback. The English learning system analyzes the user's utterances and generates appropriate responses from a generation AI, allowing the user to enjoy English conversations anytime, anywhere. The English learning system also detects the user's pronunciation and grammatical errors and provides real-time feedback. Furthermore, the English learning system records the user's conversations and provides detailed feedback. For example, when a user says, "The weather is nice today," the generation AI replies, "Yes, it's sunny today." The English learning system then detects the user's pronunciation and grammatical errors and provides real-time feedback. For example, when a user says, "I went to the store," the generation AI provides feedback such as, "'goed' is incorrect. The correct word is 'went.'" The English learning system then records the user's conversations and provides detailed feedback. For example, if a user says, "I am very happy today," the generation AI will provide feedback such as, "Your pronunciation is good, but you could emphasize the pronunciation of 'very' a little more." This allows the English learning system to analyze the user's utterances, detect pronunciation and grammar errors, and provide detailed feedback. This allows the English learning system to effectively support the user's English learning. For example, the user can immediately correct their pronunciation and grammar errors and improve their English conversation skills. In addition, the detailed feedback allows the user to improve their pronunciation and expression.

[0079] The English language learning system according to the embodiment includes a conversation unit, a learning unit, and a feedback unit. The conversation unit analyzes user utterances and provides a response. The user utterances include, but are not limited to, everyday conversations, questions, and opinions. The conversation unit converts the user utterances into text data using, for example, speech recognition technology and analyzes the content of the utterances using natural language processing technology. The conversation unit can also generate appropriate responses using a machine learning model. For example, when the user says, "The weather is nice today," the generation AI can respond with, "Yes, it's sunny today." When the user says, "I'm hungry," the generation AI can respond with, "Is there anything you'd like to eat?" When the user asks, "What are your plans for tomorrow?" the generation AI can respond with, "I have a meeting tomorrow." The learning unit detects the user's pronunciation and grammar errors and provides feedback. For example, the learning unit analyzes the user's pronunciation using speech recognition technology and detects grammar errors using a grammar analysis algorithm. The learning unit can also provide real-time feedback. For example, if a user says, "I went to the store," the generation AI can provide feedback such as, "'goed' is incorrect. The correct answer is 'went'." If a user says, "She don't like apples," the learning unit can provide feedback such as, "'don't' is incorrect. The correct answer is 'doesn't'." If a user says, "He is more taller than me," the generation AI can provide feedback such as, "'more taller' is incorrect. The correct answer is 'taller'." The feedback unit can record a user's conversation and provide detailed feedback later. For example, if a user says, "I am very happy today," the generation AI can provide feedback such as, "Your pronunciation is good, but you could emphasize the pronunciation of 'very' a little more."Furthermore, when a user says, "I think this is a good idea," the feedback unit can cause the generation AI to provide feedback such as, "Your pronunciation is good, but you should practice pronouncing 'think' a little more." When a user says, "I want to go to the park," the feedback unit can cause the generation AI to provide feedback such as, "Your pronunciation is good, but you should practice pronouncing 'want' a little more." This enables the English language learning system according to the embodiment to analyze user utterances, detect pronunciation and grammatical errors, and provide detailed feedback.

[0080] The English learning system further includes a support unit that provides information in English to support the user's daily life. The support unit provides information in English to support the user's daily life. For example, when the user enters a restaurant, the generation AI can ask in English, "What are the recommended menu items at this restaurant?" When the user goes shopping, the support unit can also ask in English, "Where is this item?" When the user gets lost, the support unit can also ask in English, "How do I get to this place?" This allows the user to use English naturally in their daily lives. Some or all of the above-described processing in the support unit may be performed using AI, for example, or may be performed without AI. For example, the support unit can input the user's utterances into the generation AI, which can then generate appropriate English questions.

[0081] The English learning system further includes an analysis unit that analyzes the user's utterances and generates an appropriate response. The analysis unit analyzes the user's utterances and generates an appropriate response. For example, the analysis unit converts the user's utterances into text data using speech recognition technology and analyzes the content of the utterances using natural language processing technology. The analysis unit can also generate an appropriate response using a machine learning model. For example, when the user says, "The weather is nice today," the analysis unit can cause the generation AI to respond, "Yes, it's sunny today." When the user says, "I'm hungry," the analysis unit can cause the generation AI to respond, "Is there anything you'd like to eat?" When the user asks, "What are your plans for tomorrow?" the analysis unit can cause the generation AI to respond, "I have a meeting tomorrow." This makes it possible to analyze the user's utterances and generate an appropriate response. Some or all of the above-described processing in the analysis unit may be performed using, for example, AI, or may be performed without AI. For example, the analysis unit can input the user's utterances into the generation AI, which can then generate an appropriate response.

[0082] The English learning system further includes a protection unit that encrypts or anonymizes data to protect the user's data. The protection unit encrypts or anonymizes data to protect the user's data. The protection unit can encrypt the user's data using, for example, AES encryption technology. The protection unit can also anonymize the user's data using data masking technology. For example, the protection unit encrypts the user's personal information to prevent third parties from accessing it. The protection unit can also anonymize the user's speech data to protect privacy. This makes it possible to protect the user's data. Some or all of the above-mentioned processing in the protection unit may be performed using, for example, AI, or may be performed without using AI. For example, the protection unit can input the user's data to a generation AI, which can then perform appropriate encryption or anonymization.

[0083] The conversation unit can estimate the user's emotions and adjust the tone or content of a response based on the estimated user's emotions. For example, if the user is nervous, the generation AI can respond in a calm tone, providing a sense of security. Alternatively, if the user is having fun, the generation AI can respond in a cheerful tone, livening up the conversation. Alternatively, if the user is tired, the generation AI can respond in a concise and gentle tone, reducing the user's burden. This enables a response that is appropriate for the user's emotions. Emotion estimation is achieved using an emotion estimation function, for example, with an emotion engine or 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 may be performed using, for example, AI, or without AI. For example, the conversation unit can input the user's utterances into the generation AI, which can then generate an appropriate tone and content of a response.

[0084] The conversation unit can analyze the user's interests during a conversation and select a conversation topic based on that. For example, if the user is interested in sports, the generation AI can provide topics related to sports. If the user is talking about travel, the generation AI can provide information about travel destinations and recommended spots. If the user is interested in music, the generation AI can provide topics about the latest music trends and artists. This enables conversations based on the user's interests. Some or all of the above-mentioned processing in the conversation unit can be performed using, or without, AI. For example, the conversation unit can input the user's utterances into the generation AI, which can then select an appropriate conversation topic.

[0085] The conversation unit can refer to the user's past conversation history and generate a customized response. For example, the conversation unit allows the generation AI to provide related topics based on what the user has previously said. The conversation unit can also allow the generation AI to provide new information based on topics in which the user has previously shown interest. The conversation unit can also allow the generation AI to provide additional information or answers based on what the user has previously asked. This makes it possible to provide a customized response based on the user's past conversation history. Some or all of the above-mentioned processing in the conversation unit may be performed using AI, for example, or may be performed without using AI. For example, the conversation unit can input the user's past conversation history into the generation AI, which then generates a customized response.

[0086] The conversation unit can analyze the context of the conversation and switch the conversation at an appropriate time. For example, if the user shows signs of getting bored with the topic, the generation AI can provide a new topic. Furthermore, after the user asks a question, the conversation unit can provide an answer at an appropriate time. Furthermore, if the user indicates that they want to change the topic, the generation AI can smoothly switch the topic. This makes it possible to switch the conversation at an appropriate time according to the context of the conversation. Some or all of the above-mentioned processing in the conversation unit may be performed using AI, for example, or may be performed without using AI. For example, the conversation unit can input the user's utterances into the generation AI, and the generation AI can switch the conversation at an appropriate time.

[0087] The conversation unit can estimate the user's emotions and adjust the conversation speed based on the estimated user's emotions. For example, if the user is in a hurry, the generation AI can speed up the conversation. Alternatively, if the user is relaxed, the generation AI can proceed with the conversation at a slower pace. Alternatively, if the user is tired, the generation AI can provide concise and short responses. This enables the conversation speed to be adjusted according to the user's emotions. The emotion estimation is realized using an emotion estimation function, for example, with 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, AI, or without AI. For example, the conversation unit can input the user's utterances into the generation AI, which can then generate an appropriate conversation speed.

[0088] The conversation unit can analyze the user's gestures and facial expressions during the conversation and adjust the response based on the analysis. For example, if the user smiles, the generation AI can provide a humorous response. If the user looks confused, the generation AI can add an explanation. If the user nods, the generation AI can continue the conversation. This enables responses based on the user's gestures and facial expressions. Some or all of the above-described processing in the conversation unit may be performed using AI, for example, or may be performed without using AI. For example, the conversation unit can input the user's gestures and facial expressions into the generation AI, which can then generate an appropriate response.

[0089] The conversation unit can provide relevant information and suggestions to the user based on the content of the conversation. For example, if the user is talking about traveling, the generation AI can suggest recommended travel destinations. Also, if the user is talking about cooking, the generation AI can provide recipes. Also, if the user is talking about movies, the generation AI can provide information about related movies. This makes it possible to provide relevant information and suggestions based on the content of the conversation. Some or all of the above-mentioned processing in the conversation unit may be performed using AI, for example, or may be performed without using AI. For example, the conversation unit can input the user's utterances into the generation AI, which can then generate appropriate information and suggestions.

[0090] The conversation unit can translate what the user says during the conversation and generate a response in a different language. For example, if the user speaks in English, the generation AI can respond in Japanese. Also, if the user speaks in French, the generation AI can respond in English. Also, if the user speaks in Spanish, the generation AI can respond in German. This makes it possible to translate the user's utterances and respond in other languages. Some or all of the above-mentioned processing in the conversation unit may be performed using AI, for example, or may be performed without using AI. For example, the conversation unit can input the user's utterances into the generation AI, which can then generate an appropriate translation and response.

[0091] The learning unit can estimate the user's emotions and adjust the feedback expression method based on the estimated user's emotions. For example, if the user is nervous, the learning unit can cause the generation AI to provide feedback in a gentle tone. Furthermore, if the user is relaxed, the learning unit can cause the generation AI to provide detailed feedback. Furthermore, if the user is tired, the learning unit can cause the generation AI to provide concise, to-the-point feedback. This enables the feedback expression method to be adjusted according to the user's emotions. The emotion estimation is realized using an emotion estimation function, for example, with an emotion engine or a generation AI. The generation AI can be, for example, 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 learning unit can be performed using, for example, an AI, or can be performed without using an AI. For example, the learning unit can input the user's utterances into the generation AI, which can then generate an appropriate feedback expression method.

[0092] The learning unit can analyze the user's learning progress and provide a study plan. For example, if the user is struggling with a particular grammar point, the generation AI can provide a study plan focusing on that point. Furthermore, if the user is struggling with pronunciation, the generation AI can provide a study plan that emphasizes pronunciation practice. Furthermore, if the user wants to improve their vocabulary, the generation AI can provide a study plan specialized for vocabulary learning. This makes it possible to provide an optimal study plan based on the user's learning progress. Some or all of the above-described processing in the learning unit may be performed using, or without, AI. For example, the learning unit can input the user's learning data into the generation AI, which can then generate an appropriate study plan.

[0093] The learning unit can analyze the user's pronunciation and grammar errors in detail and suggest specific ways to improve them. For example, if the user says, "I went to the store," the generation AI can provide feedback such as, "'goed' is incorrect. The correct word is 'went'." Alternatively, if the user says, "She don't like apples," the generation AI can provide feedback such as, "'don't' is incorrect. The correct word is 'doesn't'." Alternatively, if the user says, "He is more taller than me," the generation AI can provide feedback such as, "'more taller' is incorrect. The correct word is 'taller'." This allows the generation AI to suggest specific ways to improve the user's pronunciation and grammar errors. Some or all of the above-described processing in the learning unit may be performed using, or without, AI. For example, the learning unit can input the user's utterances into the generation AI, which can then generate appropriate ways to improve the pronunciation and grammar.

[0094] The learning unit can refer to the user's learning history and provide individually customized feedback. For example, the learning unit can have the generation AI provide feedback on a grammar item that the user made a mistake on in the past. The learning unit can also have the generation AI provide feedback for review based on content that the user has previously studied. The learning unit can also have the generation AI provide related feedback based on topics that the user has previously shown interest in. This makes it possible to provide customized feedback based on the user's learning history. Some or all of the above-described processing in the learning unit may be performed using, or without, AI. For example, the learning unit can input the user's learning history into the generation AI, which then generates customized feedback.

[0095] The learning unit can estimate the user's emotions and adjust the frequency of feedback based on the estimated user emotions. For example, if the user is nervous, the learning unit causes the generation AI to reduce the frequency of feedback to reduce the burden. Furthermore, if the user is relaxed, the learning unit can cause the generation AI to increase the frequency of feedback to improve the learning effect. Furthermore, if the user is tired, the learning unit can cause the generation AI to adjust the frequency of feedback and provide it at an appropriate time. This enables the frequency of feedback to be adjusted 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 may be a text generation AI (e.g., LLM) or a multimodal generation AI, but is not limited to such examples. Some or all of the above-described processing in the learning unit may be performed using, for example, an AI, or may be performed without using an AI. For example, the learning unit can input the user's utterances into the generation AI, which then generates an appropriate feedback frequency.

[0096] The learning unit can provide different feedback formats (text, audio, video, etc.) depending on the user's learning style. For example, if the user is a visual learner, the generation AI can provide video-format feedback. If the user is an auditory learner, the learning unit can also provide audio-format feedback. If the user is a text-based learner, the learning unit can also provide text-format feedback. This makes it possible to provide feedback formats according to the user's learning style. Some or all of the above-mentioned processing in the learning unit may be performed using AI, for example, or may be performed without using AI. For example, the learning unit can input the user's learning style into the generation AI, which can then generate an appropriate feedback format.

[0097] The learning unit can provide feedback focused on specific skills based on the user's learning goals. For example, if the user wants to improve their pronunciation, the generation AI can provide feedback on pronunciation. Furthermore, if the user wants to strengthen their grammar, the generation AI can provide feedback on grammar. Furthermore, if the user wants to improve their vocabulary, the generation AI can provide feedback on vocabulary. This makes it possible to provide feedback focused on specific skills based on the user's learning goals. Some or all of the above-described processing in the learning unit may be performed using AI, or may be performed without AI. For example, the learning unit can input the user's learning goals into the generation AI, which can then generate appropriate feedback.

[0098] The learning unit can provide optimal feedback depending on the user's learning environment (location, time of day, etc.). For example, if the user is studying in a quiet place, the generation AI can provide detailed feedback. Furthermore, if the user is studying while on the move, the learning unit can provide concise feedback. Furthermore, if the user is studying at night, the generation AI can provide feedback in a relaxed tone. This makes it possible to provide optimal feedback depending on the user's learning environment. Some or all of the above-mentioned processing in the learning unit may be performed using AI, for example, or may be performed without using AI. For example, the learning unit can input the user's learning environment into the generation AI, which can then generate appropriate feedback.

[0099] The feedback unit can estimate the user's emotions and adjust the content of the feedback based on the estimated user's emotions. For example, if the user is nervous, the generation AI can provide feedback in a gentle tone. Furthermore, if the user is relaxed, the feedback unit can provide detailed feedback. Furthermore, if the user is tired, the generation AI can provide concise, to-the-point feedback. This enables the content of the feedback to be adjusted 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, for example, 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 feedback unit can be performed using, for example, an AI, or can be performed without using an AI. For example, the feedback unit can input the user's utterances into the generation AI, which can then generate appropriate feedback content.

[0100] The feedback unit can analyze the user's conversation history in detail and suggest specific improvements. For example, the feedback unit allows the generation AI to provide feedback on grammar items that the user made mistakes on in the past. The feedback unit can also allow the generation AI to provide feedback for review based on content the user has previously studied. The feedback unit can also allow the generation AI to provide related feedback based on topics the user has previously shown interest in. This makes it possible to suggest specific improvements based on the user's conversation history. Some or all of the above-mentioned processing in the feedback unit may be performed using, or without, AI. For example, the feedback unit can input the user's conversation history into the generation AI, which then generates appropriate improvements.

[0101] The feedback unit can customize the content of the feedback to match the user's learning goals. For example, if the user wants to improve their pronunciation, the generation AI can provide feedback on their pronunciation. Furthermore, if the user wants to strengthen their grammar, the feedback unit can provide feedback on their grammar. Furthermore, if the user wants to improve their vocabulary, the feedback unit can provide feedback on their vocabulary. This makes it possible to provide customized feedback based on the user's learning goals. Some or all of the above-described processing in the feedback unit may be performed using, or without, AI. For example, the feedback unit can input the user's learning goals into the generation AI, which can then generate appropriate feedback.

[0102] The feedback unit can adjust the timing of feedback to match the user's learning rhythm. For example, if the user is concentrating, the generation AI can increase the frequency of feedback. Also, if the user is tired, the feedback unit can reduce the frequency of feedback. Also, if the user is taking a break, the feedback unit can pause feedback and provide it when the user resumes. This makes it possible to adjust the timing of feedback according to the user's learning rhythm. Some or all of the above-mentioned processing in the feedback unit may be performed using AI, for example, or may be performed without using AI. For example, the feedback unit can input the user's learning rhythm into the generation AI, which can then generate appropriate feedback timing.

[0103] The feedback unit can estimate the user's emotions and adjust the form of the feedback based on the estimated user's emotions. For example, if the user is nervous, the generation AI can provide feedback in a gentle tone. Furthermore, if the user is relaxed, the feedback unit can provide detailed feedback. Furthermore, if the user is tired, the generation AI can provide concise, to-the-point feedback. This enables the adjustment of the form of feedback 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, for example, 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 feedback unit can be performed using, for example, an AI, or can be performed without using an AI. For example, the feedback unit can input the user's utterances into the generation AI, which can then generate an appropriate form of feedback.

[0104] The feedback unit can adjust the content of the feedback based on the user's interests. For example, if the user is interested in sports, the generation AI can provide feedback related to sports. If the user is talking about travel, the feedback unit can also provide information about travel destinations and recommended spots. If the user is interested in music, the feedback unit can also provide topics about the latest music trends and artists. This makes it possible to adjust the content of the feedback based on the user's interests. Some or all of the above-described processing in the feedback unit may be performed using AI, for example, or may be performed without using AI. For example, the feedback unit can input the user's interests into the generation AI, which can then generate appropriate feedback content.

[0105] The feedback unit can link the content of the feedback with other learning resources (books, videos, etc.). For example, if the user is struggling with a particular grammar point, the generation AI can suggest books or videos related to that point. Also, if the user is struggling with pronunciation, the feedback unit can suggest videos that are useful for pronunciation practice. Also, if the user wants to improve their vocabulary, the feedback unit can suggest books that are useful for vocabulary learning. This makes it possible to provide feedback linked to other learning resources. Some or all of the above-mentioned processing in the feedback unit may be performed, for example, using AI, or may be performed without using AI. For example, the feedback unit can input the user's learning data into the generation AI, which can then suggest appropriate learning resources.

[0106] The feedback unit can provide feedback content in stages according to the user's learning progress. For example, if the user is at a beginner's level, the generation AI can provide basic feedback. Furthermore, if the user is at an intermediate level, the feedback unit can also provide intermediate-level feedback. Furthermore, if the user is at an advanced level, the generation AI can also provide advanced feedback. This makes it possible to provide feedback in stages according to the user's learning progress. Some or all of the above-mentioned processing in the feedback unit may be performed using AI, for example, or may be performed without using AI. For example, the feedback unit can input the user's learning progress into the generation AI, which can then generate appropriate feedback.

[0107] The support unit can estimate the user's emotions and adjust the support content based on the estimated user's emotions. For example, if the user is nervous, the generation AI can provide support in a gentle tone. Furthermore, if the user is relaxed, the generation AI can provide detailed support. Furthermore, if the user is tired, the generation AI can provide concise, to-the-point support. This enables the support content to be adjusted 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, for example, 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 support unit may be performed using, for example, an AI, or may be performed without using an AI. For example, the support unit can input the user's utterances into the generation AI, which can then generate appropriate support content.

[0108] The support unit can analyze the user's current situation and environment in real time and provide optimal support. For example, if the user is at a restaurant, the generation AI can provide a translation of the menu. If the user is at an airport, the generation AI can also provide support for checking flight information. If the user is at a hotel, the generation AI can also provide support for check-in procedures. This makes it possible to provide optimal support based on the user's current situation and environment. Some or all of the above-mentioned processing in the support unit may be performed using AI, for example, or may be performed without using AI. For example, the support unit can input the user's current situation and environment into the generation AI, which can then generate appropriate support.

[0109] The assistance unit can refer to the user's past assistance history and provide individually customized assistance. For example, the assistance unit allows the generation AI to provide relevant assistance based on assistance content that the user has used in the past. The assistance unit can also allow the generation AI to provide relevant assistance based on topics in which the user has shown interest in the past. The assistance unit can also allow the generation AI to provide relevant assistance based on places the user has visited in the past. This makes it possible to provide customized assistance based on the user's past assistance history. Some or all of the above-described processing in the assistance unit may be performed using AI, for example, or may be performed without using AI. For example, the assistance unit can input the user's past assistance history into the generation AI, which can then generate appropriate assistance.

[0110] The support unit can adjust the support content to match the user's learning goals. For example, if the user wants to improve their pronunciation, the generation AI can provide support regarding pronunciation. Furthermore, if the user wants to strengthen their grammar, the support unit can provide support regarding grammar. Furthermore, if the user wants to improve their vocabulary, the support unit can provide support regarding vocabulary. This makes it possible to adjust the support content based on the user's learning goals. Some or all of the above-mentioned processing in the support unit may be performed using AI, for example, or may be performed without using AI. For example, the support unit can input the user's learning goals into the generation AI, which can then generate appropriate support.

[0111] The support unit can estimate the user's emotions and adjust the frequency of support based on the estimated user emotions. For example, if the user is nervous, the generation AI can reduce the frequency of support to reduce the burden. Furthermore, if the user is relaxed, the support unit can increase the frequency of support to improve learning effectiveness. Furthermore, if the user is tired, the generation AI can adjust the frequency of support and provide it at an appropriate time. This enables adjustment of the frequency of support according to the user's emotions. Emotion estimation is realized using an emotion estimation function, for example, an emotion engine or a generation AI. The generation AI can be a text generation AI (e.g., LLM) or a multimodal generation AI, but is not limited to such examples. Some or all of the above-described processing in the support unit may be performed using, for example, an AI, or may be performed without using an AI. For example, the support unit can input the user's utterances into the generation AI, which can then generate an appropriate frequency of support.

[0112] The support unit can adjust the support content based on the user's interests and concerns. For example, if the user is interested in sports, the generation AI can provide support related to sports. Furthermore, if the user is talking about travel, the generation AI can provide information about travel destinations and recommended spots. Furthermore, if the user is interested in music, the generation AI can provide topics about the latest music trends and artists. This makes it possible to adjust the support content based on the user's interests and concerns. Some or all of the above-mentioned processing in the support unit may be performed using AI, for example, or may be performed without using AI. For example, the support unit can input the user's interests and concerns into the generation AI, which can then generate appropriate support content.

[0113] The support unit can link the support content with other learning resources (books, videos, etc.). For example, if the user is struggling with a particular grammar point, the generation AI can suggest books or videos related to that point. Also, if the user is struggling with pronunciation, the generation AI can suggest videos that are useful for pronunciation practice. Also, if the user wants to improve their vocabulary, the generation AI can suggest books that are useful for vocabulary learning. This makes it possible to provide support content that is linked with other learning resources. Some or all of the above-mentioned processing in the support unit may be performed, for example, using AI, or may be performed without using AI. For example, the support unit can input the user's learning data into the generation AI, which can then suggest appropriate learning resources.

[0114] The support unit can provide support content in stages according to the user's learning progress. For example, if the user is at a beginner's level, the generation AI can provide basic support. Furthermore, if the user is at an intermediate level, the support unit can also provide intermediate-level support. Furthermore, if the user is at an advanced level, the generation AI can also provide advanced support. This makes it possible to provide support content in stages according to the user's learning progress. Some or all of the above-mentioned processing in the support unit may be performed using AI, for example, or may be performed without using AI. For example, the support unit can input the user's learning progress into the generation AI, which can then generate appropriate support.

[0115] The analysis unit can estimate the user's emotions and adjust the display method of the analysis results based on the estimated user emotions. For example, if the user is nervous, the generation AI can display the analysis results in a gentle tone. Furthermore, if the user is relaxed, the analysis unit can display detailed analysis results. Furthermore, if the user is tired, the generation AI can display concise, to-the-point analysis results. This makes it possible to adjust the display method of the analysis results according to the user's emotions. Emotion estimation is achieved using an emotion estimation function, for example, an emotion engine or a generation AI. The generation AI can be 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 analysis unit can be performed using, for example, an AI, or can be performed without using an AI. For example, the analysis unit can input the user's utterances into the generation AI, which can then generate an appropriate display method for the analysis results.

[0116] The analysis unit can analyze the user's utterances in detail and suggest specific improvements. For example, if the user says, "I went to the store," the generation AI can provide feedback such as, "'goed' is incorrect. The correct word is 'went'." Alternatively, if the user says, "She doesn't like apples," the generation AI can provide feedback such as, "'don't' is incorrect. The correct word is 'doesn't'." Alternatively, if the user says, "He is more taller than me," the generation AI can provide feedback such as, "'more taller' is incorrect. The correct word is 'taller'." This allows specific improvements to be suggested based on the user's utterances. Some or all of the above-described processing in the analysis unit may be performed using, or without, AI. For example, the analysis unit can input the user's utterances into the generation AI, which can then generate appropriate improvements.

[0117] The analysis unit can customize the analysis results to suit the user's learning goals. For example, if the user wants to improve their pronunciation, the generation AI can provide analysis results related to pronunciation. Furthermore, if the user wants to strengthen their grammar, the analysis unit can provide analysis results related to grammar. Furthermore, if the user wants to improve their vocabulary, the analysis unit can provide analysis results related to vocabulary. This makes it possible to provide customized analysis results based on the user's learning goals. Some or all of the above-mentioned processing in the analysis unit may be performed using, or without, AI. For example, the analysis unit can input the user's learning goals into the generation AI, which can then generate appropriate analysis results.

[0118] The analysis unit can adjust the timing of the analysis results to match the user's learning rhythm. For example, if the user is concentrating, the analysis unit causes the generation AI to increase the frequency of the analysis results. Also, if the user is tired, the analysis unit can cause the generation AI to decrease the frequency of the analysis results. Also, if the user is taking a break, the analysis unit can cause the generation AI to pause the analysis results and provide them when the user resumes. This makes it possible to adjust the timing of the analysis results according to the user's learning rhythm. Some or all of the above-mentioned processing in the analysis unit may be performed using, or without, AI. For example, the analysis unit can input the user's learning rhythm into the generation AI, and the generation AI can generate appropriate timing for the analysis results.

[0119] The analysis unit can estimate the user's emotions and adjust the format of the analysis results based on the estimated user emotions. For example, if the user is nervous, the generation AI can display the analysis results in a gentle tone. Furthermore, if the user is relaxed, the analysis unit can display detailed analysis results. Furthermore, if the user is tired, the generation AI can display concise, to-the-point analysis results. This enables the format of the analysis results to be adjusted according to the user's emotions. Emotion estimation is achieved using an emotion estimation function, for example, an emotion engine or a generation AI. The generation AI can be, but is not limited to, a text generation AI (e.g., LLM) or a multimodal generation AI. Some or all of the above-described processing in the analysis unit can be performed using, for example, an AI, or can be performed without using an AI. For example, the analysis unit can input the user's utterances into the generation AI, which can then generate an appropriate format for the analysis results.

[0120] The analysis unit can adjust the analysis results based on the user's interests. For example, if the user is interested in sports, the generation AI can provide analysis results related to sports. If the user is talking about travel, the analysis unit can also provide information about travel destinations and recommended spots. If the user is interested in music, the analysis unit can also provide topics about the latest music trends and artists. This makes it possible to adjust the analysis results based on the user's interests. Some or all of the above-mentioned processing in the analysis unit may be performed using AI, for example, or may be performed without using AI. For example, the analysis unit can input the user's interests into the generation AI, which can then generate appropriate analysis results.

[0121] The analysis unit can link the analysis results with other learning resources (books, videos, etc.). For example, if the user is struggling with a particular grammar point, the generation AI can suggest books or videos related to that point. Also, if the user is struggling with pronunciation, the analysis unit can suggest videos that are useful for pronunciation practice. Also, if the user wants to improve their vocabulary, the generation AI can suggest books that are useful for vocabulary learning. This makes it possible to provide analysis results that are linked with other learning resources. Some or all of the above-mentioned processing in the analysis unit may be performed, for example, using AI, or may be performed without using AI. For example, the analysis unit can input the user's learning data into the generation AI, which can then suggest appropriate learning resources.

[0122] The analysis unit can provide analysis results in stages according to the user's learning progress. For example, if the user is at a beginner's level, the generation AI can provide basic analysis results. Furthermore, if the user is at an intermediate level, the analysis unit can also provide intermediate-level analysis results. Furthermore, if the user is at an advanced level, the generation AI can also provide advanced analysis results. This makes it possible to provide analysis results in stages according to the user's learning progress. Some or all of the above-mentioned processing in the analysis unit may be performed using AI, for example, or may be performed without using AI. For example, the analysis unit can input the user's learning progress into the generation AI, and the generation AI can generate appropriate analysis results.

[0123] The protection unit can estimate the user's emotions and adjust the data protection method based on the estimated user emotions. For example, if the user is nervous, the generation AI can simplify the data protection explanation to provide a sense of security. Furthermore, if the user is relaxed, the generation AI can provide a detailed explanation of data protection. Furthermore, if the user is tired, the generation AI can provide a concise and to-the-point explanation of data protection. This enables the data protection method to be adjusted 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, for example, 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 protection unit may be performed using, for example, an AI, or may be performed without using an AI. For example, the protection unit can input the user's utterances into the generation AI, which can then generate an appropriate data protection method.

[0124] The protection unit can analyze the user's data in detail and select an encryption method. For example, if the user's data has high confidentiality, the generation AI can select a strong encryption method. If the user's data has medium confidentiality, the protection unit can also select a moderate encryption method. If the user's data has low confidentiality, the protection unit can also select a basic encryption method. This makes it possible to select the optimal encryption method based on the user's data. Some or all of the above-mentioned processing in the protection unit can be performed using AI, for example, or can be performed without using AI. For example, the protection unit can input the user's data into the generation AI, and the generation AI can generate an appropriate encryption method.

[0125] The protection unit can customize the content of data protection to match the user's privacy settings. For example, if the user selects a high privacy setting, the generation AI can provide strict data protection. Alternatively, if the user selects a medium privacy setting, the protection unit can provide moderate data protection. Alternatively, if the user selects a low privacy setting, the generation AI can provide basic data protection. This makes it possible to provide customized data protection based on the user's privacy settings. Some or all of the above-mentioned processing in the protection unit may be performed using AI, for example, or may be performed without using AI. For example, the protection unit can input the user's privacy settings into the generation AI, which can then generate appropriate data protection content.

[0126] The protection unit can adjust the timing of data protection according to the user's usage status. For example, if the user frequently uses data, the generation AI can provide data protection in real time. Alternatively, if the user occasionally uses data, the protection unit can cause the generation AI to provide data protection periodically. Alternatively, if the user rarely uses data, the protection unit can cause the generation AI to provide data protection as needed. This makes it possible to adjust the timing of data protection according to the user's usage status. Some or all of the above-mentioned processing in the protection unit may be performed using AI, for example, or may be performed without using AI. For example, the protection unit can input the user's usage status to the generation AI, which can then generate an appropriate timing for data protection.

[0127] The protection unit can estimate the user's emotions and adjust the frequency of data protection based on the estimated user emotions. For example, if the user is nervous, the generation AI can increase the frequency of data protection to provide a sense of security. Furthermore, if the user is relaxed, the protection unit can reduce the frequency of data protection to reduce the burden. Furthermore, if the user is tired, the protection unit can adjust the frequency of data protection and provide it at an appropriate time. This enables the frequency of data protection to be adjusted according to the user's emotions. Emotion estimation is achieved using an emotion estimation function, for example, an emotion engine or a generation AI. The generation AI can be, for example, 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 protection unit may be performed using, for example, AI, or without AI. For example, the protection unit can input the user's utterances into the generation AI, which can then generate an appropriate frequency of data protection.

[0128] The protection unit can adjust the content of data protection based on the user's interests and concerns. For example, if the user is interested in high security, the generation AI can provide strong data protection. Alternatively, if the user is interested in medium security, the protection unit can provide moderate data protection. Alternatively, if the user is interested in low security, the generation AI can provide basic data protection. This makes it possible to adjust the content of data protection based on the user's interests and concerns. Some or all of the above-mentioned processing in the protection unit may be performed using AI, for example, or may be performed without using AI. For example, the protection unit can input the user's interests and concerns into the generation AI, which can then generate appropriate data protection content.

[0129] The protection unit can link the data protection content with other security resources (firewalls, antivirus software, etc.). For example, the generation AI of the protection unit can link with a firewall to strengthen data protection. The protection unit can also link with antivirus software to strengthen data protection. The protection unit can also link with other security resources to provide comprehensive data protection. This makes it possible to provide data protection in cooperation with other security resources. Some or all of the above-mentioned processing in the protection unit may be performed using AI, for example, or may be performed without using AI. For example, the protection unit can input other security resources into the generation AI, which can then generate appropriate data protection content.

[0130] The protection unit can provide data protection content in stages according to the user's usage status. For example, if the user frequently uses data, the generation AI can provide data protection in real time. Alternatively, if the user occasionally uses data, the protection unit can provide data protection periodically. Alternatively, if the user rarely uses data, the protection unit can provide data protection as needed. This makes it possible to provide data protection in stages according to the user's usage status. Some or all of the above-mentioned processing in the protection unit may be performed using AI, for example, or may be performed without using AI. For example, the protection unit can input the user's usage status to the generation AI, which can then generate appropriate data protection content. === Hard Collateral 1-1 === For example, each of the multiple elements including the conversation unit, learning unit, feedback unit, support unit, analysis unit, and protection unit is realized in at least one of the smart device 14 and the data processing device 12. For example, the conversation unit analyzes the user's utterances using the processor 46 and control unit 46A of the smart device 14, and the generation AI provides an appropriate response. The learning unit detects the user's pronunciation and grammar errors using the specific processing unit 290 of the data processing device 12 and provides feedback in real time. The feedback unit records the user's conversations in the storage 50 of the smart device 14 and provides detailed feedback. The support unit provides information in English to support the user's daily life using the processor 46 and control unit 46A of the smart device 14. The analysis unit analyzes the user's utterances using the specific processing unit 290 of the data processing device 12 and generates an appropriate response. The protection unit encrypts or anonymizes the user's data using the specific processing unit 290 of the data processing device 12. === Hard Collateral 1-2 === For example, each of the multiple elements including the conversation unit, learning unit, feedback unit, support unit, analysis unit, and protection unit is realized in at least one of the smart glasses 214 and the data processing device 12. For example, the conversation unit analyzes the user's utterances using the processor 46 and control unit 46A of the smart glasses 214, and the generation AI provides an appropriate response. The learning unit detects the user's pronunciation and grammar errors using the specific processing unit 290 of the data processing device 12 and provides feedback in real time. The feedback unit records the user's conversation in the storage 50 of the smart glasses 214 and provides detailed feedback. The support unit provides information in English to support the user's daily life using the processor 46 and control unit 46A of the smart glasses 214. The analysis unit analyzes the user's utterances using the specific processing unit 290 of the data processing device 12 and generates an appropriate response. The protection unit encrypts or anonymizes the user's data using the specific processing unit 290 of the data processing device 12. === Hard Collateral 1-3 === For example, each of the multiple elements including the conversation unit, learning unit, feedback unit, support unit, analysis unit, and protection unit is realized in at least one of the headset-type terminal 314 and the data processing device 12. For example, the conversation unit analyzes the user's utterances using the processor 46 and control unit 46A of the headset-type terminal 314, and the generation AI provides an appropriate response. The learning unit detects the user's pronunciation and grammar errors using the specific processing unit 290 of the data processing device 12 and provides feedback in real time. The feedback unit records the user's conversations in the storage 50 of the headset-type terminal 314 and provides detailed feedback. The support unit provides information in English to support the user's daily life using the processor 46 and control unit 46A of the headset-type terminal 314. The analysis unit analyzes the user's utterances using the specific processing unit 290 of the data processing device 12 and generates an appropriate response. The protection unit encrypts or anonymizes the user's data using the specific processing unit 290 of the data processing device 12. === Hard Collateral 1-4 === For example, each of the multiple elements including the conversation unit, learning unit, feedback unit, support unit, analysis unit, and protection unit is realized by at least one of the robot 414 and the data processing device 12. For example, the conversation unit analyzes the user's utterances using the processor 46 and control unit 46A of the robot 414, and the generation AI provides an appropriate response. The learning unit detects the user's pronunciation and grammar errors using the specific processing unit 290 of the data processing device 12 and provides feedback in real time. The feedback unit records the user's conversations in the storage 50 of the robot 414 and provides detailed feedback. The support unit provides information in English to support the user's daily life using the processor 46 and control unit 46A of the robot 414. The analysis unit analyzes the user's utterances using the specific processing unit 290 of the data processing device 12 and generates an appropriate response. The protection unit encrypts or anonymizes the user's data using the specific processing unit 290 of the data processing device 12.

[0131] The system according to the embodiment is not limited to the above-described example, and various modifications are possible, for example, as follows.

[0132] In addition to analyzing user utterances, English learning systems can also provide customized learning plans based on the user's learning style. For example, visual learners can receive feedback using visual aids and infographics. Auditory learners can receive audio feedback and podcast-style learning materials. Furthermore, users who prefer hands-on learning can progress through interactive simulations and role-playing. This makes it possible to provide the optimal learning experience based on the user's learning style.

[0133] The English learning system can estimate the user's emotions and adjust the learning progress based on the estimated emotions. For example, if the user is feeling stressed, the system can provide light topics and easy tasks to help them relax. If the user is highly motivated, the system can provide challenging tasks and new topics. Furthermore, if the user is tired, the system can slow down the learning pace and encourage them to take a break. This allows for flexible learning progress according to the user's emotions.

[0134] The English learning system can not only analyze a user's utterances but also provide feedback that takes into account the background and context of the user's utterances. For example, if a user is practicing business English conversation, the system can provide feedback focusing on business vocabulary and formal expressions. If a user is practicing travel conversation, the system can provide feedback that takes into account travel-related phrases and cultural background. Furthermore, if a user is practicing everyday conversation, the system can provide feedback on casual expressions and slang. This allows for specific feedback tailored to the user's learning goals.

[0135] The English learning system not only analyzes the user's utterances, but also analyzes the frequency and patterns of the user's utterances to visualize learning progress. For example, if the user frequently makes mistakes on a particular grammar point, the system can provide additional practice questions on that point. Also, if the user struggles with a particular pronunciation, the system can provide special pronunciation practice sessions. Furthermore, if the user shows interest in a particular topic, the system can provide learning materials related to that topic. This allows for a personalized learning plan based on the user's learning progress.

[0136] The English learning system can estimate a user's emotions and adjust learning feedback based on the estimated emotions. For example, if a user is confident, the system can emphasize positive feedback and encourage further challenges. If a user is anxious, the system can provide feedback in a gentle tone to reassure the user. Furthermore, if a user is excited, the system can harness that energy and suggest interactive learning activities. This allows the system to provide appropriate feedback according to the user's emotions.

[0137] In addition to analyzing user utterances, the English learning system can provide personalized study reminders based on the user's learning history. For example, it can send reminders to periodically review what the user has learned in the past. If the user has set a specific goal, it can track the user's progress toward that goal and provide reminders based on the level of achievement. Furthermore, if the user has stopped studying, the system can send reminders to encourage them to resume. This can support the user's study habits and encourage continuous learning.

[0138] An English learning system can provide a function to estimate a user's emotions and increase their motivation to learn based on the estimated emotions. For example, if a user is losing motivation to learn, the system can restore their motivation by sending encouraging messages or sharing successful experiences. If a user is highly motivated to learn, the system can maintain their motivation by providing further challenges and rewards. Furthermore, if a user feels anxious about learning, the system can provide a relaxing environment and a sense of security. This makes it possible to manage motivation according to the user's emotions.

[0139] The English learning system not only analyzes the user's speech, but also the tone and rhythm of the user's speech and can provide feedback to help improve pronunciation. For example, if the user uses the wrong accent for a particular word, the system can provide feedback indicating the correct accent for that word. Also, if the user speaks too fast, the system can suggest an appropriate speaking speed. Furthermore, if the user uses the wrong rhythm, the system can suggest ways to practice rhythm. This makes it possible to comprehensively improve the user's pronunciation skills.

[0140] The English learning system can estimate the user's emotions and adjust the learning pace based on the estimated emotions. For example, if the user is in a hurry, the system can speed up the learning pace to provide effective learning in a short time. If the user is relaxed, the system can proceed with the learning at a slower pace to promote deep understanding. Furthermore, if the user is tired, the system can provide a concise and short learning session to reduce the burden. This allows for flexible learning progress according to the user's emotions.

[0141] The English language learning system can not only analyze a user's utterances, but also provide relevant cultural background and knowledge based on the content of the user's utterances. For example, if a user uses a particular English expression, the system can explain the expression's cultural background and historical meaning. Also, if a user is talking about a specific topic, the system can provide cultural information and facts related to that topic. Furthermore, the system can provide information about manners and customs that are useful when users communicate with people from different cultures. This allows users to deepen not only their language skills but also their cultural understanding.

[0142] The processing flow of the second embodiment will be briefly explained below.

[0143] Step 1: The conversation unit analyzes the user's utterances and replies. User utterances include everyday conversations, questions, opinions, etc. The conversation unit converts the user's utterances into text data using speech recognition technology and analyzes the content of the utterances using natural language processing technology. The conversation unit also uses a machine learning model to generate an appropriate response. For example, if a user says, "The weather is nice today," the generation AI replies, "Yes, it's sunny today." If a user says, "I'm hungry," the generation AI can also reply, "Is there anything you'd like to eat?" Furthermore, if a user asks, "What are your plans for tomorrow?" the generation AI can reply, "I have a meeting tomorrow." Step 2: The learning unit detects the user's pronunciation and grammar errors and provides feedback. The learning unit uses speech recognition technology to analyze the user's pronunciation and a grammar analysis algorithm to detect grammatical errors. The learning unit also provides real-time feedback. For example, if the user says, "I went to the store," the generation AI can provide feedback such as, "'goed' is incorrect. The correct word is 'went'." If the user says, "She don't like apples," the generation AI can also provide feedback such as, "'don't' is incorrect. The correct word is 'doesn't'." If the user says, "He is more taller than me," the generation AI can also provide feedback such as, "'more taller' is incorrect. The correct word is 'taller'." Step 3: The feedback unit records the user's conversation and provides detailed feedback. The feedback unit can record the user's conversation and provide detailed feedback later. For example, if the user says, "I am very happy today," the generation AI can provide feedback such as, "Your pronunciation is good, but you should emphasize the pronunciation of 'very' a little more." If the user says, "I think this is a good idea," the generation AI can provide feedback such as, "Your pronunciation is good, but you should practice the pronunciation of 'think' a little more." If the user says, "I want to go to the park," the generation AI can provide feedback such as, "Your pronunciation is good, but you should practice the pronunciation of 'want' a little more."

[0144] 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.

[0145] 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.

[0146] 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.

[0147] The correspondence between each part and the device or control part is not limited to the above example, and various modifications are possible.

[0148] [Second embodiment] FIG. 3 shows an example of the configuration of a data processing system 210 according to the second embodiment.

[0149] 3, the data processing system 210 includes a data processing device 12 and smart glasses 214. An example of the data processing device 12 is a server.

[0150] 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.

[0151] 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.

[0152] 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.

[0153] 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).

[0154] 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.

[0155] 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.

[0156] 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.

[0157] 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.

[0158] 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.

[0159] 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.

[0160] 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.

[0161] 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.

[0162] 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.

[0163] The correspondence between each part and the device or control part is not limited to the above example, and various modifications are possible.

[0164] [Third embodiment] FIG. 5 shows an example of the configuration of a data processing system 310 according to the third embodiment.

[0165] 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.

[0166] 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.

[0167] 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.

[0168] 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.

[0169] 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).

[0170] 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.

[0171] Fig. 6 shows an example of the main functions of the data processing device 12 and the headset 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.

[0172] 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.

[0173] 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.

[0174] 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.

[0175] 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.

[0176] 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.

[0177] 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.

[0178] 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.

[0179] The correspondence between each part and the device or control part is not limited to the above example, and various modifications are possible.

[0180] [Fourth embodiment] FIG. 7 shows an example of the configuration of a data processing system 410 according to the fourth embodiment.

[0181] 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.

[0182] 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.

[0183] 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.

[0184] 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.

[0185] 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).

[0186] 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.

[0187] 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.

[0188] 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.

[0189] 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.

[0190] 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.

[0191] 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.

[0192] 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.

[0193] 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.

[0194] 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.

[0195] 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.

[0196] The correspondence between each part and the device or control part is not limited to the above example, and various modifications are possible.

[0197] 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.

[0198] 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.

[0199] 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.

[0200] 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).

[0201] Human emotions are based on various balances, such as posture and blood sugar levels. When these balances deviate from the ideal, a state of discomfort is expressed, and when they approach the ideal, a state of pleasure is expressed. Emotions can also be created for robots, cars, and motorcycles, based on various balances, such as posture and remaining battery life. When these balances deviate from the ideal, a state of discomfort is expressed, and when they approach the ideal, a state of pleasure is expressed. An emotion map can be generated, for example, based on Dr. Mitsuyoshi's emotion map (Research on speech emotion recognition and brain physiological signal analysis systems for emotions, Tokushima University, doctoral dissertation: https: / / ci.nii.ac.jp / naid / 500000375379). The left half of the emotion map lists emotions belonging to the area called "reaction," where sensation is dominant. The right half of the emotion map lists emotions belonging to the area called "situation," where situational awareness is dominant.

[0202] 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."

[0203] 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.

[0204] 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.

[0205] 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.

[0206] 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.

[0207] 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.

[0208] 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.

[0209] 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.

[0210] 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.

[0211] 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.

[0212] 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.

[0213] The above-described description and illustrations are a detailed explanation of the parts related to the technology of the present disclosure and are merely an example of the technology of the present disclosure. For example, the above description of the configuration, functions, actions, and effects is an explanation of an example of the configuration, functions, actions, and effects of the parts related to the technology of the present disclosure. Therefore, it goes without saying that unnecessary parts may be deleted, new elements may be added, or replacements may be made to the above-described description and illustrations within the scope of the gist of the technology of the present disclosure. Furthermore, in order to avoid confusion and to facilitate understanding of the parts related to the technology of the present disclosure, the above-described description and illustrations omit explanations of common technical knowledge that do not require particular explanation to enable the implementation of the technology of the present disclosure.

[0214] 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.

[0215] [Explanation of symbols]

[0216] 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 conversation part that analyzes the user's comments and responds; a learning unit that detects the user's pronunciation and grammar errors and provides feedback; a feedback unit that records the user's conversation and provides detailed feedback; Equipped with A system characterized by:

2. To support users in their daily lives, the system has a support section that provides information in English.

2. The system of claim 1.

3. Equipped with an analysis unit that analyzes user comments and generates appropriate responses 2. The system of claim 1.

4. To protect user data, a protection unit is provided that encrypts or anonymizes data.

2. The system of claim 1.

5. The conversation unit is Inferring a user's emotions and adjusting the tone or content of a response based on the inferred user emotions 2. The system of claim 1.

6. The conversation unit is Analyzing the user's interests during a conversation and selecting the topic of the conversation based on that 2. The system of claim 1.

7. The conversation unit is Referencing the user's past conversation history to generate customized responses 2. The system of claim 1.

8. The conversation unit is Analyze the context of the conversation and switch conversations at the right time 2. The system of claim 1.

9. The conversation unit is Estimate the user's emotions and adjust the pace of the conversation based on the estimated user emotions.

2. The system of claim 1.

Images