system

Abstract

The system according to this embodiment aims to enable users to efficiently learn multiple languages ​​without embarrassment or time management issues. [Solution] The system according to the embodiment comprises a reception unit, a generation unit, a speech recognition unit, and a feedback unit. The reception unit receives the user's specification of the language and field they wish to learn. The generation unit generates a conversation scenario based on the information received by the reception unit. The speech recognition unit converts the user's speech into text. The feedback unit analyzes the text converted by the speech recognition unit and generates feedback and questions.

Description

Technical Field

[0004] ,

[0006] , , ,

[0005] , , , ,

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

Background Art

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

Prior Art Documents

Patent Documents

[0003]

Patent Document 1

Summary of the Invention

Problems to be Solved by the Invention

[0004] In the conventional technology, there is a problem that in an online English conversation classroom, shyness and time adjustment with the instructor are required, making efficient learning difficult.

[0005] The system according to the embodiment aims to enable a user to efficiently learn multiple languages without the problems of shyness and time adjustment.

Means for Solving the Problems

[0006] The system according to this embodiment comprises a reception unit, a generation unit, a speech recognition unit, and a feedback unit. The reception unit receives the user's specification of the language and field they wish to learn. The generation unit generates a conversation scenario based on the information received by the reception unit. The speech recognition unit converts the user's speech into text. The feedback unit analyzes the text converted by the speech recognition unit and generates feedback and questions. [Effects of the Invention]

[0007] The system according to this embodiment allows users to efficiently learn multiple languages ​​without embarrassment or time management issues. [Brief explanation of the drawing]

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

[0028] (Example of form 1) The multilingual conversation learning system according to an embodiment of the present invention is an online service that utilizes generative AI to provide multilingual conversation learning tailored to the individual's level and field. In this multilingual conversation learning system, the user specifies the language and field they wish to learn, the generative AI generates an appropriate conversation scenario, the user engages in conversation using speech recognition technology, and the content is converted into text. The generative AI analyzes the converted text and generates appropriate feedback and questions. This allows the user to learn multiple languages ​​efficiently and at their own pace without feeling embarrassed. For example, the user specifies the language and field they wish to learn. For example, if the user wants to learn business conversation in English, they specify "English" and "Business." This information is input into the generative AI. Next, the generative AI generates an appropriate conversation scenario based on the user's specifications. The generative AI creates a conversation scenario based on the specified language and field. For example, in the case of business conversation, a meeting scenario or a presentation scenario is generated. Based on the generated scenario, the user engages in conversation using speech recognition technology. What the user says is converted into text in real time. For example, if the user says, "I want to talk about the progress of the meeting," that content is converted into text. The generative AI analyzes the text that has been converted and generates appropriate feedback and questions. For example, if a user says, "I want to talk about the progress of the meeting," the generative AI will generate a question such as, "Specifically, what kind of progress are you thinking of?" This allows the user to continue the conversation. This mechanism allows users to learn multiple languages ​​efficiently and on a flexible schedule without feeling embarrassed. For example, even if a user wants to learn in 20 minutes of free time, the generative AI will generate an appropriate scenario, enabling effective learning in a short amount of time. Also, because the conversation is with the generative AI, the user can enjoy the conversation without feeling self-conscious. Furthermore, the generative AI supports multiple languages, and learning is possible in various languages ​​such as English, French, German, Italian, Chinese, and Japanese. This allows users to freely select and learn languages ​​according to their interests and needs.This allows the multilingual conversation learning system to efficiently learn multiple languages ​​by generating conversation scenarios based on user specifications and providing speech recognition and feedback.

[0029] The multilingual conversation learning system according to this embodiment comprises a reception unit, a generation unit, a speech recognition unit, and a feedback unit. The reception unit receives the user's specification of the language and field they wish to learn. For example, if a user wants to learn business conversation in English, the reception unit can receive specifications such as "English" and "business." The reception unit, for example, stores the language and field specified by the user in a database and passes it to the generation unit. The generation unit generates conversation scenarios based on the specified language and field. The generation unit generates conversation scenarios based on the specified language and field, for example, using a generation AI. For example, in the case of business conversations, the generation unit can generate meeting scenarios or presentation scenarios. The generation unit generates appropriate conversation scenarios based on the user's specifications using a generation AI. The speech recognition unit converts the user's speech into text. The speech recognition unit can convert what the user is saying into text in real time, for example. For example, if a user says, "I want to talk about the progress of the meeting," the speech recognition unit converts that content into text. The speech recognition unit can convert the user's speech into text with high accuracy using speech recognition technology. The feedback unit analyzes the text-converted content and generates appropriate feedback and questions. For example, if a user says, "I want to talk about the progress of the meeting," the feedback unit can generate a question such as, "Specifically, what kind of progress are you thinking of?" The feedback unit uses the generation AI to generate appropriate feedback and questions in response to the user's statements. As a result, the multilingual conversation learning system according to this embodiment can efficiently learn multiple languages ​​by generating conversation scenarios based on user specifications and performing speech recognition and feedback.

[0030] The reception desk accepts the user's selection of the language and subject they wish to learn. For example, if a user wants to learn business English, the reception desk can accept the selection of "English" and "Business." The reception desk then stores the user's specified language and subject in a database and passes it to the generation department. Specifically, the reception desk provides options for the user to select the language and subject they wish to learn through the user interface. Users can select their desired language and subject using dropdown menus or checkboxes. Once the selection is complete, the reception desk stores the information in the database and passes it to the generation department. This process is designed to be easy for users to operate and enhances user convenience by providing an intuitive interface. Furthermore, the reception desk can also suggest appropriate languages ​​and subjects based on the user's past learning history and progress. For example, if a user previously studied "Business English," the reception desk can use that information to suggest what they should learn next. This allows the user to learn efficiently. The reception desk can also collect user feedback and use it to improve the system. For example, if a user is dissatisfied with a particular language or subject, the system can be adjusted or improved based on that feedback. This allows the reception department to respond flexibly to user needs, thereby improving the overall user experience of the system.

[0031] The generation unit generates conversation scenarios based on the specified language and field. For example, using generative AI, the generation unit can generate conversation scenarios based on the specified language and field. For instance, in the case of business conversations, the generation unit can generate meeting scenarios and presentation scenarios. The generation unit uses generative AI to generate appropriate conversation scenarios based on user specifications. Specifically, the generative AI generates conversation scenarios based on the language and field specified by the user, taking into account relevant context and situations. For example, when generating business conversation scenarios, it creates scenarios that simulate actual business scenes, such as meeting progress, presentation preparation, and negotiation. The generative AI has learned from a large dataset and can generate natural conversation flows and appropriate expressions. Furthermore, the generation unit can adjust the difficulty and content of scenarios according to the user's level and learning objectives. For example, it can generate scenarios with basic phrases and simple conversations for beginners, and scenarios with specialized terminology and complex conversations for advanced learners. The generation unit can also improve scenarios based on user feedback to provide a more effective learning experience. For example, if a user finds a particular scenario too difficult, the difficulty level of the scenario can be adjusted based on that feedback. This allows the generation unit to flexibly generate scenarios that meet user needs, maximizing the learning effect.

[0032] The speech recognition unit converts the user's speech into text. For example, it can convert what the user says into text in real time. For instance, if a user says, "I want to talk about the meeting's progress," the speech recognition unit will convert that into text. The speech recognition unit uses speech recognition technology to convert the user's speech into text with high accuracy. Specifically, the speech recognition unit analyzes the user's utterance in real time and converts the audio signal into text data. Speech recognition technology uses a combination of acoustic and linguistic models to accurately recognize the content of the utterance. The acoustic model extracts features from the audio signal, and the linguistic model generates the optimal text considering the context and grammar. This allows the speech recognition unit to convert the user's utterance into text with high accuracy. Furthermore, the speech recognition unit also incorporates technologies to mitigate the effects of noise and accent. For example, noise cancellation technology is used to remove background noise and improve speech clarity. The speech recognition model is also trained to handle different accents and pronunciation variations. This allows the speech recognition unit to accurately recognize and convert various user utterances into text. Furthermore, the speech recognition unit can maintain a natural conversational flow by taking into account the user's speaking speed and intonation. For example, even if the user speaks quickly, the speech recognition unit can adapt to that speed and convert it to text in real time. This allows the speech recognition unit to accurately and quickly convert the user's speech into text, improving the overall performance of the system.

[0033] The feedback unit analyzes the text-converted content and generates appropriate feedback and questions. For example, using generative AI, the feedback unit analyzes the text-converted content and generates appropriate feedback and questions. For instance, if a user says, "I want to talk about meeting progress," the feedback unit can generate a question such as, "Specifically, what kind of progress are you thinking of?" The feedback unit uses generative AI to generate appropriate feedback and questions in response to user statements. Specifically, the feedback unit analyzes the user's text-converted statements and generates appropriate feedback and questions based on that content. The generative AI uses natural language processing technology to understand the intent and context of the user's statements and provides corresponding feedback. For example, if a user says, "I'm worried about preparing my presentation," the feedback unit generates a specific question such as, "Which parts are you particularly worried about?" This allows the user to organize their thoughts and learn more deeply. Furthermore, the feedback unit can provide individually customized feedback by considering the user's learning progress and past statement history. For example, if a user has previously studied "meeting progress," it can provide more advanced questions and feedback based on that history. This allows the user to continuously deepen their learning. Furthermore, the feedback function can also provide evaluations and advice on user statements. For example, if a user makes mistakes in pronunciation or grammar, it will point these out and teach the correct expressions. This allows users to understand their weaknesses and improve them. The feedback function plays an important role in enriching the user's learning experience and supporting effective learning.

[0034] The generation unit can generate conversation scenarios based on a specified language and field. For example, the generation unit uses a generation AI to generate conversation scenarios based on a specified language and field. For example, in the case of business conversations, the generation unit can generate meeting scenarios and presentation scenarios. The generation unit uses a generation AI to generate appropriate conversation scenarios based on user specifications. This allows for the generation of appropriate conversation scenarios based on a specified language and field. Some or all of the above-described processes in the generation unit may be performed using a generation AI, or without a generation AI. For example, the generation unit can input a prompt to the generation AI to generate a conversation scenario based on user specifications, and the generation AI can generate the conversation scenario.

[0035] The speech recognition unit can convert the user's voice into text in real time. For example, the speech recognition unit can convert what the user says into text in real time. For example, if the user says, "I want to talk about the progress of the meeting," the speech recognition unit will convert that into text. The speech recognition unit can convert the user's voice into text with high accuracy using speech recognition technology. This enables smooth conversation by converting the user's voice into text in real time. Some or all of the above processing in the speech recognition unit may be performed using, for example, a generative AI, or it may be performed without a generative AI. For example, the speech recognition unit can input the user's voice data into a generative AI, and the generative AI can convert the voice data into text data.

[0036] The feedback unit can analyze the text-converted content and generate appropriate feedback and questions. For example, the feedback unit uses a generative AI to analyze the text-converted content and generate appropriate feedback and questions. For example, if a user says, "I want to talk about the meeting's progress," the feedback unit can generate a question such as, "Specifically, what kind of progress are you thinking of?" The feedback unit uses a generative AI to generate appropriate feedback and questions in response to the user's statements. This enhances the user's learning effect by analyzing the text-converted content and generating appropriate feedback and questions. Some or all of the above-described processes in the feedback unit may be performed using a generative AI, or they may be performed without a generative AI. For example, the feedback unit can input text data into a generative AI, which can then generate feedback and questions.

[0037] The generation unit can generate conversation scenarios that support multiple languages. The generation unit generates conversation scenarios that support multiple languages, for example, using a generation AI. For example, it can generate conversation scenarios in various languages ​​such as English, French, German, Italian, Chinese, and Japanese. The generation unit generates conversation scenarios that support multiple languages ​​based on user specifications using a generation AI. This enables learning in various languages ​​by generating conversation scenarios that support multiple languages. Some or all of the above-described processes in the generation unit may be performed using a generation AI, for example, or without a generation AI. For example, the generation unit can input a prompt to the generation AI to generate conversation scenarios that support multiple languages ​​based on user specifications, and the generation AI can generate conversation scenarios that support multiple languages.

[0038] The system includes a progress management unit. The progress management unit manages the user's progress and records their learning history. For example, the progress management unit can monitor the user's learning progress in real time and manage their progress. For example, the progress management unit records the content and time the user has studied and understands their progress. The progress management unit can also save the user's learning history to a database and refer to past learning content. For example, the progress management unit records the content the user has studied in the past and test results and manages their learning history. This allows the system to manage the user's progress and understand their learning progress by recording their learning history. Some or all of the above-described processes in the progress management unit may be performed using, for example, a generative AI, or not using a generative AI. For example, the progress management unit can input the user's learning history into a generative AI, which can then analyze the learning history and manage the progress.

[0039] The reception desk can analyze the user's past learning history and suggest the optimal combination of language and subject area. For example, the reception desk can suggest the next subject to learn based on what the user has learned in the past. The reception desk can also suggest, for example, that the user relearn subjects they previously struggled with. The reception desk can also suggest, for example, that the user further explore subjects they previously excelled in. In this way, by analyzing the user's past learning history, the reception desk can suggest the optimal learning content. Some or all of the above processing in the reception desk may be performed using, for example, a generative AI, or without a generative AI. For example, the reception desk can input the user's past learning history data into a generative AI, which can then suggest the optimal combination of language and subject area.

[0040] The reception unit can filter the user's current learning progress when they specify the learning language and field. For example, if the user is at a beginner level, the reception unit will suggest basic conversation scenarios. If the user is at an intermediate level, the reception unit may also suggest more advanced conversation scenarios. If the user is at an advanced level, the reception unit may also suggest more specialized conversation scenarios. This allows the reception unit to provide appropriate learning content by filtering based on the user's current learning progress. Some or all of the above processing in the reception unit may be performed using, for example, a generative AI, or without a generative AI. For example, the reception unit can input the user's current learning progress data into a generative AI, which can then perform the filtering.

[0041] The reception desk can suggest highly relevant languages ​​and fields of study by considering the user's geographical location when the user specifies the language and field of study. For example, if the user is traveling, the reception desk can suggest the local language and travel conversations. For example, if the user is on a business trip, the reception desk can suggest business conversations for that region. For example, if the user is studying abroad, the reception desk can suggest academic conversations for that region. This allows the system to provide highly relevant learning content by considering the user's geographical location. Some or all of the above processing in the reception desk may be performed using, for example, a generative AI, or not using a generative AI. For example, the reception desk can input the user's geographical location data into a generative AI, which can then suggest highly relevant languages ​​and fields of study.

[0042] The reception desk can analyze the user's social media activity when they specify a learning language and field, and suggest relevant languages ​​and fields. For example, if the user posts many travel photos on social media, the reception desk can suggest travel conversations. If the user posts many business-related posts, the reception desk can also suggest business conversations. If the user posts many posts about their daily life, the reception desk can also suggest everyday conversations. This allows the reception desk to provide highly relevant learning content by analyzing the user's social media activity. Some or all of the above processing in the reception desk may be performed using, for example, a generative AI, or not using a generative AI. For example, the reception desk can input the user's social media activity data into a generative AI, which can then suggest relevant languages ​​and fields.

[0043] The generation unit can generate the optimal scenario by referring to the user's past learning history when generating conversation scenarios. For example, the generation unit can generate a scenario for the user to learn next based on what the user has learned in the past. For example, the generation unit can also generate a scenario for the user to learn again if they have previously struggled with it. For example, the generation unit can also generate a scenario for the user to delve deeper into if they have previously excelled at it. In this way, the optimal conversation scenario can be generated by referring to the user's past learning history. Some or all of the above processing in the generation unit may be performed using a generation AI, for example, or without a generation AI. For example, the generation unit can input the user's past learning history data into a generation AI, and the generation AI can generate the optimal scenario.

[0044] The generation unit can adjust the difficulty level of conversation scenarios based on the user's current learning progress. For example, if the user is at a beginner level, the generation unit will generate a basic scenario. If the user is at an intermediate level, the generation unit can also generate an advanced scenario. If the user is at an advanced level, the generation unit can also generate a specialized scenario. By adjusting the difficulty level of the scenarios based on the user's current learning progress, appropriate learning content can be provided. Some or all of the above processing in the generation unit may be performed using a generation AI, for example, or without a generation AI. For example, the generation unit can input the user's current learning progress data into the generation AI, which can then adjust the difficulty level of the scenarios.

[0045] The generation unit can generate highly relevant scenarios by considering the user's geographical location information when generating conversation scenarios. For example, if the user is traveling, the generation unit can generate conversation scenarios for that region. For example, if the user is on a business trip, the generation unit can also generate business conversation scenarios for that region. For example, if the user is studying abroad, the generation unit can also generate academic conversation scenarios for that region. In this way, highly relevant conversation scenarios can be generated by considering the user's geographical location information. Some or all of the above processing in the generation unit may be performed using a generation AI, for example, or without a generation AI. For example, the generation unit can input the user's geographical location information data into a generation AI, and the generation AI can generate highly relevant scenarios.

[0046] The generation unit can analyze the user's social media activity and generate relevant scenarios when generating conversation scenarios. For example, if the user posts many travel photos on social media, the generation unit can generate a travel conversation scenario. For example, if the user posts many business-related posts, the generation unit can also generate a business conversation scenario. For example, if the user posts many posts about their daily life, the generation unit can also generate a daily conversation scenario. In this way, by analyzing the user's social media activity, it is possible to generate highly relevant conversation scenarios. Some or all of the above processing in the generation unit may be performed using, for example, a generation AI, or without using a generation AI. For example, the generation unit can input the user's social media activity data into a generation AI, and the generation AI can generate relevant scenarios.

[0047] The speech recognition unit can apply the optimal recognition algorithm by referring to the user's past speech history during speech recognition. For example, the speech recognition unit applies the optimal recognition algorithm based on words previously pronounced by the user. For example, the speech recognition unit can also adjust the recognition algorithm by considering specific pronunciation habits from the user's past speech history. For example, the speech recognition unit can analyze the user's past speech history and apply the most efficient recognition algorithm. This allows the optimal recognition algorithm to be applied by referring to the user's past speech history. Some or all of the above processing in the speech recognition unit may be performed using, for example, a generative AI, or without a generative AI. For example, the speech recognition unit can input the user's past speech history data into a generative AI, which can then apply the optimal recognition algorithm.

[0048] The speech recognition unit can adjust the difficulty level of recognition based on the user's current learning progress during speech recognition. For example, if the user is at a beginner level, the speech recognition unit can adjust to recognize simple words and phrases. For example, if the user is at an intermediate level, the speech recognition unit can also adjust to recognize complex sentences. For example, if the user is at an advanced level, the speech recognition unit can also adjust to recognize specialized terminology. This allows for appropriate speech recognition by adjusting the difficulty level of recognition based on the user's current learning progress. Some or all of the above processing in the speech recognition unit may be performed using, for example, a generative AI, or without a generative AI. For example, the speech recognition unit can input the user's current learning progress data into a generative AI, which can then adjust the difficulty level of recognition.

[0049] The speech recognition unit can apply a highly relevant recognition algorithm by considering the user's geographical location information during speech recognition. For example, if the user is traveling, the speech recognition unit can apply a recognition algorithm corresponding to the local pronunciation. For example, if the user is on a business trip, the speech recognition unit can also apply a recognition algorithm corresponding to the local business terminology. For example, if the user is studying abroad, the speech recognition unit can also apply a recognition algorithm corresponding to the local academic terminology. This allows for the application of a highly relevant recognition algorithm by considering the user's geographical location information. Some or all of the above processing in the speech recognition unit may be performed using, for example, a generative AI, or without a generative AI. For example, the speech recognition unit can input the user's geographical location data into a generative AI, which can then apply a highly relevant recognition algorithm.

[0050] The speech recognition unit can analyze the user's social media activity during speech recognition and apply relevant recognition algorithms. For example, if the user posts many travel photos on social media, the speech recognition unit can apply a recognition algorithm that corresponds to travel conversations. For example, if the user makes many business-related posts, the speech recognition unit can also apply a recognition algorithm that corresponds to business conversations. For example, if the user makes many posts about daily life, the speech recognition unit can also apply a recognition algorithm that corresponds to daily conversations. In this way, by analyzing the user's social media activity, a highly relevant recognition algorithm can be applied. Some or all of the above processing in the speech recognition unit may be performed using, for example, a generative AI, or without a generative AI. For example, the speech recognition unit can input the user's social media activity data into a generative AI, and the generative AI can apply a relevant recognition algorithm.

[0051] The feedback unit can generate optimal feedback by referring to the user's past learning history when generating feedback. For example, the feedback unit can provide feedback on what the user should learn next based on what the user has learned in the past. For example, the feedback unit can also provide feedback to encourage the user to relearn topics they previously struggled with. For example, the feedback unit can also provide feedback to encourage the user to further explore topics they previously excelled at. In this way, optimal feedback can be generated by referring to the user's past learning history. Some or all of the above processing in the feedback unit may be performed using, for example, a generation AI, or without a generation AI. For example, the feedback unit can input the user's past learning history data into a generation AI, which can then generate optimal feedback.

[0052] The feedback unit can adjust the content of the feedback based on the user's current learning progress when generating feedback. For example, if the user is at a beginner level, the feedback unit provides basic feedback. For example, if the user is at an intermediate level, the feedback unit can also provide advanced feedback. For example, if the user is at an advanced level, the feedback unit can also provide expert feedback. This allows for the provision of appropriate feedback by adjusting the content of the feedback based on the user's current learning progress. Some or all of the above processing in the feedback unit may be performed using, for example, a generative AI, or without a generative AI. For example, the feedback unit can input the user's current learning progress data into the generative AI, which can then adjust the content of the feedback.

[0053] The feedback unit can generate highly relevant feedback by considering the user's geographical location information when generating feedback. For example, if the user is traveling, the feedback unit can provide feedback related to the culture of that region. For example, if the user is on a business trip, the feedback unit can also provide feedback related to the business customs of that region. For example, if the user is studying abroad, the feedback unit can also provide feedback related to the academic culture of that region. This allows the feedback unit to provide highly relevant feedback by considering the user's geographical location information. Some or all of the above processing in the feedback unit may be performed using, for example, a generating AI, or without using a generating AI. For example, the feedback unit can input the user's geographical location information data into a generating AI, which can then generate highly relevant feedback.

[0054] The feedback unit can analyze the user's social media activity and generate relevant feedback when generating feedback. For example, if the user posts many travel photos on social media, the feedback unit can provide feedback related to travel conversations. For example, if the user posts many business-related posts, the feedback unit can also provide feedback related to business conversations. For example, if the user posts many posts about daily life, the feedback unit can also provide feedback related to daily life conversations. In this way, by analyzing the user's social media activity, it is possible to provide highly relevant feedback. Some or all of the above processing in the feedback unit may be performed using, for example, a generative AI, or without a generative AI. For example, the feedback unit can input the user's social media activity data into a generative AI, and the generative AI can generate relevant feedback.

[0055] The progress management unit can select the optimal progress management method by referring to the user's past learning history when managing learning progress. For example, the progress management unit manages the content the user should learn next based on what the user has learned in the past. For example, the progress management unit can also manage the progress so that the user relearns content that they previously found difficult. For example, the progress management unit can also manage the progress so that the user further explores content that they previously excelled at. In this way, the optimal progress management method can be selected by referring to the user's past learning history. Some or all of the above processing in the progress management unit may be performed using, for example, a generative AI, or without a generative AI. For example, the progress management unit can input the user's past learning history data into a generative AI, and the generative AI can select the optimal progress management method.

[0056] The progress management unit can select the optimal progress management method when managing learning progress, taking into account the user's geographical location information. For example, if the user is traveling, the progress management unit can prioritize managing content related to the culture of that region. For example, if the user is on a business trip, the progress management unit can prioritize managing content related to the business customs of that region. For example, if the user is studying abroad, the progress management unit can prioritize managing content related to the academic culture of that region. In this way, the optimal progress management method can be selected by taking into account the user's geographical location information. Some or all of the above processing in the progress management unit may be performed using, for example, a generative AI, or without a generative AI. For example, the progress management unit can input the user's geographical location information data into a generative AI, and the generative AI can select the optimal progress management method.

[0057] The system according to the embodiment is not limited to the example described above, and various modifications are possible, for example, as follows.

[0058] A multilingual conversation learning system can analyze a user's learning style and suggest the optimal learning method. For example, users who prefer visual learning can be provided with scenarios that heavily utilize images and videos. Users who prefer auditory learning can be provided with audio guides or podcast-style scenarios. Furthermore, users who prefer practical learning can be provided with interactive simulations. By providing the optimal learning method tailored to the user's learning style, the system can enhance learning effectiveness.

[0059] A multilingual conversation learning system can provide a customized learning plan based on the user's learning goals. For example, if a user aims to pass a specific exam, it can provide scenarios and practice questions tailored to that exam. If a user aims to enter a specific profession, it can provide specialized terminology and conversation scenarios related to that profession. Furthermore, if a user's purpose is travel, it can provide scenarios that include information about the culture and customs of their travel destination. This allows for a customized learning plan tailored to the user's learning goals, thereby increasing their motivation to learn.

[0060] A multilingual conversation learning system can analyze a user's learning history and provide appropriate feedback based on their learning progress. For example, if a user has difficulty in a particular area, the system can provide feedback to encourage them to focus on that area. It can also provide additional scenarios to further explore areas where the user excels. Furthermore, if a user continues learning for a certain period, the system can provide feedback praising their efforts. This allows the system to maintain the user's motivation to learn by providing appropriate feedback based on their learning history.

[0061] A multilingual conversation learning system can provide region-specific learning content by taking into account the user's geographical location. For example, if a user is traveling in a particular country, it can provide scenarios related to that country's culture and customs. Similarly, if a user is on a business trip, it can provide scenarios related to the local business customs and terminology. Furthermore, if a user is studying abroad, it can provide scenarios related to the region's academic culture and student life. By considering the user's geographical location and providing region-specific learning content, a more practical learning experience can be achieved.

[0062] A multilingual conversation learning system can analyze a user's social media activity and provide relevant learning content. For example, if a user posts many travel photos on social media, it can provide scenarios related to travel conversation. Similarly, if a user frequently posts business-related content, it can provide scenarios related to business conversation. Furthermore, if a user frequently posts about their daily life, it can provide scenarios related to daily conversation. In this way, by analyzing a user's social media activity, the system can provide highly relevant learning content.

[0063] The multilingual conversation learning system can monitor the user's learning progress in real time and adjust the learning content accordingly. For example, if a user is falling behind in a particular area, the system can adjust the scenario to focus on that area. Conversely, if a user is progressing quickly in a particular area, it can offer a more challenging scenario. Furthermore, if a user has been learning for a certain period, the system can offer a scenario that rewards their efforts. By monitoring the user's learning progress in real time and adjusting the learning content accordingly, the system can provide a more effective learning experience.

[0064] The following briefly describes the processing flow for example form 1.

[0065] Step 1: The reception desk receives the user's specification of the language and field they wish to learn. For example, if a user wants to learn business English, the reception desk can receive specifications such as "English" and "Business." The reception desk saves the language and field specified by the user to the database and passes it to the generation desk. Step 2: The generation unit generates conversation scenarios based on the specified language and field. The generation unit uses generative AI to generate conversation scenarios based on the specified language and field. For example, in the case of business conversations, the generation unit can generate meeting scenarios and presentation scenarios. Step 3: The speech recognition unit converts the user's voice into text. The speech recognition unit can convert what the user says into text in real time. For example, if the user says, "I want to talk about the progress of the meeting," the speech recognition unit will convert that into text. Step 4: The feedback unit analyzes the converted text and generates appropriate feedback and questions. The feedback unit uses a generation AI to analyze the converted text and generate appropriate feedback and questions. For example, if a user says, "I want to talk about the meeting's progress," the feedback unit can generate a question such as, "What specific progress are you thinking of?"

[0066] (Example of form 2) The multilingual conversation learning system according to an embodiment of the present invention is an online service that utilizes generative AI to provide multilingual conversation learning tailored to the individual's level and field. In this multilingual conversation learning system, the user specifies the language and field they wish to learn, the generative AI generates an appropriate conversation scenario, the user engages in conversation using speech recognition technology, and the content is converted into text. The generative AI analyzes the converted text and generates appropriate feedback and questions. This allows the user to learn multiple languages ​​efficiently and at their own pace without feeling embarrassed. For example, the user specifies the language and field they wish to learn. For example, if the user wants to learn business conversation in English, they specify "English" and "Business." This information is input into the generative AI. Next, the generative AI generates an appropriate conversation scenario based on the user's specifications. The generative AI creates a conversation scenario based on the specified language and field. For example, in the case of business conversation, a meeting scenario or a presentation scenario is generated. Based on the generated scenario, the user engages in conversation using speech recognition technology. What the user says is converted into text in real time. For example, if the user says, "I want to talk about the progress of the meeting," that content is converted into text. The generative AI analyzes the text that has been converted and generates appropriate feedback and questions. For example, if a user says, "I want to talk about the progress of the meeting," the generative AI will generate a question such as, "Specifically, what kind of progress are you thinking of?" This allows the user to continue the conversation. This mechanism allows users to learn multiple languages ​​efficiently and on a flexible schedule without feeling embarrassed. For example, even if a user wants to learn in 20 minutes of free time, the generative AI will generate an appropriate scenario, enabling effective learning in a short amount of time. Also, because the conversation is with the generative AI, the user can enjoy the conversation without feeling self-conscious. Furthermore, the generative AI supports multiple languages, and learning is possible in various languages ​​such as English, French, German, Italian, Chinese, and Japanese. This allows users to freely select and learn languages ​​according to their interests and needs.This allows the multilingual conversation learning system to efficiently learn multiple languages ​​by generating conversation scenarios based on user specifications and providing speech recognition and feedback.

[0067] The multilingual conversation learning system according to this embodiment comprises a reception unit, a generation unit, a speech recognition unit, and a feedback unit. The reception unit receives the user's specification of the language and field they wish to learn. For example, if a user wants to learn business conversation in English, the reception unit can receive specifications such as "English" and "business." The reception unit, for example, stores the language and field specified by the user in a database and passes it to the generation unit. The generation unit generates conversation scenarios based on the specified language and field. The generation unit generates conversation scenarios based on the specified language and field, for example, using a generation AI. For example, in the case of business conversations, the generation unit can generate meeting scenarios or presentation scenarios. The generation unit generates appropriate conversation scenarios based on the user's specifications using a generation AI. The speech recognition unit converts the user's speech into text. The speech recognition unit can convert what the user is saying into text in real time, for example. For example, if a user says, "I want to talk about the progress of the meeting," the speech recognition unit converts that content into text. The speech recognition unit can convert the user's speech into text with high accuracy using speech recognition technology. The feedback unit analyzes the text-converted content and generates appropriate feedback and questions. For example, if a user says, "I want to talk about the progress of the meeting," the feedback unit can generate a question such as, "Specifically, what kind of progress are you thinking of?" The feedback unit uses the generation AI to generate appropriate feedback and questions in response to the user's statements. As a result, the multilingual conversation learning system according to this embodiment can efficiently learn multiple languages ​​by generating conversation scenarios based on user specifications and performing speech recognition and feedback.

[0068] The reception desk accepts the user's selection of the language and subject they wish to learn. For example, if a user wants to learn business English, the reception desk can accept the selection of "English" and "Business." The reception desk then stores the user's specified language and subject in a database and passes it to the generation department. Specifically, the reception desk provides options for the user to select the language and subject they wish to learn through the user interface. Users can select their desired language and subject using dropdown menus or checkboxes. Once the selection is complete, the reception desk stores the information in the database and passes it to the generation department. This process is designed to be easy for users to operate and enhances user convenience by providing an intuitive interface. Furthermore, the reception desk can also suggest appropriate languages ​​and subjects based on the user's past learning history and progress. For example, if a user previously studied "Business English," the reception desk can use that information to suggest what they should learn next. This allows the user to learn efficiently. The reception desk can also collect user feedback and use it to improve the system. For example, if a user is dissatisfied with a particular language or subject, the system can be adjusted or improved based on that feedback. This allows the reception department to respond flexibly to user needs, thereby improving the overall user experience of the system.

[0069] The generation unit generates conversation scenarios based on the specified language and field. For example, using generative AI, the generation unit can generate conversation scenarios based on the specified language and field. For instance, in the case of business conversations, the generation unit can generate meeting scenarios and presentation scenarios. The generation unit uses generative AI to generate appropriate conversation scenarios based on user specifications. Specifically, the generative AI generates conversation scenarios based on the language and field specified by the user, taking into account relevant context and situations. For example, when generating business conversation scenarios, it creates scenarios that simulate actual business scenes, such as meeting progress, presentation preparation, and negotiation. The generative AI has learned from a large dataset and can generate natural conversation flows and appropriate expressions. Furthermore, the generation unit can adjust the difficulty and content of scenarios according to the user's level and learning objectives. For example, it can generate scenarios with basic phrases and simple conversations for beginners, and scenarios with specialized terminology and complex conversations for advanced learners. The generation unit can also improve scenarios based on user feedback to provide a more effective learning experience. For example, if a user finds a particular scenario too difficult, the difficulty level of the scenario can be adjusted based on that feedback. This allows the generation unit to flexibly generate scenarios that meet user needs, maximizing the learning effect.

[0070] The speech recognition unit converts the user's speech into text. For example, it can convert what the user says into text in real time. For instance, if a user says, "I want to talk about the meeting's progress," the speech recognition unit will convert that into text. The speech recognition unit uses speech recognition technology to convert the user's speech into text with high accuracy. Specifically, the speech recognition unit analyzes the user's utterance in real time and converts the audio signal into text data. Speech recognition technology uses a combination of acoustic and linguistic models to accurately recognize the content of the utterance. The acoustic model extracts features from the audio signal, and the linguistic model generates the optimal text considering the context and grammar. This allows the speech recognition unit to convert the user's utterance into text with high accuracy. Furthermore, the speech recognition unit also incorporates technologies to mitigate the effects of noise and accent. For example, noise cancellation technology is used to remove background noise and improve speech clarity. The speech recognition model is also trained to handle different accents and pronunciation variations. This allows the speech recognition unit to accurately recognize and convert various user utterances into text. Furthermore, the speech recognition unit can maintain a natural conversational flow by taking into account the user's speaking speed and intonation. For example, even if the user speaks quickly, the speech recognition unit can adapt to that speed and convert it to text in real time. This allows the speech recognition unit to accurately and quickly convert the user's speech into text, improving the overall performance of the system.

[0071] The feedback unit analyzes the text-converted content and generates appropriate feedback and questions. For example, using generative AI, the feedback unit analyzes the text-converted content and generates appropriate feedback and questions. For instance, if a user says, "I want to talk about meeting progress," the feedback unit can generate a question such as, "Specifically, what kind of progress are you thinking of?" The feedback unit uses generative AI to generate appropriate feedback and questions in response to user statements. Specifically, the feedback unit analyzes the user's text-converted statements and generates appropriate feedback and questions based on that content. The generative AI uses natural language processing technology to understand the intent and context of the user's statements and provides corresponding feedback. For example, if a user says, "I'm worried about preparing my presentation," the feedback unit generates a specific question such as, "Which parts are you particularly worried about?" This allows the user to organize their thoughts and learn more deeply. Furthermore, the feedback unit can provide individually customized feedback by considering the user's learning progress and past statement history. For example, if a user has previously studied "meeting progress," it can provide more advanced questions and feedback based on that history. This allows the user to continuously deepen their learning. Furthermore, the feedback function can also provide evaluations and advice on user statements. For example, if a user makes mistakes in pronunciation or grammar, it will point these out and teach the correct expressions. This allows users to understand their weaknesses and improve them. The feedback function plays an important role in enriching the user's learning experience and supporting effective learning.

[0072] The generation unit can generate conversation scenarios based on a specified language and field. For example, the generation unit uses a generation AI to generate conversation scenarios based on a specified language and field. For example, in the case of business conversations, the generation unit can generate meeting scenarios and presentation scenarios. The generation unit uses a generation AI to generate appropriate conversation scenarios based on user specifications. This allows for the generation of appropriate conversation scenarios based on a specified language and field. Some or all of the above-described processes in the generation unit may be performed using a generation AI, or without a generation AI. For example, the generation unit can input a prompt to the generation AI to generate a conversation scenario based on user specifications, and the generation AI can generate the conversation scenario.

[0073] The speech recognition unit can convert the user's voice into text in real time. For example, the speech recognition unit can convert what the user says into text in real time. For example, if the user says, "I want to talk about the progress of the meeting," the speech recognition unit will convert that into text. The speech recognition unit can convert the user's voice into text with high accuracy using speech recognition technology. This enables smooth conversation by converting the user's voice into text in real time. Some or all of the above processing in the speech recognition unit may be performed using, for example, a generative AI, or it may be performed without a generative AI. For example, the speech recognition unit can input the user's voice data into a generative AI, and the generative AI can convert the voice data into text data.

[0074] The feedback unit can analyze the text-converted content and generate appropriate feedback and questions. For example, the feedback unit uses a generative AI to analyze the text-converted content and generate appropriate feedback and questions. For example, if a user says, "I want to talk about the meeting's progress," the feedback unit can generate a question such as, "Specifically, what kind of progress are you thinking of?" The feedback unit uses a generative AI to generate appropriate feedback and questions in response to the user's statements. This enhances the user's learning effect by analyzing the text-converted content and generating appropriate feedback and questions. Some or all of the above-described processes in the feedback unit may be performed using a generative AI, or they may be performed without a generative AI. For example, the feedback unit can input text data into a generative AI, which can then generate feedback and questions.

[0075] The generation unit can generate conversation scenarios that support multiple languages. The generation unit generates conversation scenarios that support multiple languages, for example, using a generation AI. For example, it can generate conversation scenarios in various languages ​​such as English, French, German, Italian, Chinese, and Japanese. The generation unit generates conversation scenarios that support multiple languages ​​based on user specifications using a generation AI. This enables learning in various languages ​​by generating conversation scenarios that support multiple languages. Some or all of the above-described processes in the generation unit may be performed using a generation AI, for example, or without a generation AI. For example, the generation unit can input a prompt to the generation AI to generate conversation scenarios that support multiple languages ​​based on user specifications, and the generation AI can generate conversation scenarios that support multiple languages.

[0076] The system includes a progress management unit. The progress management unit manages the user's progress and records their learning history. For example, the progress management unit can monitor the user's learning progress in real time and manage their progress. For example, the progress management unit records the content and time the user has studied and understands their progress. The progress management unit can also save the user's learning history to a database and refer to past learning content. For example, the progress management unit records the content the user has studied in the past and test results and manages their learning history. This allows the system to manage the user's progress and understand their learning progress by recording their learning history. Some or all of the above-described processes in the progress management unit may be performed using, for example, a generative AI, or not using a generative AI. For example, the progress management unit can input the user's learning history into a generative AI, which can then analyze the learning history and manage the progress.

[0077] The reception unit can estimate the user's emotions and suggest learning languages ​​and fields based on the estimated emotions. For example, if the user is feeling stressed, the reception unit can suggest relaxing travel conversation scenarios. For example, if the user is feeling motivated, the reception unit can suggest business conversation scenarios. For example, if the user is tired, the reception unit can suggest simple everyday conversation scenarios. This allows for the provision of more appropriate learning content by suggesting learning languages ​​and fields based on the user's emotions. Emotion estimation is achieved using an emotion estimation function, for example, using an emotion engine or generative AI. Generative AI is, but is not limited to, text generation AI (e.g., LLM) or multimodal generation AI. Some or all of the above processing in the reception unit may be performed using a generative AI, or not using a generative AI. For example, the reception unit can input user emotion data into a generative AI, which can then suggest learning languages ​​and fields.

[0078] The reception desk can analyze the user's past learning history and suggest the optimal combination of language and subject area. For example, the reception desk can suggest the next subject to learn based on what the user has learned in the past. The reception desk can also suggest, for example, that the user relearn subjects they previously struggled with. The reception desk can also suggest, for example, that the user further explore subjects they previously excelled in. In this way, by analyzing the user's past learning history, the reception desk can suggest the optimal learning content. Some or all of the above processing in the reception desk may be performed using, for example, a generative AI, or without a generative AI. For example, the reception desk can input the user's past learning history data into a generative AI, which can then suggest the optimal combination of language and subject area.

[0079] The reception unit can filter the user's current learning progress when they specify the learning language and field. For example, if the user is at a beginner level, the reception unit will suggest basic conversation scenarios. If the user is at an intermediate level, the reception unit may also suggest more advanced conversation scenarios. If the user is at an advanced level, the reception unit may also suggest more specialized conversation scenarios. This allows the reception unit to provide appropriate learning content by filtering based on the user's current learning progress. Some or all of the above processing in the reception unit may be performed using, for example, a generative AI, or without a generative AI. For example, the reception unit can input the user's current learning progress data into a generative AI, which can then perform the filtering.

[0080] The reception unit can estimate the user's emotions and, based on the estimated emotions, determine the priority of learning languages ​​and subjects. For example, if the user is relaxed, the reception unit will prioritize suggesting relaxing subjects. For example, if the user is focused, the reception unit may also prioritize suggesting more difficult subjects. For example, if the user is tired, the reception unit may also prioritize suggesting easier subjects. This allows for more effective learning by prioritizing learning languages ​​and subjects based on the user's emotions. Emotion estimation is achieved using an emotion estimation function, such as an emotion engine or generative AI. Generative AI may be, but is not limited to, text generation AI (e.g., LLM) or multimodal generation AI. Some or all of the above processing in the reception unit may be performed using a generative AI, or not. For example, the reception unit can input user emotion data into a generative AI, which can then determine the priority of learning languages ​​and subjects.

[0081] The reception desk can suggest highly relevant languages ​​and fields of study by considering the user's geographical location when the user specifies the language and field of study. For example, if the user is traveling, the reception desk can suggest the local language and travel conversations. For example, if the user is on a business trip, the reception desk can suggest business conversations for that region. For example, if the user is studying abroad, the reception desk can suggest academic conversations for that region. This allows the system to provide highly relevant learning content by considering the user's geographical location. Some or all of the above processing in the reception desk may be performed using, for example, a generative AI, or not using a generative AI. For example, the reception desk can input the user's geographical location data into a generative AI, which can then suggest highly relevant languages ​​and fields of study.

[0082] The reception desk can analyze the user's social media activity when they specify a learning language and field, and suggest relevant languages ​​and fields. For example, if the user posts many travel photos on social media, the reception desk can suggest travel conversations. If the user posts many business-related posts, the reception desk can also suggest business conversations. If the user posts many posts about their daily life, the reception desk can also suggest everyday conversations. This allows the reception desk to provide highly relevant learning content by analyzing the user's social media activity. Some or all of the above processing in the reception desk may be performed using, for example, a generative AI, or not using a generative AI. For example, the reception desk can input the user's social media activity data into a generative AI, which can then suggest relevant languages ​​and fields.

[0083] The generation unit can estimate the user's emotions and adjust the way the conversation scenario is presented based on the estimated emotions. For example, if the user is relaxed, the generation unit can generate a scenario that proceeds at a leisurely pace. If the user is in a hurry, the generation unit can also generate a short, to-the-point scenario. If the user is excited, the generation unit can also generate a scenario with visually stimulating effects. This allows for a more appropriate learning experience by adjusting the way the conversation scenario is presented based on the user's emotions. Emotion estimation is achieved using an emotion estimation function, such as an emotion engine or a generative AI. The generative AI is, but is not limited to, a text generation AI (e.g., LLM) or a multimodal generation AI. Some or all of the above-described processes in the generation unit may be performed using a generative AI, or not. For example, the generation unit can input user emotion data into a generative AI, which can then adjust the way the conversation scenario is presented.

[0084] The generation unit can generate the optimal scenario by referring to the user's past learning history when generating conversation scenarios. For example, the generation unit can generate a scenario for the user to learn next based on what the user has learned in the past. For example, the generation unit can also generate a scenario for the user to learn again if they have previously struggled with it. For example, the generation unit can also generate a scenario for the user to delve deeper into if they have previously excelled at it. In this way, the optimal conversation scenario can be generated by referring to the user's past learning history. Some or all of the above processing in the generation unit may be performed using a generation AI, for example, or without a generation AI. For example, the generation unit can input the user's past learning history data into a generation AI, and the generation AI can generate the optimal scenario.

[0085] The generation unit can adjust the difficulty level of conversation scenarios based on the user's current learning progress. For example, if the user is at a beginner level, the generation unit will generate a basic scenario. If the user is at an intermediate level, the generation unit can also generate an advanced scenario. If the user is at an advanced level, the generation unit can also generate a specialized scenario. By adjusting the difficulty level of the scenarios based on the user's current learning progress, appropriate learning content can be provided. Some or all of the above processing in the generation unit may be performed using a generation AI, for example, or without a generation AI. For example, the generation unit can input the user's current learning progress data into the generation AI, which can then adjust the difficulty level of the scenarios.

[0086] The generation unit can estimate the user's emotions and adjust the length of the conversation scenario based on the estimated emotions. For example, if the user is relaxed, the generation unit will generate a longer scenario. If the user is in a hurry, the generation unit can also generate a shorter, more concise scenario. If the user is excited, the generation unit can also generate a scenario with visually stimulating effects. By adjusting the length of the conversation scenario based on the user's emotions, a more appropriate learning experience can be provided. Emotion estimation is achieved using an emotion estimation function, such as an emotion engine or a generative AI. The generative AI is, but is not limited to, a text generation AI (e.g., LLM) or a multimodal generation AI. Some or all of the above processing in the generation unit may be performed using a generative AI, or not. For example, the generation unit can input user emotion data into a generative AI, which can then adjust the length of the conversation scenario.

[0087] The generation unit can generate highly relevant scenarios by considering the user's geographical location information when generating conversation scenarios. For example, if the user is traveling, the generation unit can generate conversation scenarios for that region. For example, if the user is on a business trip, the generation unit can also generate business conversation scenarios for that region. For example, if the user is studying abroad, the generation unit can also generate academic conversation scenarios for that region. In this way, highly relevant conversation scenarios can be generated by considering the user's geographical location information. Some or all of the above processing in the generation unit may be performed using a generation AI, for example, or without a generation AI. For example, the generation unit can input the user's geographical location information data into a generation AI, and the generation AI can generate highly relevant scenarios.

[0088] The generation unit can analyze the user's social media activity and generate relevant scenarios when generating conversation scenarios. For example, if the user posts many travel photos on social media, the generation unit can generate a travel conversation scenario. For example, if the user posts many business-related posts, the generation unit can also generate a business conversation scenario. For example, if the user posts many posts about their daily life, the generation unit can also generate a daily conversation scenario. In this way, by analyzing the user's social media activity, it is possible to generate highly relevant conversation scenarios. Some or all of the above processing in the generation unit may be performed using, for example, a generation AI, or without using a generation AI. For example, the generation unit can input the user's social media activity data into a generation AI, and the generation AI can generate relevant scenarios.

[0089] The speech recognition unit can estimate the user's emotions and adjust the accuracy of speech recognition based on the estimated emotions. For example, if the user is nervous, the speech recognition unit may prompt the user to speak slowly to improve the accuracy of speech recognition. For example, if the user is relaxed, the speech recognition unit may also prompt the user to speak at a natural pace. For example, if the user is in a hurry, the speech recognition unit may adjust to recognize speech quickly. This allows for more accurate speech recognition by adjusting the accuracy of speech recognition based on the user's emotions. Emotion estimation is achieved using an emotion estimation function, for example, using an emotion engine or generative AI. Generative AI is, but is not limited to, text generation AI (e.g., LLM) or multimodal generation AI. Some or all of the above processing in the speech recognition unit may be performed using a generative AI, or not using a generative AI. For example, the speech recognition unit can input user emotion data into a generative AI, which can then adjust the accuracy of speech recognition.

[0090] The speech recognition unit can apply the optimal recognition algorithm by referring to the user's past speech history during speech recognition. For example, the speech recognition unit applies the optimal recognition algorithm based on words previously pronounced by the user. For example, the speech recognition unit can also adjust the recognition algorithm by considering specific pronunciation habits from the user's past speech history. For example, the speech recognition unit can analyze the user's past speech history and apply the most efficient recognition algorithm. This allows the optimal recognition algorithm to be applied by referring to the user's past speech history. Some or all of the above processing in the speech recognition unit may be performed using, for example, a generative AI, or without a generative AI. For example, the speech recognition unit can input the user's past speech history data into a generative AI, which can then apply the optimal recognition algorithm.

[0091] The speech recognition unit can adjust the difficulty level of recognition based on the user's current learning progress during speech recognition. For example, if the user is at a beginner level, the speech recognition unit can adjust to recognize simple words and phrases. For example, if the user is at an intermediate level, the speech recognition unit can also adjust to recognize complex sentences. For example, if the user is at an advanced level, the speech recognition unit can also adjust to recognize specialized terminology. This allows for appropriate speech recognition by adjusting the difficulty level of recognition based on the user's current learning progress. Some or all of the above processing in the speech recognition unit may be performed using, for example, a generative AI, or without a generative AI. For example, the speech recognition unit can input the user's current learning progress data into a generative AI, which can then adjust the difficulty level of recognition.

[0092] The speech recognition unit can estimate the user's emotions and determine the priority of speech recognition based on the estimated emotions. For example, if the user is nervous, the speech recognition unit will prioritize speech recognition. For example, if the user is relaxed, the speech recognition unit can perform speech recognition at a natural speed. For example, if the user is in a hurry, the speech recognition unit can perform speech recognition quickly. This allows for more effective speech recognition by determining the priority of speech recognition based on the user's emotions. Emotion estimation is achieved using an emotion estimation function, for example, using an emotion engine or generative AI. The generative AI is, but is not limited to, text generation AI (e.g., LLM) or multimodal generation AI. Some or all of the above processing in the speech recognition unit may be performed using a generative AI, or not using a generative AI. For example, the speech recognition unit can input user emotion data into a generative AI, which can then determine the priority of speech recognition.

[0093] The speech recognition unit can apply a highly relevant recognition algorithm by considering the user's geographical location information during speech recognition. For example, if the user is traveling, the speech recognition unit can apply a recognition algorithm corresponding to the local pronunciation. For example, if the user is on a business trip, the speech recognition unit can also apply a recognition algorithm corresponding to the local business terminology. For example, if the user is studying abroad, the speech recognition unit can also apply a recognition algorithm corresponding to the local academic terminology. This allows for the application of a highly relevant recognition algorithm by considering the user's geographical location information. Some or all of the above processing in the speech recognition unit may be performed using, for example, a generative AI, or without a generative AI. For example, the speech recognition unit can input the user's geographical location data into a generative AI, which can then apply a highly relevant recognition algorithm.

[0094] The speech recognition unit can analyze the user's social media activity during speech recognition and apply relevant recognition algorithms. For example, if the user posts many travel photos on social media, the speech recognition unit can apply a recognition algorithm that corresponds to travel conversations. For example, if the user makes many business-related posts, the speech recognition unit can also apply a recognition algorithm that corresponds to business conversations. For example, if the user makes many posts about daily life, the speech recognition unit can also apply a recognition algorithm that corresponds to daily conversations. In this way, by analyzing the user's social media activity, a highly relevant recognition algorithm can be applied. Some or all of the above processing in the speech recognition unit may be performed using, for example, a generative AI, or without a generative AI. For example, the speech recognition unit can input the user's social media activity data into a generative AI, and the generative AI can apply a relevant recognition algorithm.

[0095] The feedback unit can estimate the user's emotions and adjust the way it expresses the feedback based on the estimated emotions. For example, if the user is nervous, the feedback unit can provide feedback in gentle words. For example, if the user is relaxed, the feedback unit can also provide detailed feedback. For example, if the user is in a hurry, the feedback unit can provide concise feedback. This allows for more appropriate feedback to be provided by adjusting the way it expresses the feedback based on the user's emotions. Emotion estimation is achieved using an emotion estimation function, such as an emotion engine or generative AI. Generative AI is, but is not limited to, text generation AI (e.g., LLM) or multimodal generation AI. Some or all of the above processing in the feedback unit may be performed using a generative AI, or not using a generative AI. For example, the feedback unit can input user emotion data into a generative AI, which can then adjust the way it expresses the feedback.

[0096] The feedback unit can generate optimal feedback by referring to the user's past learning history when generating feedback. For example, the feedback unit can provide feedback on what the user should learn next based on what the user has learned in the past. For example, the feedback unit can also provide feedback to encourage the user to relearn topics they previously struggled with. For example, the feedback unit can also provide feedback to encourage the user to further explore topics they previously excelled at. In this way, optimal feedback can be generated by referring to the user's past learning history. Some or all of the above processing in the feedback unit may be performed using, for example, a generation AI, or without a generation AI. For example, the feedback unit can input the user's past learning history data into a generation AI, which can then generate optimal feedback.

[0097] The feedback unit can adjust the content of the feedback based on the user's current learning progress when generating feedback. For example, if the user is at a beginner level, the feedback unit provides basic feedback. For example, if the user is at an intermediate level, the feedback unit can also provide advanced feedback. For example, if the user is at an advanced level, the feedback unit can also provide expert feedback. This allows for the provision of appropriate feedback by adjusting the content of the feedback based on the user's current learning progress. Some or all of the above processing in the feedback unit may be performed using, for example, a generative AI, or without a generative AI. For example, the feedback unit can input the user's current learning progress data into the generative AI, which can then adjust the content of the feedback.

[0098] The feedback unit can estimate the user's emotions and determine the priority of feedback based on the estimated emotions. For example, if the user is nervous, the feedback unit will prioritize providing feedback. For example, if the user is relaxed, the feedback unit may also provide detailed feedback. For example, if the user is in a hurry, the feedback unit may also provide concise feedback. This allows for more effective feedback by prioritizing feedback based on the user's emotions. Emotion estimation is achieved using an emotion estimation function, such as an emotion engine or generative AI. Generative AI may be, but is not limited to, text generation AI (e.g., LLM) or multimodal generation AI. Some or all of the above processing in the feedback unit may be performed using a generative AI, or not. For example, the feedback unit can input user emotion data into a generative AI, which can then determine the priority of feedback.

[0099] The feedback unit can generate highly relevant feedback by considering the user's geographical location information when generating feedback. For example, if the user is traveling, the feedback unit can provide feedback related to the culture of that region. For example, if the user is on a business trip, the feedback unit can also provide feedback related to the business customs of that region. For example, if the user is studying abroad, the feedback unit can also provide feedback related to the academic culture of that region. This allows the feedback unit to provide highly relevant feedback by considering the user's geographical location information. Some or all of the above processing in the feedback unit may be performed using, for example, a generating AI, or without using a generating AI. For example, the feedback unit can input the user's geographical location information data into a generating AI, which can then generate highly relevant feedback.

[0100] The feedback unit can analyze the user's social media activity and generate relevant feedback when generating feedback. For example, if the user posts many travel photos on social media, the feedback unit can provide feedback related to travel conversations. For example, if the user posts many business-related posts, the feedback unit can also provide feedback related to business conversations. For example, if the user posts many posts about daily life, the feedback unit can also provide feedback related to daily life conversations. In this way, by analyzing the user's social media activity, it is possible to provide highly relevant feedback. Some or all of the above processing in the feedback unit may be performed using, for example, a generative AI, or without a generative AI. For example, the feedback unit can input the user's social media activity data into a generative AI, and the generative AI can generate relevant feedback.

[0101] The progress management unit can estimate the user's emotions and adjust the learning progress management method based on the estimated user emotions. For example, if the user is nervous, the progress management unit can slow down the progress. For example, if the user is relaxed, the progress management unit can proceed at a normal pace. For example, if the user is in a hurry, the progress management unit can proceed quickly. This allows for more appropriate learning progress by adjusting the learning progress management method based on the user's emotions. Emotion estimation is achieved using an emotion estimation function, for example, using an emotion engine or generative AI. The generative AI is, but is not limited to, text generation AI (e.g., LLM) or multimodal generation AI. Some or all of the above processing in the progress management unit may be performed using a generative AI, or not using a generative AI. For example, the progress management unit can input user emotion data into a generative AI, and the generative AI can adjust the learning progress management method.

[0102] The progress management unit can select the optimal progress management method by referring to the user's past learning history when managing learning progress. For example, the progress management unit manages the content the user should learn next based on what the user has learned in the past. For example, the progress management unit can also manage the progress so that the user relearns content that they previously found difficult. For example, the progress management unit can also manage the progress so that the user further explores content that they previously excelled at. In this way, the optimal progress management method can be selected by referring to the user's past learning history. Some or all of the above processing in the progress management unit may be performed using, for example, a generative AI, or without a generative AI. For example, the progress management unit can input the user's past learning history data into a generative AI, and the generative AI can select the optimal progress management method.

[0103] The progress management unit can estimate the user's emotions and determine the priority of learning progress based on the estimated emotions. For example, if the user is nervous, the progress management unit will prioritize progress management. For example, if the user is relaxed, the progress management unit can manage progress at a normal pace. For example, if the user is in a hurry, the progress management unit can manage progress quickly. This allows for more effective learning progress by determining the priority of learning progress based on the user's emotions. Emotion estimation is achieved using an emotion estimation function, for example, using an emotion engine or generative AI. Generative AI is, but is not limited to, text generation AI (e.g., LLM) or multimodal generation AI. Some or all of the above processing in the progress management unit may be performed using a generative AI, or not using a generative AI. For example, the progress management unit can input user emotion data into a generative AI, and the generative AI can determine the priority of learning progress.

[0104] The progress management unit can select the optimal progress management method when managing learning progress, taking into account the user's geographical location information. For example, if the user is traveling, the progress management unit can prioritize managing content related to the culture of that region. For example, if the user is on a business trip, the progress management unit can prioritize managing content related to the business customs of that region. For example, if the user is studying abroad, the progress management unit can prioritize managing content related to the academic culture of that region. In this way, the optimal progress management method can be selected by taking into account the user's geographical location information. Some or all of the above processing in the progress management unit may be performed using, for example, a generative AI, or without a generative AI. For example, the progress management unit can input the user's geographical location information data into a generative AI, and the generative AI can select the optimal progress management method.

[0105] The system according to the embodiment is not limited to the example described above, and various modifications are possible, for example, as follows.

[0106] A multilingual conversation learning system can analyze a user's learning style and suggest the optimal learning method. For example, users who prefer visual learning can be provided with scenarios that heavily utilize images and videos. Users who prefer auditory learning can be provided with audio guides or podcast-style scenarios. Furthermore, users who prefer practical learning can be provided with interactive simulations. By providing the optimal learning method tailored to the user's learning style, the system can enhance learning effectiveness.

[0107] A multilingual conversation learning system can provide a customized learning plan based on the user's learning goals. For example, if a user aims to pass a specific exam, it can provide scenarios and practice questions tailored to that exam. If a user aims to enter a specific profession, it can provide specialized terminology and conversation scenarios related to that profession. Furthermore, if a user's purpose is travel, it can provide scenarios that include information about the culture and customs of their travel destination. This allows for a customized learning plan tailored to the user's learning goals, thereby increasing their motivation to learn.

[0108] The multilingual conversation learning system can estimate the user's emotions and adjust the learning pace based on those emotions. For example, if the user is stressed, the pace can be slowed to help them relax. Conversely, if the user is focused, the pace can be increased to allow for more efficient learning. Furthermore, if the user is tired, a scenario that can be completed in a short time can be provided. In this way, by adjusting the learning pace based on the user's emotions, a more effective learning experience can be provided.

[0109] A multilingual conversation learning system can analyze a user's learning history and provide appropriate feedback based on their learning progress. For example, if a user has difficulty in a particular area, the system can provide feedback to encourage them to focus on that area. It can also provide additional scenarios to further explore areas where the user excels. Furthermore, if a user continues learning for a certain period, the system can provide feedback praising their efforts. This allows the system to maintain the user's motivation to learn by providing appropriate feedback based on their learning history.

[0110] A multilingual conversation learning system can estimate the user's emotions and personalize learning content based on those emotions. For example, if the user is relaxed, it can provide relaxing scenarios. If the user is excited, it can provide challenging scenarios to maintain that excitement. Furthermore, if the user is sad, it can provide positive scenarios to lift their spirits. By personalizing learning content based on the user's emotions, a more effective learning experience can be provided.

[0111] A multilingual conversation learning system can provide region-specific learning content by taking into account the user's geographical location. For example, if a user is traveling in a particular country, it can provide scenarios related to that country's culture and customs. Similarly, if a user is on a business trip, it can provide scenarios related to the local business customs and terminology. Furthermore, if a user is studying abroad, it can provide scenarios related to the region's academic culture and student life. By considering the user's geographical location and providing region-specific learning content, a more practical learning experience can be achieved.

[0112] The multilingual conversation learning system can estimate the user's emotions and adjust the learning timing based on those emotions. For example, if the user is relaxed, it can suggest a good time to start learning. If the user is stressed, it can suggest temporarily pausing learning. Furthermore, if the user is focused, it can suggest continuing learning. By adjusting the learning timing based on the user's emotions, it can provide a more effective learning experience.

[0113] A multilingual conversation learning system can analyze a user's social media activity and provide relevant learning content. For example, if a user posts many travel photos on social media, it can provide scenarios related to travel conversation. Similarly, if a user frequently posts business-related content, it can provide scenarios related to business conversation. Furthermore, if a user frequently posts about their daily life, it can provide scenarios related to daily conversation. In this way, by analyzing a user's social media activity, the system can provide highly relevant learning content.

[0114] The multilingual conversation learning system can estimate the user's emotions and adjust the learning feedback based on those emotions. For example, if the user is nervous, it can provide feedback in gentle language. If the user is relaxed, it can provide detailed feedback. Furthermore, if the user is in a hurry, it can provide concise feedback. In this way, by adjusting feedback based on the user's emotions, it can provide more appropriate feedback.

[0115] The multilingual conversation learning system can monitor the user's learning progress in real time and adjust the learning content accordingly. For example, if a user is falling behind in a particular area, the system can adjust the scenario to focus on that area. Conversely, if a user is progressing quickly in a particular area, it can offer a more challenging scenario. Furthermore, if a user has been learning for a certain period, the system can offer a scenario that rewards their efforts. By monitoring the user's learning progress in real time and adjusting the learning content accordingly, the system can provide a more effective learning experience.

[0116] The following briefly describes the processing flow for example form 2.

[0117] Step 1: The reception desk receives the user's specification of the language and field they wish to learn. For example, if a user wants to learn business English, the reception desk can receive specifications such as "English" and "Business." The reception desk saves the language and field specified by the user to the database and passes it to the generation desk. Step 2: The generation unit generates conversation scenarios based on the specified language and field. The generation unit uses generative AI to generate conversation scenarios based on the specified language and field. For example, in the case of business conversations, the generation unit can generate meeting scenarios and presentation scenarios. Step 3: The speech recognition unit converts the user's voice into text. The speech recognition unit can convert what the user says into text in real time. For example, if the user says, "I want to talk about the progress of the meeting," the speech recognition unit will convert that into text. Step 4: The feedback unit analyzes the converted text and generates appropriate feedback and questions. The feedback unit uses a generation AI to analyze the converted text and generate appropriate feedback and questions. For example, if a user says, "I want to talk about the meeting's progress," the feedback unit can generate a question such as, "What specific progress are you thinking of?"

[0118] The specific processing unit 290 transmits the result of the specific processing to the smart device 14. In the smart device 14, the control unit 46A causes the output device 40 to output the result of the specific processing. The microphone 38B acquires audio indicating user input for the result of the specific processing. The control unit 46A transmits the audio data indicating user input acquired by the microphone 38B to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the audio data.

[0119] Data generation model 58 is a form of so-called generative AI (Artificial Intelligence). An example of data generation model 58 is ChatGPT (registered trademark) (Internet search).<URL: https: / / openai.com / blog / chatgpt> Examples of generative AI include text generation AI, image generation AI, and multimodal generation AI. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 is input with prompts containing instructions, and with inference data such as audio data representing speech, text data representing text, and image data representing images (e.g., still image data or video data). The data generation model 58 infers from the input inference data according to the instructions indicated by the prompts, and outputs the inference result in one or more data formats from audio data, text data, and image data. The data generation model 58 includes, for example, text generation AI, image generation AI, and multimodal generation AI. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization. The specific processing unit 290 performs the specific processing described above using the data generation model 58. The data generation model 58 may be a fine-tuned model that outputs inference results from prompts that do not contain instructions, in which case the data generation model 58 can output inference results from prompts that do not contain instructions. In the data processing device 12, etc., there are multiple types of data generation models 58, and the data generation model 58 includes AI other than generative AI. AI other than generative AI includes, for example, linear regression, logistic regression, decision trees, random forests, support vector machines (SVMs), k-means clustering, convolutional neural networks (CNNs), recurrent neural networks (RNNs), generative adversarial networks (GANs), or naive Bayes, and can perform various processes, but is not limited to these examples. Also, the AI ​​may be an AI agent. Furthermore, when the processing of each of the above parts is performed by the AI, the processing may be performed by the AI ​​in part or in whole, but is not limited to this example.Furthermore, processing performed by AI, including generative AI, may be replaced with rule-based processing, and rule-based processing may be replaced with processing performed by AI, including generative AI.

[0120] Furthermore, the processing performed by the data processing system 10 described above is carried out by the specific processing unit 290 of the data processing device 12 or the control unit 46A of the smart device 14, but it may also be carried out by the specific processing unit 290 of the data processing device 12 and the control unit 46A of the smart device 14. In addition, the specific processing unit 290 of the data processing device 12 acquires or collects information necessary for processing from the smart device 14 or an external device, and the smart device 14 acquires or collects information necessary for processing from the data processing device 12 or an external device.

[0121] Each of the multiple elements described above, including the reception unit, generation unit, speech recognition unit, feedback unit, and progress management unit, is implemented in at least one of the smart device 14 and the data processing unit 12. For example, the reception unit is implemented by the control unit 46A of the smart device 14, where the user specifies the language and field they wish to learn. The generation unit is implemented by the specific processing unit 290 of the data processing unit 12, where a generation AI is used to generate a conversation scenario. The speech recognition unit is implemented by the control unit 46A of the smart device 14, where the user's speech is converted into text. The feedback unit is implemented by the specific processing unit 290 of the data processing unit 12, where the converted text is analyzed to generate feedback and questions. The progress management unit is implemented by the specific processing unit 290 of the data processing unit 12, where the user's progress is managed and the learning history is recorded. The correspondence between each unit and the device or control unit is not limited to the example described above and can be modified in various ways.

[0122] [Second Embodiment] Figure 3 shows an example of the configuration of the data processing system 210 according to the second embodiment.

[0123] As shown in Figure 3, the data processing system 210 includes a data processing device 12 and smart glasses 214. An example of the data processing device 12 is a server.

[0124] The data processing device 12 comprises a computer 22, a database 24, and a communication interface 26. The computer 22 comprises a processor 28, RAM 30, and storage 32. The processor 28, RAM 30, and storage 32 are connected to a bus 34. The database 24 and the communication interface 26 are also connected to the bus 34. The communication interface 26 is connected to a network 54. An example of the network 54 is a WAN and / or LAN.

[0125] The smart glasses 214 include a computer 36, a microphone 238, a speaker 240, a camera 42, and a communication interface 44. The computer 36 includes a processor 46, RAM 48, and storage 50. The processor 46, RAM 48, and storage 50 are connected to a bus 52. The microphone 238, speaker 240, and camera 42 are also connected to the bus 52.

[0126] The microphone 238 receives voice signals from the user and accepts instructions from the user. The microphone 238 captures the voice signals from the user, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio according to the instructions from the processor 46.

[0127] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an image sensor such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, which captures images of the area around the user (for example, an imaging range defined by a field of view equivalent to the field of vision of a typical healthy person).

[0128] Communication interface 44 is connected to network 54. Communication interfaces 44 and 26 are responsible for the exchange of various information between processor 46 and processor 28 via network 54. The exchange of various information between processor 46 and processor 28 using communication interfaces 44 and 26 is performed in a secure manner.

[0129] Figure 4 shows an example of the main functions of the data processing device 12 and the smart glasses 214. As shown in Figure 4, the data processing device 12 performs specific processing by the processor 28. The storage 32 stores the specific processing program 56.

[0130] The processor 28 reads a specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific processing is realized by the processor 28 acting as a specific processing unit 290 according to the specific processing program 56 executed on the RAM 30.

[0131] Storage 32 stores the data generation model 58 and the emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290. The identification processing unit 290 can estimate the user's emotions using the emotion identification model 59 and perform identification processing using the user's emotions. The emotion estimation function (emotion identification function) using the emotion identification model 59 performs various estimations and predictions regarding the user's emotions, including but not limited to these examples. Furthermore, emotion estimation and prediction also include, for example, emotion analysis.

[0132] In the smart glasses 214, specific processing is performed by the processor 46. The storage 50 stores a specific processing program 60. The processor 46 reads the specific processing program 60 from the storage 50 and executes the read specific processing program 60 on the RAM 48. The specific processing is realized by the processor 46 acting as a control unit 46A according to the specific processing program 60 executed on the RAM 48. The smart glasses 214 also have a data generation model 58 and an emotion identification model 59, similar to the data generation model and emotion identification model 59, and can perform processing similar to that of the specific processing unit 290 using these models.

[0133] Furthermore, other devices besides the data processing device 12 may also have the data generation model 58. For example, a server device may have the data generation model 58. In this case, the data processing device 12 obtains processing results (such as prediction results) using the data generation model 58 by communicating with the server device that has the data generation model 58. Also, the data processing device 12 may be a server device or a terminal device owned by the user (for example, a mobile phone, robot, home appliance, etc.).

[0134] The specific processing unit 290 transmits the result of the specific processing to the smart glasses 214. In the smart glasses 214, the control unit 46A causes the speaker 240 to output the result of the specific processing. The microphone 238 acquires audio indicating user input for the result of the specific processing. The control unit 46A transmits the audio data indicating user input acquired by the microphone 238 to the data processing unit 12. In the data processing unit 12, the specific processing unit 290 acquires the audio data.

[0135] The data generation model 58 is a so-called generative AI. An example of a data generation model 58 is a generative AI such as ChatGPT. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 is input with prompts containing instructions, and inference data such as audio data representing speech, text data representing text, and image data representing images (e.g., still image data or video data). The data generation model 58 infers from the input inference data according to the instructions indicated by the prompts, and outputs the inference result in one or more data formats such as audio data, text data, and image data. The data generation model 58 includes, for example, text generation AI, image generation AI, and multimodal generation AI. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization. The specific processing unit 290 performs the specific processing described above using the data generation model 58. The data generation model 58 may be a fine-tuned model that outputs inference results from prompts that do not contain instructions, in which case the data generation model 58 can output inference results from prompts that do not contain instructions. In the data processing device 12, etc., there are multiple types of data generation models 58, and the data generation model 58 includes AI other than generative AI. AI other than generative AI includes, for example, linear regression, logistic regression, decision trees, random forests, support vector machines (SVM), k-means clustering, convolutional neural networks (CNN), recurrent neural networks (RNN), generative adversarial networks (GAN), or naive Bayes, and can perform various processes, but is not limited to these examples. Also, the AI ​​may be an AI agent. Furthermore, when the processing of each part described above is performed by the AI, the processing may be performed by the AI ​​in part or in whole, but is not limited to this example. Also, processing performed by an AI including a generative AI may be replaced by rule-based processing, and rule-based processing may be replaced by processing performed by an AI including a generative AI.

[0136] The data processing system 210 according to the second embodiment performs the same processing as the data processing system 10 according to the first embodiment. The processing by the data processing system 210 is performed by the specific processing unit 290 of the data processing device 12 or the control unit 46A of the smart glasses 214, but it may also be performed by the specific processing unit 290 of the data processing device 12 and the control unit 46A of the smart glasses 214. In addition, the specific processing unit 290 of the data processing device 12 acquires or collects information necessary for processing from the smart glasses 214 or an external device, and the smart glasses 214 acquires or collects information necessary for processing from the data processing device 12 or an external device.

[0137] Each of the multiple elements described above, including the reception unit, generation unit, speech recognition unit, feedback unit, and progress management unit, is implemented in at least one of the smart glasses 214 and the data processing unit 12. For example, the reception unit is implemented by the control unit 46A of the smart glasses 214, where the user specifies the language and field they wish to learn. The generation unit is implemented by the specific processing unit 290 of the data processing unit 12, where a generation AI is used to generate a conversation scenario. The speech recognition unit is implemented by the control unit 46A of the smart glasses 214, where the user's voice is converted into text. The feedback unit is implemented by the specific processing unit 290 of the data processing unit 12, where the converted text is analyzed to generate feedback and questions. The progress management unit is implemented by the specific processing unit 290 of the data processing unit 12, where the user's progress is managed and the learning history is recorded. The correspondence between each unit and the device or control unit is not limited to the example described above and can be modified in various ways.

[0138] [Third Embodiment] Figure 5 shows an example of the configuration of the data processing system 310 according to the third embodiment.

[0139] As shown in Figure 5, the data processing system 310 includes a data processing device 12 and a headset terminal 314. An example of the data processing device 12 is a server.

[0140] The data processing device 12 comprises a computer 22, a database 24, and a communication interface 26. The computer 22 comprises a processor 28, RAM 30, and storage 32. The processor 28, RAM 30, and storage 32 are connected to a bus 34. The database 24 and the communication interface 26 are also connected to the bus 34. The communication interface 26 is connected to a network 54. An example of the network 54 is a WAN and / or LAN.

[0141] The headset terminal 314 includes a computer 36, a microphone 238, a speaker 240, a camera 42, a communication interface 44, and a display 343. The computer 36 includes a processor 46, RAM 48, and storage 50. The processor 46, RAM 48, and storage 50 are connected to a bus 52. The microphone 238, speaker 240, camera 42, and display 343 are also connected to the bus 52.

[0142] The microphone 238 receives voice signals from the user and accepts instructions from the user. The microphone 238 captures the voice signals from the user, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio according to the instructions from the processor 46.

[0143] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an image sensor such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, which captures images of the area around the user (for example, an imaging range defined by a field of view equivalent to the field of vision of a typical healthy person).

[0144] Communication interface 44 is connected to network 54. Communication interfaces 44 and 26 are responsible for the exchange of various information between processor 46 and processor 28 via network 54. The exchange of various information between processor 46 and processor 28 using communication interfaces 44 and 26 is performed in a secure manner.

[0145] Figure 6 shows an example of the main functions of the data processing device 12 and the headset terminal 314. As shown in Figure 6, the data processing device 12 performs specific processing using the processor 28. The storage 32 stores the specific processing program 56.

[0146] The processor 28 reads a specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific processing is realized by the processor 28 acting as a specific processing unit 290 according to the specific processing program 56 executed on the RAM 30.

[0147] Storage 32 stores the data generation model 58 and the emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290. The identification processing unit 290 can estimate the user's emotions using the emotion identification model 59 and perform identification processing using the user's emotions. The emotion estimation function (emotion identification function) using the emotion identification model 59 performs various estimations and predictions regarding the user's emotions, including but not limited to these examples. Furthermore, emotion estimation and prediction also include, for example, emotion analysis.

[0148] In the headset terminal 314, specific processing is performed by the processor 46. The storage 50 stores a specific program 60. The processor 46 reads the specific program 60 from the storage 50 and executes the read specific program 60 on the RAM 48. The specific processing is realized by the processor 46 acting as a control unit 46A according to the specific program 60 executed on the RAM 48. The headset terminal 314 also has a data generation model 58 and an emotion identification model 59, similar to the data generation model and emotion identification model 59, and can perform processing similar to that of the specific processing unit 290 using these models.

[0149] Furthermore, other devices besides the data processing device 12 may also have the data generation model 58. For example, a server device may have the data generation model 58. In this case, the data processing device 12 obtains processing results (such as prediction results) using the data generation model 58 by communicating with the server device that has the data generation model 58. Also, the data processing device 12 may be a server device or a terminal device owned by the user (for example, a mobile phone, robot, home appliance, etc.).

[0150] The specific processing unit 290 transmits the result of the specific processing to the headset terminal 314. In the headset terminal 314, the control unit 46A causes the speaker 240 and display 343 to output the result of the specific processing. The microphone 238 acquires audio indicating user input for the result of the specific processing. The control unit 46A transmits the audio data indicating user input acquired by the microphone 238 to the data processing unit 12. In the data processing unit 12, the specific processing unit 290 acquires the audio data.

[0151] The data generation model 58 is a so-called generative AI. An example of a data generation model 58 is a generative AI such as ChatGPT. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 is input with prompts containing instructions, and inference data such as audio data representing speech, text data representing text, and image data representing images (e.g., still image data or video data). The data generation model 58 infers from the input inference data according to the instructions indicated by the prompts, and outputs the inference result in one or more data formats such as audio data, text data, and image data. The data generation model 58 includes, for example, text generation AI, image generation AI, and multimodal generation AI. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization. The specific processing unit 290 performs the specific processing described above using the data generation model 58. The data generation model 58 may be a fine-tuned model that outputs inference results from prompts that do not contain instructions, in which case the data generation model 58 can output inference results from prompts that do not contain instructions. In the data processing device 12, etc., there are multiple types of data generation models 58, and the data generation model 58 includes AI other than generative AI. AI other than generative AI includes, for example, linear regression, logistic regression, decision trees, random forests, support vector machines (SVM), k-means clustering, convolutional neural networks (CNN), recurrent neural networks (RNN), generative adversarial networks (GAN), or naive Bayes, and can perform various processes, but is not limited to these examples. Also, the AI ​​may be an AI agent. Furthermore, when the processing of each part described above is performed by the AI, the processing may be performed by the AI ​​in part or in whole, but is not limited to this example. Also, processing performed by an AI including a generative AI may be replaced by rule-based processing, and rule-based processing may be replaced by processing performed by an AI including a generative AI.

[0152] The data processing system 310 according to the third embodiment performs the same processing as the data processing system 10 according to the first embodiment. The processing by the data processing system 310 is performed by the specific processing unit 290 of the data processing device 12 or the control unit 46A of the headset terminal 314, but may also be performed by the specific processing unit 290 of the data processing device 12 and the control unit 46A of the headset terminal 314. In addition, the specific processing unit 290 of the data processing device 12 acquires or collects information necessary for processing from the headset terminal 314 or an external device, and the headset terminal 314 acquires or collects information necessary for processing from the data processing device 12 or an external device.

[0153] Each of the multiple elements described above, including the reception unit, generation unit, speech recognition unit, feedback unit, and progress management unit, is implemented in at least one of the headset terminal 314 and the data processing unit 12. For example, the reception unit is implemented by the control unit 46A of the headset terminal 314, where the user specifies the language and field they wish to learn. The generation unit is implemented by the specific processing unit 290 of the data processing unit 12, where a generation AI is used to generate a conversation scenario. The speech recognition unit is implemented by the control unit 46A of the headset terminal 314, where the user's voice is converted into text. The feedback unit is implemented by the specific processing unit 290 of the data processing unit 12, where the converted text is analyzed to generate feedback and questions. The progress management unit is implemented by the specific processing unit 290 of the data processing unit 12, where the user's progress is managed and the learning history is recorded. The correspondence between each unit and the device or control unit is not limited to the example described above and can be modified in various ways.

[0154] [Fourth Embodiment] Figure 7 shows an example of the configuration of the data processing system 410 according to the fourth embodiment.

[0155] As shown in Figure 7, the data processing system 410 includes a data processing device 12 and a robot 414. An example of the data processing device 12 is a server.

[0156] The data processing device 12 comprises a computer 22, a database 24, and a communication interface 26. The computer 22 comprises a processor 28, RAM 30, and storage 32. The processor 28, RAM 30, and storage 32 are connected to a bus 34. The database 24 and the communication interface 26 are also connected to the bus 34. The communication interface 26 is connected to a network 54. An example of the network 54 is a WAN and / or LAN.

[0157] The robot 414 includes a computer 36, a microphone 238, a speaker 240, a camera 42, a communication interface 44, and a controlled object 443. The computer 36 includes a processor 46, RAM 48, and storage 50. The processor 46, RAM 48, and storage 50 are connected to a bus 52. The microphone 238, speaker 240, camera 42, and controlled object 443 are also connected to the bus 52.

[0158] The microphone 238 receives voice signals from the user and accepts instructions from the user. The microphone 238 captures the voice signals from the user, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio according to the instructions from the processor 46.

[0159] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an image sensor such as a CMOS image sensor or CCD image sensor, which captures images of the area around the user (for example, an imaging range defined by a field of view equivalent to the field of vision of a typical healthy person).

[0160] Communication interface 44 is connected to network 54. Communication interfaces 44 and 26 are responsible for the exchange of various information between processor 46 and processor 28 via network 54. The exchange of various information between processor 46 and processor 28 using communication interfaces 44 and 26 is performed in a secure manner.

[0161] The controlled object 443 includes a display device, LEDs in the eyes, and motors that drive the arms, hands, and feet. The posture and gestures of the robot 414 are controlled by controlling the motors of the arms, hands, and feet. Some of the robot 414's emotions can be expressed by controlling these motors. The robot 414's facial expressions can also be expressed by controlling the illumination state of the LEDs in its eyes.

[0162] Figure 8 shows an example of the main functions of the data processing device 12 and the robot 414. As shown in Figure 8, the data processing device 12 performs specific processing using the processor 28. The storage 32 stores the specific processing program 56.

[0163] The processor 28 reads a specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific processing is realized by the processor 28 acting as a specific processing unit 290 according to the specific processing program 56 executed on the RAM 30.

[0164] Storage 32 stores the data generation model 58 and the emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290. The identification processing unit 290 can estimate the user's emotions using the emotion identification model 59 and perform identification processing using the user's emotions. The emotion estimation function (emotion identification function) using the emotion identification model 59 performs various estimations and predictions regarding the user's emotions, including but not limited to these examples. Furthermore, emotion estimation and prediction also include, for example, emotion analysis.

[0165] In robot 414, specific processing is performed by processor 46. A specific program 60 is stored in storage 50. Processor 46 reads the specific program 60 from storage 50 and executes it on RAM 48. The specific processing is achieved by processor 46 acting as a control unit 46A according to the specific program 60 executed on RAM 48. Robot 414 also has data generation model 58 and emotion identification model 59, similar to those of the robot, and can perform processing similar to that of the specific processing unit 290 using these models.

[0166] Furthermore, other devices besides the data processing device 12 may also have the data generation model 58. For example, a server device may have the data generation model 58. In this case, the data processing device 12 obtains processing results (such as prediction results) using the data generation model 58 by communicating with the server device that has the data generation model 58. Also, the data processing device 12 may be a server device or a terminal device owned by the user (for example, a mobile phone, robot, home appliance, etc.).

[0167] The specific processing unit 290 transmits the result of the specific processing to the robot 414. In the robot 414, the control unit 46A causes the speaker 240 and the controlled object 443 to output the result of the specific processing. The microphone 238 acquires audio indicating user input for the result of the specific processing. The control unit 46A transmits the audio data indicating user input acquired by the microphone 238 to the data processing unit 12. In the data processing unit 12, the specific processing unit 290 acquires the audio data.

[0168] The data generation model 58 is a so-called generative AI. An example of a data generation model 58 is a generative AI such as ChatGPT. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 is input with prompts containing instructions, and inference data such as audio data representing speech, text data representing text, and image data representing images (e.g., still image data or video data). The data generation model 58 infers from the input inference data according to the instructions indicated by the prompts, and outputs the inference result in one or more data formats such as audio data, text data, and image data. The data generation model 58 includes, for example, text generation AI, image generation AI, and multimodal generation AI. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization. The specific processing unit 290 performs the specific processing described above using the data generation model 58. The data generation model 58 may be a fine-tuned model that outputs inference results from prompts that do not contain instructions, in which case the data generation model 58 can output inference results from prompts that do not contain instructions. In the data processing device 12, etc., there are multiple types of data generation models 58, and the data generation model 58 includes AI other than generative AI. AI other than generative AI includes, for example, linear regression, logistic regression, decision trees, random forests, support vector machines (SVM), k-means clustering, convolutional neural networks (CNN), recurrent neural networks (RNN), generative adversarial networks (GAN), or naive Bayes, and can perform various processes, but is not limited to these examples. Also, the AI ​​may be an AI agent. Furthermore, when the processing of each part described above is performed by the AI, the processing may be performed by the AI ​​in part or in whole, but is not limited to this example. Also, processing performed by an AI including a generative AI may be replaced by rule-based processing, and rule-based processing may be replaced by processing performed by an AI including a generative AI.

[0169] The data processing system 410 according to the fourth embodiment performs the same processing as the data processing system 10 according to the first embodiment. The processing by the data processing system 410 is performed by the specific processing unit 290 of the data processing device 12 or the control unit 46A of the robot 414, but it may also be performed by the specific processing unit 290 of the data processing device 12 and the control unit 46A of the robot 414. In addition, the specific processing unit 290 of the data processing device 12 acquires or collects information necessary for processing from the robot 414 or an external device, and the robot 414 acquires or collects information necessary for processing from the data processing device 12 or an external device.

[0170] Each of the multiple elements described above, including the reception unit, generation unit, speech recognition unit, feedback unit, and progress management unit, is implemented in at least one of the robot 414 and the data processing unit 12. For example, the reception unit is implemented by the control unit 46A of the robot 414, where the user specifies the language and field they wish to learn. The generation unit is implemented by the specific processing unit 290 of the data processing unit 12, where a conversation scenario is generated using a generation AI. The speech recognition unit is implemented by the control unit 46A of the robot 414, where the user's speech is converted into text. The feedback unit is implemented by the specific processing unit 290 of the data processing unit 12, where the converted text is analyzed to generate feedback and questions. The progress management unit is implemented by the specific processing unit 290 of the data processing unit 12, where the user's progress is managed and the learning history is recorded. The correspondence between each unit and the device or control unit is not limited to the example described above and can be modified in various ways.

[0171] Furthermore, the emotion identification model 59, acting as an emotion engine, may determine the user's emotion according to a specific mapping. Specifically, the emotion identification model 59 may determine the user's emotion according to a specific mapping, which is an emotion map (see Figure 9). Similarly, the emotion identification model 59 may also determine the robot's emotion, and the identification processing unit 290 may perform identification processing using the robot's emotion.

[0172] Figure 9 shows the emotion map 400, in which multiple emotions are mapped. In the emotion map 400, emotions are arranged in concentric circles radiating from the center. The closer to the center of the concentric circles, the more primitive the emotions are located. Further out of the concentric circles, emotions representing states and actions arising from mental states are located. Emotion is a concept that includes feelings and mental states. On the left side of the concentric circles, emotions that are generally generated from reactions occurring in the brain are located. On the right side of the concentric circles, emotions that are generally induced by situational judgment are located. Above and below the concentric circles, emotions that are generally generated from reactions occurring in the brain and induced by situational judgment are located. In addition, the emotion of "pleasure" is located on the upper side of the concentric circles, and the emotion of "displeasure" is located on the lower side. Thus, in the emotion map 400, multiple emotions are mapped based on the structure in which emotions arise, and emotions that are likely to occur simultaneously are mapped close together.

[0173] These emotions are distributed at the 3 o'clock position on the Emotion Map 400, and usually fluctuate between feelings of security and anxiety. In the right half of the Emotion Map 400, situational awareness takes precedence over internal feelings, resulting in a calm impression.

[0174] The inside of the Emotion Map 400 represents inner thoughts, while the outside represents actions. Therefore, the further you go from the outside of the Emotion Map 400, the more visible (expressed in actions) your emotions become.

[0175] Here, human emotions are based on various balances, such as posture and blood sugar levels. When these balances deviate from the ideal, it results in discomfort, and when they approach the ideal, it results in pleasure. Similarly, in robots, cars, and motorcycles, emotions can be created based on various balances, such as posture and battery level. When these balances deviate from the ideal, it results in discomfort, and when they approach the ideal, it results in pleasure. The emotion map can be generated based, for example, on Dr. Mitsuyoshi's emotion map (Research on a system for analyzing brain physiological signals of speech emotion recognition and emotion, Tokushima University, doctoral dissertation: https: / / ci.nii.ac.jp / naid / 500000375379). The left half of the emotion map contains emotions belonging to a region called "response," where sensation is dominant. The right half of the emotion map contains emotions belonging to a region called "situation," where situational awareness is dominant.

[0176] The emotion map defines two emotions that promote learning. One is the emotion around the middle of the negative "repentance" and "reflection" on the situation side. In other words, it is when the robot experiences negative emotions such as "I never want to feel this way again" or "I don't want to be scolded again." The other is the emotion around the positive "desire" on the reaction side. In other words, it is when the robot has positive feelings such as "I want more" or "I want to know more."

[0177] The emotion identification model 59 inputs user input into a pre-trained neural network, obtains emotion values ​​representing each emotion shown in the emotion map 400, and determines the user's emotion. This neural network is pre-trained based on multiple training data sets, which are combinations of user input and emotion values ​​representing each emotion shown in the emotion map 400. Furthermore, this neural network is trained so that emotions located close together have similar values, as shown in the emotion map 900 in Figure 10. Figure 10 shows an example where multiple emotions such as "reassured," "calm," and "confident" have similar emotion values.

[0178] In the above embodiment, an example was given in which a specific process is performed by a single computer 22. However, the technology of this disclosure is not limited thereto, and a distributed processing method for the specific process may be used, which includes computer 22 and multiple other computers.

[0179] In the above embodiment, an example was given in which the specific processing program 56 is stored in the storage 32, but the technology of this disclosure is not limited thereto. For example, the specific processing program 56 may be stored in a portable, computer-readable, non-temporary storage medium such as a USB (Universal Serial Bus) memory. The specific processing program 56 stored in the non-temporary storage medium is installed in the computer 22 of the data processing device 12. The processor 28 executes specific processing according to the specific processing program 56.

[0180] 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.

[0181] Furthermore, it is not necessary to store the entirety of the specific processing program 56 in a storage device such as a server connected to the data processing device 12 via the network 54, or to store the entirety of the specific processing program 56 in the storage 32; it is acceptable to store only a portion of the specific processing program 56.

[0182] The following types of processors can be used as hardware resources to perform specific processing. Examples of processors include a CPU, a general-purpose processor that functions as a hardware resource to perform specific processing by executing software, i.e., a program. Other examples of processors include dedicated electrical circuits, such as FPGAs (Field-Programmable Gate Arrays), PLDs (Programmable Logic Devices), or ASICs (Application Specific Integrated Circuits), which have circuit configurations specifically designed to perform specific processing. All of these processors have built-in or connected memory, and all of them perform specific processing by using memory.

[0183] The hardware resource that performs a specific process may consist of one of these various processors, or it may consist of a combination of two or more processors of the same or different types (for example, a combination of multiple FPGAs, or a combination of a CPU and an FPGA). Alternatively, the hardware resource that performs a specific process may consist of a single processor.

[0184] Examples of configurations using a single processor include, firstly, a configuration in which one or more CPUs and software are combined to form a single processor, and this processor functions as a hardware resource that performs a specific process. Secondly, there is a configuration using a processor that realizes the functions of the entire system, including multiple hardware resources that perform a specific process, on a single IC chip, as exemplified by SoCs (System-on-a-chip). In this way, a specific process is realized using one or more of the above types of processors as hardware resources.

[0185] Furthermore, the hardware structure of these various processors can more specifically utilize electrical circuits that combine circuit elements such as semiconductor devices. Also, the specific processing described above is merely an example. Therefore, it goes without saying that unnecessary steps can be deleted, new steps added, or the processing order rearranged, as long as it does not deviate from the main purpose.

[0186] Furthermore, although the above-described examples were divided into four embodiments, some or all of these embodiments may be combined. Also, the smart device 14, smart glasses 214, headset terminal 314, and robot 414 are just examples, and they may be combined, or other devices may be used. Also, although the above-described examples were divided into two embodiments, Embodiment 1 and Embodiment 2, these may be combined.

[0187] The descriptions and illustrations presented above are detailed explanations of the technical aspects of this disclosure and are merely examples of the technical aspects. For example, the above descriptions of the structure, function, operation, and effect are examples of the structure, function, operation, and effect of the technical aspects of this disclosure. Therefore, it goes without saying that you may delete unnecessary parts, add new elements, or replace elements in the descriptions and illustrations presented above, as long as you do not deviate from the essence of the technical aspects of this disclosure. Furthermore, in order to avoid confusion and facilitate understanding of the technical aspects of this disclosure, explanations of common technical knowledge and other things that do not require special explanation to enable the implementation of the technical aspects of this disclosure have been omitted from the descriptions and illustrations presented above.

[0188] All documents, patent applications, and technical standards described herein are incorporated by reference to the same extent as if each individual document, patent application, and technical standard were specifically and individually noted to be incorporated by reference.

[0189] (Note 1) A reception desk that accepts requests for the language and field of study you wish to learn, A generation unit generates a conversation scenario based on the information received by the reception unit, A speech recognition unit that converts the user's voice into text, The system includes a feedback unit that analyzes the text converted by the speech recognition unit and generates feedback or questions. A system characterized by the following features. (Note 2) The generating unit is Generate conversation scenarios based on specified language and field. The system described in Appendix 1, characterized by the features described herein. (Note 3) The aforementioned speech recognition unit, Converts user speech to text in real time. The system described in Appendix 1, characterized by the features described herein. (Note 4) The aforementioned feedback unit is The system analyzes the converted text and generates appropriate feedback and questions. The system described in Appendix 1, characterized by the features described herein. (Note 5) The generating unit is Generate multilingual conversation scenarios The system described in Appendix 1, characterized by the features described herein. (Note 6) It includes a progress management unit that manages the user's progress and records their learning history. The system described in Appendix 1, characterized by the features described herein. (Note 7) The aforementioned reception unit is It estimates the user's emotions and suggests learning languages ​​and fields based on those estimated emotions. The system described in Appendix 1, characterized by the features described herein. (Note 8) The aforementioned reception unit is It analyzes the user's past learning history and suggests the optimal combination of language and subject area. The system described in Appendix 1, characterized by the features described herein. (Note 9) The aforementioned reception unit is When specifying the learning language and field, filtering is performed based on the user's current learning progress. The system described in Appendix 1, characterized by the features described herein. (Note 10) The aforementioned reception unit is It estimates the user's emotions and determines the priority of learning languages ​​and subjects based on the estimated user emotions. The system described in Appendix 1, characterized by the features described herein. (Note 11) The aforementioned reception unit is When specifying learning languages ​​and fields, the system suggests highly relevant languages ​​and fields considering the user's geographical location. The system described in Appendix 1, characterized by the features described herein. (Note 12) The aforementioned reception unit is When specifying the learning language and field, the system analyzes the user's social media activity and suggests relevant languages ​​and fields. The system described in Appendix 1, characterized by the features described herein. (Note 13) The generating unit is It estimates the user's emotions and adjusts the way the conversation scenario is presented based on those estimated emotions. The system described in Appendix 1, characterized by the features described herein. (Note 14) The generating unit is When generating conversation scenarios, the system references the user's past learning history to generate the optimal scenario. The system described in Appendix 1, characterized by the features described herein. (Note 15) The generating unit is When generating conversation scenarios, adjust the difficulty level of the scenarios based on the user's current learning progress. The system described in Appendix 1, characterized by the features described herein. (Note 16) The generating unit is It estimates the user's emotions and adjusts the length of the conversation scenario based on the estimated user emotions. The system described in Appendix 1, characterized by the features described herein. (Note 17) The generating unit is When generating conversation scenarios, the system considers the user's geographical location to generate highly relevant scenarios. The system described in Appendix 1, characterized by the features described herein. (Note 18) The generating unit is When generating conversation scenarios, the system analyzes the user's social media activity and generates relevant scenarios. The system described in Appendix 1, characterized by the features described herein. (Note 19) The aforementioned speech recognition unit, It estimates the user's emotions and adjusts the accuracy of speech recognition based on the estimated emotions. The system described in Appendix 1, characterized by the features described herein. (Note 20) The aforementioned speech recognition unit, During speech recognition, the system refers to the user's past speech history to apply the most suitable recognition algorithm. The system described in Appendix 1, characterized by the features described herein. (Note 21) The aforementioned speech recognition unit, During speech recognition, the difficulty level of recognition is adjusted based on the user's current learning progress. The system described in Appendix 1, characterized by the features described herein. (Note 22) The aforementioned speech recognition unit, It estimates the user's emotions and determines the priority of speech recognition based on the estimated emotions. The system described in Appendix 1, characterized by the features described herein. (Note 23) The aforementioned speech recognition unit, During speech recognition, the system applies a highly relevant recognition algorithm that takes into account the user's geographical location. The system described in Appendix 1, characterized by the features described herein. (Note 24) The aforementioned speech recognition unit, During speech recognition, the system analyzes the user's social media activity and applies relevant recognition algorithms. The system described in Appendix 1, characterized by the features described herein. (Note 25) The aforementioned feedback unit is It estimates the user's emotions and adjusts how feedback is expressed based on those estimated emotions. The system described in Appendix 1, characterized by the features described herein. (Note 26) The aforementioned feedback unit is When generating feedback, the system references the user's past learning history to generate the most appropriate feedback. The system described in Appendix 1, characterized by the features described herein. (Note 27) The aforementioned feedback unit is When generating feedback, adjust the content of the feedback based on the user's current learning progress. The system described in Appendix 1, characterized by the features described herein. (Note 28) The aforementioned feedback unit is It estimates the user's emotions and prioritizes feedback based on those estimated emotions. The system described in Appendix 1, characterized by the features described herein. (Note 29) The aforementioned feedback unit is When generating feedback, the system considers the user's geographical location to generate more relevant feedback. The system described in Appendix 1, characterized by the features described herein. (Note 30) The aforementioned feedback unit is When generating feedback, the system analyzes the user's social media activity and generates relevant feedback. The system described in Appendix 1, characterized by the features described herein. (Note 31) The aforementioned progress management department, It estimates the user's emotions and adjusts the learning progress management method based on the estimated user emotions. The system described in Appendix 1, characterized by the features described herein. (Note 32) The aforementioned progress management department, When managing learning progress, the system selects the optimal progress management method by referring to the user's past learning history. The system described in Appendix 1, characterized by the features described herein. (Note 33) The aforementioned progress management department, It estimates the user's emotions and determines the priority of the learning process based on the estimated user emotions. The system described in Appendix 1, characterized by the features described herein. (Note 34) The aforementioned progress management department, When managing learning progress, the optimal progress management method is selected by considering the user's geographical location. The system described in Appendix 1, characterized by the features described herein. [Explanation of symbols]

[0190] 10, 210, 310, 410 Data Processing Systems 12 Data Processing Devices 14 Smart Devices 214 Smart Glasses 314 Headset-type terminal 414 Robots

Claims

1. A reception desk that accepts requests for the language and field of study you wish to learn, A generation unit generates a conversation scenario based on the information received by the reception unit, A speech recognition unit that converts the user's voice into text, The system includes a feedback unit that analyzes the text converted by the speech recognition unit and generates feedback or questions. A system characterized by the following features.

2. The generating unit is Generate conversation scenarios based on specified language and field. The system according to feature 1.

3. The aforementioned speech recognition unit, Converts user speech to text in real time. The system according to feature 1.

4. The aforementioned feedback unit is The system analyzes the converted text and generates appropriate feedback and questions. The system according to feature 1.

5. The generating unit is Generate multilingual conversation scenarios The system according to feature 1.

6. It includes a progress management unit that manages the user's progress and records their learning history. The system according to feature 1.

7. The aforementioned reception unit is It estimates the user's emotions and suggests learning languages ​​and fields based on those estimated emotions. The system according to feature 1.

8. The aforementioned reception unit is It analyzes the user's past learning history and suggests the optimal combination of language and subject area. The system according to feature 1.

9. The aforementioned reception unit is When specifying the learning language and field, filtering is performed based on the user's current learning progress. The system according to feature 1.

10. The aforementioned reception unit is It estimates the user's emotions and determines the priority of learning languages ​​and subjects based on the estimated user emotions. The system according to feature 1.

Images