System

Abstract

To provide a system providing a proper teaching material according to a language skill of a user and providing a feedback of a pronunciation and a grammar in real-time.SOLUTION: A system according to an embodiment includes an evaluation unit, a providing unit, an interactive unit, a feedback unit, and an adjustment unit. The evaluation unit evaluates a language skill of a user. The providing unit provides a teaching material according to a level of the skill of the user on the basis of an evaluation result by the evaluation unit. The interactive unit uses the teaching material to interact with the user. The feedback unit provides a feedback relating to a pronunciation and a grammar in real-time on the basis of an interactive result by the interactive unit. The adjustment unit adjusts a pace and a content of learning on the basis of the progress of the user.SELECTED DRAWING: Figure 1

Description

[Technical field]

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

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

[0003] [Patent Document 1] JP 2022-180282 A Summary of the Invention [Problem to be solved by the invention]

[0004] Conventional techniques do not adequately provide appropriate learning materials based on a user's language skills, or provide real-time feedback on pronunciation and grammar, and there is room for improvement.

[0005] The system according to the embodiment aims to provide appropriate learning materials according to the user's language skills and to provide feedback on pronunciation and grammar in real time. [Means for solving the problem]

[0006] The system according to the embodiment includes an evaluation unit, a provision unit, a dialogue unit, a feedback unit, and an adjustment unit. The evaluation unit evaluates the language skills of a user. The provision unit provides learning materials according to the user's skill level based on the evaluation result by the evaluation unit. The dialogue unit dialogues with the user using the learning materials. The feedback unit provides feedback on pronunciation and grammar in real time based on the dialogue result by the dialogue unit. The adjustment unit adjusts the pace and content of learning based on the user's progress. Effect of the Invention

[0007] The system according to the embodiment can provide appropriate learning materials according to the user's language skills and provide feedback on pronunciation and grammar in real time. [Brief description of the drawings]

[0008] [Figure 1] 1 is a conceptual diagram showing an example of the configuration of a data processing system according to a first embodiment. [Diagram 2] 1 is a conceptual diagram showing an example of main functions of a data processing device and a smart device according to a first embodiment. FIG. [Diagram 3] FIG. 11 is a conceptual diagram showing an example of the configuration of a data processing system according to a second embodiment. [Figure 4] FIG. 11 is a conceptual diagram showing an example of main functions of a data processing device and smart glasses according to a second embodiment. [Diagram 5] FIG. 13 is a conceptual diagram showing an example of the configuration of a data processing system according to a third embodiment. [Figure 6] FIG. 11 is a conceptual diagram showing an example of main functions of a data processing device and a headset-type terminal according to a third embodiment. [Figure 7] FIG. 13 is a conceptual diagram showing an example of the configuration of a data processing system according to a fourth embodiment. [Figure 8] FIG. 13 is a conceptual diagram showing an example of main functions of a data processing device and a robot according to a fourth embodiment. [Figure 9] 1 shows an emotion map onto which multiple emotions are mapped. [Figure 10] 1 shows an emotion map onto which multiple emotions are mapped. DETAILED DESCRIPTION OF THE PREFERRED EMBODIMENTS

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

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

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

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

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

[0014] In the following embodiments, a communication I / F (Interface) with a code is an interface including a communication processor and an antenna. The communication I / F controls communication between multiple computers. An example of a communication standard applied to the communication I / F is a wireless communication standard including 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." In other words, "A and / or B" means that it may be only A, only B, or a combination of A and B. In addition, in this specification, the same idea as "A and / or B" is also applied when three or more things are expressed by connecting them with "and / or."

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

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

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

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

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

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

[0022] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 are responsible for transmitting and receiving various types of information between the processor 46 and the processor 28 via the network 54.

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

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

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

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

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

[0028] (Example 1) A system according to an embodiment of the present invention is a system for evaluating a user's language skills and providing learning materials at an appropriate level. The system includes an evaluation unit for evaluating the user's language skills, a provision unit for providing appropriate learning materials based on the evaluation results, a dialogue unit for dialogue with the user using the provided learning materials, a feedback unit for providing feedback on pronunciation and grammar in real time based on the dialogue results, and an adjustment unit for adjusting the pace and content of learning based on the user's progress. The evaluation unit analyzes the pronunciation, grammar, and vocabulary usage of the language spoken by the user to evaluate the language skills. The adjustment unit generates an individualized learning plan based on the evaluation results and the user's learning history. The feedback unit evaluates pronunciation using voice analysis technology and provides specific pronunciation guidance. In addition, the feedback unit provides feedback according to the user's emotional state, highlights grammatical errors in real time, and makes correction suggestions. The adjustment unit adjusts the learning pace based on the user's physiological data and adjusts the learning materials in real time based on the feedback. Furthermore, the system includes a control unit for controlling smart home devices based on the evaluation results. The provision unit provides learning materials that allow the user to learn information about specific cultural events and holidays, and learning cultural backgrounds and daily conversations related to a specific region. This enables the system to support effective language learning by assessing the user's language skills, providing appropriate learning materials, providing interactive feedback, and adjusting the pace and content of learning.

[0029] A language learning system according to an embodiment includes an evaluation unit, a provision unit, a dialogue unit, a feedback unit, and an adjustment unit. The evaluation unit evaluates the language skills of a user. For example, the evaluation unit analyzes the pronunciation, grammar, and vocabulary usage of the language spoken by the user to evaluate the language skills. The evaluation unit analyzes the pronunciation of the user using a voice recognition technology and evaluates the accuracy of the grammar using a grammar analysis technology. The evaluation unit also analyzes the usage of vocabulary and evaluates the richness of the vocabulary. The provision unit provides teaching materials according to the skill level of the user based on the evaluation result by the evaluation unit. The provision unit provides, for example, text teaching materials, audio teaching materials, video teaching materials, interactive exercises, etc. The provision unit selects and provides appropriate teaching materials based on the evaluation result of the user. The dialogue unit uses the provided teaching materials to dialogue with the user. The dialogue unit performs, for example, voice dialogue, text dialogue, video dialogue, etc. The dialogue unit evaluates the accuracy of the pronunciation and grammar of the user in real time and provides feedback. The feedback unit provides feedback on pronunciation and grammar in real time based on the dialogue result by the dialogue unit. The feedback unit evaluates the user's pronunciation using voice analysis technology and provides specific pronunciation guidance. The feedback unit also highlights the user's grammatical errors in real time and provides correction suggestions. The adjustment unit adjusts the pace and content of learning based on the user's progress. The adjustment unit generates an individualized learning plan based on the evaluation result and the user's learning history. The adjustment unit adjusts the learning pace based on the user's physiological data and adjusts the learning materials in real time based on the feedback. As a result, the language learning system according to the embodiment can support effective language learning by evaluating the user's language skills, providing appropriate learning materials, providing feedback through dialogue, and adjusting the learning pace and content.

[0030] The evaluation unit evaluates the language skills of the user. For example, the evaluation unit analyzes the pronunciation, grammar, and vocabulary usage of the language spoken by the user to evaluate the language skills. Specifically, the evaluation unit uses a voice recognition technology to analyze the user's pronunciation, and uses a grammar analysis technology to evaluate the accuracy of the grammar. The voice recognition technology analyzes the user's pronunciation at the phoneme level and compares it with the pronunciation of a native speaker to evaluate the accuracy of the pronunciation. For example, when a user pronounces a specific word or phrase, the voice recognition system analyzes the voice data and evaluates the degree of phoneme agreement and the accuracy of intonation. The grammar analysis technology analyzes the text and voice data input by the user to detect grammatical errors. For example, it checks the subject and verb agreement, tense agreement, use of prepositions, etc. to evaluate the grammatical accuracy. Furthermore, the evaluation unit analyzes the usage of vocabulary and evaluates the richness of the vocabulary. The vocabulary analysis technology analyzes the types and frequency of words used by the user to evaluate the diversity and appropriateness of the vocabulary. For example, the evaluator evaluates how diverse the vocabulary a user uses when talking about a particular topic and whether that vocabulary is appropriate to the context. This allows the evaluator to evaluate the user's language skills from multiple angles and provide detailed feedback.

[0031] The providing unit provides teaching materials according to the skill level of the user based on the evaluation result by the evaluating unit. Specifically, text teaching materials, audio teaching materials, video teaching materials, interactive exercises, etc. are provided. The providing unit selects and provides appropriate teaching materials based on the evaluation result of the user. For example, if the user's pronunciation is inaccurate, audio teaching materials and video teaching materials for pronunciation practice are provided to enable the user to learn correct pronunciation. In addition, if there are many grammatical errors, text teaching materials and interactive exercises for learning the basics of grammar are provided. Furthermore, if the user's vocabulary is insufficient, a wordbook, flash cards, and vocabulary-based exercises for increasing vocabulary are provided. The providing unit can also customize the format and content of the teaching materials according to the user's learning style and preferences. For example, for a user who prefers visual learning, teaching materials that make heavy use of video teaching materials and infographics are provided, and for a user who prefers auditory learning, audio teaching materials and podcasts are provided. In this way, the providing unit can provide optimal teaching materials according to the individual needs of the user and support effective learning.

[0032] The dialogue unit uses the provided learning materials to have a dialogue with the user. Specifically, the dialogue unit performs voice dialogue, text dialogue, video dialogue, and the like. The dialogue unit evaluates the accuracy of the user's pronunciation and grammar in real time and provides feedback. For example, in voice dialogue, the dialogue unit analyzes words and phrases pronounced by the user and evaluates the accuracy of the pronunciation and the appropriateness of the intonation. If the user makes an incorrect pronunciation, the dialogue unit immediately presents the correct pronunciation and encourages the user to practice. In text dialogue, the dialogue unit analyzes sentences entered by the user and evaluates grammatical errors and the appropriateness of vocabulary. If the user makes a grammatical error, the dialogue unit highlights the error and presents the correct grammar. In video dialogue, the dialogue unit analyzes the content of speech, facial expressions, and gestures of the user and evaluates the overall communication skills. The dialogue unit provides appropriate feedback and supports practice so that the user can have a natural dialogue. Furthermore, the dialogue unit can record the user's dialogue history and track the progress. As a result, the dialogue unit can adjust the content and difficulty of the dialogue according to the user's progress in learning, and support effective learning.

[0033] The feedback unit provides feedback on pronunciation and grammar in real time based on the dialogue result by the dialogue unit. Specifically, the feedback unit evaluates the user's pronunciation using voice analysis technology and provides specific pronunciation guidance. For example, if the user mispronounces a particular word, the feedback unit points out the error and presents the correct pronunciation in voice or text. In addition, if the user makes a grammatical error, the feedback unit highlights the error and suggests a correction. For example, if the user makes a mistake in matching a subject and a verb, the feedback unit highlights that part and presents the correct grammar. In addition, the feedback unit can adjust the content and method of feedback according to the user's progress. For example, for a beginner user, the feedback unit focuses on teaching basic pronunciation and grammar, and for an advanced user, the feedback unit provides more advanced pronunciation and grammar guidance. In this way, the feedback unit can provide effective feedback according to the individual needs of the user and improve the quality of learning.

[0034] The adjustment unit adjusts the pace and content of the learning based on the user's progress. Specifically, an individualized learning plan is generated based on the evaluation results and the user's learning history. The adjustment unit adjusts the learning pace based on the user's physiological data and adjusts the learning materials in real time based on the feedback. For example, the adjustment unit monitors the user's heart rate and stress level and adjusts the learning load. If the user is tired, the adjustment unit slows down the learning pace and provides relaxing learning materials. Also, if the user is concentrating, the adjustment unit increases the learning pace and provides more difficult learning materials. Furthermore, the adjustment unit adjusts the learning content in real time based on the user's feedback. For example, if the user shows interest in a particular topic, additional learning materials related to that topic are provided. In this way, the adjustment unit can provide a flexible learning plan according to the user's individual needs and circumstances, and support effective learning.

[0035] The evaluation unit can analyze the pronunciation, grammar, and vocabulary usage of the language spoken by the user and evaluate the language skills of the user. The evaluation unit, for example, uses speech recognition technology to analyze the pronunciation of the user. For example, the evaluation unit evaluates phoneme accuracy, intonation, rhythm, etc. The evaluation unit also uses grammar analysis technology to evaluate grammar accuracy. For example, the evaluation unit evaluates sentence structure, tense agreement, grammatical accuracy, etc. Furthermore, the evaluation unit uses vocabulary analysis technology to analyze vocabulary usage. For example, the evaluation unit evaluates vocabulary richness, appropriate use, context-dependent selection, etc. This enables more accurate evaluation of language skills by analyzing the pronunciation, grammar, and vocabulary usage of the user. Part or all of the above-mentioned processing in the evaluation unit may be performed, for example, using AI, or may be performed without using AI. For example, the evaluation unit can input the user's pronunciation data to the generation AI and cause the generation AI to execute pronunciation evaluation.

[0036] The adjustment unit can generate an individualized learning plan based on the evaluation result by the evaluation unit and the user's learning history. For example, the adjustment unit creates a learning plan taking into consideration the user's learning goals, learning schedule, and selection of teaching materials. The adjustment unit can also monitor the user's progress in real time and adjust the learning plan as appropriate. For example, the adjustment unit can analyze the user's learning history, identify specific weaknesses, and generate a corresponding learning plan. In this way, an individualized learning plan can be generated, thereby providing the user with optimal learning content. Some or all of the above-mentioned processing in the adjustment unit may be performed, for example, using AI, or may be performed without using AI. For example, the adjustment unit can input the user's learning history data into the generation AI and cause the generation AI to generate a learning plan.

[0037] The feedback unit can evaluate the user's pronunciation using a voice analysis technology and provide specific pronunciation guidance. The feedback unit, for example, uses a voice analysis technology to evaluate the user's pronunciation. For example, the feedback unit analyzes the user's pronunciation using a voice recognition technology and evaluates the accuracy of phonemes, intonation, rhythm, and the like. The feedback unit also identifies problems with the user's pronunciation and makes correction suggestions in order to provide specific pronunciation guidance. For example, the feedback unit highlights the user's pronunciation errors in real time and makes correction suggestions. This makes it possible to provide specific pronunciation guidance by using the voice analysis technology. Some or all of the above-mentioned processing in the feedback unit may be performed using, for example, a generation AI, or may be performed without using a generation AI. For example, the feedback unit can input the user's pronunciation data into the generation AI and cause the generation AI to perform pronunciation evaluation and guidance.

[0038] The adjustment unit can adjust the learning pace based on the physiological data of the user. The adjustment unit, for example, uses a sensor to collect the physiological data of the user. For example, the adjustment unit collects and analyzes physiological data such as heart rate, skin electrodermal activity, and brain waves. The adjustment unit evaluates the stress level and concentration of the user based on the collected physiological data and adjusts the learning pace. For example, the adjustment unit slows down the learning pace when the user's heart rate is high. In addition, the adjustment unit can also speed up the learning pace when the user's heart rate is stable. This allows more effective learning by adjusting the learning pace based on the physiological data of the user. Part or all of the above-mentioned processing in the adjustment unit may be performed, for example, using AI or may be performed without using AI. For example, the adjustment unit can input the physiological data of the user to the generation AI and cause the generation AI to adjust the learning pace.

[0039] The feedback unit can highlight the user's grammar errors in real time and make correction suggestions. The feedback unit, for example, uses grammar analysis technology to detect the user's grammar errors. For example, the feedback unit uses a grammar check algorithm to detect and highlight the user's grammar errors in real time. The feedback unit also makes correction suggestions for the detected grammar errors. For example, when the user makes a grammar error, the feedback unit highlights the error location in real time and makes appropriate correction suggestions. This makes it possible to improve the user's grammar skills by highlighting the grammar errors in real time and making correction suggestions. Some or all of the above-mentioned processing in the feedback unit may be performed, for example, using a generation AI, or may be performed without using a generation AI. For example, the feedback unit can input the user's grammar error data to the generation AI and cause the generation AI to detect errors and make correction suggestions.

[0040] The evaluation unit can evaluate the richness of the user's vocabulary. The evaluation unit uses, for example, a vocabulary analysis technique to analyze the user's vocabulary usage. For example, the evaluation unit evaluates the number and diversity of vocabulary used by the user. The evaluation unit can also evaluate whether the user uses vocabulary appropriately. For example, the evaluation unit evaluates whether the user selects appropriate vocabulary according to the context. This enables a more accurate evaluation of language skills by evaluating the richness of the user's vocabulary. A part or all of the above-mentioned processing in the evaluation unit may be performed, for example, using AI, or may be performed without using AI. For example, the evaluation unit can input the user's vocabulary data to the generation AI and cause the generation AI to perform vocabulary evaluation.

[0041] The adjustment unit can adjust the teaching materials in real time based on the user's feedback. The adjustment unit, for example, uses a feedback analysis technique to collect and analyze the user's feedback. For example, the adjustment unit analyzes the feedback provided by the user in real time and adjusts the content and difficulty of the teaching materials. The adjustment unit can also adjust the learning plan as appropriate based on the user's feedback. For example, the adjustment unit changes the content of the teaching materials or adds new teaching materials based on the feedback provided by the user. This enables more effective learning by adjusting the teaching materials in real time based on the user's feedback. Some or all of the above-mentioned processing in the adjustment unit may be performed, for example, using AI or may be performed without using AI. For example, the adjustment unit can input the user's feedback data into the generation AI and cause the generation AI to adjust the teaching materials.

[0042] The system includes a control unit that controls smart home devices based on the evaluation results. For example, the control unit controls smart home devices such as lighting, temperature control, and sound systems to optimize the user's learning environment. The control unit adjusts the settings of the devices to provide an environment suitable for learning based on the user's evaluation results. For example, the control unit adjusts the lighting to provide a relaxing environment when the user's evaluation result is high. The control unit can also adjust the temperature to provide an environment where the user can concentrate when the user's evaluation result is low. This allows the learning environment to be optimized by controlling the smart home devices based on the evaluation results. Some or all of the above-mentioned processing in the control unit may be performed, for example, using AI or may be performed without using AI. For example, the control unit can input the user's evaluation result data to the generation AI and cause the generation AI to control the device.

[0043] The providing unit can provide teaching materials that allow the user to learn information about specific cultural events and holidays. The providing unit, for example, provides teaching materials including information about specific cultural events and holidays. For example, the providing unit collects information about cultural events and holidays that the user wants to learn about, and creates teaching materials based on the information. The providing unit provides text teaching materials, video teaching materials, interactive exercises, and the like that include information about cultural events and holidays selected by the user. This allows the user to deepen their cultural understanding by providing teaching materials that allow the user to learn information about specific cultural events and holidays. Some or all of the above-mentioned processing in the providing unit may be performed, for example, using AI, or may be performed without using AI. For example, the providing unit can input the user's selection data into the generating AI and cause the generating AI to create teaching materials.

[0044] The providing unit can provide teaching materials that enable the user to learn cultural background and daily conversations related to a specific region selected by the user. The providing unit provides teaching materials including, for example, cultural background and daily conversations related to a specific region. For example, the providing unit collects information about the region that the user wants to learn and creates teaching materials based on the information. The providing unit provides text teaching materials, video teaching materials, interactive exercises, and the like that include cultural background and daily conversations related to the region selected by the user. This allows the user to deepen their understanding of the region by providing teaching materials that enable the user to learn cultural background and daily conversations related to the specific region. Some or all of the above-mentioned processing in the providing unit may be performed, for example, using AI, or may be performed without using AI. For example, the providing unit can input the user's selection data into the generating AI and cause the generating AI to create teaching materials.

[0045] The evaluation unit can analyze the user's past learning history and improve the accuracy of the evaluation. The evaluation unit, for example, uses a learning history analysis technique to collect and analyze the user's past learning history. For example, the evaluation unit analyzes the content, learning time, achievement level, teaching materials used, etc., that the user has learned in the past, and improves the accuracy of the evaluation. The evaluation unit adjusts the evaluation criteria based on the user's past learning history. For example, the evaluation unit adjusts the evaluation criteria and identifies specific weak points based on the content that the user has learned in the past. The evaluation unit can also analyze the user's past learning history and collect data for improving the accuracy of the evaluation. As a result, the accuracy of the evaluation is improved by analyzing the past learning history. Some or all of the above-mentioned processing in the evaluation unit may be performed, for example, using AI, or may be performed without using AI. For example, the evaluation unit can input the user's learning history data to the generation AI and cause the generation AI to execute the improvement of the accuracy of the evaluation.

[0046] During the evaluation, the evaluation unit can analyze the user's pronunciation, grammar, and vocabulary usage in real time and provide immediate feedback. The evaluation unit, for example, uses speech recognition technology to analyze the user's pronunciation in real time. For example, the evaluation unit analyzes the pronunciation of the language spoken by the user in real time and provides immediate feedback. The evaluation unit also uses grammar analysis technology to analyze the user's grammatical errors in real time and provide immediate correction suggestions. For example, the evaluation unit detects the user's grammatical errors in real time and provides correction suggestions. Furthermore, the evaluation unit uses vocabulary analysis technology to analyze the user's vocabulary usage in real time and provide immediate evaluation. For example, the evaluation unit evaluates the number and diversity of vocabulary used by the user in real time. As a result, the user's learning effect is improved by analyzing in real time and providing immediate feedback. A part or all of the above-mentioned processing in the evaluation unit may be performed using, for example, AI, or may be performed without using AI. For example, the evaluation unit can input the user's pronunciation data, grammar data, and vocabulary data into the generation AI and cause the generation AI to perform real-time analysis and immediate feedback.

[0047] The evaluation unit can customize the evaluation criteria by taking into account the geographical location information of the user at the time of evaluation. The evaluation unit, for example, uses GPS technology to acquire the geographical location information of the user. For example, when the user is in a specific region, the evaluation unit adjusts the evaluation criteria by taking into account the language characteristics of the region. In addition, when the user moves to a different region, the evaluation unit can also reset the evaluation criteria based on the language characteristics of the new region. Furthermore, the evaluation unit reflects the language characteristics specific to the region in the evaluation based on the geographical location information of the user. For example, when the user is in a specific region, the evaluation unit performs the evaluation by taking into account the dialect and accent of the region. As a result, by taking into account the geographical location information, it is possible to perform an evaluation specific to the region. A part or all of the above-mentioned processing in the evaluation unit may be performed, for example, using AI, or may be performed without using AI. For example, the evaluation unit can input the geographical location data of the user to the generation AI and cause the generation AI to execute customization of the evaluation criteria.

[0048] The evaluation unit can analyze the user's social media activities at the time of evaluation and reflect related vocabulary and expressions in the evaluation. The evaluation unit uses, for example, social media analysis technology to analyze the user's social media activities. For example, the evaluation unit analyzes the user's social media posts and reflects the vocabulary and expressions used in the evaluation. The evaluation unit can also identify vocabulary and expressions frequently used by the user and incorporate them into the evaluation criteria. Furthermore, the evaluation unit collects data for improving the accuracy of the evaluation based on the user's social media activities. For example, the evaluation unit analyzes the user's social media posts and reflects related vocabulary and expressions in the evaluation. As a result, the accuracy of the evaluation is improved by analyzing the social media activities. A part or all of the above-mentioned processing in the evaluation unit may be performed, for example, using AI or may be performed without using AI. For example, the evaluation unit can input the user's social media data to the generation AI and cause the generation AI to improve the accuracy of the evaluation.

[0049] The providing unit can select the optimal teaching material by referring to the user's past learning history at the time of providing. The providing unit, for example, uses a learning history analysis technique to collect and analyze the user's past learning history. For example, the providing unit analyzes the content, learning time, achievement level, teaching materials used, etc., that the user has learned in the past, and selects the optimal teaching material. The providing unit selects the optimal teaching material based on the user's past learning history. For example, the optimal teaching material is selected and specific weak points are identified based on the content that the user has learned in the past. The providing unit can also analyze the user's past learning history and collect data for selecting the optimal teaching material. As a result, the optimal teaching material can be provided by referring to the past learning history. A part or all of the above-mentioned processing in the providing unit may be performed, for example, using AI, or may be performed without using AI. For example, the providing unit can input the user's learning history data to the generating AI and cause the generating AI to select the optimal teaching material.

[0050] The providing unit can provide teaching materials in different formats according to the user's learning style at the time of providing. The providing unit uses, for example, a learning style analysis technique to evaluate the user's learning style. For example, the providing unit provides visual teaching materials when the user is a visual learner. The providing unit can also provide audio teaching materials when the user is an auditory learner. Furthermore, the providing unit can provide interactive teaching materials when the user is a tactile learner. For example, the providing unit selects and provides teaching materials in an optimal format according to the user's learning style. This improves the learning effect by providing teaching materials according to the learning style. A part or all of the above-mentioned processing in the providing unit may be performed, for example, using AI or may be performed without using AI. For example, the providing unit can input the user's learning style data to the generating AI and cause the generating AI to select the optimal teaching materials.

[0051] The providing unit can provide region-specific teaching materials in consideration of the geographical location information of the user at the time of providing. The providing unit uses, for example, GPS technology to acquire the geographical location information of the user. For example, when the user is in a specific region, the providing unit provides teaching materials related to the culture and language characteristics of the region. In addition, when the user moves to a different region, the providing unit can also provide teaching materials related to the culture and language characteristics of the new region. Furthermore, the providing unit provides region-specific teaching materials based on the geographical location information of the user. For example, when the user is in a specific region, the providing unit provides teaching materials related to the culture and language characteristics of the region. In this way, region-specific teaching materials can be provided by taking the geographical location information into consideration. A part or all of the above-mentioned processing in the providing unit may be performed, for example, using AI, or may be performed without using AI. For example, the providing unit can input the geographical location data of the user to the generating AI and cause the generating AI to provide region-specific teaching materials.

[0052] The providing unit can analyze the user's social media activity and provide related teaching materials at the time of providing. The providing unit, for example, uses a social media analysis technique to analyze the user's social media activity. For example, the providing unit analyzes the user's social media posts and provides teaching materials including related vocabulary and expressions. The providing unit can also identify vocabulary and expressions frequently used by the user and provide corresponding teaching materials. Furthermore, the providing unit collects data for providing related teaching materials based on the user's social media activity. For example, the providing unit analyzes the user's social media posts and provides teaching materials including related vocabulary and expressions. In this way, related teaching materials can be provided by analyzing social media activities. A part or all of the above-mentioned processing in the providing unit may be performed, for example, using AI, or may be performed without using AI. For example, the providing unit can input the user's social media data to the generating AI and cause the generating AI to provide related teaching materials.

[0053] The dialogue unit can improve the accuracy of the dialogue by referring to the user's past dialogue history during the dialogue. The dialogue unit, for example, uses a dialogue history analysis technique to collect and analyze the user's past dialogue history. For example, the dialogue unit improves the accuracy of the dialogue based on the content of the dialogue the user has had in the past. The dialogue unit can also identify a specific weakness from the user's past dialogue history and engage in a dialogue corresponding to the weakness. Furthermore, the dialogue unit analyzes the user's past dialogue history and collects data for improving the accuracy of the dialogue. For example, the dialogue unit improves the accuracy of the dialogue based on the content of the user's past dialogue. As a result, the accuracy of the dialogue is improved by referring to the past dialogue history. A part or all of the above-mentioned processing in the dialogue unit may be performed, for example, using AI, or may be performed without using AI. For example, the dialogue unit can input the user's dialogue history data to the generation AI and cause the generation AI to execute the improvement of the dialogue accuracy.

[0054] The dialogue unit can adjust the difficulty of the dialogue in accordance with the user's learning progress during the dialogue. The dialogue unit uses, for example, a learning progress analysis technique to evaluate the user's learning progress. For example, the dialogue unit performs an easy dialogue when the user's learning progress is delayed. In addition, the dialogue unit can perform a difficult dialogue when the user's learning progress is good. Furthermore, the dialogue unit adjusts the difficulty of the dialogue in accordance with the user's learning progress. For example, the dialogue unit adjusts the difficulty of the dialogue based on the user's learning progress. As a result, the learning effect is improved by adjusting the difficulty of the dialogue in accordance with the learning progress. A part or all of the above-mentioned processing in the dialogue unit may be performed, for example, using AI, or may be performed without using AI. For example, the dialogue unit can input the user's learning progress data to the generation AI and cause the generation AI to adjust the difficulty of the dialogue.

[0055] The dialogue unit can provide region-specific dialogue content in consideration of the geographical location information of the user during dialogue. The dialogue unit, for example, uses GPS technology to acquire the geographical location information of the user. For example, when the user is in a specific region, the dialogue unit provides dialogue content related to the culture and language characteristics of the region. In addition, when the user moves to a different region, the dialogue unit can also provide dialogue content related to the culture and language characteristics of the new region. Furthermore, the dialogue unit provides region-specific dialogue content based on the geographical location information of the user. For example, when the user is in a specific region, the dialogue unit provides dialogue content related to the culture and language characteristics of the region. In this way, region-specific dialogue content can be provided by taking the geographical location information into consideration. Part or all of the above-mentioned processing in the dialogue unit may be performed, for example, using AI, or may be performed without using AI. For example, the dialogue unit can input the geographical location data of the user to the generation AI and cause the generation AI to provide region-specific dialogue content.

[0056] The dialogue unit can analyze the user's social media activity during dialogue and provide related dialogue content. The dialogue unit, for example, uses social media analysis technology to analyze the user's social media activity. For example, the dialogue unit analyzes the user's social media posts and provides dialogue content including related vocabulary and expressions. The dialogue unit can also identify vocabulary and expressions frequently used by the user and provide corresponding dialogue content. Furthermore, the dialogue unit collects data for providing related dialogue content based on the user's social media activity. For example, the dialogue unit analyzes the user's social media posts and provides dialogue content including related vocabulary and expressions. In this way, related dialogue content can be provided by analyzing social media activity. Part or all of the above-mentioned processing in the dialogue unit may be performed, for example, using AI or may be performed without using AI. For example, the dialogue unit can input the user's social media data to the generation AI and cause the generation AI to provide related dialogue content.

[0057] The feedback unit can improve the accuracy of the feedback by referring to the user's past learning history when providing feedback. The feedback unit, for example, uses a learning history analysis technique to collect and analyze the user's past learning history. For example, the feedback unit analyzes the content, learning time, achievement level, teaching materials used, etc., that the user has learned in the past, and improves the accuracy of the feedback. The feedback unit adjusts the content of the feedback based on the user's past learning history. For example, the feedback unit adjusts the content of the feedback based on the content that the user has learned in the past, and identifies specific weak points. The feedback unit can also analyze the user's past learning history and collect data for improving the accuracy of the feedback. As a result, the accuracy of the feedback is improved by referring to the past learning history. A part or all of the above-mentioned processing in the feedback unit may be performed, for example, using AI, or may be performed without using AI. For example, the feedback unit can input the user's learning history data to the generation AI and cause the generation AI to improve the accuracy of the feedback.

[0058] The feedback unit can highlight the user's pronunciation and grammar errors in real time and make correction suggestions at the time of feedback. The feedback unit, for example, uses a voice analysis technique to detect the user's pronunciation errors. For example, when the user makes a pronunciation error, the feedback unit highlights the user's pronunciation and makes a correction suggestion in real time. The feedback unit also uses a grammar analysis technique to detect the user's grammar errors. For example, when the user makes a grammar error, the feedback unit highlights the user's grammar error in real time and makes a correction suggestion. Furthermore, the feedback unit analyzes the user's pronunciation and grammar errors in real time and makes an immediate correction suggestion. For example, the feedback unit highlights the user's pronunciation errors in real time and makes a correction suggestion. As a result, the learning effect is improved by highlighting the pronunciation and grammar errors in real time and making a correction suggestion. A part or all of the above-mentioned processing in the feedback unit may be performed, for example, using AI, or may be performed without using AI. For example, the feedback unit can input the user's pronunciation data and grammar data to the generation AI and cause the generation AI to detect errors and make correction suggestions.

[0059] The feedback unit can provide region-specific feedback by taking into account the geographical location information of the user at the time of feedback. The feedback unit, for example, uses GPS technology to acquire the geographical location information of the user. For example, when the user is in a specific region, the feedback unit provides feedback on the culture and language characteristics of the region. In addition, when the user moves to a different region, the feedback unit can also provide feedback on the culture and language characteristics of the new region. Furthermore, the feedback unit provides region-specific feedback based on the geographical location information of the user. For example, when the user is in a specific region, the feedback unit provides feedback on the culture and language characteristics of the region. In this way, region-specific feedback can be provided by taking into account the geographical location information. Part or all of the above-mentioned processing in the feedback unit may be performed, for example, using AI or may be performed without using AI. For example, the feedback unit can input the geographical location data of the user to the generation AI and cause the generation AI to provide region-specific feedback.

[0060] The feedback unit can analyze the user's social media activity and provide relevant feedback at the time of feedback. The feedback unit, for example, uses social media analysis technology to analyze the user's social media activity. For example, the feedback unit analyzes the user's social media posts and provides feedback including relevant vocabulary and expressions. The feedback unit can also identify vocabulary and expressions frequently used by the user and provide corresponding feedback. Furthermore, the feedback unit collects data for providing relevant feedback based on the user's social media activity. For example, the feedback unit analyzes the user's social media posts and provides feedback including relevant vocabulary and expressions. In this way, it is possible to provide relevant feedback by analyzing social media activity. Some or all of the above-mentioned processing in the feedback unit may be performed, for example, using AI or may be performed without using AI. For example, the feedback unit can input the user's social media data to the generation AI and cause the generation AI to provide relevant feedback.

[0061] During the adjustment, the adjustment unit can generate an optimal learning plan by referring to the user's past learning history. The adjustment unit uses, for example, a learning history analysis technique to collect and analyze the user's past learning history. For example, the adjustment unit analyzes the content, learning time, achievement level, teaching materials used, etc., that the user has learned in the past, and generates an optimal learning plan. The adjustment unit generates an optimal learning plan based on the user's past learning history. For example, the adjustment unit generates an optimal learning plan and identifies specific weak points based on the content that the user has learned in the past. The adjustment unit can also analyze the user's past learning history and collect data for generating an optimal learning plan. As a result, the optimal learning plan can be generated by referring to the past learning history. A part or all of the above-mentioned processing in the adjustment unit may be performed, for example, using AI, or may be performed without using AI. For example, the adjustment unit can input the user's learning history data to the generation AI and cause the generation AI to generate an optimal learning plan.

[0062] During the adjustment, the adjustment unit can analyze the physiological data of the user and customize the pace and content of the learning. The adjustment unit, for example, uses a sensor to collect the physiological data of the user. For example, the adjustment unit collects and analyzes physiological data such as heart rate, skin electrodermal activity, and brain waves. The adjustment unit evaluates the stress level and concentration of the user based on the collected physiological data, and customizes the learning pace and content. For example, the adjustment unit slows down the learning pace when the user's heart rate is high. In addition, the adjustment unit can also speed up the learning pace when the user's heart rate is stable. Furthermore, the adjustment unit customizes the learning content based on the physiological data of the user. For example, the adjustment unit analyzes the sleep data of the user and adjusts the learning content. As a result, the pace and content of the learning can be customized by analyzing the physiological data. Part or all of the above-mentioned processing in the adjustment unit may be performed, for example, using AI, or may be performed without using AI. For example, the adjustment unit can input the physiological data of the user to the generation AI and cause the generation AI to customize the learning pace and content.

[0063] During the adjustment, the adjustment unit can provide a region-specific learning plan by taking into account the geographical location information of the user. The adjustment unit uses, for example, GPS technology to acquire the geographical location information of the user. For example, when the user is in a specific region, the adjustment unit provides a learning plan related to the culture and language characteristics of the region. In addition, when the user moves to a different region, the adjustment unit can also provide a learning plan related to the culture and language characteristics of the new region. Furthermore, the adjustment unit provides a region-specific learning plan based on the geographical location information of the user. For example, when the user is in a specific region, the adjustment unit provides a learning plan related to the culture and language characteristics of the region. In this way, a region-specific learning plan can be provided by taking into account the geographical location information. Part or all of the above-mentioned processing in the adjustment unit may be performed, for example, using AI or may be performed without using AI. For example, the adjustment unit can input the geographical location data of the user to the generation AI and cause the generation AI to provide a region-specific learning plan.

[0064] At the time of adjustment, the adjustment unit can analyze the user's social media activity and provide related learning content. The adjustment unit, for example, uses social media analysis technology to analyze the user's social media activity. For example, the adjustment unit analyzes the user's social media posts and provides learning content including related vocabulary and expressions. The adjustment unit can also identify vocabulary and expressions frequently used by the user and provide corresponding learning content. Furthermore, the adjustment unit collects data for providing related learning content based on the user's social media activity. For example, the adjustment unit analyzes the user's social media posts and provides learning content including related vocabulary and expressions. In this way, related learning content can be provided by analyzing social media activity. Part or all of the above-mentioned processing in the adjustment unit may be performed, for example, using AI or may be performed without using AI. For example, the adjustment unit can input the user's social media data to the generation AI and cause the generation AI to provide related learning content.

[0065] During control, the control unit can select the optimal control method by referring to the user's past device usage history. The control unit, for example, uses a device usage history analysis technique to collect and analyze the user's past device usage history. For example, the control unit selects the optimal control method based on the device settings used by the user in the past. The control unit can also identify a specific setting from the user's past device usage history and select a control method corresponding to the setting. Furthermore, the control unit analyzes the user's past device usage history and collects data for selecting the optimal control method. For example, the control unit selects the optimal control method based on the device settings used by the user in the past. In this way, the optimal control method can be selected by referring to the past device usage history. A part or all of the above-mentioned processing in the control unit may be performed, for example, using AI or may be performed without using AI. For example, the control unit can input the user's device usage history data to the generation AI and cause the generation AI to select the optimal control method.

[0066] The control unit can customize the device settings according to the user's learning progress during control. The control unit uses, for example, a learning progress analysis technique to evaluate the user's learning progress. For example, when the user's learning progress is delayed, the control unit customizes the device settings to provide an environment where the user can concentrate. In addition, when the user's learning progress is good, the control unit can also customize the device settings to provide an environment where the user can relax. Furthermore, the control unit customizes the device settings according to the user's learning progress. For example, the control unit customizes the device settings based on the user's learning progress. This allows the learning environment to be optimized by customizing the device settings according to the learning progress. Part or all of the above-mentioned processing in the control unit may be performed, for example, using AI, or may be performed without using AI. For example, the control unit can input the user's learning progress data to the generation AI and cause the generation AI to execute customization of the device settings.

[0067] The control unit can provide region-specific device settings during control by taking into account the geographical location information of the user. The control unit, for example, uses GPS technology to acquire the geographical location information of the user. For example, when the user is in a specific region, the control unit provides device settings suitable for the culture and climate of the region. In addition, when the user moves to a different region, the control unit can also provide device settings suitable for the culture and climate of the new region. Furthermore, the control unit provides region-specific device settings based on the geographical location information of the user. For example, when the user is in a specific region, the control unit provides device settings suitable for the culture and climate of the region. In this way, region-specific device settings can be provided by taking into account the geographical location information. Part or all of the above-mentioned processing in the control unit may be performed, for example, using AI or may be performed without using AI. For example, the control unit can input the geographical location data of the user to the generation AI and cause the generation AI to provide region-specific device settings.

[0068] During control, the control unit can analyze the user's social media activity and provide the relevant device settings. The control unit, for example, uses social media analysis technology to analyze the user's social media activity. For example, the control unit analyzes the user's social media posts and provides the relevant device settings. The control unit can also identify device settings that are frequently used by the user and provide a corresponding control method. Furthermore, the control unit collects data for providing the relevant device settings based on the user's social media activity. For example, the control unit analyzes the user's social media posts and provides the relevant device settings. In this way, the relevant device settings can be provided by analyzing the social media activity. Some or all of the above-mentioned processing in the control unit may be performed, for example, using AI or may be performed without using AI. For example, the control unit can input the user's social media data to the generation AI and cause the generation AI to provide the relevant device settings.

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

[0070] The evaluation unit may also take into account the user's learning style when evaluating the user's language skills. For example, if the user is a visual learner, the evaluation unit may use an evaluation method that includes many visual elements. If the user is an auditory learner, the evaluation unit may use an evaluation method that emphasizes audio. Furthermore, if the user is a tactile learner, the evaluation unit may use an evaluation method that includes interactive elements. This allows evaluation according to the user's learning style, resulting in a more accurate evaluation of language skills.

[0071] The evaluation unit may also take into account the user's social media activity when evaluating the user's language skills. For example, the evaluation unit may analyze the user's social media posts and reflect the vocabulary and expressions used in the evaluation. The evaluation unit may also identify vocabulary and expressions frequently used by the user and adjust the evaluation criteria based on the vocabulary and expressions. Furthermore, the evaluation unit may collect data to improve the accuracy of the evaluation based on the user's social media activity. This allows for a more accurate evaluation of language skills by taking social media activity into account.

[0072] The adjustment unit may also take into account the geographic location information of the user when adjusting the user's learning pace. For example, when the user is in a particular region, the adjustment unit adjusts the learning pace based on the culture and language characteristics of the region. Also, when the user moves to a different region, the adjustment unit may reset the learning pace based on the culture and language characteristics of the new region. Furthermore, the adjustment unit may provide a region-specific learning pace based on the user's geographic location information. In this way, a region-specific learning pace can be provided by taking into account the geographic location information.

[0073] The feedback unit may also take into account the user's learning history when highlighting the user's pronunciation and grammar errors in real time and making correction suggestions. For example, the feedback unit may identify specific weaknesses based on the user's past learning history and make corresponding correction suggestions. The feedback unit may also analyze the user's learning history and tailor the feedback content based on what was previously learned. Furthermore, the feedback unit may collect data based on the user's learning history to improve the accuracy of the feedback. This allows for more effective feedback to be provided by taking into account the learning history.

[0074] The adjustment unit can also take into account the user's past physiological data when adjusting the learning pace based on the user's physiological data. For example, the adjustment unit can provide a learning pace that corresponds to a specific physiological state based on the user's past physiological data. The adjustment unit can also analyze the user's physiological data and adjust the learning pace based on what learning pace was effective in the past. Furthermore, the adjustment unit can collect data for improving the accuracy of the learning pace based on the user's physiological data. In this way, a more effective learning pace can be provided by taking into account the past physiological data.

[0075] The evaluation unit may also take into account the geographic location information of the user when evaluating the richness of the user's vocabulary. For example, when the user is in a particular region, the evaluation unit may evaluate the vocabulary taking into account the language characteristics of the region. Also, when the user moves to a different region, the evaluation unit may reset the evaluation of the vocabulary based on the language characteristics of the new region. Furthermore, the evaluation unit may provide a region-specific vocabulary evaluation based on the geographic location information of the user. In this way, a region-specific vocabulary evaluation can be provided by taking into account the geographic location information.

[0076] The process flow of the first embodiment will be briefly described below.

[0077] Step 1: The evaluation unit evaluates the language skills of the user. The evaluation unit analyzes the pronunciation, grammar, and vocabulary usage of the language spoken by the user to evaluate the language skills. The evaluation unit analyzes the user's pronunciation using speech recognition technology and evaluates the accuracy of grammar using grammar analysis technology. In addition, the evaluation unit analyzes the usage of vocabulary to evaluate the richness of vocabulary. Step 2: The provision unit provides learning materials according to the user's skill level based on the evaluation results by the evaluation unit. The provision unit provides text learning materials, audio learning materials, video learning materials, interactive exercises, etc., and selects and provides appropriate learning materials based on the user's evaluation results. Step 3: The dialogue unit uses the provided learning materials to dialogue with the user. The dialogue unit conducts voice dialogue, text dialogue, video dialogue, etc., evaluates the accuracy of the user's pronunciation and grammar in real time, and provides feedback. Step 4: The feedback unit provides real-time feedback on pronunciation and grammar based on the dialogue results of the dialogue unit. The feedback unit evaluates the user's pronunciation using speech analysis technology and provides specific pronunciation guidance. It also highlights the user's grammatical errors in real time and makes correction suggestions. Step 5: The adjustment unit adjusts the pace and content of the learning based on the user's progress. The adjustment unit generates an individualized learning plan based on the assessment results and the user's learning history. It adjusts the learning pace based on the user's physiological data and adjusts the learning materials in real time based on the feedback.

[0078] (Example 2) A system according to an embodiment of the present invention is a system for evaluating a user's language skills and providing learning materials at an appropriate level. The system includes an evaluation unit for evaluating the user's language skills, a provision unit for providing appropriate learning materials based on the evaluation results, a dialogue unit for dialogue with the user using the provided learning materials, a feedback unit for providing feedback on pronunciation and grammar in real time based on the dialogue results, and an adjustment unit for adjusting the pace and content of learning based on the user's progress. The evaluation unit analyzes the pronunciation, grammar, and vocabulary usage of the language spoken by the user to evaluate the language skills. The adjustment unit generates an individualized learning plan based on the evaluation results and the user's learning history. The feedback unit evaluates pronunciation using voice analysis technology and provides specific pronunciation guidance. In addition, the feedback unit provides feedback according to the user's emotional state, highlights grammatical errors in real time, and makes correction suggestions. The adjustment unit adjusts the learning pace based on the user's physiological data and adjusts the learning materials in real time based on the feedback. Furthermore, the system includes a control unit for controlling smart home devices based on the evaluation results. The provision unit provides learning materials that allow the user to learn information about specific cultural events and holidays, and learning cultural backgrounds and daily conversations related to a specific region. This enables the system to support effective language learning by assessing the user's language skills, providing appropriate learning materials, providing interactive feedback, and adjusting the pace and content of learning.

[0079] A language learning system according to an embodiment includes an evaluation unit, a provision unit, a dialogue unit, a feedback unit, and an adjustment unit. The evaluation unit evaluates the language skills of a user. For example, the evaluation unit analyzes the pronunciation, grammar, and vocabulary usage of the language spoken by the user to evaluate the language skills. The evaluation unit analyzes the pronunciation of the user using a voice recognition technology and evaluates the accuracy of the grammar using a grammar analysis technology. The evaluation unit also analyzes the usage of vocabulary and evaluates the richness of the vocabulary. The provision unit provides teaching materials according to the skill level of the user based on the evaluation result by the evaluation unit. The provision unit provides, for example, text teaching materials, audio teaching materials, video teaching materials, interactive exercises, etc. The provision unit selects and provides appropriate teaching materials based on the evaluation result of the user. The dialogue unit uses the provided teaching materials to dialogue with the user. The dialogue unit performs, for example, voice dialogue, text dialogue, video dialogue, etc. The dialogue unit evaluates the accuracy of the pronunciation and grammar of the user in real time and provides feedback. The feedback unit provides feedback on pronunciation and grammar in real time based on the dialogue result by the dialogue unit. The feedback unit evaluates the user's pronunciation using voice analysis technology and provides specific pronunciation guidance. The feedback unit also highlights the user's grammatical errors in real time and provides correction suggestions. The adjustment unit adjusts the pace and content of learning based on the user's progress. The adjustment unit generates an individualized learning plan based on the evaluation result and the user's learning history. The adjustment unit adjusts the learning pace based on the user's physiological data and adjusts the learning materials in real time based on the feedback. As a result, the language learning system according to the embodiment can support effective language learning by evaluating the user's language skills, providing appropriate learning materials, providing feedback through dialogue, and adjusting the learning pace and content.

[0080] The evaluation unit evaluates the language skills of the user. For example, the evaluation unit analyzes the pronunciation, grammar, and vocabulary usage of the language spoken by the user to evaluate the language skills. Specifically, the evaluation unit uses a voice recognition technology to analyze the user's pronunciation, and uses a grammar analysis technology to evaluate the accuracy of the grammar. The voice recognition technology analyzes the user's pronunciation at the phoneme level and compares it with the pronunciation of a native speaker to evaluate the accuracy of the pronunciation. For example, when a user pronounces a specific word or phrase, the voice recognition system analyzes the voice data and evaluates the degree of phoneme agreement and the accuracy of intonation. The grammar analysis technology analyzes the text and voice data input by the user to detect grammatical errors. For example, it checks the subject and verb agreement, tense agreement, use of prepositions, etc. to evaluate the grammatical accuracy. Furthermore, the evaluation unit analyzes the usage of vocabulary and evaluates the richness of the vocabulary. The vocabulary analysis technology analyzes the types and frequency of words used by the user to evaluate the diversity and appropriateness of the vocabulary. For example, the evaluator evaluates how diverse the vocabulary a user uses when talking about a particular topic and whether that vocabulary is appropriate to the context. This allows the evaluator to evaluate the user's language skills from multiple angles and provide detailed feedback.

[0081] The providing unit provides teaching materials according to the skill level of the user based on the evaluation result by the evaluating unit. Specifically, text teaching materials, audio teaching materials, video teaching materials, interactive exercises, etc. are provided. The providing unit selects and provides appropriate teaching materials based on the evaluation result of the user. For example, if the user's pronunciation is inaccurate, audio teaching materials and video teaching materials for pronunciation practice are provided to enable the user to learn correct pronunciation. In addition, if there are many grammatical errors, text teaching materials and interactive exercises for learning the basics of grammar are provided. Furthermore, if the user's vocabulary is insufficient, a wordbook, flash cards, and vocabulary-based exercises for increasing vocabulary are provided. The providing unit can also customize the format and content of the teaching materials according to the user's learning style and preferences. For example, for a user who prefers visual learning, teaching materials that make heavy use of video teaching materials and infographics are provided, and for a user who prefers auditory learning, audio teaching materials and podcasts are provided. In this way, the providing unit can provide optimal teaching materials according to the individual needs of the user and support effective learning.

[0082] The dialogue unit uses the provided learning materials to have a dialogue with the user. Specifically, the dialogue unit performs voice dialogue, text dialogue, video dialogue, and the like. The dialogue unit evaluates the accuracy of the user's pronunciation and grammar in real time and provides feedback. For example, in voice dialogue, the dialogue unit analyzes words and phrases pronounced by the user and evaluates the accuracy of the pronunciation and the appropriateness of the intonation. If the user makes an incorrect pronunciation, the dialogue unit immediately presents the correct pronunciation and encourages the user to practice. In text dialogue, the dialogue unit analyzes sentences entered by the user and evaluates grammatical errors and the appropriateness of vocabulary. If the user makes a grammatical error, the dialogue unit highlights the error and presents the correct grammar. In video dialogue, the dialogue unit analyzes the content of speech, facial expressions, and gestures of the user and evaluates the overall communication skills. The dialogue unit provides appropriate feedback and supports practice so that the user can have a natural dialogue. Furthermore, the dialogue unit can record the user's dialogue history and track the progress. As a result, the dialogue unit can adjust the content and difficulty of the dialogue according to the user's progress in learning, and support effective learning.

[0083] The feedback unit provides feedback on pronunciation and grammar in real time based on the dialogue result by the dialogue unit. Specifically, the feedback unit evaluates the user's pronunciation using voice analysis technology and provides specific pronunciation guidance. For example, if the user mispronounces a particular word, the feedback unit points out the error and presents the correct pronunciation in voice or text. In addition, if the user makes a grammatical error, the feedback unit highlights the error and suggests a correction. For example, if the user makes a mistake in matching a subject and a verb, the feedback unit highlights that part and presents the correct grammar. In addition, the feedback unit can adjust the content and method of feedback according to the user's progress. For example, for a beginner user, the feedback unit focuses on teaching basic pronunciation and grammar, and for an advanced user, the feedback unit provides more advanced pronunciation and grammar guidance. In this way, the feedback unit can provide effective feedback according to the individual needs of the user and improve the quality of learning.

[0084] The adjustment unit adjusts the pace and content of the learning based on the user's progress. Specifically, an individualized learning plan is generated based on the evaluation results and the user's learning history. The adjustment unit adjusts the learning pace based on the user's physiological data and adjusts the learning materials in real time based on the feedback. For example, the adjustment unit monitors the user's heart rate and stress level and adjusts the learning load. If the user is tired, the adjustment unit slows down the learning pace and provides relaxing learning materials. Also, if the user is concentrating, the adjustment unit increases the learning pace and provides more difficult learning materials. Furthermore, the adjustment unit adjusts the learning content in real time based on the user's feedback. For example, if the user shows interest in a particular topic, additional learning materials related to that topic are provided. In this way, the adjustment unit can provide a flexible learning plan according to the user's individual needs and circumstances, and support effective learning.

[0085] The evaluation unit can analyze the pronunciation, grammar, and vocabulary usage of the language spoken by the user and evaluate the language skills of the user. The evaluation unit, for example, uses speech recognition technology to analyze the pronunciation of the user. For example, the evaluation unit evaluates phoneme accuracy, intonation, rhythm, etc. The evaluation unit also uses grammar analysis technology to evaluate grammar accuracy. For example, the evaluation unit evaluates sentence structure, tense agreement, grammatical accuracy, etc. Furthermore, the evaluation unit uses vocabulary analysis technology to analyze vocabulary usage. For example, the evaluation unit evaluates vocabulary richness, appropriate use, context-dependent selection, etc. This enables more accurate evaluation of language skills by analyzing the pronunciation, grammar, and vocabulary usage of the user. Part or all of the above-mentioned processing in the evaluation unit may be performed, for example, using AI, or may be performed without using AI. For example, the evaluation unit can input the user's pronunciation data to the generation AI and cause the generation AI to execute pronunciation evaluation.

[0086] The adjustment unit can generate an individualized learning plan based on the evaluation result by the evaluation unit and the user's learning history. For example, the adjustment unit creates a learning plan taking into consideration the user's learning goals, learning schedule, and selection of teaching materials. The adjustment unit can also monitor the user's progress in real time and adjust the learning plan as appropriate. For example, the adjustment unit can analyze the user's learning history, identify specific weaknesses, and generate a corresponding learning plan. In this way, an individualized learning plan can be generated, thereby providing the user with optimal learning content. Some or all of the above-mentioned processing in the adjustment unit may be performed, for example, using AI, or may be performed without using AI. For example, the adjustment unit can input the user's learning history data into the generation AI and cause the generation AI to generate a learning plan.

[0087] The feedback unit can evaluate the user's pronunciation using a voice analysis technology and provide specific pronunciation guidance. The feedback unit, for example, uses a voice analysis technology to evaluate the user's pronunciation. For example, the feedback unit analyzes the user's pronunciation using a voice recognition technology and evaluates the accuracy of phonemes, intonation, rhythm, and the like. The feedback unit also identifies problems with the user's pronunciation and makes correction suggestions in order to provide specific pronunciation guidance. For example, the feedback unit highlights the user's pronunciation errors in real time and makes correction suggestions. This makes it possible to provide specific pronunciation guidance by using the voice analysis technology. Some or all of the above-mentioned processing in the feedback unit may be performed using, for example, a generation AI, or may be performed without using a generation AI. For example, the feedback unit can input the user's pronunciation data into the generation AI and cause the generation AI to perform pronunciation evaluation and guidance.

[0088] The feedback unit can provide feedback according to the emotional state of the user. The feedback unit uses, for example, an emotion estimation algorithm to estimate the emotional state of the user. For example, the feedback unit analyzes the facial expression of the user using an expression analysis technique to calculate an emotion score. The feedback unit can also analyze the voice tone of the user using a voice analysis technique to calculate an emotion score. Furthermore, the feedback unit can collect physiological data (heart rate and electrodermal activity) with a sensor and estimate emotions using an emotion estimation algorithm. For example, the feedback unit calculates an emotion score based on the fluctuation of the heart rate. This enables more effective learning by providing feedback according to the emotional state of the user. The emotion estimation is realized using an emotion estimation function using, for example, an emotion engine or a generation AI. The generation AI is, for example, a text generation AI (for example, LLM) or a multimodal generation AI, but is not limited to such examples. A part or all of the above-mentioned processing in the feedback unit may be performed using, for example, an AI, or may be performed without using an AI. For example, the feedback unit can input image data of a user captured by a camera into the generation AI and have the generation AI estimate emotions.

[0089] The adjustment unit can adjust the learning pace based on the physiological data of the user. The adjustment unit, for example, uses a sensor to collect the physiological data of the user. For example, the adjustment unit collects and analyzes physiological data such as heart rate, skin electrodermal activity, and brain waves. The adjustment unit evaluates the stress level and concentration of the user based on the collected physiological data and adjusts the learning pace. For example, the adjustment unit slows down the learning pace when the user's heart rate is high. In addition, the adjustment unit can also speed up the learning pace when the user's heart rate is stable. This allows more effective learning by adjusting the learning pace based on the physiological data of the user. Part or all of the above-mentioned processing in the adjustment unit may be performed, for example, using AI or may be performed without using AI. For example, the adjustment unit can input the physiological data of the user to the generation AI and cause the generation AI to adjust the learning pace.

[0090] The feedback unit can highlight the user's grammar errors in real time and make correction suggestions. The feedback unit, for example, uses grammar analysis technology to detect the user's grammar errors. For example, the feedback unit uses a grammar check algorithm to detect and highlight the user's grammar errors in real time. The feedback unit also makes correction suggestions for the detected grammar errors. For example, when the user makes a grammar error, the feedback unit highlights the error location in real time and makes appropriate correction suggestions. This makes it possible to improve the user's grammar skills by highlighting the grammar errors in real time and making correction suggestions. Some or all of the above-mentioned processing in the feedback unit may be performed, for example, using a generation AI, or may be performed without using a generation AI. For example, the feedback unit can input the user's grammar error data to the generation AI and cause the generation AI to detect errors and make correction suggestions.

[0091] The evaluation unit can evaluate the richness of the user's vocabulary. The evaluation unit uses, for example, a vocabulary analysis technique to analyze the user's vocabulary usage. For example, the evaluation unit evaluates the number and diversity of vocabulary used by the user. The evaluation unit can also evaluate whether the user uses vocabulary appropriately. For example, the evaluation unit evaluates whether the user selects appropriate vocabulary according to the context. This enables a more accurate evaluation of language skills by evaluating the richness of the user's vocabulary. A part or all of the above-mentioned processing in the evaluation unit may be performed, for example, using AI, or may be performed without using AI. For example, the evaluation unit can input the user's vocabulary data to the generation AI and cause the generation AI to perform vocabulary evaluation.

[0092] The adjustment unit can adjust the teaching materials in real time based on the user's feedback. The adjustment unit, for example, uses a feedback analysis technique to collect and analyze the user's feedback. For example, the adjustment unit analyzes the feedback provided by the user in real time and adjusts the content and difficulty of the teaching materials. The adjustment unit can also adjust the learning plan as appropriate based on the user's feedback. For example, the adjustment unit changes the content of the teaching materials or adds new teaching materials based on the feedback provided by the user. This enables more effective learning by adjusting the teaching materials in real time based on the user's feedback. Some or all of the above-mentioned processing in the adjustment unit may be performed, for example, using AI or may be performed without using AI. For example, the adjustment unit can input the user's feedback data into the generation AI and cause the generation AI to adjust the teaching materials.

[0093] The system includes a control unit that controls smart home devices based on the evaluation results. For example, the control unit controls smart home devices such as lighting, temperature control, and sound systems to optimize the user's learning environment. The control unit adjusts the settings of the devices to provide an environment suitable for learning based on the user's evaluation results. For example, the control unit adjusts the lighting to provide a relaxing environment when the user's evaluation result is high. The control unit can also adjust the temperature to provide an environment where the user can concentrate when the user's evaluation result is low. This allows the learning environment to be optimized by controlling the smart home devices based on the evaluation results. Some or all of the above-mentioned processing in the control unit may be performed, for example, using AI or may be performed without using AI. For example, the control unit can input the user's evaluation result data to the generation AI and cause the generation AI to control the device.

[0094] The providing unit can provide teaching materials that allow the user to learn information about specific cultural events and holidays. The providing unit, for example, provides teaching materials including information about specific cultural events and holidays. For example, the providing unit collects information about cultural events and holidays that the user wants to learn about, and creates teaching materials based on the information. The providing unit provides text teaching materials, video teaching materials, interactive exercises, and the like that include information about cultural events and holidays selected by the user. This allows the user to deepen their cultural understanding by providing teaching materials that allow the user to learn information about specific cultural events and holidays. Some or all of the above-mentioned processing in the providing unit may be performed, for example, using AI, or may be performed without using AI. For example, the providing unit can input the user's selection data into the generating AI and cause the generating AI to create teaching materials.

[0095] The providing unit can provide teaching materials that enable the user to learn cultural background and daily conversations related to a specific region selected by the user. The providing unit provides teaching materials including, for example, cultural background and daily conversations related to a specific region. For example, the providing unit collects information about the region that the user wants to learn and creates teaching materials based on the information. The providing unit provides text teaching materials, video teaching materials, interactive exercises, and the like that include cultural background and daily conversations related to the region selected by the user. This allows the user to deepen their understanding of the region by providing teaching materials that enable the user to learn cultural background and daily conversations related to the specific region. Some or all of the above-mentioned processing in the providing unit may be performed, for example, using AI, or may be performed without using AI. For example, the providing unit can input the user's selection data into the generating AI and cause the generating AI to create teaching materials.

[0096] The evaluation unit can estimate the user's emotion and adjust the evaluation criteria based on the estimated user's emotion. The evaluation unit uses, for example, an emotion estimation algorithm to estimate the user's emotion. For example, the evaluation unit can analyze the user's facial expression using facial expression analysis technology and calculate an emotion score. The evaluation unit can also analyze the user's voice tone using voice analysis technology and calculate an emotion score. Furthermore, the evaluation unit can collect physiological data (heart rate and electrodermal activity) with a sensor and estimate the emotion using an emotion estimation algorithm. For example, the evaluation unit calculates an emotion score based on the fluctuation of the heart rate. The evaluation unit adjusts the evaluation criteria based on the estimated user's emotion. For example, if the user is nervous, the evaluation criteria can be relaxed to allow the user to relax. Also, if the user is relaxed, the evaluation criteria can be tightened and a more detailed evaluation can be performed. This allows for more accurate evaluation by adjusting the evaluation criteria based on the user's emotion. The emotion estimation is realized using an emotion estimation function using, for example, an emotion engine or a generation AI. The generation AI may be, but is not limited to, a text generation AI (e.g., LLM) or a multimodal generation AI. Some or all of the above-mentioned processes in the evaluation unit may be performed, for example, using an AI or may be performed without using an AI. For example, the evaluation unit may input user emotion data to the generation AI and cause the generation AI to adjust the evaluation criteria.

[0097] The evaluation unit can analyze the user's past learning history and improve the accuracy of the evaluation. The evaluation unit, for example, uses a learning history analysis technique to collect and analyze the user's past learning history. For example, the evaluation unit analyzes the content, learning time, achievement level, teaching materials used, etc., that the user has learned in the past, and improves the accuracy of the evaluation. The evaluation unit adjusts the evaluation criteria based on the user's past learning history. For example, the evaluation unit adjusts the evaluation criteria and identifies specific weak points based on the content that the user has learned in the past. The evaluation unit can also analyze the user's past learning history and collect data for improving the accuracy of the evaluation. As a result, the accuracy of the evaluation is improved by analyzing the past learning history. Some or all of the above-mentioned processing in the evaluation unit may be performed, for example, using AI, or may be performed without using AI. For example, the evaluation unit can input the user's learning history data to the generation AI and cause the generation AI to execute the improvement of the accuracy of the evaluation.

[0098] During the evaluation, the evaluation unit can analyze the user's pronunciation, grammar, and vocabulary usage in real time and provide immediate feedback. The evaluation unit, for example, uses speech recognition technology to analyze the user's pronunciation in real time. For example, the evaluation unit analyzes the pronunciation of the language spoken by the user in real time and provides immediate feedback. The evaluation unit also uses grammar analysis technology to analyze the user's grammatical errors in real time and provide immediate correction suggestions. For example, the evaluation unit detects the user's grammatical errors in real time and provides correction suggestions. Furthermore, the evaluation unit uses vocabulary analysis technology to analyze the user's vocabulary usage in real time and provide immediate evaluation. For example, the evaluation unit evaluates the number and diversity of vocabulary used by the user in real time. As a result, the user's learning effect is improved by analyzing in real time and providing immediate feedback. A part or all of the above-mentioned processing in the evaluation unit may be performed using, for example, AI, or may be performed without using AI. For example, the evaluation unit can input the user's pronunciation data, grammar data, and vocabulary data into the generation AI and cause the generation AI to perform real-time analysis and immediate feedback.

[0099] The evaluation unit can estimate the user's emotion and adjust the display method of the evaluation result based on the estimated user's emotion. The evaluation unit uses, for example, an emotion estimation algorithm to estimate the user's emotion. For example, the evaluation unit uses a facial expression analysis technique to analyze the user's facial expression and calculate an emotion score. The evaluation unit can also use a voice analysis technique to analyze the user's voice tone and calculate an emotion score. Furthermore, the evaluation unit can collect physiological data (heart rate and electrodermal activity) with a sensor and estimate the emotion using an emotion estimation algorithm. For example, the evaluation unit calculates an emotion score based on the fluctuation of the heart rate. The evaluation unit adjusts the display method of the evaluation result based on the estimated user's emotion. For example, if the user is nervous, the evaluation result is displayed simply so that the user can relax. Also, if the user is relaxed, detailed evaluation results are displayed so that the user can check the progress of learning. This deepens the user's understanding by adjusting the display method of the evaluation result based on the user's emotion. The emotion estimation is realized using an emotion estimation function using, for example, an emotion engine or a generation AI. The generation AI may be a text generation AI (e.g., LLM) or a multimodal generation AI, but is not limited to such examples. Some or all of the above-mentioned processing in the evaluation unit may be performed, for example, using AI, or may be performed without using AI. For example, the evaluation unit may input user emotion data to the generation AI and cause the generation AI to adjust the display method of the evaluation result.

[0100] The evaluation unit can customize the evaluation criteria by taking into account the geographical location information of the user at the time of evaluation. The evaluation unit, for example, uses GPS technology to acquire the geographical location information of the user. For example, when the user is in a specific region, the evaluation unit adjusts the evaluation criteria by taking into account the language characteristics of the region. In addition, when the user moves to a different region, the evaluation unit can also reset the evaluation criteria based on the language characteristics of the new region. Furthermore, the evaluation unit reflects the language characteristics specific to the region in the evaluation based on the geographical location information of the user. For example, when the user is in a specific region, the evaluation unit performs the evaluation by taking into account the dialect and accent of the region. As a result, by taking into account the geographical location information, it is possible to perform an evaluation specific to the region. A part or all of the above-mentioned processing in the evaluation unit may be performed, for example, using AI, or may be performed without using AI. For example, the evaluation unit can input the geographical location data of the user to the generation AI and cause the generation AI to execute customization of the evaluation criteria.

[0101] The evaluation unit can analyze the user's social media activities at the time of evaluation and reflect related vocabulary and expressions in the evaluation. The evaluation unit uses, for example, social media analysis technology to analyze the user's social media activities. For example, the evaluation unit analyzes the user's social media posts and reflects the vocabulary and expressions used in the evaluation. The evaluation unit can also identify vocabulary and expressions frequently used by the user and incorporate them into the evaluation criteria. Furthermore, the evaluation unit collects data for improving the accuracy of the evaluation based on the user's social media activities. For example, the evaluation unit analyzes the user's social media posts and reflects related vocabulary and expressions in the evaluation. As a result, the accuracy of the evaluation is improved by analyzing the social media activities. A part or all of the above-mentioned processing in the evaluation unit may be performed, for example, using AI or may be performed without using AI. For example, the evaluation unit can input the user's social media data to the generation AI and cause the generation AI to improve the accuracy of the evaluation.

[0102] The providing unit can estimate the user's emotion and adjust the difficulty of the teaching material based on the estimated user's emotion. The providing unit, for example, uses an emotion estimation algorithm to estimate the user's emotion. For example, the providing unit can analyze the user's facial expression using facial expression analysis technology and calculate an emotion score. The providing unit can also analyze the user's voice tone using voice analysis technology and calculate an emotion score. Furthermore, the providing unit can collect physiological data (heart rate and electrodermal activity) with a sensor and estimate the emotion using an emotion estimation algorithm. For example, the providing unit calculates an emotion score based on the fluctuation of the heart rate. The providing unit adjusts the difficulty of the teaching material based on the estimated user's emotion. For example, when the user is nervous, easy teaching material is provided to allow the user to relax. Also, when the user is relaxed, difficult teaching material can be provided to improve the effect of learning. As a result, the learning effect is improved by adjusting the difficulty of the teaching material based on the user's emotion. The estimation of the emotion is realized using an emotion estimation function using, for example, an emotion engine or a generation AI. The generation AI may be a text generation AI (e.g., LLM) or a multimodal generation AI, but is not limited to such examples. Some or all of the above-mentioned processing in the providing unit may be performed, for example, using AI, or may be performed without using AI. For example, the providing unit may input the user's emotion data to the generation AI and cause the generation AI to adjust the difficulty level of the teaching material.

[0103] The providing unit can select the optimal teaching material by referring to the user's past learning history at the time of providing. The providing unit, for example, uses a learning history analysis technique to collect and analyze the user's past learning history. For example, the providing unit analyzes the content, learning time, achievement level, teaching materials used, etc., that the user has learned in the past, and selects the optimal teaching material. The providing unit selects the optimal teaching material based on the user's past learning history. For example, the optimal teaching material is selected and specific weak points are identified based on the content that the user has learned in the past. The providing unit can also analyze the user's past learning history and collect data for selecting the optimal teaching material. As a result, the optimal teaching material can be provided by referring to the past learning history. A part or all of the above-mentioned processing in the providing unit may be performed, for example, using AI, or may be performed without using AI. For example, the providing unit can input the user's learning history data to the generating AI and cause the generating AI to select the optimal teaching material.

[0104] The providing unit can provide teaching materials in different formats according to the user's learning style at the time of providing. The providing unit uses, for example, a learning style analysis technique to evaluate the user's learning style. For example, the providing unit provides visual teaching materials when the user is a visual learner. The providing unit can also provide audio teaching materials when the user is an auditory learner. Furthermore, the providing unit can provide interactive teaching materials when the user is a tactile learner. For example, the providing unit selects and provides teaching materials in an optimal format according to the user's learning style. This improves the learning effect by providing teaching materials according to the learning style. A part or all of the above-mentioned processing in the providing unit may be performed, for example, using AI or may be performed without using AI. For example, the providing unit can input the user's learning style data to the generating AI and cause the generating AI to select the optimal teaching materials.

[0105] The providing unit can estimate the user's emotion and adjust the display method of the teaching material based on the estimated user's emotion. The providing unit uses, for example, an emotion estimation algorithm to estimate the user's emotion. For example, the providing unit analyzes the user's facial expression using facial expression analysis technology and calculates an emotion score. The providing unit can also analyze the user's voice tone using voice analysis technology and calculate an emotion score. Furthermore, the providing unit can collect physiological data (heart rate and electrodermal activity) with a sensor and estimate the emotion using an emotion estimation algorithm. For example, the providing unit calculates an emotion score based on the fluctuation of the heart rate. The providing unit adjusts the display method of the teaching material based on the estimated user's emotion. For example, when the user is nervous, a simple display method is provided to allow the user to relax. Also, when the user is relaxed, a detailed display method can be provided to enhance the effect of learning. As a result, the learning effect is improved by adjusting the display method of the teaching material based on the user's emotion. The emotion estimation is realized using an emotion estimation function using, for example, an emotion engine or a generation AI. The generation AI may be a text generation AI (e.g., LLM) or a multimodal generation AI, but is not limited to such examples. Some or all of the above-mentioned processing in the providing unit may be performed, for example, using AI, or may be performed without using AI. For example, the providing unit may input user emotion data to the generation AI and cause the generation AI to adjust the display method of the teaching material.

[0106] The providing unit can provide region-specific teaching materials in consideration of the geographical location information of the user at the time of providing. The providing unit uses, for example, GPS technology to acquire the geographical location information of the user. For example, when the user is in a specific region, the providing unit provides teaching materials related to the culture and language characteristics of the region. In addition, when the user moves to a different region, the providing unit can also provide teaching materials related to the culture and language characteristics of the new region. Furthermore, the providing unit provides region-specific teaching materials based on the geographical location information of the user. For example, when the user is in a specific region, the providing unit provides teaching materials related to the culture and language characteristics of the region. In this way, region-specific teaching materials can be provided by taking the geographical location information into consideration. A part or all of the above-mentioned processing in the providing unit may be performed, for example, using AI, or may be performed without using AI. For example, the providing unit can input the geographical location data of the user to the generating AI and cause the generating AI to provide region-specific teaching materials.

[0107] The providing unit can analyze the user's social media activity and provide related teaching materials at the time of providing. The providing unit, for example, uses a social media analysis technique to analyze the user's social media activity. For example, the providing unit analyzes the user's social media posts and provides teaching materials including related vocabulary and expressions. The providing unit can also identify vocabulary and expressions frequently used by the user and provide corresponding teaching materials. Furthermore, the providing unit collects data for providing related teaching materials based on the user's social media activity. For example, the providing unit analyzes the user's social media posts and provides teaching materials including related vocabulary and expressions. In this way, related teaching materials can be provided by analyzing social media activities. A part or all of the above-mentioned processing in the providing unit may be performed, for example, using AI, or may be performed without using AI. For example, the providing unit can input the user's social media data to the generating AI and cause the generating AI to provide related teaching materials.

[0108] The dialogue unit can estimate the user's emotion and adjust the tone and content of the dialogue based on the estimated user's emotion. The dialogue unit, for example, uses an emotion estimation algorithm to estimate the user's emotion. For example, the dialogue unit can analyze the user's facial expression using facial expression analysis technology and calculate an emotion score. The dialogue unit can also analyze the user's voice tone using voice analysis technology and calculate an emotion score. Furthermore, the dialogue unit can collect physiological data (heart rate and electrodermal activity) with a sensor and estimate the emotion using an emotion estimation algorithm. For example, the dialogue unit calculates an emotion score based on the fluctuation of the heart rate. The dialogue unit adjusts the tone and content of the dialogue based on the estimated user's emotion. For example, if the user is nervous, the dialogue can be conducted in a calm tone. Also, if the user is relaxed, the dialogue can be conducted in a bright tone. As a result, the effect of the dialogue is improved by adjusting the tone and content of the dialogue based on the user's emotion. The emotion estimation is realized using an emotion estimation function using, for example, an emotion engine or a generation AI. The generation AI may be, but is not limited to, a text generation AI (e.g., LLM) or a multimodal generation AI. Some or all of the above-mentioned processing in the dialogue unit may be performed, for example, using AI or may be performed without using AI. For example, the dialogue unit may input user emotion data to the generation AI and cause the generation AI to adjust the tone and content of the dialogue.

[0109] The dialogue unit can improve the accuracy of the dialogue by referring to the user's past dialogue history during the dialogue. The dialogue unit, for example, uses a dialogue history analysis technique to collect and analyze the user's past dialogue history. For example, the dialogue unit improves the accuracy of the dialogue based on the content of the dialogue the user has had in the past. The dialogue unit can also identify a specific weakness from the user's past dialogue history and engage in a dialogue corresponding to the weakness. Furthermore, the dialogue unit analyzes the user's past dialogue history and collects data for improving the accuracy of the dialogue. For example, the dialogue unit improves the accuracy of the dialogue based on the content of the user's past dialogue. As a result, the accuracy of the dialogue is improved by referring to the past dialogue history. A part or all of the above-mentioned processing in the dialogue unit may be performed, for example, using AI, or may be performed without using AI. For example, the dialogue unit can input the user's dialogue history data to the generation AI and cause the generation AI to execute the improvement of the dialogue accuracy.

[0110] The dialogue unit can adjust the difficulty of the dialogue in accordance with the user's learning progress during the dialogue. The dialogue unit uses, for example, a learning progress analysis technique to evaluate the user's learning progress. For example, the dialogue unit performs an easy dialogue when the user's learning progress is delayed. In addition, the dialogue unit can perform a difficult dialogue when the user's learning progress is good. Furthermore, the dialogue unit adjusts the difficulty of the dialogue in accordance with the user's learning progress. For example, the dialogue unit adjusts the difficulty of the dialogue based on the user's learning progress. As a result, the learning effect is improved by adjusting the difficulty of the dialogue in accordance with the learning progress. A part or all of the above-mentioned processing in the dialogue unit may be performed, for example, using AI, or may be performed without using AI. For example, the dialogue unit can input the user's learning progress data to the generation AI and cause the generation AI to adjust the difficulty of the dialogue.

[0111] The dialogue unit can estimate the user's emotion and adjust the order of dialogue based on the estimated user's emotion. The dialogue unit uses, for example, an emotion estimation algorithm to estimate the user's emotion. For example, the dialogue unit analyzes the user's facial expression using an expression analysis technique and calculates an emotion score. The dialogue unit can also analyze the user's voice tone using a voice analysis technique and calculate an emotion score. Furthermore, the dialogue unit can collect physiological data (heart rate and electrodermal activity) with a sensor and estimate the emotion using an emotion estimation algorithm. For example, the dialogue unit calculates an emotion score based on the fluctuation of the heart rate. The dialogue unit adjusts the order of dialogue based on the estimated user's emotion. For example, if the user is nervous, the dialogue can start with an easy dialogue. Also, if the user is relaxed, the dialogue can start with a more difficult dialogue. In this way, the effect of the dialogue is improved by adjusting the order of dialogue based on the user's emotion. The emotion estimation is realized using an emotion estimation function using, for example, an emotion engine or a generation AI. The generation AI is, for example, a text generation AI (for example, LLM) or a multimodal generation AI, but is not limited to such examples. A part or all of the above-mentioned processing in the dialogue unit may be performed using, for example, an AI, or may be performed without using an AI. For example, the dialogue unit may input the user's emotion data to the generation AI and cause the generation AI to adjust the order of dialogue.

[0112] The dialogue unit can provide region-specific dialogue content in consideration of the geographical location information of the user during dialogue. The dialogue unit, for example, uses GPS technology to acquire the geographical location information of the user. For example, when the user is in a specific region, the dialogue unit provides dialogue content related to the culture and language characteristics of the region. In addition, when the user moves to a different region, the dialogue unit can also provide dialogue content related to the culture and language characteristics of the new region. Furthermore, the dialogue unit provides region-specific dialogue content based on the geographical location information of the user. For example, when the user is in a specific region, the dialogue unit provides dialogue content related to the culture and language characteristics of the region. In this way, region-specific dialogue content can be provided by taking the geographical location information into consideration. Part or all of the above-mentioned processing in the dialogue unit may be performed, for example, using AI, or may be performed without using AI. For example, the dialogue unit can input the geographical location data of the user to the generation AI and cause the generation AI to provide region-specific dialogue content.

[0113] The dialogue unit can analyze the user's social media activity during dialogue and provide related dialogue content. The dialogue unit, for example, uses social media analysis technology to analyze the user's social media activity. For example, the dialogue unit analyzes the user's social media posts and provides dialogue content including related vocabulary and expressions. The dialogue unit can also identify vocabulary and expressions frequently used by the user and provide corresponding dialogue content. Furthermore, the dialogue unit collects data for providing related dialogue content based on the user's social media activity. For example, the dialogue unit analyzes the user's social media posts and provides dialogue content including related vocabulary and expressions. In this way, related dialogue content can be provided by analyzing social media activity. Part or all of the above-mentioned processing in the dialogue unit may be performed, for example, using AI or may be performed without using AI. For example, the dialogue unit can input the user's social media data to the generation AI and cause the generation AI to provide related dialogue content.

[0114] The feedback unit can estimate the user's emotion and adjust the content of the feedback based on the estimated user's emotion. The feedback unit uses, for example, an emotion estimation algorithm to estimate the user's emotion. For example, the feedback unit can analyze the user's facial expression using an expression analysis technique and calculate an emotion score. The feedback unit can also analyze the user's voice tone using a voice analysis technique and calculate an emotion score. Furthermore, the feedback unit can collect physiological data (heart rate and electrodermal activity) with a sensor and estimate the emotion using an emotion estimation algorithm. For example, the feedback unit calculates an emotion score based on the fluctuation of the heart rate. The feedback unit adjusts the content of the feedback based on the estimated user's emotion. For example, when the user is nervous, the feedback unit provides feedback in gentle words to allow the user to relax. Also, when the user is relaxed, the feedback unit can provide detailed feedback to enhance the effect of learning. As a result, the learning effect is improved by adjusting the content of the feedback based on the user's emotion. The emotion estimation is realized using an emotion estimation function using, for example, an emotion engine or a generation AI. The generation AI is, for example, a text generation AI (for example, LLM) or a multimodal generation AI, but is not limited to such examples. A part or all of the above-mentioned processing in the feedback unit may be performed using, for example, AI, or may be performed without using AI. For example, the feedback unit may input the user's emotion data to the generation AI and cause the generation AI to adjust the content of the feedback.

[0115] The feedback unit can improve the accuracy of the feedback by referring to the user's past learning history when providing feedback. The feedback unit, for example, uses a learning history analysis technique to collect and analyze the user's past learning history. For example, the feedback unit analyzes the content, learning time, achievement level, teaching materials used, etc., that the user has learned in the past, and improves the accuracy of the feedback. The feedback unit adjusts the content of the feedback based on the user's past learning history. For example, the feedback unit adjusts the content of the feedback based on the content that the user has learned in the past, and identifies specific weak points. The feedback unit can also analyze the user's past learning history and collect data for improving the accuracy of the feedback. As a result, the accuracy of the feedback is improved by referring to the past learning history. A part or all of the above-mentioned processing in the feedback unit may be performed, for example, using AI, or may be performed without using AI. For example, the feedback unit can input the user's learning history data to the generation AI and cause the generation AI to improve the accuracy of the feedback.

[0116] The feedback unit can highlight the user's pronunciation and grammar errors in real time and make correction suggestions at the time of feedback. The feedback unit, for example, uses a voice analysis technique to detect the user's pronunciation errors. For example, when the user makes a pronunciation error, the feedback unit highlights the user's pronunciation and makes a correction suggestion in real time. The feedback unit also uses a grammar analysis technique to detect the user's grammar errors. For example, when the user makes a grammar error, the feedback unit highlights the user's grammar error in real time and makes a correction suggestion. Furthermore, the feedback unit analyzes the user's pronunciation and grammar errors in real time and makes an immediate correction suggestion. For example, the feedback unit highlights the user's pronunciation errors in real time and makes a correction suggestion. As a result, the learning effect is improved by highlighting the pronunciation and grammar errors in real time and making a correction suggestion. A part or all of the above-mentioned processing in the feedback unit may be performed, for example, using AI, or may be performed without using AI. For example, the feedback unit can input the user's pronunciation data and grammar data to the generation AI and cause the generation AI to detect errors and make correction suggestions.

[0117] The feedback unit can estimate the user's emotion and adjust the display method of the feedback based on the estimated user's emotion. The feedback unit, for example, uses an emotion estimation algorithm to estimate the user's emotion. For example, the feedback unit can analyze the user's facial expression using facial expression analysis technology and calculate an emotion score. The feedback unit can also analyze the user's voice tone using voice analysis technology and calculate an emotion score. Furthermore, the feedback unit can collect physiological data (heart rate and electrodermal activity) with a sensor and estimate the emotion using an emotion estimation algorithm. For example, the feedback unit calculates an emotion score based on the fluctuation of the heart rate. The feedback unit adjusts the display method of the feedback based on the estimated user's emotion. For example, when the user is nervous, a simple display method is provided to allow the user to relax. Also, when the user is relaxed, a detailed display method can be provided to enhance the effect of learning. As a result, the learning effect is improved by adjusting the display method of the feedback based on the user's emotion. The emotion estimation is realized using an emotion estimation function using, for example, an emotion engine or a generation AI. The generation AI may be, but is not limited to, a text generation AI (e.g., LLM) or a multimodal generation AI. Some or all of the above-mentioned processing in the feedback unit may be performed, for example, using an AI, or may be performed without using an AI. For example, the feedback unit may input user emotion data to the generation AI and cause the generation AI to adjust the method of displaying the feedback.

[0118] The feedback unit can provide region-specific feedback by taking into account the geographical location information of the user at the time of feedback. The feedback unit, for example, uses GPS technology to acquire the geographical location information of the user. For example, when the user is in a specific region, the feedback unit provides feedback on the culture and language characteristics of the region. In addition, when the user moves to a different region, the feedback unit can also provide feedback on the culture and language characteristics of the new region. Furthermore, the feedback unit provides region-specific feedback based on the geographical location information of the user. For example, when the user is in a specific region, the feedback unit provides feedback on the culture and language characteristics of the region. In this way, region-specific feedback can be provided by taking into account the geographical location information. Part or all of the above-mentioned processing in the feedback unit may be performed, for example, using AI or may be performed without using AI. For example, the feedback unit can input the geographical location data of the user to the generation AI and cause the generation AI to provide region-specific feedback.

[0119] The feedback unit can analyze the user's social media activity and provide relevant feedback at the time of feedback. The feedback unit, for example, uses social media analysis technology to analyze the user's social media activity. For example, the feedback unit analyzes the user's social media posts and provides feedback including relevant vocabulary and expressions. The feedback unit can also identify vocabulary and expressions frequently used by the user and provide corresponding feedback. Furthermore, the feedback unit collects data for providing relevant feedback based on the user's social media activity. For example, the feedback unit analyzes the user's social media posts and provides feedback including relevant vocabulary and expressions. In this way, it is possible to provide relevant feedback by analyzing social media activity. Some or all of the above-mentioned processing in the feedback unit may be performed, for example, using AI or may be performed without using AI. For example, the feedback unit can input the user's social media data to the generation AI and cause the generation AI to provide relevant feedback.

[0120] The adjustment unit can estimate the user's emotion and adjust the learning pace based on the estimated user's emotion. The adjustment unit uses, for example, an emotion estimation algorithm to estimate the user's emotion. For example, the adjustment unit uses a facial expression analysis technique to analyze the user's facial expression and calculate an emotion score. The adjustment unit can also use a voice analysis technique to analyze the user's voice tone and calculate an emotion score. Furthermore, the adjustment unit can collect physiological data (heart rate and electrodermal activity) with a sensor and estimate the emotion using an emotion estimation algorithm. For example, the adjustment unit calculates an emotion score based on the fluctuation of the heart rate. The adjustment unit adjusts the learning pace based on the estimated user's emotion. For example, if the user is nervous, the learning pace is slowed down to allow the user to relax. Also, if the user is relaxed, the learning pace can be accelerated to improve the effect of learning. As a result, the learning effect is improved by adjusting the learning pace based on the user's emotion. The emotion estimation is realized using an emotion estimation function using, for example, an emotion engine or a generation AI. The generation AI may be, but is not limited to, a text generation AI (e.g., LLM) or a multimodal generation AI. Some or all of the above-mentioned processes in the adjustment unit may be performed, for example, using an AI, or may be performed without using an AI. For example, the adjustment unit may input the user's emotion data to the generation AI and cause the generation AI to adjust the learning pace.

[0121] During the adjustment, the adjustment unit can generate an optimal learning plan by referring to the user's past learning history. The adjustment unit uses, for example, a learning history analysis technique to collect and analyze the user's past learning history. For example, the adjustment unit analyzes the content, learning time, achievement level, teaching materials used, etc., that the user has learned in the past, and generates an optimal learning plan. The adjustment unit generates an optimal learning plan based on the user's past learning history. For example, the adjustment unit generates an optimal learning plan and identifies specific weak points based on the content that the user has learned in the past. The adjustment unit can also analyze the user's past learning history and collect data for generating an optimal learning plan. As a result, the optimal learning plan can be generated by referring to the past learning history. A part or all of the above-mentioned processing in the adjustment unit may be performed, for example, using AI, or may be performed without using AI. For example, the adjustment unit can input the user's learning history data to the generation AI and cause the generation AI to generate an optimal learning plan.

[0122] During the adjustment, the adjustment unit can analyze the physiological data of the user and customize the pace and content of the learning. The adjustment unit, for example, uses a sensor to collect the physiological data of the user. For example, the adjustment unit collects and analyzes physiological data such as heart rate, skin electrodermal activity, and brain waves. The adjustment unit evaluates the stress level and concentration of the user based on the collected physiological data, and customizes the learning pace and content. For example, the adjustment unit slows down the learning pace when the user's heart rate is high. In addition, the adjustment unit can also speed up the learning pace when the user's heart rate is stable. Furthermore, the adjustment unit customizes the learning content based on the physiological data of the user. For example, the adjustment unit analyzes the sleep data of the user and adjusts the learning content. As a result, the pace and content of the learning can be customized by analyzing the physiological data. Part or all of the above-mentioned processing in the adjustment unit may be performed, for example, using AI, or may be performed without using AI. For example, the adjustment unit can input the physiological data of the user to the generation AI and cause the generation AI to customize the learning pace and content.

[0123] The adjustment unit can estimate the user's emotion and determine the priority of the learning contents based on the estimated user's emotion. The adjustment unit uses, for example, an emotion estimation algorithm to estimate the user's emotion. For example, the adjustment unit analyzes the user's facial expression using an expression analysis technique and calculates an emotion score. The adjustment unit can also analyze the user's voice tone using a voice analysis technique and calculate an emotion score. Furthermore, the adjustment unit can collect physiological data (heart rate and electrodermal activity) with a sensor and estimate the emotion using an emotion estimation algorithm. For example, the adjustment unit calculates an emotion score based on the fluctuation of the heart rate. The adjustment unit determines the priority of the learning contents based on the estimated user's emotion. For example, when the user is nervous, easy learning contents are prioritized. Also, when the user is relaxed, learning contents with high difficulty can be prioritized. As a result, the learning effect is improved by determining the priority of the learning contents based on the user's emotion. The emotion estimation is realized using an emotion estimation function using, for example, an emotion engine or a generation AI. The generation AI is, for example, a text generation AI (for example, LLM) or a multimodal generation AI, but is not limited to such examples. A part or all of the above-mentioned processing in the adjustment unit may be performed using, for example, an AI, or may be performed without using an AI. For example, the adjustment unit may input the user's emotion data to the generation AI and cause the generation AI to determine the priority order of the learning contents.

[0124] During the adjustment, the adjustment unit can provide a region-specific learning plan by taking into account the geographical location information of the user. The adjustment unit uses, for example, GPS technology to acquire the geographical location information of the user. For example, when the user is in a specific region, the adjustment unit provides a learning plan related to the culture and language characteristics of the region. In addition, when the user moves to a different region, the adjustment unit can also provide a learning plan related to the culture and language characteristics of the new region. Furthermore, the adjustment unit provides a region-specific learning plan based on the geographical location information of the user. For example, when the user is in a specific region, the adjustment unit provides a learning plan related to the culture and language characteristics of the region. In this way, a region-specific learning plan can be provided by taking into account the geographical location information. Part or all of the above-mentioned processing in the adjustment unit may be performed, for example, using AI or may be performed without using AI. For example, the adjustment unit can input the geographical location data of the user to the generation AI and cause the generation AI to provide a region-specific learning plan.

[0125] At the time of adjustment, the adjustment unit can analyze the user's social media activity and provide related learning content. The adjustment unit, for example, uses social media analysis technology to analyze the user's social media activity. For example, the adjustment unit analyzes the user's social media posts and provides learning content including related vocabulary and expressions. The adjustment unit can also identify vocabulary and expressions frequently used by the user and provide corresponding learning content. Furthermore, the adjustment unit collects data for providing related learning content based on the user's social media activity. For example, the adjustment unit analyzes the user's social media posts and provides learning content including related vocabulary and expressions. In this way, related learning content can be provided by analyzing social media activity. Part or all of the above-mentioned processing in the adjustment unit may be performed, for example, using AI or may be performed without using AI. For example, the adjustment unit can input the user's social media data to the generation AI and cause the generation AI to provide related learning content.

[0126] The control unit can estimate the user's emotion and adjust the control method of the smart home device based on the estimated user's emotion. The control unit, for example, uses an emotion estimation algorithm to estimate the user's emotion. For example, the control unit can analyze the user's facial expression using facial expression analysis technology and calculate an emotion score. The control unit can also analyze the user's voice tone using voice analysis technology and calculate an emotion score. Furthermore, the control unit can collect physiological data (heart rate and electrodermal activity) with a sensor and estimate the emotion using an emotion estimation algorithm. For example, the control unit calculates an emotion score based on the fluctuation of the heart rate. The control unit adjusts the control method of the smart home device based on the estimated user's emotion. For example, when the user is nervous, the control unit controls the smart home device to provide an environment where the user can relax. Also, when the user is relaxed, the control unit can control the smart home device to provide an environment where the user can concentrate on learning. This allows the learning environment to be optimized by adjusting the control method of the smart home device based on the user's emotion. The emotion estimation is realized using an emotion estimation function using, for example, an emotion engine or a generation AI. The generation AI may be, but is not limited to, a text generation AI (e.g., LLM) or a multimodal generation AI. Some or all of the above-mentioned processing in the control unit may be performed, for example, using AI or may be performed without using AI. For example, the control unit may input user emotion data to the generation AI and cause the generation AI to adjust the control method of the smart home device.

[0127] During control, the control unit can select the optimal control method by referring to the user's past device usage history. The control unit, for example, uses a device usage history analysis technique to collect and analyze the user's past device usage history. For example, the control unit selects the optimal control method based on the device settings used by the user in the past. The control unit can also identify a specific setting from the user's past device usage history and select a control method corresponding to the setting. Furthermore, the control unit analyzes the user's past device usage history and collects data for selecting the optimal control method. For example, the control unit selects the optimal control method based on the device settings used by the user in the past. In this way, the optimal control method can be selected by referring to the past device usage history. A part or all of the above-mentioned processing in the control unit may be performed, for example, using AI or may be performed without using AI. For example, the control unit can input the user's device usage history data to the generation AI and cause the generation AI to select the optimal control method.

[0128] The control unit can customize the device settings according to the user's learning progress during control. The control unit uses, for example, a learning progress analysis technique to evaluate the user's learning progress. For example, when the user's learning progress is delayed, the control unit customizes the device settings to provide an environment where the user can concentrate. In addition, when the user's learning progress is good, the control unit can also customize the device settings to provide an environment where the user can relax. Furthermore, the control unit customizes the device settings according to the user's learning progress. For example, the control unit customizes the device settings based on the user's learning progress. This allows the learning environment to be optimized by customizing the device settings according to the learning progress. Part or all of the above-mentioned processing in the control unit may be performed, for example, using AI, or may be performed without using AI. For example, the control unit can input the user's learning progress data to the generation AI and cause the generation AI to execute customization of the device settings.

[0129] The control unit can estimate the user's emotion and adjust the device control sequence based on the estimated user's emotion. The control unit uses, for example, an emotion estimation algorithm to estimate the user's emotion. For example, the control unit analyzes the user's facial expression using facial expression analysis technology and calculates an emotion score. The control unit can also analyze the user's voice tone using voice analysis technology and calculate an emotion score. Furthermore, the control unit can collect physiological data (heart rate and electrodermal activity) with a sensor and estimate the emotion using an emotion estimation algorithm. For example, the control unit calculates an emotion score based on the heart rate fluctuation. The control unit adjusts the device control sequence based on the estimated user's emotion. For example, when the user is nervous, the device control sequence is adjusted to provide an environment where the user can relax. Also, when the user is relaxed, the device control sequence can be adjusted to provide an environment where the user can concentrate on learning. In this way, the learning environment can be optimized by adjusting the device control sequence based on the user's emotion. The emotion estimation is realized using an emotion estimation function using, for example, an emotion engine or a generation AI. The generation AI is, for example, a text generation AI (for example, LLM) or a multimodal generation AI, but is not limited to such examples. A part or all of the above-mentioned processing in the control unit may be performed using, for example, AI, or may be performed without using AI. For example, the control unit may input the user's emotion data to the generation AI and cause the generation AI to adjust the control sequence of the devices.

[0130] The control unit can provide region-specific device settings during control by taking into account the geographical location information of the user. The control unit, for example, uses GPS technology to acquire the geographical location information of the user. For example, when the user is in a specific region, the control unit provides device settings suitable for the culture and climate of the region. In addition, when the user moves to a different region, the control unit can also provide device settings suitable for the culture and climate of the new region. Furthermore, the control unit provides region-specific device settings based on the geographical location information of the user. For example, when the user is in a specific region, the control unit provides device settings suitable for the culture and climate of the region. In this way, region-specific device settings can be provided by taking into account the geographical location information. Part or all of the above-mentioned processing in the control unit may be performed, for example, using AI or may be performed without using AI. For example, the control unit can input the geographical location data of the user to the generation AI and cause the generation AI to provide region-specific device settings.

[0131] During control, the control unit can analyze the user's social media activity and provide the relevant device settings. The control unit, for example, uses social media analysis technology to analyze the user's social media activity. For example, the control unit analyzes the user's social media posts and provides the relevant device settings. The control unit can also identify device settings that are frequently used by the user and provide a corresponding control method. Furthermore, the control unit collects data for providing the relevant device settings based on the user's social media activity. For example, the control unit analyzes the user's social media posts and provides the relevant device settings. In this way, the relevant device settings can be provided by analyzing the social media activity. Some or all of the above-mentioned processing in the control unit may be performed, for example, using AI or may be performed without using AI. For example, the control unit can input the user's social media data to the generation AI and cause the generation AI to provide the relevant device settings.

[0132] The system according to the embodiment is not limited to the above-described example, and various modifications are possible, for example, as follows.

[0133] The evaluation unit may also take into account the user's learning style when evaluating the user's language skills. For example, if the user is a visual learner, the evaluation unit may use an evaluation method that includes many visual elements. If the user is an auditory learner, the evaluation unit may use an evaluation method that emphasizes audio. Furthermore, if the user is a tactile learner, the evaluation unit may use an evaluation method that includes interactive elements. This allows evaluation according to the user's learning style, resulting in a more accurate evaluation of language skills.

[0134] The evaluation unit may also take into account the user's social media activity when evaluating the user's language skills. For example, the evaluation unit may analyze the user's social media posts and reflect the vocabulary and expressions used in the evaluation. The evaluation unit may also identify vocabulary and expressions frequently used by the user and adjust the evaluation criteria based on the vocabulary and expressions. Furthermore, the evaluation unit may collect data to improve the accuracy of the evaluation based on the user's social media activity. This allows for a more accurate evaluation of language skills by taking social media activity into account.

[0135] The adjustment unit may also take into account the geographic location information of the user when adjusting the user's learning pace. For example, when the user is in a particular region, the adjustment unit adjusts the learning pace based on the culture and language characteristics of the region. Also, when the user moves to a different region, the adjustment unit may reset the learning pace based on the culture and language characteristics of the new region. Furthermore, the adjustment unit may provide a region-specific learning pace based on the user's geographic location information. In this way, a region-specific learning pace can be provided by taking into account the geographic location information.

[0136] The feedback unit may also take into account the user's learning history when highlighting the user's pronunciation and grammar errors in real time and making correction suggestions. For example, the feedback unit may identify specific weaknesses based on the user's past learning history and make corresponding correction suggestions. The feedback unit may also analyze the user's learning history and tailor the feedback content based on what was previously learned. Furthermore, the feedback unit may collect data based on the user's learning history to improve the accuracy of the feedback. This allows for more effective feedback to be provided by taking into account the learning history.

[0137] The feedback unit may also take into account the user's past emotional data when providing feedback according to the user's emotional state. For example, the feedback unit may provide feedback corresponding to a particular emotional state based on the user's past emotional data. The feedback unit may also analyze the user's emotional data and adjust the content of the feedback based on what feedback has been effective in the past. Furthermore, the feedback unit may collect data for improving the accuracy of the feedback based on the user's emotional data. In this way, more effective feedback can be provided by taking into account the past emotional data.

[0138] The adjustment unit can also take into account the user's past physiological data when adjusting the learning pace based on the user's physiological data. For example, the adjustment unit can provide a learning pace that corresponds to a specific physiological state based on the user's past physiological data. The adjustment unit can also analyze the user's physiological data and adjust the learning pace based on what learning pace was effective in the past. Furthermore, the adjustment unit can collect data for improving the accuracy of the learning pace based on the user's physiological data. In this way, a more effective learning pace can be provided by taking into account the past physiological data.

[0139] The feedback unit may also highlight the user's grammatical errors in real time and take into account the user's emotional state when making correction suggestions. For example, the feedback unit may provide gentle correction suggestions when the user is nervous, or provide detailed correction suggestions when the user is relaxed. Furthermore, the feedback unit may adjust the content of the correction suggestions based on the user's emotional state. This allows for more effective correction suggestions to be provided by taking into account the user's emotional state.

[0140] The evaluation unit may also take into account the geographic location information of the user when evaluating the richness of the user's vocabulary. For example, when the user is in a particular region, the evaluation unit may evaluate the vocabulary taking into account the language characteristics of the region. Also, when the user moves to a different region, the evaluation unit may reset the evaluation of the vocabulary based on the language characteristics of the new region. Furthermore, the evaluation unit may provide a region-specific vocabulary evaluation based on the geographic location information of the user. In this way, a region-specific vocabulary evaluation can be provided by taking into account the geographic location information.

[0141] The adjustment unit can also take into account the emotional state of the user when adjusting the learning material in real time based on the user's feedback. For example, the adjustment unit can provide easy learning material when the user is nervous, or provide more difficult learning material when the user is relaxed. Furthermore, the adjustment unit can adjust the content of the learning material based on the emotional state of the user. In this way, more effective learning material can be provided by taking the emotional state of the user into account.

[0142] The control unit may also take into account the emotional state of the user when controlling the smart home device based on the evaluation result. For example, when the user is nervous, the control unit may adjust the lighting to provide a relaxing environment. Also, when the user is relaxed, the control unit may adjust the temperature to provide an environment where the user can concentrate. Furthermore, the control unit may adjust the settings of the smart home device based on the emotional state of the user. In this way, a more effective learning environment can be provided by taking into account the emotional state of the user.

[0143] The process flow of the second embodiment will be briefly described below.

[0144] Step 1: The evaluation unit evaluates the language skills of the user. The evaluation unit analyzes the pronunciation, grammar, and vocabulary usage of the language spoken by the user to evaluate the language skills. The evaluation unit analyzes the user's pronunciation using speech recognition technology and evaluates the accuracy of grammar using grammar analysis technology. In addition, the evaluation unit analyzes the usage of vocabulary to evaluate the richness of vocabulary. Step 2: The provision unit provides learning materials according to the user's skill level based on the evaluation results by the evaluation unit. The provision unit provides text learning materials, audio learning materials, video learning materials, interactive exercises, etc., and selects and provides appropriate learning materials based on the user's evaluation results. Step 3: The dialogue unit uses the provided learning materials to dialogue with the user. The dialogue unit conducts voice dialogue, text dialogue, video dialogue, etc., evaluates the accuracy of the user's pronunciation and grammar in real time, and provides feedback. Step 4: The feedback unit provides real-time feedback on pronunciation and grammar based on the dialogue results of the dialogue unit. The feedback unit evaluates the user's pronunciation using speech analysis technology and provides specific pronunciation guidance. It also highlights the user's grammatical errors in real time and makes correction suggestions. Step 5: The adjustment unit adjusts the pace and content of the learning based on the user's progress. The adjustment unit generates an individualized learning plan based on the assessment results and the user's learning history. It adjusts the learning pace based on the user's physiological data and adjusts the learning materials in real time based on the feedback.

[0145] 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 a voice indicating a user input for the result of the specific processing. The control unit 46A transmits the voice data indicating the user input acquired by the microphone 38B to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the voice data.

[0146] The data generation model 58 is a so-called generative AI (Artificial Intelligence). An example of the data generation model 58 is ChatGPT (registered trademark) (Internet search<URL: https: / / openai.com / blog / chatgpt> ) and other generation AIs. The data generation model 58 is obtained by performing deep learning on a neural network. A prompt including an instruction is input to the data generation model 58, and inference data such as voice data indicating a voice, text data indicating a text, and image data indicating an image (e.g., still image data or video data) are input. The data generation model 58 infers the input inference data according to the instruction indicated by the prompt, and outputs the inference result in one or more data formats of voice data, text data, and image data. The data generation model 58 includes, for example, a text generation AI, an image generation AI, and a multimodal generation AI. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization. The specification processing unit 290 performs the above-mentioned specification processing while using the data generation model 58. The data generation model 58 may be a fine-tuned model so as to output an inference result from a prompt that does not include an instruction, and in this case, the data generation model 58 can output an inference result from a prompt that does not include an instruction. In the data processing device 12 and the like, the data generation model 58 includes a plurality of types, and the data generation model 58 includes an AI other than the generation AI. The AI ​​other than the generation AI is, for example, a linear regression, a logistic regression, a decision tree, a random forest, a support vector machine (SVM), a k-means clustering, a convolutional neural network (CNN), a recurrent neural network (RNN), a generative adversarial network (GAN), or a naive Bayes, and can perform various processes, but is not limited to such examples. The AI ​​may also be an AI agent. In addition, when the processes of each of the above-mentioned parts are performed by an AI, the processes are performed in part or in whole by the AI, but are not limited to such examples.In addition, processing performed by AI including the generation AI may be replaced with rule-based processing, and rule-based processing may be replaced with processing performed by AI including the generation AI.

[0147] Furthermore, the above-described processing by the data processing system 10 is executed by the specific processing unit 290 of the data processing device 12 or the control unit 46A of the smart device 14, but may also be executed by the specific processing unit 290 of the data processing device 12 and the control unit 46A of the smart device 14. Furthermore, the specific processing unit 290 of the data processing device 12 acquires or collects information required for processing from the smart device 14 or an external device, and the smart device 14 acquires or collects information required for processing from the data processing device 12 or an external device.

[0148] For example, the evaluation unit analyzes the user's pronunciation and grammar using the camera 42 and microphone 38B of the smart device 14, and evaluates the language skills using the specific processing unit 290 of the data processing device 12. The provision unit, for example, selects appropriate teaching materials using the specific processing unit 290 of the data processing device 12, and provides them through the output device 40 of the smart device 14. The dialogue unit performs voice dialogue or text dialogue using the control unit 46A of the smart device 14, and the feedback unit provides feedback on pronunciation and grammar in real time using the control unit 46A of the smart device 14 and the specific processing unit 290 of the data processing device 12. The adjustment unit generates a learning plan using the specific processing unit 290 of the data processing device 12, and adjusts the learning pace using the control unit 46A of the smart device 14. The control unit controls the smart home device using the specific processing unit 290 of the data processing device 12 to optimize the learning environment. The correspondence between each unit and the device or control unit is not limited to the above-mentioned example, and various changes are possible.

[0149] [Second embodiment] FIG. 3 shows an example of the configuration of a data processing system 210 according to the second embodiment.

[0150] 3, the data processing system 210 includes the data processing device 12 and smart glasses 214. An example of the data processing device 12 is a server.

[0151] 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. The database 24 and the communication I / F 26 are also connected to the bus 34. The communication I / F 26 is connected to a network 54. Examples of the network 54 include a WAN and / or a LAN.

[0152] The smart glasses 214 include a computer 36, a microphone 238, a speaker 240, a camera 42, and a communication I / F 44. The computer 36 includes a processor 46, a RAM 48, and a storage 50. The processor 46, the RAM 48, and the storage 50 are connected to a bus 52. The microphone 238, the speaker 240, and the camera 42 are also connected to the bus 52.

[0153] The microphone 238 receives instructions and the like from the user by receiving voice uttered by the user. The microphone 238 captures the voice uttered by the user, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs the voice according to instructions from the processor 46.

[0154] Camera 42 is a small digital camera equipped with an optical system including a lens, an aperture, and a shutter, and an imaging element such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, and captures images of the user's surroundings (e.g., an imaging range defined by an angle of view equivalent to the width of the field of vision of an average healthy person).

[0155] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 are responsible for the exchange of various information between the processor 46 and the processor 28 via the network 54. The exchange of various information between the processor 46 and the processor 28 using the communication I / Fs 44 and 26 is performed in a secure state.

[0156] Fig. 4 shows an example of main functions of the data processing device 12 and the smart glasses 214. As shown in Fig. 4, in the data processing device 12, a specific process is performed by the processor 28. A specific process program 56 is stored in the storage 32.

[0157] The processor 28 reads the specific processing program 56 from the storage 32, and executes the read specific processing program 56 on the RAM 30. The specific processing is realized by the processor 28 operating as a specific processing unit 290 in accordance with the specific processing program 56 executed on the RAM 30.

[0158] The storage 32 stores a data generation model 58 and an emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290. The identification processing unit 290 can estimate the emotion of the user using the emotion identification model 59 and perform identification processing using the user's emotion. In the emotion estimation function (emotion identification function) using the emotion identification model 59, various estimations and predictions regarding the user's emotion, including estimation and prediction of the user's emotion, are performed, but are not limited to such examples. In addition, the estimation and prediction of the emotion also include, for example, analysis of the emotion.

[0159] In the smart glasses 214, the 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 operating as the control unit 46A in accordance with the specific processing program 60 executed on the RAM 48. Note that the smart glasses 214 have a data generation model and an emotion identification model similar to the data generation model 58 and the emotion identification model 59, and can also perform processing similar to that of the specific processing unit 290 using these models.

[0160] Note that a device other than the data processing device 12 may have the data generation model 58. For example, a server device may have the data generation model 58. In this case, the data processing device 12 obtains a processing result (such as a prediction result) using the data generation model 58 by communicating with the server device having the data generation model 58. In addition, the data processing device 12 may be a server device, or may be a terminal device (such as a mobile phone, a robot, or a home appliance) owned by a user.

[0161] 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 a voice indicating a user input for the result of the specific processing. The control unit 46A transmits the voice data indicating the user input acquired by the microphone 238 to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the voice data.

[0162] The data generation model 58 is a so-called generative AI. An example of the data generation model 58 is a generative AI such as ChatGPT. The data generation model 58 is obtained by performing deep learning on a neural network. A prompt including an instruction is input to the data generation model 58, and inference data such as voice data indicating a voice, text data indicating a text, and image data indicating an image (e.g., still image data or video data) is input. The data generation model 58 infers the input inference data according to the instruction indicated by the prompt, and outputs the inference result in one or more data formats of voice data, text data, and image data. The data generation model 58 includes, for example, a text generation AI, an image generation AI, and a multimodal generation AI. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization. The specification processing unit 290 performs the above-mentioned specification processing while using the data generation model 58. The data generation model 58 may be a fine-tuned model so as to output an inference result from a prompt that does not include an instruction, and in this case, the data generation model 58 can output an inference result from a prompt that does not include an instruction. In the data processing device 12 and the like, the data generation model 58 includes a plurality of types, and the data generation model 58 includes an AI other than the generation AI. The AI ​​other than the generation AI is, for example, a linear regression, a logistic regression, a decision tree, a random forest, a support vector machine (SVM), a k-means clustering, a convolutional neural network (CNN), a recurrent neural network (RNN), a generative adversarial network (GAN), or a naive Bayes, and can perform various processes, but is not limited to such examples. The AI ​​may be an AI agent. In addition, when the processes of each part described above are performed by an AI, the processes are performed in part or in whole by the AI, but are not limited to such examples. In addition, the processes performed by the AI ​​including the generation AI may be replaced with rule-based processes, and the rule-based processes may be replaced with processes performed by the AI ​​including the generation AI.

[0163] The data processing system 210 according to the second embodiment performs the same processing as the data processing system 10 according to the first embodiment. The processing by the data processing system 210 is executed by the specific processing unit 290 of the data processing device 12 or the control unit 46A of the smart glasses 214, but may be executed 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 required for processing from the smart glasses 214 or an external device, and the smart glasses 214 acquires or collects information required for processing from the data processing device 12 or an external device.

[0164] For example, the evaluation unit analyzes the user's pronunciation and grammar using the camera 42 and microphone 238 of the smart glasses 214, and evaluates the language skills using the specific processing unit 290 of the data processing device 12. The provision unit, for example, selects appropriate teaching materials using the specific processing unit 290 of the data processing device 12 and provides them through the speaker 240 of the smart glasses 214. The dialogue unit performs voice dialogue or text dialogue using the control unit 46A of the smart glasses 214, and the feedback unit provides feedback on pronunciation and grammar in real time using the control unit 46A of the smart glasses 214 and the specific processing unit 290 of the data processing device 12. The adjustment unit generates a learning plan using the specific processing unit 290 of the data processing device 12, and adjusts the learning pace using the control unit 46A of the smart glasses 214. The control unit controls the smart home device using the specific processing unit 290 of the data processing device 12 to optimize the learning environment. The correspondence between each unit and the device or control unit is not limited to the above-mentioned example, and various changes are possible.

[0165] [Third embodiment] FIG. 5 shows an example of the configuration of a data processing system 310 according to the third embodiment.

[0166] 5, the data processing system 310 includes the data processing device 12 and a headset type terminal 314. An example of the data processing device 12 is a server.

[0167] 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. The database 24 and the communication I / F 26 are also connected to the bus 34. The communication I / F 26 is connected to a network 54. Examples of the network 54 include a WAN and / or a LAN.

[0168] The headset type terminal 314 includes a computer 36, a microphone 238, a speaker 240, a camera 42, a communication I / F 44, and a display 343. The computer 36 includes a processor 46, a RAM 48, and a storage 50. The processor 46, the RAM 48, and the storage 50 are connected to a bus 52. The microphone 238, the speaker 240, the camera 42, and the display 343 are also connected to the bus 52.

[0169] The microphone 238 receives instructions and the like from the user by receiving voice uttered by the user. The microphone 238 captures the voice uttered by the user, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs the voice according to instructions from the processor 46.

[0170] Camera 42 is a small digital camera equipped with an optical system including a lens, an aperture, and a shutter, and an imaging element such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, and captures images of the user's surroundings (e.g., an imaging range defined by an angle of view equivalent to the width of the field of vision of an average healthy person).

[0171] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 are responsible for the exchange of various information between the processor 46 and the processor 28 via the network 54. The exchange of various information between the processor 46 and the processor 28 using the communication I / Fs 44 and 26 is performed in a secure state.

[0172] Fig. 6 shows an example of the main functions of the data processing device 12 and the headset type terminal 314. As shown in Fig. 6, in the data processing device 12, a specific process is performed by the processor 28. A specific process program 56 is stored in the storage 32.

[0173] The processor 28 reads the specific processing program 56 from the storage 32, and executes the read specific processing program 56 on the RAM 30. The specific processing is realized by the processor 28 operating as a specific processing unit 290 in accordance with the specific processing program 56 executed on the RAM 30.

[0174] The storage 32 stores a data generation model 58 and an emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290. The identification processing unit 290 can estimate the emotion of the user using the emotion identification model 59 and perform identification processing using the user's emotion. In the emotion estimation function (emotion identification function) using the emotion identification model 59, various estimations and predictions regarding the user's emotion, including estimation and prediction of the user's emotion, are performed, but are not limited to such examples. In addition, the estimation and prediction of the emotion also include, for example, analysis of the emotion.

[0175] In the headset type terminal 314, the 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 operating as the control unit 46A in accordance with the specific program 60 executed on the RAM 48. Note that the headset type terminal 314 has a data generation model and an emotion identification model similar to the data generation model 58 and the emotion identification model 59, and can also perform processing similar to that of the identification processing unit 290 using these models.

[0176] Note that a device other than the data processing device 12 may have the data generation model 58. For example, a server device may have the data generation model 58. In this case, the data processing device 12 obtains a processing result (such as a prediction result) using the data generation model 58 by communicating with the server device having the data generation model 58. In addition, the data processing device 12 may be a server device, or may be a terminal device (such as a mobile phone, a robot, or a home appliance) owned by a user.

[0177] The specific processing unit 290 transmits the result of the specific processing to the headset type terminal 314. In the headset type terminal 314, the control unit 46A causes the speaker 240 and the display 343 to output the result of the specific processing. The microphone 238 acquires voice indicating a user input for the result of the specific processing. The control unit 46A transmits voice data indicating the user input acquired by the microphone 238 to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the voice data.

[0178] The data generation model 58 is a so-called generative AI. An example of the data generation model 58 is a generative AI such as ChatGPT. The data generation model 58 is obtained by performing deep learning on a neural network. A prompt including an instruction is input to the data generation model 58, and inference data such as voice data indicating a voice, text data indicating a text, and image data indicating an image (e.g., still image data or video data) is input. The data generation model 58 infers the input inference data according to the instruction indicated by the prompt, and outputs the inference result in one or more data formats of voice data, text data, and image data. The data generation model 58 includes, for example, a text generation AI, an image generation AI, and a multimodal generation AI. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization. The specification processing unit 290 performs the above-mentioned specification processing while using the data generation model 58. The data generation model 58 may be a fine-tuned model so as to output an inference result from a prompt that does not include an instruction, and in this case, the data generation model 58 can output an inference result from a prompt that does not include an instruction. In the data processing device 12 and the like, the data generation model 58 includes a plurality of types, and the data generation model 58 includes an AI other than the generation AI. The AI ​​other than the generation AI is, for example, a linear regression, a logistic regression, a decision tree, a random forest, a support vector machine (SVM), a k-means clustering, a convolutional neural network (CNN), a recurrent neural network (RNN), a generative adversarial network (GAN), or a naive Bayes, and can perform various processes, but is not limited to such examples. The AI ​​may be an AI agent. In addition, when the processes of each part described above are performed by an AI, the processes are performed in part or in whole by the AI, but are not limited to such examples. In addition, the processes performed by the AI ​​including the generation AI may be replaced with rule-based processes, and the rule-based processes may be replaced with processes performed by the AI ​​including the generation AI.

[0179] The data processing system 310 according to the third embodiment performs the same processing as the data processing system 10 according to the first embodiment. The processing by the data processing system 310 is executed by the specific processing unit 290 of the data processing device 12 or the control unit 46A of the headset type terminal 314, but may be executed by the specific processing unit 290 of the data processing device 12 and the control unit 46A of the headset type terminal 314. In addition, the specific processing unit 290 of the data processing device 12 acquires or collects information required for processing from the headset type terminal 314 or an external device, and the headset type terminal 314 acquires or collects information required for processing from the data processing device 12 or an external device.

[0180] For example, the evaluation unit analyzes the user's pronunciation and grammar using the camera 42 and microphone 238 of the headset type terminal 314, and evaluates the language skills using the specific processing unit 290 of the data processing device 12. The provision unit selects appropriate teaching materials using the specific processing unit 290 of the data processing device 12, and provides them through the speaker 240 of the headset type terminal 314. The dialogue unit performs voice dialogue or text dialogue using the control unit 46A of the headset type terminal 314, and the feedback unit provides feedback on pronunciation and grammar in real time using the control unit 46A of the headset type terminal 314 and the specific processing unit 290 of the data processing device 12. The adjustment unit generates a learning plan using the specific processing unit 290 of the data processing device 12, and adjusts the learning pace using the control unit 46A of the headset type terminal 314. The control unit controls the smart home device using the specific processing unit 290 of the data processing device 12 to optimize the learning environment. The correspondence between each unit and the device or control unit is not limited to the above-mentioned example, and various changes are possible.

[0181] [Fourth embodiment] FIG. 7 shows an example of the configuration of a data processing system 410 according to the fourth embodiment.

[0182] 7, a data processing system 410 includes a data processing device 12 and a robot 414. An example of the data processing device 12 is a server.

[0183] 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. The database 24 and the communication I / F 26 are also connected to the bus 34. The communication I / F 26 is connected to a network 54. Examples of the network 54 include a WAN and / or a LAN.

[0184] The robot 414 includes a computer 36, a microphone 238, a speaker 240, a camera 42, a communication I / F 44, and a control target 443. The computer 36 includes a processor 46, a RAM 48, and a storage 50. The processor 46, the RAM 48, and the storage 50 are connected to a bus 52. The microphone 238, the speaker 240, the camera 42, and the control target 443 are also connected to the bus 52.

[0185] The microphone 238 receives instructions and the like from the user by receiving voice uttered by the user. The microphone 238 captures the voice uttered by the user, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs the voice according to instructions from the processor 46.

[0186] Camera 42 is a small digital camera equipped with an optical system including a lens, an aperture, and a shutter, and an imaging element such as a CMOS image sensor or a CCD image sensor, and captures images of the user's surroundings (e.g., an imaging range defined by an angle of view equivalent to the width of the field of vision of a typical healthy person).

[0187] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 are responsible for the exchange of various information between the processor 46 and the processor 28 via the network 54. The exchange of various information between the processor 46 and the processor 28 using the communication I / Fs 44 and 26 is performed in a secure state.

[0188] The control object 443 includes a display device, LEDs in the eyes, and motors for driving the arms, hands, and legs. The posture and behavior of the robot 414 are controlled by controlling the motors of the arms, hands, and legs. Some of the emotions of the robot 414 can be expressed by controlling these motors. In addition, the facial expressions of the robot 414 can also be expressed by controlling the light emission state of the LEDs in the eyes of the robot 414.

[0189] Fig. 8 shows an example of the main functions of the data processing device 12 and the robot 414. As shown in Fig. 8, in the data processing device 12, a specific process is performed by the processor 28. A specific process program 56 is stored in the storage 32.

[0190] The processor 28 reads the specific processing program 56 from the storage 32, and executes the read specific processing program 56 on the RAM 30. The specific processing is realized by the processor 28 operating as a specific processing unit 290 in accordance with the specific processing program 56 executed on the RAM 30.

[0191] The storage 32 stores a data generation model 58 and an emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290. The identification processing unit 290 can estimate the emotion of the user using the emotion identification model 59 and perform identification processing using the user's emotion. In the emotion estimation function (emotion identification function) using the emotion identification model 59, various estimations and predictions regarding the user's emotion, including estimation and prediction of the user's emotion, are performed, but are not limited to such examples. In addition, the estimation and prediction of the emotion also include, for example, analysis of the emotion.

[0192] In the robot 414, the specific processing is performed by the processor 46. The storage 50 stores a specific program 60. The processor 46 reads out the specific program 60 from the storage 50, and executes the specific program 60 on the RAM 48. The specific processing is realized by the processor 46 operating as the control unit 46A in accordance with the specific program 60 executed on the RAM 48. The robot 414 has a data generation model and an emotion identification model similar to the data generation model 58 and the emotion identification model 59, and can also perform processing similar to that of the specific processing unit 290 using these models.

[0193] Note that a device other than the data processing device 12 may have the data generation model 58. For example, a server device may have the data generation model 58. In this case, the data processing device 12 obtains a processing result (such as a prediction result) using the data generation model 58 by communicating with the server device having the data generation model 58. In addition, the data processing device 12 may be a server device, or may be a terminal device (such as a mobile phone, a robot, or a home appliance) owned by a user.

[0194] The specific processing unit 290 transmits the result of the specific processing to the robot 414. In the robot 414, the control unit 46A causes the speaker 240 and the control target 443 to output the result of the specific processing. The microphone 238 acquires a voice indicating a user input for the result of the specific processing. The control unit 46A transmits voice data indicating the user input acquired by the microphone 238 to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the voice data.

[0195] The data generation model 58 is a so-called generative AI. An example of the data generation model 58 is a generative AI such as ChatGPT. The data generation model 58 is obtained by performing deep learning on a neural network. A prompt including an instruction is input to the data generation model 58, and inference data such as voice data indicating a voice, text data indicating a text, and image data indicating an image (e.g., still image data or video data) is input. The data generation model 58 infers the input inference data according to the instruction indicated by the prompt, and outputs the inference result in one or more data formats of voice data, text data, and image data. The data generation model 58 includes, for example, a text generation AI, an image generation AI, and a multimodal generation AI. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization. The specification processing unit 290 performs the above-mentioned specification processing while using the data generation model 58. The data generation model 58 may be a fine-tuned model so as to output an inference result from a prompt that does not include an instruction, and in this case, the data generation model 58 can output an inference result from a prompt that does not include an instruction. In the data processing device 12 and the like, the data generation model 58 includes a plurality of types, and the data generation model 58 includes an AI other than the generation AI. The AI ​​other than the generation AI is, for example, a linear regression, a logistic regression, a decision tree, a random forest, a support vector machine (SVM), a k-means clustering, a convolutional neural network (CNN), a recurrent neural network (RNN), a generative adversarial network (GAN), or a naive Bayes, and can perform various processes, but is not limited to such examples. The AI ​​may be an AI agent. In addition, when the processes of each part described above are performed by an AI, the processes are performed in part or in whole by the AI, but are not limited to such examples. In addition, the processes performed by the AI ​​including the generation AI may be replaced with rule-based processes, and the rule-based processes may be replaced with processes performed by the AI ​​including the generation AI.

[0196] The data processing system 410 according to the fourth embodiment performs the same processing as the data processing system 10 according to the first embodiment. The processing by the data processing system 410 is executed by the specific processing unit 290 of the data processing device 12 or the control unit 46A of the robot 414, but may be executed 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 required for processing from the robot 414 or an external device, etc., and the robot 414 acquires or collects information required for processing from the data processing device 12 or an external device, etc.

[0197] For example, the evaluation unit analyzes the user's pronunciation and grammar using the camera 42 and microphone 238 of the robot 414, and evaluates the language skills using the specific processing unit 290 of the data processing device 12. The provision unit selects appropriate teaching materials using the specific processing unit 290 of the data processing device 12, and provides them through the speaker 240 of the robot 414. The dialogue unit performs voice dialogue or text dialogue using the control unit 46A of the robot 414, and the feedback unit provides feedback on pronunciation and grammar in real time using the control unit 46A of the robot 414 and the specific processing unit 290 of the data processing device 12. The adjustment unit generates a learning plan using the specific processing unit 290 of the data processing device 12, and adjusts the learning pace using the control unit 46A of the robot 414. The control unit controls the smart home device using the specific processing unit 290 of the data processing device 12 to optimize the learning environment. The correspondence between each unit and the device or control unit is not limited to the above-mentioned example, and various changes are possible.

[0198] The emotion identification model 59 as an emotion engine may determine the emotion of the user according to a specific mapping. Specifically, the emotion identification model 59 may determine the emotion of the user according to an emotion map (see FIG. 9), which is a specific mapping. Similarly, the emotion identification model 59 may determine the emotion of the robot, and the identification processing unit 290 may perform identification processing using the emotion of the robot.

[0199] FIG. 9 is a diagram showing an emotion map 400 on which multiple emotions are mapped. In the emotion map 400, emotions are arranged in concentric circles radiating from the center. The closer to the center of the concentric circles, the more primitive emotions are arranged. The more outside the concentric circles, the more emotions that represent states and actions that arise from a state of mind are arranged. Emotions are a concept that includes emotions and mental states. On the left side of the concentric circles, emotions that are generally generated from reactions that occur in the brain are arranged. On the right side of the concentric circles, emotions that are generally induced by situational judgment are arranged. On the upper and lower sides of the concentric circles, emotions that are generally generated from reactions that occur in the brain and are induced by situational judgment are arranged. In addition, on the upper side of the concentric circles, emotions of "pleasure" are arranged, and on the lower side, emotions of "discomfort" are arranged. In this way, in the emotion map 400, multiple emotions are mapped based on the structure in which emotions are generated, and emotions that tend to occur simultaneously are mapped close to each other.

[0200] These emotions are distributed in the 3 o'clock direction of emotion map 400 and usually fluctuate between relief and anxiety. In the right half of emotion map 400, situational awareness dominates over internal sensations, resulting in a sense of calm.

[0201] The inside of emotion map 400 represents what is going on inside one's mind, and the outside of emotion map 400 represents behavior, so the further out you go on emotion map 400, the more visible the emotions become (the more they are expressed in behavior).

[0202] Here, human emotions are based on various balances such as posture and blood sugar level, and when these balances are far from the ideal, it indicates an unpleasant state, and when they are close to the ideal, it indicates a pleasant state. Emotions can also be created for robots, cars, motorcycles, etc., based on various balances such as posture and battery level, so that when these balances are far from the ideal, it indicates an unpleasant state, and when they are close to the ideal, it indicates a pleasant state. The emotion map may be generated, for example, based on the emotion map of Dr. Mitsuyoshi (Research on speech emotion recognition and emotion brain physiological signal analysis system, Tokushima University, doctoral dissertation: https: / / ci.nii.ac.jp / naid / 500000375379). On the left half of the emotion map, emotions belonging to an area called "reaction" where sensation is dominant are lined up. On the right half of the emotion map, emotions belonging to an area called "situation" where situation recognition is dominant are lined up.

[0203] The emotion map defines two emotions that promote learning. The first is the negative emotion around the middle of "repentance" or "remorse" on the situation side. In other words, this 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 positive emotion around "desire" on the response side. In other words, this is when the robot has positive feelings such as "I want more" or "I want to know more."

[0204] The emotion identification model 59 inputs the user input to a pre-trained neural network, obtains emotion values ​​indicating each emotion shown in the emotion map 400, and determines the emotion of the user. This neural network is pre-trained based on multiple learning data that are combinations of the user input and emotion values ​​indicating each emotion shown in the emotion map 400. Furthermore, this neural network is trained so that emotions that are located close to each other have similar values, as in the emotion map 900 shown in Fig. 10. Fig. 10 shows an example in which multiple emotions, "relief," "calm," and "encouraging," have similar emotion values.

[0205] In the above embodiment, an example was given in which a specific process is performed by one computer 22, but the technology disclosed herein is not limited to this, and distributed processing of the specific process may be performed by multiple computers, including computer 22.

[0206] In the above embodiment, an example in which the specific processing program 56 is stored in the storage 32 has been described, but the technology of the present disclosure is not limited to this. For example, the specific processing program 56 may be stored in a portable computer-readable non-transitory storage medium such as a Universal Serial Bus (USB) memory. The specific processing program 56 stored in the non-transitory storage medium is installed in the computer 22 of the data processing device 12. The processor 28 executes the specific processing in accordance with the specific processing program 56.

[0207] In addition, 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 upon request from the data processing device 12.

[0208] It is not necessary to store all of the specific processing program 56 in a storage device such as a server connected to the data processing device 12 via the network 54, or to store all of the specific processing program 56 in the storage 32; only a portion of the specific processing program 56 may be stored.

[0209] As the hardware resource for executing the specific process, various processors as shown below can be used. An example of the processor is a CPU, which is a general-purpose processor that functions as a hardware resource for executing the specific process by executing software, i.e., a program. Another example of the processor is a dedicated electric circuit, which is a processor having a circuit configuration designed exclusively for executing a specific process, such as a Field-Programmable Gate Array (FPGA), a Programmable Logic Device (PLD), or an Application Specific Integrated Circuit (ASIC). Each processor has a built-in or connected memory, and each processor executes the specific process by using the memory.

[0210] The hardware resource that executes the specific process may be one of these various processors, or may be a combination of two or more processors of the same or different types (for example, a combination of multiple FPGAs, or a combination of a CPU and an FPGA). Also, the hardware resource that executes the specific process may be a single processor.

[0211] As an example of a configuration using one processor, first, one processor is configured by combining one or more CPUs and software, and this processor functions as a hardware resource that executes a specific process. Second, there is a configuration using a processor that realizes the functions of the entire system including multiple hardware resources that execute a specific process on a single IC chip, as typified by SoC (System-on-a-chip). In this way, a specific process is realized using one or more of the above-mentioned various processors as hardware resources.

[0212] Furthermore, more specifically, the hardware structure of these various processors can be an electric circuit that combines circuit elements such as semiconductor elements. The specific processes described above are merely examples. It goes without saying that unnecessary steps may be deleted, new steps may be added, or the order of processes may be changed without departing from the spirit of the invention.

[0213] In the above example, the first to fourth embodiments are described separately, but some or all of these embodiments may be combined. The smart device 14, the smart glasses 214, the headset terminal 314, and the robot 414 are only examples, and they may be combined with each other, or may be other devices. In the above example, the first and second embodiments are described separately, but they may be combined.

[0214] The above description and illustrations are detailed descriptions of the parts related to the technology of the present disclosure, and are merely an example of the technology of the present disclosure. For example, the above description of the configuration, function, action, and effect is an example of the configuration, function, action, and effect of the parts related to the technology of the present disclosure. Therefore, it goes without saying that unnecessary parts may be deleted, new elements may be added, or replaced with respect to the description and illustrations shown above, within the scope of the gist of the technology of the present disclosure. In addition, in order to avoid confusion and to facilitate understanding of the parts related to the technology of the present disclosure, the description and illustrations shown above omit explanations of technical common sense that do not require particular explanation in enabling the implementation of the technology of the present disclosure.

[0215] All publications, patent applications, and standards mentioned in this specification are herein incorporated by reference to the same extent as if each individual publication, patent application, and standard was specifically and individually indicated to be incorporated by reference.

[0216] (Appendix 1) an evaluation unit for evaluating a user's language skills; a providing unit that provides educational materials according to a skill level of the user based on a result of the evaluation by the evaluating unit; A dialogue unit that uses the teaching material to have a dialogue with the user; a feedback unit that provides feedback on pronunciation and grammar in real time based on a dialogue result by the dialogue unit; and an adjustment unit that adjusts the pace and content of learning based on the user's progress. (Appendix 2) The evaluation unit is A system for assessing the language skills of a user by analyzing the pronunciation, grammar, and vocabulary usage of the language spoken by the user. (Appendix 3) The adjustment unit is A system that generates an individualized learning plan based on the evaluation results by the evaluation unit and the user's learning history. (Appendix 4) The feedback unit is Evaluating the user's pronunciation using voice analysis technology and providing specific pronunciation guidance 2. The system of claim 1, (Appendix 5) The feedback unit is Providing feedback according to the emotional state of the user 2. The system of claim 1, (Appendix 6) The adjustment unit is Adjusting the pace of learning based on physiological data of the user 2. The system of claim 1, (Appendix 7) The feedback unit is Highlighting the user's grammar errors in real time and providing correction suggestions 2. The system of claim 1, (Appendix 8) The evaluation unit is Evaluate the user's vocabulary 2. The system of claim 1, (Appendix 9) The adjustment unit is Adjusting the educational material in real time based on the user's feedback 2. The system of claim 1, (Appendix 10) Equipped with a control unit that controls smart home devices based on the evaluation results 2. The system of claim 1, (Appendix 11) The providing unit is Providing educational materials that allow said users to learn information about certain cultural events and holidays 2. The system of claim 1, (Appendix 12) The providing unit is Providing educational materials that enable users to learn about cultural background and everyday conversations related to a specific region selected by the user 2. The system of claim 1, (Appendix 13) The evaluation unit is Inferring user emotions and adjusting evaluation criteria based on the estimated user emotions 2. The system of claim 1, (Appendix 14) The evaluation unit is Analyze users' past learning history to improve the accuracy of evaluations 2. The system of claim 1, (Appendix 15) The evaluation unit is During the assessment, the system analyzes the user's pronunciation, grammar and vocabulary usage in real time to provide immediate feedback 2. The system of claim 1, (Appendix 16) The evaluation unit is Inferring user emotion and adjusting the way rating results are displayed based on the estimated user emotion 2. The system of claim 1, (Appendix 17) The evaluation unit is Customize evaluation criteria by considering the user's geographic location during evaluation 2. The system of claim 1, (Appendix 18) The evaluation unit is During the evaluation, the user's social media activity is analyzed and relevant vocabulary and expressions are reflected in the evaluation. 2. The system of claim 1, (Appendix 19) The providing unit is Estimating a user's emotions and adjusting the difficulty of learning materials based on the estimated user's emotions 2. The system of claim 1, (Appendix 20) The providing unit is When providing the learning materials, the most suitable learning materials are selected by referring to the user's past learning history. 2. The system of claim 1, (Appendix 21) The providing unit is At the time of delivery, the material is presented in different formats depending on the user's learning style. 2. The system of claim 1, (Appendix 22) The providing unit is Estimating a user's emotions and adjusting the way educational materials are displayed based on the estimated user's emotions 2. The system of claim 1, (Appendix 23) The providing unit is At the time of delivery, the site provides region-specific educational materials by taking into account the user's geographic location. 2. The system of claim 1, (Appendix 24) The providing unit is When offered, analyze your social media activity to provide you with relevant educational materials 2. The system of claim 1, (Appendix 25) The dialogue unit includes: Infer user emotions and adjust the tone and content of the dialogue based on the inferred user emotions 2. The system of claim 1, (Appendix 26) The dialogue unit includes: During dialogue, the accuracy of the dialogue is improved by referring to the user's past dialogue history. 2. The system of claim 1, (Appendix 27) The dialogue unit includes: During dialogue, the difficulty of the dialogue is adjusted according to the user's learning progress. 2. The system of claim 1, (Appendix 28) The dialogue unit includes: Estimate user emotions and adjust dialogue order based on the estimated user emotions 2. The system of claim 1, (Appendix 29) The dialogue unit includes: During dialogue, the system takes into account the user's geographic location to provide region-specific dialogue content. 2. The system of claim 1, (Appendix 30) The dialogue unit includes: Analyze your social media activity during interactions and provide relevant conversation content 2. The system of claim 1, (Appendix 31) The feedback unit is Inferring user emotions and adjusting feedback based on the estimated user emotions 2. The system of claim 1, (Appendix 32) The feedback unit is When providing feedback, the accuracy of the feedback can be improved by referring to the user's past learning history. 2. The system of claim 1, (Appendix 33) The feedback unit is During feedback, the system highlights the user's pronunciation and grammar errors in real time and offers correction suggestions 2. The system of claim 1, (Appendix 34) The feedback unit is Inferring a user's emotions and adjusting the way feedback is presented based on the inferred user emotions 2. The system of claim 1, (Appendix 35) The feedback unit is When providing feedback, consider the user's geographic location to provide location-specific feedback 2. The system of claim 1, (Appendix 36) The feedback unit is When feedback is provided, analyze the user's social media activity and provide relevant feedback 2. The system of claim 1, (Appendix 37) The adjustment unit is Inferring a user's emotions and adjusting the learning pace based on the estimated user's emotions 2. The system of claim 1, (Appendix 38) The adjustment unit is When making adjustments, the system generates an optimal learning plan by referring to the user's past learning history. 2. The system of claim 1, (Appendix 39) The adjustment unit is During training, the physiological data of the user is analyzed to customize the pace and content of learning. 2. The system of claim 1, (Appendix 40) The adjustment unit is Estimate user emotions and prioritize learning content based on the estimated user emotions 2. The system of claim 1, (Appendix 41) The adjustment unit is When adjusting, it takes into account the user's geographic location to provide location-specific learning plans. 2. The system of claim 1, (Appendix 42) The adjustment unit is Analyze users' social media activity and provide relevant learnings when making adjustments 2. The system of claim 1, (Appendix 43) The control unit is To estimate a user's emotion and adjust a control method of a smart home device based on the estimated user's emotion. 2. The system of claim 1, (Appendix 44) The control unit is When controlling devices, the system selects the optimal control method by referring to the user's past device usage history. 2. The system of claim 1, (Appendix 45) The control unit is When controlling, customize device settings according to the user's learning progress 2. The system of claim 1, (Appendix 46) The control unit is Estimating a user's emotion and adjusting the device control sequence based on the estimated user's emotion 2. The system of claim 1, (Appendix 47) The control unit is When controlling, the geographic location of the user is taken into account to provide region-specific device settings 2. The system of claim 1, (Appendix 48) The control unit is When in control, analyze your social media activity and provide relevant device settings 2. The system of claim 1, [Explanation of symbols]

[0217] 10, 210, 310, 410 Data Processing Systems 12 Data Processing Device 14 Smart Devices 214 Smart Glasses 314 Headset-type terminal 414 Robot

Claims

1. an evaluation unit for evaluating a user's language skills; a providing unit that provides educational materials according to a skill level of the user based on a result of the evaluation by the evaluating unit; A dialogue unit that uses the teaching material to have a dialogue with the user; a feedback unit that provides feedback on pronunciation and grammar in real time based on a dialogue result by the dialogue unit; and an adjustment unit that adjusts the pace and content of learning based on the user's progress.

2. The evaluation unit is Analyzing the pronunciation, grammar, and vocabulary usage of the language spoken by the user to assess the language skills of the user 2. The system of claim 1 .

3. The adjustment unit is A personalized learning plan is generated based on the evaluation result by the evaluation unit and the learning history of the user.

2. The system of claim 1 .

4. The feedback unit is Evaluating the user's pronunciation using voice analysis technology and providing specific pronunciation guidance 2. The system of claim 1 .

5. The feedback unit is Providing feedback according to the emotional state of the user 2. The system of claim 1 .

6. The adjustment unit is Adjusting the pace of learning based on physiological data of the user 2. The system of claim 1 .

7. The feedback unit is Highlighting the user's grammar errors in real time and providing correction suggestions 2. The system of claim 1 .

8. The evaluation unit is Evaluate the user's vocabulary 2. The system of claim 1 .

9. The adjustment unit is Adjusting the educational material in real time based on the user's feedback 2. The system of claim 1 .

Images