system

Abstract

The system according to the embodiment aims to record a user's learning progress while having a real-time conversation with a native speaker. [Solution] A system according to an embodiment includes a matching unit, a support unit, and a recording unit. The matching unit matches a native speaker based on a user's selection. The support unit supports real-time conversation between the user and the native speaker matched by the matching unit. The recording unit records the user's learning progress based on the content of the conversation supported by the support unit.

Description

[Technical Field]

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

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

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

[0004] Conventional technologies do not adequately allow users to record their learning progress while conversing with native speakers in real time, and there is room for improvement.

[0005] The system according to the embodiment aims to record a user's learning progress while having a real-time conversation with a native speaker. [Means for solving the problem]

[0006] The system according to the embodiment includes a matching unit, a support unit, and a recording unit. The matching unit matches a native speaker based on a user's selection. The support unit supports real-time conversation between the user and the native speaker matched by the matching unit. The recording unit records the user's learning progress based on the content of the conversation supported by the support unit. [Effects of the Invention]

[0007] The system according to the embodiment allows users to record their learning progress while conversing with native speakers in real time. [Brief explanation of the drawings]

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

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

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

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

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

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

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

[0015] In the following embodiments, "A and / or B" is synonymous with "at least one of A and B." In other words, "A and / or B" means that it may be only A, only B, or a combination of A and B. Furthermore, in this specification, the same concept as "A and / or B" is also applied when three or more things are expressed connected by "and / or."

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

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

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

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

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

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

[0022] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 control the exchange of various information between the processor 46 and the processor 28 via the network 54.

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

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

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

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

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

[0028] (Example 1) An English learning support system according to an embodiment of the present invention provides an online English conversation app specialized for English learning using a generative AI. This English learning support system begins when a user logs in to the app and selects a conversation topic and level. The generative AI then matches an appropriate native speaker based on the user's selection. The matched native speaker and the user then begin a real-time conversation within the app. The generative AI then supports the conversation and provides appropriate feedback. For example, if the user makes a grammatical error, the generative AI points out the error and suggests a correct expression. When the user learns a new word, the generative AI explains the meaning and usage of the word. Furthermore, based on the content of the conversation, the generative AI records the user's learning progress and reflects it in the next conversation. This app enables users to effectively learn English through real-time conversations with native speakers. Furthermore, with the support of the generative AI, users can learn at their own pace and efficiently improve their English skills. For example, a user logs in to the app and selects a conversation topic and level. The generative AI then matches an appropriate native speaker based on the user's selection. The matched native speaker and the user then begin a real-time conversation within the app. During this process, the generative AI supports the conversation and provides appropriate feedback. For example, if the user makes a grammatical error, the generative AI will point out the mistake and suggest the correct expression. Also, if the user learns a new word, the generative AI will explain the meaning and usage of that word. Furthermore, based on the content of the conversation, the generative AI records the user's learning progress and reflects it in the next conversation. This app allows users to effectively learn English through real-time conversations with native speakers. Furthermore, with the support of the generative AI, users can study at their own pace and efficiently improve their English skills. This allows the English learning support system to match users with native speakers based on their selections, support real-time conversations, and record learning progress, enabling effective English learning.

[0029] An English learning support system according to an embodiment includes a matching unit, a support unit, and a recording unit. The matching unit matches a native speaker based on a user's selection. The user's selection may include, but is not limited to, a conversation topic or level. For example, if a user wants to learn business English, the matching unit may select a native speaker with business experience. If a user wants to learn travel English, the matching unit may select a native speaker knowledgeable about travel. If a user is interested in a particular hobby, the matching unit may select a native speaker knowledgeable about that hobby. The support unit supports real-time conversations between the user and the native speaker matched by the matching unit. For example, if the user makes a grammatical error, the support unit may point out the error and provide a correct expression. If the user learns a new word, the support unit may explain the meaning and usage of the word. Furthermore, the support unit may analyze the user's pronunciation in real time and provide appropriate pronunciation guidance. For example, if the user mispronounces a particular word, the support unit may provide real-time guidance on correct pronunciation. Furthermore, if the user has difficulty pronouncing a particular sound, the support unit can provide pronunciation practice for that sound. The recording unit records the user's learning progress based on the content of the conversation supported by the support unit. For example, the recording unit saves the content of the conversation as text data and evaluates the user's learning progress. The recording unit can also visually display the user's learning progress as a graph or chart. Furthermore, the recording unit can customize the content of the next conversation based on the user's learning progress. For example, the recording unit sets the user to review words and phrases learned in the previous conversation in the next conversation. In this way, the English learning support system according to the embodiment matches native speakers based on the user's selection, supports real-time conversation, and records the user's learning progress, thereby enabling effective English learning.

[0030] The feedback unit can provide feedback. For example, if the user makes a grammatical error, the feedback unit can point out the error and present the correct expression. Furthermore, if the user learns a new word, the feedback unit can explain the meaning and usage of the word. Furthermore, the feedback unit can analyze the user's pronunciation in real time and provide appropriate pronunciation instruction. For example, if the user mispronounces a particular word, the feedback unit can provide real-time instruction on the correct pronunciation. Furthermore, if the user has difficulty pronouncing a particular sound, the feedback unit can provide pronunciation practice for that sound. Thus, by providing the feedback unit, the user can receive feedback in real time. Some or all of the above-described processing in the feedback unit may be performed using, or without, 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 evaluate and provide pronunciation instruction.

[0031] The explanation unit can explain the meaning and usage of a new word. For example, when a user learns a new word, the explanation unit explains the meaning and usage of the word. For example, the explanation unit can provide a definition of the new word and explain how the word is used using specific example sentences. The explanation unit can also show the pronunciation of the new word so that the user can practice correct pronunciation. Furthermore, the explanation unit can provide synonyms and antonyms of the new word so that the user can more deeply understand the meaning of the word. Thus, by providing the explanation unit, the user can learn the meaning and usage of the new word. Some or all of the above-mentioned processing in the explanation unit may be performed using, for example, a generation AI, or may be performed without using a generation AI. For example, the explanation unit can input the meaning and usage of a new word into the generation AI, and the generation AI can explain the word.

[0032] The matching unit may include an algorithm that matches native speakers based on a user's selection. For example, if a user wants to learn business English, the matching unit may include an algorithm that selects native speakers with business experience. Alternatively, if a user wants to learn travel English, the matching unit may include an algorithm that selects native speakers knowledgeable about travel. Furthermore, if a user is interested in a particular hobby, the matching unit may include an algorithm that selects native speakers knowledgeable about that hobby. By matching native speakers based on the user's selection, an appropriate conversation partner can be provided. Some or all of the above-described processing in the matching unit may be performed using, or without, a generation AI. For example, the matching unit may input user selection data into the generation AI, which then executes an algorithm to select an appropriate native speaker.

[0033] The support unit can point out the user's grammatical errors and present a correct expression. For example, if the user makes a grammatical error, the support unit points out the error and presents a correct expression. For example, if the user uses the present tense where the past tense should be used, the support unit presents the correct expression in the past tense. The support unit can also present the correct usage of the article if the user makes a mistake in the article. Furthermore, the support unit can also present the correct usage of the preposition if the user makes a mistake in the preposition. This improves learning effectiveness by correcting the user's grammatical errors in real time. Some or all of the above-described processing in the support unit may be performed, for example, using a generation AI, or may be performed without using a generation AI. For example, the support unit can input the user's grammatical errors into a generation AI, which then presents a correct expression.

[0034] The recording unit can record the user's learning progress based on the content of the conversation and reflect it in the next conversation. The recording unit, for example, saves the content of the conversation as text data and evaluates the user's learning progress. For example, the recording unit can record new words and phrases learned by the user and evaluate their understanding. The recording unit can also visually display the user's learning progress as a graph or chart. For example, the recording unit can display the user's learning progress as a line graph or bar graph, providing it in a visually easy-to-understand format. The recording unit can also customize the content of the next conversation based on the user's learning progress. For example, the recording unit can set the user to review words and phrases learned in the previous conversation in the next conversation. This enables continuous learning by recording learning progress and reflecting it in the next conversation. Some or all of the above-mentioned processing in the recording unit can be performed, for example, using a generation AI, or can be performed without using a generation AI. For example, the recording unit can input the content of the conversation into a generation AI, which can evaluate the learning progress and customize the content of the next conversation.

[0035] The matching unit can analyze the user's past conversation history and select the most suitable native speaker. For example, the matching unit selects a native speaker who is knowledgeable about similar topics based on topics that the user has liked to talk about in the past. The matching unit can also select a compatible native speaker based on feedback from native speakers with whom the user has spoken in the past. Furthermore, the matching unit can select a native speaker who is accustomed to a specific accent or pronunciation from the user's past conversation history. This allows the user to be provided with a conversation partner that suits their preferences by selecting the most suitable native speaker based on the past conversation history. Some or all of the above-described processing in the matching unit can be performed using, or without, a generation AI. For example, the matching unit can input the user's past conversation history data into the generation AI, which can then select the most suitable native speaker.

[0036] During matching, the matching unit can perform filtering based on the user's current learning goals and areas of interest. For example, if the user wants to learn business English, the matching unit can select a native speaker with business experience. Furthermore, if the user wants to learn travel English, the matching unit can select a native speaker knowledgeable about travel. Furthermore, if the user is interested in a particular hobby, the matching unit can select a native speaker knowledgeable about that hobby. This enables more effective learning by filtering based on the user's learning goals and areas of interest. Some or all of the above-described processing in the matching unit can be performed using, or without, a generation AI. For example, the matching unit can input the user's learning goals and areas of interest data into the generation AI, which can then perform the filtering.

[0037] During matching, the matching unit can prioritize matching with highly relevant native speakers by taking into account the user's geographical location information. For example, if the user lives in a specific region, the matching unit can prioritize matching with native speakers familiar with the culture and accent of that region. Furthermore, if the user uses the app while traveling, the matching unit can also prioritize matching with native speakers familiar with that region. Furthermore, if the user wants to learn English from a specific country, the matching unit can also prioritize matching with native speakers from that country. This allows for more relevant native speakers to be provided by taking the user's geographical location information into consideration. Some or all of the above-described processing in the matching unit can be performed using, or without, a generation AI. For example, the matching unit can input the user's geographical location information data into the generation AI, which can then prioritize matching with highly relevant native speakers.

[0038] During matching, the matching unit can analyze the user's social media activity and match relevant native speakers. For example, the matching unit can select native speakers who are knowledgeable about topics in which the user is interested on social media. The matching unit can also select native speakers who share interests with people the user follows on social media. Furthermore, the matching unit can select native speakers with specific hobbies or interests from the user's social media activity. This allows for more relevant native speakers to be provided by analyzing the user's social media activity. Some or all of the above-described processing in the matching unit can be performed using, or without, a generation AI. For example, the matching unit can input the user's social media activity data into a generation AI, which can then match relevant native speakers.

[0039] The support unit can analyze the user's pronunciation in real time during a conversation and provide appropriate pronunciation guidance. For example, if the user mispronounces a particular word, the support unit can provide real-time guidance on correct pronunciation. Furthermore, if the user has difficulty pronouncing a particular sound, the support unit can also provide pronunciation practice for that sound. Furthermore, the support unit can analyze the user's pronunciation habits and provide guidance on areas for improvement in real time. This allows for real-time analysis of the user's pronunciation and appropriate guidance, thereby enabling pronunciation improvement. Some or all of the above-described processing in the support unit may be performed, for example, using a generation AI, or may be performed without using a generation AI. For example, the support unit can input the user's pronunciation data into the generation AI, which can then evaluate and provide guidance on pronunciation.

[0040] The support unit can evaluate the user's level of understanding in real time during a conversation and provide appropriate support. For example, if the user does not understand a particular phrase, the support unit can explain the meaning of the phrase in real time. Furthermore, if the user does not understand the content of the conversation, the support unit can also re-explain it in simpler terms. Furthermore, the support unit can evaluate the user's level of understanding and provide an appropriate level of support. This improves learning effectiveness by evaluating the user's level of understanding in real time and providing appropriate support. Some or all of the above-described processing in the support unit may be performed, for example, using a generation AI, or may be performed without using a generation AI. For example, the support unit can input the user's level of understanding data into the generation AI, which can evaluate the user's level of understanding and provide appropriate support.

[0041] During a conversation, the support unit can provide highly relevant topics by taking into account the user's geographical location information. For example, if the user lives in a particular area, the support unit can provide topics related to that area. Furthermore, if the user is using the app while traveling, the support unit can also provide topics related to that area. Furthermore, if the user is interested in the culture of a particular country, the support unit can also provide topics related to that country. This allows for more relevant topics to be provided by taking the user's geographical location information into account. Some or all of the above-described processing in the support unit may be performed using, or without, a generation AI. For example, the support unit can input the user's geographical location information data into the generation AI, which can then provide highly relevant topics.

[0042] During a conversation, the support unit can analyze the user's social media activity and provide related topics. For example, the support unit can provide conversations related to topics the user is interested in on social media. The support unit can also provide topics related to people the user follows on social media. Furthermore, the support unit can provide topics related to specific hobbies or interests from the user's social media activity. This allows for more relevant topics to be provided by analyzing the user's social media activity. Some or all of the above-described processing in the support unit can be performed using, or without, a generation AI. For example, the support unit can input the user's social media activity data into the generation AI, which can then provide related topics.

[0043] When recording, the recording unit can select the optimal recording method by referring to the user's past learning history. For example, the recording unit can preferentially provide a recording method that the user has used favorably in the past. The recording unit can also select the most effective recording method from the user's past learning history. Furthermore, the recording unit can analyze the user's past learning history and suggest the optimal recording method. In this way, the optimal recording method can be provided by referring to the past learning history. Some or all of the above-mentioned processing in the recording unit can be performed using, or without, the generation AI, for example. For example, the recording unit can input the user's past learning history data into the generation AI, which can then select the optimal recording method.

[0044] The recording unit can customize the recorded content based on the user's current learning goals when recording. For example, if the user has set a specific goal, the recording unit can provide recorded content related to that goal. Furthermore, if the user has set a short-term goal, the recording unit can provide recorded content tailored to that goal. Furthermore, if the user has set a long-term goal, the recording unit can provide recorded content tailored to that goal. This enables more effective learning by customizing the recorded content based on the user's current learning goals. Some or all of the above-described processing in the recording unit can be performed, for example, using or without the generation AI. For example, the recording unit can input the user's learning goal data into the generation AI, which can then customize the recorded content.

[0045] The recording unit can select the optimal recording method by taking into account the user's geographical location information when recording. For example, if the user lives in a specific region, the recording unit can provide a recording method related to the culture and accent of that region. Furthermore, if the user is using the app while traveling, the recording unit can also provide a recording method related to that region. Furthermore, if the user wants to learn English from a specific country, the recording unit can also provide a recording method related to that country. This allows for more relevant recording methods to be provided by taking the geographical location information into account. Some or all of the above-described processing in the recording unit can be performed using, or without, a generation AI. For example, the recording unit can input the user's geographical location information data into the generation AI, which can then select the optimal recording method.

[0046] During recording, the recording unit can analyze the user's social media activity and record related learning progress. For example, the recording unit can record learning progress related to topics in which the user is interested on social media. The recording unit can also record learning progress related to people the user follows on social media. Furthermore, the recording unit can record learning progress related to specific hobbies or interests from the user's social media activity. This allows for more relevant learning progress to be recorded by analyzing social media activity. Some or all of the above-described processing in the recording unit can be performed using, or without, the generation AI, for example. For example, the recording unit can input the user's social media activity data into the generation AI, which can then record the related learning progress.

[0047] When providing feedback, the feedback unit can provide optimal feedback by referring to the user's past learning history. For example, the feedback unit can provide relevant feedback based on what the user has learned in the past. Furthermore, if the user has repeatedly made a specific mistake based on the user's past learning history, the feedback unit can provide feedback on that point. Furthermore, the feedback unit can analyze the user's past learning history and provide the most effective feedback. In this way, optimal feedback can be provided by referring to the past learning history. Some or all of the above-mentioned processing in the feedback unit can be performed using, or without, a generation AI. For example, the feedback unit can input the user's past learning history data into the generation AI, which can then provide optimal feedback.

[0048] When providing feedback, the feedback unit can provide optimal feedback by taking into account the user's geographical location information. For example, if the user lives in a specific region, the feedback unit can provide feedback related to the culture and accent of that region. Furthermore, if the user is using the app while traveling, the feedback unit can provide feedback related to that region. Furthermore, if the user wants to learn English from a specific country, the feedback unit can provide feedback related to that country. By taking geographical location information into account, more relevant feedback can be provided. Some or all of the above-described processing in the feedback unit can be performed using, or without, a generation AI. For example, the feedback unit can input the user's geographical location information data into the generation AI, which can then provide optimal feedback.

[0049] When providing an explanation, the explanation unit can provide the most appropriate explanation by referring to the user's past learning history. For example, the explanation unit provides explanations of related words based on what the user has learned in the past. The explanation unit can also provide an explanation by taking into account the user's level of understanding of specific words from the user's past learning history. Furthermore, the explanation unit can analyze the user's past learning history and provide the most effective explanation. In this way, the most appropriate explanation can be provided by referring to the past learning history. Some or all of the above-mentioned processing in the explanation unit may be performed using, or without, a generation AI. For example, the explanation unit can input the user's past learning history data into the generation AI, which can then provide the most appropriate explanation.

[0050] The explanation unit can provide optimal explanations by taking into account the user's geographical location information. For example, if the user lives in a specific region, the explanation unit can provide explanations of words related to the culture and accent of that region. Furthermore, if the user is using the app while traveling, the explanation unit can also provide explanations of words related to that region. Furthermore, if the user wants to learn English from a specific country, the explanation unit can also provide explanations of words related to that country. This allows for more relevant explanations to be provided by taking geographical location information into consideration. Some or all of the above-described processing in the explanation unit may be performed using, or without, a generation AI. For example, the explanation unit can input the user's geographical location information data into the generation AI, which can then provide optimal explanations.

[0051] The system according to the embodiment is not limited to the above-described example, and various modifications are possible, for example, as follows.

[0052] The English learning support system may further include a learning plan unit that analyzes the user's learning style and provides an individually optimized learning plan. For example, if the user is a visual learner, the learning plan unit may provide learning materials that make extensive use of images and videos. If the user is an auditory learner, the learning plan unit may provide audio learning materials or podcasts. Furthermore, if the user prefers hands-on learning, the learning plan unit may provide learning materials that include interactive simulations and role-playing. This makes it possible to maximize learning effectiveness by providing an optimal learning plan according to the user's learning style.

[0053] The English learning support system may further include a gamification section that introduces gamification elements to maintain user motivation. For example, the gamification section may award badges or points when a user achieves a specific learning goal. It may also provide bonuses for users who continue studying continuously. It may also provide a leaderboard where users can compete with other learners to show their progress in learning. This can increase user motivation and encourage continuous learning.

[0054] The English learning support system can further include a resource recommendation unit that analyzes the user's learning history and recommends optimal learning resources. For example, the resource recommendation unit recommends related learning materials based on what the user has learned in the past. If the user wants to improve a specific skill, the resource recommendation unit can recommend learning materials specialized for that skill. Furthermore, if the user is interested in a specific topic, the resource recommendation unit can recommend learning materials related to that topic. This can improve learning effectiveness by providing optimal learning resources based on the user's learning history.

[0055] The English learning support system may further include a dashboard section that visually displays the user's learning progress. For example, the dashboard section may display the user's learning progress as graphs or charts. It may also display the goals the user has achieved and the badges the user has earned. Furthermore, the dashboard may display the user's learning history in a timeline format, allowing the user to look back on past learning content. This allows the user to visually grasp their learning progress and maintain their motivation.

[0056] The English learning support system may further include a comparison unit that compares the user's learning progress with other learners. For example, the comparison unit may compare the user's learning progress with other learners at the same level. The comparison unit may also compare the user's learning progress with their own past progress. Furthermore, the comparison unit may compare the user's learning progress with a global average. This allows the user to objectively evaluate their learning progress and increase their motivation to learn.

[0057] The English learning support system can further include a customization unit that customizes the next learning content based on the user's learning progress. For example, the customization unit reflects in the next learning content the content that the user struggled with in the previous learning. Also, if the user wants to improve a specific skill, the customization unit can provide learning content specialized for that skill. Furthermore, if the user is interested in a specific topic, the customization unit can provide learning content related to that topic. In this way, customizing the next learning content based on the user's learning progress can improve learning effectiveness.

[0058] The processing flow of the first embodiment will be briefly explained below.

[0059] Step 1: The matching unit matches native speakers based on the user's selection. The user's selection includes the topic and level of conversation. For example, if a user wants to learn business English, a native speaker with business experience can be selected. Or, if a user wants to learn travel English, a native speaker with travel experience can be selected. Furthermore, if a user is interested in a particular hobby, a native speaker with expertise in that hobby can be selected. Step 2: The support unit assists the user in real-time conversations with native speakers matched by the matching unit. For example, if the user makes a grammatical error, it will point out the error and suggest the correct expression. Also, if the user learns a new word, it can explain the meaning and usage of that word. It can also analyze the user's pronunciation in real time and provide appropriate pronunciation guidance. If the user mispronounces a particular word, it can provide real-time guidance on the correct pronunciation, and if the user has difficulty pronouncing a particular sound, it can provide pronunciation practice for that sound. Step 3: The recording unit records the user's learning progress based on the content of the conversation assisted by the support unit. For example, the content of the conversation may be saved as text data to evaluate the user's learning progress. The learning progress may also be displayed visually as a graph or chart. Furthermore, the content of the next conversation may be customized based on the user's learning progress. For example, the recording unit may set the next conversation to review words and phrases learned in the previous conversation.

[0060] (Example 2) An English learning support system according to an embodiment of the present invention provides an online English conversation app specialized for English learning using a generative AI. This English learning support system begins when a user logs in to the app and selects a conversation topic and level. The generative AI then matches an appropriate native speaker based on the user's selection. The matched native speaker and the user then begin a real-time conversation within the app. The generative AI then supports the conversation and provides appropriate feedback. For example, if the user makes a grammatical error, the generative AI points out the error and suggests a correct expression. When the user learns a new word, the generative AI explains the meaning and usage of the word. Furthermore, based on the content of the conversation, the generative AI records the user's learning progress and reflects it in the next conversation. This app enables users to effectively learn English through real-time conversations with native speakers. Furthermore, with the support of the generative AI, users can learn at their own pace and efficiently improve their English skills. For example, a user logs in to the app and selects a conversation topic and level. The generative AI then matches an appropriate native speaker based on the user's selection. The matched native speaker and the user then begin a real-time conversation within the app. During this process, the generative AI supports the conversation and provides appropriate feedback. For example, if the user makes a grammatical error, the generative AI will point out the mistake and suggest the correct expression. Also, if the user learns a new word, the generative AI will explain the meaning and usage of that word. Furthermore, based on the content of the conversation, the generative AI records the user's learning progress and reflects it in the next conversation. This app allows users to effectively learn English through real-time conversations with native speakers. Furthermore, with the support of the generative AI, users can study at their own pace and efficiently improve their English skills. This allows the English learning support system to match users with native speakers based on their selections, support real-time conversations, and record learning progress, enabling effective English learning.

[0061] An English learning support system according to an embodiment includes a matching unit, a support unit, and a recording unit. The matching unit matches a native speaker based on a user's selection. The user's selection may include, but is not limited to, a conversation topic or level. For example, if a user wants to learn business English, the matching unit may select a native speaker with business experience. If a user wants to learn travel English, the matching unit may select a native speaker knowledgeable about travel. If a user is interested in a particular hobby, the matching unit may select a native speaker knowledgeable about that hobby. The support unit supports real-time conversations between the user and the native speaker matched by the matching unit. For example, if the user makes a grammatical error, the support unit may point out the error and provide a correct expression. If the user learns a new word, the support unit may explain the meaning and usage of the word. Furthermore, the support unit may analyze the user's pronunciation in real time and provide appropriate pronunciation guidance. For example, if the user mispronounces a particular word, the support unit may provide real-time guidance on correct pronunciation. Furthermore, if the user has difficulty pronouncing a particular sound, the support unit can provide pronunciation practice for that sound. The recording unit records the user's learning progress based on the content of the conversation supported by the support unit. For example, the recording unit saves the content of the conversation as text data and evaluates the user's learning progress. The recording unit can also visually display the user's learning progress as a graph or chart. Furthermore, the recording unit can customize the content of the next conversation based on the user's learning progress. For example, the recording unit sets the user to review words and phrases learned in the previous conversation in the next conversation. In this way, the English learning support system according to the embodiment matches native speakers based on the user's selection, supports real-time conversation, and records the user's learning progress, thereby enabling effective English learning.

[0062] The feedback unit can provide feedback. For example, if the user makes a grammatical error, the feedback unit can point out the error and present the correct expression. Furthermore, if the user learns a new word, the feedback unit can explain the meaning and usage of the word. Furthermore, the feedback unit can analyze the user's pronunciation in real time and provide appropriate pronunciation instruction. For example, if the user mispronounces a particular word, the feedback unit can provide real-time instruction on the correct pronunciation. Furthermore, if the user has difficulty pronouncing a particular sound, the feedback unit can provide pronunciation practice for that sound. Thus, by providing the feedback unit, the user can receive feedback in real time. Some or all of the above-described processing in the feedback unit may be performed using, or without, 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 evaluate and provide pronunciation instruction.

[0063] The explanation unit can explain the meaning and usage of a new word. For example, when a user learns a new word, the explanation unit explains the meaning and usage of the word. For example, the explanation unit can provide a definition of the new word and explain how the word is used using specific example sentences. The explanation unit can also show the pronunciation of the new word so that the user can practice correct pronunciation. Furthermore, the explanation unit can provide synonyms and antonyms of the new word so that the user can more deeply understand the meaning of the word. Thus, by providing the explanation unit, the user can learn the meaning and usage of the new word. Some or all of the above-mentioned processing in the explanation unit may be performed using, for example, a generation AI, or may be performed without using a generation AI. For example, the explanation unit can input the meaning and usage of a new word into the generation AI, and the generation AI can explain the word.

[0064] The matching unit may include an algorithm that matches native speakers based on a user's selection. For example, if a user wants to learn business English, the matching unit may include an algorithm that selects native speakers with business experience. Alternatively, if a user wants to learn travel English, the matching unit may include an algorithm that selects native speakers knowledgeable about travel. Furthermore, if a user is interested in a particular hobby, the matching unit may include an algorithm that selects native speakers knowledgeable about that hobby. By matching native speakers based on the user's selection, an appropriate conversation partner can be provided. Some or all of the above-described processing in the matching unit may be performed using, or without, a generation AI. For example, the matching unit may input user selection data into the generation AI, which then executes an algorithm to select an appropriate native speaker.

[0065] The support unit can point out the user's grammatical errors and present a correct expression. For example, if the user makes a grammatical error, the support unit points out the error and presents a correct expression. For example, if the user uses the present tense where the past tense should be used, the support unit presents the correct expression in the past tense. The support unit can also present the correct usage of the article if the user makes a mistake in the article. Furthermore, the support unit can also present the correct usage of the preposition if the user makes a mistake in the preposition. This improves learning effectiveness by correcting the user's grammatical errors in real time. Some or all of the above-described processing in the support unit may be performed, for example, using a generation AI, or may be performed without using a generation AI. For example, the support unit can input the user's grammatical errors into a generation AI, which then presents a correct expression.

[0066] The recording unit can record the user's learning progress based on the content of the conversation and reflect it in the next conversation. The recording unit, for example, saves the content of the conversation as text data and evaluates the user's learning progress. For example, the recording unit can record new words and phrases learned by the user and evaluate their understanding. The recording unit can also visually display the user's learning progress as a graph or chart. For example, the recording unit can display the user's learning progress as a line graph or bar graph, providing it in a visually easy-to-understand format. The recording unit can also customize the content of the next conversation based on the user's learning progress. For example, the recording unit can set the user to review words and phrases learned in the previous conversation in the next conversation. This enables continuous learning by recording learning progress and reflecting it in the next conversation. Some or all of the above-mentioned processing in the recording unit can be performed, for example, using a generation AI, or can be performed without using a generation AI. For example, the recording unit can input the content of the conversation into a generation AI, which can evaluate the learning progress and customize the content of the next conversation.

[0067] The matching unit can estimate the user's emotions and adjust the selection of native speakers based on the estimated user emotions. For example, if the user is nervous, the matching unit can select a native speaker with a relaxed demeanor. Furthermore, if the user is excited, the matching unit can select an energetic native speaker. Furthermore, if the user is depressed, the matching unit can select a native speaker who speaks in a gentle tone. This allows the user to select a native speaker appropriate for the user's emotions, thereby providing a more appropriate conversation partner. The emotion estimation is achieved using an emotion estimation function, for example, an emotion engine or a generation AI. The generation AI can be, for example, a text generation AI (e.g., LLM) or a multimodal generation AI, but is not limited to such examples. Some or all of the above-described processing in the matching unit can be performed using, for example, the generation AI, or can be performed without using the generation AI. For example, the matching unit can input the user's emotion data into the generation AI, which can then adjust the selection of native speakers.

[0068] The matching unit can analyze the user's past conversation history and select the most suitable native speaker. For example, the matching unit selects a native speaker who is knowledgeable about similar topics based on topics that the user has liked to talk about in the past. The matching unit can also select a compatible native speaker based on feedback from native speakers with whom the user has spoken in the past. Furthermore, the matching unit can select a native speaker who is accustomed to a specific accent or pronunciation from the user's past conversation history. This allows the user to be provided with a conversation partner that suits their preferences by selecting the most suitable native speaker based on the past conversation history. Some or all of the above-described processing in the matching unit can be performed using, or without, a generation AI. For example, the matching unit can input the user's past conversation history data into the generation AI, which can then select the most suitable native speaker.

[0069] During matching, the matching unit can perform filtering based on the user's current learning goals and areas of interest. For example, if the user wants to learn business English, the matching unit can select a native speaker with business experience. Furthermore, if the user wants to learn travel English, the matching unit can select a native speaker knowledgeable about travel. Furthermore, if the user is interested in a particular hobby, the matching unit can select a native speaker knowledgeable about that hobby. This enables more effective learning by filtering based on the user's learning goals and areas of interest. Some or all of the above-described processing in the matching unit can be performed using, or without, a generation AI. For example, the matching unit can input the user's learning goals and areas of interest data into the generation AI, which can then perform the filtering.

[0070] The matching unit can estimate the user's emotions and determine matching priorities based on the estimated user's emotions. For example, if the user is nervous, the matching unit can prioritize matching with native speakers who have a relaxed demeanor. Furthermore, if the user is excited, the matching unit can also prioritize matching with energetic native speakers. Furthermore, if the user is depressed, the matching unit can also prioritize matching with native speakers who speak in a gentle tone. This allows matching to be performed based on the user's emotions, thereby providing a more appropriate conversation partner. Emotion estimation is achieved using an emotion estimation function, for example, using an emotion engine or a generation AI. The generation AI can be a text generation AI (e.g., LLM) or a multimodal generation AI, but is not limited to such examples. Some or all of the above-described processing in the matching unit can be performed using, for example, the generation AI, or can be performed without using the generation AI. For example, the matching unit can input the user's emotion data into the generation AI, which can then determine the matching priorities.

[0071] During matching, the matching unit can prioritize matching with highly relevant native speakers by taking into account the user's geographical location information. For example, if the user lives in a specific region, the matching unit can prioritize matching with native speakers familiar with the culture and accent of that region. Furthermore, if the user uses the app while traveling, the matching unit can also prioritize matching with native speakers familiar with that region. Furthermore, if the user wants to learn English from a specific country, the matching unit can also prioritize matching with native speakers from that country. This allows for more relevant native speakers to be provided by taking the user's geographical location information into consideration. Some or all of the above-described processing in the matching unit can be performed using, or without, a generation AI. For example, the matching unit can input the user's geographical location information data into the generation AI, which can then prioritize matching with highly relevant native speakers.

[0072] During matching, the matching unit can analyze the user's social media activity and match relevant native speakers. For example, the matching unit can select native speakers who are knowledgeable about topics in which the user is interested on social media. The matching unit can also select native speakers who share interests with people the user follows on social media. Furthermore, the matching unit can select native speakers with specific hobbies or interests from the user's social media activity. This allows for more relevant native speakers to be provided by analyzing the user's social media activity. Some or all of the above-described processing in the matching unit can be performed using, or without, a generation AI. For example, the matching unit can input the user's social media activity data into a generation AI, which can then match relevant native speakers.

[0073] The support unit can estimate the user's emotions and adjust the way the conversation proceeds based on the estimated user's emotions. For example, if the user is nervous, the support unit can proceed the conversation in a relaxed atmosphere. Furthermore, if the user is excited, the support unit can proceed the conversation in an energetic tone. Furthermore, if the user is depressed, the support unit can proceed the conversation in a gentle tone. This enables more effective learning by providing a way to proceed the conversation according to the user's emotions. The emotion estimation is realized using an emotion estimation function, for example, an emotion engine or a generation AI. The generation AI can be a text generation AI (e.g., LLM) or a multimodal generation AI, but is not limited to such examples. Some or all of the above-mentioned processing in the support unit can be performed using, for example, the generation AI, or can be performed without using the generation AI. For example, the support unit can input the user's emotion data into the generation AI, which can then adjust the way the conversation proceeds.

[0074] The support unit can analyze the user's pronunciation in real time during a conversation and provide appropriate pronunciation guidance. For example, if the user mispronounces a particular word, the support unit can provide real-time guidance on correct pronunciation. Furthermore, if the user has difficulty pronouncing a particular sound, the support unit can also provide pronunciation practice for that sound. Furthermore, the support unit can analyze the user's pronunciation habits and provide guidance on areas for improvement in real time. This allows for real-time analysis of the user's pronunciation and appropriate guidance, thereby enabling pronunciation improvement. Some or all of the above-described processing in the support unit may be performed, for example, using a generation AI, or may be performed without using a generation AI. For example, the support unit can input the user's pronunciation data into the generation AI, which can then evaluate and provide guidance on pronunciation.

[0075] The support unit can evaluate the user's level of understanding in real time during a conversation and provide appropriate support. For example, if the user does not understand a particular phrase, the support unit can explain the meaning of the phrase in real time. Furthermore, if the user does not understand the content of the conversation, the support unit can also re-explain it in simpler terms. Furthermore, the support unit can evaluate the user's level of understanding and provide an appropriate level of support. This improves learning effectiveness by evaluating the user's level of understanding in real time and providing appropriate support. Some or all of the above-described processing in the support unit may be performed, for example, using a generation AI, or may be performed without using a generation AI. For example, the support unit can input the user's level of understanding data into the generation AI, which can evaluate the user's level of understanding and provide appropriate support.

[0076] The support unit can estimate the user's emotions and adjust the conversation topic based on the estimated user emotions. For example, if the user is nervous, the support unit can provide a relaxing topic. If the user is excited, the support unit can also provide an energetic topic. If the user is depressed, the support unit can also provide a topic with a gentle tone. This enables more effective learning by providing a conversation topic that corresponds to the user's emotions. The emotion estimation is realized using an emotion estimation function, for example, an emotion engine or a generation AI. The generation AI can be a text generation AI (e.g., LLM) or a multimodal generation AI, but is not limited to such examples. Some or all of the above-described processing in the support unit can be performed using, for example, the generation AI, or can be performed without using the generation AI. For example, the support unit can input the user's emotion data into the generation AI, which can then adjust the conversation topic.

[0077] During a conversation, the support unit can provide highly relevant topics by taking into account the user's geographical location information. For example, if the user lives in a particular area, the support unit can provide topics related to that area. Furthermore, if the user is using the app while traveling, the support unit can also provide topics related to that area. Furthermore, if the user is interested in the culture of a particular country, the support unit can also provide topics related to that country. This allows for more relevant topics to be provided by taking the user's geographical location information into account. Some or all of the above-described processing in the support unit may be performed using, or without, a generation AI. For example, the support unit can input the user's geographical location information data into the generation AI, which can then provide highly relevant topics.

[0078] During a conversation, the support unit can analyze the user's social media activity and provide related topics. For example, the support unit can provide conversations related to topics the user is interested in on social media. The support unit can also provide topics related to people the user follows on social media. Furthermore, the support unit can provide topics related to specific hobbies or interests from the user's social media activity. This allows for more relevant topics to be provided by analyzing the user's social media activity. Some or all of the above-described processing in the support unit can be performed using, or without, a generation AI. For example, the support unit can input the user's social media activity data into the generation AI, which can then provide related topics.

[0079] The recording unit can estimate the user's emotions and adjust the recording method of the learning progress based on the estimated user emotions. For example, if the user is nervous, the recording unit can provide a simple and highly visible recording method. Furthermore, if the user is relaxed, the recording unit can provide a detailed recording method. Furthermore, if the user is depressed, the recording unit can provide a recording method that includes positive feedback. This enables more effective learning by providing a recording method that corresponds to the user's emotions. The emotion estimation is realized using an emotion estimation function, for example, an emotion engine or a generation AI. The generation AI can be, but is not limited to, a text generation AI (e.g., LLM) or a multimodal generation AI. Some or all of the above-described processing in the recording unit can be performed using, for example, the generation AI, or can be performed without using the generation AI. For example, the recording unit can input the user's emotion data into the generation AI, which can then adjust the recording method of the learning progress.

[0080] When recording, the recording unit can select the optimal recording method by referring to the user's past learning history. For example, the recording unit can preferentially provide a recording method that the user has used favorably in the past. The recording unit can also select the most effective recording method from the user's past learning history. Furthermore, the recording unit can analyze the user's past learning history and suggest the optimal recording method. In this way, the optimal recording method can be provided by referring to the past learning history. Some or all of the above-mentioned processing in the recording unit can be performed using, or without, the generation AI, for example. For example, the recording unit can input the user's past learning history data into the generation AI, which can then select the optimal recording method.

[0081] The recording unit can customize the recorded content based on the user's current learning goals when recording. For example, if the user has set a specific goal, the recording unit can provide recorded content related to that goal. Furthermore, if the user has set a short-term goal, the recording unit can provide recorded content tailored to that goal. Furthermore, if the user has set a long-term goal, the recording unit can provide recorded content tailored to that goal. This enables more effective learning by customizing the recorded content based on the user's current learning goals. Some or all of the above-described processing in the recording unit can be performed, for example, using or without the generation AI. For example, the recording unit can input the user's learning goal data into the generation AI, which can then customize the recorded content.

[0082] The recording unit can estimate the user's emotions and adjust the display method of the learning progress based on the estimated user emotions. For example, if the user is nervous, the recording unit can provide a simple, highly visible display method. Furthermore, if the user is relaxed, the recording unit can provide a detailed display method. Furthermore, if the user is depressed, the recording unit can provide a display method including positive feedback. This enables more effective learning by providing a display method that corresponds to the user's emotions. The emotion estimation is realized using an emotion estimation function, for example, an emotion engine or a generation AI. The generation AI can be, but is not limited to, a text generation AI (e.g., LLM) or a multimodal generation AI. Some or all of the above-described processing in the recording unit can be performed using, for example, the generation AI, or can be performed without using the generation AI. For example, the recording unit can input the user's emotion data into the generation AI, which can then adjust the display method of the learning progress.

[0083] The recording unit can select the optimal recording method by taking into account the user's geographical location information when recording. For example, if the user lives in a specific region, the recording unit can provide a recording method related to the culture and accent of that region. Furthermore, if the user is using the app while traveling, the recording unit can also provide a recording method related to that region. Furthermore, if the user wants to learn English from a specific country, the recording unit can also provide a recording method related to that country. This allows for more relevant recording methods to be provided by taking the geographical location information into account. Some or all of the above-described processing in the recording unit can be performed using, or without, a generation AI. For example, the recording unit can input the user's geographical location information data into the generation AI, which can then select the optimal recording method.

[0084] During recording, the recording unit can analyze the user's social media activity and record related learning progress. For example, the recording unit can record learning progress related to topics in which the user is interested on social media. The recording unit can also record learning progress related to people the user follows on social media. Furthermore, the recording unit can record learning progress related to specific hobbies or interests from the user's social media activity. This allows for more relevant learning progress to be recorded by analyzing social media activity. Some or all of the above-described processing in the recording unit can be performed using, or without, the generation AI, for example. For example, the recording unit can input the user's social media activity data into the generation AI, which can then record the related learning progress.

[0085] The feedback unit can estimate the user's emotions and adjust the content of the feedback based on the estimated user's emotions. For example, if the user is nervous, the feedback unit can provide feedback in a gentle tone. Furthermore, if the user is relaxed, the feedback unit can provide detailed feedback. Furthermore, if the user is depressed, the feedback unit can provide positive feedback. This enables more effective learning by providing feedback according to the user's emotions. The emotion estimation is realized using an emotion estimation function, for example, an emotion engine or a generation AI. The generation AI can be, but is not limited to, a text generation AI (e.g., LLM) or a multimodal generation AI. Some or all of the above-described processing in the feedback unit can be performed using, for example, the generation AI, or can be performed without using the generation AI. For example, the feedback unit can input the user's emotion data into the generation AI, which can then adjust the content of the feedback.

[0086] When providing feedback, the feedback unit can provide optimal feedback by referring to the user's past learning history. For example, the feedback unit can provide relevant feedback based on what the user has learned in the past. Furthermore, if the user has repeatedly made a specific mistake based on the user's past learning history, the feedback unit can provide feedback on that point. Furthermore, the feedback unit can analyze the user's past learning history and provide the most effective feedback. In this way, optimal feedback can be provided by referring to the past learning history. Some or all of the above-mentioned processing in the feedback unit can be performed using, or without, a generation AI. For example, the feedback unit can input the user's past learning history data into the generation AI, which can then provide optimal feedback.

[0087] The feedback unit can estimate the user's emotions and adjust the timing of the feedback based on the estimated user's emotions. For example, if the user is nervous, the feedback unit can provide gentle feedback in the middle of a conversation. Furthermore, if the user is relaxed, the feedback unit can provide detailed feedback at the end of the conversation. Furthermore, if the user is depressed, the feedback unit can provide positive feedback in the middle of a conversation. This enables more effective learning by providing feedback at a timing appropriate to the user's emotions. The emotion estimation is realized using an emotion estimation function, for example, an emotion engine or a generation AI. The generation AI can be, but is not limited to, a text generation AI (e.g., LLM) or a multimodal generation AI. Some or all of the above-described processing in the feedback unit can be performed using, for example, the generation AI, or can be performed without using the generation AI. For example, the feedback unit can input the user's emotion data into the generation AI, which can then adjust the timing of the feedback.

[0088] When providing feedback, the feedback unit can provide optimal feedback by taking into account the user's geographical location information. For example, if the user lives in a specific region, the feedback unit can provide feedback related to the culture and accent of that region. Furthermore, if the user is using the app while traveling, the feedback unit can provide feedback related to that region. Furthermore, if the user wants to learn English from a specific country, the feedback unit can provide feedback related to that country. By taking geographical location information into account, more relevant feedback can be provided. Some or all of the above-described processing in the feedback unit can be performed using, or without, a generation AI. For example, the feedback unit can input the user's geographical location information data into the generation AI, which can then provide optimal feedback.

[0089] The explanation unit can estimate the user's emotions and adjust the word explanation method based on the estimated user's emotions. For example, if the user is nervous, the explanation unit can provide a simple, highly visible explanation method. Furthermore, if the user is relaxed, the explanation unit can provide a detailed explanation method. Furthermore, if the user is depressed, the explanation unit can provide an explanation method including positive feedback. This enables more effective learning by providing an explanation method that corresponds to the user's emotions. The emotion estimation is realized using an emotion estimation function, for example, an emotion engine or a generation AI. The generation AI can be, but is not limited to, a text generation AI (e.g., LLM) or a multimodal generation AI. Some or all of the above-described processing in the explanation unit can be performed using, for example, the generation AI, or can be performed without using the generation AI. For example, the explanation unit can input the user's emotion data into the generation AI, which can then adjust the word explanation method.

[0090] When providing an explanation, the explanation unit can provide the most appropriate explanation by referring to the user's past learning history. For example, the explanation unit provides explanations of related words based on what the user has learned in the past. The explanation unit can also provide an explanation by taking into account the user's level of understanding of specific words from the user's past learning history. Furthermore, the explanation unit can analyze the user's past learning history and provide the most effective explanation. In this way, the most appropriate explanation can be provided by referring to the past learning history. Some or all of the above-mentioned processing in the explanation unit may be performed using, or without, a generation AI. For example, the explanation unit can input the user's past learning history data into the generation AI, which can then provide the most appropriate explanation.

[0091] The explanation unit can estimate the user's emotions and prioritize word explanations based on the estimated user emotions. For example, if the user is nervous, the explanation unit can prioritize simple and important word explanations. Furthermore, if the user is relaxed, the explanation unit can prioritize detailed word explanations. Furthermore, if the user is depressed, the explanation unit can prioritize word explanations containing positive feedback. This enables more effective learning by providing word explanations in a priority order according to the user's emotions. The emotion estimation is realized using an emotion estimation function, for example, an emotion engine or a generation AI. The generation AI can be, but is not limited to, a text generation AI (e.g., LLM) or a multimodal generation AI. Some or all of the above-described processing in the explanation unit can be performed using, for example, the generation AI, or can be performed without using the generation AI. For example, the explanation unit can input the user's emotion data into the generation AI, which can then prioritize word explanations.

[0092] The explanation unit can provide optimal explanations by taking into account the user's geographical location information. For example, if the user lives in a specific region, the explanation unit can provide explanations of words related to the culture and accent of that region. Furthermore, if the user is using the app while traveling, the explanation unit can also provide explanations of words related to that region. Furthermore, if the user wants to learn English from a specific country, the explanation unit can also provide explanations of words related to that country. This allows for more relevant explanations to be provided by taking geographical location information into consideration. Some or all of the above-described processing in the explanation unit may be performed using, or without, a generation AI. For example, the explanation unit can input the user's geographical location information data into the generation AI, which can then provide optimal explanations. === Hard Collateral 1-1 === Each of the multiple elements including the above-mentioned matching unit, support unit, and recording unit is realized, for example, by at least one of the smart device 14 and the data processing device 12. For example, the matching unit is realized by the control unit 46A of the smart device 14 and matches a native speaker based on the user's selection. The support unit is realized, for example, by the specific processing unit 290 of the data processing device 12 and supports real-time conversation and provides appropriate feedback. The recording unit is realized, for example, by the specific processing unit 290 of the data processing device 12 and records the user's learning progress based on the content of the conversation. === Hard Collateral 1-2 === Each of the multiple elements including the above-mentioned matching unit, support unit, and recording unit is realized, for example, by at least one of the smart glasses 214 and the data processing device 12. For example, the matching unit is realized by the control unit 46A of the smart glasses 214 and matches a native speaker based on the user's selection. The support unit is realized, for example, by the specific processing unit 290 of the data processing device 12 and supports real-time conversation and provides appropriate feedback. The recording unit is realized, for example, by the specific processing unit 290 of the data processing device 12 and records the user's learning progress based on the content of the conversation. === Hard Collateral 1-3 === Each of the multiple elements including the above-mentioned matching unit, support unit, and recording unit is realized, for example, by at least one of the headset type terminal 314 and the data processing device 12. For example, the matching unit is realized by the control unit 46A of the headset type terminal 314 and matches a native speaker based on the user's selection. The support unit is realized, for example, by the specific processing unit 290 of the data processing device 12 and supports real-time conversation and provides appropriate feedback. The recording unit is realized, for example, by the specific processing unit 290 of the data processing device 12 and records the user's learning progress based on the content of the conversation. === Hard Collateral 1-4 === Each of the multiple elements including the above-mentioned matching unit, support unit, and recording unit is realized, for example, by at least one of the robot 414 and the data processing device 12. For example, the matching unit is realized by the control unit 46A of the robot 414 and matches a native speaker based on the user's selection. The support unit is realized, for example, by the specific processing unit 290 of the data processing device 12 and supports real-time conversation and provides appropriate feedback. The recording unit is realized, for example, by the specific processing unit 290 of the data processing device 12 and records the user's learning progress based on the content of the conversation.

[0093] The system according to the embodiment is not limited to the above-described example, and various modifications are possible, for example, as follows.

[0094] The English learning support system may further include a learning plan unit that analyzes the user's learning style and provides an individually optimized learning plan. For example, if the user is a visual learner, the learning plan unit may provide learning materials that make extensive use of images and videos. If the user is an auditory learner, the learning plan unit may provide audio learning materials or podcasts. Furthermore, if the user prefers hands-on learning, the learning plan unit may provide learning materials that include interactive simulations and role-playing. This makes it possible to maximize learning effectiveness by providing an optimal learning plan according to the user's learning style.

[0095] The English learning support system may further include a gamification section that introduces gamification elements to maintain user motivation. For example, the gamification section may award badges or points when a user achieves a specific learning goal. It may also provide bonuses for users who continue studying continuously. It may also provide a leaderboard where users can compete with other learners to show their progress in learning. This can increase user motivation and encourage continuous learning.

[0096] The English learning support system may further include an emotion adjustment unit that estimates the user's emotions and adjusts the study plan based on the estimated emotions. For example, if the user is tired, the emotion adjustment unit may provide an easy study plan that can be completed in a short time. Alternatively, if the user is concentrating, the emotion adjustment unit may provide a more difficult study plan. Furthermore, if the user is feeling stressed, the emotion adjustment unit may provide a study plan with content that will help the user relax. In this way, by providing a study plan that corresponds to the user's emotions, the learning effect can be improved.

[0097] The English learning support system can further include a resource recommendation unit that analyzes the user's learning history and recommends optimal learning resources. For example, the resource recommendation unit recommends related learning materials based on what the user has learned in the past. If the user wants to improve a specific skill, the resource recommendation unit can recommend learning materials specialized for that skill. Furthermore, if the user is interested in a specific topic, the resource recommendation unit can recommend learning materials related to that topic. This can improve learning effectiveness by providing optimal learning resources based on the user's learning history.

[0098] The English learning support system may further include a feedback adjustment unit that estimates the user's emotions and adjusts the form of feedback based on the estimated emotions. For example, the feedback adjustment unit may provide feedback in a gentle tone if the user is nervous. Alternatively, the feedback adjustment unit may provide detailed feedback if the user is relaxed. Furthermore, the feedback adjustment unit may provide positive feedback if the user is depressed. This allows for improved learning effectiveness by providing feedback according to the user's emotions.

[0099] The English learning support system may further include a dashboard section that visually displays the user's learning progress. For example, the dashboard section may display the user's learning progress as graphs or charts. It may also display the goals the user has achieved and the badges the user has earned. Furthermore, the dashboard may display the user's learning history in a timeline format, allowing the user to look back on past learning content. This allows the user to visually grasp their learning progress and maintain their motivation.

[0100] The English learning support system may further include a progress display adjustment unit that estimates the user's emotions and adjusts the display method of the learning progress based on the estimated emotions. For example, if the user is nervous, the progress display adjustment unit may provide a simple, highly visible display method. If the user is relaxed, the progress display adjustment unit may provide a detailed display method. Furthermore, if the user is depressed, the progress display adjustment unit may provide a display method that includes positive feedback. In this way, by providing a display method that corresponds to the user's emotions, the learning effect can be improved.

[0101] The English learning support system may further include a comparison unit that compares the user's learning progress with other learners. For example, the comparison unit may compare the user's learning progress with other learners at the same level. The comparison unit may also compare the user's learning progress with their own past progress. Furthermore, the comparison unit may compare the user's learning progress with a global average. This allows the user to objectively evaluate their learning progress and increase their motivation to learn.

[0102] The English learning support system may further include a resource recommendation adjustment unit that estimates the user's emotions and adjusts the method of recommending learning resources based on the estimated emotions. For example, if the user is nervous, the resource recommendation adjustment unit may recommend resources with relaxing content. If the user is relaxed, the resource recommendation adjustment unit may also recommend more difficult resources. Furthermore, if the user is depressed, the resource recommendation adjustment unit may also recommend resources with positive content. In this way, by recommending resources according to the user's emotions, learning effectiveness can be improved.

[0103] The English learning support system can further include a customization unit that customizes the next learning content based on the user's learning progress. For example, the customization unit reflects in the next learning content the content that the user struggled with in the previous learning. Also, if the user wants to improve a specific skill, the customization unit can provide learning content specialized for that skill. Furthermore, if the user is interested in a specific topic, the customization unit can provide learning content related to that topic. In this way, customizing the next learning content based on the user's learning progress can improve learning effectiveness.

[0104] The processing flow of the second embodiment will be briefly explained below.

[0105] Step 1: The matching unit matches native speakers based on the user's selection. The user's selection includes the topic and level of conversation. For example, if a user wants to learn business English, a native speaker with business experience can be selected. Or, if a user wants to learn travel English, a native speaker with travel experience can be selected. Furthermore, if a user is interested in a particular hobby, a native speaker with expertise in that hobby can be selected. Step 2: The support unit assists the user in real-time conversations with native speakers matched by the matching unit. For example, if the user makes a grammatical error, it will point out the error and suggest the correct expression. Also, if the user learns a new word, it can explain the meaning and usage of that word. It can also analyze the user's pronunciation in real time and provide appropriate pronunciation guidance. If the user mispronounces a particular word, it can provide real-time guidance on the correct pronunciation, and if the user has difficulty pronouncing a particular sound, it can provide pronunciation practice for that sound. Step 3: The recording unit records the user's learning progress based on the content of the conversation assisted by the support unit. For example, the content of the conversation may be saved as text data to evaluate the user's learning progress. The learning progress may also be displayed visually as a graph or chart. Furthermore, the content of the next conversation may be customized based on the user's learning progress. For example, the recording unit may set the next conversation to review words and phrases learned in the previous conversation.

[0106] The specific processing unit 290 transmits the result of the specific processing to the smart device 14. In the smart device 14, the control unit 46A causes the output device 40 to output the result of the specific processing. The microphone 38B acquires audio indicating a user input regarding the result of the specific processing. The control unit 46A transmits audio data indicating the user input acquired by the microphone 38B to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the audio data.

[0107] The data generation model 58 is a so-called generative AI (Artificial Intelligence). An example of the data generation model 58 is ChatGPT (registered trademark) (Internet search engine).<URL: https: / / openai.com / blog / chatgpt> Examples of the generative AI include a neural network (NN) and a neural network (NN). The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 receives a prompt containing an instruction, as well as inference data such as voice data representing speech, text data representing text, and image data representing an image (e.g., still image data or video data). The data generation model 58 performs inference on the input inference data in accordance with the instruction indicated by the prompt, and outputs the inference result in one or more data formats of voice data, text data, image data, etc. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization. The specification processing unit 290 performs the above-mentioned specification processing using the data generation model 58. The data generation model 58 may be a fine-tuned model so as to output an inference result from a prompt that does not include an instruction. In this case, the data generation model 58 can output an inference result from a prompt that does not include an instruction. The data processing device 12 and the like include multiple types of data generation models 58, and the data generation model 58 includes AIs other than the generative AI. The AI ​​other than the generative AI may be, for example, linear regression, logistic regression, decision tree, random forest, support vector machine (SVM), k-means clustering, convolutional neural network (CNN), recurrent neural network (RNN), generative adversarial network (GAN), or naive Bayes, and may perform various processes, but is not limited to these examples. The AI ​​may also be an AI agent. When the processing of each of the above-mentioned parts is performed by an AI, the processing may be performed in part or entirely by the AI, but is not limited to these examples. The processing performed by an AI including the generative AI may be replaced with rule-based processing, and rule-based processing may be replaced with processing performed by an AI including the generative AI.

[0108] Furthermore, the processing by the data processing system 10 described above is executed by the specific processing unit 290 of the data processing device 12 or the control unit 46A of the smart device 14, but may also be executed by the specific processing unit 290 of the data processing device 12 and the control unit 46A of the smart device 14. Furthermore, the specific processing unit 290 of the data processing device 12 acquires or collects information necessary for processing from the smart device 14 or an external device, and the smart device 14 acquires or collects information necessary for processing from the data processing device 12 or an external device.

[0109] The correspondence between each part and the device or control part is not limited to the example described above, and various modifications are possible.

[0110] [Second embodiment] FIG. 3 shows an example of the configuration of a data processing system 210 according to the second embodiment.

[0111] 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.

[0112] The data processing device 12 includes a computer 22, a database 24, and a communication I / F 26. The computer 22 includes a processor 28, a RAM 30, and a storage 32. The processor 28, RAM 30, and storage 32 are connected to a bus 34. The database 24 and the communication I / F 26 are also connected to the bus 34. The communication I / F 26 is connected to a network 54. Examples of the network 54 include a WAN and / or a LAN.

[0113] 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.

[0114] The microphone 238 receives instructions and the like from the user by receiving voice uttered by the user. The microphone 238 captures the voice uttered by the user, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio according to instructions from the processor 46.

[0115] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an imaging element such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, and captures images of the user's surroundings (for example, an imaging range defined by an angle of view equivalent to the field of vision of a typical healthy person).

[0116] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 are responsible for the exchange of various information between the processor 46 and the processor 28 via the network 54. The exchange of various information between the processor 46 and the processor 28 using the communication I / Fs 44 and 26 is carried out in a secure state.

[0117] Fig. 4 shows an example of the main functions of the data processing device 12 and the smart glasses 214. As shown in Fig. 4, in the data processing device 12, a specific process is performed by the processor 28. A specific process program 56 is stored in the storage 32.

[0118] 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.

[0119] The storage 32 stores a data generation model 58 and an emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290. The identification processing unit 290 can estimate a user's emotion using the emotion identification model 59 and perform identification processing using the user's emotion. The emotion estimation function (emotion identification function) using the emotion identification model 59 performs various estimations and predictions regarding the user's emotion, including estimation and prediction of the user's emotion, but is not limited to these examples. Furthermore, the estimation and prediction of emotion also includes, for example, emotion analysis.

[0120] In the smart glasses 214, the specific processing is performed by the processor 46. A specific processing program 60 is stored in the storage 50. The processor 46 reads the specific processing program 60 from the storage 50 and executes the read specific processing program 60 on the RAM 48. The specific processing is realized by the processor 46 operating as the control unit 46A in accordance with the specific processing program 60 executed on the RAM 48. The smart glasses 214 also have a data generation model and an emotion identification model similar to the data generation model 58 and the emotion identification model 59, and can perform processing similar to that of the specific processing unit 290 using these models.

[0121] Note that a device other than the data processing device 12 may have the data generation model 58. For example, a server device may have the data generation model 58. In this case, the data processing device 12 communicates with the server device having the data generation model 58 to obtain a processing result (such as a prediction result) using the data generation model 58. Furthermore, the data processing device 12 may be a server device, or may be a terminal device (for example, a mobile phone, a robot, a home appliance, etc.) owned by a user.

[0122] The specific processing unit 290 transmits the result of the specific processing to the smart glasses 214. In the smart glasses 214, the control unit 46A causes the speaker 240 to output the result of the specific processing. The microphone 238 acquires audio indicating a user input regarding the result of the specific processing. The control unit 46A transmits audio data indicating the user input acquired by the microphone 238 to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the audio data.

[0123] The data generation model 58 is a so-called generative AI. An example of the data generation model 58 is a generative AI such as ChatGPT. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 receives a prompt including an instruction, as well as inference data such as audio data indicating speech, text data indicating text, and image data indicating an image (e.g., still image data or video data). The data generation model 58 performs inference on the input inference data in accordance with the instruction indicated by the prompt, and outputs the inference result in one or more data formats, such as audio data, text data, and image data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization. The identification processing unit 290 performs the above-mentioned identification processing using the data generation model 58. The data generation model 58 may be a fine-tuned model so as to output an inference result from a prompt that does not include an instruction. In this case, the data generation model 58 can output an inference result from a prompt that does not include an instruction. The data processing device 12 and the like include multiple types of data generation models 58, and the data generation models 58 include AIs other than the generation AI. Examples of AIs other than the generation AI include, but are not limited to, linear regression, logistic regression, decision trees, random forests, support vector machines (SVMs), k-means clustering, convolutional neural networks (CNNs), recurrent neural networks (RNNs), generative adversarial networks (GANs), and naive Bayes. These AIs can perform various types of processing, but are not limited to these examples. The AI ​​may also be an AI agent. When the processing of each of the above-described parts is performed by an AI, the processing may be performed in part or entirely by the AI, but is not limited to these examples. Processing performed by an AI, including the generation AI, may be replaced with rule-based processing, and rule-based processing may be replaced with processing performed by an AI, including the generation AI.

[0124] The data processing system 210 according to the second embodiment performs the same processing as the data processing system 10 according to the first embodiment. The processing by the data processing system 210 is executed by the specific processing unit 290 of the data processing device 12 or the control unit 46A of the smart glasses 214, but may also be executed by the specific processing unit 290 of the data processing device 12 and the control unit 46A of the smart glasses 214. Furthermore, the specific processing unit 290 of the data processing device 12 acquires or collects information required for processing from the smart glasses 214 or an external device, etc., and the smart glasses 214 acquires or collects information required for processing from the data processing device 12 or an external device, etc.

[0125] The correspondence between each part and the device or control part is not limited to the example described above, and various modifications are possible.

[0126] [Third embodiment] FIG. 5 shows an example of the configuration of a data processing system 310 according to the third embodiment.

[0127] 5, the data processing system 310 includes the data processing device 12 and a headset terminal 314. An example of the data processing device 12 is a server.

[0128] The data processing device 12 includes a computer 22, a database 24, and a communication I / F 26. The computer 22 includes a processor 28, a RAM 30, and a storage 32. The processor 28, RAM 30, and storage 32 are connected to a bus 34. The database 24 and the communication I / F 26 are also connected to the bus 34. The communication I / F 26 is connected to a network 54. Examples of the network 54 include a WAN and / or a LAN.

[0129] 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.

[0130] The microphone 238 receives instructions and the like from the user by receiving voice uttered by the user. The microphone 238 captures the voice uttered by the user, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio according to instructions from the processor 46.

[0131] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an imaging element such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, and captures images of the user's surroundings (for example, an imaging range defined by an angle of view equivalent to the field of vision of a typical healthy person).

[0132] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 are responsible for the exchange of various information between the processor 46 and the processor 28 via the network 54. The exchange of various information between the processor 46 and the processor 28 using the communication I / Fs 44 and 26 is carried out in a secure state.

[0133] 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.

[0134] 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.

[0135] The storage 32 stores a data generation model 58 and an emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290. The identification processing unit 290 can estimate a user's emotion using the emotion identification model 59 and perform identification processing using the user's emotion. The emotion estimation function (emotion identification function) using the emotion identification model 59 performs various estimations and predictions regarding the user's emotion, including estimation and prediction of the user's emotion, but is not limited to these examples. Furthermore, the estimation and prediction of emotion also includes, for example, emotion analysis.

[0136] In the headset type terminal 314, the identification process is performed by the processor 46. A identification program 60 is stored in the storage 50. The processor 46 reads the identification program 60 from the storage 50 and executes the read identification program 60 on the RAM 48. The identification process is realized by the processor 46 operating as a control unit 46A in accordance with the identification program 60 executed on the RAM 48. Note that the headset type terminal 314 has a data generation model and an emotion identification model similar to the data generation model 58 and the emotion identification model 59, and can also perform processing similar to that of the identification processing unit 290 using these models.

[0137] Note that a device other than the data processing device 12 may have the data generation model 58. For example, a server device may have the data generation model 58. In this case, the data processing device 12 communicates with the server device having the data generation model 58 to obtain a processing result (such as a prediction result) using the data generation model 58. Furthermore, the data processing device 12 may be a server device, or may be a terminal device (for example, a mobile phone, a robot, a home appliance, etc.) owned by a user.

[0138] The specific processing unit 290 transmits the result of the specific processing to the headset type terminal 314. In the headset type terminal 314, the control unit 46A causes the speaker 240 and the display 343 to output the result of the specific processing. The microphone 238 acquires audio indicating a user input regarding the result of the specific processing. The control unit 46A transmits audio data indicating the user input acquired by the microphone 238 to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the audio data.

[0139] The data generation model 58 is a so-called generative AI. An example of the data generation model 58 is a generative AI such as ChatGPT. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 receives a prompt including an instruction, as well as inference data such as audio data indicating speech, text data indicating text, and image data indicating an image (e.g., still image data or video data). The data generation model 58 performs inference on the input inference data in accordance with the instruction indicated by the prompt, and outputs the inference result in one or more data formats, such as audio data, text data, and image data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization. The identification processing unit 290 performs the above-mentioned identification processing using the data generation model 58. The data generation model 58 may be a fine-tuned model so as to output an inference result from a prompt that does not include an instruction. In this case, the data generation model 58 can output an inference result from a prompt that does not include an instruction. The data processing device 12 and the like include multiple types of data generation models 58, and the data generation models 58 include AIs other than the generation AI. Examples of AIs other than the generation AI include, but are not limited to, linear regression, logistic regression, decision trees, random forests, support vector machines (SVMs), k-means clustering, convolutional neural networks (CNNs), recurrent neural networks (RNNs), generative adversarial networks (GANs), and naive Bayes. These AIs can perform various types of processing, but are not limited to these examples. The AI ​​may also be an AI agent. When the processing of each of the above-described parts is performed by an AI, the processing may be performed in part or entirely by the AI, but is not limited to these examples. Processing performed by an AI, including the generation AI, may be replaced with rule-based processing, and rule-based processing may be replaced with processing performed by an AI, including the generation AI.

[0140] The data processing system 310 according to the third embodiment performs the same processing as the data processing system 10 according to the first embodiment. The processing by the data processing system 310 is executed by the specific processing unit 290 of the data processing device 12 or the control unit 46A of the headset type terminal 314, but may also be executed by the specific processing unit 290 of the data processing device 12 and the control unit 46A of the headset type terminal 314. Furthermore, the specific processing unit 290 of the data processing device 12 acquires or collects information required for processing from the headset type terminal 314 or an external device, etc., and the headset type terminal 314 acquires or collects information required for processing from the data processing device 12 or an external device, etc.

[0141] The correspondence between each part and the device or control part is not limited to the example described above, and various modifications are possible.

[0142] [Fourth embodiment] FIG. 7 shows an example of the configuration of a data processing system 410 according to the fourth embodiment.

[0143] 7, the data processing system 410 includes a data processing device 12 and a robot 414. An example of the data processing device 12 is a server.

[0144] The data processing device 12 includes a computer 22, a database 24, and a communication I / F 26. The computer 22 includes a processor 28, a RAM 30, and a storage 32. The processor 28, RAM 30, and storage 32 are connected to a bus 34. The database 24 and the communication I / F 26 are also connected to the bus 34. The communication I / F 26 is connected to a network 54. Examples of the network 54 include a WAN and / or a LAN.

[0145] 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.

[0146] The microphone 238 receives instructions and the like from the user by receiving voice uttered by the user. The microphone 238 captures the voice uttered by the user, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio according to instructions from the processor 46.

[0147] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an imaging element such as a CMOS image sensor or a CCD image sensor, and captures images of the user's surroundings (for example, an imaging range defined by an angle of view equivalent to the field of vision of a typical healthy person).

[0148] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 are responsible for the exchange of various information between the processor 46 and the processor 28 via the network 54. The exchange of various information between the processor 46 and the processor 28 using the communication I / Fs 44 and 26 is carried out in a secure state.

[0149] The control object 443 includes a display device, LEDs in the eyes, and motors that drive the arms, hands, and feet. The posture and gestures of the robot 414 are controlled by controlling the motors of the arms, hands, and feet. Some of the emotions of the robot 414 can be expressed by controlling these motors. In addition, the facial expressions of the robot 414 can also be expressed by controlling the light emission state of the LEDs in the eyes of the robot 414.

[0150] 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.

[0151] 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.

[0152] The storage 32 stores a data generation model 58 and an emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290. The identification processing unit 290 can estimate a user's emotion using the emotion identification model 59 and perform identification processing using the user's emotion. The emotion estimation function (emotion identification function) using the emotion identification model 59 performs various estimations and predictions regarding the user's emotion, including estimation and prediction of the user's emotion, but is not limited to these examples. Furthermore, the estimation and prediction of emotion also includes, for example, emotion analysis.

[0153] In the robot 414, the processor 46 performs the identification process. The storage 50 stores the identification program 60. The processor 46 reads the identification program 60 from the storage 50 and executes the read identification program 60 on the RAM 48. The identification process is realized by the processor 46 operating as the control unit 46A in accordance with the identification program 60 executed on the RAM 48. The robot 414 also has a data generation model and an emotion identification model similar to the data generation model 58 and the emotion identification model 59, and can perform the same process as the identification processing unit 290 using these models.

[0154] Note that a device other than the data processing device 12 may have the data generation model 58. For example, a server device may have the data generation model 58. In this case, the data processing device 12 communicates with the server device having the data generation model 58 to obtain a processing result (such as a prediction result) using the data generation model 58. Furthermore, the data processing device 12 may be a server device, or may be a terminal device (for example, a mobile phone, a robot, a home appliance, etc.) owned by a user.

[0155] The specific processing unit 290 transmits the result of the specific processing to the robot 414. In the robot 414, the control unit 46A causes the speaker 240 and the control target 443 to output the result of the specific processing. The microphone 238 acquires voice indicating a user input regarding the result of the specific processing. The control unit 46A transmits voice data indicating the user input acquired by the microphone 238 to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the voice data.

[0156] The data generation model 58 is a so-called generative AI. An example of the data generation model 58 is a generative AI such as ChatGPT. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 receives a prompt including an instruction, as well as inference data such as audio data indicating speech, text data indicating text, and image data indicating an image (e.g., still image data or video data). The data generation model 58 performs inference on the input inference data in accordance with the instruction indicated by the prompt, and outputs the inference result in one or more data formats, such as audio data, text data, and image data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization. The identification processing unit 290 performs the above-mentioned identification processing using the data generation model 58. The data generation model 58 may be a fine-tuned model so as to output an inference result from a prompt that does not include an instruction. In this case, the data generation model 58 can output an inference result from a prompt that does not include an instruction. The data processing device 12 and the like include multiple types of data generation models 58, and the data generation models 58 include AIs other than the generation AI. Examples of AIs other than the generation AI include, but are not limited to, linear regression, logistic regression, decision trees, random forests, support vector machines (SVMs), k-means clustering, convolutional neural networks (CNNs), recurrent neural networks (RNNs), generative adversarial networks (GANs), and naive Bayes. These AIs can perform various types of processing, but are not limited to these examples. The AI ​​may also be an AI agent. When the processing of each of the above-described parts is performed by an AI, the processing may be performed in part or entirely by the AI, but is not limited to these examples. Processing performed by an AI, including the generation AI, may be replaced with rule-based processing, and rule-based processing may be replaced with processing performed by an AI, including the generation AI.

[0157] The data processing system 410 according to the fourth embodiment performs the same processing as the data processing system 10 according to the first embodiment. The processing by the data processing system 410 is executed by the specific processing unit 290 of the data processing device 12 or the control unit 46A of the robot 414, but may also be executed by the specific processing unit 290 of the data processing device 12 and the control unit 46A of the robot 414. Furthermore, the specific processing unit 290 of the data processing device 12 acquires or collects information required for processing from the robot 414 or an external device, etc., and the robot 414 acquires or collects information required for processing from the data processing device 12 or an external device, etc.

[0158] The correspondence between each part and the device or control part is not limited to the example described above, and various modifications are possible.

[0159] The emotion identification model 59 as an emotion engine may determine the user's emotion according to a specific mapping. Specifically, the emotion identification model 59 may determine the user's emotion according to an emotion map (see FIG. 9), which is a specific mapping. Similarly, the emotion identification model 59 may determine the robot's emotion, and the identification processing unit 290 may perform identification processing using the robot's emotion.

[0160] FIG. 9 illustrates an emotion map 400 on which multiple emotions are mapped. In the emotion map 400, emotions are arranged in concentric circles radiating from the center. Emotions closer to the center of the concentric circles are more primitive. Emotions representing states and behaviors arising from a state of mind are arranged on the outer edges of the concentric circles. The concept of emotion encompasses both emotions and mental states. Emotions generally generated from reactions occurring in the brain are arranged on the left side of the concentric circles. Emotions generally induced by situational judgment are arranged on the right side of the concentric circles. Emotions generally generated from reactions occurring in the brain and induced by situational judgment are arranged on the upper and lower sides of the concentric circles. Furthermore, the emotion of "pleasure" is arranged on the upper side of the concentric circles, and the emotion of "discomfort" is arranged on the lower side. In this way, in the emotion map 400, multiple emotions are mapped based on the structure by which emotions are generated, and emotions that tend to occur simultaneously are mapped close to each other.

[0161] These emotions are distributed in the 3 o'clock direction on emotion map 400, and typically fluctuate between relief and anxiety. In the right half of emotion map 400, situational awareness dominates over internal sensations, resulting in a sense of calm.

[0162] The inside of emotion map 400 represents what is going on in the mind, and the outside of emotion map 400 represents behavior, so the further you go outside emotion map 400, the more visible the emotions become (the more they are expressed in behavior).

[0163] Human emotions are based on various balances, such as posture and blood sugar levels. When these balances deviate from the ideal, a state of discomfort is expressed, and when they approach the ideal, a state of pleasure is expressed. Emotions can also be created for robots, cars, and motorcycles, based on various balances, such as posture and remaining battery life. When these balances deviate from the ideal, a state of discomfort is expressed, and when they approach the ideal, a state of pleasure is expressed. An emotion map can be generated, for example, based on Dr. Mitsuyoshi's emotion map (Research on speech emotion recognition and brain physiological signal analysis systems for emotions, Tokushima University, doctoral dissertation: https: / / ci.nii.ac.jp / naid / 500000375379). The left half of the emotion map lists emotions belonging to the area called "reaction," where sensation is dominant. The right half of the emotion map lists emotions belonging to the area called "situation," where situational awareness is dominant.

[0164] The emotion map defines two emotions that promote learning. One is a negative emotion on the situation side, around the middle of "repentance" or "reflection." In other words, this occurs when the robot experiences negative emotions such as "I never want to feel this way again" or "I don't want to be scolded again." The other is a positive emotion on the response side, around "desire." In other words, this occurs when the robot experiences positive feelings such as "I want more" or "I want to know more."

[0165] The emotion identification model 59 inputs user input into a pre-trained neural network, obtains emotion values ​​indicating each emotion shown in the emotion map 400, and determines the user's emotion. This neural network is pre-trained based on multiple pieces of training data that are combinations of user input and emotion values ​​indicating each emotion shown in the emotion map 400. Furthermore, this neural network is trained so that emotions that are located close to each other have similar values, as in the emotion map 900 shown in FIG. 10. FIG. 10 shows an example in which multiple emotions, "relieved," "calm," and "reassuring," have similar emotion values.

[0166] 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.

[0167] In the above embodiment, an example in which the specific processing program 56 is stored in the storage 32 has been described, but the technology of the present disclosure is not limited to this. For example, the specific processing program 56 may be stored in a portable, computer-readable, non-transitory storage medium such as a USB (Universal Serial Bus) memory. The specific processing program 56 stored in the non-transitory storage medium is installed in the computer 22 of the data processing device 12. The processor 28 executes the specific processing in accordance with the specific processing program 56.

[0168] Alternatively, the specific processing program 56 may be stored in a storage device such as a server connected to the data processing device 12 via the network 54, and the specific processing program 56 may be downloaded and installed on the computer 22 in response to a request from the data processing device 12.

[0169] 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.

[0170] The hardware resource for executing a specific process can be any of the following types of processors: A processor, for example, is a CPU, which is a general-purpose processor that functions as a hardware resource for executing a specific process by executing software, i.e., a program. A processor also includes a dedicated electrical circuit, such as an FPGA (Field-Programmable Gate Array), a PLD (Programmable Logic Device), or an ASIC (Application Specific Integrated Circuit), which is a processor with a circuit configuration designed specifically for executing a specific process. Each processor has built-in or connected memory, and each processor uses the memory to execute the specific process.

[0171] The hardware resource that executes the specific process may be configured with one of these various processors, or may be configured with a combination of two or more processors of the same or different types (for example, a combination of multiple FPGAs, or a combination of a CPU and an FPGA). Also, the hardware resource that executes the specific process may be a single processor.

[0172] As an example of a system configured with a single processor, first, one processor is configured by combining one or more CPUs and software, and this processor functions as a hardware resource that executes a specific process. Second, there is a system that uses a processor that realizes the functions of an entire system including multiple hardware resources that execute a specific process on a single IC chip, as typified by SoC (System-on-a-chip). In this way, a specific process is realized using one or more of the above-mentioned various processors as hardware resources.

[0173] Furthermore, the hardware structure of these various processors can be, more specifically, an electric circuit that combines circuit elements such as semiconductor devices. The specific processing described above is merely an example. Therefore, it goes without saying that unnecessary steps may be deleted, new steps may be added, or the processing order may be rearranged, without departing from the spirit of the invention.

[0174] In the above example, the first to fourth embodiments have been described separately, but some or all of these embodiments may be combined. The smart device 14, smart glasses 214, headset terminal 314, and robot 414 are merely examples, and they may be combined, or other devices may be used. In the above example, the first and second embodiments have been described separately, but they may be combined.

[0175] The above-described description and illustrations are a detailed explanation of the parts related to the technology of the present disclosure and are merely an example of the technology of the present disclosure. For example, the above description of the configuration, functions, actions, and effects is an explanation of an example of the configuration, functions, actions, and effects of the parts related to the technology of the present disclosure. Therefore, it goes without saying that unnecessary parts may be deleted, new elements may be added, or replacements may be made to the above-described description and illustrations within the scope of the gist of the technology of the present disclosure. Furthermore, to avoid confusion and facilitate understanding of the parts related to the technology of the present disclosure, the above-described description and illustrations omit explanations of common technical knowledge that do not require particular explanation to enable the implementation of the technology of the present disclosure.

[0176] All publications, patent applications, and technical standards mentioned in this specification are herein incorporated by reference to the same extent as if each individual publication, patent application, or technical standard was specifically and individually indicated to be incorporated by reference.

[0177] [Explanation of symbols]

[0178] 10, 210, 310, 410 Data Processing Systems 12 Data Processing Device 14 Smart Devices 214 Smart Glasses 314 Headset-type terminal 414 Robot

Claims

1. a matching unit that matches native speakers based on the user's selection; a support unit that supports real-time conversation between the user and the native speaker matched by the matching unit; a recording unit that records the user's learning progress based on the content of the conversation supported by the support unit. A system characterized by:

2. A feedback unit is provided to provide feedback.

2. The system of claim 1.

3. Includes an explanation section that explains the meaning and usage of new words 2. The system of claim 1.

4. The matching unit Includes an algorithm that matches native speakers based on user selections 2. The system of claim 1.

5. The support portion is Point out the user's grammatical errors and suggest correct expressions 2. The system of claim 1.

6. The recording unit Record the user's learning progress based on the content of the conversation and reflect it in the next conversation 2. The system of claim 1.

7. The matching unit Estimate user emotions and adjust native speaker selection based on the estimated user emotions 2. The system of claim 1.

8. The matching unit Analyze the user's past conversation history and select the most suitable native speaker 2. The system of claim 1.

9. The matching unit When matching, filtering is performed based on the user's current learning goals and interests.

2. The system of claim 1.

Images