system

Abstract

The system according to the embodiment aims to provide efficient and continuous conversation practice in a language other than one's native language. [Solution] A system according to an embodiment includes a selection unit, a start unit, a response unit, a correction unit, and a scenario providing unit. The selection unit selects the language in which the user wishes to converse. The start unit starts the conversation in the language selected by the selection unit. The response unit understands what the user says to the generated AI and returns a response. The correction unit points out and corrects the user's pronunciation and grammar errors based on the response provided by the response unit. The scenario providing unit practices conversation on a specific topic based on the correction provided by the correction 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] With conventional technology, practicing conversation in a language other than one's native language required finding a partner and arranging time, making it difficult to continue.

[0005] The system according to the embodiment aims to provide efficient and continuous conversation practice in a language other than one's native language. [Means for solving the problem]

[0006] The system according to the embodiment includes a selection unit, a start unit, a response unit, a correction unit, and a scenario providing unit. The selection unit selects the language in which the user wishes to converse. The start unit starts the conversation in the language selected by the selection unit. The response unit understands what the user says to the generating AI and returns a response. The correction unit points out and corrects the user's pronunciation and grammar errors based on the response provided by the response unit. The scenario providing unit practices conversation on a specific topic based on the correction provided by the correction unit. [Effects of the Invention]

[0007] The system according to the embodiment allows efficient and continuous conversation practice in a language other than one's native language. [Brief explanation of the drawings]

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

[0028] (Example 1) A language learning system according to an embodiment of the present invention utilizes a generative AI to provide an environment in which users can freely converse in languages ​​other than their native language. In this language learning system, a user selects the language in which they wish to converse, and the generative AI initiates a conversation in that language. The user can freely speak to the generative AI, which understands the content and provides appropriate responses. For example, if the user selects English, the generative AI initiates a conversation in English and responds to the user's speech in English. This system allows users to progress through language learning at their own pace, facilitating continuous learning. The generative AI can also point out the user's pronunciation and grammar errors and provide appropriate corrections. For example, if a user says, "I went to the store," the generative AI will point out, "'goed' is incorrect. The correct form is 'went'." Furthermore, the system allows users to practice conversations on specific topics and provides conversation scenarios tailored to their needs. For example, if a user wants to practice business conversations, the generative AI will provide business-related topics and conduct the conversation based on those topics. This allows users to acquire language skills useful in real-world situations. This language learning system allows users to progress through language learning at their own pace, facilitating continuous learning. It also helps users acquire accurate language skills by pointing out pronunciation and grammar mistakes and providing appropriate corrections.Furthermore, by practicing conversations on specific topics, users can acquire language skills that are useful in real-life situations.

[0029] A language learning system according to an embodiment includes a selection unit, an initiation unit, a response unit, a correction unit, and a scenario providing unit. The selection unit selects a language in which a user wishes to converse. For example, the selection unit allows the user to select from languages ​​such as English, Japanese, and Spanish. The selection unit can also allow the user to select a language using voice input or text input. The initiation unit starts a conversation in the language selected by the selection unit. For example, if the user selects English, the initiation unit starts the conversation in English. The initiation unit can also adjust the timing of the start of the conversation based on the language selected by the user. The response unit understands what the user says to the generation AI and returns an appropriate response. For example, the response unit understands what the user says using voice recognition technology or natural language processing technology. The response unit can also return an appropriate response to the user using a voice response or a text response. The correction unit points out the user's pronunciation or grammar errors based on the response provided by the response unit and makes appropriate corrections. For example, if a user says, "I went to the store," the correction unit points out, "'goed' is incorrect. The correct form is 'went'." The correction unit can also provide corrections to the user using audio feedback or text feedback. The scenario providing unit practices a conversation on a specific topic based on the content corrected by the correction unit. For example, if a user wants to practice business conversation, the scenario providing unit provides a business-related topic and advances the conversation based on that topic. This allows the language learning system according to the embodiment to allow the user to progress with language learning at their own pace, facilitating continuous learning. Furthermore, by pointing out the user's pronunciation and grammar errors and making appropriate corrections, the user can acquire accurate language skills. Furthermore, by practicing conversation on a specific topic, the user can acquire language skills that are useful in real situations.

[0030] The selection unit can analyze the user's past language learning history and automatically select a language. For example, the selection unit can analyze the user's progress in languages ​​they have previously learned and suggest the next language they should learn. For example, the selection unit can analyze the user's progress in English and suggest Spanish as the next language they should learn. The selection unit can also select a new language based on the user's best language among the languages ​​they have previously learned. For example, the selection unit can select a new kanji character based on the user's best kanji character among the Japanese characters they have previously learned. The selection unit can also suggest the user to restudy the user's weakest language among the languages ​​they have previously learned. For example, the selection unit can suggest the user to restudy the user's weakest grammar among the French characters they have previously learned. This enables efficient learning by selecting the optimal language based on the user's past learning history. Some or all of the above-described processing by the selection unit may be performed using, or without, AI. For example, the selection unit can input the user's past learning data into a generation AI and have the generation AI select the optimal language.

[0031] The selection unit can suggest languages ​​of difficulty based on the user's current learning progress. For example, if the user is at a beginner's level, the selection unit can suggest a basic language. For example, if the user is at a beginner's level, the selection unit can suggest basic English phrases. Furthermore, if the user is at an intermediate level, the selection unit can suggest a language with which the user can carry out everyday conversations. For example, if the user is at an intermediate level, the selection unit can suggest everyday Spanish conversations. Furthermore, if the user is at an advanced level, the selection unit can suggest a language with which the user can speak about specialized topics. For example, if the user is at an advanced level, the selection unit can suggest business English. This can improve learning effectiveness by suggesting a language of appropriate difficulty according to the user's current learning progress. Some or all of the above-described processing by the selection unit can be performed using, for example, AI, or can be performed without AI. For example, the selection unit can input the user's learning progress data into a generation AI and cause the generation AI to suggest languages ​​of appropriate difficulty.

[0032] The selection unit can preferentially suggest a language associated with a region based on the user's geographical location information. For example, if the user is traveling, the selection unit can suggest a language used in the region. For example, if the user is traveling, the selection unit can suggest the official language of the country to which the user is traveling. Furthermore, if the user is planning to move, the selection unit can suggest a language used in the new place of residence. For example, if the user is planning to move, the selection unit can suggest a language used in the new place of residence. Furthermore, if the user is attending an international event, the selection unit can suggest a language used in the event. For example, if the user is attending an international conference, the selection unit can suggest the official language of the conference. This can improve practicality by suggesting an appropriate language based on the geographical location information. Some or all of the above-described processing by the selection unit may be performed using AI, for example, or without AI. For example, the selection unit can input the user's geographical location data into the generation AI and cause the generation AI to suggest a language associated with the region.

[0033] The selection unit can analyze the user's social media activity and suggest languages ​​of interest. For example, the selection unit can suggest the language of accounts the user frequently follows. For example, if the accounts the user frequently follows post in French, the selection unit can suggest French. The selection unit can also suggest the language of content the user frequently views. For example, if the videos the user frequently views are in Spanish, the selection unit can suggest Spanish. The selection unit can also suggest the language of online communities the user participates in. For example, if the online forum the user participates in is in German, the selection unit can suggest German. This can increase motivation to learn by suggesting languages ​​of interest based on social media activity. Some or all of the above-described processing by the selection unit can be performed using AI, for example, or without AI. For example, the selection unit can input the user's social media data into the generation AI and cause the generation AI to suggest languages ​​of interest.

[0034] The initiation unit can analyze the user's past conversation history and select an optimal initiation method. For example, the initiation unit can reuse an initiation method that the user previously preferred. For example, the initiation unit can reuse a greeting phrase that the user previously preferred. The initiation unit can also avoid initiation methods that the user previously avoided. For example, the initiation unit can avoid topics that the user previously avoided. Furthermore, the initiation unit can refer to conversation initiation methods that the user has previously successfully used. For example, the initiation unit can start a new conversation based on conversation initiation methods that the user has previously successfully used. This enables efficient conversations by selecting an optimal initiation method based on the past conversation history. Some or all of the above-described processing in the initiation unit can be performed using, for example, AI, or can be performed without using AI. For example, the initiation unit can input the user's past conversation data into the generation AI and cause the generation AI to select an optimal initiation method.

[0035] The start unit can automatically generate an appropriate conversation scenario based on the user's current learning progress. For example, if the user is at a beginner's level, the start unit generates a scenario that starts with a simple greeting. For example, if the user is at a beginner's level, the start unit can generate a scenario of basic greetings and self-introductions. Furthermore, if the user is at an intermediate level, the start unit can generate a scenario including everyday conversations. For example, if the user is at an intermediate level, the start unit can generate a conversation scenario for shopping or a restaurant. Furthermore, if the user is at an advanced level, the start unit can generate a scenario including a specialized topic. For example, if the user is at an advanced level, the start unit can generate a scenario for a business meeting or presentation. This can improve learning effectiveness by providing an appropriate conversation scenario according to the user's current learning progress. Some or all of the above-described processing in the start unit may be performed using, or without, AI. For example, the start unit can input the user's learning progress data into the generation AI and cause the generation AI to automatically generate an appropriate conversation scenario.

[0036] The initiation unit can start a conversation on a topic related to the region, taking into account the user's geographical location information. For example, if the user is traveling, the initiation unit can start a conversation about tourist spots in the region. For example, if the user is traveling, the initiation unit can start a conversation about tourist spots at the travel destination. Furthermore, if the user is planning to move, the initiation unit can start a conversation about information about the user's new residence. For example, if the user is planning to move, the initiation unit can start a conversation about lifestyle information in the new residence. Furthermore, if the user is attending an international event, the initiation unit can start a conversation about the event. For example, if the user is attending an international conference, the initiation unit can start a conversation about the content and participants of the conference. This improves practicality by starting a conversation on an appropriate topic based on the geographical location information. Some or all of the above-described processing in the initiation unit can be performed using AI, for example, or without AI. For example, the initiation unit can input the user's geographical location data into the generation AI and cause the generation AI to start a conversation on a topic related to the region.

[0037] The initiation unit can analyze the user's social media activity and start a conversation on a topic of interest. For example, the initiation unit can start a conversation on a topic of an account frequently followed by the user. For example, if an account frequently followed by the user posts about cooking, the initiation unit can start a conversation about cooking. The initiation unit can also start a conversation on a topic of content frequently viewed by the user. For example, if the videos frequently viewed by the user are about travel, the initiation unit can start a conversation about travel. The initiation unit can also start a conversation on a topic of an online community in which the user participates. For example, if the online forum in which the user participates is about technology, the initiation unit can start a conversation about technology. This can increase motivation to learn by starting a conversation on a topic of interest based on social media activity. Some or all of the above-described processing in the initiation unit can be performed using, for example, AI, or can be performed without AI. For example, the initiation unit can input the user's social media data into the generation AI and cause the generation AI to start a conversation on a topic of interest.

[0038] The response unit can analyze the user's past conversation history and select the optimal response method. For example, the response unit can reuse a response method that the user previously preferred. For example, the response unit can reuse a phrase that the user previously preferred. The response unit can also avoid a response method that the user previously avoided. For example, the response unit can avoid a topic that the user previously avoided. Furthermore, the response unit can refer to a response method that the user used in a successful conversation in the past. For example, the response unit can generate a new response based on a response method that the user used in a successful conversation in the past. This enables efficient conversations by selecting the optimal response method based on the past conversation history. Some or all of the above-described processing in the response unit can be performed using, for example, AI, or can be performed without AI. For example, the response unit can input the user's past conversation data into a generation AI and have the generation AI select the optimal response method.

[0039] The response unit can automatically generate appropriate responses based on the user's current learning progress. For example, if the user is at a beginner's level, the response unit generates simple responses. For example, if the user is at a beginner's level, the response unit can generate responses using basic phrases. Furthermore, if the user is at an intermediate level, the response unit can generate responses including everyday conversations. For example, if the user is at an intermediate level, the response unit can generate responses including conversations about shopping or restaurants. Furthermore, if the user is at an advanced level, the response unit can generate responses including specialized topics. For example, if the user is at an advanced level, the response unit can generate responses related to business meetings or presentations. This can improve learning effectiveness by providing appropriate responses according to the user's current learning progress. Some or all of the above-described processing in the response unit can be performed using, for example, AI, or without AI. For example, the response unit can input the user's learning progress data into a generation AI and cause the generation AI to automatically generate appropriate responses.

[0040] The response unit can generate a response including information related to the region, taking into account the user's geographical location information. For example, if the user is traveling, the response unit can respond with information about tourist spots in the region. For example, if the user is traveling, the response unit can provide a response including information about tourist spots at the travel destination. Furthermore, if the user is planning to move, the response unit can also provide information about the user's new residence. For example, if the user is planning to move, the response unit can provide a response about lifestyle information for the new residence. Furthermore, if the user is participating in an international event, the response unit can also provide a response about the event. For example, if the user is participating in an international conference, the response unit can provide a response including information about the conference content and participants. This can improve practicality by providing appropriate information based on the geographical location information. Some or all of the above-described processing by the response unit can be performed using AI, for example, or without AI. For example, the response unit can input the user's geographical location data into the generation AI and cause the generation AI to generate a response including information related to the region.

[0041] The response unit can analyze the user's social media activity and generate a response including information of interest. For example, the response unit generates a response including information about accounts frequently followed by the user. For example, if the accounts frequently followed by the user post about technology, the response unit can generate a response including information about technology. The response unit can also generate a response including information about content frequently viewed by the user. For example, if the videos frequently viewed by the user are about travel, the response unit can generate a response including information about travel. The response unit can also generate a response including information about online communities in which the user participates. For example, if the online forum in which the user participates is about cooking, the response unit can generate a response including information about cooking. This can increase the user's motivation to learn by providing information of interest based on the user's social media activity. Some or all of the above-described processing by the response unit can be performed using, for example, AI, or without AI. For example, the response unit can input the user's social media data into a generation AI and cause the generation AI to generate a response including information of interest.

[0042] The correction unit can analyze the user's past pronunciation and grammar errors and select the optimal correction method. For example, the correction unit can focus on correcting pronunciations that the user frequently made incorrectly in the past. For example, the correction unit can have the user re-practice pronunciations that the user frequently made incorrectly in the past. The correction unit can also re-explain and correct grammar that the user made incorrectly in the past. For example, the correction unit can re-explain grammar rules that the user made incorrectly in the past and have the user practice them. Furthermore, the correction unit can refer to correction methods that the user used successfully in the past. For example, the correction unit can suggest a new correction method based on correction methods that the user used successfully in the past. This enables efficient learning by providing the optimal correction method based on past errors. Some or all of the above-described processing in the correction unit can be performed using, for example, AI, or without AI. For example, the correction unit can input the user's past learning data into the generation AI and cause the generation AI to select the optimal correction method.

[0043] The correction unit can automatically generate appropriate correction content based on the user's current learning progress. For example, if the user is at a beginner's level, the correction unit can correct basic pronunciation and grammar. For example, if the user is at a beginner's level, the correction unit can correct basic pronunciation and grammar. Furthermore, if the user is at an intermediate level, the correction unit can also correct pronunciation and grammar in everyday conversation. For example, if the user is at an intermediate level, the correction unit can correct pronunciation and grammar in everyday conversation. Furthermore, if the user is at an advanced level, the correction unit can also correct pronunciation and grammar in specialized topics. For example, if the user is at an advanced level, the correction unit can correct pronunciation and grammar in specialized topics. This can improve learning effectiveness by providing appropriate correction content according to the user's current learning progress. Some or all of the above-described processing by the correction unit may be performed using, or without, AI. For example, the correction unit can input the user's learning progress data into a generation AI and cause the generation AI to automatically generate appropriate correction content.

[0044] The correction unit can prioritize correction of pronunciation and grammar related to a region, taking into account the user's geographical location information. For example, if the user is traveling, the correction unit can prioritize correction of pronunciation and grammar commonly used in that region. For example, if the user is traveling, the correction unit can prioritize correction of pronunciation and grammar commonly used in the country to which the user is traveling. Furthermore, if the user is planning to move, the correction unit can prioritize correction of pronunciation and grammar required in the new place of residence. For example, if the user is planning to move, the correction unit can prioritize correction of pronunciation and grammar based on the language characteristics of the new place of residence. Furthermore, if the user is attending an international event, the correction unit can prioritize correction of pronunciation and grammar required for the event. For example, if the user is attending an international conference, the correction unit can prioritize correction of pronunciation and grammar of the language used in the conference. This can improve practicality by providing appropriate corrections based on geographical location information. Some or all of the above-mentioned processing by the correction unit can be performed, for example, using AI or without AI. For example, the correction unit can input the user's geographic location data into the generation AI and cause the generation AI to perform region-related pronunciation and grammar corrections.

[0045] The correction unit can analyze the user's social media activity and make corrections related to topics of interest. For example, the correction unit corrects pronunciation and grammar related to topics of accounts frequently followed by the user. For example, if an account frequently followed by the user posts about technology, the correction unit can correct pronunciation and grammar related to technology. The correction unit can also correct pronunciation and grammar related to topics of content frequently viewed by the user. For example, if the videos frequently viewed by the user are about travel, the correction unit can correct pronunciation and grammar related to travel. The correction unit can also correct pronunciation and grammar related to topics of online communities in which the user participates. For example, if the online forum in which the user participates is about cooking, the correction unit can correct pronunciation and grammar related to cooking. This can increase motivation to learn by providing corrections related to topics of interest based on social media activity. Some or all of the above-mentioned processing by the correction unit can be performed using, for example, AI, or without AI. For example, the correction unit can input the user's social media data into the generation AI and cause the generation AI to perform corrections related to topics of interest.

[0046] The scenario providing unit can analyze the user's past conversation history and select an optimal scenario. The scenario providing unit, for example, can provide a scenario that the user previously preferred. For example, the scenario providing unit can provide a travel scenario that the user previously preferred. The scenario providing unit can also avoid scenarios that the user previously avoided. For example, the scenario providing unit can avoid business conversation scenarios that the user previously avoided. Furthermore, the scenario providing unit can refer to scenarios that the user previously used successfully. For example, the scenario providing unit can provide a new scenario based on an everyday conversation scenario that the user previously used successfully. This enables efficient learning by providing an optimal scenario based on the user's past conversation history. Some or all of the above-described processing in the scenario providing unit may be performed using, for example, AI, or may be performed without AI. For example, the scenario providing unit can input the user's past conversation data into a generation AI and cause the generation AI to select an optimal scenario.

[0047] The scenario providing unit can automatically generate an appropriate scenario based on the user's current learning progress. For example, if the user is at a beginner's level, the scenario providing unit generates a simple scenario. For example, if the user is at a beginner's level, the scenario providing unit can generate a scenario of basic greetings and self-introductions. Furthermore, if the user is at an intermediate level, the scenario providing unit can generate a scenario including everyday conversations. For example, if the user is at an intermediate level, the scenario providing unit can generate a conversation scenario for shopping or a restaurant. Furthermore, if the user is at an advanced level, the scenario providing unit can generate a scenario including specialized topics. For example, if the user is at an advanced level, the scenario providing unit can generate a scenario for a business meeting or presentation. This can improve learning effectiveness by providing an appropriate scenario according to the user's current learning progress. Some or all of the above-described processing in the scenario providing unit can be performed using, for example, AI, or without AI. For example, the scenario providing unit can input the user's learning progress data into a generation AI and cause the generation AI to automatically generate an appropriate scenario.

[0048] The scenario providing unit can provide a scenario related to a region by taking into account the user's geographical location information. For example, if the user is traveling, the scenario providing unit can provide a scenario about tourist spots in the region. For example, if the user is traveling, the scenario providing unit can provide a scenario about tourist spots at the travel destination. Furthermore, if the user is planning to move, the scenario providing unit can provide a scenario about information about the user's new residence. For example, if the user is planning to move, the scenario providing unit can provide a scenario about lifestyle information in the new residence. Furthermore, if the user is participating in an international event, the scenario providing unit can provide a scenario about the event. For example, if the user is participating in an international conference, the scenario providing unit can provide a scenario about the content and participants of the conference. This can improve practicality by providing an appropriate scenario based on the geographical location information. Some or all of the above-described processing by the scenario providing unit can be performed using AI, for example, or without AI. For example, the scenario providing unit can input the user's geographical location data into the generation AI and cause the generation AI to provide a scenario related to the region.

[0049] The scenario providing unit can analyze the user's social media activity and provide scenarios related to topics of interest. For example, the scenario providing unit can provide scenarios related to topics of accounts frequently followed by the user. For example, if the accounts frequently followed by the user post about technology, the scenario providing unit can provide technology-related scenarios. The scenario providing unit can also provide scenarios related to topics of content frequently viewed by the user. For example, if the videos frequently viewed by the user are about travel, the scenario providing unit can provide travel-related scenarios. Furthermore, the scenario providing unit can also provide scenarios related to topics of online communities in which the user participates. For example, if the online forum in which the user participates is about cooking, the scenario providing unit can provide cooking-related scenarios. This can increase motivation to learn by providing scenarios related to topics of interest based on social media activity. Some or all of the above-described processing by the scenario providing unit can be performed using, for example, AI, or without AI. For example, the scenario providing unit can input the user's social media data into the generation AI and cause the generation AI to provide scenarios related to topics of interest.

[0050] The system according to the embodiment is not limited to the above-described example, and various modifications are possible, for example, as follows.

[0051] The selection unit can monitor the user's health condition and suggest appropriate timing for language learning. For example, if the user is tired, the selection unit can suggest a simple lesson that can be completed in a short time. Also, if the user is healthy and energetic, the selection unit can suggest a long, intensive study. Furthermore, if the user is sick or feeling unwell, the selection unit can suggest a lesson with relaxing content. This can improve the learning effect by providing the optimal learning timing according to the user's health condition.

[0052] The initiation unit can analyze the user's past study patterns and propose an optimal study schedule. For example, the initiation unit can analyze the time periods in which the user studied in the past and propose to start studying during those time periods. The initiation unit can also analyze how often the user studied in the past and propose a study schedule based on that frequency. Furthermore, the initiation unit can analyze the content the user studied in the past and propose a study schedule based on that content. This makes it possible to support efficient study by providing an optimal study schedule based on the user's past study patterns.

[0053] The response unit can analyze the user's learning style and select the optimal response method. For example, if the user is a visual learner, the response unit can provide a response that includes visual information. If the user is an auditory learner, the response unit can also provide a response that emphasizes audio. Furthermore, if the user is an experiential learner, the response unit can also provide a response that includes practical examples. This makes it possible to improve learning effectiveness by providing the optimal response method according to the user's learning style.

[0054] The correction unit can analyze the user's learning history and select the optimal correction method. For example, the correction unit can analyze what the user has learned in the past and make corrections based on that content. The correction unit can also analyze where the user made mistakes in the past and focus on those parts when making corrections. Furthermore, the correction unit can refer to correction methods that the user has used successfully in the past and make corrections using those methods. This makes it possible to support efficient learning by providing the optimal correction method based on the user's past learning history.

[0055] The scenario providing unit can set a learning goal for the user and provide a scenario based on that goal. For example, if the user wants to learn business English, the scenario providing unit can provide a business-related scenario. Also, if the user wants to learn travel English, the scenario providing unit can provide a travel-related scenario. Furthermore, if the user wants to learn everyday conversation, the scenario providing unit can provide a everyday conversation-related scenario. This can improve the learning effect by providing an optimal scenario according to the user's learning goal.

[0056] The processing flow of the first embodiment will be briefly explained below.

[0057] Step 1: The selection unit selects the language in which the user wishes to converse. For example, the user can select from languages ​​such as English, Japanese, and Spanish. The user can also select the language using voice input or text input. Step 2: The initiation unit initiates the conversation in the language selected by the selection unit. For example, if the user selects English, the conversation is initiated in English. The initiation unit can also adjust the timing of the conversation start based on the language selected by the user. Step 3: The response unit understands what the user is saying to the generated AI and returns an appropriate response. For example, it can use voice recognition technology or natural language processing technology to understand what the user is saying and return an appropriate response using voice or text. Step 4: The correction unit points out the user's pronunciation and grammar errors based on the response from the response unit and makes appropriate corrections. For example, if the user says, "I went to the store," the correction unit will point out, "'goed' is incorrect. The correct form is 'went'." Corrections can also be made using voice feedback or text feedback. Step 5: The scenario providing unit practices a conversation on a specific topic based on the content corrected by the correcting unit. For example, if the user wants to practice business conversation, the scenario providing unit provides a business-related topic and conducts a conversation based on that topic.

[0058] (Example 2) A language learning system according to an embodiment of the present invention utilizes a generative AI to provide an environment in which users can freely converse in languages ​​other than their native language. In this language learning system, a user selects the language in which they wish to converse, and the generative AI initiates a conversation in that language. The user can freely speak to the generative AI, which understands the content and provides appropriate responses. For example, if the user selects English, the generative AI initiates a conversation in English and responds to the user's speech in English. This system allows users to progress through language learning at their own pace, facilitating continuous learning. The generative AI can also point out the user's pronunciation and grammar errors and provide appropriate corrections. For example, if a user says, "I went to the store," the generative AI will point out, "'goed' is incorrect. The correct form is 'went'." Furthermore, the system allows users to practice conversations on specific topics and provides conversation scenarios tailored to their needs. For example, if a user wants to practice business conversations, the generative AI will provide business-related topics and conduct the conversation based on those topics. This allows users to acquire language skills useful in real-world situations. This language learning system allows users to progress through language learning at their own pace, facilitating continuous learning. It also helps users acquire accurate language skills by pointing out pronunciation and grammar mistakes and providing appropriate corrections.Furthermore, by practicing conversations on specific topics, users can acquire language skills that are useful in real-life situations.

[0059] A language learning system according to an embodiment includes a selection unit, an initiation unit, a response unit, a correction unit, and a scenario providing unit. The selection unit selects a language in which a user wishes to converse. For example, the selection unit allows the user to select from languages ​​such as English, Japanese, and Spanish. The selection unit can also allow the user to select a language using voice input or text input. The initiation unit starts a conversation in the language selected by the selection unit. For example, if the user selects English, the initiation unit starts the conversation in English. The initiation unit can also adjust the timing of the start of the conversation based on the language selected by the user. The response unit understands what the user says to the generation AI and returns an appropriate response. For example, the response unit understands what the user says using voice recognition technology or natural language processing technology. The response unit can also return an appropriate response to the user using a voice response or a text response. The correction unit points out the user's pronunciation or grammar errors based on the response provided by the response unit and makes appropriate corrections. For example, if a user says, "I went to the store," the correction unit points out, "'goed' is incorrect. The correct form is 'went'." The correction unit can also provide corrections to the user using audio feedback or text feedback. The scenario providing unit practices a conversation on a specific topic based on the content corrected by the correction unit. For example, if a user wants to practice business conversation, the scenario providing unit provides a business-related topic and advances the conversation based on that topic. This allows the language learning system according to the embodiment to allow the user to progress with language learning at their own pace, facilitating continuous learning. Furthermore, by pointing out the user's pronunciation and grammar errors and making appropriate corrections, the user can acquire accurate language skills. Furthermore, by practicing conversation on a specific topic, the user can acquire language skills that are useful in real situations.

[0060] The selection unit can estimate the user's emotions and suggest a language based on the estimated user's emotions. For example, if the user is relaxed, the selection unit determines that the user has a high motivation to learn and suggests a language with a high level of difficulty. For example, if the user is relaxed, the selection unit can suggest business English. Furthermore, if the user is stressed, the selection unit can suggest simple and familiar language. For example, if the user is stressed, the selection unit can suggest phrases for everyday conversation. Furthermore, if the user is excited, the selection unit can suggest language that allows for lively conversation to help the user utilize their energy. For example, if the user is excited, the selection unit can suggest a topic related to sports. This can increase the user's motivation to learn by suggesting the optimal language according to the user's emotions. Emotion estimation is achieved using an emotion estimation function, for example, an emotion engine or a generation AI. The generation AI can be, but is not limited to, a text generation AI (e.g., LLM) or a multimodal generation AI. Some or all of the above-described processing in the selection unit may be performed using, for example, an AI, or may be performed without using an AI. For example, the selection unit can input the user's facial expression data into the generation AI and cause the generation AI to estimate the user's emotions.

[0061] The selection unit can analyze the user's past language learning history and automatically select a language. For example, the selection unit can analyze the user's progress in languages ​​they have previously learned and suggest the next language they should learn. For example, the selection unit can analyze the user's progress in English and suggest Spanish as the next language they should learn. The selection unit can also select a new language based on the user's best language among the languages ​​they have previously learned. For example, the selection unit can select a new kanji character based on the user's best kanji character among the Japanese characters they have previously learned. The selection unit can also suggest the user to restudy the user's weakest language among the languages ​​they have previously learned. For example, the selection unit can suggest the user to restudy the user's weakest grammar among the French characters they have previously learned. This enables efficient learning by selecting the optimal language based on the user's past learning history. Some or all of the above-described processing by the selection unit may be performed using, or without, AI. For example, the selection unit can input the user's past learning data into a generation AI and have the generation AI select the optimal language.

[0062] The selection unit can suggest languages ​​of difficulty based on the user's current learning progress. For example, if the user is at a beginner's level, the selection unit can suggest a basic language. For example, if the user is at a beginner's level, the selection unit can suggest basic English phrases. Furthermore, if the user is at an intermediate level, the selection unit can suggest a language with which the user can carry out everyday conversations. For example, if the user is at an intermediate level, the selection unit can suggest everyday Spanish conversations. Furthermore, if the user is at an advanced level, the selection unit can suggest a language with which the user can speak about specialized topics. For example, if the user is at an advanced level, the selection unit can suggest business English. This can improve learning effectiveness by suggesting a language of appropriate difficulty according to the user's current learning progress. Some or all of the above-described processing by the selection unit can be performed using, for example, AI, or can be performed without AI. For example, the selection unit can input the user's learning progress data into a generation AI and cause the generation AI to suggest languages ​​of appropriate difficulty.

[0063] The selection unit can estimate the user's emotion and customize the interface based on the estimated user emotion. For example, if the user is nervous, the selection unit can provide a simple, highly visible interface. For example, if the user is nervous, the selection unit can provide a simple interface. Furthermore, if the user is relaxed, the selection unit can provide an interface containing detailed information. For example, if the user is relaxed, the selection unit can provide an interface containing detailed explanations and guides. Furthermore, if the user is excited, the selection unit can provide a visually stimulating interface. For example, if the user is excited, the selection unit can provide a colorful and dynamic interface. This can improve usability by providing an interface that corresponds to the user's emotion. 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 selection unit can be performed using, for example, an AI. For example, the selection unit can input the user's facial expression data into the generation AI and cause the generation AI to customize the interface.

[0064] The selection unit can preferentially suggest a language associated with a region based on the user's geographical location information. For example, if the user is traveling, the selection unit can suggest a language used in the region. For example, if the user is traveling, the selection unit can suggest the official language of the country to which the user is traveling. Furthermore, if the user is planning to move, the selection unit can suggest a language used in the new place of residence. For example, if the user is planning to move, the selection unit can suggest a language used in the new place of residence. Furthermore, if the user is attending an international event, the selection unit can suggest a language used in the event. For example, if the user is attending an international conference, the selection unit can suggest the official language of the conference. This can improve practicality by suggesting an appropriate language based on the geographical location information. Some or all of the above-described processing by the selection unit may be performed using AI, for example, or without AI. For example, the selection unit can input the user's geographical location data into the generation AI and cause the generation AI to suggest a language associated with the region.

[0065] The selection unit can analyze the user's social media activity and suggest languages ​​of interest. For example, the selection unit can suggest the language of accounts the user frequently follows. For example, if the accounts the user frequently follows post in French, the selection unit can suggest French. The selection unit can also suggest the language of content the user frequently views. For example, if the videos the user frequently views are in Spanish, the selection unit can suggest Spanish. The selection unit can also suggest the language of online communities the user participates in. For example, if the online forum the user participates in is in German, the selection unit can suggest German. This can increase motivation to learn by suggesting languages ​​of interest based on social media activity. Some or all of the above-described processing by the selection unit can be performed using AI, for example, or without AI. For example, the selection unit can input the user's social media data into the generation AI and cause the generation AI to suggest languages ​​of interest.

[0066] The initiation unit can estimate the user's emotions and adjust the timing of starting the conversation based on the estimated user's emotions. For example, if the user is relaxed, the initiation unit can immediately start the conversation. Furthermore, if the user is nervous, the initiation unit can wait a short time before starting the conversation. For example, if the user is nervous, the initiation unit can allow the user a few minutes to relax before starting the conversation. Furthermore, if the user is excited, the initiation unit can immediately start a conversation to utilize their energy. For example, if the user is excited, the initiation unit can immediately start a lively conversation. This allows the conversation to start at an appropriate time according to the user's emotions, thereby improving learning effectiveness. The emotion estimation is realized using an emotion estimation function, such as 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 initiation unit can be performed using, for example, an AI, or without an AI. For example, the initiation unit can input the user's facial expression data into the generation AI and cause the generation AI to adjust the timing of the start of the conversation.

[0067] The initiation unit can analyze the user's past conversation history and select an optimal initiation method. For example, the initiation unit can reuse an initiation method that the user previously preferred. For example, the initiation unit can reuse a greeting phrase that the user previously preferred. The initiation unit can also avoid initiation methods that the user previously avoided. For example, the initiation unit can avoid topics that the user previously avoided. Furthermore, the initiation unit can refer to conversation initiation methods that the user has previously successfully used. For example, the initiation unit can start a new conversation based on conversation initiation methods that the user has previously successfully used. This enables efficient conversations by selecting an optimal initiation method based on the past conversation history. Some or all of the above-described processing in the initiation unit can be performed using, for example, AI, or can be performed without using AI. For example, the initiation unit can input the user's past conversation data into the generation AI and cause the generation AI to select an optimal initiation method.

[0068] The start unit can automatically generate an appropriate conversation scenario based on the user's current learning progress. For example, if the user is at a beginner's level, the start unit generates a scenario that starts with a simple greeting. For example, if the user is at a beginner's level, the start unit can generate a scenario of basic greetings and self-introductions. Furthermore, if the user is at an intermediate level, the start unit can generate a scenario including everyday conversations. For example, if the user is at an intermediate level, the start unit can generate a conversation scenario for shopping or a restaurant. Furthermore, if the user is at an advanced level, the start unit can generate a scenario including a specialized topic. For example, if the user is at an advanced level, the start unit can generate a scenario for a business meeting or presentation. This can improve learning effectiveness by providing an appropriate conversation scenario according to the user's current learning progress. Some or all of the above-described processing in the start unit may be performed using, or without, AI. For example, the start unit can input the user's learning progress data into the generation AI and cause the generation AI to automatically generate an appropriate conversation scenario.

[0069] The initiation unit can estimate the user's emotions and customize a conversation initiation method based on the estimated user's emotions. For example, if the user is nervous, the initiation unit can start the conversation in a calm tone. For example, if the user is nervous, the initiation unit can greet the user in a calm tone. Furthermore, if the user is relaxed, the initiation unit can start the conversation in a friendly tone. For example, if the user is relaxed, the initiation unit can start the conversation in a friendly tone. Furthermore, if the user is excited, the initiation unit can start the conversation in an energetic tone. For example, if the user is excited, the initiation unit can start the conversation in a lively tone. This improves usability by providing a conversation initiation method that corresponds to the user's emotions. Emotion estimation is realized using an emotion estimation function, for example, an emotion engine or a generation AI. The generation AI can be a text generation AI (e.g., LLM) or a multimodal generation AI, but is not limited to such examples. Some or all of the above-described processing in the initiation unit can be performed, for example, using AI or without AI. For example, the initiation unit can input the user's facial expression data into the generation AI and cause the generation AI to customize how the conversation starts.

[0070] The initiation unit can start a conversation on a topic related to the region, taking into account the user's geographical location information. For example, if the user is traveling, the initiation unit can start a conversation about tourist spots in the region. For example, if the user is traveling, the initiation unit can start a conversation about tourist spots at the travel destination. Furthermore, if the user is planning to move, the initiation unit can start a conversation about information about the user's new residence. For example, if the user is planning to move, the initiation unit can start a conversation about lifestyle information in the new residence. Furthermore, if the user is attending an international event, the initiation unit can start a conversation about the event. For example, if the user is attending an international conference, the initiation unit can start a conversation about the content and participants of the conference. This improves practicality by starting a conversation on an appropriate topic based on the geographical location information. Some or all of the above-described processing in the initiation unit can be performed using AI, for example, or without AI. For example, the initiation unit can input the user's geographical location data into the generation AI and cause the generation AI to start a conversation on a topic related to the region.

[0071] The initiation unit can analyze the user's social media activity and start a conversation on a topic of interest. For example, the initiation unit can start a conversation on a topic of an account frequently followed by the user. For example, if an account frequently followed by the user posts about cooking, the initiation unit can start a conversation about cooking. The initiation unit can also start a conversation on a topic of content frequently viewed by the user. For example, if the videos frequently viewed by the user are about travel, the initiation unit can start a conversation about travel. The initiation unit can also start a conversation on a topic of an online community in which the user participates. For example, if the online forum in which the user participates is about technology, the initiation unit can start a conversation about technology. This can increase motivation to learn by starting a conversation on a topic of interest based on social media activity. Some or all of the above-described processing in the initiation unit can be performed using, for example, AI, or can be performed without AI. For example, the initiation unit can input the user's social media data into the generation AI and cause the generation AI to start a conversation on a topic of interest.

[0072] The response unit can estimate the user's emotions and adjust the tone and style of the response based on the estimated user's emotions. For example, if the user is nervous, the response unit can respond in a calm tone. For example, if the user is nervous, the response unit can respond in a gentle tone. Furthermore, if the user is relaxed, the response unit can respond in a friendly tone. For example, if the user is relaxed, the response unit can respond in a friendly tone. Furthermore, if the user is excited, the response unit can respond in an energetic tone. For example, if the user is excited, the response unit can respond in a lively tone. This can improve usability by providing a response that corresponds to the user's emotions. Emotion estimation is realized using an emotion estimation function, for example, an emotion engine or a generation AI. The generation AI can be, 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 response unit can be performed, for example, using AI or without AI. For example, the response unit can input the user's facial expression data into the generation AI and have the generation AI adjust the tone and style of the response.

[0073] The response unit can analyze the user's past conversation history and select the optimal response method. For example, the response unit can reuse a response method that the user previously preferred. For example, the response unit can reuse a phrase that the user previously preferred. The response unit can also avoid a response method that the user previously avoided. For example, the response unit can avoid a topic that the user previously avoided. Furthermore, the response unit can refer to a response method that the user used in a successful conversation in the past. For example, the response unit can generate a new response based on a response method that the user used in a successful conversation in the past. This enables efficient conversations by selecting the optimal response method based on the past conversation history. Some or all of the above-described processing in the response unit can be performed using, for example, AI, or can be performed without AI. For example, the response unit can input the user's past conversation data into a generation AI and have the generation AI select the optimal response method.

[0074] The response unit can automatically generate appropriate responses based on the user's current learning progress. For example, if the user is at a beginner's level, the response unit generates simple responses. For example, if the user is at a beginner's level, the response unit can generate responses using basic phrases. Furthermore, if the user is at an intermediate level, the response unit can generate responses including everyday conversations. For example, if the user is at an intermediate level, the response unit can generate responses including conversations about shopping or restaurants. Furthermore, if the user is at an advanced level, the response unit can generate responses including specialized topics. For example, if the user is at an advanced level, the response unit can generate responses related to business meetings or presentations. This can improve learning effectiveness by providing appropriate responses according to the user's current learning progress. Some or all of the above-described processing in the response unit can be performed using, for example, AI, or without AI. For example, the response unit can input the user's learning progress data into a generation AI and cause the generation AI to automatically generate appropriate responses.

[0075] The response unit can estimate the user's emotions and adjust the length of the response based on the estimated user's emotions. For example, if the user is in a hurry, the response unit can provide a short and to-the-point response. For example, if the user is in a hurry, the response unit can provide a concise response. Furthermore, if the user is relaxed, the response unit can provide a response including a detailed explanation. For example, if the user is relaxed, the response unit can provide a response including a detailed explanation. Furthermore, if the user is excited, the response unit can provide a response with a visually stimulating effect. For example, if the user is excited, the response unit can provide a response with a visual effect. This improves usability by providing a response length that corresponds to the user's emotions. Emotion estimation is achieved using an emotion estimation function, for example, an emotion engine or a generation AI. The generation AI can be, but is not limited to, a text generation AI (e.g., LLM) or a multimodal generation AI. Some or all of the above-described processing in the response unit can be performed using, for example, an AI, or without an AI. For example, the response unit can input the user's facial expression data into the generation AI and cause the generation AI to adjust the length of the response.

[0076] The response unit can generate a response including information related to the region, taking into account the user's geographical location information. For example, if the user is traveling, the response unit can respond with information about tourist spots in the region. For example, if the user is traveling, the response unit can provide a response including information about tourist spots at the travel destination. Furthermore, if the user is planning to move, the response unit can also provide information about the user's new residence. For example, if the user is planning to move, the response unit can provide a response about lifestyle information for the new residence. Furthermore, if the user is participating in an international event, the response unit can also provide a response about the event. For example, if the user is participating in an international conference, the response unit can provide a response including information about the conference content and participants. This can improve practicality by providing appropriate information based on the geographical location information. Some or all of the above-described processing by the response unit can be performed using AI, for example, or without AI. For example, the response unit can input the user's geographical location data into the generation AI and cause the generation AI to generate a response including information related to the region.

[0077] The response unit can analyze the user's social media activity and generate a response including information of interest. For example, the response unit generates a response including information about accounts frequently followed by the user. For example, if the accounts frequently followed by the user post about technology, the response unit can generate a response including information about technology. The response unit can also generate a response including information about content frequently viewed by the user. For example, if the videos frequently viewed by the user are about travel, the response unit can generate a response including information about travel. The response unit can also generate a response including information about online communities in which the user participates. For example, if the online forum in which the user participates is about cooking, the response unit can generate a response including information about cooking. This can increase the user's motivation to learn by providing information of interest based on the user's social media activity. Some or all of the above-described processing by the response unit can be performed using, for example, AI, or without AI. For example, the response unit can input the user's social media data into a generation AI and cause the generation AI to generate a response including information of interest.

[0078] The correction unit can estimate the user's emotions and adjust the timing and method of correction based on the estimated user's emotions. For example, if the user is nervous, the correction unit can make gentle and careful corrections. For example, if the user is nervous, the correction unit can make corrections in a calm tone. Furthermore, if the user is relaxed, the correction unit can make corrections including detailed explanations. For example, if the user is relaxed, the correction unit can make corrections including detailed explanations. Furthermore, if the user is excited, the correction unit can make corrections in an energetic tone. For example, if the user is excited, the correction unit can make corrections in an active tone. This can improve usability by providing corrections according to the user's emotions. Emotion estimation is realized using an emotion estimation function, for example, an emotion engine or a generation AI. The generation AI can be a text generation AI (e.g., LLM) or a multimodal generation AI, but is not limited to such examples. Some or all of the above-mentioned processing in the correction unit can be performed using, for example, AI, or without AI. For example, the correction unit can input the user's facial expression data into the generation AI and have the generation AI adjust the timing and method of correction.

[0079] The correction unit can analyze the user's past pronunciation and grammar errors and select the optimal correction method. For example, the correction unit can focus on correcting pronunciations that the user frequently made incorrectly in the past. For example, the correction unit can have the user re-practice pronunciations that the user frequently made incorrectly in the past. The correction unit can also re-explain and correct grammar that the user made incorrectly in the past. For example, the correction unit can re-explain grammar rules that the user made incorrectly in the past and have the user practice them. Furthermore, the correction unit can refer to correction methods that the user used successfully in the past. For example, the correction unit can suggest a new correction method based on correction methods that the user used successfully in the past. This enables efficient learning by providing the optimal correction method based on past errors. Some or all of the above-described processing in the correction unit can be performed using, for example, AI, or without AI. For example, the correction unit can input the user's past learning data into the generation AI and cause the generation AI to select the optimal correction method.

[0080] The correction unit can automatically generate appropriate correction content based on the user's current learning progress. For example, if the user is at a beginner's level, the correction unit can correct basic pronunciation and grammar. For example, if the user is at a beginner's level, the correction unit can correct basic pronunciation and grammar. Furthermore, if the user is at an intermediate level, the correction unit can also correct pronunciation and grammar in everyday conversation. For example, if the user is at an intermediate level, the correction unit can correct pronunciation and grammar in everyday conversation. Furthermore, if the user is at an advanced level, the correction unit can also correct pronunciation and grammar in specialized topics. For example, if the user is at an advanced level, the correction unit can correct pronunciation and grammar in specialized topics. This can improve learning effectiveness by providing appropriate correction content according to the user's current learning progress. Some or all of the above-described processing by the correction unit may be performed using, or without, AI. For example, the correction unit can input the user's learning progress data into a generation AI and cause the generation AI to automatically generate appropriate correction content.

[0081] The correction unit can estimate the user's emotions and determine the priority of corrections based on the estimated user's emotions. For example, if the user is nervous, the correction unit can start with simple corrections. For example, if the user is nervous, the correction unit can start with simple pronunciation or grammar corrections. Furthermore, if the user is relaxed, the correction unit can make detailed corrections. For example, if the user is relaxed, the correction unit can make detailed pronunciation or grammar corrections. Furthermore, if the user is excited, the correction unit can make corrections in an energetic tone. For example, if the user is excited, the correction unit can make corrections in an active tone. This improves usability by providing correction priorities according to the user's emotions. Emotion estimation is realized using an emotion estimation function, for example, an emotion engine or a generation AI. The generation AI can be a text generation AI (e.g., LLM) or a multimodal generation AI, but is not limited to such examples. Some or all of the above-mentioned processing in the correction unit may be performed using, for example, an AI, or may be performed without using an AI. For example, the correction unit can input the user's facial expression data into the generation AI and have the generation AI determine the priority of corrections.

[0082] The correction unit can prioritize correction of pronunciation and grammar related to a region, taking into account the user's geographical location information. For example, if the user is traveling, the correction unit can prioritize correction of pronunciation and grammar commonly used in that region. For example, if the user is traveling, the correction unit can prioritize correction of pronunciation and grammar commonly used in the country to which the user is traveling. Furthermore, if the user is planning to move, the correction unit can prioritize correction of pronunciation and grammar required in the new place of residence. For example, if the user is planning to move, the correction unit can prioritize correction of pronunciation and grammar based on the language characteristics of the new place of residence. Furthermore, if the user is attending an international event, the correction unit can prioritize correction of pronunciation and grammar required for the event. For example, if the user is attending an international conference, the correction unit can prioritize correction of pronunciation and grammar of the language used in the conference. This can improve practicality by providing appropriate corrections based on geographical location information. Some or all of the above-mentioned processing by the correction unit can be performed, for example, using AI or without AI. For example, the correction unit can input the user's geographic location data into the generation AI and cause the generation AI to perform region-related pronunciation and grammar corrections.

[0083] The correction unit can analyze the user's social media activity and make corrections related to topics of interest. For example, the correction unit corrects pronunciation and grammar related to topics of accounts frequently followed by the user. For example, if an account frequently followed by the user posts about technology, the correction unit can correct pronunciation and grammar related to technology. The correction unit can also correct pronunciation and grammar related to topics of content frequently viewed by the user. For example, if the videos frequently viewed by the user are about travel, the correction unit can correct pronunciation and grammar related to travel. The correction unit can also correct pronunciation and grammar related to topics of online communities in which the user participates. For example, if the online forum in which the user participates is about cooking, the correction unit can correct pronunciation and grammar related to cooking. This can increase motivation to learn by providing corrections related to topics of interest based on social media activity. Some or all of the above-mentioned processing by the correction unit can be performed using, for example, AI, or without AI. For example, the correction unit can input the user's social media data into the generation AI and cause the generation AI to perform corrections related to topics of interest.

[0084] The scenario providing unit can estimate the user's emotions and adjust the content and difficulty of the scenario based on the estimated user's emotions. For example, when the user is relaxed, the scenario providing unit can provide a more difficult scenario. For example, when the user is relaxed, the scenario providing unit can provide a scenario including business conversations or specialized topics. Furthermore, when the user is nervous, the scenario providing unit can provide a simple scenario. For example, when the user is nervous, the scenario providing unit can provide a scenario including basic greetings and everyday conversations. Furthermore, when the user is excited, the scenario providing unit can provide an energetic scenario. For example, when the user is excited, the scenario providing unit can provide a scenario including lively conversations and discussions. This can improve learning effectiveness by providing a scenario that corresponds to the user's emotions. Emotion estimation is realized using an emotion estimation function, for example, an emotion engine or a generation AI. The generation AI can be, 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 scenario providing unit can be performed using, for example, an AI, or without an AI. For example, the scenario providing unit can input the user's facial expression data into the generation AI and have the generation AI adjust the content and difficulty of the scenario.

[0085] The scenario providing unit can analyze the user's past conversation history and select an optimal scenario. The scenario providing unit, for example, can provide a scenario that the user previously preferred. For example, the scenario providing unit can provide a travel scenario that the user previously preferred. The scenario providing unit can also avoid scenarios that the user previously avoided. For example, the scenario providing unit can avoid business conversation scenarios that the user previously avoided. Furthermore, the scenario providing unit can refer to scenarios that the user previously used successfully. For example, the scenario providing unit can provide a new scenario based on an everyday conversation scenario that the user previously used successfully. This enables efficient learning by providing an optimal scenario based on the user's past conversation history. Some or all of the above-described processing in the scenario providing unit may be performed using, for example, AI, or may be performed without AI. For example, the scenario providing unit can input the user's past conversation data into a generation AI and cause the generation AI to select an optimal scenario.

[0086] The scenario providing unit can automatically generate an appropriate scenario based on the user's current learning progress. For example, if the user is at a beginner's level, the scenario providing unit generates a simple scenario. For example, if the user is at a beginner's level, the scenario providing unit can generate a scenario of basic greetings and self-introductions. Furthermore, if the user is at an intermediate level, the scenario providing unit can generate a scenario including everyday conversations. For example, if the user is at an intermediate level, the scenario providing unit can generate a conversation scenario for shopping or a restaurant. Furthermore, if the user is at an advanced level, the scenario providing unit can generate a scenario including specialized topics. For example, if the user is at an advanced level, the scenario providing unit can generate a scenario for a business meeting or presentation. This can improve learning effectiveness by providing an appropriate scenario according to the user's current learning progress. Some or all of the above-described processing in the scenario providing unit can be performed using, for example, AI, or without AI. For example, the scenario providing unit can input the user's learning progress data into a generation AI and cause the generation AI to automatically generate an appropriate scenario.

[0087] The scenario providing unit can estimate the user's emotions and adjust the display method of the scenario based on the estimated user's emotions. For example, when the user is nervous, the scenario providing unit can provide a simple, highly visible display method. For example, when the user is nervous, the scenario providing unit can provide a display method with a simple design. Furthermore, when the user is relaxed, the scenario providing unit can provide a display method including detailed information. For example, when the user is relaxed, the scenario providing unit can provide a display method including detailed explanations and guides. Furthermore, when the user is excited, the scenario providing unit can provide a visually stimulating display method. For example, when the user is excited, the scenario providing unit can provide a colorful and dynamic display method. This can improve usability by providing a display method that corresponds to the user's emotions. Emotion estimation is realized using an emotion estimation function, for example, using an emotion engine or 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 scenario providing unit can be performed using, for example, AI, or without AI. For example, the scenario providing unit can input the user's facial expression data into the generation AI and have the generation AI adjust the way the scenario is displayed.

[0088] The scenario providing unit can provide a scenario related to a region by taking into account the user's geographical location information. For example, if the user is traveling, the scenario providing unit can provide a scenario about tourist spots in the region. For example, if the user is traveling, the scenario providing unit can provide a scenario about tourist spots at the travel destination. Furthermore, if the user is planning to move, the scenario providing unit can provide a scenario about information about the user's new residence. For example, if the user is planning to move, the scenario providing unit can provide a scenario about lifestyle information in the new residence. Furthermore, if the user is participating in an international event, the scenario providing unit can provide a scenario about the event. For example, if the user is participating in an international conference, the scenario providing unit can provide a scenario about the content and participants of the conference. This can improve practicality by providing an appropriate scenario based on the geographical location information. Some or all of the above-described processing by the scenario providing unit can be performed using AI, for example, or without AI. For example, the scenario providing unit can input the user's geographical location data into the generation AI and cause the generation AI to provide a scenario related to the region.

[0089] The scenario providing unit can analyze the user's social media activity and provide scenarios related to topics of interest. For example, the scenario providing unit can provide scenarios related to topics of accounts frequently followed by the user. For example, if the accounts frequently followed by the user post about technology, the scenario providing unit can provide technology-related scenarios. The scenario providing unit can also provide scenarios related to topics of content frequently viewed by the user. For example, if the videos frequently viewed by the user are about travel, the scenario providing unit can provide travel-related scenarios. Furthermore, the scenario providing unit can also provide scenarios related to topics of online communities in which the user participates. For example, if the online forum in which the user participates is about cooking, the scenario providing unit can provide cooking-related scenarios. This can increase motivation to learn by providing scenarios related to topics of interest based on social media activity. Some or all of the above-described processing by the scenario providing unit can be performed using, for example, AI, or without AI. For example, the scenario providing unit can input the user's social media data into the generation AI and cause the generation AI to provide scenarios related to topics of interest. === Hard Collateral 1-1 === Each of the multiple elements, including the selection unit, initiation unit, response unit, correction unit, and scenario providing unit, described above, is realized, for example, by at least one of the smart device 14 and the data processing device 12. For example, the selection unit is realized by the control unit 46A of the smart device 14 and allows the user to select a language in which the user wishes to converse. The initiation unit is realized by the specific processing unit 290 of the data processing device 12 and starts a conversation in the selected language. The response unit is realized by the control unit 46A of the smart device 14 and understands what the user is saying and returns an appropriate response. The correction unit is realized by the specific processing unit 290 of the data processing device 12 and points out the user's pronunciation and grammar errors and makes appropriate corrections. The scenario providing unit is realized by the control unit 46A of the smart device 14 and allows the user to practice conversation on a specific topic. === Hard Collateral 1-2 === Each of the multiple elements, including the selection unit, initiation unit, response unit, correction unit, and scenario providing unit, described above, is implemented, for example, by at least one of the smart glasses 214 and the data processing device 12. For example, the selection unit is implemented by the control unit 46A of the smart glasses 214 and selects the language in which the user wishes to converse. The initiation unit is implemented, for example, by the specific processing unit 290 of the data processing device 12 and starts a conversation in the selected language. The response unit is implemented, for example, by the control unit 46A of the smart glasses 214 and understands what the user is saying and returns an appropriate response. The correction unit is implemented, for example, by the specific processing unit 290 of the data processing device 12 and points out the user's pronunciation or grammatical errors and makes appropriate corrections. The scenario providing unit is implemented, for example, by the control unit 46A of the smart glasses 214 and practices conversation on a specific topic. === Hard Collateral 1-3 === Each of the multiple elements, including the selection unit, initiation unit, response unit, correction unit, and scenario providing unit, described above, is realized, for example, by at least one of the headset-type terminal 314 and the data processing device 12. For example, the selection unit is realized by the control unit 46A of the headset-type terminal 314 and selects the language in which the user wishes to converse. The initiation unit is realized by the specific processing unit 290 of the data processing device 12 and starts a conversation in the selected language. The response unit is realized by the control unit 46A of the headset-type terminal 314 and understands what the user is saying and returns an appropriate response. The correction unit is realized by the specific processing unit 290 of the data processing device 12 and points out the user's pronunciation and grammatical errors and makes appropriate corrections. The scenario providing unit is realized by the control unit 46A of the headset-type terminal 314 and practices conversation on a specific topic. === Hard Collateral 1-4 === Each of the multiple elements, including the selection unit, initiation unit, response unit, correction unit, and scenario providing unit, described above, is realized, for example, by at least one of the robot 414 and the data processing device 12. For example, the selection unit is realized by the control unit 46A of the robot 414 and allows the user to select a language in which the user wishes to converse. The initiation unit is realized by the specific processing unit 290 of the data processing device 12 and starts a conversation in the selected language. The response unit is realized by the control unit 46A of the robot 414 and understands what the user is saying and returns an appropriate response. The correction unit is realized by the specific processing unit 290 of the data processing device 12 and points out the user's pronunciation and grammar errors and makes appropriate corrections. The scenario providing unit is realized by the control unit 46A of the robot 414 and allows the user to practice conversation on a specific topic.

[0090] The system according to the embodiment is not limited to the above-described example, and various modifications are possible, for example, as follows.

[0091] The selection unit can monitor the user's health condition and suggest appropriate timing for language learning. For example, if the user is tired, the selection unit can suggest a simple lesson that can be completed in a short time. Also, if the user is healthy and energetic, the selection unit can suggest a long, intensive study. Furthermore, if the user is sick or feeling unwell, the selection unit can suggest a lesson with relaxing content. This can improve the learning effect by providing the optimal learning timing according to the user's health condition.

[0092] The selection unit can estimate the user's emotions and evaluate the progress of learning based on the estimated user emotions. For example, if the user is relaxed, the selection unit can determine that the user's progress in learning is good and suggest moving on to the next step. In addition, if the user is feeling stressed, the selection unit can determine that the user's progress in learning is slow and suggest reviewing the lesson. Furthermore, if the user is excited, the selection unit can determine that the user's progress in learning is fast and suggest a more difficult task. In this way, efficient learning can be supported by evaluating the user's progress in learning according to their emotions.

[0093] The initiation unit can analyze the user's past study patterns and propose an optimal study schedule. For example, the initiation unit can analyze the time periods in which the user studied in the past and propose to start studying during those time periods. The initiation unit can also analyze how often the user studied in the past and propose a study schedule based on that frequency. Furthermore, the initiation unit can analyze the content the user studied in the past and propose a study schedule based on that content. This makes it possible to support efficient study by providing an optimal study schedule based on the user's past study patterns.

[0094] The initiation unit can estimate the user's emotions and provide feedback to increase the user's motivation to learn based on the estimated user's emotions. For example, if the user is relaxed, the initiation unit can provide positive feedback to increase the user's motivation to learn. Also, if the user is feeling stressed, the initiation unit can provide encouraging feedback to maintain the user's motivation to learn. Furthermore, if the user is excited, the initiation unit can provide challenging feedback to further increase the user's motivation to learn. In this way, by providing feedback according to the user's emotions, the user's motivation to learn can be increased.

[0095] The response unit can analyze the user's learning style and select the optimal response method. For example, if the user is a visual learner, the response unit can provide a response that includes visual information. If the user is an auditory learner, the response unit can also provide a response that emphasizes audio. Furthermore, if the user is an experiential learner, the response unit can also provide a response that includes practical examples. This makes it possible to improve learning effectiveness by providing the optimal response method according to the user's learning style.

[0096] The response unit can estimate the user's emotions and adjust the content of the response based on the estimated user's emotions. For example, the response unit can provide a response with detailed explanations when the user is relaxed. The response unit can also provide a concise and to-the-point response when the user is stressed. Furthermore, the response unit can provide a response with an energetic tone when the user is excited. This can improve usability by providing a response according to the user's emotions.

[0097] The correction unit can analyze the user's learning history and select the optimal correction method. For example, the correction unit can analyze what the user has learned in the past and make corrections based on that content. The correction unit can also analyze where the user made mistakes in the past and focus on those parts when making corrections. Furthermore, the correction unit can refer to correction methods that the user has used successfully in the past and make corrections using those methods. This makes it possible to support efficient learning by providing the optimal correction method based on the user's past learning history.

[0098] The correction unit can estimate the user's emotions and adjust the correction feedback based on the estimated user's emotions. For example, the correction unit can provide detailed feedback when the user is relaxed. Alternatively, the correction unit can provide concise and to-the-point feedback when the user is stressed. Furthermore, the correction unit can provide feedback in an energetic tone when the user is excited. This can improve learning effectiveness by providing feedback according to the user's emotions.

[0099] The scenario providing unit can set a learning goal for the user and provide a scenario based on that goal. For example, if the user wants to learn business English, the scenario providing unit can provide a business-related scenario. Also, if the user wants to learn travel English, the scenario providing unit can provide a travel-related scenario. Furthermore, if the user wants to learn everyday conversation, the scenario providing unit can provide a everyday conversation-related scenario. This can improve the learning effect by providing an optimal scenario according to the user's learning goal.

[0100] The scenario providing unit can estimate the user's emotions and adjust the speed at which the scenario progresses based on the estimated user's emotions. For example, if the user is relaxed, the scenario providing unit can advance the scenario at a normal speed. Also, if the user is feeling stressed, the scenario providing unit can advance the scenario at a slower speed. Furthermore, if the user is excited, the scenario providing unit can advance the scenario at a faster speed. In this way, by providing a scenario progress speed that corresponds to the user's emotions, the learning effect can be improved.

[0101] The processing flow of the second embodiment will be briefly explained below.

[0102] Step 1: The selection unit selects the language in which the user wishes to converse. For example, the user can select from languages ​​such as English, Japanese, and Spanish. The user can also select the language using voice input or text input. Step 2: The initiation unit initiates the conversation in the language selected by the selection unit. For example, if the user selects English, the conversation is initiated in English. The initiation unit can also adjust the timing of the conversation start based on the language selected by the user. Step 3: The response unit understands what the user is saying to the generated AI and returns an appropriate response. For example, it can use voice recognition technology or natural language processing technology to understand what the user is saying and return an appropriate response using voice or text. Step 4: The correction unit points out the user's pronunciation and grammar errors based on the response from the response unit and makes appropriate corrections. For example, if the user says, "I went to the store," the correction unit will point out, "'goed' is incorrect. The correct form is 'went'." Corrections can also be made using voice feedback or text feedback. Step 5: The scenario providing unit practices a conversation on a specific topic based on the content corrected by the correcting unit. For example, if the user wants to practice business conversation, the scenario providing unit provides a business-related topic and conducts a conversation based on that topic.

[0103] 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.

[0104] 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.

[0105] 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.

[0106] The correspondence between each part and the device or control part is not limited to the example described above, and various modifications are possible.

[0107] [Second embodiment] FIG. 3 shows an example of the configuration of a data processing system 210 according to the second embodiment.

[0108] 3, the data processing system 210 includes a data processing device 12 and smart glasses 214. An example of the data processing device 12 is a server.

[0109] 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.

[0110] 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.

[0111] 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.

[0112] 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).

[0113] 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.

[0114] 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.

[0115] 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.

[0116] 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.

[0117] 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.

[0118] 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.

[0119] 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.

[0120] 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.

[0121] 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.

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

[0123] [Third embodiment] FIG. 5 shows an example of the configuration of a data processing system 310 according to the third embodiment.

[0124] 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.

[0125] The data processing device 12 includes a computer 22, a database 24, and a communication I / F 26. The computer 22 includes a processor 28, a RAM 30, and a storage 32. The processor 28, RAM 30, and storage 32 are connected to a bus 34. The database 24 and the communication I / F 26 are also connected to the bus 34. The communication I / F 26 is connected to a network 54. Examples of the network 54 include a WAN and / or a LAN.

[0126] The 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.

[0127] The microphone 238 receives instructions and the like from the user by receiving voice uttered by the user. The microphone 238 captures the voice uttered by the user, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio according to instructions from the processor 46.

[0128] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an imaging element such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, and captures images of the user's surroundings (for example, an imaging range defined by an angle of view equivalent to the field of vision of a typical healthy person).

[0129] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 are responsible for the exchange of various information between the processor 46 and the processor 28 via the network 54. The exchange of various information between the processor 46 and the processor 28 using the communication I / Fs 44 and 26 is carried out in a secure state.

[0130] Fig. 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.

[0131] The processor 28 reads the specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific processing is realized by the processor 28 operating as a specific processing unit 290 in accordance with the specific processing program 56 executed on the RAM 30.

[0132] The storage 32 stores a data generation model 58 and an emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290. The identification processing unit 290 can estimate a user's emotion using the emotion identification model 59 and perform identification processing using the user's emotion. The emotion estimation function (emotion identification function) using the emotion identification model 59 performs various estimations and predictions regarding the user's emotion, including estimation and prediction of the user's emotion, but is not limited to these examples. Furthermore, the estimation and prediction of emotion also includes, for example, emotion analysis.

[0133] In the 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.

[0134] Note that a device other than the data processing device 12 may have the data generation model 58. For example, a server device may have the data generation model 58. In this case, the data processing device 12 communicates with the server device having the data generation model 58 to obtain a processing result (such as a prediction result) using the data generation model 58. Furthermore, the data processing device 12 may be a server device, or may be a terminal device (for example, a mobile phone, a robot, a home appliance, etc.) owned by a user.

[0135] The specific processing unit 290 transmits the result of the specific processing to the 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.

[0136] The data generation model 58 is a so-called generative AI. An example of the data generation model 58 is a generative AI such as ChatGPT. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 receives a prompt 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.

[0137] 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.

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

[0139] [Fourth embodiment] FIG. 7 shows an example of the configuration of a data processing system 410 according to the fourth embodiment.

[0140] 7, a data processing system 410 includes a data processing device 12 and a robot 414. An example of the data processing device 12 is a server.

[0141] The data processing device 12 includes a computer 22, a database 24, and a communication I / F 26. The computer 22 includes a processor 28, a RAM 30, and a storage 32. The processor 28, RAM 30, and storage 32 are connected to a bus 34. The database 24 and the communication I / F 26 are also connected to the bus 34. The communication I / F 26 is connected to a network 54. Examples of the network 54 include a WAN and / or a LAN.

[0142] The 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.

[0143] The microphone 238 receives instructions and the like from the user by receiving voice uttered by the user. The microphone 238 captures the voice uttered by the user, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio according to instructions from the processor 46.

[0144] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an imaging element such as a CMOS 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).

[0145] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 are responsible for the exchange of various information between the processor 46 and the processor 28 via the network 54. The exchange of various information between the processor 46 and the processor 28 using the communication I / Fs 44 and 26 is carried out in a secure state.

[0146] 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.

[0147] 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.

[0148] 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.

[0149] 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.

[0150] 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.

[0151] 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.

[0152] 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.

[0153] 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.

[0154] 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.

[0155] The correspondence between each part and the device or control part is not limited to the example described above, and various modifications are possible.

[0156] 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.

[0157] 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.

[0158] 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.

[0159] 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).

[0160] 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.

[0161] 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."

[0162] 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.

[0163] 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.

[0164] 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.

[0165] 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.

[0166] 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.

[0167] 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.

[0168] 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.

[0169] 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.

[0170] 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.

[0171] 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.

[0172] 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.

[0173] 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.

[0174] [Explanation of symbols]

[0175] 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 selection section for selecting a language in which the user wishes to converse; an initiation unit that initiates a conversation in the language selected by the selection unit; A response unit that understands what the user says to the generated AI and returns a response; a correction unit that points out and corrects the user's pronunciation and grammar errors based on the response content from the response unit; a scenario providing unit that practices a conversation on a specific topic based on the content corrected by the correcting unit. A system characterized by:

2. The selection unit Estimate user emotions and suggest words based on the estimated user emotions 2. The system of claim 1.

3. The selection unit Analyze the user's past language learning history and automatically select a language 2. The system of claim 1.

4. The selection unit Suggest language difficulty levels based on the user's current learning progress 2. The system of claim 1.

5. The selection unit Estimate user emotions and customize the interface based on the estimated user emotions 2. The system of claim 1.

6. The selection unit Prioritize localized language suggestions based on the user's geographic location 2. The system of claim 1.

7. The selection unit Analyze your social media activity to suggest languages ​​that interest you 2. The system of claim 1.

8. The start portion Estimates the user's emotions and adjusts the timing of conversation start based on the estimated user emotions.

2. The system of claim 1.

Images