system

Abstract

The system according to the embodiment aims to make it easier for English learners to understand the content of learning materials and improve learning efficiency. [Solution] The system according to the embodiment includes a reading unit, an interlocutor unit, a paraphrase unit, and an adjustment unit. The reading unit reads English learning materials. The interlocutor unit speaks to the learner based on the content of the materials read by the reading unit. The paraphrase unit rephrases the content spoken to by the interlocutor unit in Japanese according to the learner's level. The adjustment unit grasps the learner's progress based on the content paraphrased by the paraphrase unit and adjusts the content of the materials.

Description

[Technical Field]

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

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

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

[0004] Conventional technology has the problem that it does not provide sufficient support to help English learners understand the content of the learning materials, resulting in low learning efficiency.

[0005] The system according to the embodiment aims to make it easier for English learners to understand the content of learning materials and improve learning efficiency. [Means for solving the problem]

[0006] The system according to the embodiment includes a reading unit, an interlocutor unit, a paraphrase unit, and an adjustment unit. The reading unit reads English learning materials. The interlocutor unit speaks to the learner based on the content of the materials read by the reading unit. The paraphrase unit rephrases the content spoken to by the interlocutor unit in Japanese according to the learner's level. The adjustment unit grasps the learner's progress based on the content paraphrased by the paraphrase unit and adjusts the content of the materials. [Effects of the Invention]

[0007] The system according to the embodiment can make it easier for English learners to understand the content of the learning material and improve their learning efficiency. [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 efficiently acquire English by speaking to a language learner. The language learning system has the generative AI read English learning materials, understand the content of the materials, and speak to the learner at the appropriate time. Furthermore, the generative AI paraphrases the material in Japanese according to the learner's level and adjusts the content of the materials according to the learner's progress. For example, if a learner says "Hello," the language learning system replies with "Hello, how are you?" This allows the learner to learn English in a natural conversational flow. Next, the generative AI paraphrases the material in Japanese according to the learner's level. For example, if a learner does not understand the question "What is your name?", the generative AI explains in Japanese with "What is your name?" This allows the learner to understand English without stress. Furthermore, the generative AI adjusts the content of the materials according to the learner's progress. For example, once a learner has mastered basic greetings, the generative AI teaches everyday conversational phrases as the next step. In this way, the learner can learn English at their own pace. This allows the language learning system to efficiently acquire English by using generative AI to speak to language learners. For example, learners can learn English through natural conversation by being spoken to by the generative AI. Also, learners can understand English without stress because the generative AI paraphrases what is said in Japanese. Furthermore, the generative AI adjusts the content of the learning materials according to the learner's progress, allowing them to acquire English efficiently.

[0029] A language learning system according to an embodiment includes a reading unit, an interlocutor unit, a paraphrasing unit, and an adjustment unit. The reading unit reads English language learning materials using a generation AI. For example, the reading unit can read English language learning materials such as textbooks, audio materials, and video materials. The reading unit understands the content of the materials using the generation AI and speaks to the learner at an appropriate time. The interlocutor unit speaks to the learner using the generation AI based on the content of the materials read by the reading unit. For example, if the learner says "Hello," the interlocutor unit replies with "Hello, how are you?" The interlocutor unit can also use the generation AI to analyze the learner's utterance and generate an appropriate response based on the content. For example, the interlocutor unit analyzes the learner's utterance using speech recognition technology and generates a response using the generation AI. The paraphrasing unit uses the generation AI to rephrase the content spoken by the interlocutor into Japanese according to the learner's level. For example, if the learner does not understand the question "What is your name?", the paraphrasing unit explains in Japanese as "Anata no na me wa? (What is your name?)." The paraphrasing unit can also use the generation AI to provide detailed explanations in Japanese for content that the learner does not understand. For example, the paraphrasing unit uses the generation AI to provide explanations and illustrations using examples in response to the learner's questions. The adjustment unit uses the generation AI to understand the learner's progress based on the content paraphrased by the paraphrasing unit and adjust the content of the teaching materials. For example, the adjustment unit evaluates the accuracy of the learner's statements and answers and provides the next step of teaching materials based on the results. The adjustment unit can also use the generation AI to adjust the content of the teaching materials according to the learner's progress. For example, if the learner has mastered basic greetings, the adjustment unit can teach everyday conversation phrases as the next step. As a result, the language learning system according to the embodiment can efficiently acquire English by utilizing the generation AI to speak to the language learner.

[0030] The interlocutor can analyze the learner's utterances and generate a response based on the content of the utterances. The interlocutor can analyze the learner's utterances using, for example, speech recognition technology. For example, the interlocutor can acquire the learner's utterances as audio data and analyze the content using a generation AI. The interlocutor can also analyze the learner's utterances using natural language processing technology. For example, the interlocutor can convert the learner's utterances into text data and analyze the content using a generation AI. The interlocutor can also generate an appropriate response based on the learner's utterances using a generation AI. For example, if the learner says "Hello," the interlocutor can respond with "Hello, how are you?" The interlocutor can also generate a template-based response based on the learner's utterances using a generation AI. For example, if the learner asks "What is your name?" the interlocutor can respond with "My name is AI." This allows for natural conversation by generating an appropriate response based on the learner's utterances.

[0031] The paraphrasing unit can provide detailed explanations in Japanese for content that the learner does not understand. For example, the paraphrasing unit uses a generation AI to identify content that the learner does not understand. For example, the paraphrasing unit analyzes the learner's questions and test results to identify content that the learner does not understand. The paraphrasing unit also uses a generation AI to provide detailed explanations in Japanese for content that the learner does not understand. For example, if the learner does not understand the question, "What is your name?", the paraphrasing unit can explain in Japanese, "What is your name?" The paraphrasing unit can also use a generation AI to provide explanations and illustrations for content that the learner does not understand using examples. For example, if the learner does not understand the question, "How do you say 'apple' in Japanese?", the paraphrasing unit can explain in Japanese, "'Apple' is said to be 'ringo' in Japanese," and display an image of an apple. This allows the learner to understand English without stress by explaining content that the learner does not understand in Japanese.

[0032] The adjustment unit can evaluate the accuracy of the learner's statements and answers, and select and provide learning materials for the next step based on the results. The adjustment unit, for example, uses a generation AI to evaluate the accuracy of the learner's statements and answers. For example, the adjustment unit analyzes the learner's statements and evaluates the rate of correct answers and the types of incorrect answers. The adjustment unit also uses a generation AI to select and provide learning materials for the next step according to the learner's progress. For example, if the learner has mastered basic greetings, the adjustment unit may teach everyday conversation phrases as the next step. The adjustment unit can also use a generation AI to adjust the difficulty level of the learning materials according to the learner's progress. For example, if the learner understands basic grammar, the adjustment unit may teach advanced grammar as the next step. In this way, the content of the learning materials can be adjusted according to the learner's progress, allowing for efficient English acquisition.

[0033] The adjustment unit can adjust the content of the learning materials based on the learner's progress. The adjustment unit, for example, uses a generation AI to grasp the learner's progress. For example, the adjustment unit analyzes the learner's study time and test results to grasp the learner's progress. The adjustment unit also uses a generation AI to adjust the content of the learning materials based on the learner's progress. For example, if the learner has mastered basic greetings, the adjustment unit may teach everyday conversation phrases as the next step. The adjustment unit can also use a generation AI to adjust the difficulty level of the learning materials according to the learner's progress. For example, if the learner understands basic grammar, the adjustment unit may teach advanced grammar as the next step. In this way, adjusting the content of the learning materials according to the learner's progress allows the learner to acquire English efficiently.

[0034] When reading the contents of the teaching materials, the reading unit can emphasize important parts based on the learner's past learning history. The reading unit, for example, uses a generation AI to refer to the learner's past learning history. For example, the reading unit analyzes learning logs and test results to understand the learner's past learning history. The reading unit also uses a generation AI to emphasize important parts based on the learner's past learning history. For example, the reading unit reads by emphasizing parts that the learner previously struggled with. The reading unit can also read parts on which the learner previously scored high at a normal speed. Furthermore, the reading unit can read in detail parts on which the learner previously asked questions. In this way, the learning effect can be improved by emphasizing important parts by referring to the learner's past learning history.

[0035] When reading teaching materials, the reading unit can provide relevant information based on the learner's areas of interest. The reading unit, for example, uses a generation AI to identify the learner's areas of interest. For example, the reading unit analyzes survey results and past learning content to understand the learner's areas of interest. The reading unit also uses a generation AI to provide relevant information based on the learner's areas of interest. For example, the reading unit provides information related to topics that the learner is interested in. The reading unit can also provide additional information based on keywords that the learner has previously searched for. Furthermore, the reading unit can provide the latest research results related to the areas in which the learner has expressed interest. This makes it possible to pique the learner's interest by providing relevant additional information based on the learner's areas of interest.

[0036] When reading teaching materials, the reading unit can adjust the reading depth based on the learner's level of understanding. The reading unit, for example, uses a generation AI to evaluate the learner's level of understanding. For example, the reading unit analyzes test results and the rate of correct answers to questions to grasp the learner's level of understanding. The reading unit also uses a generation AI to adjust the reading depth based on the learner's level of understanding. For example, the reading unit reads in detail the parts that the learner does not understand. The reading unit can also simply read the parts that the learner does understand. Furthermore, the reading unit can supplementarily read the parts that the learner only partially understands. In this way, the learning effect can be improved by adjusting the reading depth according to the learner's level of understanding.

[0037] When reading teaching materials, the reading unit can add region-specific examples based on the learner's geographical background. The reading unit, for example, uses a generation AI to identify the learner's geographical background. For example, the reading unit analyzes residential information and cultural background to understand the learner's geographical background. The reading unit also uses a generation AI to add region-specific examples based on the learner's geographical background. For example, if the learner lives in Japan, the reading unit can add examples from Japan. If the learner lives in the United States, the reading unit can also add examples from the United States. Furthermore, if the learner lives in Europe, the reading unit can add examples from Europe. This allows the learner's understanding to be deepened by adding region-specific examples taking into account the learner's geographical background.

[0038] When reading teaching materials, the reading unit can analyze the learner's social media activity and incorporate related topics. The reading unit, for example, uses a generation AI to analyze the learner's social media activity. For example, the reading unit analyzes the content of the learner's posts and the number of likes to understand the learner's interests. The reading unit also uses a generation AI to incorporate related topics based on the learner's social media activity. For example, the reading unit incorporates topics in which the learner has shown interest on social media. The reading unit can also incorporate content from accounts the learner follows on social media. Furthermore, the reading unit can incorporate content from articles the learner has shared on social media. In this way, the learner's interest can be piqued by analyzing the learner's social media activity and incorporating related topics.

[0039] When reading teaching materials, the reading unit can customize the reading method by reflecting the learner's past feedback. The reading unit, for example, uses a generation AI to refer to the learner's past feedback. For example, the reading unit analyzes survey results and comments to understand the learner's past feedback. The reading unit also uses a generation AI to customize the reading method based on the learner's past feedback. For example, the reading unit adjusts the reading method based on feedback previously submitted by the learner. The reading unit can also adjust the reading method based on the learner's past evaluations. Furthermore, the reading unit can also adjust the reading method based on the learner's past comments. In this way, the learning effect can be improved by customizing the reading method by reflecting the learner's past feedback.

[0040] When speaking to a learner, the conversation unit can generate follow-up questions based on the learner's speech history. The conversation unit, for example, uses a generation AI to refer to the learner's speech history. For example, the conversation unit analyzes past conversation logs and the content of questions to understand the learner's speech history. The conversation unit also uses a generation AI to generate follow-up questions based on the learner's speech history. For example, the conversation unit generates follow-up questions based on questions the learner has asked in the past. The conversation unit can also generate follow-up questions based on content the learner has said in the past. Furthermore, the conversation unit can generate follow-up questions based on content in which the learner has shown interest in the past. In this way, the learner's understanding can be deepened by generating appropriate follow-up questions by referring to the learner's speech history.

[0041] When speaking to a learner, the conversation unit can select a conversation topic based on the learner's interests or concerns. The conversation unit, for example, uses a generation AI to identify the learner's interests or concerns. For example, the conversation unit analyzes survey results and past learning content to understand the learner's interests or concerns. The conversation unit also uses a generation AI to select a conversation topic based on the learner's interests or concerns. For example, the conversation unit selects a topic in which the learner is interested. The conversation unit can also select a topic based on keywords that the learner has searched for in the past. Furthermore, the conversation unit can select a topic based on a field in which the learner has shown interest. In this way, the learner's interest can be aroused by selecting a conversation topic based on the learner's interests or concerns.

[0042] When speaking to a learner, the conversation unit can adjust the difficulty of the conversation based on the learner's level of comprehension. The conversation unit, for example, uses a generation AI to evaluate the learner's level of comprehension. For example, the conversation unit analyzes test results and the rate of correct answers to questions to grasp the learner's level of comprehension. The conversation unit also uses a generation AI to adjust the difficulty of the conversation based on the learner's level of comprehension. For example, the conversation unit provides a conversation with a high level of difficulty if the learner understands. The conversation unit can also provide a conversation with a low level of difficulty if the learner does not understand. Furthermore, the conversation unit can also provide a conversation with an appropriate level of difficulty if the learner only partially understands. This makes it possible to improve learning effectiveness by adjusting the difficulty of the conversation according to the learner's level of comprehension.

[0043] When speaking to a learner, the conversation unit can provide region-specific topics based on the learner's geographical background. The conversation unit, for example, uses a generation AI to identify the learner's geographical background. For example, the conversation unit analyzes residential information and cultural background to understand the learner's geographical background. The conversation unit also uses a generation AI to provide region-specific topics based on the learner's geographical background. For example, if the learner lives in Japan, the conversation unit can provide Japanese topics. If the learner lives in the United States, the conversation unit can also provide American topics. Furthermore, if the learner lives in Europe, the conversation unit can provide European topics. This makes it possible to deepen the learner's understanding by providing region-specific topics taking into account the learner's geographical background.

[0044] When speaking to a learner, the conversation unit can analyze the learner's social media activity and provide related topics. The conversation unit, for example, uses a generative AI to analyze the learner's social media activity. For example, the conversation unit analyzes the content of the learner's posts and the number of likes to understand the learner's interests. The conversation unit also uses a generative AI to provide related topics based on the learner's social media activity. For example, the conversation unit provides topics that the learner has shown interest in on social media. The conversation unit can also provide topics of accounts that the learner follows on social media. Furthermore, the conversation unit can provide topics of articles that the learner has shared on social media. In this way, the learner's interest can be piqued by analyzing the learner's social media activity and providing related topics.

[0045] When speaking to a learner, the speaking unit can customize the speaking method based on the learner's past feedback. The speaking unit, for example, uses a generation AI to refer to the learner's past feedback. For example, the speaking unit analyzes survey results and comments to understand the learner's past feedback. The speaking unit also uses a generation AI to customize the speaking method based on the learner's past feedback. For example, the speaking unit adjusts the speaking method based on feedback previously submitted by the learner. The speaking unit can also adjust the speaking method based on the learner's past evaluations. Furthermore, the speaking unit can adjust the speaking method based on the learner's past comments. In this way, the learning effect can be improved by customizing the speaking method to reflect the learner's past feedback.

[0046] When explaining to a learner in Japanese, the paraphrasing unit can adjust the level of detail of the explanation based on the learner's level of understanding. The paraphrasing unit, for example, uses a generation AI to evaluate the learner's level of understanding. For example, the paraphrasing unit analyzes test results and the correct answer rate for questions to grasp the learner's level of understanding. The paraphrasing unit also uses a generation AI to adjust the level of detail of the explanation based on the learner's level of understanding. For example, the paraphrasing unit provides a simplified explanation if the learner understands. The paraphrasing unit can also provide a detailed explanation if the learner does not understand. Furthermore, the paraphrasing unit can provide supplementary explanation if the learner only partially understands. In this way, the learning effect can be improved by adjusting the level of detail of the explanation according to the learner's level of understanding.

[0047] When explaining to a learner in Japanese, the paraphrasing unit can provide examples based on the learner's past learning history. The paraphrasing unit, for example, uses a generation AI to refer to the learner's past learning history. For example, the paraphrasing unit analyzes learning logs and test results to understand the learner's past learning history. The paraphrasing unit also uses a generation AI to provide examples based on the learner's past learning history. For example, the paraphrasing unit provides appropriate examples based on content that the learner has learned in the past. The paraphrasing unit can also provide appropriate examples based on content that the learner has asked in the past. Furthermore, the paraphrasing unit can provide appropriate examples based on content in which the learner has shown interest in the past. In this way, the learner's understanding can be deepened by providing appropriate examples by referring to the learner's past learning history.

[0048] When explaining to a learner in Japanese, the paraphrasing unit can provide relevant information based on the learner's areas of interest. The paraphrasing unit, for example, uses a generation AI to identify the learner's areas of interest. For example, the paraphrasing unit analyzes survey results and past learning content to understand the learner's areas of interest. The paraphrasing unit also uses a generation AI to provide relevant information based on the learner's areas of interest. For example, the paraphrasing unit provides information related to areas in which the learner is interested. The paraphrasing unit can also provide relevant information based on keywords that the learner has previously searched for. Furthermore, the paraphrasing unit can provide the latest research results related to areas in which the learner has expressed interest. This makes it possible to pique the learner's interest by providing relevant information based on the learner's areas of interest.

[0049] When explaining to a learner in Japanese, the paraphrasing unit can provide region-specific examples based on the learner's geographical background. The paraphrasing unit, for example, uses a generation AI to identify the learner's geographical background. For example, the paraphrasing unit analyzes residential information and cultural background to understand the learner's geographical background. The paraphrasing unit also uses a generation AI to provide region-specific examples based on the learner's geographical background. For example, if the learner lives in Japan, the paraphrasing unit can provide examples from Japan. If the learner lives in the United States, the paraphrasing unit can also provide examples from the United States. Furthermore, if the learner lives in Europe, the paraphrasing unit can provide examples from Europe. This makes it possible to deepen the learner's understanding by providing region-specific examples taking into account the learner's geographical background.

[0050] When explaining to a learner in Japanese, the paraphrasing unit can analyze the learner's social media activity and provide relevant information. The paraphrasing unit, for example, uses a generation AI to analyze the learner's social media activity. For example, the paraphrasing unit analyzes the content of the learner's posts and the number of likes to understand the learner's interests. The paraphrasing unit also uses a generation AI to provide relevant information based on the learner's social media activity. For example, the paraphrasing unit provides relevant information based on the content in which the learner has shown interest on social media. The paraphrasing unit can also provide relevant information based on the content of accounts the learner follows on social media. Furthermore, the paraphrasing unit can provide relevant information based on the content of articles the learner has shared on social media. In this way, the learner's social media activity can be analyzed and relevant information provided to pique the learner's interest.

[0051] When explaining to a learner in Japanese, the paraphrasing unit can customize the explanation method based on the learner's past feedback. The paraphrasing unit, for example, uses a generation AI to refer to the learner's past feedback. For example, the paraphrasing unit analyzes survey results and comments to understand the learner's past feedback. The paraphrasing unit also uses a generation AI to customize the explanation method based on the learner's past feedback. For example, the paraphrasing unit adjusts the explanation method based on feedback previously submitted by the learner. The paraphrasing unit can also adjust the explanation method based on the learner's past evaluations. Furthermore, the paraphrasing unit can also adjust the explanation method based on the learner's past comments. In this way, the explanation method can be customized to reflect the learner's past feedback, thereby improving the learning effect.

[0052] When grasping the learner's progress, the adjustment unit can evaluate the progress based on the learner's speech history. The adjustment unit, for example, uses a generation AI to refer to the learner's speech history. For example, the adjustment unit analyzes past conversation logs and the content of questions to grasp the learner's speech history. The adjustment unit also uses a generation AI to evaluate the progress based on the learner's speech history. For example, the adjustment unit evaluates the progress based on the content of past speeches made by the learner. The adjustment unit can also evaluate the progress based on the content of questions asked by the learner in the past. Furthermore, the adjustment unit can evaluate the progress based on assignments submitted by the learner in the past. In this way, by evaluating the progress by referring to the learner's speech history, it is possible to improve the learning effect.

[0053] When grasping the learner's progress, the adjustment unit can select the next step learning material based on the learner's level of understanding. The adjustment unit, for example, uses a generation AI to evaluate the learner's level of understanding. For example, the adjustment unit analyzes test results and the rate of correct answers to questions to grasp the learner's level of understanding. The adjustment unit also uses a generation AI to select the next step learning material based on the learner's level of understanding. For example, the adjustment unit provides the next step learning material if the learner understands. The adjustment unit can also provide supplementary learning material if the learner does not understand. Furthermore, the adjustment unit can provide supplementary learning material if the learner only partially understands. In this way, the learning effect can be improved by selecting the next step learning material according to the learner's level of understanding.

[0054] When grasping the learner's progress, the adjustment unit can change the content of the learning materials based on the learner's areas of interest. The adjustment unit, for example, uses a generation AI to identify the learner's areas of interest. For example, the adjustment unit analyzes questionnaire results and past learning content to grasp the learner's areas of interest. The adjustment unit also uses a generation AI to change the content of the learning materials based on the learner's areas of interest. For example, the adjustment unit provides learning materials related to the learner's areas of interest. The adjustment unit can also provide learning materials based on keywords the learner has searched for in the past. Furthermore, the adjustment unit can provide the latest research results related to the areas in which the learner has expressed interest. In this way, the content of the learning materials can be customized based on the learner's areas of interest to pique the learner's interest.

[0055] The adjustment unit can evaluate a learner's progress by taking into account the learner's geographical background. The adjustment unit, for example, uses a generation AI to identify the learner's geographical background. For example, the adjustment unit analyzes residential information and cultural background to understand the learner's geographical background. The adjustment unit also uses a generation AI to evaluate based on the learner's geographical background. For example, the adjustment unit applies Japanese evaluation standards if the learner lives in Japan. The adjustment unit can also apply American evaluation standards if the learner lives in the United States. The adjustment unit can also apply European evaluation standards if the learner lives in Europe. This makes it possible to deepen the learner's understanding by evaluating the learner while taking into account their geographical background.

[0056] When grasping the learner's progress, the adjustment unit can analyze the learner's social media activity to evaluate the progress. The adjustment unit, for example, uses a generation AI to analyze the learner's social media activity. For example, the adjustment unit analyzes the content of the learner's posts and the number of likes to grasp the learner's interests. The adjustment unit also uses a generation AI to evaluate the learner's progress based on the learner's social media activity. For example, the adjustment unit evaluates the learner's progress based on the content of the learner's posts on social media. The adjustment unit can also evaluate the learner's progress based on articles the learner shared on social media. Furthermore, the adjustment unit can evaluate the learner's progress based on the content of accounts the learner follows on social media. In this way, by analyzing the learner's social media activity and evaluating the learner's progress, it is possible to draw out the learner's interest.

[0057] When grasping the learner's progress, the adjustment unit can customize the assessment method based on the learner's past feedback. The adjustment unit, for example, uses a generation AI to refer to the learner's past feedback. For example, the adjustment unit analyzes survey results and comments to grasp the learner's past feedback. The adjustment unit also uses a generation AI to customize the assessment method based on the learner's past feedback. For example, the adjustment unit adjusts the assessment method based on feedback previously submitted by the learner. The adjustment unit can also adjust the assessment method based on the learner's past assessments. Furthermore, the adjustment unit can also adjust the assessment method based on the learner's past comments. In this way, the learning effect can be improved by customizing the assessment method to reflect the learner's past feedback.

[0058] The system according to the embodiment is not limited to the above-described example, and various modifications are possible, for example, as follows.

[0059] The language learning system further includes a feedback unit. The feedback unit can provide instant feedback to the learner's utterances and answers. For example, if the learner asks, "What is your name?", the feedback unit can provide positive feedback such as, "Good question!". If the learner gives an incorrect answer, the feedback unit can also provide encouraging feedback such as, "Almost there, try again!". Furthermore, the feedback unit can adjust the content of the feedback according to the learner's progress. For example, if the learner has mastered basic grammar, the feedback unit can provide more advanced feedback. This allows the learner to receive instant feedback and improve their learning effectiveness.

[0060] The language learning system further includes a customization unit. The customization unit can customize the learning plan based on the learner's individual needs and goals. For example, if a learner wants to learn business English, the customization unit can provide business-related learning materials. If a learner wants to learn travel English, the customization unit can also provide travel-related learning materials. The customization unit can also adjust the learning plan according to the learner's progress. For example, if a learner has weaknesses in a particular area, the customization unit can provide a plan that focuses on that area. This allows the learner to study effectively according to their own goals.

[0061] The language learning system further includes a motivation unit. The motivation unit can provide a function to maintain the learner's motivation. For example, the motivation unit can award badges or points when a learner achieves a certain goal. The motivation unit can also provide a ranking function that allows a learner to compete with other learners. Furthermore, the motivation unit can send encouraging messages according to the learner's progress. For example, if a learner continues to study continuously, the motivation unit can send a message such as "Great job! Keep it up!". This allows the learner to continue studying while maintaining their motivation.

[0062] The language learning system further includes a reminder unit. The reminder unit can send regular reminders to encourage the learner to study. For example, the reminder unit can send a reminder if the learner has not studied for a certain period of time. The reminder unit can also suggest the optimal study time based on the learner's schedule. Furthermore, the reminder unit can adjust the content of the reminder according to the learner's progress. For example, if the learner is approaching a specific goal, the reminder unit can send a reminder such as "You are almost there! Keep going!". This helps the learner develop the habit of studying regularly.

[0063] The language learning system further includes an interactive section. The interactive section may provide interactive features that allow a learner to progress through their learning at their own pace. For example, the interactive section may provide a dashboard that allows a learner to check their progress. The interactive section may also provide a feature that allows a learner to customize their learning content. The interactive section may also provide a forum for a learner to communicate with other learners. This allows a learner to share information with other learners while progressing through their learning at their own pace.

[0064] The language learning system further includes a progress tracking unit. The progress tracking unit can track the learner's learning progress in detail and adjust the learning plan based on the results. For example, the progress tracking unit records how often the learner studies. The progress tracking unit can also evaluate how well the learner has understood each learning material. The progress tracking unit can also adjust the learning plan according to the learner's progress. For example, if the learner is lagging behind in a particular area, the progress tracking unit can provide a plan to focus on that area. This allows the learner to study effectively while keeping track of their own progress.

[0065] The processing flow of the first embodiment will be briefly explained below.

[0066] Step 1: The reading unit uses the generation AI to read the English learning materials. For example, the reading unit can read English learning materials such as textbooks, audio materials, and video materials. The reading unit uses the generation AI to understand the content of the materials and speaks to the learner at the appropriate time. Step 2: The interlocutor uses a generation AI to speak to the learner based on the content of the learning material read by the reader. For example, if the learner says "Hello," the interlocutor replies, "Hello, how are you?" The interlocutor can also use a generation AI to analyze the learner's utterances and generate an appropriate response based on the content. For example, the interlocutor uses voice recognition technology to analyze the learner's utterances and uses a generation AI to generate a response. Step 3: The paraphrasing unit uses the generation AI to rephrase what has been spoken by the speaking unit into Japanese according to the learner's level. For example, if the learner does not understand the question "What is your name?", the paraphrasing unit will explain it in Japanese as "What is your name?". The paraphrasing unit can also use the generation AI to provide detailed explanations in Japanese for content that the learner does not understand. For example, the paraphrasing unit uses the generation AI to provide explanations using examples and illustrations in response to the learner's questions. Step 4: The adjustment unit uses the generation AI to understand the learner's progress based on the content paraphrased by the paraphrasing unit and adjusts the content of the learning materials. For example, the adjustment unit evaluates the accuracy of the learner's statements and answers and provides the next step of learning materials based on the results. The adjustment unit can also use the generation AI to adjust the content of the learning materials according to the learner's progress. For example, if the learner has mastered basic greetings, the adjustment unit can teach them everyday conversation phrases as the next step.

[0067] (Example 2) A language learning system according to an embodiment of the present invention utilizes a generative AI to efficiently acquire English by speaking to a language learner. The language learning system has the generative AI read English learning materials, understand the content of the materials, and speak to the learner at the appropriate time. Furthermore, the generative AI paraphrases the material in Japanese according to the learner's level and adjusts the content of the materials according to the learner's progress. For example, if a learner says "Hello," the language learning system replies with "Hello, how are you?" This allows the learner to learn English in a natural conversational flow. Next, the generative AI paraphrases the material in Japanese according to the learner's level. For example, if a learner does not understand the question "What is your name?", the generative AI explains in Japanese with "What is your name?" This allows the learner to understand English without stress. Furthermore, the generative AI adjusts the content of the materials according to the learner's progress. For example, once a learner has mastered basic greetings, the generative AI teaches everyday conversational phrases as the next step. In this way, the learner can learn English at their own pace. This allows the language learning system to efficiently acquire English by using generative AI to speak to language learners. For example, learners can learn English through natural conversation by being spoken to by the generative AI. Also, learners can understand English without stress because the generative AI paraphrases what is said in Japanese. Furthermore, the generative AI adjusts the content of the learning materials according to the learner's progress, allowing them to acquire English efficiently.

[0068] A language learning system according to an embodiment includes a reading unit, an interlocutor unit, a paraphrasing unit, and an adjustment unit. The reading unit reads English language learning materials using a generation AI. For example, the reading unit can read English language learning materials such as textbooks, audio materials, and video materials. The reading unit understands the content of the materials using the generation AI and speaks to the learner at an appropriate time. The interlocutor unit speaks to the learner using the generation AI based on the content of the materials read by the reading unit. For example, if the learner says "Hello," the interlocutor unit replies with "Hello, how are you?" The interlocutor unit can also use the generation AI to analyze the learner's utterance and generate an appropriate response based on the content. For example, the interlocutor unit analyzes the learner's utterance using speech recognition technology and generates a response using the generation AI. The paraphrasing unit uses the generation AI to rephrase the content spoken by the interlocutor into Japanese according to the learner's level. For example, if the learner does not understand the question "What is your name?", the paraphrasing unit explains in Japanese as "Anata no na me wa? (What is your name?)." The paraphrasing unit can also use the generation AI to provide detailed explanations in Japanese for content that the learner does not understand. For example, the paraphrasing unit uses the generation AI to provide explanations and illustrations using examples in response to the learner's questions. The adjustment unit uses the generation AI to understand the learner's progress based on the content paraphrased by the paraphrasing unit and adjust the content of the teaching materials. For example, the adjustment unit evaluates the accuracy of the learner's statements and answers and provides the next step of teaching materials based on the results. The adjustment unit can also use the generation AI to adjust the content of the teaching materials according to the learner's progress. For example, if the learner has mastered basic greetings, the adjustment unit can teach everyday conversation phrases as the next step. As a result, the language learning system according to the embodiment can efficiently acquire English by utilizing the generation AI to speak to the language learner.

[0069] The interlocutor can analyze the learner's utterances and generate a response based on the content of the utterances. The interlocutor can analyze the learner's utterances using, for example, speech recognition technology. For example, the interlocutor can acquire the learner's utterances as audio data and analyze the content using a generation AI. The interlocutor can also analyze the learner's utterances using natural language processing technology. For example, the interlocutor can convert the learner's utterances into text data and analyze the content using a generation AI. The interlocutor can also generate an appropriate response based on the learner's utterances using a generation AI. For example, if the learner says "Hello," the interlocutor can respond with "Hello, how are you?" The interlocutor can also generate a template-based response based on the learner's utterances using a generation AI. For example, if the learner asks "What is your name?" the interlocutor can respond with "My name is AI." This allows for natural conversation by generating an appropriate response based on the learner's utterances.

[0070] The paraphrasing unit can provide detailed explanations in Japanese for content that the learner does not understand. For example, the paraphrasing unit uses a generation AI to identify content that the learner does not understand. For example, the paraphrasing unit analyzes the learner's questions and test results to identify content that the learner does not understand. The paraphrasing unit also uses a generation AI to provide detailed explanations in Japanese for content that the learner does not understand. For example, if the learner does not understand the question, "What is your name?", the paraphrasing unit can explain in Japanese, "What is your name?" The paraphrasing unit can also use a generation AI to provide explanations and illustrations for content that the learner does not understand using examples. For example, if the learner does not understand the question, "How do you say 'apple' in Japanese?", the paraphrasing unit can explain in Japanese, "'Apple' is said to be 'ringo' in Japanese," and display an image of an apple. This allows the learner to understand English without stress by explaining content that the learner does not understand in Japanese.

[0071] The adjustment unit can evaluate the accuracy of the learner's statements and answers, and select and provide learning materials for the next step based on the results. The adjustment unit, for example, uses a generation AI to evaluate the accuracy of the learner's statements and answers. For example, the adjustment unit analyzes the learner's statements and evaluates the rate of correct answers and the types of incorrect answers. The adjustment unit also uses a generation AI to select and provide learning materials for the next step according to the learner's progress. For example, if the learner has mastered basic greetings, the adjustment unit may teach everyday conversation phrases as the next step. The adjustment unit can also use a generation AI to adjust the difficulty level of the learning materials according to the learner's progress. For example, if the learner understands basic grammar, the adjustment unit may teach advanced grammar as the next step. In this way, the content of the learning materials can be adjusted according to the learner's progress, allowing for efficient English acquisition.

[0072] The adjustment unit can adjust the content of the learning materials based on the learner's progress. The adjustment unit, for example, uses a generation AI to grasp the learner's progress. For example, the adjustment unit analyzes the learner's study time and test results to grasp the learner's progress. The adjustment unit also uses a generation AI to adjust the content of the learning materials based on the learner's progress. For example, if the learner has mastered basic greetings, the adjustment unit may teach everyday conversation phrases as the next step. The adjustment unit can also use a generation AI to adjust the difficulty level of the learning materials according to the learner's progress. For example, if the learner understands basic grammar, the adjustment unit may teach advanced grammar as the next step. In this way, adjusting the content of the learning materials according to the learner's progress allows the learner to acquire English efficiently.

[0073] The reading unit can estimate the learner's emotions and change the reading speed of the learning materials based on the estimated learner's emotions. The reading unit estimates the learner's emotions using, for example, a generation AI. For example, the reading unit can analyze the learner's facial expressions using facial expression recognition technology to estimate the learner's emotions. The reading unit can also analyze the learner's tone and speed of voice using voice analysis technology to estimate the learner's emotions. Furthermore, the reading unit changes the reading speed of the learning materials based on the estimated learner's emotions using the generation AI. For example, the reading unit can read the learning materials slowly if the learner is relaxed. Also, the reading unit can read the learning materials quickly if the learner is impatient. Furthermore, the reading unit can read the learning materials at a normal speed if the learner is concentrating. In this way, adjusting the reading speed of the learning materials according to the learner's emotions can promote the learner's understanding.

[0074] When reading the contents of the teaching materials, the reading unit can emphasize important parts based on the learner's past learning history. The reading unit, for example, uses a generation AI to refer to the learner's past learning history. For example, the reading unit analyzes learning logs and test results to understand the learner's past learning history. The reading unit also uses a generation AI to emphasize important parts based on the learner's past learning history. For example, the reading unit reads by emphasizing parts that the learner previously struggled with. The reading unit can also read parts on which the learner previously scored high at a normal speed. Furthermore, the reading unit can read in detail parts on which the learner previously asked questions. In this way, the learning effect can be improved by emphasizing important parts by referring to the learner's past learning history.

[0075] When reading teaching materials, the reading unit can provide relevant information based on the learner's areas of interest. The reading unit, for example, uses a generation AI to identify the learner's areas of interest. For example, the reading unit analyzes survey results and past learning content to understand the learner's areas of interest. The reading unit also uses a generation AI to provide relevant information based on the learner's areas of interest. For example, the reading unit provides information related to topics that the learner is interested in. The reading unit can also provide additional information based on keywords that the learner has previously searched for. Furthermore, the reading unit can provide the latest research results related to the areas in which the learner has expressed interest. This makes it possible to pique the learner's interest by providing relevant additional information based on the learner's areas of interest.

[0076] When reading teaching materials, the reading unit can adjust the reading depth based on the learner's level of understanding. The reading unit, for example, uses a generation AI to evaluate the learner's level of understanding. For example, the reading unit analyzes test results and the rate of correct answers to questions to grasp the learner's level of understanding. The reading unit also uses a generation AI to adjust the reading depth based on the learner's level of understanding. For example, the reading unit reads in detail the parts that the learner does not understand. The reading unit can also simply read the parts that the learner does understand. Furthermore, the reading unit can supplementarily read the parts that the learner only partially understands. In this way, the learning effect can be improved by adjusting the reading depth according to the learner's level of understanding.

[0077] The reading unit can estimate the learner's emotions and adjust the reading order of the learning materials based on the estimated learner's emotions. The reading unit estimates the learner's emotions, for example, using a generation AI. For example, the reading unit can analyze the learner's facial expressions using facial expression recognition technology to estimate emotions. The reading unit can also analyze the learner's tone and speed of voice using voice analysis technology to estimate emotions. Furthermore, the reading unit adjusts the reading order of the learning materials based on the estimated learner's emotions using a generation AI. For example, if the learner is excited, the reading unit can start reading from interesting content. Also, if the learner is tired, the reading unit can start reading from easy content. Furthermore, if the learner is concentrating, the reading unit can start reading from difficult content. In this way, the learner's interest can be aroused by changing the reading order of the learning materials according to the learner's emotions.

[0078] When reading teaching materials, the reading unit can add region-specific examples based on the learner's geographical background. The reading unit, for example, uses a generation AI to identify the learner's geographical background. For example, the reading unit analyzes residential information and cultural background to understand the learner's geographical background. The reading unit also uses a generation AI to add region-specific examples based on the learner's geographical background. For example, if the learner lives in Japan, the reading unit can add examples from Japan. If the learner lives in the United States, the reading unit can also add examples from the United States. Furthermore, if the learner lives in Europe, the reading unit can add examples from Europe. This allows the learner's understanding to be deepened by adding region-specific examples taking into account the learner's geographical background.

[0079] When reading teaching materials, the reading unit can analyze the learner's social media activity and incorporate related topics. The reading unit, for example, uses a generation AI to analyze the learner's social media activity. For example, the reading unit analyzes the content of the learner's posts and the number of likes to understand the learner's interests. The reading unit also uses a generation AI to incorporate related topics based on the learner's social media activity. For example, the reading unit incorporates topics in which the learner has shown interest on social media. The reading unit can also incorporate content from accounts the learner follows on social media. Furthermore, the reading unit can incorporate content from articles the learner has shared on social media. In this way, the learner's interest can be piqued by analyzing the learner's social media activity and incorporating related topics.

[0080] When reading teaching materials, the reading unit can customize the reading method by reflecting the learner's past feedback. The reading unit, for example, uses a generation AI to refer to the learner's past feedback. For example, the reading unit analyzes survey results and comments to understand the learner's past feedback. The reading unit also uses a generation AI to customize the reading method based on the learner's past feedback. For example, the reading unit adjusts the reading method based on feedback previously submitted by the learner. The reading unit can also adjust the reading method based on the learner's past evaluations. Furthermore, the reading unit can also adjust the reading method based on the learner's past comments. In this way, the learning effect can be improved by customizing the reading method by reflecting the learner's past feedback.

[0081] The speaking unit can estimate the learner's emotions and change the tone and expressions of speech based on the estimated learner's emotions. The speaking unit estimates the learner's emotions using, for example, a generation AI. For example, the speaking unit analyzes the learner's facial expressions using facial expression recognition technology to estimate emotions. The speaking unit can also analyze the learner's tone and speed of voice using voice analysis technology to estimate emotions. Furthermore, the speaking unit changes the tone and expressions of speech based on the estimated learner's emotions using a generation AI. For example, if the learner is nervous, the speaking unit can speak in a calm tone. If the learner is relaxed, the speaking unit can speak in a bright tone. Furthermore, if the learner is excited, the speaking unit can speak in an energetic tone. In this way, by adjusting the tone and expressions of speech according to the learner's emotions, it is possible to promote the learner's understanding.

[0082] When speaking to a learner, the conversation unit can generate follow-up questions based on the learner's speech history. The conversation unit, for example, uses a generation AI to refer to the learner's speech history. For example, the conversation unit analyzes past conversation logs and the content of questions to understand the learner's speech history. The conversation unit also uses a generation AI to generate follow-up questions based on the learner's speech history. For example, the conversation unit generates follow-up questions based on questions the learner has asked in the past. The conversation unit can also generate follow-up questions based on content the learner has said in the past. Furthermore, the conversation unit can generate follow-up questions based on content in which the learner has shown interest in the past. In this way, the learner's understanding can be deepened by generating appropriate follow-up questions by referring to the learner's speech history.

[0083] When speaking to a learner, the conversation unit can select a conversation topic based on the learner's interests or concerns. The conversation unit, for example, uses a generation AI to identify the learner's interests or concerns. For example, the conversation unit analyzes survey results and past learning content to understand the learner's interests or concerns. The conversation unit also uses a generation AI to select a conversation topic based on the learner's interests or concerns. For example, the conversation unit selects a topic in which the learner is interested. The conversation unit can also select a topic based on keywords that the learner has searched for in the past. Furthermore, the conversation unit can select a topic based on a field in which the learner has shown interest. In this way, the learner's interest can be aroused by selecting a conversation topic based on the learner's interests or concerns.

[0084] When speaking to a learner, the conversation unit can adjust the difficulty of the conversation based on the learner's level of comprehension. The conversation unit, for example, uses a generation AI to evaluate the learner's level of comprehension. For example, the conversation unit analyzes test results and the rate of correct answers to questions to grasp the learner's level of comprehension. The conversation unit also uses a generation AI to adjust the difficulty of the conversation based on the learner's level of comprehension. For example, the conversation unit provides a conversation with a high level of difficulty if the learner understands. The conversation unit can also provide a conversation with a low level of difficulty if the learner does not understand. Furthermore, the conversation unit can also provide a conversation with an appropriate level of difficulty if the learner only partially understands. This makes it possible to improve learning effectiveness by adjusting the difficulty of the conversation according to the learner's level of comprehension.

[0085] The speaking unit can estimate the learner's emotions and change the frequency of speaking to the learner based on the estimated learner's emotions. The speaking unit estimates the learner's emotions using, for example, a generation AI. For example, the speaking unit analyzes the learner's facial expressions using facial expression recognition technology to estimate the learner's emotions. The speaking unit can also analyze the learner's tone and speed of voice using voice analysis technology to estimate the learner's emotions. Furthermore, the speaking unit changes the frequency of speaking to the learner based on the estimated learner's emotions using a generation AI. For example, the speaking unit reduces the frequency of speaking to the learner if the learner is nervous. The speaking unit can also increase the frequency of speaking to the learner if the learner is relaxed. Furthermore, the speaking unit can speak to the learner at an appropriate frequency if the learner is excited. In this way, the learner's understanding can be promoted by adjusting the frequency of speaking to the learner according to their emotions.

[0086] When speaking to a learner, the conversation unit can provide region-specific topics based on the learner's geographical background. The conversation unit, for example, uses a generation AI to identify the learner's geographical background. For example, the conversation unit analyzes residential information and cultural background to understand the learner's geographical background. The conversation unit also uses a generation AI to provide region-specific topics based on the learner's geographical background. For example, if the learner lives in Japan, the conversation unit can provide Japanese topics. If the learner lives in the United States, the conversation unit can also provide American topics. Furthermore, if the learner lives in Europe, the conversation unit can provide European topics. This makes it possible to deepen the learner's understanding by providing region-specific topics taking into account the learner's geographical background.

[0087] When speaking to a learner, the conversation unit can analyze the learner's social media activity and provide related topics. The conversation unit, for example, uses a generative AI to analyze the learner's social media activity. For example, the conversation unit analyzes the content of the learner's posts and the number of likes to understand the learner's interests. The conversation unit also uses a generative AI to provide related topics based on the learner's social media activity. For example, the conversation unit provides topics that the learner has shown interest in on social media. The conversation unit can also provide topics of accounts that the learner follows on social media. Furthermore, the conversation unit can provide topics of articles that the learner has shared on social media. In this way, the learner's interest can be piqued by analyzing the learner's social media activity and providing related topics.

[0088] When speaking to a learner, the speaking unit can customize the speaking method based on the learner's past feedback. The speaking unit, for example, uses a generation AI to refer to the learner's past feedback. For example, the speaking unit analyzes survey results and comments to understand the learner's past feedback. The speaking unit also uses a generation AI to customize the speaking method based on the learner's past feedback. For example, the speaking unit adjusts the speaking method based on feedback previously submitted by the learner. The speaking unit can also adjust the speaking method based on the learner's past evaluations. Furthermore, the speaking unit can adjust the speaking method based on the learner's past comments. In this way, the learning effect can be improved by customizing the speaking method to reflect the learner's past feedback.

[0089] The paraphrasing unit can estimate the learner's emotions and change the way the paraphrases are expressed based on the estimated learner's emotions. The paraphrasing unit estimates the learner's emotions using, for example, a generation AI. For example, the paraphrasing unit analyzes the learner's facial expressions using facial expression recognition technology to estimate the emotions. The paraphrasing unit can also analyze the learner's tone and speed of voice using speech analysis technology to estimate the emotions. Furthermore, the paraphrasing unit changes the way the paraphrases are expressed based on the estimated learner's emotions using the generation AI. For example, if the learner is nervous, the paraphrasing unit can rephrase the learner using simpler expressions. If the learner is relaxed, the paraphrasing unit can rephrase the learner using more detailed expressions. If the learner is excited, the paraphrasing unit can rephrase the learner using more energetic expressions. This makes it possible to promote the learner's understanding by adjusting the way the paraphrases are expressed based on the learner's emotions.

[0090] When explaining to a learner in Japanese, the paraphrasing unit can adjust the level of detail of the explanation based on the learner's level of understanding. The paraphrasing unit, for example, uses a generation AI to evaluate the learner's level of understanding. For example, the paraphrasing unit analyzes test results and the correct answer rate for questions to grasp the learner's level of understanding. The paraphrasing unit also uses a generation AI to adjust the level of detail of the explanation based on the learner's level of understanding. For example, the paraphrasing unit provides a simplified explanation if the learner understands. The paraphrasing unit can also provide a detailed explanation if the learner does not understand. Furthermore, the paraphrasing unit can provide supplementary explanation if the learner only partially understands. In this way, the learning effect can be improved by adjusting the level of detail of the explanation according to the learner's level of understanding.

[0091] When explaining to a learner in Japanese, the paraphrasing unit can provide examples based on the learner's past learning history. The paraphrasing unit, for example, uses a generation AI to refer to the learner's past learning history. For example, the paraphrasing unit analyzes learning logs and test results to understand the learner's past learning history. The paraphrasing unit also uses a generation AI to provide examples based on the learner's past learning history. For example, the paraphrasing unit provides appropriate examples based on content that the learner has learned in the past. The paraphrasing unit can also provide appropriate examples based on content that the learner has asked in the past. Furthermore, the paraphrasing unit can provide appropriate examples based on content in which the learner has shown interest in the past. In this way, the learner's understanding can be deepened by providing appropriate examples by referring to the learner's past learning history.

[0092] When explaining to a learner in Japanese, the paraphrasing unit can provide relevant information based on the learner's areas of interest. The paraphrasing unit, for example, uses a generation AI to identify the learner's areas of interest. For example, the paraphrasing unit analyzes survey results and past learning content to understand the learner's areas of interest. The paraphrasing unit also uses a generation AI to provide relevant information based on the learner's areas of interest. For example, the paraphrasing unit provides information related to areas in which the learner is interested. The paraphrasing unit can also provide relevant information based on keywords that the learner has previously searched for. Furthermore, the paraphrasing unit can provide the latest research results related to areas in which the learner has expressed interest. This makes it possible to pique the learner's interest by providing relevant information based on the learner's areas of interest.

[0093] The paraphrasing unit can estimate the learner's emotions and change the timing of paraphrasing based on the estimated learner's emotions. The paraphrasing unit estimates the learner's emotions using, for example, a generation AI. For example, the paraphrasing unit analyzes the learner's facial expressions using facial expression recognition technology to estimate emotions. The paraphrasing unit can also analyze the learner's tone and speed of voice using speech analysis technology to estimate emotions. Furthermore, the paraphrasing unit changes the timing of paraphrasing based on the estimated learner's emotions using the generation AI. For example, the paraphrasing unit paraphrases at a slower pace if the learner is nervous. The paraphrasing unit can also paraphrase at a normal pace if the learner is relaxed. Furthermore, the paraphrasing unit can also paraphrase at a faster pace if the learner is excited. This makes it possible to promote the learner's understanding by adjusting the timing of paraphrasing according to the learner's emotions.

[0094] When explaining to a learner in Japanese, the paraphrasing unit can provide region-specific examples based on the learner's geographical background. The paraphrasing unit, for example, uses a generation AI to identify the learner's geographical background. For example, the paraphrasing unit analyzes residential information and cultural background to understand the learner's geographical background. The paraphrasing unit also uses a generation AI to provide region-specific examples based on the learner's geographical background. For example, if the learner lives in Japan, the paraphrasing unit can provide examples from Japan. If the learner lives in the United States, the paraphrasing unit can also provide examples from the United States. Furthermore, if the learner lives in Europe, the paraphrasing unit can provide examples from Europe. This makes it possible to deepen the learner's understanding by providing region-specific examples taking into account the learner's geographical background.

[0095] When explaining to a learner in Japanese, the paraphrasing unit can analyze the learner's social media activity and provide relevant information. The paraphrasing unit, for example, uses a generation AI to analyze the learner's social media activity. For example, the paraphrasing unit analyzes the content of the learner's posts and the number of likes to understand the learner's interests. The paraphrasing unit also uses a generation AI to provide relevant information based on the learner's social media activity. For example, the paraphrasing unit provides relevant information based on the content in which the learner has shown interest on social media. The paraphrasing unit can also provide relevant information based on the content of accounts the learner follows on social media. Furthermore, the paraphrasing unit can provide relevant information based on the content of articles the learner has shared on social media. In this way, the learner's social media activity can be analyzed and relevant information provided to pique the learner's interest.

[0096] When explaining to a learner in Japanese, the paraphrasing unit can customize the explanation method based on the learner's past feedback. The paraphrasing unit, for example, uses a generation AI to refer to the learner's past feedback. For example, the paraphrasing unit analyzes survey results and comments to understand the learner's past feedback. The paraphrasing unit also uses a generation AI to customize the explanation method based on the learner's past feedback. For example, the paraphrasing unit adjusts the explanation method based on feedback previously submitted by the learner. The paraphrasing unit can also adjust the explanation method based on the learner's past evaluations. Furthermore, the paraphrasing unit can also adjust the explanation method based on the learner's past comments. In this way, the explanation method can be customized to reflect the learner's past feedback, thereby improving the learning effect.

[0097] The adjustment unit can estimate the learner's emotions and change the content of the learning materials based on the estimated learner's emotions. The adjustment unit estimates the learner's emotions using, for example, a generation AI. For example, the adjustment unit can analyze the learner's facial expressions using facial expression recognition technology to estimate the learner's emotions. The adjustment unit can also analyze the learner's tone and speed of voice using voice analysis technology to estimate the learner's emotions. Furthermore, the adjustment unit changes the content of the learning materials based on the estimated learner's emotions using a generation AI. For example, the adjustment unit can adjust the content to be easier if the learner is nervous. The adjustment unit can also adjust the content to be normal if the learner is relaxed. Furthermore, the adjustment unit can adjust the content to be more difficult if the learner is excited. In this way, adjusting the content of the learning materials according to the learner's emotions can promote the learner's understanding.

[0098] When grasping the learner's progress, the adjustment unit can evaluate the progress based on the learner's speech history. The adjustment unit, for example, uses a generation AI to refer to the learner's speech history. For example, the adjustment unit analyzes past conversation logs and the content of questions to grasp the learner's speech history. The adjustment unit also uses a generation AI to evaluate the progress based on the learner's speech history. For example, the adjustment unit evaluates the progress based on the content of past speeches made by the learner. The adjustment unit can also evaluate the progress based on the content of questions asked by the learner in the past. Furthermore, the adjustment unit can evaluate the progress based on assignments submitted by the learner in the past. In this way, by evaluating the progress by referring to the learner's speech history, it is possible to improve the learning effect.

[0099] When grasping the learner's progress, the adjustment unit can select the next step learning material based on the learner's level of understanding. The adjustment unit, for example, uses a generation AI to evaluate the learner's level of understanding. For example, the adjustment unit analyzes test results and the rate of correct answers to questions to grasp the learner's level of understanding. The adjustment unit also uses a generation AI to select the next step learning material based on the learner's level of understanding. For example, the adjustment unit provides the next step learning material if the learner understands. The adjustment unit can also provide supplementary learning material if the learner does not understand. Furthermore, the adjustment unit can provide supplementary learning material if the learner only partially understands. In this way, the learning effect can be improved by selecting the next step learning material according to the learner's level of understanding.

[0100] When grasping the learner's progress, the adjustment unit can change the content of the learning materials based on the learner's areas of interest. The adjustment unit, for example, uses a generation AI to identify the learner's areas of interest. For example, the adjustment unit analyzes questionnaire results and past learning content to grasp the learner's areas of interest. The adjustment unit also uses a generation AI to change the content of the learning materials based on the learner's areas of interest. For example, the adjustment unit provides learning materials related to the learner's areas of interest. The adjustment unit can also provide learning materials based on keywords the learner has searched for in the past. Furthermore, the adjustment unit can provide the latest research results related to the areas in which the learner has expressed interest. In this way, the content of the learning materials can be customized based on the learner's areas of interest to pique the learner's interest.

[0101] The adjustment unit can estimate the learner's emotions and change the progress evaluation criteria based on the estimated learner's emotions. The adjustment unit estimates the learner's emotions using, for example, a generation AI. For example, the adjustment unit can analyze the learner's facial expressions using facial expression recognition technology to estimate emotions. The adjustment unit can also analyze the learner's tone and speed of voice using voice analysis technology to estimate emotions. Furthermore, the adjustment unit can change the progress evaluation criteria based on the estimated learner's emotions using the generation AI. For example, the adjustment unit relaxes the evaluation criteria when the learner is nervous. The adjustment unit can also apply normal evaluation criteria when the learner is relaxed. Furthermore, the adjustment unit can apply stricter evaluation criteria when the learner is excited. In this way, the learner's understanding can be promoted by adjusting the progress evaluation criteria according to the learner's emotions.

[0102] The adjustment unit can evaluate a learner's progress by taking into account the learner's geographical background. The adjustment unit, for example, uses a generation AI to identify the learner's geographical background. For example, the adjustment unit analyzes residential information and cultural background to understand the learner's geographical background. The adjustment unit also uses a generation AI to evaluate based on the learner's geographical background. For example, the adjustment unit applies Japanese evaluation standards if the learner lives in Japan. The adjustment unit can also apply American evaluation standards if the learner lives in the United States. The adjustment unit can also apply European evaluation standards if the learner lives in Europe. This makes it possible to deepen the learner's understanding by evaluating the learner while taking into account their geographical background.

[0103] When grasping the learner's progress, the adjustment unit can analyze the learner's social media activity to evaluate the progress. The adjustment unit, for example, uses a generation AI to analyze the learner's social media activity. For example, the adjustment unit analyzes the content of the learner's posts and the number of likes to grasp the learner's interests. The adjustment unit also uses a generation AI to evaluate the learner's progress based on the learner's social media activity. For example, the adjustment unit evaluates the learner's progress based on the content of the learner's posts on social media. The adjustment unit can also evaluate the learner's progress based on articles the learner shared on social media. Furthermore, the adjustment unit can evaluate the learner's progress based on the content of accounts the learner follows on social media. In this way, by analyzing the learner's social media activity and evaluating the learner's progress, it is possible to draw out the learner's interest.

[0104] When grasping the learner's progress, the adjustment unit can customize the assessment method based on the learner's past feedback. The adjustment unit, for example, uses a generation AI to refer to the learner's past feedback. For example, the adjustment unit analyzes survey results and comments to grasp the learner's past feedback. The adjustment unit also uses a generation AI to customize the assessment method based on the learner's past feedback. For example, the adjustment unit adjusts the assessment method based on feedback previously submitted by the learner. The adjustment unit can also adjust the assessment method based on the learner's past assessments. Furthermore, the adjustment unit can also adjust the assessment method based on the learner's past comments. In this way, the learning effect can be improved by customizing the assessment method to reflect the learner's past feedback. === Hard Collateral 1-1 === Each of the multiple elements including the reading unit, speaking unit, paraphrasing unit, and adjustment 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 reading unit is realized by the computer 36 of the smart device 14 and reads the English learning materials. The speaking unit is realized by the processor 46 of the smart device 14 and speaks to the learner. The paraphrasing unit is realized by the specific processing unit 290 of the data processing device 12 and rephrases the text in Japanese according to the learner's level. The adjustment unit is realized by the specific processing unit 290 of the data processing device 12 and adjusts the content of the learning materials according to the learner's progress. === Hard Collateral 1-2 === Each of the multiple elements, including the reading unit, speaking unit, paraphrasing unit, and adjustment unit, described above, is realized, for example, by at least one of the smart glasses 214 and the data processing device 12. For example, the reading unit is realized by the computer 36 of the smart glasses 214 and reads the English learning materials. The speaking unit is realized by the processor 46 of the smart glasses 214 and speaks to the learner. The paraphrasing unit is realized by the specific processing unit 290 of the data processing device 12 and paraphrases the text in Japanese according to the learner's level. The adjustment unit is realized by the specific processing unit 290 of the data processing device 12 and adjusts the content of the learning materials according to the learner's progress. === Hard Collateral 1-3 === Each of the multiple elements including the reading unit, speaking unit, paraphrasing unit, and adjustment unit described above is realized, for example, by at least one of the headset terminal 314 and the data processing device 12. For example, the reading unit is realized by the computer 36 of the headset terminal 314 and reads the English learning materials. The speaking unit is realized by the processor 46 of the headset terminal 314 and speaks to the learner. The paraphrasing unit is realized by the specific processing unit 290 of the data processing device 12 and rephrases the text in Japanese according to the learner's level. The adjustment unit is realized by the specific processing unit 290 of the data processing device 12 and adjusts the content of the learning materials according to the learner's progress. === Hard Collateral 1-4 === Each of the multiple elements including the reading unit, speaking unit, paraphrasing unit, and adjustment unit described above is realized, for example, by at least one of the robot 414 and the data processing device 12. For example, the reading unit is realized by the computer 36 of the robot 414 and reads the English learning materials. The speaking unit is realized by the processor 46 of the robot 414 and speaks to the learner. The paraphrasing unit is realized by the specific processing unit 290 of the data processing device 12 and rephrases the text in Japanese according to the learner's level. The adjustment unit is realized by the specific processing unit 290 of the data processing device 12 and adjusts the content of the learning materials according to the learner's progress.

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

[0106] The language learning system further includes a feedback unit. The feedback unit can provide instant feedback to the learner's utterances and answers. For example, if the learner asks, "What is your name?", the feedback unit can provide positive feedback such as, "Good question!". If the learner gives an incorrect answer, the feedback unit can also provide encouraging feedback such as, "Almost there, try again!". Furthermore, the feedback unit can adjust the content of the feedback according to the learner's progress. For example, if the learner has mastered basic grammar, the feedback unit can provide more advanced feedback. This allows the learner to receive instant feedback and improve their learning effectiveness.

[0107] The language learning system further includes a sentiment analysis unit. The sentiment analysis unit can analyze the learner's emotions in real time and adjust the learning content based on the results. For example, if the learner is feeling stressed, the sentiment analysis unit can provide easy content that will help the learner relax. Also, if the learner is excited, the sentiment analysis unit can provide challenging content. Furthermore, the sentiment analysis unit can adjust the learning progress speed according to the learner's emotions. For example, if the learner is concentrating, the sentiment analysis unit can speed up the learning progress speed. This makes it possible to provide an optimal learning environment according to the learner's emotions.

[0108] The language learning system further includes a customization unit. The customization unit can customize the learning plan based on the learner's individual needs and goals. For example, if a learner wants to learn business English, the customization unit can provide business-related learning materials. If a learner wants to learn travel English, the customization unit can also provide travel-related learning materials. The customization unit can also adjust the learning plan according to the learner's progress. For example, if a learner has weaknesses in a particular area, the customization unit can provide a plan that focuses on that area. This allows the learner to study effectively according to their own goals.

[0109] The language learning system further includes a motivation unit. The motivation unit can provide a function to maintain the learner's motivation. For example, the motivation unit can award badges or points when a learner achieves a certain goal. The motivation unit can also provide a ranking function that allows a learner to compete with other learners. Furthermore, the motivation unit can send encouraging messages according to the learner's progress. For example, if a learner continues to study continuously, the motivation unit can send a message such as "Great job! Keep it up!". This allows the learner to continue studying while maintaining their motivation.

[0110] The language learning system further includes a reminder unit. The reminder unit can send regular reminders to encourage the learner to study. For example, the reminder unit can send a reminder if the learner has not studied for a certain period of time. The reminder unit can also suggest the optimal study time based on the learner's schedule. Furthermore, the reminder unit can adjust the content of the reminder according to the learner's progress. For example, if the learner is approaching a specific goal, the reminder unit can send a reminder such as "You are almost there! Keep going!". This helps the learner develop the habit of studying regularly.

[0111] The language learning system further includes an emotional feedback unit. The emotional feedback unit can estimate the learner's emotions and provide feedback based on those emotions. For example, if the learner is feeling down, the emotional feedback unit can provide encouraging feedback such as "Don't worry, you're doing great!". If the learner is feeling confident, the emotional feedback unit can also provide positive feedback such as "Excellent work! Keep it up!". Furthermore, the emotional feedback unit can adjust the content of the feedback according to the learner's emotions. For example, if the learner is feeling impatient, the emotional feedback unit can provide relaxing feedback such as "Take your time, there's no rush." ​​This allows the learner to receive appropriate feedback according to their emotions.

[0112] The language learning system further includes an interactive section. The interactive section may provide interactive features that allow a learner to progress through their learning at their own pace. For example, the interactive section may provide a dashboard that allows a learner to check their progress. The interactive section may also provide a feature that allows a learner to customize their learning content. The interactive section may also provide a forum for a learner to communicate with other learners. This allows a learner to share information with other learners while progressing through their learning at their own pace.

[0113] The language learning system further includes an emotion monitoring unit. The emotion monitoring unit can monitor the learner's emotions in real time and adjust the learning environment based on the results. For example, if the learner is tired, the emotion monitoring unit can suggest that the learner pause learning. Also, if the learner is concentrating, the emotion monitoring unit can encourage the learner to continue learning. Furthermore, the emotion monitoring unit can adjust the learning content according to the learner's emotions. For example, if the learner is relaxed, the emotion monitoring unit can provide more difficult content. In this way, it is possible to provide an optimal learning environment according to the learner's emotions.

[0114] The language learning system further includes a progress tracking unit. The progress tracking unit can track the learner's learning progress in detail and adjust the learning plan based on the results. For example, the progress tracking unit records how often the learner studies. The progress tracking unit can also evaluate how well the learner has understood each learning material. The progress tracking unit can also adjust the learning plan according to the learner's progress. For example, if the learner is lagging behind in a particular area, the progress tracking unit can provide a plan to focus on that area. This allows the learner to study effectively while keeping track of their own progress.

[0115] The language learning system further includes an emotional support unit. The emotional support unit can estimate the learner's emotions and provide support based on the emotions. For example, if the learner feels anxious, the emotional support unit can provide advice to relax. Also, if the learner feels confident, the emotional support unit can provide advice to encourage further challenges. Furthermore, the emotional support unit can support the learner's progress in learning according to the learner's emotions. For example, if the learner is concentrating, the emotional support unit can support the learner to speed up the progress of learning. In this way, the learner can receive appropriate support according to their emotions.

[0116] The processing flow of the second embodiment will be briefly explained below.

[0117] Step 1: The reading unit uses the generation AI to read the English learning materials. For example, the reading unit can read English learning materials such as textbooks, audio materials, and video materials. The reading unit uses the generation AI to understand the content of the materials and speaks to the learner at the appropriate time. Step 2: The interlocutor uses a generation AI to speak to the learner based on the content of the learning material read by the reader. For example, if the learner says "Hello," the interlocutor replies, "Hello, how are you?" The interlocutor can also use a generation AI to analyze the learner's utterances and generate an appropriate response based on the content. For example, the interlocutor uses voice recognition technology to analyze the learner's utterances and uses a generation AI to generate a response. Step 3: The paraphrasing unit uses the generation AI to rephrase what has been spoken by the speaking unit into Japanese according to the learner's level. For example, if the learner does not understand the question "What is your name?", the paraphrasing unit will explain it in Japanese as "What is your name?". The paraphrasing unit can also use the generation AI to provide detailed explanations in Japanese for content that the learner does not understand. For example, the paraphrasing unit uses the generation AI to provide explanations using examples and illustrations in response to the learner's questions. Step 4: The adjustment unit uses the generation AI to understand the learner's progress based on the content paraphrased by the paraphrasing unit and adjusts the content of the learning materials. For example, the adjustment unit evaluates the accuracy of the learner's statements and answers and provides the next step of learning materials based on the results. The adjustment unit can also use the generation AI to adjust the content of the learning materials according to the learner's progress. For example, if the learner has mastered basic greetings, the adjustment unit can teach them everyday conversation phrases as the next step.

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

[0119] The data generation model 58 is a so-called generative AI (Artificial Intelligence). An example of the data generation model 58 is ChatGPT (registered trademark) (Internet search engine).<URL: https: / / openai.com / blog / chatgpt> Examples of generative AIs include the data generation model 58, such as a neural network model (e.g., a neural network model), and a neural network model (e.g., a neural network model). The data generation model 58 is obtained by performing deep learning on a neural network. A prompt including an instruction is input to the data generation model 58, and inference data such as voice data indicating speech, text data indicating text, and image data indicating an image is also input to the data generation model 58. The data generation model 58 performs inference on the input inference data in accordance with the instruction indicated by the prompt and outputs the inference result in a data format such as voice data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization. The specification processing unit 290 performs the above-mentioned specification processing using the data generation model 58. The data generation model 58 may be a fine-tuned model so as to output an inference result from a prompt that does not include an instruction. In this case, the data generation model 58 can output an inference result from a prompt that does not include an instruction. The data processing device 12 and the like include multiple types of data generation models 58, and the data generation model 58 includes AIs other than the generative AI. The AI ​​other than the generative AI may be, for example, linear regression, logistic regression, decision tree, random forest, support vector machine (SVM), k-means clustering, convolutional neural network (CNN), recurrent neural network (RNN), generative adversarial network (GAN), or naive Bayes, and can perform various processes, but is not limited to these examples. The AI ​​may also be an AI agent. When the processes of each of the above-mentioned parts are performed by AI, the processes may be performed in part or entirely by AI, but are not limited to these examples. The processes performed by AI, including the generative AI, may be replaced with rule-based processes.

[0120] 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.

[0121] The correspondence between each part and the device or control part is not limited to the example described above, and various modifications are possible.

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

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

[0124] 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.

[0125] 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.

[0126] 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.

[0127] 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).

[0128] 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.

[0129] 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.

[0130] 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.

[0131] 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.

[0132] 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.

[0133] 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.

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

[0135] The data generation model 58 is a so-called generative AI. An example of the data generation model 58 is a generative AI such as ChatGPT. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 receives a prompt containing an instruction, as well as inference data such as voice data representing speech, text data representing text, and image data representing an image. The data generation model 58 performs inference on the input inference data in accordance with the instruction indicated by the prompt and outputs the inference result in a data format such as voice data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization. The identification processing unit 290 performs the above-mentioned identification processing using the data generation model 58. The data generation model 58 may be a fine-tuned model so as to output an inference result from a prompt that does not include an instruction. In this case, the data generation model 58 can output an inference result from a prompt that does not include an instruction. The data processing device 12 and the like include multiple types of data generation models 58, and the data generation model 58 includes AIs other than the generative AI. The AI ​​other than the generative AI may be, for example, linear regression, logistic regression, decision tree, random forest, support vector machine (SVM), k-means clustering, convolutional neural network (CNN), recurrent neural network (RNN), generative adversarial network (GAN), or naive Bayes, and can perform various processes, but is not limited to these examples. The AI ​​may also be an AI agent. When the processes of each of the above-mentioned parts are performed by AI, the processes may be performed in part or entirely by AI, but are not limited to these examples. The processes performed by AI, including the generative AI, may be replaced with rule-based processes.

[0136] The data processing system 210 according to the second embodiment performs the same processing as the data processing system 10 according to the first embodiment. The processing by the data processing system 210 is 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.

[0137] The correspondence between each part and the device or control part is not limited to the example described above, and various modifications are possible.

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

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

[0140] 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.

[0141] 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.

[0142] 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.

[0143] 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).

[0144] 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.

[0145] 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.

[0146] 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.

[0147] 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.

[0148] 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.

[0149] 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.

[0150] 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.

[0151] The data generation model 58 is a so-called generative AI. An example of the data generation model 58 is a generative AI such as ChatGPT. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 receives a prompt containing an instruction, as well as inference data such as voice data representing speech, text data representing text, and image data representing an image. The data generation model 58 performs inference on the input inference data in accordance with the instruction indicated by the prompt and outputs the inference result in a data format such as voice data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization. The identification processing unit 290 performs the above-mentioned identification processing using the data generation model 58. The data generation model 58 may be a fine-tuned model so as to output an inference result from a prompt that does not include an instruction. In this case, the data generation model 58 can output an inference result from a prompt that does not include an instruction. The data processing device 12 and the like include multiple types of data generation models 58, and the data generation model 58 includes AIs other than the generative AI. The AI ​​other than the generative AI may be, for example, linear regression, logistic regression, decision tree, random forest, support vector machine (SVM), k-means clustering, convolutional neural network (CNN), recurrent neural network (RNN), generative adversarial network (GAN), or naive Bayes, and can perform various processes, but is not limited to these examples. The AI ​​may also be an AI agent. When the processes of each of the above-mentioned parts are performed by AI, the processes may be performed in part or entirely by AI, but are not limited to these examples. The processes performed by AI, including the generative AI, may be replaced with rule-based processes.

[0152] The data processing system 310 according to the third embodiment performs the same processing as the data processing system 10 according to the first embodiment. The processing by the data processing system 310 is 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.

[0153] The correspondence between each part and the device or control part is not limited to the example described above, and various modifications are possible.

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

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

[0156] The data processing device 12 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.

[0157] 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.

[0158] 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.

[0159] 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).

[0160] 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.

[0161] 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.

[0162] 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.

[0163] 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.

[0164] 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.

[0165] 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.

[0166] 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.

[0167] The specific processing unit 290 transmits the result of the specific processing to the robot 414. In the robot 414, the control unit 46A causes the speaker 240 and the 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.

[0168] The data generation model 58 is a so-called generative AI. An example of the data generation model 58 is a generative AI such as ChatGPT. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 receives a prompt containing an instruction, as well as inference data such as voice data representing speech, text data representing text, and image data representing an image. The data generation model 58 performs inference on the input inference data in accordance with the instruction indicated by the prompt and outputs the inference result in a data format such as voice data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization. The identification processing unit 290 performs the above-mentioned identification processing using the data generation model 58. The data generation model 58 may be a fine-tuned model so as to output an inference result from a prompt that does not include an instruction. In this case, the data generation model 58 can output an inference result from a prompt that does not include an instruction. The data processing device 12 and the like include multiple types of data generation models 58, and the data generation model 58 includes AIs other than the generative AI. The AI ​​other than the generative AI may be, for example, linear regression, logistic regression, decision tree, random forest, support vector machine (SVM), k-means clustering, convolutional neural network (CNN), recurrent neural network (RNN), generative adversarial network (GAN), or naive Bayes, and can perform various processes, but is not limited to these examples. The AI ​​may also be an AI agent. When the processes of each of the above-mentioned parts are performed by AI, the processes may be performed in part or entirely by AI, but are not limited to these examples. The processes performed by AI, including the generative AI, may be replaced with rule-based processes.

[0169] The data processing system 410 according to the fourth embodiment performs the same processing as the data processing system 10 according to the first embodiment. The processing by the data processing system 410 is 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.

[0170] The correspondence between each part and the device or control part is not limited to the example described above, and various modifications are possible.

[0171] 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.

[0172] 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.

[0173] 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.

[0174] 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).

[0175] 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.

[0176] 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."

[0177] 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.

[0178] 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.

[0179] 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.

[0180] Alternatively, the specific processing program 56 may be stored in a storage device such as a server connected to the data processing device 12 via the network 54, and the specific processing program 56 may be downloaded and installed on the computer 22 in response to a request from the data processing device 12.

[0181] 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.

[0182] 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.

[0183] 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.

[0184] 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.

[0185] 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.

[0186] 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.

[0187] 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.

[0188] 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.

[0189] [Explanation of symbols]

[0190] 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 reading section that reads English learning materials, a speaking unit that speaks to the learner based on the content of the learning material read by the reading unit; a paraphrasing unit that paraphrases the content spoken by the speaking unit into Japanese according to the level of the learner; and an adjustment unit that grasps the learner's progress based on the content paraphrased by the paraphrasing unit and adjusts the content of the teaching material.

2. The speaking unit is Analyze what the learner says and generate a response based on that content 2. The system of claim 1.

3. The paraphrase unit Explain in detail in Japanese what the learner does not understand 2. The system of claim 1.

4. The adjustment unit Evaluate the content of the learner's statements and the accuracy of their answers, and select and provide learning materials for the next step based on the results.

2. The system of claim 1.

5. The adjustment unit Adapt learning materials based on learner progress 2. The system of claim 1.

6. The reading unit Estimate the learner's emotions and change the reading speed of the material based on the estimated learner's emotions 2. The system of claim 1.

7. The reading unit When reading the content of the teaching materials, highlight the important parts based on the learner's past learning history.

2. The system of claim 1.

8. The reading unit Provide relevant information based on learners' areas of interest when reading materials 2. The system of claim 1.

Images