System

Abstract

An object of a system according to an embodiment is to perform appropriate learning support according to the vocabulary and the degree of understanding of each student.SOLUTION: A system includes an analysis part, an answer part, and a review part. The analysis unit analyzes the vocabulary or the degree of understanding of the student. The answer unit answers the question using the text and the image based on the result analyzed by the analysis unit. The reviewing unit instructs appropriate review based on the answer provided by the answering unit.SELECTED DRAWING: Figure 1

Description

[Technical Field]

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

[0002] Patent document 1 discloses a persona chatbot control method performed by at least one processor, the method including the steps of receiving a user utterance, adding the user utterance to a prompt including 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 does not adequately provide appropriate learning support tailored to each student's vocabulary and level of understanding, and there is room for improvement.

[0005] The system according to the embodiment aims to provide appropriate learning support according to the vocabulary and level of understanding of each student. [Means for solving the problem]

[0006] The system according to the embodiment includes an analysis unit, an answering unit, and a reviewing unit. The analysis unit analyzes a student's vocabulary or comprehension level. The answering unit answers questions using text and images based on the results of the analysis by the analysis unit. The reviewing unit instructs appropriate review based on the answers provided by the answering unit. [Effects of the Invention]

[0007] The system according to the embodiment can provide appropriate learning support according to the vocabulary and level of understanding of each student. [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 self-learning educational tool according to an embodiment of the present invention is a system for providing a non-competitive learning environment for students in the early grades of elementary school, taking into account differences in age. The self-learning educational tool utilizes multimodal functions to analyze each student's vocabulary and comprehension. Specifically, it allows students to ask questions until they are satisfied using text and images, preventing them from feeling like they are weak at a subject. Furthermore, appropriate review based on Ebbinghaus's forgetting curve helps students solidify their learning. This supports efficient learning tailored to each student. For example, the self-learning educational tool analyzes each student's vocabulary and comprehension. Based on the text and image selected by the student, an AI evaluates the student's comprehension. For example, if a student enters the word "dog," the AI ​​evaluates whether the student understands the meaning of the word. Furthermore, if a student selects an image of a dog, the AI ​​determines whether the image is correct. Next, the self-learning educational tool allows students to ask questions using text and images until they are satisfied. For example, if a student asks, "What is a dog?", the AI ​​responds using text and images. If the student continues to ask questions, the AI ​​provides appropriate answers each time. This allows students to progress through their studies at their own pace. Furthermore, the self-learning educational tool provides appropriate review based on Ebbinghaus's forgetting curve. For example, after a student learns a new word, the AI ​​instructs them to review that word after a certain period of time has passed. This allows students to retain the learned content for a long period of time. This allows the self-learning educational tool to support efficient learning tailored to each student. For example, students with low vocabulary skills can start with simple words and gradually increase the difficulty level. Also, students with high comprehension levels can be provided with more advanced content. This allows each student to progress through their studies at their own pace. This allows the self-learning educational tool to analyze students' vocabulary and comprehension levels and provide appropriate questions and reviews to support efficient learning. For example, students can progress through their studies at their own pace and retain the learned content without feeling uncomfortable. It also reduces the burden on teachers and provides learning support tailored to each student.

[0029] A self-study education tool according to an embodiment includes an analysis unit, an answering unit, and a reviewing unit. The analysis unit analyzes a student's vocabulary or comprehension. For example, the analysis unit evaluates the student's comprehension based on text entered by the student and an image selected by the student. For example, if a student enters the word "dog," the analysis unit evaluates whether the student understands the meaning of the word. Furthermore, if a student selects an image of a dog, the analysis unit can determine whether the image is correct. The analysis unit can also evaluate a student's vocabulary. For example, the analysis unit evaluates the student's vocabulary based on the number of words the student knows and how often they are used. The answering unit answers questions using text and images based on the results of the analysis by the analysis unit. For example, if a student asks, "What is a dog?", the answering unit generates an answer using text and images. The answering unit can also answer questions until the student is satisfied. For example, if the student continues to ask further questions, the answering unit provides an appropriate answer each time. The reviewing unit instructs the student on appropriate review based on the answers provided by the answering unit. For example, the review unit may instruct appropriate review based on Ebbinghaus's forgetting curve. For example, the review unit may instruct a student to review a new word after a certain period of time has passed since the student learned the word. The review unit may also instruct review to help the student retain the learning content for a long period of time. For example, the review unit may instruct the student to review the learning content periodically. As a result, the self-learning educational tool according to the embodiment can analyze the student's vocabulary and comprehension level and provide appropriate questions and reviews to support efficient learning. For example, the self-learning educational tool according to the embodiment can allow students to study at their own pace and solidify the learning content without feeling that they are weak at the material. Furthermore, the self-learning educational tool can reduce the burden on teachers and provide learning support appropriate for each student.

[0030] The analysis unit can evaluate the student's level of understanding based on the text entered or the image selected by the student. The analysis unit evaluates the level of understanding based on, for example, the text entered by the student. For example, if the student enters the word "dog," the analysis unit evaluates whether the student understands the meaning of the word. The analysis unit can also evaluate the level of understanding based on the image selected by the student. For example, if the student selects an image of a dog, the analysis unit determines whether the image is correct. This enables individually tailored learning support by evaluating the student's level of understanding based on the student's input. Some or all of the above-described processing in the analysis unit may be performed using, for example, AI, or may be performed without using AI. For example, the analysis unit can input the text entered or the image selected by the student into a generation AI and have the generation AI evaluate the student's level of understanding.

[0031] The answering unit can answer questions until the student reaches a certain standard. For example, if a student asks, "What is a dog?", the answering unit generates an answer using text and images. For example, the answering unit provides a text description of dogs and displays images of dogs. Furthermore, if the student continues to ask questions, the answering unit can provide appropriate answers each time. For example, if a student asks, "What kind of dog is it?", the answering unit describes dog types and displays images of each type. This allows the student to answer questions until they are satisfied, thereby deepening their understanding of the learning. Some or all of the above-described processing in the answering unit may be performed using, for example, AI, or may be performed without AI. For example, the answering unit can input the student's question into a generating AI and have the generating AI generate an answer.

[0032] The review unit can instruct appropriate review based on Ebbinghaus's forgetting curve. For example, after a student learns a new word, the review unit instructs the student to review the word after a certain period of time has passed. For example, the review unit instructs the student to review the word one week, one month, or three months later. The review unit can also instruct reviews to help the student memorize the learned content over a long period of time. For example, the review unit instructs the student to review the learned content periodically. In this way, review based on Ebbinghaus's forgetting curve can promote the retention of the learned content. Some or all of the above-described processing in the review unit may be performed using, for example, AI, or may be performed without AI. For example, the review unit can input review timing based on Ebbinghaus's forgetting curve into the generation AI and cause the generation AI to execute the review instructions.

[0033] The analysis unit can evaluate a student's vocabulary ability. The analysis unit evaluates vocabulary ability based on, for example, the number of words the student knows and the frequency of their use. For example, the analysis unit counts the number of words entered by the student and evaluates vocabulary ability based on that number. The analysis unit can also analyze the frequency of words used by the student and evaluate vocabulary ability based on that frequency. For example, the analysis unit compares words frequently used by the student with words used infrequently and evaluates vocabulary ability based on the results. This enables individually tailored learning support by evaluating the student's vocabulary ability. Some or all of the above-described processing in the analysis unit may be performed using, for example, AI, or may be performed without using AI. For example, the analysis unit can input data on words entered by the student into a generation AI and have the generation AI evaluate vocabulary ability.

[0034] The answer unit can generate an answer using text and images. For example, when a student asks, "What is a dog?", the answer unit generates an answer using text and images. For example, the answer unit provides a text description of dogs and displays images of dogs. Also, when a student asks, "What kind of dog is it?", the answer unit can provide a description of dog types and display images of each type. In this way, by using text and images, it is possible to provide an answer that is visually easy to understand. Some or all of the above-described processing in the answer unit may be performed using, for example, AI, or may be performed without using AI. For example, the answer unit can input the student's question into a generation AI and have the generation AI generate an answer.

[0035] The review unit can instruct a review to ensure that the learned content is memorized over a certain period of time. For example, after a student learns a new word, the review unit instructs the student to review the word after a certain period of time has passed. For example, the review unit instructs the student to review the word one week, one month, or three months later. The review unit can also instruct a review to ensure that the learned content is memorized over a long period of time. For example, the review unit instructs the student to review the word periodically. This allows the learning effect to be improved by reviewing the learned content to ensure that the learned content is memorized over a long period of time. Some or all of the above-described processing in the review unit may be performed using, for example, AI, or may be performed without using AI. For example, the review unit can input the timing of review into the generation AI and cause the generation AI to execute the review instruction.

[0036] The analysis unit can analyze the student's past learning history and select appropriate evaluation criteria. For example, the analysis unit can focus evaluation on areas in which the student was weak in the past. For example, the analysis unit can re-ask the student questions that the student got wrong in the past and evaluate their level of understanding. The analysis unit can also set more advanced evaluation criteria based on the student's areas of strength. For example, the analysis unit can ask the student questions in areas in which the student scored highly in the past and evaluate their level of understanding. The analysis unit can also select evaluation criteria of appropriate difficulty based on the student's past grades. For example, the analysis unit can analyze the student's past grades and set evaluation criteria based on those grades. This enables individually appropriate evaluation by selecting optimal evaluation criteria based on the student's past learning history. Some or all of the above-mentioned processing in the analysis unit can be performed using, for example, AI, or without AI. For example, the analysis unit can input the student's past learning history data into the generation AI and have the generation AI select the evaluation criteria.

[0037] The analysis unit can select a means for assessing comprehension depending on the student's input method. For example, if the student uses voice input, the analysis unit uses voice recognition technology to evaluate the student's level of comprehension. For example, if the student answers a question by voice, the analysis unit analyzes the voice data and evaluates the student's level of comprehension. Furthermore, if the student uses text input, the analysis unit can use natural language processing technology to evaluate the student's level of comprehension. For example, if the student answers a question by text, the analysis unit analyzes the text data and evaluates the student's level of comprehension. Furthermore, if the student selects an image, the analysis unit can use image recognition technology to evaluate the student's level of comprehension. For example, if the student selects an image, the analysis unit analyzes the image data and evaluates the student's level of comprehension. This allows for a more accurate assessment of the student's level of comprehension by selecting an assessment means depending on the student's input method. Some or all of the above-described processing in the analysis unit may be performed using AI, or may be performed without AI. For example, the analysis unit can input the student's input data into a generation AI and have the generation AI evaluate the student's level of comprehension.

[0038] The analysis unit can filter assessments based on the student's current learning status and areas of interest. For example, the analysis unit prioritizes assessment items related to the student's current learning area. For example, the analysis unit poses questions related to the subject or topic the student is currently studying and evaluates the student's level of understanding. The analysis unit can also select assessment items that interest the student based on the student's areas of interest. For example, the analysis unit poses questions related to a topic the student is interested in and evaluates the student's level of understanding. The analysis unit can also filter appropriate assessment items based on the student's learning progress. For example, the analysis unit analyzes the student's learning progress and poses questions based on that progress. This enables more appropriate learning support by performing assessments based on the student's learning status and areas of interest. Some or all of the above-described processing in the analysis unit may be performed using, or without, AI. For example, the analysis unit can input data on the student's learning status and areas of interest into the generation AI and have the generation AI perform assessment filtering.

[0039] The analysis unit can prioritize the application of relevant evaluation criteria based on the student's geographical location information. For example, if the student lives in a particular area, the analysis unit prioritizes evaluation criteria related to that area. For example, the analysis unit poses questions related to the culture and customs of that area and evaluates the student's level of comprehension. Furthermore, if the student attends a particular school, the analysis unit can prioritize evaluation criteria based on the school's curriculum. For example, the analysis unit poses questions in line with the school's curriculum and evaluates the student's level of comprehension. Furthermore, if the student has a particular cultural background, the analysis unit can prioritize evaluation criteria related to that culture. For example, the analysis unit poses questions related to that culture and evaluates the student's level of comprehension. In this way, by taking the geographical location information into consideration, evaluation criteria appropriate for the area can be applied. Some or all of the above-described processing in the analysis unit may be performed using, or without, AI. For example, the analysis unit can input the student's geographical location information into the generation AI and cause the generation AI to apply the evaluation criteria.

[0040] The analysis unit can analyze the student's social media activity and apply relevant evaluation criteria. For example, the analysis unit can apply evaluation criteria related to topics the student has shown interest in on social media. For example, the analysis unit can pose questions related to topics the student has interest in on social media and evaluate the student's level of understanding. The analysis unit can also analyze the student's social media posts and apply relevant evaluation criteria. For example, the analysis unit can pose questions related to content the student has posted on social media and evaluate the student's level of understanding. The analysis unit can also apply relevant evaluation criteria based on the activity of the student's friends on social media. For example, the analysis unit can pose questions related to topics the student's friends have interest in and evaluate the student's level of understanding. In this way, applying evaluation criteria based on social media activity enables more individually tailored evaluation. Some or all of the above-described processing in the analysis unit can be performed using, for example, AI, or without AI. For example, the analysis unit can input the student's social media activity data into a generation AI and cause the generation AI to apply the evaluation criteria.

[0041] The analysis unit can customize the evaluation method by reflecting the student's past feedback. The analysis unit, for example, adjusts the evaluation method based on feedback provided by the student in the past. For example, the analysis unit customizes the evaluation method by referring to the items and comments the student has previously evaluated. The analysis unit can also strengthen specific evaluation items based on the student's past feedback. For example, the analysis unit prioritizes evaluation of evaluation items that the student has previously considered important. The analysis unit can also customize the evaluation method by referring to the student's feedback. For example, the analysis unit adjusts the evaluation criteria based on feedback provided by the student in the past. In this way, the evaluation method can be individually customized by reflecting the past feedback. Some or all of the above-mentioned processing in the analysis unit may be performed using, for example, AI, or may be performed without using AI. For example, the analysis unit can input the student's past feedback data into the generation AI and cause the generation AI to customize the evaluation method.

[0042] The answering unit can adjust the level of detail of the answer based on the importance of the question. For example, the answering unit may provide a detailed answer to an important question. For example, the answering unit may provide an answer including a detailed explanation to a question directly related to a learning goal. The answering unit may also provide a concise answer to a general question. For example, the answering unit may provide a concise and clear answer to an everyday question. The answering unit may also evaluate the importance of the question and adjust the level of detail of the answer according to the student's learning progress. For example, the answering unit may analyze the student's learning progress and provide a detailed answer according to that progress. This enables an appropriate answer to be provided by adjusting the level of detail of the answer according to the question's importance. Some or all of the above-described processing in the answering unit may be performed using, or without, an AI. For example, the answering unit may input question importance data to the generating AI and cause the generating AI to adjust the level of detail of the answer.

[0043] The answering unit can apply different answering algorithms depending on the question category. For example, for science questions, the AI ​​applies a scientific algorithm to generate an answer. For example, the answering unit provides an answer based on scientific knowledge for science questions. For social studies questions, the AI ​​can also apply a historical algorithm to generate an answer. For example, the answering unit provides an answer based on historical knowledge for social studies questions. For math questions, the AI ​​can also apply a mathematical algorithm to generate an answer. For example, the answering unit provides an answer based on mathematical knowledge for math questions. This enables a more appropriate answer by applying an answering algorithm according to the question category. Some or all of the above-mentioned processing in the answering unit may be performed using AI, for example, or without AI. For example, the answering unit can input question category data into the generation AI and have the generation AI apply the answering algorithm.

[0044] The answering unit can improve the accuracy of the answers based on the student's past answer results. For example, the answering unit uses the AI ​​to provide highly accurate answers to similar questions based on questions that the student has answered correctly in the past. For example, the answering unit analyzes data on questions that the student has answered correctly in the past and provides an answer based on that data. The answering unit can also provide an answer that corrects an error based on questions that the student has answered incorrectly in the past. For example, the answering unit analyzes data on questions that the student has answered incorrectly in the past and provides an answer based on that data. The answering unit can also analyze the student's past answer history and generate an optimal answer. For example, the answering unit provides an optimal answer based on the student's past answer history. This allows the accuracy of the answers to be improved by referring to the past answer results. Some or all of the above-mentioned processing in the answering unit may be performed using, or without, AI. For example, the answering unit can input the student's past answer result data into the generation AI and cause the generation AI to improve the accuracy of the answers.

[0045] The answering unit can determine the priority of answers based on the time when the question was submitted. For example, the answering unit prioritizes answers to urgent questions. For example, the answering unit prioritizes answers to questions with high urgency, such as questions before end-of-term tests. The answering unit can also provide answers to general questions with normal priority. For example, the answering unit provides answers to everyday questions with normal priority. The answering unit can also evaluate the time when the question was submitted and determine the priority of answers based on the student's learning progress. For example, the answering unit analyzes the student's learning progress and provides answers with priority according to that progress. In this way, by determining the priority of answers based on the time when the question was submitted, questions with high urgency can be responded to quickly. Some or all of the above-mentioned processing in the answering unit may be performed using AI, for example, or may be performed without AI. For example, the answering unit can input question submission time data to the generating AI and have the generating AI determine the priority of answers.

[0046] The answering unit can adjust the order of answers based on the relevance of the questions. For example, the answering unit causes the AI ​​to prioritize answers to important questions. For example, the answering unit prioritizes answers to questions directly related to learning goals. The answering unit can also cause the AI ​​to provide answers in the normal order to general questions. For example, the answering unit provides answers to everyday questions in the normal order. The answering unit can also evaluate the relevance of questions and adjust the order of answers according to the student's learning progress. For example, the answering unit analyzes the student's learning progress and provides answers in an order according to that progress. In this way, by adjusting the order of answers based on the relevance of the questions, important questions can be given priority. Some or all of the above-mentioned processing in the answering unit may be performed using, or without, AI. For example, the answering unit can input question relevance data to the generating AI and cause the generating AI to adjust the order of answers.

[0047] The answering unit can adjust the use of technical terminology in the answer depending on the student's level of expertise. For example, for a beginner student, the AI ​​provides an answer using simple language. For example, for a beginner student, the answering unit provides an answer using simple language that avoids technical terminology. Also, for an intermediate student, the AI ​​can provide an answer using appropriate technical terminology. For example, for an intermediate student, the answering unit can provide an answer using appropriate technical terminology. Also, for an advanced student, the AI ​​can provide an answer using advanced technical terminology. For example, for an advanced student, the answering unit can provide an answer using advanced technical terminology. In this way, by adjusting the use of technical terminology in the answer depending on the student's level of expertise, an answer that is easy to understand can be provided. Some or all of the above-mentioned processing in the answering unit may be performed using AI, for example, or may be performed without using AI. For example, the answering unit can input student's expertise level data into the generating AI and cause the generating AI to use technical terminology in the answer.

[0048] The review unit can apply an optimal review algorithm based on past review data. For example, the review unit uses AI to apply an optimal review algorithm based on review methods that have been effective for students in the past. For example, the review unit analyzes data on review methods that have been effective for students in the past and applies a review algorithm based on that data. The review unit can also analyze students' past review data and suggest the most effective review method. For example, the review unit suggests the optimal review method based on the students' past review data. The review unit can also select an appropriate review algorithm based on the students' learning progress. For example, the review unit analyzes the students' learning progress and applies a review algorithm according to that progress. This enables effective review by applying an optimal review algorithm based on the past review data. Some or all of the above-mentioned processing in the review unit may be performed using AI, for example, or may be performed without using AI. For example, the review unit can input past review data into a generation AI and have the generation AI apply a review algorithm.

[0049] The review unit can optimize the timing of review by analyzing the student's learning history. For example, after a student learns a new word, the review unit instructs the student to review the word after a certain period of time has passed. For example, the review unit instructs the student to review the word one week, one month, or three months later. The review unit can also suggest optimal review timing based on the student's learning progress. For example, the review unit can analyze the student's learning progress and suggest review timing based on that progress. The review unit can also set effective review timing based on the student's past learning history. For example, the review unit can analyze the student's past learning history and set review timing based on that history. This enables effective review by optimizing the review timing based on the learning history. Some or all of the above-mentioned processing in the review unit may be performed using, for example, AI, or may be performed without AI. For example, the review unit can input the student's learning history data into a generation AI and cause the generation AI to optimize the review timing.

[0050] The review unit can improve the review method by reflecting the student's feedback. For example, the review unit adjusts the review method based on feedback provided by the student in the past. For example, the review unit improves the review method by referring to the student's previously evaluated review methods and comments. The review unit can also strengthen a specific review method based on the student's past feedback. For example, the review unit prioritizes the application of review methods that have been effective for the student in the past. The review unit can also customize the review method by referring to the student's feedback. For example, the review unit adjusts the review method based on the student's previously provided feedback. In this way, the review method can be individually improved by reflecting the student's feedback. Some or all of the above-mentioned processing in the review unit may be performed using, for example, AI, or may be performed without using AI. For example, the review unit can input the student's past feedback data into a generation AI and have the generation AI improve the review method.

[0051] The review unit can select the optimal review method based on the student's geographical location information. For example, if the student is at home, the AI ​​in the review unit can suggest review methods that can be done at home. For example, the review unit can suggest simple review methods that can be done at home. Also, if the student is at school, the AI ​​can suggest review methods that can be done in the classroom. For example, the review unit can suggest group learning or discussions that can be done in the classroom. Also, if the student is on the move, the AI ​​can suggest review methods that can be done on a mobile device. For example, the review unit can suggest short review methods that can be done while on the move. In this way, by taking the geographical location information into consideration, a review method appropriate for the area can be selected. Some or all of the above-mentioned processing in the review unit may be performed using AI, for example, or may be performed without using AI. For example, the review unit can input the student's geographical location information into the generation AI and have the generation AI select a review method.

[0052] The review unit can analyze a student's social media activity to suggest review methods. For example, the review unit uses AI to suggest related review methods based on the learning content shared by the student on social media. For example, the review unit suggests review methods related to the learning content shared by the student on social media. The review unit can also analyze a student's social media activity to suggest interesting review methods. For example, the review unit suggests review methods related to topics the student is interested in on social media. The review unit can also suggest collaborative review methods based on the activity of the student's friends on social media. For example, the review unit suggests group study that the student can do with their friends. In this way, suggesting review methods based on social media activity enables more interesting review. Some or all of the above-mentioned processing in the review unit may be performed using, for example, AI, or may be performed without using AI. For example, the review unit can input the student's social media activity data into a generation AI and have the generation AI execute the suggestion of review methods.

[0053] The review unit can customize the review method by reflecting the student's past feedback. The review unit, for example, adjusts the review method based on feedback provided by the student in the past. For example, the review unit customizes the review method by referring to the student's previously evaluated review methods and comments. The review unit can also strengthen a specific review method based on the student's past feedback. For example, the review unit prioritizes the application of review methods that have been effective for the student in the past. The review unit can also customize the review method by referring to the student's feedback. For example, the review unit adjusts the review method based on feedback provided by the student in the past. In this way, the review method can be individually customized by reflecting the past feedback. Some or all of the above-mentioned processing in the review unit may be performed using, for example, AI, or may be performed without using AI. For example, the review unit can input the student's past feedback data into a generation AI and have the generation AI customize the review method.

[0054] The system according to the embodiment is not limited to the above-described example, and various modifications are possible, for example, as follows.

[0055] The analysis unit can estimate a student's learning style and adjust the method of assessing comprehension based on the estimated learning style. For example, a student with a visual learning style can be provided with an assessment method that makes extensive use of images and videos. A student with an auditory learning style can be provided with an assessment method that uses audio or music. Furthermore, a student with a tactile learning style can be provided with an assessment method that uses an interactive touchscreen or physical teaching materials. This allows for more effective learning support by providing assessment methods that suit each student's learning style.

[0056] The answering section can adjust the difficulty of questions based on the student's learning progress. For example, for students whose learning progress is lagging, the system can start with basic questions and gradually increase the difficulty. It can also provide more advanced questions to students whose learning progress is fast. Furthermore, it can provide many questions specialized in that area to students who are weak in a particular subject. This makes it possible to provide questions according to the student's learning progress and provide learning support that is tailored to each individual student.

[0057] The review section can customize review content based on the student's learning goals. For example, for a student with a learning goal for a specific exam, it can provide review content related to that exam. Also, for a student who wants to master a specific skill, it can provide review content related to that skill. Furthermore, for a student with a long-term learning goal, it can provide step-by-step review content toward that goal. This makes it possible to provide effective learning support by providing review content that matches the student's learning goals.

[0058] The analysis unit can estimate a student's learning environment and adjust the method of assessing comprehension based on the estimated learning environment. For example, it can provide an assessment method that helps students who study in a quiet environment to improve their concentration. It can also provide an assessment method that can be completed in a short amount of time for students who study in a noisy environment. It can also provide an assessment method that uses a mobile device for students who study while on the move. This makes it possible to provide more effective learning support by providing an assessment method that suits the student's learning environment.

[0059] The analysis unit can propose future study plans based on the student's learning history. For example, it can propose a plan to focus on areas that the student was weak in in the past. It can also propose a study plan to further deepen areas in which the student is strong. It can also propose a balanced study plan. This makes it possible to provide effective learning support by proposing future study plans based on the student's learning history.

[0060] The processing flow of the first embodiment will be briefly explained below.

[0061] Step 1: The analysis unit analyzes the student's vocabulary or comprehension. For example, it evaluates the student's comprehension based on the text the student enters or the image they select. Specifically, if the student enters the word "dog," it evaluates whether they understand the meaning of that word, and if the student selects an image of a dog, it determines whether the image is correct. Furthermore, the analysis unit can also evaluate the student's vocabulary, for example, based on the number of words the student knows and how often they use them. Step 2: The answering unit answers the question using text and images based on the results of the analysis by the analyzing unit. For example, if a student asks "What is a dog?", the answering unit generates an answer using text and images. The answering unit can also continue answering questions until the student is satisfied. For example, if the student continues asking questions, the answering unit will provide appropriate answers each time. Step 3: The review section recommends appropriate review based on the answers provided by the answer section. For example, the review section recommends appropriate review based on Ebbinghaus's forgetting curve. Specifically, after a student learns a new word, the review section recommends that the student review the word after a certain period of time has passed. The review section can also recommend periodic reviews to help students retain the learned content for a long period of time.

[0062] (Example 2) A self-learning educational tool according to an embodiment of the present invention is a system for providing a non-competitive learning environment for students in the early grades of elementary school, taking into account differences in age. The self-learning educational tool utilizes multimodal functions to analyze each student's vocabulary and comprehension. Specifically, it allows students to ask questions until they are satisfied using text and images, preventing them from feeling like they are weak at a subject. Furthermore, appropriate review based on Ebbinghaus's forgetting curve helps students solidify their learning. This supports efficient learning tailored to each student. For example, the self-learning educational tool analyzes each student's vocabulary and comprehension. Based on the text and image selected by the student, an AI evaluates the student's comprehension. For example, if a student enters the word "dog," the AI ​​evaluates whether the student understands the meaning of the word. Furthermore, if a student selects an image of a dog, the AI ​​determines whether the image is correct. Next, the self-learning educational tool allows students to ask questions using text and images until they are satisfied. For example, if a student asks, "What is a dog?", the AI ​​responds using text and images. If the student continues to ask questions, the AI ​​provides appropriate answers each time. This allows students to progress through their studies at their own pace. Furthermore, the self-learning educational tool provides appropriate review based on Ebbinghaus's forgetting curve. For example, after a student learns a new word, the AI ​​instructs them to review that word after a certain period of time has passed. This allows students to retain the learned content for a long period of time. This allows the self-learning educational tool to support efficient learning tailored to each student. For example, students with low vocabulary skills can start with simple words and gradually increase the difficulty level. Also, students with high comprehension levels can be provided with more advanced content. This allows each student to progress through their studies at their own pace. This allows the self-learning educational tool to analyze students' vocabulary and comprehension levels and provide appropriate questions and reviews to support efficient learning. For example, students can progress through their studies at their own pace and retain the learned content without feeling uncomfortable. It also reduces the burden on teachers and provides learning support tailored to each student.

[0063] A self-study education tool according to an embodiment includes an analysis unit, an answering unit, and a reviewing unit. The analysis unit analyzes a student's vocabulary or comprehension. For example, the analysis unit evaluates the student's comprehension based on text entered by the student and an image selected by the student. For example, if a student enters the word "dog," the analysis unit evaluates whether the student understands the meaning of the word. Furthermore, if a student selects an image of a dog, the analysis unit can determine whether the image is correct. The analysis unit can also evaluate a student's vocabulary. For example, the analysis unit evaluates the student's vocabulary based on the number of words the student knows and how often they are used. The answering unit answers questions using text and images based on the results of the analysis by the analysis unit. For example, if a student asks, "What is a dog?", the answering unit generates an answer using text and images. The answering unit can also answer questions until the student is satisfied. For example, if the student continues to ask further questions, the answering unit provides an appropriate answer each time. The reviewing unit instructs the student on appropriate review based on the answers provided by the answering unit. For example, the review unit may instruct appropriate review based on Ebbinghaus's forgetting curve. For example, the review unit may instruct a student to review a new word after a certain period of time has passed since the student learned the word. The review unit may also instruct review to help the student retain the learning content for a long period of time. For example, the review unit may instruct the student to review the learning content periodically. As a result, the self-learning educational tool according to the embodiment can analyze the student's vocabulary and comprehension level and provide appropriate questions and reviews to support efficient learning. For example, the self-learning educational tool according to the embodiment can allow students to study at their own pace and solidify the learning content without feeling that they are weak at the material. Furthermore, the self-learning educational tool can reduce the burden on teachers and provide learning support appropriate for each student.

[0064] The analysis unit can evaluate the student's level of understanding based on the text entered or the image selected by the student. The analysis unit evaluates the level of understanding based on, for example, the text entered by the student. For example, if the student enters the word "dog," the analysis unit evaluates whether the student understands the meaning of the word. The analysis unit can also evaluate the level of understanding based on the image selected by the student. For example, if the student selects an image of a dog, the analysis unit determines whether the image is correct. This enables individually tailored learning support by evaluating the student's level of understanding based on the student's input. Some or all of the above-described processing in the analysis unit may be performed using, for example, AI, or may be performed without using AI. For example, the analysis unit can input the text entered or the image selected by the student into a generation AI and have the generation AI evaluate the student's level of understanding.

[0065] The answering unit can answer questions until the student reaches a certain standard. For example, if a student asks, "What is a dog?", the answering unit generates an answer using text and images. For example, the answering unit provides a text description of dogs and displays images of dogs. Furthermore, if the student continues to ask questions, the answering unit can provide appropriate answers each time. For example, if a student asks, "What kind of dog is it?", the answering unit describes dog types and displays images of each type. This allows the student to answer questions until they are satisfied, thereby deepening their understanding of the learning. Some or all of the above-described processing in the answering unit may be performed using, for example, AI, or may be performed without AI. For example, the answering unit can input the student's question into a generating AI and have the generating AI generate an answer.

[0066] The review unit can instruct appropriate review based on Ebbinghaus's forgetting curve. For example, after a student learns a new word, the review unit instructs the student to review the word after a certain period of time has passed. For example, the review unit instructs the student to review the word one week, one month, or three months later. The review unit can also instruct reviews to help the student memorize the learned content over a long period of time. For example, the review unit instructs the student to review the learned content periodically. In this way, review based on Ebbinghaus's forgetting curve can promote the retention of the learned content. Some or all of the above-described processing in the review unit may be performed using, for example, AI, or may be performed without AI. For example, the review unit can input review timing based on Ebbinghaus's forgetting curve into the generation AI and cause the generation AI to execute the review instructions.

[0067] The analysis unit can evaluate a student's vocabulary ability. The analysis unit evaluates vocabulary ability based on, for example, the number of words the student knows and the frequency of their use. For example, the analysis unit counts the number of words entered by the student and evaluates vocabulary ability based on that number. The analysis unit can also analyze the frequency of words used by the student and evaluate vocabulary ability based on that frequency. For example, the analysis unit compares words frequently used by the student with words used infrequently and evaluates vocabulary ability based on the results. This enables individually tailored learning support by evaluating the student's vocabulary ability. Some or all of the above-described processing in the analysis unit may be performed using, for example, AI, or may be performed without using AI. For example, the analysis unit can input data on words entered by the student into a generation AI and have the generation AI evaluate vocabulary ability.

[0068] The answer unit can generate an answer using text and images. For example, when a student asks, "What is a dog?", the answer unit generates an answer using text and images. For example, the answer unit provides a text description of dogs and displays images of dogs. Also, when a student asks, "What kind of dog is it?", the answer unit can provide a description of dog types and display images of each type. In this way, by using text and images, it is possible to provide an answer that is visually easy to understand. Some or all of the above-described processing in the answer unit may be performed using, for example, AI, or may be performed without using AI. For example, the answer unit can input the student's question into a generation AI and have the generation AI generate an answer.

[0069] The review unit can instruct a review to ensure that the learned content is memorized over a certain period of time. For example, after a student learns a new word, the review unit instructs the student to review the word after a certain period of time has passed. For example, the review unit instructs the student to review the word one week, one month, or three months later. The review unit can also instruct a review to ensure that the learned content is memorized over a long period of time. For example, the review unit instructs the student to review the word periodically. This allows the learning effect to be improved by reviewing the learned content to ensure that the learned content is memorized over a long period of time. Some or all of the above-described processing in the review unit may be performed using, for example, AI, or may be performed without using AI. For example, the review unit can input the timing of review into the generation AI and cause the generation AI to execute the review instruction.

[0070] The analysis unit can estimate a student's emotions and adjust the method for assessing comprehension based on the estimated student's emotions. For example, if a student feels anxious, the analysis unit can have the AI ​​evaluate the student's comprehension using gentle language to reduce stress. If a student is excited, the analysis unit can also have the AI ​​omit detailed explanations and evaluate the student's comprehension concisely. If a student is relaxed, the analysis unit can also have the AI ​​ask detailed questions to evaluate the student's comprehension in depth. This allows for more appropriate assessment by adjusting the method for assessing comprehension based on the student's emotions. Emotion estimation is achieved using an emotion estimation function, for example, an emotion engine or a generative AI. The generative AI can be a text generation AI (e.g., LLM) or a multimodal generation AI, but is not limited to such examples. Some or all of the above-described processing in the analysis unit can be performed using, for example, an AI, or without an AI. For example, the analysis unit can input student emotion data into the generative AI and have the generative AI adjust the evaluation method based on emotions.

[0071] The analysis unit can analyze the student's past learning history and select appropriate evaluation criteria. For example, the analysis unit can focus evaluation on areas in which the student was weak in the past. For example, the analysis unit can re-ask the student questions that the student got wrong in the past and evaluate their level of understanding. The analysis unit can also set more advanced evaluation criteria based on the student's areas of strength. For example, the analysis unit can ask the student questions in areas in which the student scored highly in the past and evaluate their level of understanding. The analysis unit can also select evaluation criteria of appropriate difficulty based on the student's past grades. For example, the analysis unit can analyze the student's past grades and set evaluation criteria based on those grades. This enables individually appropriate evaluation by selecting optimal evaluation criteria based on the student's past learning history. Some or all of the above-mentioned processing in the analysis unit can be performed using, for example, AI, or without AI. For example, the analysis unit can input the student's past learning history data into the generation AI and have the generation AI select the evaluation criteria.

[0072] The analysis unit can select a means for assessing comprehension depending on the student's input method. For example, if the student uses voice input, the analysis unit uses voice recognition technology to evaluate the student's level of comprehension. For example, if the student answers a question by voice, the analysis unit analyzes the voice data and evaluates the student's level of comprehension. Furthermore, if the student uses text input, the analysis unit can use natural language processing technology to evaluate the student's level of comprehension. For example, if the student answers a question by text, the analysis unit analyzes the text data and evaluates the student's level of comprehension. Furthermore, if the student selects an image, the analysis unit can use image recognition technology to evaluate the student's level of comprehension. For example, if the student selects an image, the analysis unit analyzes the image data and evaluates the student's level of comprehension. This allows for a more accurate assessment of the student's level of comprehension by selecting an assessment means depending on the student's input method. Some or all of the above-described processing in the analysis unit may be performed using AI, or may be performed without AI. For example, the analysis unit can input the student's input data into a generation AI and have the generation AI evaluate the student's level of comprehension.

[0073] The analysis unit can filter assessments based on the student's current learning status and areas of interest. For example, the analysis unit prioritizes assessment items related to the student's current learning area. For example, the analysis unit poses questions related to the subject or topic the student is currently studying and evaluates the student's level of understanding. The analysis unit can also select assessment items that interest the student based on the student's areas of interest. For example, the analysis unit poses questions related to a topic the student is interested in and evaluates the student's level of understanding. The analysis unit can also filter appropriate assessment items based on the student's learning progress. For example, the analysis unit analyzes the student's learning progress and poses questions based on that progress. This enables more appropriate learning support by performing assessments based on the student's learning status and areas of interest. Some or all of the above-described processing in the analysis unit may be performed using, or without, AI. For example, the analysis unit can input data on the student's learning status and areas of interest into the generation AI and have the generation AI perform assessment filtering.

[0074] The analysis unit can estimate the student's emotions and prioritize the evaluation results based on the estimated student's emotions. For example, if the student is feeling anxious, the analysis unit can cause the AI ​​to prioritize positive evaluation results. Furthermore, if the student is relaxed, the analysis unit can cause the AI ​​to prioritize detailed evaluation results. Furthermore, if the student is excited, the analysis unit can cause the AI ​​to prioritize concise evaluation results. This allows for more appropriate feedback by prioritizing the evaluation results according to the student's emotions. The emotion estimation is achieved using an emotion estimation function, such as an emotion engine or a generation AI. The generation AI can be, but is not limited to, a text generation AI (e.g., LLM) or a multimodal generation AI. Some or all of the above-described processing in the analysis unit can be performed using, for example, an AI, or without an AI. For example, the analysis unit can input the student's emotion data into the generation AI and have the generation AI determine the priorities of the evaluation results.

[0075] The analysis unit can prioritize the application of relevant evaluation criteria based on the student's geographical location information. For example, if the student lives in a particular area, the analysis unit prioritizes evaluation criteria related to that area. For example, the analysis unit poses questions related to the culture and customs of that area and evaluates the student's level of comprehension. Furthermore, if the student attends a particular school, the analysis unit can prioritize evaluation criteria based on the school's curriculum. For example, the analysis unit poses questions in line with the school's curriculum and evaluates the student's level of comprehension. Furthermore, if the student has a particular cultural background, the analysis unit can prioritize evaluation criteria related to that culture. For example, the analysis unit poses questions related to that culture and evaluates the student's level of comprehension. In this way, by taking the geographical location information into consideration, evaluation criteria appropriate for the area can be applied. Some or all of the above-described processing in the analysis unit may be performed using, or without, AI. For example, the analysis unit can input the student's geographical location information into the generation AI and cause the generation AI to apply the evaluation criteria.

[0076] The analysis unit can analyze the student's social media activity and apply relevant evaluation criteria. For example, the analysis unit can apply evaluation criteria related to topics the student has shown interest in on social media. For example, the analysis unit can pose questions related to topics the student has interest in on social media and evaluate the student's level of understanding. The analysis unit can also analyze the student's social media posts and apply relevant evaluation criteria. For example, the analysis unit can pose questions related to content the student has posted on social media and evaluate the student's level of understanding. The analysis unit can also apply relevant evaluation criteria based on the activity of the student's friends on social media. For example, the analysis unit can pose questions related to topics the student's friends have interest in and evaluate the student's level of understanding. In this way, applying evaluation criteria based on social media activity enables more individually tailored evaluation. Some or all of the above-described processing in the analysis unit can be performed using, for example, AI, or without AI. For example, the analysis unit can input the student's social media activity data into a generation AI and cause the generation AI to apply the evaluation criteria.

[0077] The analysis unit can customize the evaluation method by reflecting the student's past feedback. The analysis unit, for example, adjusts the evaluation method based on feedback provided by the student in the past. For example, the analysis unit customizes the evaluation method by referring to the items and comments the student has previously evaluated. The analysis unit can also strengthen specific evaluation items based on the student's past feedback. For example, the analysis unit prioritizes evaluation of evaluation items that the student has previously considered important. The analysis unit can also customize the evaluation method by referring to the student's feedback. For example, the analysis unit adjusts the evaluation criteria based on feedback provided by the student in the past. In this way, the evaluation method can be individually customized by reflecting the past feedback. Some or all of the above-mentioned processing in the analysis unit may be performed using, for example, AI, or may be performed without using AI. For example, the analysis unit can input the student's past feedback data into the generation AI and cause the generation AI to customize the evaluation method.

[0078] The answering unit can estimate the student's emotions and adjust the way the answer is expressed based on the estimated student's emotions. For example, if the student is feeling anxious, the AI ​​in the answering unit can provide an answer using gentle language. If the student is excited, the AI ​​in the answering unit can also provide a concise and clear answer. If the student is relaxed, the AI ​​in the answering unit can also provide an answer with detailed explanations. This allows for adjusting the way the answer is expressed based on the student's emotions, enabling more appropriate answers. Emotion estimation is achieved using an emotion estimation function, for example, using an emotion engine or generation AI. The generation AI can be a text generation AI (e.g., LLM) or a multimodal generation AI, but is not limited to such examples. Some or all of the above-mentioned processing in the answering unit can be performed using AI, for example, or without AI. For example, the answering unit can input the student's emotion data into the generation AI and have the generation AI adjust the way the answer is expressed.

[0079] The answering unit can adjust the level of detail of the answer based on the importance of the question. For example, the answering unit may provide a detailed answer to an important question. For example, the answering unit may provide an answer including a detailed explanation to a question directly related to a learning goal. The answering unit may also provide a concise answer to a general question. For example, the answering unit may provide a concise and clear answer to an everyday question. The answering unit may also evaluate the importance of the question and adjust the level of detail of the answer according to the student's learning progress. For example, the answering unit may analyze the student's learning progress and provide a detailed answer according to that progress. This enables an appropriate answer to be provided by adjusting the level of detail of the answer according to the question's importance. Some or all of the above-described processing in the answering unit may be performed using, or without, an AI. For example, the answering unit may input question importance data to the generating AI and cause the generating AI to adjust the level of detail of the answer.

[0080] The answering unit can apply different answering algorithms depending on the question category. For example, for science questions, the AI ​​applies a scientific algorithm to generate an answer. For example, the answering unit provides an answer based on scientific knowledge for science questions. For social studies questions, the AI ​​can also apply a historical algorithm to generate an answer. For example, the answering unit provides an answer based on historical knowledge for social studies questions. For math questions, the AI ​​can also apply a mathematical algorithm to generate an answer. For example, the answering unit provides an answer based on mathematical knowledge for math questions. This enables a more appropriate answer by applying an answering algorithm according to the question category. Some or all of the above-mentioned processing in the answering unit may be performed using AI, for example, or without AI. For example, the answering unit can input question category data into the generation AI and have the generation AI apply the answering algorithm.

[0081] The answering unit can improve the accuracy of the answers based on the student's past answer results. For example, the answering unit uses the AI ​​to provide highly accurate answers to similar questions based on questions that the student has answered correctly in the past. For example, the answering unit analyzes data on questions that the student has answered correctly in the past and provides an answer based on that data. The answering unit can also provide an answer that corrects an error based on questions that the student has answered incorrectly in the past. For example, the answering unit analyzes data on questions that the student has answered incorrectly in the past and provides an answer based on that data. The answering unit can also analyze the student's past answer history and generate an optimal answer. For example, the answering unit provides an optimal answer based on the student's past answer history. This allows the accuracy of the answers to be improved by referring to the past answer results. Some or all of the above-mentioned processing in the answering unit may be performed using, or without, AI. For example, the answering unit can input the student's past answer result data into the generation AI and cause the generation AI to improve the accuracy of the answers.

[0082] The answering unit can estimate the student's emotions and adjust the length of the answer based on the estimated student's emotions. For example, if the student is feeling anxious, the AI ​​in the answering unit can provide a short, to-the-point answer. Alternatively, if the student is relaxed, the AI ​​in the answering unit can provide a longer answer with detailed explanations. Alternatively, if the student is excited, the AI ​​in the answering unit can provide a concise, clear answer. This allows for more appropriate answers by adjusting the length of the answer according to the student's emotions. The emotion estimation is achieved using an emotion estimation function, for example, an emotion engine or a generation AI. The generation AI can be, but is not limited to, a text generation AI (e.g., LLM) or a multimodal generation AI. Some or all of the above-described processing in the answering unit can be performed using, for example, an AI, or without an AI. For example, the answering unit can input the student's emotion data into the generation AI and have the generation AI adjust the length of the answer.

[0083] The answering unit can determine the priority of answers based on the time when the question was submitted. For example, the answering unit prioritizes answers to urgent questions. For example, the answering unit prioritizes answers to questions with high urgency, such as questions before end-of-term tests. The answering unit can also provide answers to general questions with normal priority. For example, the answering unit provides answers to everyday questions with normal priority. The answering unit can also evaluate the time when the question was submitted and determine the priority of answers based on the student's learning progress. For example, the answering unit analyzes the student's learning progress and provides answers with priority according to that progress. In this way, by determining the priority of answers based on the time when the question was submitted, questions with high urgency can be responded to quickly. Some or all of the above-mentioned processing in the answering unit may be performed using AI, for example, or may be performed without AI. For example, the answering unit can input question submission time data to the generating AI and have the generating AI determine the priority of answers.

[0084] The answering unit can adjust the order of answers based on the relevance of the questions. For example, the answering unit causes the AI ​​to prioritize answers to important questions. For example, the answering unit prioritizes answers to questions directly related to learning goals. The answering unit can also cause the AI ​​to provide answers in the normal order to general questions. For example, the answering unit provides answers to everyday questions in the normal order. The answering unit can also evaluate the relevance of questions and adjust the order of answers according to the student's learning progress. For example, the answering unit analyzes the student's learning progress and provides answers in an order according to that progress. In this way, by adjusting the order of answers based on the relevance of the questions, important questions can be given priority. Some or all of the above-mentioned processing in the answering unit may be performed using, or without, AI. For example, the answering unit can input question relevance data to the generating AI and cause the generating AI to adjust the order of answers.

[0085] The answering unit can adjust the use of technical terminology in the answer depending on the student's level of expertise. For example, for a beginner student, the AI ​​provides an answer using simple language. For example, for a beginner student, the answering unit provides an answer using simple language that avoids technical terminology. Also, for an intermediate student, the AI ​​can provide an answer using appropriate technical terminology. For example, for an intermediate student, the answering unit can provide an answer using appropriate technical terminology. Also, for an advanced student, the AI ​​can provide an answer using advanced technical terminology. For example, for an advanced student, the answering unit can provide an answer using advanced technical terminology. In this way, by adjusting the use of technical terminology in the answer depending on the student's level of expertise, an answer that is easy to understand can be provided. Some or all of the above-mentioned processing in the answering unit may be performed using AI, for example, or may be performed without using AI. For example, the answering unit can input student's expertise level data into the generating AI and cause the generating AI to use technical terminology in the answer.

[0086] The review unit can estimate a student's emotions and adjust the review instruction method based on the estimated student's emotions. For example, if a student is feeling anxious, the AI ​​in the review unit can provide review instructions using gentle language. If a student is excited, the AI ​​in the review unit can provide concise and clear review instructions. If a student is relaxed, the AI ​​in the review unit can provide review instructions with detailed explanations. This allows for more effective review by adjusting the review instruction method according to the student's emotions. Emotion estimation is achieved using an emotion estimation function, for example, an emotion engine or a generation AI. The generation AI can be a text generation AI (e.g., LLM) or a multimodal generation AI, but is not limited to such examples. Some or all of the above-mentioned processing in the review unit can be performed using, for example, an AI, or without an AI. For example, the review unit can input student emotion data into the generation AI and have the generation AI adjust the review instruction method.

[0087] The review unit can apply an optimal review algorithm based on past review data. For example, the review unit uses AI to apply an optimal review algorithm based on review methods that have been effective for students in the past. For example, the review unit analyzes data on review methods that have been effective for students in the past and applies a review algorithm based on that data. The review unit can also analyze students' past review data and suggest the most effective review method. For example, the review unit suggests the optimal review method based on the students' past review data. The review unit can also select an appropriate review algorithm based on the students' learning progress. For example, the review unit analyzes the students' learning progress and applies a review algorithm according to that progress. This enables effective review by applying an optimal review algorithm based on the past review data. Some or all of the above-mentioned processing in the review unit may be performed using AI, for example, or may be performed without using AI. For example, the review unit can input past review data into a generation AI and have the generation AI apply a review algorithm.

[0088] The review unit can optimize the timing of review by analyzing the student's learning history. For example, after a student learns a new word, the review unit instructs the student to review the word after a certain period of time has passed. For example, the review unit instructs the student to review the word one week, one month, or three months later. The review unit can also suggest optimal review timing based on the student's learning progress. For example, the review unit can analyze the student's learning progress and suggest review timing based on that progress. The review unit can also set effective review timing based on the student's past learning history. For example, the review unit can analyze the student's past learning history and set review timing based on that history. This enables effective review by optimizing the review timing based on the learning history. Some or all of the above-mentioned processing in the review unit may be performed using, for example, AI, or may be performed without AI. For example, the review unit can input the student's learning history data into a generation AI and cause the generation AI to optimize the review timing.

[0089] The review unit can improve the review method by reflecting the student's feedback. For example, the review unit adjusts the review method based on feedback provided by the student in the past. For example, the review unit improves the review method by referring to the student's previously evaluated review methods and comments. The review unit can also strengthen a specific review method based on the student's past feedback. For example, the review unit prioritizes the application of review methods that have been effective for the student in the past. The review unit can also customize the review method by referring to the student's feedback. For example, the review unit adjusts the review method based on the student's previously provided feedback. In this way, the review method can be individually improved by reflecting the student's feedback. Some or all of the above-mentioned processing in the review unit may be performed using, for example, AI, or may be performed without using AI. For example, the review unit can input the student's past feedback data into a generation AI and have the generation AI improve the review method.

[0090] The review unit can estimate the student's emotions and determine review priorities based on the estimated student's emotions. For example, if the student is feeling anxious, the AI ​​in the review unit can prioritize positive review content. Furthermore, if the student is relaxed, the AI ​​in the review unit can prioritize detailed review content. Furthermore, if the student is excited, the AI ​​in the review unit can prioritize concise review content. This enables more effective review by determining review priorities based on the student's emotions. The emotion estimation is achieved using an emotion estimation function, for example, an emotion engine or a generation AI. The generation AI can be, but is not limited to, a text generation AI (e.g., LLM) or a multimodal generation AI. Some or all of the above-described processing in the review unit can be performed using, for example, an AI, or without an AI. For example, the review unit can input the student's emotion data into the generation AI and have the generation AI determine the review priorities.

[0091] The review unit can select the optimal review method based on the student's geographical location information. For example, if the student is at home, the AI ​​in the review unit can suggest review methods that can be done at home. For example, the review unit can suggest simple review methods that can be done at home. Also, if the student is at school, the AI ​​can suggest review methods that can be done in the classroom. For example, the review unit can suggest group learning or discussions that can be done in the classroom. Also, if the student is on the move, the AI ​​can suggest review methods that can be done on a mobile device. For example, the review unit can suggest short review methods that can be done while on the move. In this way, by taking the geographical location information into consideration, a review method appropriate for the area can be selected. Some or all of the above-mentioned processing in the review unit may be performed using AI, for example, or may be performed without using AI. For example, the review unit can input the student's geographical location information into the generation AI and have the generation AI select a review method.

[0092] The review unit can analyze a student's social media activity to suggest review methods. For example, the review unit uses AI to suggest related review methods based on the learning content shared by the student on social media. For example, the review unit suggests review methods related to the learning content shared by the student on social media. The review unit can also analyze a student's social media activity to suggest interesting review methods. For example, the review unit suggests review methods related to topics the student is interested in on social media. The review unit can also suggest collaborative review methods based on the activity of the student's friends on social media. For example, the review unit suggests group study that the student can do with their friends. In this way, suggesting review methods based on social media activity enables more interesting review. Some or all of the above-mentioned processing in the review unit may be performed using, for example, AI, or may be performed without using AI. For example, the review unit can input the student's social media activity data into a generation AI and have the generation AI execute the suggestion of review methods.

[0093] The review unit can customize the review method by reflecting the student's past feedback. The review unit, for example, adjusts the review method based on feedback provided by the student in the past. For example, the review unit customizes the review method by referring to the student's previously evaluated review methods and comments. The review unit can also strengthen a specific review method based on the student's past feedback. For example, the review unit prioritizes the application of review methods that have been effective for the student in the past. The review unit can also customize the review method by referring to the student's feedback. For example, the review unit adjusts the review method based on feedback provided by the student in the past. In this way, the review method can be individually customized by reflecting the past feedback. Some or all of the above-mentioned processing in the review unit may be performed using, for example, AI, or may be performed without using AI. For example, the review unit can input the student's past feedback data into a generation AI and have the generation AI customize the review method. === Hard Collateral 1-1 === Each of the multiple elements including the above-mentioned analysis unit, answering unit, and review unit is realized, for example, by at least one of the smart device 14 and the data processing device 12. For example, the analysis unit acquires student input using the camera 42 and microphone 38B of the smart device 14, and evaluates the student's vocabulary and comprehension level using the control unit 46A. The answering unit is realized, for example, by the specific processing unit 290 of the data processing device 12, and answers the student's questions using text and images. The review unit is realized, for example, by the specific processing unit 290 of the data processing device 12, and instructs appropriate review based on the Ebbinghaus forgetting curve. === Hard Collateral 1-2 === Each of the multiple elements, including the above-mentioned analysis unit, answering unit, and review unit, is realized, for example, by at least one of the smart glasses 214 and the data processing device 12. For example, the analysis unit acquires student input using the camera 42 and microphone 238 of the smart glasses 214, and evaluates the student's vocabulary and comprehension level using the control unit 46A. The answering unit is realized, for example, by the specific processing unit 290 of the data processing device 12, and answers the student's questions using text and images. The review unit is realized, for example, by the specific processing unit 290 of the data processing device 12, and instructs appropriate review based on the Ebbinghaus forgetting curve. === Hard Collateral 1-3 === Each of the multiple elements including the above-mentioned analysis unit, answering unit, and review unit is realized, for example, by at least one of the headset-type terminal 314 and the data processing device 12. For example, the analysis unit acquires student input using the camera 42 and microphone 238 of the headset-type terminal 314, and evaluates the student's vocabulary and comprehension level using the control unit 46A. The answering unit is realized, for example, by the specific processing unit 290 of the data processing device 12, and answers the student's questions using text and images. The review unit is realized, for example, by the specific processing unit 290 of the data processing device 12, and instructs appropriate review based on the Ebbinghaus forgetting curve. === Hard Collateral 1-4 === Each of the multiple elements including the above-mentioned analysis unit, answering unit, and review unit is realized, for example, by at least one of the robot 414 and the data processing device 12. For example, the analysis unit obtains input from the student using the camera 42 or microphone 238 of the robot 414, and evaluates the student's vocabulary and comprehension level using the control unit 46A. The answering unit is realized, for example, by the specific processing unit 290 of the data processing device 12, and answers the student's questions using text and images. The review unit is realized, for example, by the specific processing unit 290 of the data processing device 12, and instructs appropriate review based on the Ebbinghaus forgetting curve.

[0094] The system according to the embodiment is not limited to the above-described example, and various modifications are possible, for example, as follows.

[0095] The analysis unit can estimate a student's learning style and adjust the method of assessing comprehension based on the estimated learning style. For example, a student with a visual learning style can be provided with an assessment method that makes extensive use of images and videos. A student with an auditory learning style can be provided with an assessment method that uses audio or music. Furthermore, a student with a tactile learning style can be provided with an assessment method that uses an interactive touchscreen or physical teaching materials. This allows for more effective learning support by providing assessment methods that suit each student's learning style.

[0096] The answering section can adjust the difficulty of questions based on the student's learning progress. For example, for students whose learning progress is lagging, the system can start with basic questions and gradually increase the difficulty. It can also provide more advanced questions to students whose learning progress is fast. Furthermore, it can provide many questions specialized in that area to students who are weak in a particular subject. This makes it possible to provide questions according to the student's learning progress and provide learning support that is tailored to each individual student.

[0097] The review section can customize review content based on the student's learning goals. For example, for a student with a learning goal for a specific exam, it can provide review content related to that exam. Also, for a student who wants to master a specific skill, it can provide review content related to that skill. Furthermore, for a student with a long-term learning goal, it can provide step-by-step review content toward that goal. This makes it possible to provide effective learning support by providing review content that matches the student's learning goals.

[0098] The analysis unit can estimate a student's learning environment and adjust the method of assessing comprehension based on the estimated learning environment. For example, it can provide an assessment method that helps students who study in a quiet environment to improve their concentration. It can also provide an assessment method that can be completed in a short amount of time for students who study in a noisy environment. It can also provide an assessment method that uses a mobile device for students who study while on the move. This makes it possible to provide more effective learning support by providing an assessment method that suits the student's learning environment.

[0099] The answering part can estimate the student's emotions and adjust the timing of the answer based on the estimated student's emotions. For example, if a student is feeling anxious, the AI ​​can provide a quick answer to reassure them. If the student is relaxed, the AI ​​can provide a slow, detailed answer. Furthermore, if the student is excited, the AI ​​can provide a concise and clear answer. This allows for more appropriate answers by adjusting the timing of the answer according to the student's emotions.

[0100] The review department can estimate a student's emotions and adjust the frequency of review based on the estimated student emotions. For example, if a student feels anxious, the AI ​​can reassure them by instructing them to review frequently. If a student feels relaxed, the AI ​​can also instruct them to review at a moderate frequency. Furthermore, if a student feels excited, the AI ​​can instruct them to review for a shorter period of time. This allows for more effective review by adjusting the frequency of review according to the student's emotions.

[0101] The analysis unit can estimate a student's emotions and adjust the way learning content is presented based on the estimated student's emotions. For example, if a student is feeling anxious, the AI ​​can present learning content in gentle language. If a student is relaxed, the AI ​​can present learning content with detailed explanations. Furthermore, if a student is excited, the AI ​​can present learning content in a concise and clear manner. This allows for more effective learning support by adjusting the way learning content is presented according to the student's emotions.

[0102] The answering part can estimate the student's emotions and adjust the format of the answer based on the estimated student's emotions. For example, if the student is feeling anxious, the AI ​​can provide an answer in a simple and easy-to-understand format. If the student is relaxed, the AI ​​can provide an answer in a format that includes detailed information. Furthermore, if the student is excited, the AI ​​can provide an answer in a visually appealing format. This allows for more appropriate answers to be provided by adjusting the format of the answer according to the student's emotions.

[0103] The review module can estimate a student's emotions and adjust the review content based on the estimated student emotions. For example, if a student is feeling anxious, the AI ​​can provide a review with positive content. If a student is relaxed, the AI ​​can provide a review with detailed content. Furthermore, if a student is excited, the AI ​​can provide a review with concise and clear content. This allows for more effective review by adjusting the review content according to the student's emotions.

[0104] The analysis unit can propose future study plans based on the student's learning history. For example, it can propose a plan to focus on areas that the student was weak in in the past. It can also propose a study plan to further deepen areas in which the student is strong. It can also propose a balanced study plan. This makes it possible to provide effective learning support by proposing future study plans based on the student's learning history.

[0105] The processing flow of the second embodiment will be briefly explained below.

[0106] Step 1: The analysis unit analyzes the student's vocabulary or comprehension. For example, it evaluates the student's comprehension based on the text the student enters or the image they select. Specifically, if the student enters the word "dog," it evaluates whether they understand the meaning of that word, and if the student selects an image of a dog, it determines whether the image is correct. Furthermore, the analysis unit can also evaluate the student's vocabulary, for example, based on the number of words the student knows and how often they use them. Step 2: The answering unit answers the question using text and images based on the results of the analysis by the analyzing unit. For example, if a student asks "What is a dog?", the answering unit generates an answer using text and images. The answering unit can also continue answering questions until the student is satisfied. For example, if the student continues asking questions, the answering unit will provide appropriate answers each time. Step 3: The review section recommends appropriate review based on the answers provided by the answer section. For example, the review section recommends appropriate review based on Ebbinghaus's forgetting curve. Specifically, after a student learns a new word, the review section recommends that the student review the word after a certain period of time has passed. The review section can also recommend periodic reviews to help students retain the learned content for a long period of time.

[0107] 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.

[0108] 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.

[0109] 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.

[0110] The correspondence between each part and the device or control part is not limited to the example described above, and various modifications are possible.

[0111] [Second embodiment] FIG. 3 shows an example of the configuration of a data processing system 210 according to the second embodiment.

[0112] 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.

[0113] 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.

[0114] 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.

[0115] 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.

[0116] 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).

[0117] 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.

[0118] 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.

[0119] 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.

[0120] 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.

[0121] 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.

[0122] 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.

[0123] 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.

[0124] 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 AI 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.

[0125] 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.

[0126] The correspondence between each part and the device or control part is not limited to the example described above, and various modifications are possible.

[0127] [Third embodiment] FIG. 5 shows an example of the configuration of a data processing system 310 according to the third embodiment.

[0128] 5, the data processing system 310 includes the data processing device 12 and a headset terminal 314. An example of the data processing device 12 is a server.

[0129] 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.

[0130] 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.

[0131] 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.

[0132] 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).

[0133] 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.

[0134] 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.

[0135] 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.

[0136] 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.

[0137] 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.

[0138] 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.

[0139] 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.

[0140] 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 AI 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.

[0141] 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.

[0142] The correspondence between each part and the device or control part is not limited to the example described above, and various modifications are possible.

[0143] [Fourth embodiment] FIG. 7 shows an example of the configuration of a data processing system 410 according to the fourth embodiment.

[0144] 7, a data processing system 410 includes a data processing device 12 and a robot 414. An example of the data processing device 12 is a server.

[0145] 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.

[0146] 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.

[0147] 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.

[0148] 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).

[0149] 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.

[0150] 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.

[0151] 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.

[0152] 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.

[0153] 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.

[0154] 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.

[0155] 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.

[0156] 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.

[0157] 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 AI 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.

[0158] 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.

[0159] The correspondence between each part and the device or control part is not limited to the example described above, and various modifications are possible.

[0160] 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.

[0161] 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.

[0162] 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.

[0163] 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).

[0164] 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 "reaction" domain, where sensation is dominant. The right half of the emotion map lists emotions belonging to the "situation" domain, where situational awareness is dominant.

[0165] 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."

[0166] 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.

[0167] 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.

[0168] 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.

[0169] 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.

[0170] 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.

[0171] 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.

[0172] 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.

[0173] 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.

[0174] 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.

[0175] 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.

[0176] 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.

[0177] 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.

[0178] [Explanation of symbols]

[0179] 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 system comprising: an analysis unit that analyzes a student's vocabulary or level of understanding; an answering unit that answers questions using text and images based on the results of the analysis by the analysis unit; and a review unit that instructs appropriate review based on the answers provided by the answering unit.

2. The system according to claim 1 , wherein the analysis unit evaluates the student's level of understanding based on text entered by the student or an image selected by the student.

3. 2. The system of claim 1, wherein the answering section answers questions until the student reaches a certain standard.

4. The review section Providing appropriate review instructions based on Ebbinghaus's forgetting curve The system of claim 1 .

5. The analysis unit Assessing students' vocabulary The system of claim 1 .

6. The answering section Generate answers using text and images The system of claim 1 .

7. 2. The system according to claim 1, wherein the review section instructs review to memorize the learned content for a certain period of time.

8. The analysis unit Estimate student emotions and adjust comprehension assessment methods based on the estimated student emotions The system of claim 1 .

Images