system

Abstract

The system according to the embodiment aims to detect areas where a learner is weak and to provide appropriate compensation. [Solution] The system according to the embodiment includes a reception unit, a generation unit, a scoring unit, an explanation unit, a detection unit, a completion unit, and a simplification unit. The reception unit accepts settings for the subject or range of study and the grade level. The generation unit automatically generates questions based on the settings accepted by the reception unit. The scoring unit scores the user's answers to the questions generated by the generation unit. The explanation unit provides explanations based on the results of the scoring by the scoring unit. The detection unit detects weak areas based on the explanation results obtained by the explanation unit. The completion unit generates questions to complete the weak areas detected by the detection unit. The simplification unit simplifies the questions generated by the completion unit according to the user's level of understanding.

Description

[Technical Field]

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

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

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

[0004] Conventional technology has had the problem of making it difficult to efficiently detect areas where learners are weak and provide appropriate compensation.

[0005] The system according to the embodiment aims to detect areas where a learner is weak and to provide appropriate compensation. [Means for solving the problem]

[0006] The system according to the embodiment includes a reception unit, a generation unit, a scoring unit, an explanation unit, a detection unit, a completion unit, and an simplification unit. The reception unit accepts settings for the subject or range of study and the grade level. The generation unit automatically generates questions based on the settings accepted by the reception unit. The scoring unit scores the user's answers to the questions generated by the generation unit. The explanation unit provides explanations based on the results of scoring by the scoring unit. The detection unit detects weak areas based on the explanation results obtained by the explanation unit. The completion unit generates questions to complete the weak areas detected by the detection unit. The simplification unit simplifies the questions generated by the completion unit according to the user's level of understanding. [Effects of the Invention]

[0007] The system according to the embodiment can detect areas where a learner is weak and provide appropriate compensation. [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 learning support system according to an embodiment of the present invention automatically generates questions based on the user's input, such as the subject, desired study area, and grade level. The system then grades and provides explanations based on the user's answers. The learning support system also detects weak areas based on the user's answers and customizes the questions by providing supplementary questions or simplifying the questions to make them easier to understand. For example, when a user inputs the user's input, such as the subject, desired study area, and grade level, the system automatically generates questions based on the input. The generated questions are presented to the user, and the user answers the questions. The system grades the answers and provides explanations. The explanations include the reason for correct answers and a detailed explanation of the mistake if the answer is incorrect. Furthermore, the system analyzes the user's answers to detect weak areas. For example, if the user makes many mistakes on a particular question, it determines that the user is weak in that area. Once a weak area is detected, the system generates questions to supplement the area. For example, if the user lacks understanding of a particular concept, it generates supplementary questions related to that concept. The system also simplifies questions based on the user's level of understanding. For example, if the user is struggling with a difficult question, it presents an easier version of that question. This allows the user to deepen their understanding step by step. In this way, the system supports the user's learning and allows them to progress through the learning efficiently. This allows the learning support system to efficiently support the user's learning, complement weak areas, and provide questions according to the user's level of understanding.

[0029] A learning assistance system according to an embodiment includes a receiving unit, a generating unit, a scoring unit, an explanation unit, a detection unit, a completion unit, and a simplification unit. The receiving unit provides an interface for a user to set a subject, a desired range of study, a grade level, and the like. For example, the receiving unit may provide a drop-down menu or checkboxes for a user to select a specific subject or grade level. The receiving unit may also provide a text input field for a user to specify in detail the range of study the user wishes to perform. The generating unit automatically generates questions based on the settings received by the receiving unit. For example, the generating unit may execute an algorithm to generate questions based on a specific subject or grade level. The generating unit may generate, for example, mathematics questions for an eighth-grade level student. The generating unit may also provide an interface for presenting the generated questions to the user. The scoring unit scores a user's answers to the questions generated by the generating unit. For example, the scoring unit executes an algorithm to determine whether the user's answers are correct. For example, the scoring unit may award points if the user's answers are correct and deduct points if the user's answers are incorrect. The scoring unit can also award partial points. The explanation unit provides explanations based on the results scored by the scoring unit. For example, the explanation unit executes an algorithm that explains the reason for a correct answer and explains the mistake for an incorrect answer. The explanation unit, for example, explains the correct solution and theoretical background for a question that the user got wrong. The explanation unit can also provide explanations in text or video format. The detection unit detects weak areas based on the explanation results obtained by the explanation unit. For example, the detection unit executes an algorithm that determines that a specific area is weak if the user makes many mistakes on that question. The detection unit identifies weak areas by analyzing, for example, the user's error rate and answer time. The completion unit generates questions to complete the weak areas detected by the detection unit. For example, the completion unit executes an algorithm that generates completion questions related to a specific concept. The completion unit generates basic and applied questions for concepts that the user does not fully understand. The completion unit can also provide an interface for presenting the generated completion questions to the user.The simplification unit simplifies the problems generated by the completion unit according to the user's level of understanding. For example, if the user is struggling with a difficult problem, the simplification unit executes an algorithm to simplify the problem and present it to the user. The simplification unit, for example, adjusts the difficulty of the problem or provides hints. The simplification unit can also change the format of the problem according to the user's level of understanding. This allows the learning assistance system according to the embodiment to efficiently support the user's learning, complement weak areas, and provide problems according to the user's level of understanding.

[0030] The generation unit can generate questions based on a specific subject or grade range. For example, the generation unit executes an algorithm that generates questions based on a specific subject or grade range. For example, the generation unit can generate mathematics questions for an eighth-grade student. The generation unit can also provide an interface for presenting the generated questions to the user. The generation unit can generate questions of an appropriate level of difficulty based on a subject or grade range set by the user. For example, the generation unit can generate questions ranging from basic to applied questions based on the range set by the user. The generation unit can also diversify the format of the generated questions. For example, the generation unit can generate questions in various formats, such as multiple-choice questions, essay questions, and practical questions. This allows the generation unit to generate questions appropriate for a specific subject or grade.

[0031] The scoring unit can determine whether the user's answer is correct. The scoring unit, for example, executes an algorithm to determine whether the user's answer is correct. For example, the scoring unit awards points when the user's answer is correct, and deducts points when the user's answer is incorrect. The scoring unit can also award partial points. For example, the scoring unit executes an algorithm to award partial points when the user's answer is partially correct. For example, the scoring unit can award partial points when the user's answer is close to the correct answer. The scoring unit can also award full points when the user's answer is completely correct. In this way, the scoring unit can determine whether the user's answer is correct or incorrect.

[0032] The explanation unit can explain the reason for the correct answer if the answer is correct, and what is wrong if the answer is incorrect. For example, the explanation unit executes an algorithm that explains the reason for the correct answer if the answer is correct, and what is wrong if the answer is incorrect. For example, the explanation unit explains the correct solution and the theoretical background for a problem that the user got wrong. The explanation unit can also provide the explanation in text format or video format. For example, the explanation unit can provide a detailed explanation in text format for a problem that the user got wrong. The explanation unit can also provide a visual explanation in video format for a problem that the user got wrong. This allows the explanation unit to understand the reason for the correct answer and the cause of the error.

[0033] The detection unit can determine that a user is weak in a particular area if mistakes are frequently made on a particular problem. For example, the detection unit executes an algorithm that determines that a user is weak in a particular area if mistakes are frequently made on a particular problem. For example, the detection unit analyzes the user's error rate and answer time to identify the weak area. For example, if a user frequently makes mistakes on a particular problem, the detection unit can determine that the user is weak in an area related to that problem. Furthermore, the detection unit can also determine that the user is weak in an area related to that problem if the user takes a long time to answer. This allows the detection unit to accurately detect the user's weak areas.

[0034] The completion unit can generate completion questions related to a specific concept. For example, the completion unit executes an algorithm that generates completion questions related to a specific concept. For example, the completion unit generates basic questions and application questions for a concept that the user lacks understanding of. The completion unit can also provide an interface for presenting the generated completion questions to the user. For example, if the user lacks understanding of a specific concept, the completion unit can generate basic questions related to the concept. Also, if the user has a deeper understanding of a specific concept, the completion unit can generate application questions related to the concept. In this way, the completion unit can provide completion questions to deepen the user's understanding.

[0035] The simplification unit can simplify a difficult problem when the user is struggling with it. For example, when the user is struggling with a difficult problem, the simplification unit executes an algorithm to simplify the problem and present it to the user. For example, the simplification unit adjusts the difficulty of the problem or provides hints. The simplification unit can also change the format of the problem according to the user's level of understanding. For example, when the user is struggling with a particular problem, the simplification unit can simplify the problem by adjusting the difficulty of the problem. The simplification unit can also provide hints for the problem when the user lacks understanding of the particular problem. In this way, the simplification unit can simplify the problem according to the user's level of understanding.

[0036] The reception unit can analyze the user's past learning history and suggest optimal settings. The reception unit, for example, executes an algorithm that analyzes the user's past learning history and suggests optimal settings. For example, the reception unit automatically suggests optimal settings based on the subjects and ranges that the user has studied in the past. The reception unit can also preferentially display settings for a specific grade or range based on the user's past learning history. Furthermore, the reception unit can analyze the user's learning history and suggest settings based on the content that is frequently studied. This allows the reception unit to suggest optimal settings based on the user's past learning history.

[0037] The reception unit can perform filtering based on the user's current learning progress when inputting the setting content. For example, the reception unit executes an algorithm that performs filtering based on the user's current learning progress when inputting the setting content. For example, the reception unit suggests setting content for an appropriate range or grade based on the user's current learning progress. The reception unit can also filter and display setting content with a high level of difficulty based on the user's progress. Furthermore, the reception unit can preferentially display setting content for an appropriate subject or range based on the user's learning progress. This allows the reception unit to provide setting content that matches the user's current learning progress.

[0038] The reception unit can prioritize displaying highly relevant setting contents in consideration of the user's geographical location information when inputting setting contents. For example, the reception unit executes an algorithm that prioritizes displaying highly relevant setting contents in consideration of the user's geographical location information when inputting setting contents. For example, the reception unit can suggest setting contents for subjects or scopes related to the region based on the user's geographical location information. The reception unit can also prioritize displaying setting contents based on the region's educational curriculum based on the user's location information. Furthermore, the reception unit can suggest setting contents based on the region's educational trends in consideration of the user's geographical location information. This allows the reception unit to provide setting contents based on the user's geographical location information.

[0039] The reception unit can analyze the user's social media activity when the settings are input and suggest related settings. For example, the reception unit executes an algorithm that analyzes the user's social media activity when the settings are input and suggests related settings. For example, the reception unit identifies subjects or areas of interest from the user's social media activity and suggests settings. The reception unit can also display related settings based on learning content shared by the user on social media. Furthermore, the reception unit can analyze the user's social media activity and suggest settings based on trends. This allows the reception unit to provide settings based on the user's social media activity.

[0040] The generation unit can generate optimal questions by referring to past question data when generating questions. For example, when generating questions, the generation unit executes an algorithm that references past question data to generate optimal questions. For example, the generation unit generates questions that are suited to the user's learning history based on past question data. The generation unit can also generate questions that are frequently answered incorrectly from the past question data with priority. Furthermore, the generation unit can analyze past question data and generate questions that correspond to the user's level of understanding. This allows the generation unit to provide optimal questions based on past question data.

[0041] The generator can apply different generation algorithms depending on the user's learning style when generating questions. For example, the generator executes an algorithm that applies different generation algorithms depending on the user's learning style when generating questions. For example, if the user has a visual learning style, the generator generates questions that make extensive use of diagrams and graphs. Also, if the user has an auditory learning style, the generator can generate questions that include audio and video. Furthermore, if the user has an experiential learning style, the generator can generate practical questions. In this way, the generator can provide questions that match the user's learning style.

[0042] The generation unit can determine the priority of questions based on the user's learning history when generating questions. For example, the generation unit executes an algorithm for determining the priority of questions based on the user's learning history when generating questions. For example, the generation unit prioritizes generating questions that are frequently answered incorrectly based on the user's learning history. The generation unit can also prioritize generating questions that are in a low level of understanding based on the user's learning history. Furthermore, the generation unit can analyze the user's learning history and prioritize generating questions according to the user's learning progress. This allows the generation unit to provide a priority of questions based on the user's learning history.

[0043] The generation unit can customize the content of questions based on the user's interests when generating questions. For example, the generation unit executes an algorithm that customizes the content of questions based on the user's interests when generating questions. For example, the generation unit generates questions on related topics based on the user's interests. The generation unit can also preferentially generate questions related to fields in which the user is interested. Furthermore, the generation unit can analyze the user's interests and generate questions to increase the user's motivation to learn. This allows the generation unit to provide questions based on the user's interests.

[0044] The scoring unit can optimize the scoring algorithm by referring to past scoring data during scoring. For example, the scoring unit executes an algorithm that optimizes the scoring algorithm by referring to past scoring data during scoring. For example, the scoring unit analyzes the user's answer patterns based on the past scoring data and optimizes the scoring algorithm. The scoring unit can also adjust the scoring criteria for questions that are frequently answered incorrectly based on the past scoring data. Furthermore, the scoring unit can apply a scoring algorithm according to the user's level of understanding by referring to the past scoring data. This allows the scoring unit to provide an optimal scoring algorithm based on the past scoring data.

[0045] The scoring unit can analyze the user's answer patterns during scoring to improve the accuracy of scoring. For example, the scoring unit executes an algorithm that analyzes the user's answer patterns during scoring to improve the accuracy of scoring. For example, the scoring unit analyzes the user's answer patterns and adjusts the scoring criteria for questions that are frequently answered incorrectly. The scoring unit can also optimize the scoring criteria for areas of low understanding based on the user's answer patterns. Furthermore, the scoring unit can analyze the user's answer patterns and apply individual scoring criteria. This allows the scoring unit to provide highly accurate scoring based on the user's answer patterns.

[0046] The scoring unit can customize the scoring criteria based on the user's learning history when scoring. For example, the scoring unit executes an algorithm that customizes the scoring criteria based on the user's learning history when scoring. For example, the scoring unit adjusts the scoring criteria for questions that are frequently answered incorrectly based on the user's learning history. The scoring unit can also optimize the scoring criteria for areas of low understanding based on the user's learning history. Furthermore, the scoring unit can refer to the user's learning history and apply individual scoring criteria. This allows the scoring unit to provide customized scoring criteria based on the user's learning history.

[0047] The scoring unit can provide additional feedback based on the content of the user's answers during scoring. For example, the scoring unit executes an algorithm that provides additional feedback based on the content of the user's answers during scoring. For example, the scoring unit analyzes the content of the user's answers and provides additional feedback for areas where the user has low understanding. The scoring unit can also provide additional feedback for questions that the user frequently gets wrong based on the content of the user's answers. Furthermore, the scoring unit can provide individual feedback based on the content of the user's answers. This allows the scoring unit to provide additional feedback based on the content of the user's answers.

[0048] The explanation unit can optimize the explanation algorithm by referring to past explanation data when giving an explanation. For example, the explanation unit executes an algorithm that optimizes the explanation algorithm by referring to past explanation data when giving an explanation. For example, the explanation unit provides explanations based on the past explanation data according to the user's level of understanding. The explanation unit can also optimize explanations for questions that are frequently answered incorrectly from the past explanation data. Furthermore, the explanation unit can also provide explanations based on the user's learning style by referring to the past explanation data. This allows the explanation unit to provide an optimal explanation algorithm based on the past explanation data.

[0049] The commentary unit can adjust the level of detail of the commentary according to the user's level of understanding when providing commentary. For example, the commentary unit executes an algorithm that adjusts the level of detail of the commentary according to the user's level of understanding when providing commentary. For example, the commentary unit provides a concise commentary when the user's level of understanding is high. Furthermore, the commentary unit can also provide a detailed commentary when the user's level of understanding is low. Furthermore, the commentary unit can adjust the level of detail of the commentary to an appropriate level according to the user's level of understanding. This allows the commentary unit to provide a level of detail of the commentary according to the user's level of understanding.

[0050] The commentary unit can determine the priority of the commentary based on the user's learning history when providing commentary. For example, the commentary unit executes an algorithm for determining the priority of the commentary based on the user's learning history when providing commentary. For example, the commentary unit can prioritize providing explanations for questions that are frequently answered incorrectly based on the user's learning history. The commentary unit can also prioritize providing explanations for areas of low understanding based on the user's learning history. Furthermore, the commentary unit can refer to the user's learning history and prioritize providing explanations according to the user's learning progress. This allows the commentary unit to provide priority of explanations based on the user's learning history.

[0051] The commentary unit can customize the content of the commentary based on the user's interests when providing commentary. For example, the commentary unit executes an algorithm that customizes the content of the commentary based on the user's interests when providing commentary. For example, the commentary unit provides commentary on related topics based on the user's interests. The commentary unit can also provide commentary related to fields in which the user is interested preferentially. Furthermore, the commentary unit can analyze the user's interests and provide commentary to increase the user's motivation to learn. This allows the commentary unit to provide commentary content based on the user's interests.

[0052] The detection unit can optimize the detection algorithm by referring to past detection data during detection. For example, the detection unit executes an algorithm that optimizes the detection algorithm by referring to past detection data during detection. For example, the detection unit accurately detects areas in which the user is weak based on past detection data. The detection unit can also optimize the detection algorithm for questions that are frequently answered incorrectly based on past detection data. Furthermore, the detection unit can apply a detection algorithm according to the user's level of understanding by referring to past detection data. This allows the detection unit to provide an optimal detection algorithm based on past detection data.

[0053] The detection unit can analyze the user's answer patterns during detection to improve the detection accuracy of weak areas. For example, the detection unit executes an algorithm that analyzes the user's answer patterns during detection to improve the detection accuracy of weak areas. For example, the detection unit analyzes the user's answer patterns to improve the detection accuracy for questions that are frequently answered incorrectly. The detection unit can also improve the detection accuracy for areas with low comprehension based on the user's answer patterns. Furthermore, the detection unit can analyze the user's answer patterns to improve individual detection accuracy. This allows the detection unit to provide highly accurate detection of weak areas based on the user's answer patterns.

[0054] The detection unit can determine the priority of weak areas based on the user's learning history at the time of detection. For example, the detection unit executes an algorithm for determining the priority of weak areas based on the user's learning history at the time of detection. For example, the detection unit determines the priority of questions that are frequently answered incorrectly based on the user's learning history. The detection unit can also determine the priority of areas with low levels of understanding based on the user's learning history. Furthermore, the detection unit can refer to the user's learning history and determine the priority according to the user's learning progress. In this way, the detection unit can provide the priority of weak areas based on the user's learning history.

[0055] The detection unit can customize the content of the weak areas based on the user's interests upon detection. For example, the detection unit executes an algorithm for customizing the content of the weak areas based on the user's interests upon detection. For example, the detection unit displays weak areas of related topics based on the user's interests. The detection unit can also preferentially display weak areas related to fields in which the user is interested. Furthermore, the detection unit can analyze the user's interests and display weak areas to increase the user's motivation to learn. This allows the detection unit to provide content of the weak areas based on the user's interests.

[0056] The completion unit can optimize the generation algorithm by referring to past completion data when generating completion questions. For example, the completion unit executes an algorithm that optimizes the generation algorithm by referring to past completion data when generating completion questions. For example, the completion unit generates completion questions for areas in which the user is weak based on past completion data. The completion unit can also generate completion questions for questions that are frequently answered incorrectly from past completion data. Furthermore, the completion unit can generate completion questions according to the user's level of understanding by referring to past completion data. This allows the completion unit to provide optimal completion questions based on past completion data.

[0057] The completion unit can apply different generation algorithms depending on the user's learning style when generating completion questions. For example, the completion unit executes an algorithm that applies different generation algorithms depending on the user's learning style when generating completion questions. For example, if the user has a visual learning style, the completion unit generates completion questions that make extensive use of diagrams and graphs. Also, if the user has an auditory learning style, the completion unit can generate completion questions that include audio and video. Furthermore, if the user has an experiential learning style, the completion unit can generate practical completion questions. In this way, the completion unit can provide completion questions that suit the user's learning style.

[0058] The completion unit can determine the priority of completion questions based on the user's learning history when generating completion questions. For example, the completion unit executes an algorithm for determining the priority of completion questions based on the user's learning history when generating completion questions. For example, the completion unit can preferentially generate completion questions for questions that are frequently answered incorrectly based on the user's learning history. The completion unit can also preferentially generate completion questions for areas of low understanding based on the user's learning history. Furthermore, the completion unit can refer to the user's learning history and preferentially generate completion questions according to the user's learning progress. This allows the completion unit to provide a priority order of completion questions based on the user's learning history.

[0059] The completion unit can customize the content of the completion question based on the user's interests when generating the completion question. For example, the completion unit executes an algorithm to customize the content of the completion question based on the user's interests when generating the completion question. For example, the completion unit generates completion questions on related topics based on the user's interests. The completion unit can also preferentially generate completion questions related to fields in which the user is interested. Furthermore, the completion unit can analyze the user's interests and generate completion questions to increase the user's motivation to learn. This allows the completion unit to provide completion questions based on the user's interests.

[0060] The simplification unit can optimize the simplification algorithm by referring to past simplification data when simplifying a question. For example, the simplification unit executes an algorithm that optimizes the simplification algorithm by referring to past simplification data when simplifying a question. For example, the simplification unit provides an simplification method for areas in which the user is weak based on past simplification data. The simplification unit can also provide an simplification method for questions that are frequently answered incorrectly based on past simplification data. Furthermore, the simplification unit can also provide an simplification method according to the user's level of understanding by referring to past simplification data. This allows the simplification unit to provide an optimal simplification algorithm based on past simplification data.

[0061] The simplification unit can adjust the level of detail of the simplification according to the user's level of understanding during simplification. For example, the simplification unit executes an algorithm that adjusts the level of detail of the simplification according to the user's level of understanding during simplification. For example, the simplification unit provides a simple simplification method when the user's level of understanding is high. Furthermore, the simplification unit can also provide a detailed simplification method when the user's level of understanding is low. Furthermore, the simplification unit can adjust the appropriate level of detail of the simplification according to the user's level of understanding. This allows the simplification unit to provide a level of detail of the simplification according to the user's level of understanding.

[0062] The simplification unit can determine the priority of simplified questions based on the user's learning history when simplifying the questions. For example, the simplification unit executes an algorithm for determining the priority of simplified questions based on the user's learning history when simplifying the questions. For example, the simplification unit can prioritize providing simplified questions for questions that are frequently answered incorrectly based on the user's learning history. The simplification unit can also prioritize providing simplified questions for areas of low understanding based on the user's learning history. Furthermore, the simplification unit can refer to the user's learning history and prioritize providing simplified questions according to the user's learning progress. This allows the simplification unit to prioritize simplified questions based on the user's learning history.

[0063] The simplification unit can customize the content of simplified questions based on the user's interests during simplification. For example, the simplification unit executes an algorithm to customize the content of simplified questions based on the user's interests during simplification. For example, the simplification unit provides simplified questions on related topics based on the user's interests. The simplification unit can also preferentially provide simplified questions related to fields in which the user is interested. Furthermore, the simplification unit can analyze the user's interests and provide simplified questions to increase the user's motivation to learn. This allows the simplification unit to provide simplified questions based on the user's interests.

[0064] The system according to the embodiment is not limited to the above-described example, and various modifications are possible, for example, as follows.

[0065] The learning support system may further include a presentation unit that customizes the way questions are presented depending on the user's learning style. For example, questions that make extensive use of diagrams and graphs may be presented to a user with a visual learning style, and questions that include audio and video may be presented to a user with an auditory learning style. Furthermore, practical questions may be presented to a user with an experiential learning style. In this way, the presentation unit can provide the optimal way to present questions depending on the user's learning style.

[0066] The generation unit can adjust the difficulty of questions based on the user's learning history. For example, the generation unit can increase the difficulty of questions for which the user has a high rate of correct answers in the past, and conversely, decrease the difficulty of questions for which the user has a low rate of correct answers. The generation unit can also generate questions that gradually increase in difficulty according to the user's learning progress. Furthermore, the generation unit can analyze the user's learning history and generate questions designed to deepen understanding in a specific field. This allows the generation unit to provide optimal questions based on the user's learning history.

[0067] The scoring unit can customize the form of feedback based on the content of the user's answers. For example, if a user requests detailed feedback, the scoring unit can provide specific explanations and additional reference materials. Alternatively, if a user requests concise feedback, the scoring unit can provide feedback that summarizes only the key points. Furthermore, the scoring unit can provide visual or audio feedback depending on the user's learning style. This allows the scoring unit to provide optimal feedback according to the user's needs.

[0068] The commentary unit can customize the content of the commentary based on the user's learning history. For example, it can provide more detailed commentary for questions that the user has answered incorrectly in the past, and provide concise commentary for questions that the user has answered correctly. The commentary unit can also analyze the user's learning history and provide additional commentary to deepen the user's understanding of a particular field. Furthermore, the commentary unit can provide visual or audio commentary depending on the user's learning style. This allows the commentary unit to provide optimal commentary based on the user's learning history.

[0069] The detection unit can improve the accuracy of detecting weak areas based on the user's learning history. For example, it can analyze patterns of questions that the user has answered incorrectly in the past and detect questions with similar patterns as weak areas. The detection unit can also analyze the user's learning history and prioritize detection of areas in which the user has a low level of understanding in a specific field. Furthermore, the detection unit can adjust the method for detecting weak areas according to the user's learning progress. This allows the detection unit to provide highly accurate detection of weak areas based on the user's learning history.

[0070] The processing flow of the first embodiment will be briefly explained below.

[0071] Step 1: The reception unit provides an interface for the user to set the subject, range of study, grade level, etc. For example, the reception unit may provide a drop-down menu or checkboxes for the user to select a specific subject or grade level. The reception unit may also provide a text input field for the user to set the range of study in detail. Step 2: The generator automatically generates questions based on the settings received by the receiver. For example, the generator executes an algorithm to generate questions based on a specific subject or grade level. For example, the generator can generate mathematics questions for an eighth-grade student. The generator can also provide an interface for presenting the generated questions to the user. Step 3: The scoring unit scores the user's answers to the questions generated by the generator. For example, the scoring unit executes an algorithm to determine whether the user's answers are correct. For example, the scoring unit awards points if the user's answers are correct and deducts points if the user's answers are incorrect. The scoring unit can also award partial credit. Step 4: The explanation unit provides an explanation based on the results scored by the scoring unit. For example, the explanation unit executes an algorithm that explains the reason for the correct answer if the answer is correct, and explains the mistake if the answer is incorrect. For example, the explanation unit explains the correct solution and theoretical background for a problem that the user got wrong. The explanation unit can also provide explanations in text or video format. Step 5: The detection unit detects weak areas based on the explanations provided by the explanation unit. For example, the detection unit executes an algorithm that determines that a particular area is weak if the user makes many mistakes on a particular question. The detection unit identifies weak areas by analyzing, for example, the user's error rate and answer time. Step 6: The completion unit generates questions to complete the weak areas detected by the detection unit. For example, the completion unit executes an algorithm to generate completion questions related to a specific concept. For example, the completion unit generates basic questions and applied questions for concepts that the user does not fully understand. The completion unit can also provide an interface for presenting the generated completion questions to the user. Step 7: The simplification unit simplifies the problems generated by the completion unit according to the user's level of understanding. For example, if the user is struggling with a difficult problem, the simplification unit executes an algorithm to simplify the problem and present it to the user. For example, the simplification unit adjusts the difficulty of the problem or provides hints. The simplification unit can also change the format of the problem according to the user's level of understanding.

[0072] (Example 2) A learning support system according to an embodiment of the present invention automatically generates questions based on the user's input, such as the subject, desired study area, and grade level. The system then grades and provides explanations based on the user's answers. The learning support system also detects weak areas based on the user's answers and customizes the questions by providing supplementary questions or simplifying the questions to make them easier to understand. For example, when a user inputs the user's input, such as the subject, desired study area, and grade level, the system automatically generates questions based on the input. The generated questions are presented to the user, and the user answers the questions. The system grades the answers and provides explanations. The explanations include the reason for correct answers and a detailed explanation of the mistake if the answer is incorrect. Furthermore, the system analyzes the user's answers to detect weak areas. For example, if the user makes many mistakes on a particular question, it determines that the user is weak in that area. Once a weak area is detected, the system generates questions to supplement the area. For example, if the user lacks understanding of a particular concept, it generates supplementary questions related to that concept. The system also simplifies questions based on the user's level of understanding. For example, if the user is struggling with a difficult question, it presents an easier version of that question. This allows the user to deepen their understanding step by step. In this way, the system supports the user's learning and allows them to progress through the learning efficiently. This allows the learning support system to efficiently support the user's learning, complement weak areas, and provide questions according to the user's level of understanding.

[0073] A learning assistance system according to an embodiment includes a receiving unit, a generating unit, a scoring unit, an explanation unit, a detection unit, a completion unit, and a simplification unit. The receiving unit provides an interface for a user to set a subject, a desired range of study, a grade level, and the like. For example, the receiving unit may provide a drop-down menu or checkboxes for a user to select a specific subject or grade level. The receiving unit may also provide a text input field for a user to specify in detail the range of study the user wishes to perform. The generating unit automatically generates questions based on the settings received by the receiving unit. For example, the generating unit may execute an algorithm to generate questions based on a specific subject or grade level. The generating unit may generate, for example, mathematics questions for an eighth-grade level student. The generating unit may also provide an interface for presenting the generated questions to the user. The scoring unit scores a user's answers to the questions generated by the generating unit. For example, the scoring unit executes an algorithm to determine whether the user's answers are correct. For example, the scoring unit may award points if the user's answers are correct and deduct points if the user's answers are incorrect. The scoring unit can also award partial points. The explanation unit provides explanations based on the results scored by the scoring unit. For example, the explanation unit executes an algorithm that explains the reason for a correct answer and explains the mistake for an incorrect answer. The explanation unit, for example, explains the correct solution and theoretical background for a question that the user got wrong. The explanation unit can also provide explanations in text or video format. The detection unit detects weak areas based on the explanation results obtained by the explanation unit. For example, the detection unit executes an algorithm that determines that a specific area is weak if the user makes many mistakes on that question. The detection unit identifies weak areas by analyzing, for example, the user's error rate and answer time. The completion unit generates questions to complete the weak areas detected by the detection unit. For example, the completion unit executes an algorithm that generates completion questions related to a specific concept. The completion unit generates basic and applied questions for concepts that the user does not fully understand. The completion unit can also provide an interface for presenting the generated completion questions to the user.The simplification unit simplifies the problems generated by the completion unit according to the user's level of understanding. For example, if the user is struggling with a difficult problem, the simplification unit executes an algorithm to simplify the problem and present it to the user. The simplification unit, for example, adjusts the difficulty of the problem or provides hints. The simplification unit can also change the format of the problem according to the user's level of understanding. This allows the learning assistance system according to the embodiment to efficiently support the user's learning, complement weak areas, and provide problems according to the user's level of understanding.

[0074] The generation unit can generate questions based on a specific subject or grade range. For example, the generation unit executes an algorithm that generates questions based on a specific subject or grade range. For example, the generation unit can generate mathematics questions for an eighth-grade student. The generation unit can also provide an interface for presenting the generated questions to the user. The generation unit can generate questions of an appropriate level of difficulty based on a subject or grade range set by the user. For example, the generation unit can generate questions ranging from basic to applied questions based on the range set by the user. The generation unit can also diversify the format of the generated questions. For example, the generation unit can generate questions in various formats, such as multiple-choice questions, essay questions, and practical questions. This allows the generation unit to generate questions appropriate for a specific subject or grade.

[0075] The scoring unit can determine whether the user's answer is correct. The scoring unit, for example, executes an algorithm to determine whether the user's answer is correct. For example, the scoring unit awards points when the user's answer is correct, and deducts points when the user's answer is incorrect. The scoring unit can also award partial points. For example, the scoring unit executes an algorithm to award partial points when the user's answer is partially correct. For example, the scoring unit can award partial points when the user's answer is close to the correct answer. The scoring unit can also award full points when the user's answer is completely correct. In this way, the scoring unit can determine whether the user's answer is correct or incorrect.

[0076] The explanation unit can explain the reason for the correct answer if the answer is correct, and what is wrong if the answer is incorrect. For example, the explanation unit executes an algorithm that explains the reason for the correct answer if the answer is correct, and what is wrong if the answer is incorrect. For example, the explanation unit explains the correct solution and the theoretical background for a problem that the user got wrong. The explanation unit can also provide the explanation in text format or video format. For example, the explanation unit can provide a detailed explanation in text format for a problem that the user got wrong. The explanation unit can also provide a visual explanation in video format for a problem that the user got wrong. This allows the explanation unit to understand the reason for the correct answer and the cause of the error.

[0077] The detection unit can determine that a user is weak in a particular area if mistakes are frequently made on a particular problem. For example, the detection unit executes an algorithm that determines that a user is weak in a particular area if mistakes are frequently made on a particular problem. For example, the detection unit analyzes the user's error rate and answer time to identify the weak area. For example, if a user frequently makes mistakes on a particular problem, the detection unit can determine that the user is weak in an area related to that problem. Furthermore, the detection unit can also determine that the user is weak in an area related to that problem if the user takes a long time to answer. This allows the detection unit to accurately detect the user's weak areas.

[0078] The completion unit can generate completion questions related to a specific concept. For example, the completion unit executes an algorithm that generates completion questions related to a specific concept. For example, the completion unit generates basic questions and application questions for a concept that the user lacks understanding of. The completion unit can also provide an interface for presenting the generated completion questions to the user. For example, if the user lacks understanding of a specific concept, the completion unit can generate basic questions related to the concept. Also, if the user has a deeper understanding of a specific concept, the completion unit can generate application questions related to the concept. In this way, the completion unit can provide completion questions to deepen the user's understanding.

[0079] The simplification unit can simplify a difficult problem when the user is struggling with it. For example, when the user is struggling with a difficult problem, the simplification unit executes an algorithm to simplify the problem and present it to the user. For example, the simplification unit adjusts the difficulty of the problem or provides hints. The simplification unit can also change the format of the problem according to the user's level of understanding. For example, when the user is struggling with a particular problem, the simplification unit can simplify the problem by adjusting the difficulty of the problem. The simplification unit can also provide hints for the problem when the user lacks understanding of the particular problem. In this way, the simplification unit can simplify the problem according to the user's level of understanding.

[0080] The learning assistance system further includes a reception unit that estimates a user's emotions and customizes the input interface for the settings based on the estimated user emotions. The reception unit, for example, executes an algorithm that estimates the user's emotions and customizes the input interface for the settings based on the estimated user emotions. For example, if the user is feeling stressed, the reception unit provides a simple and intuitive interface and minimizes input steps. Furthermore, if the user is relaxed, the reception unit can provide detailed setting options and suggest customizable input methods. Furthermore, if the user is in a hurry, the reception unit prioritizes voice input to enable quick input of the settings. This allows the reception unit to provide an input interface that corresponds to the user's emotions. The emotion estimation is realized using an emotion estimation function, for example, an emotion engine or a generation AI. The generation AI may be, but is not limited to, a text generation AI (e.g., LLM) or a multimodal generation AI. Some or all of the above-described processing in the reception unit may be performed using AI, or without AI. For example, the reception unit may input the user's facial expression data into the generation AI and have the generation AI perform emotion estimation.

[0081] The reception unit can analyze the user's past learning history and suggest optimal settings. The reception unit, for example, executes an algorithm that analyzes the user's past learning history and suggests optimal settings. For example, the reception unit automatically suggests optimal settings based on the subjects and ranges that the user has studied in the past. The reception unit can also preferentially display settings for a specific grade or range based on the user's past learning history. Furthermore, the reception unit can analyze the user's learning history and suggest settings based on the content that is frequently studied. This allows the reception unit to suggest optimal settings based on the user's past learning history.

[0082] The reception unit can perform filtering based on the user's current learning progress when inputting the setting content. For example, the reception unit executes an algorithm that performs filtering based on the user's current learning progress when inputting the setting content. For example, the reception unit suggests setting content for an appropriate range or grade based on the user's current learning progress. The reception unit can also filter and display setting content with a high level of difficulty based on the user's progress. Furthermore, the reception unit can preferentially display setting content for an appropriate subject or range based on the user's learning progress. This allows the reception unit to provide setting content that matches the user's current learning progress.

[0083] The reception unit can estimate the user's emotions and adjust the input order of the settings based on the estimated user emotions. The reception unit, for example, executes an algorithm that estimates the user's emotions and adjusts the input order of the settings based on the estimated user emotions. For example, if the user is nervous, the reception unit can have the user input the settings in order from simple to complex. Furthermore, if the user is relaxed, the reception unit can have the user input the detailed settings first. Furthermore, if the user is in a hurry, the reception unit can have the user input the important settings first. This allows the reception unit to provide an input order that corresponds to the user's emotions. The emotion estimation is realized using an emotion estimation function, for example, an emotion engine or a generation AI. The generation AI can be, but is not limited to, a text generation AI (e.g., LLM) or a multimodal generation AI. Some or all of the above-described processing in the reception unit can be performed using, for example, an AI, or without an AI. For example, the reception unit can input the user's facial expression data into the generation AI and cause the generation AI to estimate the user's emotions.

[0084] The reception unit can prioritize displaying highly relevant setting contents in consideration of the user's geographical location information when inputting setting contents. For example, the reception unit executes an algorithm that prioritizes displaying highly relevant setting contents in consideration of the user's geographical location information when inputting setting contents. For example, the reception unit can suggest setting contents for subjects or scopes related to the region based on the user's geographical location information. The reception unit can also prioritize displaying setting contents based on the region's educational curriculum based on the user's location information. Furthermore, the reception unit can suggest setting contents based on the region's educational trends in consideration of the user's geographical location information. This allows the reception unit to provide setting contents based on the user's geographical location information.

[0085] The reception unit can analyze the user's social media activity when the settings are input and suggest related settings. For example, the reception unit executes an algorithm that analyzes the user's social media activity when the settings are input and suggests related settings. For example, the reception unit identifies subjects or areas of interest from the user's social media activity and suggests settings. The reception unit can also display related settings based on learning content shared by the user on social media. Furthermore, the reception unit can analyze the user's social media activity and suggest settings based on trends. This allows the reception unit to provide settings based on the user's social media activity.

[0086] The generation unit can estimate the user's emotions and adjust the difficulty of questions based on the estimated user emotions. The generation unit, for example, executes an algorithm that estimates the user's emotions and adjusts the difficulty of questions based on the estimated user emotions. For example, the generation unit generates questions with a high level of difficulty when the user is relaxed. The generation unit can also generate questions with a low level of difficulty when the user is stressed. Furthermore, the generation unit can generate questions with an appropriate level of difficulty when the user is excited. This allows the generation unit to provide questions with a level of difficulty that corresponds to the user's emotions. Emotion estimation is achieved using an emotion estimation function, for example, an emotion engine or a generation AI. The generation AI may be, but is not limited to, a text generation AI (e.g., LLM) or a multimodal generation AI. Some or all of the above-described processing in the generation unit may be performed using, for example, an AI, or may be performed without using an AI. For example, the generation unit may input the user's facial expression data into the generation AI and cause the generation AI to estimate emotions.

[0087] The generation unit can generate optimal questions by referring to past question data when generating questions. For example, when generating questions, the generation unit executes an algorithm that references past question data to generate optimal questions. For example, the generation unit generates questions that are suited to the user's learning history based on past question data. The generation unit can also generate questions that are frequently answered incorrectly from the past question data with priority. Furthermore, the generation unit can analyze past question data and generate questions that correspond to the user's level of understanding. This allows the generation unit to provide optimal questions based on past question data.

[0088] The generator can apply different generation algorithms depending on the user's learning style when generating questions. For example, the generator executes an algorithm that applies different generation algorithms depending on the user's learning style when generating questions. For example, if the user has a visual learning style, the generator generates questions that make extensive use of diagrams and graphs. Also, if the user has an auditory learning style, the generator can generate questions that include audio and video. Furthermore, if the user has an experiential learning style, the generator can generate practical questions. In this way, the generator can provide questions that match the user's learning style.

[0089] The generation unit can estimate the user's emotions and adjust the question format based on the estimated user emotions. The generation unit, for example, executes an algorithm that estimates the user's emotions and adjusts the question format based on the estimated user emotions. For example, the generation unit generates long questions when the user is relaxed. The generation unit can also generate short questions when the user is stressed. Furthermore, the generation unit can generate visually stimulating questions when the user is excited. This allows the generation unit to provide a question format that corresponds to the user's emotions. The emotion estimation is achieved using an emotion estimation function, for example, an emotion engine or a generation AI. The generation AI may be a text generation AI (e.g., LLM) or a multimodal generation AI, but is not limited to such examples. Some or all of the above-mentioned processing in the generation unit may be performed using an AI, for example, or without an AI. For example, the generation unit may input the user's facial expression data into the generation AI and cause the generation AI to estimate the emotion.

[0090] The generation unit can determine the priority of questions based on the user's learning history when generating questions. For example, the generation unit executes an algorithm for determining the priority of questions based on the user's learning history when generating questions. For example, the generation unit prioritizes generating questions that are frequently answered incorrectly based on the user's learning history. The generation unit can also prioritize generating questions that are in a low level of understanding based on the user's learning history. Furthermore, the generation unit can analyze the user's learning history and prioritize generating questions according to the user's learning progress. This allows the generation unit to provide a priority of questions based on the user's learning history.

[0091] The generation unit can customize the content of questions based on the user's interests when generating questions. For example, the generation unit executes an algorithm that customizes the content of questions based on the user's interests when generating questions. For example, the generation unit generates questions on related topics based on the user's interests. The generation unit can also preferentially generate questions related to fields in which the user is interested. Furthermore, the generation unit can analyze the user's interests and generate questions to increase the user's motivation to learn. This allows the generation unit to provide questions based on the user's interests.

[0092] The scoring unit can estimate the user's emotion and adjust the feedback method of the scoring result based on the estimated user emotion. The scoring unit, for example, executes an algorithm that estimates the user's emotion and adjusts the feedback method of the scoring result based on the estimated user emotion. For example, the scoring unit can provide detailed feedback when the user is relaxed. The scoring unit can also provide concise feedback when the user is stressed. Furthermore, the scoring unit can provide positive feedback when the user is excited. This allows the scoring unit to provide a feedback method that corresponds to the user's emotion. Emotion estimation is realized using an emotion estimation function, for example, an emotion engine or a generation AI. The generation AI can be 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 scoring unit may be performed using an AI, for example, or without an AI. For example, the scoring unit can input the user's facial expression data into the generation AI and cause the generation AI to estimate the emotion.

[0093] The scoring unit can optimize the scoring algorithm by referring to past scoring data during scoring. For example, the scoring unit executes an algorithm that optimizes the scoring algorithm by referring to past scoring data during scoring. For example, the scoring unit analyzes the user's answer patterns based on the past scoring data and optimizes the scoring algorithm. The scoring unit can also adjust the scoring criteria for questions that are frequently answered incorrectly based on the past scoring data. Furthermore, the scoring unit can apply a scoring algorithm according to the user's level of understanding by referring to the past scoring data. This allows the scoring unit to provide an optimal scoring algorithm based on the past scoring data.

[0094] The scoring unit can analyze the user's answer patterns during scoring to improve the accuracy of scoring. For example, the scoring unit executes an algorithm that analyzes the user's answer patterns during scoring to improve the accuracy of scoring. For example, the scoring unit analyzes the user's answer patterns and adjusts the scoring criteria for questions that are frequently answered incorrectly. The scoring unit can also optimize the scoring criteria for areas of low understanding based on the user's answer patterns. Furthermore, the scoring unit can analyze the user's answer patterns and apply individual scoring criteria. This allows the scoring unit to provide highly accurate scoring based on the user's answer patterns.

[0095] The scoring unit can estimate the user's emotions and adjust the display order of the scoring results based on the estimated user emotions. The scoring unit, for example, executes an algorithm that estimates the user's emotions and adjusts the display order of the scoring results based on the estimated user emotions. For example, if the user is relaxed, the scoring unit can display detailed scoring results first. If the user is stressed, the scoring unit can also display concise scoring results first. Furthermore, if the user is excited, the scoring unit can also display positive scoring results first. This allows the scoring unit to provide a display order of the scoring results according to the user's emotions. Emotion estimation is realized using an emotion estimation function, for example, an emotion engine or a generation AI. The generation AI can be a text generation AI (e.g., LLM) or a multimodal generation AI, but is not limited to such examples. Some or all of the above-mentioned processing in the scoring unit may be performed using an AI, for example, or without an AI. For example, the scoring unit can input the user's facial expression data into the generation AI and cause the generation AI to estimate the emotion.

[0096] The scoring unit can customize the scoring criteria based on the user's learning history when scoring. For example, the scoring unit executes an algorithm that customizes the scoring criteria based on the user's learning history when scoring. For example, the scoring unit adjusts the scoring criteria for questions that are frequently answered incorrectly based on the user's learning history. The scoring unit can also optimize the scoring criteria for areas of low understanding based on the user's learning history. Furthermore, the scoring unit can refer to the user's learning history and apply individual scoring criteria. This allows the scoring unit to provide customized scoring criteria based on the user's learning history.

[0097] The scoring unit can provide additional feedback based on the content of the user's answers during scoring. For example, the scoring unit executes an algorithm that provides additional feedback based on the content of the user's answers during scoring. For example, the scoring unit analyzes the content of the user's answers and provides additional feedback for areas where the user has low understanding. The scoring unit can also provide additional feedback for questions that the user frequently gets wrong based on the content of the user's answers. Furthermore, the scoring unit can provide individual feedback based on the content of the user's answers. This allows the scoring unit to provide additional feedback based on the content of the user's answers.

[0098] The commentary unit can estimate the user's emotions and adjust the manner in which the commentary is expressed based on the estimated user emotions. The commentary unit, for example, executes an algorithm that estimates the user's emotions and adjusts the manner in which the commentary is expressed based on the estimated user emotions. For example, the commentary unit can provide detailed commentary when the user is relaxed. The commentary unit can also provide concise commentary when the user is stressed. Furthermore, the commentary unit can provide visually stimulating commentary when the user is excited. This allows the commentary unit to provide a manner in which the commentary is expressed based on the user's emotions. Emotion estimation is realized using an emotion estimation function, for example, an emotion engine or a generation AI. The generation AI can be a text generation AI (e.g., LLM) or a multimodal generation AI, but is not limited to such examples. Some or all of the above-mentioned processing in the commentary unit may be performed using an AI, for example, or without an AI. For example, the commentary unit can input the user's facial expression data into the generation AI and cause the generation AI to estimate the emotion.

[0099] The explanation unit can optimize the explanation algorithm by referring to past explanation data when giving an explanation. For example, the explanation unit executes an algorithm that optimizes the explanation algorithm by referring to past explanation data when giving an explanation. For example, the explanation unit provides explanations based on the past explanation data according to the user's level of understanding. The explanation unit can also optimize explanations for questions that are frequently answered incorrectly from the past explanation data. Furthermore, the explanation unit can also provide explanations based on the user's learning style by referring to the past explanation data. This allows the explanation unit to provide an optimal explanation algorithm based on the past explanation data.

[0100] The commentary unit can adjust the level of detail of the commentary according to the user's level of understanding when providing commentary. For example, the commentary unit executes an algorithm that adjusts the level of detail of the commentary according to the user's level of understanding when providing commentary. For example, the commentary unit provides a concise commentary when the user's level of understanding is high. Furthermore, the commentary unit can also provide a detailed commentary when the user's level of understanding is low. Furthermore, the commentary unit can adjust the level of detail of the commentary to an appropriate level according to the user's level of understanding. This allows the commentary unit to provide a level of detail of the commentary according to the user's level of understanding.

[0101] The commentary unit can estimate the user's emotions and adjust the length of the commentary based on the estimated user emotions. The commentary unit, for example, executes an algorithm that estimates the user's emotions and adjusts the length of the commentary based on the estimated user emotions. For example, the commentary unit can provide detailed commentary when the user is relaxed. The commentary unit can also provide concise commentary when the user is stressed. Furthermore, the commentary unit can provide visually stimulating commentary when the user is excited. This allows the commentary unit to provide a length of commentary that corresponds to the user's emotions. Emotion estimation is realized using an emotion estimation function, for example, an emotion engine or a generation AI. The generation AI can be a text generation AI (e.g., LLM) or a multimodal generation AI, but is not limited to such examples. Some or all of the above-mentioned processing in the commentary unit may be performed using AI, for example, or without AI. For example, the commentary unit can input the user's facial expression data into the generation AI and cause the generation AI to estimate the emotion.

[0102] The commentary unit can determine the priority of the commentary based on the user's learning history when providing commentary. For example, the commentary unit executes an algorithm for determining the priority of the commentary based on the user's learning history when providing commentary. For example, the commentary unit can prioritize providing explanations for questions that are frequently answered incorrectly based on the user's learning history. The commentary unit can also prioritize providing explanations for areas of low understanding based on the user's learning history. Furthermore, the commentary unit can refer to the user's learning history and prioritize providing explanations according to the user's learning progress. This allows the commentary unit to provide priority of explanations based on the user's learning history.

[0103] The commentary unit can customize the content of the commentary based on the user's interests when providing commentary. For example, the commentary unit executes an algorithm that customizes the content of the commentary based on the user's interests when providing commentary. For example, the commentary unit provides commentary on related topics based on the user's interests. The commentary unit can also provide commentary related to fields in which the user is interested preferentially. Furthermore, the commentary unit can analyze the user's interests and provide commentary to increase the user's motivation to learn. This allows the commentary unit to provide commentary content based on the user's interests.

[0104] The detection unit can estimate the user's emotions and adjust the method for detecting weak areas based on the estimated user emotions. The detection unit, for example, executes an algorithm that estimates the user's emotions and adjusts the method for detecting weak areas based on the estimated user emotions. For example, when the user is relaxed, the detection unit performs a detailed analysis to detect weak areas. Furthermore, when the user is stressed, the detection unit can also perform a brief analysis to detect weak areas. Furthermore, when the user is excited, the detection unit can also detect weak areas in a visually stimulating manner. This allows the detection unit to provide a method for detecting weak areas according to the user's emotions. Emotion estimation is realized using an emotion estimation function, for example, an emotion engine or a generation AI. The generation AI can be a text generation AI (e.g., LLM) or a multimodal generation AI, but is not limited to such examples. Some or all of the above-described processing in the detection unit may be performed using AI, or may be performed without AI. For example, the detection unit can input the user's facial expression data into the generation AI and cause the generation AI to estimate emotions.

[0105] The detection unit can optimize the detection algorithm by referring to past detection data during detection. For example, the detection unit executes an algorithm that optimizes the detection algorithm by referring to past detection data during detection. For example, the detection unit accurately detects areas in which the user is weak based on past detection data. The detection unit can also optimize the detection algorithm for questions that are frequently answered incorrectly based on past detection data. Furthermore, the detection unit can apply a detection algorithm according to the user's level of understanding by referring to past detection data. This allows the detection unit to provide an optimal detection algorithm based on past detection data.

[0106] The detection unit can analyze the user's answer patterns during detection to improve the detection accuracy of weak areas. For example, the detection unit executes an algorithm that analyzes the user's answer patterns during detection to improve the detection accuracy of weak areas. For example, the detection unit analyzes the user's answer patterns to improve the detection accuracy for questions that are frequently answered incorrectly. The detection unit can also improve the detection accuracy for areas with low comprehension based on the user's answer patterns. Furthermore, the detection unit can analyze the user's answer patterns to improve individual detection accuracy. This allows the detection unit to provide highly accurate detection of weak areas based on the user's answer patterns.

[0107] The detection unit can estimate the user's emotion and adjust the display method of the weak area based on the estimated user emotion. The detection unit, for example, executes an algorithm that estimates the user's emotion and adjusts the display method of the weak area based on the estimated user emotion. For example, the detection unit can provide a detailed display method when the user is relaxed. The detection unit can also provide a simple display method when the user is stressed. Furthermore, the detection unit can provide a visually stimulating display method when the user is excited. This allows the detection unit to provide a display method of the weak area according to the user's emotion. Emotion estimation is realized using an emotion estimation function, for example, an emotion engine or a generation AI. The generation AI can be 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 detection unit may be performed using an AI, for example, or without an AI. For example, the detection unit can input the user's facial expression data into the generation AI and cause the generation AI to estimate the emotion.

[0108] The detection unit can determine the priority of weak areas based on the user's learning history at the time of detection. For example, the detection unit executes an algorithm for determining the priority of weak areas based on the user's learning history at the time of detection. For example, the detection unit determines the priority of questions that are frequently answered incorrectly based on the user's learning history. The detection unit can also determine the priority of areas with low levels of understanding based on the user's learning history. Furthermore, the detection unit can refer to the user's learning history and determine the priority according to the user's learning progress. In this way, the detection unit can provide the priority of weak areas based on the user's learning history.

[0109] The detection unit can customize the content of the weak areas based on the user's interests upon detection. For example, the detection unit executes an algorithm for customizing the content of the weak areas based on the user's interests upon detection. For example, the detection unit displays weak areas of related topics based on the user's interests. The detection unit can also preferentially display weak areas related to fields in which the user is interested. Furthermore, the detection unit can analyze the user's interests and display weak areas to increase the user's motivation to learn. This allows the detection unit to provide content of the weak areas based on the user's interests.

[0110] The completion unit can estimate the user's emotions and adjust the method for generating completion questions based on the estimated user emotions. The completion unit, for example, executes an algorithm that estimates the user's emotions and adjusts the method for generating completion questions based on the estimated user emotions. For example, the completion unit generates detailed completion questions when the user is relaxed. The completion unit can also generate concise completion questions when the user is stressed. Furthermore, the completion unit can generate visually stimulating completion questions when the user is excited. This allows the completion unit to provide a method for generating completion questions according to the user's emotions. The emotion estimation is realized using an emotion estimation function, for example, an emotion engine or a generation AI. The generation AI can be a text generation AI (e.g., LLM) or a multimodal generation AI, but is not limited to such examples. Some or all of the above-described processing in the completion unit may be performed using an AI, for example, or without an AI. For example, the completion unit can input the user's facial expression data into the generation AI and cause the generation AI to estimate the emotion.

[0111] The completion unit can optimize the generation algorithm by referring to past completion data when generating completion questions. For example, the completion unit executes an algorithm that optimizes the generation algorithm by referring to past completion data when generating completion questions. For example, the completion unit generates completion questions for areas in which the user is weak based on past completion data. The completion unit can also generate completion questions for questions that are frequently answered incorrectly from past completion data. Furthermore, the completion unit can generate completion questions according to the user's level of understanding by referring to past completion data. This allows the completion unit to provide optimal completion questions based on past completion data.

[0112] The completion unit can apply different generation algorithms depending on the user's learning style when generating completion questions. For example, the completion unit executes an algorithm that applies different generation algorithms depending on the user's learning style when generating completion questions. For example, if the user has a visual learning style, the completion unit generates completion questions that make extensive use of diagrams and graphs. Also, if the user has an auditory learning style, the completion unit can generate completion questions that include audio and video. Furthermore, if the user has an experiential learning style, the completion unit can generate practical completion questions. In this way, the completion unit can provide completion questions that suit the user's learning style.

[0113] The completion unit can estimate the user's emotions and adjust the format of the completion questions based on the estimated user emotions. The completion unit, for example, executes an algorithm that estimates the user's emotions and adjusts the format of the completion questions based on the estimated user emotions. For example, the completion unit generates long completion questions when the user is relaxed. The completion unit can also generate short completion questions when the user is stressed. Furthermore, the completion unit can generate visually stimulating completion questions when the user is excited. This allows the completion unit to provide a completion question format that corresponds to the user's emotions. The emotion estimation is realized using an emotion estimation function, for example, an emotion engine or a generation AI. The generation AI can be a text generation AI (e.g., LLM) or a multimodal generation AI, but is not limited to such examples. Some or all of the above-described processing in the completion unit may be performed using an AI, for example, or without an AI. For example, the completion unit can input the user's facial expression data into the generation AI and cause the generation AI to estimate the emotion.

[0114] The completion unit can determine the priority of completion questions based on the user's learning history when generating completion questions. For example, the completion unit executes an algorithm for determining the priority of completion questions based on the user's learning history when generating completion questions. For example, the completion unit can preferentially generate completion questions for questions that are frequently answered incorrectly based on the user's learning history. The completion unit can also preferentially generate completion questions for areas of low understanding based on the user's learning history. Furthermore, the completion unit can refer to the user's learning history and preferentially generate completion questions according to the user's learning progress. This allows the completion unit to provide a priority order of completion questions based on the user's learning history.

[0115] The completion unit can customize the content of the completion question based on the user's interests when generating the completion question. For example, the completion unit executes an algorithm to customize the content of the completion question based on the user's interests when generating the completion question. For example, the completion unit generates completion questions on related topics based on the user's interests. The completion unit can also preferentially generate completion questions related to fields in which the user is interested. Furthermore, the completion unit can analyze the user's interests and generate completion questions to increase the user's motivation to learn. This allows the completion unit to provide completion questions based on the user's interests.

[0116] The simplification unit can estimate the user's emotions and adjust the simplification method for the questions based on the estimated user emotions. The simplification unit, for example, executes an algorithm that estimates the user's emotions and adjusts the simplification method for the questions based on the estimated user emotions. For example, the simplification unit can provide a detailed simplification method when the user is relaxed. The simplification unit can also provide a concise simplification method when the user is stressed. Furthermore, the simplification unit can also provide a visually stimulating simplification method when the user is excited. This allows the simplification unit to provide a simplification method for the questions according to the user's emotions. The emotion estimation is realized using an emotion estimation function, for example, an emotion engine or a generation AI. The generation AI can be, but is not limited to, a text generation AI (e.g., LLM) or a multimodal generation AI. Some or all of the above-described processing in the simplification unit may be performed using, for example, an AI, or may be performed without using an AI. For example, the simplification unit can input the user's facial expression data into the generation AI and cause the generation AI to estimate the emotion.

[0117] The simplification unit can optimize the simplification algorithm by referring to past simplification data when simplifying a question. For example, the simplification unit executes an algorithm that optimizes the simplification algorithm by referring to past simplification data when simplifying a question. For example, the simplification unit provides an simplification method for areas in which the user is weak based on past simplification data. The simplification unit can also provide an simplification method for questions that are frequently answered incorrectly based on past simplification data. Furthermore, the simplification unit can also provide an simplification method according to the user's level of understanding by referring to past simplification data. This allows the simplification unit to provide an optimal simplification algorithm based on past simplification data.

[0118] The simplification unit can adjust the level of detail of the simplification according to the user's level of understanding during simplification. For example, the simplification unit executes an algorithm that adjusts the level of detail of the simplification according to the user's level of understanding during simplification. For example, the simplification unit provides a simple simplification method when the user's level of understanding is high. Furthermore, the simplification unit can also provide a detailed simplification method when the user's level of understanding is low. Furthermore, the simplification unit can adjust the appropriate level of detail of the simplification according to the user's level of understanding. This allows the simplification unit to provide a level of detail of the simplification according to the user's level of understanding.

[0119] The simplification unit can estimate the user's emotions and adjust the display method of simplified questions based on the estimated user emotions. The simplification unit, for example, executes an algorithm that estimates the user's emotions and adjusts the display method of simplified questions based on the estimated user emotions. For example, the simplification unit provides a detailed display method when the user is relaxed. The simplification unit can also provide a concise display method when the user is stressed. Furthermore, the simplification unit can also provide a visually stimulating display method when the user is excited. This allows the simplification unit to provide a display method of simplified questions according to the user's emotions. Emotion estimation is realized using an emotion estimation function, for example, an emotion engine or a generation AI. The generation AI can be a text generation AI (e.g., LLM) or a multimodal generation AI, but is not limited to such examples. Some or all of the above-mentioned processing in the simplification unit may be performed using an AI, for example, or without an AI. For example, the simplification unit can input the user's facial expression data into the generation AI and cause the generation AI to estimate the emotion.

[0120] The simplification unit can determine the priority of simplified questions based on the user's learning history when simplifying the questions. For example, the simplification unit executes an algorithm for determining the priority of simplified questions based on the user's learning history when simplifying the questions. For example, the simplification unit can prioritize providing simplified questions for questions that are frequently answered incorrectly based on the user's learning history. The simplification unit can also prioritize providing simplified questions for areas of low understanding based on the user's learning history. Furthermore, the simplification unit can refer to the user's learning history and prioritize providing simplified questions according to the user's learning progress. This allows the simplification unit to prioritize simplified questions based on the user's learning history.

[0121] The simplification unit can customize the content of simplified questions based on the user's interests during simplification. For example, the simplification unit executes an algorithm to customize the content of simplified questions based on the user's interests during simplification. For example, the simplification unit provides simplified questions on related topics based on the user's interests. The simplification unit can also preferentially provide simplified questions related to fields in which the user is interested. Furthermore, the simplification unit can analyze the user's interests and provide simplified questions to increase the user's motivation to learn. This allows the simplification unit to provide simplified questions based on the user's interests. === Hard Collateral 1-1 === Each of the above-described elements, including the reception unit, generation unit, scoring unit, explanation unit, detection unit, completion unit, and simplification unit, is implemented, for example, by at least one of the smart device 14 and the data processing device 12. For example, the reception unit is implemented by the control unit 46A of the smart device 14 and provides an interface for the user to set the subject, the range of study, the grade, etc. The generation unit is implemented, for example, by the specific processing unit 290 of the data processing device 12 and automatically generates questions based on the settings received by the reception unit. The scoring unit is implemented, for example, by the specific processing unit 290 of the data processing device 12 and scores the user's answers to the generated questions. The explanation unit is implemented, for example, by the specific processing unit 290 of the data processing device 12 and provides explanations based on the scoring results. The detection unit is implemented, for example, by the specific processing unit 290 of the data processing device 12 and detects weak areas based on the explanation results. The completion unit is implemented, for example, by the specific processing unit 290 of the data processing device 12 and generates questions to complement the detected weak areas. The simplification unit is realized, for example, by the specific processing unit 290 of the data processing device 12, and simplifies the generated questions according to the user's level of understanding. Furthermore, the reception unit using the emotion estimation function is realized, for example, by the control unit 46A of the smart device 14, and customizes the input interface for setting contents based on the user's emotion. === Hard Collateral 1-2 === Each of the multiple elements, including the above-mentioned reception unit, generation unit, scoring unit, explanation unit, detection unit, completion unit, and simplification unit, is realized, for example, by at least one of the smart glasses 214 and the data processing device 12. For example, the reception unit is realized by the control unit 46A of the smart glasses 214 and provides an interface for the user to set the subject, the range of study desired, the grade, etc. The generation unit is realized, for example, by the specific processing unit 290 of the data processing device 12 and automatically generates questions based on the settings received by the reception unit. The scoring unit is realized, for example, by the specific processing unit 290 of the data processing device 12 and scores the user's answers to the generated questions. The explanation unit is realized, for example, by the specific processing unit 290 of the data processing device 12 and provides explanations based on the scoring results. The detection unit is realized, for example, by the specific processing unit 290 of the data processing device 12 and detects weak areas based on the explanation results. The completion unit is realized, for example, by the specific processing unit 290 of the data processing device 12 and generates questions to complement the detected weak areas. The simplification unit is realized, for example, by the specific processing unit 290 of the data processing device 12, and simplifies the generated questions according to the user's level of understanding. Furthermore, the reception unit using the emotion estimation function is realized, for example, by the control unit 46A of the smart glasses 214, and customizes the input interface for setting contents based on the user's emotion. === Hard Collateral 1-3 === Each of the multiple elements, including the above-mentioned reception unit, generation unit, scoring unit, explanation unit, detection unit, completion unit, and simplification unit, is realized, for example, by at least one of the headset-type terminal 314 and the data processing device 12. For example, the reception unit is realized by the control unit 46A of the headset-type terminal 314 and provides an interface for the user to set the subject, the range of study desired, the grade, etc. The generation unit is realized, for example, by the specific processing unit 290 of the data processing device 12 and automatically generates questions based on the settings received by the reception unit. The scoring unit is realized, for example, by the specific processing unit 290 of the data processing device 12 and scores the user's answers to the generated questions. The explanation unit is realized, for example, by the specific processing unit 290 of the data processing device 12 and provides explanations based on the scoring results. The detection unit is realized, for example, by the specific processing unit 290 of the data processing device 12 and detects weak areas based on the explanation results. The completion unit is realized, for example, by the specific processing unit 290 of the data processing device 12 and generates questions to complement the detected weak areas. The simplification unit is realized, for example, by the specific processing unit 290 of the data processing device 12, and simplifies the generated questions according to the user's level of understanding. Furthermore, the reception unit using the emotion estimation function is realized, for example, by the control unit 46A of the headset terminal 314, and customizes the input interface for setting contents based on the user's emotion. === Hard Collateral 1-4 === Each of the multiple elements, including the above-mentioned reception unit, generation unit, scoring unit, explanation unit, detection unit, completion unit, and simplification unit, is realized, for example, by at least one of the robot 414 and the data processing device 12. For example, the reception unit is realized by the control unit 46A of the robot 414 and provides an interface for the user to set the subject, the range of study desired, the grade level, etc. The generation unit is realized, for example, by the specific processing unit 290 of the data processing device 12 and automatically generates questions based on the settings received by the reception unit. The scoring unit is realized, for example, by the specific processing unit 290 of the data processing device 12 and scores the user's answers to the generated questions. The explanation unit is realized, for example, by the specific processing unit 290 of the data processing device 12 and provides explanations based on the scoring results. The detection unit is realized, for example, by the specific processing unit 290 of the data processing device 12 and detects weak areas based on the explanation results. The completion unit is realized, for example, by the specific processing unit 290 of the data processing device 12 and generates questions to complement the detected weak areas. The simplification unit is realized, for example, by the specific processing unit 290 of the data processing device 12, and simplifies the generated questions according to the user's level of understanding. Furthermore, the reception unit using the emotion estimation function is realized, for example, by the control unit 46A of the robot 414, and customizes the input interface for setting contents based on the user's emotion.

[0122] The system according to the embodiment is not limited to the above-described example, and various modifications are possible, for example, as follows.

[0123] The learning support system may further include a presentation unit that customizes the way questions are presented depending on the user's learning style. For example, questions that make extensive use of diagrams and graphs may be presented to a user with a visual learning style, and questions that include audio and video may be presented to a user with an auditory learning style. Furthermore, practical questions may be presented to a user with an experiential learning style. In this way, the presentation unit can provide the optimal way to present questions depending on the user's learning style.

[0124] The generation unit can adjust the difficulty of questions based on the user's learning history. For example, the generation unit can increase the difficulty of questions for which the user has a high rate of correct answers in the past, and conversely, decrease the difficulty of questions for which the user has a low rate of correct answers. The generation unit can also generate questions that gradually increase in difficulty according to the user's learning progress. Furthermore, the generation unit can analyze the user's learning history and generate questions designed to deepen understanding in a specific field. This allows the generation unit to provide optimal questions based on the user's learning history.

[0125] The scoring unit can customize the form of feedback based on the content of the user's answers. For example, if a user requests detailed feedback, the scoring unit can provide specific explanations and additional reference materials. Alternatively, if a user requests concise feedback, the scoring unit can provide feedback that summarizes only the key points. Furthermore, the scoring unit can provide visual or audio feedback depending on the user's learning style. This allows the scoring unit to provide optimal feedback according to the user's needs.

[0126] The commentary unit can customize the content of the commentary based on the user's learning history. For example, it can provide more detailed commentary for questions that the user has answered incorrectly in the past, and provide concise commentary for questions that the user has answered correctly. The commentary unit can also analyze the user's learning history and provide additional commentary to deepen the user's understanding of a particular field. Furthermore, the commentary unit can provide visual or audio commentary depending on the user's learning style. This allows the commentary unit to provide optimal commentary based on the user's learning history.

[0127] The detection unit can improve the accuracy of detecting weak areas based on the user's learning history. For example, it can analyze patterns of questions that the user has answered incorrectly in the past and detect questions with similar patterns as weak areas. The detection unit can also analyze the user's learning history and prioritize detection of areas in which the user has a low level of understanding in a specific field. Furthermore, the detection unit can adjust the method for detecting weak areas according to the user's learning progress. This allows the detection unit to provide highly accurate detection of weak areas based on the user's learning history.

[0128] The completion unit can estimate the user's emotions and adjust the difficulty of the completion questions based on the estimated user's emotions. For example, if the user is feeling stressed, it can generate low-difficulty completion questions, and if the user is relaxed, it can generate high-difficulty completion questions. Also, if the user is excited, it can generate visually stimulating completion questions. In this way, the completion unit can provide optimal completion questions according to the user's emotions.

[0129] The simplification unit can estimate the user's emotions and adjust the method of simplifying the questions based on the estimated user's emotions. For example, if the user is feeling stressed, not only can the difficulty of the questions be lowered but also many hints can be provided. Also, if the user is relaxed, the problem can be solved with fewer hints. Furthermore, if the user is excited, visually stimulating hints can be provided. In this way, the simplification unit can provide the optimal simplification method according to the user's emotions.

[0130] The reception unit can estimate the user's emotions and customize the input interface for the settings based on the estimated user emotions. For example, if the user is feeling stressed, a simple and intuitive interface can be provided to minimize the input steps. Alternatively, if the user is relaxed, detailed setting options can be provided and a customizable input method can be suggested. Furthermore, if the user is in a hurry, voice input can be prioritized to allow the user to input the settings quickly. In this way, the reception unit can provide an input interface that corresponds to the user's emotions.

[0131] The generation unit can estimate the user's emotions and adjust the question format based on the estimated user's emotions. For example, if the user is relaxed, it can generate long questions, and if the user is stressed, it can generate short questions. Also, if the user is excited, it can generate visually stimulating questions. In this way, the generation unit can provide the optimal question format according to the user's emotions.

[0132] The scoring unit can estimate the user's emotions and adjust the feedback method of the scoring result based on the estimated user's emotions. For example, if the user is relaxed, detailed feedback can be provided, and if the user is stressed, brief feedback can be provided. Also, if the user is excited, positive feedback can be provided. This allows the scoring unit to provide the optimal feedback method according to the user's emotions.

[0133] The processing flow of the second embodiment will be briefly explained below.

[0134] Step 1: The reception unit provides an interface for the user to set the subject, range of study, grade level, etc. For example, the reception unit may provide a drop-down menu or checkboxes for the user to select a specific subject or grade level. The reception unit may also provide a text input field for the user to set the range of study in detail. Step 2: The generator automatically generates questions based on the settings received by the receiver. For example, the generator executes an algorithm to generate questions based on a specific subject or grade level. For example, the generator can generate mathematics questions for an eighth-grade student. The generator can also provide an interface for presenting the generated questions to the user. Step 3: The scoring unit scores the user's answers to the questions generated by the generator. For example, the scoring unit executes an algorithm to determine whether the user's answers are correct. For example, the scoring unit awards points if the user's answers are correct and deducts points if the user's answers are incorrect. The scoring unit can also award partial credit. Step 4: The explanation unit provides an explanation based on the results scored by the scoring unit. For example, the explanation unit executes an algorithm that explains the reason for the correct answer if the answer is correct, and explains the mistake if the answer is incorrect. For example, the explanation unit explains the correct solution and theoretical background for a problem that the user got wrong. The explanation unit can also provide explanations in text or video format. Step 5: The detection unit detects weak areas based on the explanations provided by the explanation unit. For example, the detection unit executes an algorithm that determines that a particular area is weak if the user makes many mistakes on a particular question. The detection unit identifies weak areas by analyzing, for example, the user's error rate and answer time. Step 6: The completion unit generates questions to complete the weak areas detected by the detection unit. For example, the completion unit executes an algorithm to generate completion questions related to a specific concept. For example, the completion unit generates basic questions and applied questions for concepts that the user does not fully understand. The completion unit can also provide an interface for presenting the generated completion questions to the user. Step 7: The simplification unit simplifies the problems generated by the completion unit according to the user's level of understanding. For example, if the user is struggling with a difficult problem, the simplification unit executes an algorithm to simplify the problem and present it to the user. For example, the simplification unit adjusts the difficulty of the problem or provides hints. The simplification unit can also change the format of the problem according to the user's level of understanding.

[0135] 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.

[0136] The data generation model 58 is a so-called generative AI (Artificial Intelligence). An example of the data generation model 58 is ChatGPT (registered trademark) (Internet search engine).<URL: https: / / openai.com / blog / chatgpt> Examples of the generative AI include a neural network (NN) and a neural network (NN). The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 receives a prompt containing an instruction, as well as inference data such as voice data representing speech, text data representing text, and image data representing an image (e.g., still image data or video data). The data generation model 58 performs inference on the input inference data in accordance with the instruction indicated by the prompt, and outputs the inference result in one or more data formats of voice data, text data, image data, etc. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization. The specification processing unit 290 performs the above-mentioned specification processing using the data generation model 58. The data generation model 58 may be a fine-tuned model so as to output an inference result from a prompt that does not include an instruction. In this case, the data generation model 58 can output an inference result from a prompt that does not include an instruction. The data processing device 12 and the like include multiple types of data generation models 58, and the data generation model 58 includes AIs other than the generative AI. The AI ​​other than the generative AI may be, for example, linear regression, logistic regression, decision tree, random forest, support vector machine (SVM), k-means clustering, convolutional neural network (CNN), recurrent neural network (RNN), generative adversarial network (GAN), or naive Bayes, and may perform various processes, but is not limited to these examples. The AI ​​may also be an AI agent. When the processing of each of the above-mentioned parts is performed by an AI, the processing may be performed in part or entirely by the AI, but is not limited to these examples. The processing performed by an AI including the generative AI may be replaced with rule-based processing, and rule-based processing may be replaced with processing performed by an AI including the generative AI.

[0137] 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.

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

[0139] [Second embodiment] FIG. 3 shows an example of the configuration of a data processing system 210 according to the second embodiment.

[0140] 3, the data processing system 210 includes a data processing device 12 and smart glasses 214. An example of the data processing device 12 is a server.

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

[0142] The 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.

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

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

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

[0146] 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.

[0147] 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.

[0148] 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.

[0149] 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.

[0150] 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.

[0151] 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.

[0152] The data generation model 58 is a so-called generative AI. An example of the data generation model 58 is a generative AI such as ChatGPT. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 receives a prompt including an instruction, as well as inference data such as audio data indicating speech, text data indicating text, and image data indicating an image (e.g., still image data or video data). The data generation model 58 performs inference on the input inference data in accordance with the instruction indicated by the prompt, and outputs the inference result in one or more data formats, such as audio data, text data, and image data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization. The identification processing unit 290 performs the above-mentioned identification processing using the data generation model 58. The data generation model 58 may be a fine-tuned model so as to output an inference result from a prompt that does not include an instruction. In this case, the data generation model 58 can output an inference result from a prompt that does not include an instruction. The data processing device 12 and the like include multiple types of data generation models 58, and the data generation models 58 include AIs other than the generation AI. Examples of AIs other than the generation AI include, but are not limited to, linear regression, logistic regression, decision trees, random forests, support vector machines (SVMs), k-means clustering, convolutional neural networks (CNNs), recurrent neural networks (RNNs), generative adversarial networks (GANs), and naive Bayes. These AIs can perform various types of processing, but are not limited to these examples. The AI ​​may also be an AI agent. When the processing of each of the above-described parts is performed by an AI, the processing may be performed in part or entirely by the AI, but is not limited to these examples. Processing performed by an AI, including the generation AI, may be replaced with rule-based processing, and rule-based processing may be replaced with processing performed by an AI, including the generation AI.

[0153] 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.

[0154] The correspondence between each part and the device or control part is not limited to the example described above, and various modifications are possible.

[0155] [Third embodiment] FIG. 5 shows an example of the configuration of a data processing system 310 according to the third embodiment.

[0156] 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.

[0157] 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.

[0158] 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.

[0159] 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.

[0160] 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).

[0161] 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.

[0162] 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.

[0163] The processor 28 reads the specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific processing is realized by the processor 28 operating as a specific processing unit 290 in accordance with the specific processing program 56 executed on the RAM 30.

[0164] The storage 32 stores a data generation model 58 and an emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290. The identification processing unit 290 can estimate a user's emotion using the emotion identification model 59 and perform identification processing using the user's emotion. The emotion estimation function (emotion identification function) using the emotion identification model 59 performs various estimations and predictions regarding the user's emotion, including estimation and prediction of the user's emotion, but is not limited to these examples. Furthermore, the estimation and prediction of emotion also includes, for example, emotion analysis.

[0165] In the 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.

[0166] Note that a device other than the data processing device 12 may have the data generation model 58. For example, a server device may have the data generation model 58. In this case, the data processing device 12 communicates with the server device having the data generation model 58 to obtain a processing result (such as a prediction result) using the data generation model 58. Furthermore, the data processing device 12 may be a server device, or may be a terminal device (for example, a mobile phone, a robot, a home appliance, etc.) owned by a user.

[0167] The specific processing unit 290 transmits the result of the specific processing to the 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.

[0168] The data generation model 58 is a so-called generative AI. An example of the data generation model 58 is a generative AI such as ChatGPT. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 receives a prompt including an instruction, as well as inference data such as audio data indicating speech, text data indicating text, and image data indicating an image (e.g., still image data or video data). The data generation model 58 performs inference on the input inference data in accordance with the instruction indicated by the prompt, and outputs the inference result in one or more data formats, such as audio data, text data, and image data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization. The identification processing unit 290 performs the above-mentioned identification processing using the data generation model 58. The data generation model 58 may be a fine-tuned model so as to output an inference result from a prompt that does not include an instruction. In this case, the data generation model 58 can output an inference result from a prompt that does not include an instruction. The data processing device 12 and the like include multiple types of data generation models 58, and the data generation models 58 include AIs other than the generation AI. Examples of AIs other than the generation AI include, but are not limited to, linear regression, logistic regression, decision trees, random forests, support vector machines (SVMs), k-means clustering, convolutional neural networks (CNNs), recurrent neural networks (RNNs), generative adversarial networks (GANs), and naive Bayes. These AIs can perform various types of processing, but are not limited to these examples. The AI ​​may also be an AI agent. When the processing of each of the above-described parts is performed by an AI, the processing may be performed in part or entirely by the AI, but is not limited to these examples. Processing performed by an AI, including the generation AI, may be replaced with rule-based processing, and rule-based processing may be replaced with processing performed by an AI, including the generation AI.

[0169] 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.

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

[0171] [Fourth embodiment] FIG. 7 shows an example of the configuration of a data processing system 410 according to the fourth embodiment.

[0172] 7, the data processing system 410 includes a data processing device 12 and a robot 414. An example of the data processing device 12 is a server.

[0173] 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.

[0174] 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.

[0175] 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.

[0176] 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).

[0177] 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.

[0178] 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.

[0179] 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.

[0180] 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.

[0181] 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.

[0182] 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.

[0183] 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.

[0184] 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.

[0185] The data generation model 58 is a so-called generative AI. An example of the data generation model 58 is a generative AI such as ChatGPT. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 receives a prompt including an instruction, as well as inference data such as audio data indicating speech, text data indicating text, and image data indicating an image (e.g., still image data or video data). The data generation model 58 performs inference on the input inference data in accordance with the instruction indicated by the prompt, and outputs the inference result in one or more data formats, such as audio data, text data, and image data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization. The identification processing unit 290 performs the above-mentioned identification processing using the data generation model 58. The data generation model 58 may be a fine-tuned model so as to output an inference result from a prompt that does not include an instruction. In this case, the data generation model 58 can output an inference result from a prompt that does not include an instruction. The data processing device 12 and the like include multiple types of data generation models 58, and the data generation models 58 include AIs other than the generation AI. Examples of AIs other than the generation AI include, but are not limited to, linear regression, logistic regression, decision trees, random forests, support vector machines (SVMs), k-means clustering, convolutional neural networks (CNNs), recurrent neural networks (RNNs), generative adversarial networks (GANs), and naive Bayes. These AIs can perform various types of processing, but are not limited to these examples. The AI ​​may also be an AI agent. When the processing of each of the above-described parts is performed by an AI, the processing may be performed in part or entirely by the AI, but is not limited to these examples. Processing performed by an AI, including the generation AI, may be replaced with rule-based processing, and rule-based processing may be replaced with processing performed by an AI, including the generation AI.

[0186] 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.

[0187] The correspondence between each part and the device or control part is not limited to the example described above, and various modifications are possible.

[0188] 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.

[0189] 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.

[0190] 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.

[0191] 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).

[0192] Human emotions are based on various balances, such as posture and blood sugar levels. When these balances deviate from the ideal, a state of discomfort is expressed, and when they approach the ideal, a state of pleasure is expressed. Emotions can also be created for robots, cars, and motorcycles, based on various balances, such as posture and remaining battery life. When these balances deviate from the ideal, a state of discomfort is expressed, and when they approach the ideal, a state of pleasure is expressed. An emotion map can be generated, for example, based on Dr. Mitsuyoshi's emotion map (Research on speech emotion recognition and brain physiological signal analysis systems for emotions, Tokushima University, doctoral dissertation: https: / / ci.nii.ac.jp / naid / 500000375379). The left half of the emotion map lists emotions belonging to the area called "reaction," where sensation is dominant. The right half of the emotion map lists emotions belonging to the area called "situation," where situational awareness is dominant.

[0193] 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."

[0194] 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.

[0195] 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.

[0196] 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.

[0197] 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.

[0198] 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.

[0199] 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.

[0200] 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.

[0201] 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.

[0202] 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.

[0203] 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.

[0204] 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.

[0205] 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.

[0206] [Explanation of symbols]

[0207] 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 reception desk where you can set your subject, desired study area, and grade level. a generation unit that automatically generates questions based on the setting content received by the reception unit; a scoring unit that scores the user's answers to the questions generated by the generating unit; a commentary unit that provides commentary based on the results of the scoring by the scoring unit; a detection unit that detects a weak area based on the comment result obtained by the comment unit; a completion unit that generates questions to complete the weak areas detected by the detection unit; a simplification unit that simplifies the questions generated by the completion unit in accordance with the user's level of understanding. A system characterized by:

2. The generation unit Generate questions based on specific subjects or grade ranges 2. The system of claim 1.

3. The scoring unit Determine if the user's answer is correct 2. The system of claim 1.

4. The commentary section If it's correct, explain why, if it's wrong, explain why 2. The system of claim 1.

5. The detection unit If you make frequent mistakes on a particular problem, you may be considered weak in that area.

2. The system of claim 1.

6. The complementing unit Generate completion questions related to a specific concept 2. The system of claim 1.

7. The simplification unit If the user is struggling with a difficult problem, present them with an easier version of that problem.

2. The system of claim 1.

8. The reception unit Estimate the user's emotions and customize the input interface for settings based on the estimated user emotions.

2. The system of claim 1.

Images