System

Abstract

An object of the system according to the embodiment is to cope with individual learning needs and provide effective learning support.SOLUTION: A system according to an embodiment includes a capture unit, an analysis unit, a provision unit, an accumulation unit, and a generation unit. The capturing unit captures the user's answer. The analysis unit analyzes the answer captured by the capture unit. The providing unit provides the advice based on the result analyzed by the analyzing unit. The accumulation unit accumulates the weak points based on the result analyzed by the analysis unit. The generation unit generates a problem for overcoming a weak point based on the difficult point accumulated by the accumulation unit.SELECTED DRAWING: Figure 1

Description

[Technical Field]

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

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

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

[0004] Conventional technology has faced challenges such as a shortage of private tutors and difficulty in meeting individual learning needs.

[0005] The system according to the embodiment aims to respond to individual learning needs and provide effective learning support. [Means for solving the problem]

[0006] The system according to the embodiment includes a capture unit, an analysis unit, a provision unit, a collection unit, and a generation unit. The capture unit captures the user's answers. The analysis unit analyzes the answers captured by the capture unit. The provision unit provides advice based on the results of the analysis by the analysis unit. The collection unit collects weak points based on the results of the analysis by the analysis unit. The generation unit generates questions for overcoming weaknesses based on the weak points collected by the collection unit. [Effects of the Invention]

[0007] The system according to the embodiment can respond to individual learning needs and provide effective learning support. [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 system according to an embodiment of the present invention uses AI smart glasses to provide tutor-like instruction. When a user solves a problem while wearing the smart glasses, a generation AI analyzes the user's answers in real time and provides advice as needed. For example, if a problem takes a long time to solve, the generation AI provides appropriate advice. The generation AI also identifies spelling and typos and provides guidance. Furthermore, the generation AI accumulates weak points based on the user's answers and generates questions to address these weaknesses. This allows it to address areas that are difficult for a real tutor to address. This allows the system using AI smart glasses to track a user's learning progress in real time and provide optimal individual instruction. For example, it can be used as a tool to alleviate the teacher shortage in schools.

[0029] The AI ​​smart glasses system according to the embodiment includes a capture unit, an analysis unit, a provision unit, an accumulation unit, and a generation unit. The capture unit captures a user's answers. For example, the capture unit can capture the answers in real time while the user is solving problems while wearing the smart glasses. The capture unit can use methods such as image capture, audio capture, and text capture. The analysis unit analyzes the answers captured by the capture unit using a generation AI. The analysis unit analyzes the content of the answers using methods such as natural language processing, statistical analysis, and machine learning algorithms. The provision unit provides advice based on the results of the analysis by the analysis unit. The provision unit can provide advice by methods such as text messages, audio guides, and video tutorials. The accumulation unit accumulates weak points based on the results of the analysis by the analysis unit. The accumulation unit accumulates weak points based on criteria such as specific problem areas and frequently made mistakes in problem types. The generation unit generates problems to overcome the weak points based on the weak points accumulated by the accumulation unit. The generation unit can generate questions based on criteria such as the difficulty level of the questions, the format of the questions, the frequency of questions, etc. As a result, the AI ​​smart glasses system according to the embodiment can analyze the user's answers in real time, provide appropriate advice, collect weak points, and generate questions to overcome the weaknesses.

[0030] The capture unit can capture the user's answers in real time. For example, the capture unit captures the answers in real time when the user solves a problem while wearing the smart glasses. The capture unit can use methods such as image capture, audio capture, and text capture. For example, the capture unit captures the answer using a camera in the smart glasses when the user inputs the answer. The capture unit can also record the user's voice with a microphone and perform audio capture. Furthermore, the capture unit can also perform text capture when the user inputs text. In this way, the user's answers can be captured in real time, allowing for immediate analysis.

[0031] The analysis unit analyzes the content of the user's answer and can provide appropriate advice if the user is taking too long to solve the problem or makes an error. The analysis unit uses the generation AI to analyze the content of the user's answer. The analysis unit analyzes the content of the answer using methods such as natural language processing, statistical analysis, and machine learning algorithms. The analysis unit analyzes the content of the user's answer and provides appropriate advice if the user is taking too long to solve the problem or makes an error. For example, if the user is taking too long to answer, the analysis unit causes the generation AI to provide a hint for the answer. Furthermore, if the user's answer contains an error, the analysis unit can have the generation AI point out the error and instruct the user on the correct way to answer. In this way, by analyzing the content of the user's answer and providing appropriate advice, learning efficiency can be improved.

[0032] The providing unit can find errors in spelling and typographical errors and provide guidance. The providing unit provides advice based on the results of analysis by the analyzing unit. The providing unit can provide advice by methods such as text messages, audio guides, and video tutorials. The providing unit can find errors in spelling and typographical errors and provide guidance. For example, the providing unit can use a generation AI to detect spelling and typographical errors included in the user's answer and provide guidance on correct spelling and grammar. The providing unit can also provide specific methods for the user to correct typographical errors. This can promote accurate answers by finding errors in spelling and typographical errors and providing guidance.

[0033] The accumulation unit can accumulate weak points based on the content of the user's answers. The accumulation unit accumulates weak points based on the results of analysis by the analysis unit. The accumulation unit accumulates weak points based on criteria such as a specific problem area or a type of problem that is frequently made incorrectly. The accumulation unit accumulates weak points based on the content of the user's answers. For example, if the user has difficulty with a specific mathematical concept, the accumulation unit accumulates problems related to that concept. The accumulation unit can also identify a type of problem that the user frequently makes mistakes on and accumulate weak points related to that type of problem. In this way, by accumulating the user's weak points, individual learning needs can be met.

[0034] The generation unit can generate questions to overcome weaknesses based on the accumulated weak points. The generation unit generates questions to overcome weaknesses based on the weak points accumulated by the accumulation unit. The generation unit can generate questions based on criteria such as question difficulty, question format, and question frequency. The generation unit generates questions to overcome weaknesses based on the accumulated weak points. For example, if a user has difficulty with a particular mathematical concept, the generation unit can generate questions related to that concept. The generation unit can also generate questions related to problem types that the user frequently makes mistakes on. This can support effective learning by generating questions to overcome the user's weak points.

[0035] The capture unit can analyze the user's past answer history and select the optimal capture method. The capture unit analyzes the user's past answer history and selects the optimal capture method. For example, the capture unit preferentially selects a capture method (audio, text, etc.) that the user has frequently used in the past. The capture unit can also select the optimal capture method for a specific time period from the user's past answer history. Furthermore, the capture unit can analyze the user's past answer history and select the most efficient capture method. In this way, the optimal capture method can be selected by analyzing the user's past answer history.

[0036] The capture unit can filter answers based on the user's current learning situation and areas of interest when capturing answers. The capture unit can filter answers based on the user's current learning situation and areas of interest when capturing answers. For example, the capture unit captures only answers related to the area the user is currently studying. The capture unit can also preferentially capture highly relevant answers based on the user's areas of interest. Furthermore, the capture unit can filter and capture appropriate answers according to the user's learning progress. In this way, highly relevant answers can be captured by filtering based on the user's learning situation and areas of interest.

[0037] The capture unit can select the optimal capture means depending on the user's input method when capturing an answer. The capture unit selects the optimal capture means depending on the user's input method (voice, text, handwriting, etc.) when capturing an answer. For example, if the user is answering by voice, the capture unit can preferentially select voice capture. Also, if the user is answering by text, the capture unit can preferentially select text capture. Furthermore, if the user is answering by handwriting, the capture unit can preferentially select handwriting capture. This allows for efficient capture by selecting the optimal capture means depending on the user's input method.

[0038] When capturing answers, the capture unit can prioritize capturing highly relevant answers by taking into account the user's geographical location information. When capturing answers, the capture unit prioritizes capturing highly relevant answers by taking into account the user's geographical location information. For example, when the user is in a specific area, the capture unit prioritizes capturing answers related to that area. Furthermore, when the user is moving, the capture unit can also prioritize capturing answers related to the user's current location. Furthermore, when the user is in a specific location, the capture unit can also prioritize capturing answers related to that location. In this way, highly relevant answers can be captured by taking into account the user's geographical location information.

[0039] The capture unit can analyze the user's social media activity when capturing an answer and capture related answers. The capture unit can analyze the user's social media activity when capturing an answer and capture related answers. For example, the capture unit captures answers related to content shared by the user on social media. The capture unit can also analyze the user's social media activity and capture related answers. Furthermore, the capture unit can capture related answers by referring to the activity of the user's friends on social media. In this way, related answers can be captured by analyzing the user's social media activity.

[0040] The capture unit can customize the capture method by reflecting the user's past feedback when capturing an answer. The capture unit customizes the capture method by reflecting the user's past feedback when capturing an answer. The capture unit selects the optimal capture method based on, for example, feedback provided by the user in the past. The capture unit can also customize a specific capture method based on the user's past feedback. Furthermore, the capture unit can optimize the capture method by reflecting the user's past feedback. In this way, the optimal capture method can be customized by reflecting the user's past feedback.

[0041] The analysis unit can adjust the level of detail of the analysis based on the importance of the answer during analysis. The analysis unit uses the generation AI to adjust the level of detail of the analysis based on the importance of the answer during analysis. The analysis unit adjusts the level of detail of the analysis based on criteria such as the importance of the answer, the purpose of the analysis, and the user's level of understanding. The analysis unit performs a detailed analysis for important answers. The analysis unit can also perform a concise analysis for answers with low importance. Furthermore, the analysis unit can dynamically adjust the level of detail of the analysis according to the importance of the answer. This enables efficient analysis by adjusting the level of detail of the analysis based on the importance of the answer.

[0042] The analysis unit can apply different analysis algorithms depending on the category of the answer during analysis. The analysis unit uses the generation AI to apply different analysis algorithms depending on the category of the answer during analysis. The analysis unit performs analysis using methods such as natural language processing algorithms, machine learning algorithms, and statistical analysis algorithms. The analysis unit applies an analysis algorithm specifically for mathematics to mathematics answers. The analysis unit can also apply an analysis algorithm specifically for English to English answers. Furthermore, the analysis unit can apply an analysis algorithm specifically for science to science answers. In this way, by applying different analysis algorithms depending on the category of the answer, more accurate analysis is possible.

[0043] The analysis unit can improve the accuracy of the analysis by referring to the user's past analysis results during analysis. The analysis unit uses the generation AI to improve the accuracy of the analysis by referring to the user's past analysis results during analysis. The analysis unit improves the accuracy of the analysis based on criteria such as past answer data, the accuracy of the analysis results, and user feedback. The analysis unit improves the accuracy of the current analysis based on the user's past analysis results. The analysis unit can also optimize the analysis algorithm by referring to the user's past analysis results. Furthermore, the analysis unit can analyze the user's past analysis results and improve the accuracy of the analysis. In this way, the accuracy of the analysis can be improved by referring to the user's past analysis results.

[0044] The analysis unit can determine the analysis priority based on the time of answer submission during analysis. The analysis unit uses the generation AI to determine the analysis priority based on the time of answer submission during analysis. The analysis unit determines the analysis priority based on criteria such as the time of answer submission, the importance of the answer, and the purpose of the analysis. The analysis unit prioritizes analysis of answers that have been submitted recently. The analysis unit can also postpone answers that have been submitted older. Furthermore, the analysis unit can dynamically adjust the analysis priority based on the time of submission. This enables efficient analysis by determining the analysis priority based on the time of answer submission.

[0045] The analysis unit can adjust the order of analysis based on the relevance of the answers during analysis. The analysis unit uses the generation AI to adjust the order of analysis based on the relevance of the answers during analysis. The analysis unit adjusts the order of analysis based on criteria such as the relevance of the answers, the importance of the answers, and the purpose of the analysis. The analysis unit prioritizes analysis of highly relevant answers. The analysis unit can also postpone less relevant answers. Furthermore, the analysis unit can dynamically adjust the order of analysis based on the relevance of the answers. This enables efficient analysis by adjusting the order of analysis based on the relevance of the answers.

[0046] The analysis unit can adjust the use of technical terms in the analysis according to the user's level of expertise during analysis. The analysis unit uses the generation AI to adjust the use of technical terms in the analysis according to the user's level of expertise during analysis. The analysis unit adjusts the use of technical terms in the analysis based on criteria such as the user's level of expertise, the purpose of the analysis, and the content of the answer. If the user's level of expertise is high, the analysis unit provides an analysis that makes heavy use of technical terms. In addition, if the user's level of expertise is low, the analysis unit can also provide an analysis in simpler terms. Furthermore, the analysis unit can dynamically adjust the use of technical terms in the analysis according to the user's level of expertise. This makes it possible to provide analysis results that are easier to understand by adjusting the use of technical terms in the analysis according to the user's level of expertise.

[0047] The providing unit can adjust the level of detail of the advice based on the importance of the answer when providing the advice. The providing unit uses AI to adjust the level of detail of the advice based on the importance of the answer when providing the advice. The providing unit adjusts the level of detail of the advice based on criteria such as the importance of the answer, the purpose of the advice, and the user's level of understanding. The providing unit provides detailed advice for important answers. The providing unit can also provide concise advice for answers with low importance. Furthermore, the providing unit can dynamically adjust the level of detail of the advice according to the importance of the answer. This enables efficient advice by adjusting the level of detail of the advice based on the importance of the answer.

[0048] The providing unit can apply different advice algorithms depending on the category of the answer when providing advice. The providing unit uses AI to apply different advice algorithms depending on the category of the answer when providing advice. The providing unit provides advice using methods such as natural language processing algorithms, machine learning algorithms, and statistical analysis algorithms. The providing unit applies a mathematics-specific advice algorithm to mathematics answers. The providing unit can also apply an English-specific advice algorithm to English answers. The providing unit can also apply a science-specific advice algorithm to science answers. In this way, applying different advice algorithms depending on the answer category enables more accurate advice.

[0049] The providing unit can determine the priority of advice based on the time of submission of the answer when providing the advice. The providing unit uses AI to determine the priority of advice based on the time of submission of the answer when providing the advice. The providing unit determines the priority of advice based on criteria such as the time of submission of the answer, the importance of the answer, and the purpose of the advice. The providing unit provides advice preferentially to answers that have been submitted recently. The providing unit can also postpone answers that have been submitted older. Furthermore, the providing unit can dynamically adjust the priority of advice based on the time of submission. This enables efficient advice by determining the priority of advice based on the time of submission of the answer.

[0050] The providing unit can adjust the order of advice based on the relevance of the answers when providing advice. The providing unit uses AI to adjust the order of advice based on the relevance of the answers when providing advice. The providing unit adjusts the order of advice based on criteria such as the relevance of the answers, the importance of the answers, and the purpose of the advice. The providing unit provides advice preferentially for highly relevant answers. The providing unit can also postpone less relevant answers. Furthermore, the providing unit can dynamically adjust the order of advice based on the relevance of the answers. This enables efficient advice by adjusting the order of advice based on the relevance of the answers.

[0051] The providing unit can adjust the use of technical terms in the advice according to the user's level of expertise when providing the advice. The providing unit uses AI to adjust the use of technical terms in the advice according to the user's level of expertise when providing the advice. The providing unit adjusts the use of technical terms in the advice based on criteria such as the user's level of expertise, the purpose of the advice, and the content of the answer. If the user's level of expertise is high, the providing unit provides advice that uses a lot of technical terms. Furthermore, if the user's level of expertise is low, the providing unit can also provide advice in simpler terms. Furthermore, the providing unit can dynamically adjust the use of technical terms in the advice according to the user's level of expertise. In this way, by adjusting the use of technical terms in the advice according to the user's level of expertise, it is possible to provide advice that is easier to understand.

[0052] The accumulation unit can adjust the level of detail of weak points based on the importance of the answer when accumulating. The accumulation unit uses the generation AI to adjust the level of detail of weak points based on the importance of the answer when accumulating. The accumulation unit adjusts the level of detail of weak points based on criteria such as the importance of the answer, the purpose of accumulation, and the user's level of understanding. The accumulation unit accumulates detailed weak points for important answers. The accumulation unit can also accumulate concise weak points for answers with low importance. Furthermore, the accumulation unit can dynamically adjust the level of detail of weak points according to the importance of the answer. This enables efficient accumulation by adjusting the level of detail of weak points based on the importance of the answer.

[0053] The accumulation unit can apply different accumulation algorithms depending on the category of the answer when accumulating. The accumulation unit uses a generation AI to apply different accumulation algorithms depending on the category of the answer when accumulating. The accumulation unit performs accumulation using methods such as natural language processing algorithms, machine learning algorithms, and statistical analysis algorithms. The accumulation unit applies an accumulation algorithm dedicated to mathematics to mathematics answers. The accumulation unit can also apply an accumulation algorithm dedicated to English to English answers. Furthermore, the accumulation unit can also apply an accumulation algorithm dedicated to science to science answers. In this way, by applying different accumulation algorithms depending on the category of the answer, more accurate accumulation is possible.

[0054] The accumulation unit can improve the accuracy of accumulation by referring to the user's past accumulation results when accumulating. The accumulation unit uses the generation AI to improve the accuracy of accumulation by referring to the user's past accumulation results when accumulating. The accumulation unit improves the accuracy of accumulation based on criteria such as past answer data, the accuracy of the accumulation results, and user feedback. The accumulation unit improves the accuracy of the current accumulation based on the user's past accumulation results. The accumulation unit can also optimize the accumulation algorithm by referring to the user's past accumulation results. Furthermore, the accumulation unit can analyze the user's past accumulation results and improve the accuracy of accumulation. In this way, the accuracy of accumulation can be improved by referring to the user's past accumulation results.

[0055] The accumulation unit can determine the priority of weak points based on the time of submission of answers when accumulating. The accumulation unit uses a generation AI to determine the priority of weak points based on the time of submission of answers when accumulating. The accumulation unit determines the priority of weak points based on criteria such as the time of submission of the answer, the importance of the answer, and the purpose of accumulation. The accumulation unit prioritizes weak points in answers that have been submitted recently. The accumulation unit can also postpone weak points in answers that have been submitted older. Furthermore, the accumulation unit can dynamically adjust the priority of weak points based on the time of submission. This enables efficient accumulation by determining the priority of weak points based on the time of submission of the answer.

[0056] The accumulation unit can adjust the order of weak points based on the relevance of the answers when accumulating. The accumulation unit uses a generation AI to adjust the order of weak points based on the relevance of the answers when accumulating. The accumulation unit adjusts the order of weak points based on criteria such as the relevance of the answers, the importance of the answers, and the purpose of accumulation. The accumulation unit prioritizes accumulating weak points of highly relevant answers. The accumulation unit can also postpone weak points of less relevant answers. Furthermore, the accumulation unit can dynamically adjust the order of weak points based on the relevance of the answers. This allows for efficient accumulation by adjusting the order of weak points based on the relevance of the answers.

[0057] The accumulation unit can adjust the level of detail of weak points according to the user's level of expertise when accumulating. The accumulation unit uses the generation AI to adjust the level of detail of weak points according to the user's level of expertise when accumulating. The accumulation unit adjusts the level of detail of weak points based on criteria such as the user's level of expertise, the purpose of accumulation, and the content of the answer. If the user's level of expertise is high, the accumulation unit accumulates detailed weak points. Also, if the user's level of expertise is low, the accumulation unit can accumulate concise weak points. Furthermore, the accumulation unit can dynamically adjust the level of detail of weak points according to the user's level of expertise. In this way, by adjusting the level of detail of weak points according to the user's level of expertise, more appropriate weak points can be accumulated.

[0058] The generation unit can adjust the level of detail of the questions based on the importance of the weak points when generating the questions. The generation unit uses the generation AI to adjust the level of detail of the questions based on the importance of the weak points when generating the questions. The generation unit adjusts the level of detail of the questions based on criteria such as the importance of the weak points, the purpose of the question, and the user's level of understanding. The generation unit generates detailed questions for important weak points. The generation unit can also generate concise questions for weak points with low importance. Furthermore, the generation unit can dynamically adjust the level of detail of the questions according to the importance of the weak points. This enables efficient question generation by adjusting the level of detail of the questions based on the importance of the weak points.

[0059] The generation unit can apply different generation algorithms depending on the category of weak points when generating questions. The generation unit uses a generation AI to apply different generation algorithms depending on the category of weak points when generating questions. The generation unit generates questions using methods such as natural language processing algorithms, machine learning algorithms, and statistical analysis algorithms. The generation unit applies a generation algorithm specifically for mathematics to weak points in mathematics. The generation unit can also apply a generation algorithm specifically for English to weak points in English. Furthermore, the generation unit can apply a generation algorithm specifically for science to weak points in science. In this way, by applying different generation algorithms depending on the category of weak points, more accurate question generation is possible.

[0060] The generation unit can improve the accuracy of questions by referring to the user's past generation results when generating questions. The generation unit uses a generation AI to improve the accuracy of questions by referring to the user's past generation results when generating questions. The generation unit improves the accuracy of questions based on criteria such as past answer data, the accuracy of the generation results, and user feedback. The generation unit improves the accuracy of current questions based on the user's past generation results. The generation unit can also optimize the generation algorithm by referring to the user's past generation results. Furthermore, the generation unit can analyze the user's past generation results and improve the accuracy of questions. In this way, the accuracy of questions can be improved by referring to the user's past generation results.

[0061] The generation unit can determine the priority of questions based on the time of submission of weak points when generating questions. The generation unit uses the generation AI to determine the priority of questions based on the time of submission of weak points when generating questions. The generation unit determines the priority of questions based on criteria such as the time of submission of weak points, the importance of weak points, and the purpose of the question. The generation unit generates questions with priority given to weak points that have been submitted recently. The generation unit can also postpone weak points that have been submitted older. Furthermore, the generation unit can dynamically adjust the priority of questions based on the time of submission. This enables efficient question generation by determining the priority of questions based on the time of submission of weak points.

[0062] The generation unit can adjust the order of questions based on the relevance of weak points when generating questions. The generation unit uses the generation AI to adjust the order of questions based on the relevance of weak points when generating questions. The generation unit adjusts the order of questions based on criteria such as the relevance of weak points, the importance of weak points, and the purpose of the question. The generation unit generates questions with priority for weak points that are highly relevant. The generation unit can also postpone weak points that are less relevant. Furthermore, the generation unit can dynamically adjust the order of questions based on the relevance of weak points. This enables efficient question generation by adjusting the order of questions based on the relevance of weak points.

[0063] The generation unit can adjust the use of technical terminology in questions according to the user's level of expertise when generating questions. The generation unit uses a generation AI to adjust the use of technical terminology in questions according to the user's level of expertise when generating questions. The generation unit adjusts the use of technical terminology in questions based on criteria such as the user's level of expertise, the purpose of the question, and the content of the user's weak points. If the user's level of expertise is high, the generation unit generates questions that use a lot of technical terminology. In addition, if the user's level of expertise is low, the generation unit can also generate questions in simple language. Furthermore, the generation unit can dynamically adjust the use of technical terminology in questions according to the user's level of expertise. In this way, by adjusting the use of technical terminology in questions according to the user's level of expertise, questions that are easier to understand can be generated.

[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] When capturing a user's answers, the capture unit can monitor the user's learning environment and adjust the capture method according to changes in the environment. For example, if the user is studying in a quiet environment, it can prioritize audio capture. Also, if the user is on the move, it can prioritize text capture. Furthermore, if the user is studying in a group, it can simultaneously capture multiple audio recordings and analyze them individually in the analysis unit. This allows for more effective learning support by selecting the optimal capture method according to the user's learning environment.

[0066] When analyzing the content of a user's answers, the analysis unit can also improve the accuracy of the analysis by taking into account the user's learning history. For example, it can focus its analysis on areas where the user made mistakes in similar questions in the past. It can also perform a concise analysis of answers in areas in which the user excels. Furthermore, it can dynamically adjust the level of detail of the analysis according to the user's learning progress. This allows for more accurate analysis by taking into account the user's learning history.

[0067] When providing advice on a user's answer, the providing unit can also customize the format of the advice according to the user's learning style. For example, advice using diagrams and graphs can be provided to a user who prefers visual learning. Audio guides can also be provided preferentially to a user who prefers auditory learning. Furthermore, advice incorporating real-life examples can be provided to a user who prefers practical learning. In this way, the learning effect can be maximized by providing advice according to the user's learning style.

[0068] When accumulating the user's weak points, the accumulation unit can also adjust the accumulation method based on the user's learning goals. For example, for short-term goals, weak points can be accumulated based on the most recent answers. For long-term goals, weak points can be accumulated by taking into account the entire past answer history. Furthermore, for users aiming to take a specific exam or obtain a qualification, questions related to that exam can be accumulated with a focus. This makes it possible to accumulate weak points according to the user's learning goals.

[0069] When generating questions based on the user's weak points, the generation unit can also adjust the difficulty of the questions according to the user's learning pace. For example, it can generate high-difficulty questions for a user who learns at a fast pace. It can also generate basic questions for a user who learns at a slow pace. It can also adjust the frequency of questions according to the user's learning pace. This makes it possible to provide effective learning support by generating questions according to the user's learning pace.

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

[0071] Step 1: The capture unit captures the user's answer. For example, the capture unit can capture the answer in real time while the user is solving the problem while wearing the smart glasses. The capture unit can also use methods such as image capture, audio capture, and text capture. Step 2: The analysis unit uses the generation AI to analyze the answers captured by the capture unit. The analysis unit analyzes the content of the answers using methods such as natural language processing, statistical analysis, and machine learning algorithms. Step 3: The providing unit provides advice based on the results of the analysis by the analyzing unit. The providing unit can provide advice by, for example, a text message, an audio guide, a video tutorial, or the like. Step 4: The accumulation unit accumulates weak points based on the results of the analysis by the analysis unit. For example, the accumulation unit accumulates weak points based on criteria such as specific problem areas or frequently made mistakes in problem types. Step 5: The generator generates questions to overcome the weaknesses based on the weak points accumulated by the accumulation unit. The generator can generate questions based on criteria such as difficulty level, question format, and question frequency.

[0072] (Example 2) A system according to an embodiment of the present invention uses AI smart glasses to provide tutor-like instruction. When a user solves a problem while wearing the smart glasses, a generation AI analyzes the user's answers in real time and provides advice as needed. For example, if a problem takes a long time to solve, the generation AI provides appropriate advice. The generation AI also identifies spelling and typos and provides guidance. Furthermore, the generation AI accumulates weak points based on the user's answers and generates questions to address these weaknesses. This allows it to address areas that are difficult for a real tutor to address. This allows the system using AI smart glasses to track a user's learning progress in real time and provide optimal individual instruction. For example, it can be used as a tool to alleviate the teacher shortage in schools.

[0073] The AI ​​smart glasses system according to the embodiment includes a capture unit, an analysis unit, a provision unit, an accumulation unit, and a generation unit. The capture unit captures a user's answers. For example, the capture unit can capture the answers in real time while the user is solving problems while wearing the smart glasses. The capture unit can use methods such as image capture, audio capture, and text capture. The analysis unit analyzes the answers captured by the capture unit using a generation AI. The analysis unit analyzes the content of the answers using methods such as natural language processing, statistical analysis, and machine learning algorithms. The provision unit provides advice based on the results of the analysis by the analysis unit. The provision unit can provide advice by methods such as text messages, audio guides, and video tutorials. The accumulation unit accumulates weak points based on the results of the analysis by the analysis unit. The accumulation unit accumulates weak points based on criteria such as specific problem areas and frequently made mistakes in problem types. The generation unit generates problems to overcome the weak points based on the weak points accumulated by the accumulation unit. The generation unit can generate questions based on criteria such as the difficulty level of the questions, the format of the questions, the frequency of questions, etc. As a result, the AI ​​smart glasses system according to the embodiment can analyze the user's answers in real time, provide appropriate advice, collect weak points, and generate questions to overcome the weaknesses.

[0074] The capture unit can capture the user's answers in real time. For example, the capture unit captures the answers in real time when the user solves a problem while wearing the smart glasses. The capture unit can use methods such as image capture, audio capture, and text capture. For example, the capture unit captures the answer using a camera in the smart glasses when the user inputs the answer. The capture unit can also record the user's voice with a microphone and perform audio capture. Furthermore, the capture unit can also perform text capture when the user inputs text. In this way, the user's answers can be captured in real time, allowing for immediate analysis.

[0075] The analysis unit analyzes the content of the user's answer and can provide appropriate advice if the user is taking too long to solve the problem or makes an error. The analysis unit uses the generation AI to analyze the content of the user's answer. The analysis unit analyzes the content of the answer using methods such as natural language processing, statistical analysis, and machine learning algorithms. The analysis unit analyzes the content of the user's answer and provides appropriate advice if the user is taking too long to solve the problem or makes an error. For example, if the user is taking too long to answer, the analysis unit causes the generation AI to provide a hint for the answer. Furthermore, if the user's answer contains an error, the analysis unit can have the generation AI point out the error and instruct the user on the correct way to answer. In this way, by analyzing the content of the user's answer and providing appropriate advice, learning efficiency can be improved.

[0076] The providing unit can find errors in spelling and typographical errors and provide guidance. The providing unit provides advice based on the results of analysis by the analyzing unit. The providing unit can provide advice by methods such as text messages, audio guides, and video tutorials. The providing unit can find errors in spelling and typographical errors and provide guidance. For example, the providing unit can use a generation AI to detect spelling and typographical errors included in the user's answer and provide guidance on correct spelling and grammar. The providing unit can also provide specific methods for the user to correct typographical errors. This can promote accurate answers by finding errors in spelling and typographical errors and providing guidance.

[0077] The accumulation unit can accumulate weak points based on the content of the user's answers. The accumulation unit accumulates weak points based on the results of analysis by the analysis unit. The accumulation unit accumulates weak points based on criteria such as a specific problem area or a type of problem that is frequently made incorrectly. The accumulation unit accumulates weak points based on the content of the user's answers. For example, if the user has difficulty with a specific mathematical concept, the accumulation unit accumulates problems related to that concept. The accumulation unit can also identify a type of problem that the user frequently makes mistakes on and accumulate weak points related to that type of problem. In this way, by accumulating the user's weak points, individual learning needs can be met.

[0078] The generation unit can generate questions to overcome weaknesses based on the accumulated weak points. The generation unit generates questions to overcome weaknesses based on the weak points accumulated by the accumulation unit. The generation unit can generate questions based on criteria such as question difficulty, question format, and question frequency. The generation unit generates questions to overcome weaknesses based on the accumulated weak points. For example, if a user has difficulty with a particular mathematical concept, the generation unit can generate questions related to that concept. The generation unit can also generate questions related to problem types that the user frequently makes mistakes on. This can support effective learning by generating questions to overcome the user's weak points.

[0079] The capture unit can estimate the user's emotions and adjust the timing of capturing an answer based on the estimated user's emotions. The capture unit estimates the user's emotions and adjusts the timing of capturing an answer based on the estimated user's emotions. The capture unit estimates the user's emotions using methods such as facial expression recognition, voice analysis, and self-reporting. If the user is in a hurry, the capture unit can delay the timing of capturing an answer and capture it after the user has calmed down. Furthermore, if the user is relaxed, the capture unit can also advance the timing of capturing an answer to capture it smoothly. Furthermore, if the user is concentrating, the capture unit can optimize the timing of capturing an answer so as not to disturb the user's concentration. In this way, by adjusting the capture timing according to the user's emotions, it is possible to capture an answer at a more appropriate timing.

[0080] The capture unit can analyze the user's past answer history and select the optimal capture method. The capture unit analyzes the user's past answer history and selects the optimal capture method. For example, the capture unit preferentially selects a capture method (audio, text, etc.) that the user has frequently used in the past. The capture unit can also select the optimal capture method for a specific time period from the user's past answer history. Furthermore, the capture unit can analyze the user's past answer history and select the most efficient capture method. In this way, the optimal capture method can be selected by analyzing the user's past answer history.

[0081] The capture unit can filter answers based on the user's current learning situation and areas of interest when capturing answers. The capture unit can filter answers based on the user's current learning situation and areas of interest when capturing answers. For example, the capture unit captures only answers related to the area the user is currently studying. The capture unit can also preferentially capture highly relevant answers based on the user's areas of interest. Furthermore, the capture unit can filter and capture appropriate answers according to the user's learning progress. In this way, highly relevant answers can be captured by filtering based on the user's learning situation and areas of interest.

[0082] The capture unit can select the optimal capture means depending on the user's input method when capturing an answer. The capture unit selects the optimal capture means depending on the user's input method (voice, text, handwriting, etc.) when capturing an answer. For example, if the user is answering by voice, the capture unit can preferentially select voice capture. Also, if the user is answering by text, the capture unit can preferentially select text capture. Furthermore, if the user is answering by handwriting, the capture unit can preferentially select handwriting capture. This allows for efficient capture by selecting the optimal capture means depending on the user's input method.

[0083] The capture unit can estimate the user's emotions and determine the priority of answers to be captured based on the estimated user's emotions. The capture unit estimates the user's emotions and determines the priority of answers to be captured based on the estimated user's emotions. The capture unit estimates the user's emotions using methods such as facial expression recognition, voice analysis, and self-reporting. The capture unit prioritizes capturing important answers when the user is in a hurry. The capture unit can also capture all answers equally when the user is relaxed. Furthermore, the capture unit can prioritize capturing answers with higher difficulty when the user is concentrating. In this way, by determining the priority of answers to be captured according to the user's emotions, important answers can be captured with higher priority.

[0084] When capturing answers, the capture unit can prioritize capturing highly relevant answers by taking into account the user's geographical location information. When capturing answers, the capture unit prioritizes capturing highly relevant answers by taking into account the user's geographical location information. For example, when the user is in a specific area, the capture unit prioritizes capturing answers related to that area. Furthermore, when the user is moving, the capture unit can also prioritize capturing answers related to the user's current location. Furthermore, when the user is in a specific location, the capture unit can also prioritize capturing answers related to that location. In this way, highly relevant answers can be captured by taking into account the user's geographical location information.

[0085] The capture unit can analyze the user's social media activity when capturing an answer and capture related answers. The capture unit can analyze the user's social media activity when capturing an answer and capture related answers. For example, the capture unit captures answers related to content shared by the user on social media. The capture unit can also analyze the user's social media activity and capture related answers. Furthermore, the capture unit can capture related answers by referring to the activity of the user's friends on social media. In this way, related answers can be captured by analyzing the user's social media activity.

[0086] The capture unit can customize the capture method by reflecting the user's past feedback when capturing an answer. The capture unit customizes the capture method by reflecting the user's past feedback when capturing an answer. The capture unit selects the optimal capture method based on, for example, feedback provided by the user in the past. The capture unit can also customize a specific capture method based on the user's past feedback. Furthermore, the capture unit can optimize the capture method by reflecting the user's past feedback. In this way, the optimal capture method can be customized by reflecting the user's past feedback.

[0087] The analysis unit can estimate the user's emotions and adjust the way the analysis is presented based on the estimated user's emotions. The analysis unit uses generative AI to estimate the user's emotions and adjust the way the analysis is presented based on the estimated user's emotions. The analysis unit estimates the user's emotions using methods such as facial expression recognition, voice analysis, and self-reporting. The analysis unit provides detailed analysis results when the user is relaxed. The analysis unit can also provide concise analysis results when the user is impatient. Furthermore, the analysis unit can provide analysis results that emphasize important points when the user is concentrating. This makes it possible to provide more appropriate analysis results by adjusting the way the analysis is presented according to the user's emotions.

[0088] The analysis unit can adjust the level of detail of the analysis based on the importance of the answer during analysis. The analysis unit uses the generation AI to adjust the level of detail of the analysis based on the importance of the answer during analysis. The analysis unit adjusts the level of detail of the analysis based on criteria such as the importance of the answer, the purpose of the analysis, and the user's level of understanding. The analysis unit performs a detailed analysis for important answers. The analysis unit can also perform a concise analysis for answers with low importance. Furthermore, the analysis unit can dynamically adjust the level of detail of the analysis according to the importance of the answer. This enables efficient analysis by adjusting the level of detail of the analysis based on the importance of the answer.

[0089] The analysis unit can apply different analysis algorithms depending on the category of the answer during analysis. The analysis unit uses the generation AI to apply different analysis algorithms depending on the category of the answer during analysis. The analysis unit performs analysis using methods such as natural language processing algorithms, machine learning algorithms, and statistical analysis algorithms. The analysis unit applies an analysis algorithm specifically for mathematics to mathematics answers. The analysis unit can also apply an analysis algorithm specifically for English to English answers. Furthermore, the analysis unit can apply an analysis algorithm specifically for science to science answers. In this way, by applying different analysis algorithms depending on the category of the answer, more accurate analysis is possible.

[0090] The analysis unit can improve the accuracy of the analysis by referring to the user's past analysis results during analysis. The analysis unit uses the generation AI to improve the accuracy of the analysis by referring to the user's past analysis results during analysis. The analysis unit improves the accuracy of the analysis based on criteria such as past answer data, the accuracy of the analysis results, and user feedback. The analysis unit improves the accuracy of the current analysis based on the user's past analysis results. The analysis unit can also optimize the analysis algorithm by referring to the user's past analysis results. Furthermore, the analysis unit can analyze the user's past analysis results and improve the accuracy of the analysis. In this way, the accuracy of the analysis can be improved by referring to the user's past analysis results.

[0091] The analysis unit can estimate the user's emotions and adjust the length of the analysis based on the estimated user emotions. The analysis unit uses generative AI to estimate the user's emotions and adjust the length of the analysis based on the estimated user emotions. The analysis unit estimates the user's emotions using methods such as facial expression recognition, voice analysis, and self-reporting. The analysis unit can provide a short, to-the-point analysis when the user is in a hurry. The analysis unit can also provide a detailed analysis when the user is relaxed. Furthermore, the analysis unit can provide an analysis that emphasizes important points when the user is concentrating. This allows the length of the analysis to be adjusted according to the user's emotions, thereby providing more appropriate analysis results.

[0092] The analysis unit can determine the analysis priority based on the time of answer submission during analysis. The analysis unit uses the generation AI to determine the analysis priority based on the time of answer submission during analysis. The analysis unit determines the analysis priority based on criteria such as the time of answer submission, the importance of the answer, and the purpose of the analysis. The analysis unit prioritizes analysis of answers that have been submitted recently. The analysis unit can also postpone answers that have been submitted older. Furthermore, the analysis unit can dynamically adjust the analysis priority based on the time of submission. This enables efficient analysis by determining the analysis priority based on the time of answer submission.

[0093] The analysis unit can adjust the order of analysis based on the relevance of the answers during analysis. The analysis unit uses the generation AI to adjust the order of analysis based on the relevance of the answers during analysis. The analysis unit adjusts the order of analysis based on criteria such as the relevance of the answers, the importance of the answers, and the purpose of the analysis. The analysis unit prioritizes analysis of highly relevant answers. The analysis unit can also postpone less relevant answers. Furthermore, the analysis unit can dynamically adjust the order of analysis based on the relevance of the answers. This enables efficient analysis by adjusting the order of analysis based on the relevance of the answers.

[0094] The analysis unit can adjust the use of technical terms in the analysis according to the user's level of expertise during analysis. The analysis unit uses the generation AI to adjust the use of technical terms in the analysis according to the user's level of expertise during analysis. The analysis unit adjusts the use of technical terms in the analysis based on criteria such as the user's level of expertise, the purpose of the analysis, and the content of the answer. If the user's level of expertise is high, the analysis unit provides an analysis that makes heavy use of technical terms. In addition, if the user's level of expertise is low, the analysis unit can also provide an analysis in simpler terms. Furthermore, the analysis unit can dynamically adjust the use of technical terms in the analysis according to the user's level of expertise. This makes it possible to provide analysis results that are easier to understand by adjusting the use of technical terms in the analysis according to the user's level of expertise.

[0095] The providing unit can estimate the user's emotions and adjust the way in which advice is expressed based on the estimated user's emotions. The providing unit uses AI to estimate the user's emotions and adjust the way in which advice is expressed based on the estimated user's emotions. The providing unit estimates the user's emotions using methods such as facial expression recognition, voice analysis, and self-reporting. The providing unit provides detailed advice when the user is relaxed. The providing unit can also provide concise advice when the user is impatient. Furthermore, the providing unit can provide advice that emphasizes important points when the user is concentrating. This makes it possible to provide more appropriate advice by adjusting the way in which advice is expressed according to the user's emotions.

[0096] The providing unit can adjust the level of detail of the advice based on the importance of the answer when providing the advice. The providing unit uses AI to adjust the level of detail of the advice based on the importance of the answer when providing the advice. The providing unit adjusts the level of detail of the advice based on criteria such as the importance of the answer, the purpose of the advice, and the user's level of understanding. The providing unit provides detailed advice for important answers. The providing unit can also provide concise advice for answers with low importance. Furthermore, the providing unit can dynamically adjust the level of detail of the advice according to the importance of the answer. This enables efficient advice by adjusting the level of detail of the advice based on the importance of the answer.

[0097] The providing unit can apply different advice algorithms depending on the category of the answer when providing advice. The providing unit uses AI to apply different advice algorithms depending on the category of the answer when providing advice. The providing unit provides advice using methods such as natural language processing algorithms, machine learning algorithms, and statistical analysis algorithms. The providing unit applies a mathematics-specific advice algorithm to mathematics answers. The providing unit can also apply an English-specific advice algorithm to English answers. The providing unit can also apply a science-specific advice algorithm to science answers. In this way, applying different advice algorithms depending on the answer category enables more accurate advice.

[0098] The providing unit can estimate the user's emotions and adjust the length of the advice based on the estimated user's emotions. The providing unit uses AI to estimate the user's emotions and adjust the length of the advice based on the estimated user's emotions. The providing unit estimates the user's emotions using methods such as facial expression recognition, voice analysis, and self-reporting. The providing unit can provide short, to-the-point advice when the user is in a hurry. The providing unit can also provide detailed advice when the user is relaxed. Furthermore, the providing unit can provide advice that emphasizes important points when the user is concentrating. This makes it possible to provide more appropriate advice by adjusting the length of the advice according to the user's emotions.

[0099] The providing unit can determine the priority of advice based on the time of submission of the answer when providing the advice. The providing unit uses AI to determine the priority of advice based on the time of submission of the answer when providing the advice. The providing unit determines the priority of advice based on criteria such as the time of submission of the answer, the importance of the answer, and the purpose of the advice. The providing unit provides advice preferentially to answers that have been submitted recently. The providing unit can also postpone answers that have been submitted older. Furthermore, the providing unit can dynamically adjust the priority of advice based on the time of submission. This enables efficient advice by determining the priority of advice based on the time of submission of the answer.

[0100] The providing unit can adjust the order of advice based on the relevance of the answers when providing advice. The providing unit uses AI to adjust the order of advice based on the relevance of the answers when providing advice. The providing unit adjusts the order of advice based on criteria such as the relevance of the answers, the importance of the answers, and the purpose of the advice. The providing unit provides advice preferentially for highly relevant answers. The providing unit can also postpone less relevant answers. Furthermore, the providing unit can dynamically adjust the order of advice based on the relevance of the answers. This enables efficient advice by adjusting the order of advice based on the relevance of the answers.

[0101] The providing unit can adjust the use of technical terms in the advice according to the user's level of expertise when providing the advice. The providing unit uses AI to adjust the use of technical terms in the advice according to the user's level of expertise when providing the advice. The providing unit adjusts the use of technical terms in the advice based on criteria such as the user's level of expertise, the purpose of the advice, and the content of the answer. If the user's level of expertise is high, the providing unit provides advice that uses a lot of technical terms. Furthermore, if the user's level of expertise is low, the providing unit can also provide advice in simpler terms. Furthermore, the providing unit can dynamically adjust the use of technical terms in the advice according to the user's level of expertise. In this way, by adjusting the use of technical terms in the advice according to the user's level of expertise, it is possible to provide advice that is easier to understand.

[0102] The accumulation unit can estimate the user's emotions and adjust the accumulation method of the weak points based on the estimated user emotions. The accumulation unit uses a generation AI to estimate the user's emotions and adjust the accumulation method of the weak points based on the estimated user emotions. The accumulation unit estimates the user's emotions using methods such as facial expression recognition, voice analysis, and self-reporting. The accumulation unit accumulates detailed weak points when the user is relaxed. The accumulation unit can also accumulate concise weak points when the user is impatient. Furthermore, the accumulation unit can accumulate weak points by emphasizing important points when the user is concentrating. In this way, by adjusting the accumulation method of the weak points according to the user's emotions, more appropriate weak points can be accumulated.

[0103] The accumulation unit can adjust the level of detail of weak points based on the importance of the answer when accumulating. The accumulation unit uses the generation AI to adjust the level of detail of weak points based on the importance of the answer when accumulating. The accumulation unit adjusts the level of detail of weak points based on criteria such as the importance of the answer, the purpose of accumulation, and the user's level of understanding. The accumulation unit accumulates detailed weak points for important answers. The accumulation unit can also accumulate concise weak points for answers with low importance. Furthermore, the accumulation unit can dynamically adjust the level of detail of weak points according to the importance of the answer. This enables efficient accumulation by adjusting the level of detail of weak points based on the importance of the answer.

[0104] The accumulation unit can apply different accumulation algorithms depending on the category of the answer when accumulating. The accumulation unit uses a generation AI to apply different accumulation algorithms depending on the category of the answer when accumulating. The accumulation unit performs accumulation using methods such as natural language processing algorithms, machine learning algorithms, and statistical analysis algorithms. The accumulation unit applies an accumulation algorithm dedicated to mathematics to mathematics answers. The accumulation unit can also apply an accumulation algorithm dedicated to English to English answers. Furthermore, the accumulation unit can also apply an accumulation algorithm dedicated to science to science answers. In this way, by applying different accumulation algorithms depending on the category of the answer, more accurate accumulation is possible.

[0105] The accumulation unit can improve the accuracy of accumulation by referring to the user's past accumulation results when accumulating. The accumulation unit uses the generation AI to improve the accuracy of accumulation by referring to the user's past accumulation results when accumulating. The accumulation unit improves the accuracy of accumulation based on criteria such as past answer data, the accuracy of the accumulation results, and user feedback. The accumulation unit improves the accuracy of the current accumulation based on the user's past accumulation results. The accumulation unit can also optimize the accumulation algorithm by referring to the user's past accumulation results. Furthermore, the accumulation unit can analyze the user's past accumulation results and improve the accuracy of accumulation. In this way, the accuracy of accumulation can be improved by referring to the user's past accumulation results.

[0106] The accumulation unit can estimate the user's emotions and determine the priority of weak points based on the estimated user emotions. The accumulation unit uses a generation AI to estimate the user's emotions and determine the priority of weak points based on the estimated user emotions. The accumulation unit estimates the user's emotions using methods such as facial expression recognition, voice analysis, and self-reporting. The accumulation unit prioritizes important weak points when the user is impatient. The accumulation unit can also accumulate all weak points evenly when the user is relaxed. Furthermore, the accumulation unit can prioritize difficult weak points when the user is concentrating. In this way, by determining the priority of weak points according to the user's emotions, important weak points can be prioritized.

[0107] The accumulation unit can determine the priority of weak points based on the time of submission of answers when accumulating. The accumulation unit uses a generation AI to determine the priority of weak points based on the time of submission of answers when accumulating. The accumulation unit determines the priority of weak points based on criteria such as the time of submission of the answer, the importance of the answer, and the purpose of accumulation. The accumulation unit prioritizes weak points in answers that have been submitted recently. The accumulation unit can also postpone weak points in answers that have been submitted older. Furthermore, the accumulation unit can dynamically adjust the priority of weak points based on the time of submission. This enables efficient accumulation by determining the priority of weak points based on the time of submission of the answer.

[0108] The accumulation unit can adjust the order of weak points based on the relevance of the answers when accumulating. The accumulation unit uses a generation AI to adjust the order of weak points based on the relevance of the answers when accumulating. The accumulation unit adjusts the order of weak points based on criteria such as the relevance of the answers, the importance of the answers, and the purpose of accumulation. The accumulation unit prioritizes accumulating weak points of highly relevant answers. The accumulation unit can also postpone weak points of less relevant answers. Furthermore, the accumulation unit can dynamically adjust the order of weak points based on the relevance of the answers. This allows for efficient accumulation by adjusting the order of weak points based on the relevance of the answers.

[0109] The accumulation unit can adjust the level of detail of weak points according to the user's level of expertise when accumulating. The accumulation unit uses the generation AI to adjust the level of detail of weak points according to the user's level of expertise when accumulating. The accumulation unit adjusts the level of detail of weak points based on criteria such as the user's level of expertise, the purpose of accumulation, and the content of the answer. If the user's level of expertise is high, the accumulation unit accumulates detailed weak points. Also, if the user's level of expertise is low, the accumulation unit can accumulate concise weak points. Furthermore, the accumulation unit can dynamically adjust the level of detail of weak points according to the user's level of expertise. In this way, by adjusting the level of detail of weak points according to the user's level of expertise, more appropriate weak points can be accumulated.

[0110] The generation unit can estimate the user's emotions and adjust the way the questions are presented to be generated based on the estimated user emotions. The generation unit uses a generation AI to estimate the user's emotions and adjust the way the questions are presented to be generated based on the estimated user emotions. The generation unit estimates the user's emotions using methods such as facial expression recognition, voice analysis, and self-reporting. The generation unit generates detailed questions when the user is relaxed. The generation unit can also generate concise questions when the user is impatient. Furthermore, the generation unit can generate questions that emphasize important points when the user is concentrating. This makes it possible to generate more appropriate questions by adjusting the way the questions are presented according to the user's emotions.

[0111] The generation unit can adjust the level of detail of the questions based on the importance of the weak points when generating the questions. The generation unit uses the generation AI to adjust the level of detail of the questions based on the importance of the weak points when generating the questions. The generation unit adjusts the level of detail of the questions based on criteria such as the importance of the weak points, the purpose of the question, and the user's level of understanding. The generation unit generates detailed questions for important weak points. The generation unit can also generate concise questions for weak points with low importance. Furthermore, the generation unit can dynamically adjust the level of detail of the questions according to the importance of the weak points. This enables efficient question generation by adjusting the level of detail of the questions based on the importance of the weak points.

[0112] The generation unit can apply different generation algorithms depending on the category of weak points when generating questions. The generation unit uses a generation AI to apply different generation algorithms depending on the category of weak points when generating questions. The generation unit generates questions using methods such as natural language processing algorithms, machine learning algorithms, and statistical analysis algorithms. The generation unit applies a generation algorithm specifically for mathematics to weak points in mathematics. The generation unit can also apply a generation algorithm specifically for English to weak points in English. Furthermore, the generation unit can apply a generation algorithm specifically for science to weak points in science. In this way, by applying different generation algorithms depending on the category of weak points, more accurate question generation is possible.

[0113] The generation unit can improve the accuracy of questions by referring to the user's past generation results when generating questions. The generation unit uses a generation AI to improve the accuracy of questions by referring to the user's past generation results when generating questions. The generation unit improves the accuracy of questions based on criteria such as past answer data, the accuracy of the generation results, and user feedback. The generation unit improves the accuracy of current questions based on the user's past generation results. The generation unit can also optimize the generation algorithm by referring to the user's past generation results. Furthermore, the generation unit can analyze the user's past generation results and improve the accuracy of questions. In this way, the accuracy of questions can be improved by referring to the user's past generation results.

[0114] The generation unit can estimate the user's emotions and adjust the length of the questions to be generated based on the estimated user emotions. The generation unit uses a generation AI to estimate the user's emotions and adjust the length of the questions to be generated based on the estimated user emotions. The generation unit estimates the user's emotions using methods such as facial expression recognition, voice analysis, and self-reporting. The generation unit can generate short, to-the-point questions when the user is in a hurry. The generation unit can also generate detailed questions when the user is relaxed. Furthermore, the generation unit can generate questions that emphasize important points when the user is concentrating. This makes it possible to generate more appropriate questions by adjusting the length of the questions according to the user's emotions.

[0115] The generation unit can determine the priority of questions based on the time of submission of weak points when generating questions. The generation unit uses the generation AI to determine the priority of questions based on the time of submission of weak points when generating questions. The generation unit determines the priority of questions based on criteria such as the time of submission of weak points, the importance of weak points, and the purpose of the question. The generation unit generates questions with priority given to weak points that have been submitted recently. The generation unit can also postpone weak points that have been submitted older. Furthermore, the generation unit can dynamically adjust the priority of questions based on the time of submission. This enables efficient question generation by determining the priority of questions based on the time of submission of weak points.

[0116] The generation unit can adjust the order of questions based on the relevance of weak points when generating questions. The generation unit uses the generation AI to adjust the order of questions based on the relevance of weak points when generating questions. The generation unit adjusts the order of questions based on criteria such as the relevance of weak points, the importance of weak points, and the purpose of the question. The generation unit generates questions with priority for weak points that are highly relevant. The generation unit can also postpone weak points that are less relevant. Furthermore, the generation unit can dynamically adjust the order of questions based on the relevance of weak points. This enables efficient question generation by adjusting the order of questions based on the relevance of weak points.

[0117] The generation unit can adjust the use of technical terminology in questions according to the user's level of expertise when generating questions. The generation unit uses a generation AI to adjust the use of technical terminology in questions according to the user's level of expertise when generating questions. The generation unit adjusts the use of technical terminology in questions based on criteria such as the user's level of expertise, the purpose of the question, and the content of the user's weak points. If the user's level of expertise is high, the generation unit generates questions that use a lot of technical terminology. In addition, if the user's level of expertise is low, the generation unit can also generate questions in simple language. Furthermore, the generation unit can dynamically adjust the use of technical terminology in questions according to the user's level of expertise. In this way, by adjusting the use of technical terminology in questions according to the user's level of expertise, questions that are easier to understand can be generated. === Hard Collateral 1-1 === Each of the multiple elements, including the capture unit, analysis unit, provision unit, accumulation unit, and generation unit, described above, is realized, for example, by at least one of the smart device 14 and the data processing device 12. For example, the capture unit captures the user's answers in real time using the camera 42 or microphone 38B of the smart device 14. The analysis unit is realized, for example, by the specific processing unit 290 of the data processing device 12 and analyzes the captured answers using a generation AI. The provision unit is realized, for example, by the control unit 46A of the smart device 14 and provides a text message or audio guidance based on the analysis results. The accumulation unit is realized, for example, by the specific processing unit 290 of the data processing device 12 and accumulates weak points based on the analysis results. The generation unit is realized, for example, by the specific processing unit 290 of the data processing device 12 and generates questions to overcome weaknesses based on the accumulated weak points. === Hard Collateral 1-2 === Each of the multiple elements, including the capture unit, analysis unit, provision unit, accumulation unit, and generation unit, described above, is realized, for example, by at least one of the smart glasses 214 and the data processing device 12. For example, the capture unit captures the user's answers in real time using the camera 42 or microphone 238 of the smart glasses 214. The analysis unit is realized, for example, by the specific processing unit 290 of the data processing device 12 and analyzes the captured answers using a generation AI. The provision unit is realized, for example, by the control unit 46A of the smart glasses 214 and provides a text message or audio guidance based on the analysis results. The accumulation unit is realized, for example, by the specific processing unit 290 of the data processing device 12 and accumulates weak points based on the analysis results. The generation unit is realized, for example, by the specific processing unit 290 of the data processing device 12 and generates questions for overcoming weaknesses based on the accumulated weak points. === Hard Collateral 1-3 === Each of the multiple elements, including the capture unit, analysis unit, provision unit, accumulation unit, and generation unit, described above, is realized, for example, by at least one of the headset-type terminal 314 and the data processing device 12. For example, the capture unit captures the user's answers in real time using the camera 42 or microphone 238 of the headset-type terminal 314. The analysis unit is realized, for example, by the specific processing unit 290 of the data processing device 12 and analyzes the captured answers using a generation AI. The provision unit is realized, for example, by the control unit 46A of the headset-type terminal 314 and provides a text message or audio guidance based on the analysis results. The accumulation unit is realized, for example, by the specific processing unit 290 of the data processing device 12 and accumulates weak points based on the analysis results. The generation unit is realized, for example, by the specific processing unit 290 of the data processing device 12 and generates problems for overcoming weaknesses based on the accumulated weak points. === Hard Collateral 1-4 === Each of the multiple elements, including the capture unit, analysis unit, provision unit, accumulation unit, and generation unit, described above, is realized, for example, by at least one of the robot 414 and the data processing device 12. For example, the capture unit captures the user's answers in real time using the camera 42 or microphone 238 of the robot 414. The analysis unit is realized, for example, by the specific processing unit 290 of the data processing device 12 and analyzes the captured answers using a generation AI. The provision unit is realized, for example, by the control unit 46A of the robot 414 and provides a text message or audio guidance based on the analysis results. The accumulation unit is realized, for example, by the specific processing unit 290 of the data processing device 12 and accumulates weak points based on the analysis results. The generation unit is realized, for example, by the specific processing unit 290 of the data processing device 12 and generates questions for overcoming weaknesses based on the accumulated weak points.

[0118] The system according to the embodiment is not limited to the above-described example, and various modifications are possible, for example, as follows.

[0119] When capturing a user's answers, the capture unit can monitor the user's learning environment and adjust the capture method according to changes in the environment. For example, if the user is studying in a quiet environment, it can prioritize audio capture. Also, if the user is on the move, it can prioritize text capture. Furthermore, if the user is studying in a group, it can simultaneously capture multiple audio recordings and analyze them individually in the analysis unit. This allows for more effective learning support by selecting the optimal capture method according to the user's learning environment.

[0120] When analyzing the content of a user's answers, the analysis unit can also improve the accuracy of the analysis by taking into account the user's learning history. For example, it can focus its analysis on areas where the user made mistakes in similar questions in the past. It can also perform a concise analysis of answers in areas in which the user excels. Furthermore, it can dynamically adjust the level of detail of the analysis according to the user's learning progress. This allows for more accurate analysis by taking into account the user's learning history.

[0121] When providing advice on a user's answer, the providing unit can also customize the format of the advice according to the user's learning style. For example, advice using diagrams and graphs can be provided to a user who prefers visual learning. Audio guides can also be provided preferentially to a user who prefers auditory learning. Furthermore, advice incorporating real-life examples can be provided to a user who prefers practical learning. In this way, the learning effect can be maximized by providing advice according to the user's learning style.

[0122] When accumulating the user's weak points, the accumulation unit can also adjust the accumulation method based on the user's learning goals. For example, for short-term goals, weak points can be accumulated based on the most recent answers. For long-term goals, weak points can be accumulated by taking into account the entire past answer history. Furthermore, for users aiming to take a specific exam or obtain a qualification, questions related to that exam can be accumulated with a focus. This makes it possible to accumulate weak points according to the user's learning goals.

[0123] When generating questions based on the user's weak points, the generation unit can also adjust the difficulty of the questions according to the user's learning pace. For example, it can generate high-difficulty questions for a user who learns at a fast pace. It can also generate basic questions for a user who learns at a slow pace. It can also adjust the frequency of questions according to the user's learning pace. This makes it possible to provide effective learning support by generating questions according to the user's learning pace.

[0124] The capture unit can also estimate the user's emotions and determine the priority of answers to be captured based on the estimated user's emotions. For example, if the user is in a hurry, important answers can be captured with priority. Also, if the user is relaxed, all answers can be captured equally. Furthermore, if the user is concentrating, answers with a high level of difficulty can be captured with priority. In this way, by determining the priority of answers to be captured according to the user's emotions, important answers can be captured with priority.

[0125] The analysis unit can also estimate the user's emotions and adjust the way the analysis is presented based on the estimated user emotions. For example, if the user is relaxed, detailed analysis results can be provided. If the user is anxious, concise analysis results can be provided. Furthermore, if the user is concentrating, analysis results that emphasize important points can be provided. In this way, by adjusting the way the analysis is presented according to the user's emotions, more appropriate analysis results can be provided.

[0126] The providing unit can also estimate the user's emotions and adjust the way in which advice is expressed based on the estimated user's emotions. For example, if the user is relaxed, detailed advice can be provided. If the user is impatient, concise advice can be provided. Furthermore, if the user is concentrating, advice that emphasizes important points can be provided. In this way, more appropriate advice can be provided by adjusting the way in which advice is expressed depending on the user's emotions.

[0127] The accumulation unit can also estimate the user's emotions and adjust the accumulation method of weak points based on the estimated user's emotions. For example, if the user is relaxed, detailed weak points can be accumulated. Also, if the user is anxious, concise weak points can be accumulated. Furthermore, if the user is concentrating, important points can be emphasized and the weak points can be accumulated. In this way, by adjusting the accumulation method of weak points according to the user's emotions, more appropriate weak points can be accumulated.

[0128] The generation unit can also estimate the user's emotions and adjust the way questions are expressed based on the estimated user emotions. For example, if the user is relaxed, detailed questions can be generated. If the user is impatient, concise questions can be generated. Furthermore, if the user is concentrating, questions that emphasize important points can be generated. In this way, more appropriate questions can be generated by adjusting the way questions are expressed based on the user's emotions.

[0129] The processing flow of the second embodiment will be briefly explained below.

[0130] Step 1: The capture unit captures the user's answer. For example, the capture unit can capture the answer in real time while the user is solving the problem while wearing the smart glasses. The capture unit can also use methods such as image capture, audio capture, and text capture. Step 2: The analysis unit uses the generation AI to analyze the answers captured by the capture unit. The analysis unit analyzes the content of the answers using methods such as natural language processing, statistical analysis, and machine learning algorithms. Step 3: The providing unit provides advice based on the results of the analysis by the analyzing unit. The providing unit can provide advice by, for example, a text message, an audio guide, a video tutorial, or the like. Step 4: The accumulation unit accumulates weak points based on the results of the analysis by the analysis unit. For example, the accumulation unit accumulates weak points based on criteria such as specific problem areas or frequently made mistakes in problem types. Step 5: The generator generates questions to overcome the weaknesses based on the weak points accumulated by the accumulation unit. The generator can generate questions based on criteria such as difficulty level, question format, and question frequency.

[0131] 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.

[0132] The data generation model 58 is a so-called generative AI (Artificial Intelligence). An example of the data generation model 58 is ChatGPT (registered trademark) (Internet search engine).<URL: https: / / openai.com / blog / chatgpt> Examples of generative AIs include the data generation model 58, such as a neural network model (e.g., a neural network model), and a neural network model (e.g., a neural network model). The data generation model 58 is obtained by performing deep learning on a neural network. A prompt including an instruction is input to the data generation model 58, and inference data such as voice data indicating speech, text data indicating text, and image data indicating an image is also input to the data generation model 58. The data generation model 58 performs inference on the input inference data in accordance with the instruction indicated by the prompt and outputs the inference result in a data format such as voice data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization. The specification processing unit 290 performs the above-mentioned specification processing using the data generation model 58. The data generation model 58 may be a fine-tuned model so as to output an inference result from a prompt that does not include an instruction. In this case, the data generation model 58 can output an inference result from a prompt that does not include an instruction. The data processing device 12 and the like include multiple types of data generation models 58, and the data generation model 58 includes AIs other than the generative AI. The AI ​​other than the generative AI may be, for example, linear regression, logistic regression, decision tree, random forest, support vector machine (SVM), k-means clustering, convolutional neural network (CNN), recurrent neural network (RNN), generative adversarial network (GAN), or naive Bayes, and can perform various processes, but is not limited to these examples. The AI ​​may also be an AI agent. When the processes of each of the above-mentioned parts are performed by AI, the processes may be performed in part or entirely by AI, but are not limited to these examples. The processes performed by AI, including the generative AI, may be replaced with rule-based processes.

[0133] 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.

[0134] The correspondence between each part and the device or control part is not limited to the example described above, and various modifications are possible.

[0135] [Second embodiment] FIG. 3 shows an example of the configuration of a data processing system 210 according to the second embodiment.

[0136] 3, the data processing system 210 includes the data processing device 12 and smart glasses 214. An example of the data processing device 12 is a server.

[0137] 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.

[0138] 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.

[0139] 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.

[0140] 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).

[0141] 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.

[0142] 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.

[0143] 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.

[0144] 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.

[0145] 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.

[0146] 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.

[0147] 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.

[0148] The data generation model 58 is a so-called generative AI. An example of the data generation model 58 is a generative AI such as ChatGPT. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 receives a prompt containing an instruction, as well as inference data such as voice data representing speech, text data representing text, and image data representing an image. The data generation model 58 performs inference on the input inference data in accordance with the instruction indicated by the prompt and outputs the inference result in a data format such as voice data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization. The identification processing unit 290 performs the above-mentioned identification processing using the data generation model 58. The data generation model 58 may be a fine-tuned model so as to output an inference result from a prompt that does not include an instruction. In this case, the data generation model 58 can output an inference result from a prompt that does not include an instruction. The data processing device 12 and the like include multiple types of data generation models 58, and the data generation model 58 includes AIs other than the generative AI. The AI ​​other than the generative AI may be, for example, linear regression, logistic regression, decision tree, random forest, support vector machine (SVM), k-means clustering, convolutional neural network (CNN), recurrent neural network (RNN), generative adversarial network (GAN), or naive Bayes, and can perform various processes, but is not limited to these examples. The AI ​​may also be an AI agent. When the processes of each of the above-mentioned parts are performed by AI, the processes may be performed in part or entirely by AI, but are not limited to these examples. The processes performed by AI, including the generative AI, may be replaced with rule-based processes.

[0149] 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.

[0150] The correspondence between each part and the device or control part is not limited to the example described above, and various modifications are possible.

[0151] [Third embodiment] FIG. 5 shows an example of the configuration of a data processing system 310 according to the third embodiment.

[0152] 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.

[0153] 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.

[0154] 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.

[0155] 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.

[0156] 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).

[0157] 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.

[0158] 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.

[0159] 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.

[0160] 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.

[0161] 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.

[0162] 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.

[0163] 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.

[0164] The data generation model 58 is a so-called generative AI. An example of the data generation model 58 is a generative AI such as ChatGPT. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 receives a prompt containing an instruction, as well as inference data such as voice data representing speech, text data representing text, and image data representing an image. The data generation model 58 performs inference on the input inference data in accordance with the instruction indicated by the prompt and outputs the inference result in a data format such as voice data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization. The identification processing unit 290 performs the above-mentioned identification processing using the data generation model 58. The data generation model 58 may be a fine-tuned model so as to output an inference result from a prompt that does not include an instruction. In this case, the data generation model 58 can output an inference result from a prompt that does not include an instruction. The data processing device 12 and the like include multiple types of data generation models 58, and the data generation model 58 includes AIs other than the generative AI. The AI ​​other than the generative AI may be, for example, linear regression, logistic regression, decision tree, random forest, support vector machine (SVM), k-means clustering, convolutional neural network (CNN), recurrent neural network (RNN), generative adversarial network (GAN), or naive Bayes, and can perform various processes, but is not limited to these examples. The AI ​​may also be an AI agent. When the processes of each of the above-mentioned parts are performed by AI, the processes may be performed in part or entirely by AI, but are not limited to these examples. The processes performed by AI, including the generative AI, may be replaced with rule-based processes.

[0165] 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.

[0166] The correspondence between each part and the device or control part is not limited to the example described above, and various modifications are possible.

[0167] [Fourth embodiment] FIG. 7 shows an example of the configuration of a data processing system 410 according to the fourth embodiment.

[0168] 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.

[0169] 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.

[0170] 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.

[0171] 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.

[0172] 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).

[0173] 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.

[0174] 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.

[0175] 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.

[0176] 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.

[0177] 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.

[0178] 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.

[0179] 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.

[0180] 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.

[0181] The data generation model 58 is a so-called generative AI. An example of the data generation model 58 is a generative AI such as ChatGPT. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 receives a prompt containing an instruction, as well as inference data such as voice data representing speech, text data representing text, and image data representing an image. The data generation model 58 performs inference on the input inference data in accordance with the instruction indicated by the prompt and outputs the inference result in a data format such as voice data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization. The identification processing unit 290 performs the above-mentioned identification processing using the data generation model 58. The data generation model 58 may be a fine-tuned model so as to output an inference result from a prompt that does not include an instruction. In this case, the data generation model 58 can output an inference result from a prompt that does not include an instruction. The data processing device 12 and the like include multiple types of data generation models 58, and the data generation model 58 includes AIs other than the generative AI. The AI ​​other than the generative AI may be, for example, linear regression, logistic regression, decision tree, random forest, support vector machine (SVM), k-means clustering, convolutional neural network (CNN), recurrent neural network (RNN), generative adversarial network (GAN), or naive Bayes, and can perform various processes, but is not limited to these examples. The AI ​​may also be an AI agent. When the processes of each of the above-mentioned parts are performed by AI, the processes may be performed in part or entirely by AI, but are not limited to these examples. The processes performed by AI, including the generative AI, may be replaced with rule-based processes.

[0182] 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.

[0183] The correspondence between each part and the device or control part is not limited to the example described above, and various modifications are possible.

[0184] 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.

[0185] 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.

[0186] 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.

[0187] 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).

[0188] 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.

[0189] 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."

[0190] 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.

[0191] 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.

[0192] 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.

[0193] 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.

[0194] 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.

[0195] 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.

[0196] 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.

[0197] 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.

[0198] 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.

[0199] 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.

[0200] 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.

[0201] 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.

[0202] [Explanation of symbols]

[0203] 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 capture unit for capturing a user's answer; an analysis unit that analyzes the answers captured by the capture unit; a providing unit that provides advice based on the results of the analysis by the analyzing unit; an accumulation unit that accumulates weak points based on the results of the analysis by the analysis unit; a generation unit that generates questions for overcoming weaknesses based on the weak points accumulated by the accumulation unit. A system characterized by:

2. The capture unit Capture user answers in real time 2. The system of claim 1.

3. The analysis unit Analyzes the user's answers and provides appropriate advice if the user is taking too long to solve the problem or has made an error 2. The system of claim 1.

4. The providing unit Identify and guide spelling and typographical errors 2. The system of claim 1.

5. The accumulation section is Accumulate weak points based on user responses 2. The system of claim 1.

6. The generation unit Generate problems to overcome weaknesses based on accumulated weak points 2. The system of claim 1.

7. The capture unit Inferring user emotions and adjusting the timing of answer capture based on the estimated user emotions 2. The system of claim 1.

8. The capture unit Analyze the user's past answer history and select the optimal capture method 2. The system of claim 1.

Images