System

Abstract

A system according to an embodiment aims to provide personalized education based on the student's learning style and comprehension.SOLUTION: A system includes an understanding unit, a grasping unit, a generation unit, and a reporting unit. The understanding unit understands the textbook or lesson content. The grasping part grasps the learning style and the degree of understanding of the student based on the information understood by the understanding part. The generation unit generates a customized homework or test based on the information grasped by the grasping unit. The reporting unit reports the learning progress to the parent based on the homework assignment and the test result generated by the generation 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 the problem of making it difficult to provide personalized education tailored to each student's learning style and level of understanding.

[0005] The system of the embodiment aims to provide personalized education based on a student's learning style and level of understanding. [Means for solving the problem]

[0006] The system according to the embodiment includes an understanding unit, a grasping unit, a generation unit, and a reporting unit. The understanding unit understands the textbook or lesson content. The grasping unit grasps the student's learning style and level of comprehension based on the information understood by the understanding unit. The generation unit generates customized homework and tests based on the information grasped by the grasping unit. The reporting unit reports learning progress to parents based on the results of the homework and tests generated by the generation unit. [Effects of the Invention]

[0007] An embodiment of the system can provide personalized education based on a student's learning style and comprehension level. [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) An embodiment of the present invention provides a personalized education system that uses a multimodal large-scale language model (LLM) to personalize education and provide appropriate learning materials tailored to each learner's needs. The personalized education system understands textbook and class content and generates homework and tests tailored to each student's learning style and level of understanding. The personalized education system also reports learning progress to parents and adjusts learning plans as needed. For example, the personalized education system analyzes textbook content and class records to extract key points and concepts. The personalized education system then analyzes past test results, homework submission status, and comments made during class to identify each student's strengths and weaknesses. Furthermore, the personalized education system generates customized homework and tests based on the student's level of understanding. For example, if a student is weak in a particular subject, the system can generate homework that includes many questions related to that subject. The personalized education system also periodically analyzes each student's learning status and reports progress to parents. This allows the personalized education system to personalize education and provide effective learning tailored to each student's needs. This allows the personalized education system to report each student's learning progress to parents and make suggestions to adjust the learning plan as needed. For example, if a student is weak in a particular subject, providing specialized learning materials for that subject can improve learning efficiency. Reporting learning progress to parents also allows for more support at home.

[0029] The personalized education system according to the embodiment includes an understanding unit, a generation unit, and a reporting unit. The understanding unit understands textbook or lesson content. For example, the understanding unit analyzes the content of a textbook or lesson records to extract important points and concepts. For example, the understanding unit analyzes the content of a textbook using text analysis technology to extract important points. The understanding unit can also analyze lesson records using voice recognition technology to extract important concepts. The understanding unit can also analyze textbook diagrams using image recognition technology to extract important information. The understanding unit understands students' learning styles and levels of understanding based on the information understood by the understanding unit. For example, the understanding unit analyzes past test results, homework submission status, and comments made during class to identify each student's strengths and weaknesses. For example, the understanding unit analyzes test results to identify each student's strengths and weaknesses. The understanding unit can also analyze homework submission status to evaluate each student's learning attitude. Furthermore, the comprehension unit can analyze the content of utterances made during class and evaluate each student's level of understanding. The generation unit generates customized homework and tests based on the information grasped by the comprehension unit. The generation unit generates customized homework and tests, for example, based on the student's level of understanding. For example, for a student who is weak in a particular subject, the generation unit generates homework that includes many questions related to that subject. The generation unit can also provide more difficult questions for subjects in which the student has a high level of understanding. The generation unit can also generate homework and tests in a visually appealing format that matches the student's learning style. The reporting unit reports learning progress to parents based on the results of the homework and tests generated by the generation unit. For example, the reporting unit periodically analyzes each student's learning situation and provides progress reports to parents. The reporting unit reports learning progress and changes in understanding, for example, weekly. The reporting unit can also make suggestions to adjust the learning plan as needed. As a result, the education personalization system according to the embodiment can personalize education and provide effective learning tailored to the needs of each student.

[0030] The comprehension unit can analyze the content of a textbook or lesson records and extract important points and concepts. For example, the comprehension unit analyzes the content of a textbook using text analysis technology and extracts important points. For example, the comprehension unit extracts key theorems and formulas from each chapter of the textbook. The comprehension unit can also analyze lesson records using speech recognition technology and extract important concepts. For example, the comprehension unit analyzes the content of a teacher's remarks during class and extracts important points. The comprehension unit can also analyze diagrams in a textbook using image recognition technology and extract important information. For example, the comprehension unit extracts important data and graphs from diagrams in a textbook. This makes it possible to efficiently extract important points from textbooks and lesson content.

[0031] The grasping unit can analyze past test results, homework submission status, and utterances made during class to identify each student's areas of strength and weakness. The grasping unit, for example, analyzes past test results to identify each student's areas of strength and weakness. For example, the grasping unit analyzes the rate of correct answers on tests and patterns of incorrect answers to identify each student's areas of strength and weakness. The grasping unit can also analyze homework submission status and evaluate each student's learning attitude. For example, the grasping unit analyzes the frequency and timing of homework submission to evaluate the learning attitude. The grasping unit can also analyze utterances made during class to evaluate each student's level of understanding. For example, the grasping unit analyzes the frequency and content of utterances made during class to evaluate the level of understanding. This makes it possible to identify each student's areas of strength and weakness and provide personalized education.

[0032] The generation unit can generate customized homework and tests based on the student's level of understanding. The generation unit generates customized homework and tests based on, for example, the student's level of understanding. For example, for a student who is weak in a particular subject, the generation unit generates homework that includes many questions related to that subject. The generation unit can also provide more difficult questions for subjects in which the student has a high level of understanding. For example, the generation unit generates homework that includes applied questions and advanced questions for students with a high level of understanding. The generation unit can also generate homework and tests in a visually appealing format that matches the student's learning style. For example, the generation unit generates homework that includes many diagrams and illustrations and provides it in a format that is visually easy to understand. This makes it possible to provide homework and tests that are appropriate for the student's level of understanding.

[0033] The reporting department can periodically analyze each student's learning situation and provide progress reports to parents. The reporting department, for example, can periodically analyze each student's learning situation and provide progress reports to parents. For example, the reporting department reports learning progress and changes in understanding on a weekly basis. The reporting department can also make suggestions to adjust the learning plan as needed. For example, for students who are weak in a particular subject, the reporting department can propose a learning plan specialized for that subject. The reporting department can also propose a more difficult learning plan for subjects with a high level of understanding. For example, for students with a high level of understanding, the reporting department can propose a learning plan that includes applied problems and advanced problems. This makes it possible to report students' learning progress to parents and provide more support at home.

[0034] The reporting department can make suggestions to adjust the study plan as needed. For example, the reporting department periodically analyzes the learning situation of each student and provides progress reports to parents. For example, the reporting department reports on learning progress and changes in understanding on a weekly basis. The reporting department can also make suggestions to adjust the study plan as needed. For example, for students who are weak in a particular subject, the reporting department can propose a study plan specialized for that subject. The reporting department can also propose a more difficult study plan for subjects with a high level of understanding. For example, for students with a high level of understanding, the reporting department can propose a study plan that includes applied problems and advanced problems. This makes it possible to flexibly adjust the study plan and maximize the learning effect of students.

[0035] When analyzing the contents of a textbook, the comprehension unit can adjust the level of detail of the analysis based on the importance of each chapter. For example, when analyzing the contents of a textbook, the comprehension unit can adjust the level of detail of the analysis based on the importance of each chapter. For example, the comprehension unit can perform a detailed analysis of important chapters and emphasize important points. For less important chapters, the comprehension unit can also perform a simplified analysis and provide only basic points. Furthermore, the comprehension unit can dynamically adjust the importance of each chapter based on the student's learning progress and provide necessary information. This allows for a detailed analysis of important chapters, improving learning efficiency.

[0036] When analyzing class records, the comprehension unit can perform the analysis based on the content of the teacher's remarks or the pace at which the class is progressing. For example, when analyzing class records, the comprehension unit performs text analysis of the content of the teacher's remarks and extracts important points. For example, the comprehension unit analyzes the content of the teacher's remarks and extracts important concepts and keywords. The comprehension unit can also organize information to make it easier for students to understand based on the pace at which the class is progressing. For example, the comprehension unit analyzes the pace at which the class is progressing and provides information at an appropriate time. The comprehension unit can also prioritize analysis of important information by taking into account the frequency of the teacher's remarks and the points emphasized. For example, the comprehension unit prioritizes analysis of points emphasized by the teacher and extracts them as important information. This allows for appropriate analysis according to the progress of the class to deepen students' understanding.

[0037] The understanding unit can improve the accuracy of analysis by referring to past analysis results when analyzing textbooks or lesson content. For example, the understanding unit can improve the accuracy of analysis by referring to past analysis results when analyzing textbooks or lesson content. For example, the understanding unit stores past analysis results in a database and refers to them when performing a new analysis. The understanding unit can also improve the accuracy of analysis based on patterns obtained from past analysis results. For example, the understanding unit can use past analysis results as a feedback loop to continuously improve the analysis algorithm. This makes it possible to continuously improve the accuracy of analysis by utilizing past analysis results.

[0038] When analyzing the content of a textbook, the comprehension unit can compare it with the content of other textbooks and reference books. For example, when analyzing the content of a textbook, the comprehension unit compares it with the content of other textbooks and reference books. For example, the comprehension unit refers to the content of other textbooks that cover the same topic and performs a comparative analysis. The comprehension unit can also provide information that complements the content of the textbook based on the content of reference books. Furthermore, the comprehension unit can compare it with the content of other textbooks and reference books to highlight important points. This makes it possible to perform a more comprehensive analysis by comparing it with other textbooks and reference books.

[0039] When analyzing a lesson record, the understanding unit can perform the analysis by combining the video and audio data of the lesson. For example, when analyzing a lesson record, the understanding unit analyzes the video data of the lesson and extracts important scenes. For example, the understanding unit analyzes the video data of the lesson and extracts important points. The understanding unit can also convert audio data into text and analyze the content of what is being said. For example, the understanding unit analyzes audio data during the lesson and extracts important content of what is being said. Furthermore, the understanding unit can combine the video and audio data to perform a more detailed analysis. For example, the understanding unit integrates the video data and audio data and extracts important information. In this way, using video and audio data together enables a more detailed analysis.

[0040] The understanding unit can customize the analysis method by reflecting the student's learning history when analyzing textbooks and class content. For example, the understanding unit can customize the analysis method by reflecting the student's learning history when analyzing textbooks and class content. For example, the understanding unit can adjust the level of detail of the analysis based on the student's past learning history. The understanding unit can also change the focus of the analysis by taking into account the student's strengths and weaknesses. Furthermore, the understanding unit can use the student's learning history as a feedback loop to continuously improve the analysis method. This makes it possible to reflect the student's learning history and perform more personalized analysis.

[0041] When analyzing past test results, the comprehension unit can adjust the level of detail of the analysis based on the difficulty of each question. For example, when analyzing past test results, the comprehension unit adjusts the level of detail of the analysis based on the difficulty of each question. For example, the comprehension unit performs a detailed analysis for high-difficulty questions and provides key points for understanding. For low-difficulty questions, the comprehension unit can also perform a simplified analysis and provide only basic key points. Furthermore, the comprehension unit can dynamically adjust the difficulty of each question based on the student's learning progress and provide necessary information. This enables detailed analysis according to the difficulty of each question.

[0042] When analyzing the homework submission status, the grasping unit can perform the analysis taking into consideration the timing and method of submission. For example, when analyzing the homework submission status, the grasping unit performs the analysis taking into consideration the timing and method of submission. For example, the grasping unit analyzes the timing of homework submission to grasp the student's study habits. The grasping unit can also analyze the submission status taking into consideration the submission method (online, paper, etc.). Furthermore, the grasping unit can analyze the frequency and delay of submission to evaluate the student's learning attitude. This makes it possible to perform a detailed analysis according to the submission status.

[0043] When analyzing the content of comments made during class, the comprehension unit can perform the analysis taking into consideration the frequency of comments and the relevance of the content. For example, when analyzing the content of comments made during class, the comprehension unit performs the analysis taking into consideration the frequency of comments and the relevance of the content. For example, the comprehension unit analyzes the frequency of comments to evaluate the student's level of engagement. The comprehension unit can also analyze the relevance of the content of comments to evaluate the level of understanding. Furthermore, the comprehension unit can analyze the timing of comments to evaluate the level of concentration during class. This makes it possible to perform a detailed analysis based on the content of comments.

[0044] When analyzing past test results, the ascertaining unit can compare the results with those of other students. For example, when analyzing past test results, the ascertaining unit performs an analysis by comparing the results with those of other students. For example, the ascertaining unit compares the results with those of other students in the same class to evaluate the relative level of understanding. The ascertaining unit can also perform a comparative analysis with other students based on past test results. Furthermore, the ascertaining unit can also identify areas of strength and weakness by referring to the results of other students. This makes it possible to evaluate the relative level of understanding by comparing the results with those of other students.

[0045] When analyzing the homework submission status, the grasping unit can perform the analysis taking into consideration the content and quality of the submission. For example, when analyzing the homework submission status, the grasping unit performs the analysis taking into consideration the content and quality of the submission. For example, the grasping unit analyzes the content of the submission and evaluates the level of understanding. The grasping unit can also analyze the quality of the submission and evaluate the depth of learning. Furthermore, the grasping unit can comprehensively analyze the content and quality of the submission and evaluate the learning attitude. This makes it possible to perform a detailed analysis based on the content and quality of the submission.

[0046] When analyzing the content of utterances made during a class, the comprehension unit can compare the content of utterances made during a class with the content of utterances made during other classes. For example, when analyzing the content of utterances made during a class, the comprehension unit compares the content of utterances made during a class with the content of utterances made during other classes to evaluate the level of understanding. The comprehension unit can also compare the content of utterances made during a class with the content of utterances made during other classes to evaluate the relative level of understanding. Furthermore, the comprehension unit can analyze the frequency of utterances and the relevance of the content by referring to the content of utterances made during other classes. This makes it possible to evaluate the level of understanding in more detail by comparing the content of utterances made during a class with the content of utterances made during other classes.

[0047] When generating homework or tests, the generation unit can adjust the level of detail based on the importance of each question. For example, when generating homework or tests, the generation unit adjusts the level of detail based on the importance of each question. For example, the generation unit generates homework that includes detailed explanations for important questions. The generation unit can also generate homework that includes brief explanations for less important questions. Furthermore, the generation unit can dynamically adjust the importance of each question based on the student's learning progress and provide necessary information. This makes it possible to generate detailed homework or tests that correspond to the importance of each question.

[0048] The generation unit can generate homework and tests taking into consideration the student's past grades and level of understanding. For example, the generation unit generates homework and tests taking into consideration the student's past grades and level of understanding. For example, the generation unit generates homework of an appropriate level of difficulty based on the student's past grades. The generation unit can also generate homework to deepen the student's understanding by taking into consideration the student's level of understanding. Furthermore, the generation unit can generate optimal homework by comprehensively taking into consideration the student's past grades and level of understanding. This makes it possible to generate optimal homework and tests based on the student's past grades and level of understanding.

[0049] The generation unit can improve the accuracy of generation by referring to past generation results when generating homework or tests. For example, when generating homework or tests, the generation unit improves the accuracy of generation by referring to past generation results. For example, the generation unit stores past generation results in a database and refers to them when generating new homework or tests. The generation unit can also improve the accuracy of generation based on patterns obtained from past generation results. Furthermore, the generation unit can utilize past generation results as a feedback loop to continuously improve the generation algorithm. In this way, the accuracy of generation can be continuously improved by utilizing past generation results.

[0050] The generation unit can generate homework or tests by comparing them with the grades and levels of understanding of other students. For example, when generating homework or tests, the generation unit generates them by comparing them with the grades and levels of understanding of other students. For example, the generation unit generates homework of an appropriate level of difficulty by comparing them with the grades of other students in the same class. The generation unit can also generate homework that deepens understanding by referring to the levels of understanding of other students. Furthermore, the generation unit can generate optimal homework by comprehensively taking into account the grades and levels of understanding of other students. This makes it possible to generate homework or tests of a relative level of difficulty by comparing them with the grades and levels of understanding of other students.

[0051] The generation unit can generate homework or tests by reflecting the content of other subjects or courses. For example, when generating homework or tests, the generation unit generates them by reflecting the content of other subjects or courses. For example, the generation unit generates homework that includes related questions by referring to the content of other subjects. The generation unit can also generate homework that promotes comprehensive understanding by reflecting the content of other subjects. Furthermore, the generation unit can combine the content of other subjects or courses to generate homework that includes complex questions. This makes it possible to generate homework or tests that promote comprehensive understanding by reflecting the content of other subjects or courses.

[0052] The generation unit can customize the generation method by reflecting the student's learning history when generating homework or tests. For example, when generating homework or tests, the generation unit customizes the generation method by reflecting the student's learning history. For example, the generation unit generates homework of an appropriate level of difficulty based on the student's past learning history. The generation unit can also generate homework to deepen understanding by taking into account the student's strengths and weaknesses. Furthermore, the generation unit can utilize the student's learning history as a feedback loop to continuously improve the generation algorithm. This makes it possible to generate more personalized homework and tests by reflecting the student's learning history.

[0053] The reporting unit can adjust the level of detail of the report based on each student's level of understanding when reporting learning progress. For example, when reporting learning progress, the reporting unit adjusts the level of detail of the report based on each student's level of understanding. For example, the reporting unit provides a detailed report to students with a high level of understanding. The reporting unit can also provide a simplified report to students with a low level of understanding. Furthermore, the reporting unit can dynamically adjust the level of detail of the report based on each student's level of understanding. This makes it possible to provide a detailed report according to each student's level of understanding.

[0054] The reporting unit can improve the accuracy of the report by referring to past report results when reporting learning progress. For example, when reporting learning progress, the reporting unit improves the accuracy of the report by referring to past report results. For example, the reporting unit stores past report results in a database and refers to them when making a new report. The reporting unit can also improve the accuracy of the report based on patterns obtained from past report results. Furthermore, the reporting unit can utilize past report results as a feedback loop to continuously improve the reporting algorithm. In this way, the accuracy of the report can be continuously improved by utilizing past report results.

[0055] The reporting unit can improve the reporting method by reflecting parental feedback when reporting learning progress. For example, the reporting unit improves the reporting method by reflecting parental feedback when reporting learning progress. For example, the reporting unit adjusts the reporting method based on parental feedback. The reporting unit can also customize the report content in accordance with parental requests. Furthermore, the reporting unit can utilize parental feedback as a feedback loop to continuously improve the reporting method. In this way, a more effective reporting method can be provided by reflecting parental feedback.

[0056] The reporting unit can compare the learning progress with that of other students when reporting the learning progress. For example, the reporting unit compares the learning progress with that of other students when reporting the learning progress. For example, the reporting unit compares the learning progress with that of other students in the same class and reports the relative progress. The reporting unit can also evaluate the level of understanding by referring to the progress of other students. Furthermore, the reporting unit can customize the report content based on the progress of other students. This makes it possible to evaluate the relative progress by comparing with the progress of other students.

[0057] The reporting unit can customize the report content to reflect the interests and requests of the parent when reporting learning progress. For example, the reporting unit customizes the report content to reflect the interests and requests of the parent when reporting learning progress. For example, the reporting unit adjusts the report content based on the interests of the parent. The reporting unit can also customize the report content in accordance with the requests of the parent. Furthermore, the reporting unit can continuously improve the report content based on feedback from the parent. This makes it possible to provide customized reports that reflect the interests and requests of the parent.

[0058] The reporting department can customize the reporting method by reflecting the student's learning history when reporting learning progress. For example, when reporting learning progress, the reporting department customizes the reporting method by reflecting the student's learning history. For example, the reporting department adjusts the report content based on the student's past learning history. The reporting department can also customize the report content by taking into account the student's strengths and weaknesses. Furthermore, the reporting department can utilize the student's learning history as a feedback loop to continuously improve the reporting method. This allows for more personalized reporting by reflecting the student's learning history.

[0059] The system according to the embodiment is not limited to the above-described example, and various modifications are possible, for example, as follows.

[0060] The personalized education system may further include an interactive feedback unit. The feedback unit provides instant feedback to students after they submit their homework or tests. For example, the feedback unit may display whether a student answered correctly or incorrectly in real time and provide detailed explanations for incorrect questions. The feedback unit may also analyze the student's answer patterns and provide advice based on their level of understanding. Furthermore, the feedback unit may have an interactive function that provides instant answers when a student inputs a question for a specific question. This allows students to instantly resolve their doubts during their studies and progress efficiently.

[0061] The personalized education system can further include a motivation improvement unit. The motivation improvement unit provides a function to increase students' motivation to learn. For example, the motivation improvement unit provides a mechanism that allows students to set goals and earn badges and points according to their achievement. The motivation improvement unit can also visually display the results achieved by students as they progress through their studies, allowing them to feel their progress. Furthermore, the motivation improvement unit can provide a ranking function that allows students to compete with other students, thereby increasing their motivation to learn. This allows students to enjoy their studies.

[0062] The personalized education system may further include a learning environment adjustment unit. The learning environment adjustment unit provides a function for optimizing a student's learning environment. For example, the learning environment adjustment unit adjusts background music and lighting to provide an environment in which the student can easily concentrate. The learning environment adjustment unit may also provide music and images with a relaxing effect to provide an environment in which the student can relax. Furthermore, if the student is excited, the learning environment adjustment unit may provide an environment to improve concentration. This optimizes the student's learning environment and improves learning effectiveness.

[0063] The personalized education system can further include a learning history analysis unit. The learning history analysis unit analyzes a student's past learning history and provides information to optimize future learning plans. For example, the learning history analysis unit analyzes a student's past test results and homework submission status to identify their strengths and weaknesses. The learning history analysis unit can also analyze a student's learning patterns and propose an optimal learning schedule. Furthermore, the learning history analysis unit can set future learning goals based on the student's learning history and evaluate the degree to which they have been achieved. This makes it possible to utilize a student's learning history to provide more effective learning support.

[0064] The education personalization system can further include a learning style adaptation unit. The learning style adaptation unit adjusts the learning content according to the student's learning style. For example, the learning style adaptation unit can provide learning materials that include many diagrams and illustrations to a student who prefers visual learning. It can also provide learning materials that include audio commentary to a student who prefers auditory learning. It can also provide learning materials that include experiments and practical training to a student who prefers practical learning. In this way, it is possible to provide optimal learning content according to the student's learning style.

[0065] The personalized education system may further include a learning goal setting unit. The learning goal setting unit provides a function for students to set their own learning goals and evaluate their achievement. For example, the learning goal setting unit allows students to set short-term and long-term goals and track their progress. The learning goal setting unit may also provide specific action plans for achieving the goals. Furthermore, the learning goal setting unit may provide feedback according to the degree of goal achievement to increase student motivation. This allows students to effectively progress in their studies toward their learning goals.

[0066] The processing flow of the first embodiment will be briefly explained below.

[0067] Step 1: The comprehension unit understands the textbook or lesson content. For example, the comprehension unit analyzes the textbook content or lesson records to extract important points and concepts. Specifically, text analysis technology is used to analyze the textbook content and extract important points. Voice recognition technology can also be used to analyze lesson records and extract important concepts. Furthermore, image recognition technology can be used to analyze textbook diagrams and extract important information. Step 2: The understanding unit understands the student's learning style and level of comprehension based on the information understood by the understanding unit. The understanding unit analyzes, for example, past test results, homework submission status, and comments made during class to identify each student's strengths and weaknesses. Specifically, it analyzes test results to identify each student's strengths and weaknesses. It can also analyze homework submission status and evaluate each student's learning attitude. It can also analyze comments made during class to evaluate each student's level of comprehension. Step 3: The generation unit generates customized homework and tests based on the information grasped by the grasping unit. The generation unit generates customized homework and tests, for example, based on the student's level of understanding. Specifically, for a student who is weak in a particular subject, the generation unit generates homework that includes many questions related to that subject. It can also provide more difficult questions for subjects where the student has a high level of understanding. Furthermore, it can generate homework and tests in a visually appealing format to suit the student's learning style. Step 4: The reporting unit reports learning progress to parents based on the homework and test results generated by the generation unit. For example, the reporting unit periodically analyzes each student's learning situation and reports progress to parents. Specifically, it reports learning progress and changes in understanding on a weekly basis. It can also make suggestions to adjust the learning plan as needed.

[0068] (Example 2) An embodiment of the present invention provides a personalized education system that uses a multimodal large-scale language model (LLM) to personalize education and provide appropriate learning materials tailored to each learner's needs. The personalized education system understands textbook and class content and generates homework and tests tailored to each student's learning style and level of understanding. The personalized education system also reports learning progress to parents and adjusts learning plans as needed. For example, the personalized education system analyzes textbook content and class records to extract key points and concepts. The personalized education system then analyzes past test results, homework submission status, and comments made during class to identify each student's strengths and weaknesses. Furthermore, the personalized education system generates customized homework and tests based on the student's level of understanding. For example, if a student is weak in a particular subject, the system can generate homework that includes many questions related to that subject. The personalized education system also periodically analyzes each student's learning status and reports progress to parents. This allows the personalized education system to personalize education and provide effective learning tailored to each student's needs. This allows the personalized education system to report each student's learning progress to parents and make suggestions to adjust the learning plan as needed. For example, if a student is weak in a particular subject, providing specialized learning materials for that subject can improve learning efficiency. Reporting learning progress to parents also allows for more support at home.

[0069] The personalized education system according to the embodiment includes an understanding unit, a generation unit, and a reporting unit. The understanding unit understands textbook or lesson content. For example, the understanding unit analyzes the content of a textbook or lesson records to extract important points and concepts. For example, the understanding unit analyzes the content of a textbook using text analysis technology to extract important points. The understanding unit can also analyze lesson records using voice recognition technology to extract important concepts. The understanding unit can also analyze textbook diagrams using image recognition technology to extract important information. The understanding unit understands students' learning styles and levels of understanding based on the information understood by the understanding unit. For example, the understanding unit analyzes past test results, homework submission status, and comments made during class to identify each student's strengths and weaknesses. For example, the understanding unit analyzes test results to identify each student's strengths and weaknesses. The understanding unit can also analyze homework submission status to evaluate each student's learning attitude. Furthermore, the comprehension unit can analyze the content of utterances made during class and evaluate each student's level of understanding. The generation unit generates customized homework and tests based on the information grasped by the comprehension unit. The generation unit generates customized homework and tests, for example, based on the student's level of understanding. For example, for a student who is weak in a particular subject, the generation unit generates homework that includes many questions related to that subject. The generation unit can also provide more difficult questions for subjects in which the student has a high level of understanding. The generation unit can also generate homework and tests in a visually appealing format that matches the student's learning style. The reporting unit reports learning progress to parents based on the results of the homework and tests generated by the generation unit. For example, the reporting unit periodically analyzes each student's learning situation and provides progress reports to parents. The reporting unit reports learning progress and changes in understanding, for example, weekly. The reporting unit can also make suggestions to adjust the learning plan as needed. As a result, the education personalization system according to the embodiment can personalize education and provide effective learning tailored to the needs of each student.

[0070] The comprehension unit can analyze the content of a textbook or lesson records and extract important points and concepts. For example, the comprehension unit analyzes the content of a textbook using text analysis technology and extracts important points. For example, the comprehension unit extracts key theorems and formulas from each chapter of the textbook. The comprehension unit can also analyze lesson records using speech recognition technology and extract important concepts. For example, the comprehension unit analyzes the content of a teacher's remarks during class and extracts important points. The comprehension unit can also analyze diagrams in a textbook using image recognition technology and extract important information. For example, the comprehension unit extracts important data and graphs from diagrams in a textbook. This makes it possible to efficiently extract important points from textbooks and lesson content.

[0071] The grasping unit can analyze past test results, homework submission status, and utterances made during class to identify each student's areas of strength and weakness. The grasping unit, for example, analyzes past test results to identify each student's areas of strength and weakness. For example, the grasping unit analyzes the rate of correct answers on tests and patterns of incorrect answers to identify each student's areas of strength and weakness. The grasping unit can also analyze homework submission status and evaluate each student's learning attitude. For example, the grasping unit analyzes the frequency and timing of homework submission to evaluate the learning attitude. The grasping unit can also analyze utterances made during class to evaluate each student's level of understanding. For example, the grasping unit analyzes the frequency and content of utterances made during class to evaluate the level of understanding. This makes it possible to identify each student's areas of strength and weakness and provide personalized education.

[0072] The generation unit can generate customized homework and tests based on the student's level of understanding. The generation unit generates customized homework and tests based on, for example, the student's level of understanding. For example, for a student who is weak in a particular subject, the generation unit generates homework that includes many questions related to that subject. The generation unit can also provide more difficult questions for subjects in which the student has a high level of understanding. For example, the generation unit generates homework that includes applied questions and advanced questions for students with a high level of understanding. The generation unit can also generate homework and tests in a visually appealing format that matches the student's learning style. For example, the generation unit generates homework that includes many diagrams and illustrations and provides it in a format that is visually easy to understand. This makes it possible to provide homework and tests that are appropriate for the student's level of understanding.

[0073] The reporting department can periodically analyze each student's learning situation and provide progress reports to parents. The reporting department, for example, can periodically analyze each student's learning situation and provide progress reports to parents. For example, the reporting department reports learning progress and changes in understanding on a weekly basis. The reporting department can also make suggestions to adjust the learning plan as needed. For example, for students who are weak in a particular subject, the reporting department can propose a learning plan specialized for that subject. The reporting department can also propose a more difficult learning plan for subjects with a high level of understanding. For example, for students with a high level of understanding, the reporting department can propose a learning plan that includes applied problems and advanced problems. This makes it possible to report students' learning progress to parents and provide more support at home.

[0074] The reporting department can make suggestions to adjust the study plan as needed. For example, the reporting department periodically analyzes the learning situation of each student and provides progress reports to parents. For example, the reporting department reports on learning progress and changes in understanding on a weekly basis. The reporting department can also make suggestions to adjust the study plan as needed. For example, for students who are weak in a particular subject, the reporting department can propose a study plan specialized for that subject. The reporting department can also propose a more difficult study plan for subjects with a high level of understanding. For example, for students with a high level of understanding, the reporting department can propose a study plan that includes applied problems and advanced problems. This makes it possible to flexibly adjust the study plan and maximize the learning effect of students.

[0075] The understanding unit can estimate a student's emotions and adjust the analysis method of the textbook or class content based on the estimated student emotions. For example, the understanding unit can estimate a student's emotions and adjust the analysis method of the textbook or class content based on the estimated student emotions. For example, if a student is stressed, the understanding unit can simplify the textbook content and provide it in an easy-to-understand format. If a student is relaxed, the understanding unit can perform a detailed analysis and provide supplementary information to promote deeper understanding. Furthermore, if a student is excited, the understanding unit can analyze the textbook content in a visually appealing format to attract attention. This allows the analysis method to be adjusted according to the student's emotions, enabling more effective learning support. Emotion estimation is achieved using an emotion estimation function, for example, using an emotion engine or generative AI. Generative AI can be, but is not limited to, a text generation AI (e.g., LLM) or a multimodal generative AI.

[0076] When analyzing the contents of a textbook, the comprehension unit can adjust the level of detail of the analysis based on the importance of each chapter. For example, when analyzing the contents of a textbook, the comprehension unit can adjust the level of detail of the analysis based on the importance of each chapter. For example, the comprehension unit can perform a detailed analysis of important chapters and emphasize important points. For less important chapters, the comprehension unit can also perform a simplified analysis and provide only basic points. Furthermore, the comprehension unit can dynamically adjust the importance of each chapter based on the student's learning progress and provide necessary information. This allows for a detailed analysis of important chapters, improving learning efficiency.

[0077] When analyzing class records, the comprehension unit can perform the analysis based on the content of the teacher's remarks or the pace at which the class is progressing. For example, when analyzing class records, the comprehension unit performs text analysis of the content of the teacher's remarks and extracts important points. For example, the comprehension unit analyzes the content of the teacher's remarks and extracts important concepts and keywords. The comprehension unit can also organize information to make it easier for students to understand based on the pace at which the class is progressing. For example, the comprehension unit analyzes the pace at which the class is progressing and provides information at an appropriate time. The comprehension unit can also prioritize analysis of important information by taking into account the frequency of the teacher's remarks and the points emphasized. For example, the comprehension unit prioritizes analysis of points emphasized by the teacher and extracts them as important information. This allows for appropriate analysis according to the progress of the class to deepen students' understanding.

[0078] The understanding unit can improve the accuracy of analysis by referring to past analysis results when analyzing textbooks or lesson content. For example, the understanding unit can improve the accuracy of analysis by referring to past analysis results when analyzing textbooks or lesson content. For example, the understanding unit stores past analysis results in a database and refers to them when performing a new analysis. The understanding unit can also improve the accuracy of analysis based on patterns obtained from past analysis results. For example, the understanding unit can use past analysis results as a feedback loop to continuously improve the analysis algorithm. This makes it possible to continuously improve the accuracy of analysis by utilizing past analysis results.

[0079] The understanding unit can estimate the student's emotions and adjust the display method of the analysis results based on the estimated student's emotions. For example, the understanding unit can estimate the student's emotions and adjust the display method of the analysis results based on the estimated student's emotions. For example, if the student is feeling stressed, the understanding unit can provide a simple, highly visible display method. If the student is relaxed, the understanding unit can also provide a display method including detailed information. Furthermore, if the student is excited, the understanding unit can also provide a visually appealing display method. This can provide a display method that corresponds to the student's emotions and improve the effectiveness of learning. Emotion estimation is achieved using an emotion estimation function, for example, using an emotion engine or generation AI. The generation AI can be, but is not limited to, a text generation AI (e.g., LLM) or a multimodal generation AI.

[0080] When analyzing the content of a textbook, the comprehension unit can compare it with the content of other textbooks and reference books. For example, when analyzing the content of a textbook, the comprehension unit compares it with the content of other textbooks and reference books. For example, the comprehension unit refers to the content of other textbooks that cover the same topic and performs a comparative analysis. The comprehension unit can also provide information that complements the content of the textbook based on the content of reference books. Furthermore, the comprehension unit can compare it with the content of other textbooks and reference books to highlight important points. This makes it possible to perform a more comprehensive analysis by comparing it with other textbooks and reference books.

[0081] When analyzing a lesson record, the understanding unit can perform the analysis by combining the video and audio data of the lesson. For example, when analyzing a lesson record, the understanding unit analyzes the video data of the lesson and extracts important scenes. For example, the understanding unit analyzes the video data of the lesson and extracts important points. The understanding unit can also convert audio data into text and analyze the content of what is being said. For example, the understanding unit analyzes audio data during the lesson and extracts important content of what is being said. Furthermore, the understanding unit can combine the video and audio data to perform a more detailed analysis. For example, the understanding unit integrates the video data and audio data and extracts important information. In this way, using video and audio data together enables a more detailed analysis.

[0082] The understanding unit can customize the analysis method by reflecting the student's learning history when analyzing textbooks and class content. For example, the understanding unit can customize the analysis method by reflecting the student's learning history when analyzing textbooks and class content. For example, the understanding unit can adjust the level of detail of the analysis based on the student's past learning history. The understanding unit can also change the focus of the analysis by taking into account the student's strengths and weaknesses. Furthermore, the understanding unit can use the student's learning history as a feedback loop to continuously improve the analysis method. This makes it possible to reflect the student's learning history and perform more personalized analysis.

[0083] The assessment unit can estimate the student's emotions and adjust the method for assessing the learning style based on the estimated student's emotions. The assessment unit, for example, estimates the student's emotions and adjusts the method for assessing the learning style based on the estimated student's emotions. For example, if the student is feeling stressed, the assessment unit can suggest a learning style that allows the student to relax. Furthermore, if the student is relaxed, the assessment unit can also suggest a learning style that increases concentration. Furthermore, if the student is excited, the assessment unit can also suggest a learning style that attracts the student's interest. This makes it possible to assess the learning style according to the student's emotions. The estimation of emotions is realized using an emotion estimation function, for example, using an emotion engine or a generation AI. The generation AI can be, but is not limited to, a text generation AI (e.g., LLM) or a multimodal generation AI.

[0084] When analyzing past test results, the comprehension unit can adjust the level of detail of the analysis based on the difficulty of each question. For example, when analyzing past test results, the comprehension unit adjusts the level of detail of the analysis based on the difficulty of each question. For example, the comprehension unit performs a detailed analysis for high-difficulty questions and provides key points for understanding. For low-difficulty questions, the comprehension unit can also perform a simplified analysis and provide only basic key points. Furthermore, the comprehension unit can dynamically adjust the difficulty of each question based on the student's learning progress and provide necessary information. This enables detailed analysis according to the difficulty of each question.

[0085] When analyzing the homework submission status, the grasping unit can perform the analysis taking into consideration the timing and method of submission. For example, when analyzing the homework submission status, the grasping unit performs the analysis taking into consideration the timing and method of submission. For example, the grasping unit analyzes the timing of homework submission to grasp the student's study habits. The grasping unit can also analyze the submission status taking into consideration the submission method (online, paper, etc.). Furthermore, the grasping unit can analyze the frequency and delay of submission to evaluate the student's learning attitude. This makes it possible to perform a detailed analysis according to the submission status.

[0086] When analyzing the content of comments made during class, the comprehension unit can perform the analysis taking into consideration the frequency of comments and the relevance of the content. For example, when analyzing the content of comments made during class, the comprehension unit performs the analysis taking into consideration the frequency of comments and the relevance of the content. For example, the comprehension unit analyzes the frequency of comments to evaluate the student's level of engagement. The comprehension unit can also analyze the relevance of the content of comments to evaluate the level of understanding. Furthermore, the comprehension unit can analyze the timing of comments to evaluate the level of concentration during class. This makes it possible to perform a detailed analysis based on the content of comments.

[0087] The grasping unit can estimate the student's emotions and adjust the method for identifying the student's strong and weak areas based on the estimated student's emotions. The grasping unit, for example, estimates the student's emotions and adjusts the method for identifying the student's strong and weak areas based on the estimated student's emotions. For example, if the student is feeling stressed, the grasping unit can prioritize identifying the student's weak areas. Furthermore, if the student is relaxed, the grasping unit can prioritize identifying the student's strong areas. Furthermore, if the student is excited, the grasping unit can prioritize identifying the student's interesting areas. This makes it possible to identify the student's strong and weak areas according to the student's emotions. Emotion estimation is realized using an emotion estimation function, for example, using an emotion engine or generative AI. The generative AI can be, but is not limited to, a text generation AI (e.g., LLM) or a multimodal generation AI.

[0088] When analyzing past test results, the ascertaining unit can compare the results with those of other students. For example, when analyzing past test results, the ascertaining unit performs an analysis by comparing the results with those of other students. For example, the ascertaining unit compares the results with those of other students in the same class to evaluate the relative level of understanding. The ascertaining unit can also perform a comparative analysis with other students based on past test results. Furthermore, the ascertaining unit can also identify areas of strength and weakness by referring to the results of other students. This makes it possible to evaluate the relative level of understanding by comparing the results with those of other students.

[0089] When analyzing the homework submission status, the grasping unit can perform the analysis taking into consideration the content and quality of the submission. For example, when analyzing the homework submission status, the grasping unit performs the analysis taking into consideration the content and quality of the submission. For example, the grasping unit analyzes the content of the submission and evaluates the level of understanding. The grasping unit can also analyze the quality of the submission and evaluate the depth of learning. Furthermore, the grasping unit can comprehensively analyze the content and quality of the submission and evaluate the learning attitude. This makes it possible to perform a detailed analysis based on the content and quality of the submission.

[0090] When analyzing the content of utterances made during a class, the comprehension unit can compare the content of utterances made during a class with the content of utterances made during other classes. For example, when analyzing the content of utterances made during a class, the comprehension unit compares the content of utterances made during a class with the content of utterances made during other classes to evaluate the level of understanding. The comprehension unit can also compare the content of utterances made during a class with the content of utterances made during other classes to evaluate the relative level of understanding. Furthermore, the comprehension unit can analyze the frequency of utterances and the relevance of the content by referring to the content of utterances made during other classes. This makes it possible to evaluate the level of understanding in more detail by comparing the content of utterances made during a class with the content of utterances made during other classes.

[0091] The generation unit can estimate a student's emotions and adjust the method for generating homework and tests based on the estimated student emotions. The generation unit, for example, estimates a student's emotions and adjusts the method for generating homework and tests based on the estimated student emotions. For example, if a student is feeling stressed, the generation unit can generate homework that includes many easy questions. If a student is relaxed, the generation unit can also generate homework that includes many difficult questions. Furthermore, if a student is excited, the generation unit can also generate homework that includes many interesting questions. This makes it possible to generate homework and tests that correspond to the student's emotions. Emotion estimation is achieved using an emotion estimation function, for example, using an emotion engine or generation AI. The generation AI can be a text generation AI (e.g., LLM) or a multimodal generation AI, but is not limited to these examples.

[0092] When generating homework or tests, the generation unit can adjust the level of detail based on the importance of each question. For example, when generating homework or tests, the generation unit adjusts the level of detail based on the importance of each question. For example, the generation unit generates homework that includes detailed explanations for important questions. The generation unit can also generate homework that includes brief explanations for less important questions. Furthermore, the generation unit can dynamically adjust the importance of each question based on the student's learning progress and provide necessary information. This makes it possible to generate detailed homework or tests that correspond to the importance of each question.

[0093] The generation unit can generate homework and tests taking into consideration the student's past grades and level of understanding. For example, the generation unit generates homework and tests taking into consideration the student's past grades and level of understanding. For example, the generation unit generates homework of an appropriate level of difficulty based on the student's past grades. The generation unit can also generate homework to deepen the student's understanding by taking into consideration the student's level of understanding. Furthermore, the generation unit can generate optimal homework by comprehensively taking into consideration the student's past grades and level of understanding. This makes it possible to generate optimal homework and tests based on the student's past grades and level of understanding.

[0094] The generation unit can improve the accuracy of generation by referring to past generation results when generating homework or tests. For example, when generating homework or tests, the generation unit improves the accuracy of generation by referring to past generation results. For example, the generation unit stores past generation results in a database and refers to them when generating new homework or tests. The generation unit can also improve the accuracy of generation based on patterns obtained from past generation results. Furthermore, the generation unit can utilize past generation results as a feedback loop to continuously improve the generation algorithm. In this way, the accuracy of generation can be continuously improved by utilizing past generation results.

[0095] The generation unit can estimate the student's emotions and adjust the difficulty of homework and tests based on the estimated student emotions. The generation unit, for example, estimates the student's emotions and adjusts the difficulty of homework and tests based on the estimated student emotions. For example, if the student is feeling stressed, the generation unit can generate homework that includes many easy questions. If the student is relaxed, the generation unit can also generate homework that includes many difficult questions. Furthermore, if the student is excited, the generation unit can also generate homework that includes many interesting questions. This makes it possible to generate homework and tests with difficulty levels that correspond to the student's emotions. Emotion estimation is achieved, for example, using an emotion estimation function using an emotion engine or generation AI. The generation AI can be, but is not limited to, a text generation AI (e.g., LLM) or a multimodal generation AI.

[0096] The generation unit can generate homework or tests by comparing them with the grades and levels of understanding of other students. For example, when generating homework or tests, the generation unit generates them by comparing them with the grades and levels of understanding of other students. For example, the generation unit generates homework of an appropriate level of difficulty by comparing them with the grades of other students in the same class. The generation unit can also generate homework that deepens understanding by referring to the levels of understanding of other students. Furthermore, the generation unit can generate optimal homework by comprehensively taking into account the grades and levels of understanding of other students. This makes it possible to generate homework or tests of a relative level of difficulty by comparing them with the grades and levels of understanding of other students.

[0097] The generation unit can generate homework or tests by reflecting the content of other subjects or courses. For example, when generating homework or tests, the generation unit generates them by reflecting the content of other subjects or courses. For example, the generation unit generates homework that includes related questions by referring to the content of other subjects. The generation unit can also generate homework that promotes comprehensive understanding by reflecting the content of other subjects. Furthermore, the generation unit can combine the content of other subjects or courses to generate homework that includes complex questions. This makes it possible to generate homework or tests that promote comprehensive understanding by reflecting the content of other subjects or courses.

[0098] The generation unit can customize the generation method by reflecting the student's learning history when generating homework or tests. For example, when generating homework or tests, the generation unit customizes the generation method by reflecting the student's learning history. For example, the generation unit generates homework of an appropriate level of difficulty based on the student's past learning history. The generation unit can also generate homework to deepen understanding by taking into account the student's strengths and weaknesses. Furthermore, the generation unit can utilize the student's learning history as a feedback loop to continuously improve the generation algorithm. This makes it possible to generate more personalized homework and tests by reflecting the student's learning history.

[0099] The reporting unit can estimate the student's emotions and adjust the method of reporting the learning progress based on the estimated student emotions. For example, the reporting unit can estimate the student's emotions and adjust the method of reporting the learning progress based on the estimated student emotions. For example, if the student is feeling stressed, the reporting unit can provide a simple and highly visible reporting method. If the student is relaxed, the reporting unit can also provide a reporting method that includes detailed information. Furthermore, if the student is excited, the reporting unit can also provide a visually appealing reporting method. This can provide a reporting method that corresponds to the student's emotions and improve the effectiveness of learning. Emotion estimation is achieved using an emotion estimation function, for example, using an emotion engine or generative AI. Generative AI can be, but is not limited to, text generation AI (e.g., LLM) or multimodal generation AI.

[0100] The reporting unit can adjust the level of detail of the report based on each student's level of understanding when reporting learning progress. For example, when reporting learning progress, the reporting unit adjusts the level of detail of the report based on each student's level of understanding. For example, the reporting unit provides a detailed report to students with a high level of understanding. The reporting unit can also provide a simplified report to students with a low level of understanding. Furthermore, the reporting unit can dynamically adjust the level of detail of the report based on each student's level of understanding. This makes it possible to provide a detailed report according to each student's level of understanding.

[0101] The reporting unit can improve the accuracy of the report by referring to past report results when reporting learning progress. For example, when reporting learning progress, the reporting unit improves the accuracy of the report by referring to past report results. For example, the reporting unit stores past report results in a database and refers to them when making a new report. The reporting unit can also improve the accuracy of the report based on patterns obtained from past report results. Furthermore, the reporting unit can utilize past report results as a feedback loop to continuously improve the reporting algorithm. In this way, the accuracy of the report can be continuously improved by utilizing past report results.

[0102] The reporting unit can improve the reporting method by reflecting parental feedback when reporting learning progress. For example, the reporting unit improves the reporting method by reflecting parental feedback when reporting learning progress. For example, the reporting unit adjusts the reporting method based on parental feedback. The reporting unit can also customize the report content in accordance with parental requests. Furthermore, the reporting unit can utilize parental feedback as a feedback loop to continuously improve the reporting method. In this way, a more effective reporting method can be provided by reflecting parental feedback.

[0103] The reporting unit can estimate the student's emotions and adjust the frequency of learning progress reports based on the estimated student emotions. The reporting unit, for example, estimates the student's emotions and adjusts the frequency of learning progress reports based on the estimated student emotions. For example, if the student is feeling stressed, the reporting unit can reduce the reporting frequency to reduce the burden. Also, if the student is relaxed, the reporting unit can increase the reporting frequency to provide more detailed information. Furthermore, if the student is excited, the reporting unit can adjust the reporting frequency to provide information at an appropriate time. This makes it possible to adjust the reporting frequency according to the student's emotions. Emotion estimation is realized using an emotion estimation function, for example, using an emotion engine or generative AI. Generative AI can be, but is not limited to, text generation AI (e.g., LLM) or multimodal generation AI.

[0104] The reporting unit can compare the learning progress with that of other students when reporting the learning progress. For example, the reporting unit compares the learning progress with that of other students when reporting the learning progress. For example, the reporting unit compares the learning progress with that of other students in the same class and reports the relative progress. The reporting unit can also evaluate the level of understanding by referring to the progress of other students. Furthermore, the reporting unit can customize the report content based on the progress of other students. This makes it possible to evaluate the relative progress by comparing with the progress of other students.

[0105] The reporting unit can customize the report content to reflect the interests and requests of the parent when reporting learning progress. For example, the reporting unit customizes the report content to reflect the interests and requests of the parent when reporting learning progress. For example, the reporting unit adjusts the report content based on the interests of the parent. The reporting unit can also customize the report content in accordance with the requests of the parent. Furthermore, the reporting unit can continuously improve the report content based on feedback from the parent. This makes it possible to provide customized reports that reflect the interests and requests of the parent.

[0106] The reporting department can customize the reporting method by reflecting the student's learning history when reporting learning progress. For example, when reporting learning progress, the reporting department customizes the reporting method by reflecting the student's learning history. For example, the reporting department adjusts the report content based on the student's past learning history. The reporting department can also customize the report content by taking into account the student's strengths and weaknesses. Furthermore, the reporting department can utilize the student's learning history as a feedback loop to continuously improve the reporting method. This allows for more personalized reporting by reflecting the student's learning history. === Hard Collateral 1-1 === Each of the multiple elements, including the understanding unit, grasping unit, generation unit, and reporting 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 understanding unit is realized by the control unit 46A of the smart device 14 or the specific processing unit 290 of the data processing device 12. For example, the camera 42 and microphone 38B of the smart device 14 can be used to analyze textbook content and class records. The grasping unit is realized, for example, by the specific processing unit 290 of the data processing device 12 and analyzes past test results and homework submission status. The generation unit is realized, for example, by the control unit 46A of the smart device 14 or the specific processing unit 290 of the data processing device 12 and generates customized homework and tests. The reporting unit is realized, for example, by the specific processing unit 290 of the data processing device 12 and reports learning progress to parents. === Hard Collateral 1-2 === Each of the multiple elements, including the understanding unit, grasping unit, generation unit, and reporting unit, described above, is implemented, for example, by at least one of the smart glasses 214 and the data processing device 12. For example, the understanding unit is implemented by the control unit 46A of the smart glasses 214 or the specific processing unit 290 of the data processing device 12. For example, the camera 42 and microphone 238 of the smart glasses 214 can be used to analyze textbook content and class records. The grasping unit is implemented, for example, by the specific processing unit 290 of the data processing device 12 and analyzes past test results and homework submission status. The generation unit is implemented, for example, by the control unit 46A of the smart glasses 214 or the specific processing unit 290 of the data processing device 12 and generates customized homework and tests. The reporting unit is implemented, for example, by the specific processing unit 290 of the data processing device 12 and reports learning progress to parents. === Hard Collateral 1-3 === Each of the multiple elements including the above-mentioned understanding unit, grasping unit, generation unit, and reporting unit is realized, for example, by at least one of the headset-type terminal 314 and the data processing device 12. For example, the understanding unit is realized by the control unit 46A of the headset-type terminal 314 or the specific processing unit 290 of the data processing device 12. For example, the camera 42 and the microphone 238 of the headset-type terminal 314 can be used to analyze textbook content and class records. The grasping unit is realized, for example, by the specific processing unit 290 of the data processing device 12 and analyzes past test results and homework submission status. The generation unit is realized, for example, by the control unit 46A of the headset-type terminal 314 or the specific processing unit 290 of the data processing device 12 and generates customized homework and tests. The reporting unit is realized, for example, by the specific processing unit 290 of the data processing device 12 and reports learning progress to parents. === Hard Collateral 1-4 === Each of the multiple elements including the above-mentioned understanding unit, grasping unit, generation unit, and reporting unit is realized, for example, by at least one of the robot 414 and the data processing device 12. For example, the understanding unit is realized by the control unit 46A of the robot 414 or the specific processing unit 290 of the data processing device 12. For example, the camera 42 and the microphone 238 of the robot 414 can be used to analyze textbook content and class records. The grasping unit is realized, for example, by the specific processing unit 290 of the data processing device 12 and analyzes past test results and homework submission status. The generation unit is realized, for example, by the control unit 46A of the robot 414 or the specific processing unit 290 of the data processing device 12 and generates customized homework and tests. The reporting unit is realized, for example, by the specific processing unit 290 of the data processing device 12 and reports learning progress to parents.

[0107] The system according to the embodiment is not limited to the above-described example, and various modifications are possible, for example, as follows.

[0108] The personalized education system may further include an interactive feedback unit. The feedback unit provides instant feedback to students after they submit their homework or tests. For example, the feedback unit may display whether a student answered correctly or incorrectly in real time and provide detailed explanations for incorrect questions. The feedback unit may also analyze the student's answer patterns and provide advice based on their level of understanding. Furthermore, the feedback unit may have an interactive function that provides instant answers when a student inputs a question for a specific question. This allows students to instantly resolve their doubts during their studies and progress efficiently.

[0109] The personalized education system can further include a motivation improvement unit. The motivation improvement unit provides a function to increase students' motivation to learn. For example, the motivation improvement unit provides a mechanism that allows students to set goals and earn badges and points according to their achievement. The motivation improvement unit can also visually display the results achieved by students as they progress through their studies, allowing them to feel their progress. Furthermore, the motivation improvement unit can provide a ranking function that allows students to compete with other students, thereby increasing their motivation to learn. This allows students to enjoy their studies.

[0110] The education personalization system further includes an emotion estimation unit, which can adjust the learning content based on the student's emotions. For example, if the student is feeling stressed, the emotion estimation unit can provide easy questions that will help the student relax. Also, if the student is relaxed, the emotion estimation unit can provide more difficult questions. Furthermore, if the student is excited, the emotion estimation unit can provide interesting questions. This makes it possible to adjust the learning content according to the student's emotions, thereby achieving more effective learning support.

[0111] The personalized education system may further include a learning environment adjustment unit. The learning environment adjustment unit provides a function for optimizing a student's learning environment. For example, the learning environment adjustment unit adjusts background music and lighting to provide an environment in which the student can easily concentrate. The learning environment adjustment unit may also provide music and images with a relaxing effect to provide an environment in which the student can relax. Furthermore, if the student is excited, the learning environment adjustment unit may provide an environment to improve concentration. This optimizes the student's learning environment and improves learning effectiveness.

[0112] The personalized education system can further include a learning history analysis unit. The learning history analysis unit analyzes a student's past learning history and provides information to optimize future learning plans. For example, the learning history analysis unit analyzes a student's past test results and homework submission status to identify their strengths and weaknesses. The learning history analysis unit can also analyze a student's learning patterns and propose an optimal learning schedule. Furthermore, the learning history analysis unit can set future learning goals based on the student's learning history and evaluate the degree to which they have been achieved. This makes it possible to utilize a student's learning history to provide more effective learning support.

[0113] The education personalization system further includes an emotional feedback unit, which can provide feedback based on the student's emotions. For example, if the student is feeling stressed, the emotional feedback unit can provide an encouraging message. If the student is feeling relaxed, the emotional feedback unit can also provide a message encouraging the student to take on more challenges. Furthermore, if the student is excited, the emotional feedback unit can also provide interesting information. This allows for feedback based on the student's emotions, which can increase their motivation to learn.

[0114] The education personalization system can further include a learning style adaptation unit. The learning style adaptation unit adjusts the learning content according to the student's learning style. For example, the learning style adaptation unit can provide learning materials that include many diagrams and illustrations to a student who prefers visual learning. It can also provide learning materials that include audio commentary to a student who prefers auditory learning. It can also provide learning materials that include experiments and practical training to a student who prefers practical learning. In this way, it is possible to provide optimal learning content according to the student's learning style.

[0115] The personalized education system further includes an emotion monitoring unit, which can monitor students' emotions in real time. The emotion monitoring unit estimates emotions from students' facial expressions and voices, for example, and adjusts learning content based on that information. For example, if a student appears tired, the emotion monitoring unit can display a message encouraging the student to take a break. Also, if a student is concentrating, the emotion monitoring unit can display a message encouraging the student to continue studying. Furthermore, if a student appears excited, the emotion monitoring unit can provide additional information that will pique the student's interest. This enables real-time learning support according to the student's emotions.

[0116] The personalized education system may further include a learning goal setting unit. The learning goal setting unit provides a function for students to set their own learning goals and evaluate their achievement. For example, the learning goal setting unit allows students to set short-term and long-term goals and track their progress. The learning goal setting unit may also provide specific action plans for achieving the goals. Furthermore, the learning goal setting unit may provide feedback according to the degree of goal achievement to increase student motivation. This allows students to effectively progress in their studies toward their learning goals.

[0117] The personalized education system further includes an emotion history analysis unit, which can analyze a student's emotion history to optimize learning content. The emotion history analysis unit, for example, analyzes a student's past emotion data and evaluates the effectiveness of their learning. The emotion history analysis unit can also analyze patterns of emotion change and use this information to adjust learning content. Furthermore, the emotion history analysis unit can optimize future learning plans based on the student's emotion history. This makes it possible to utilize a student's emotion history to provide more effective learning support.

[0118] The processing flow of the second embodiment will be briefly explained below.

[0119] Step 1: The comprehension unit understands the textbook or lesson content. For example, the comprehension unit analyzes the textbook content or lesson records to extract important points and concepts. Specifically, text analysis technology is used to analyze the textbook content and extract important points. Voice recognition technology can also be used to analyze lesson records and extract important concepts. Furthermore, image recognition technology can be used to analyze textbook diagrams and extract important information. Step 2: The understanding unit understands the student's learning style and level of comprehension based on the information understood by the understanding unit. The understanding unit analyzes, for example, past test results, homework submission status, and comments made during class to identify each student's strengths and weaknesses. Specifically, it analyzes test results to identify each student's strengths and weaknesses. It can also analyze homework submission status and evaluate each student's learning attitude. It can also analyze comments made during class to evaluate each student's level of comprehension. Step 3: The generation unit generates customized homework and tests based on the information grasped by the grasping unit. The generation unit generates customized homework and tests, for example, based on the student's level of understanding. Specifically, for a student who is weak in a particular subject, the generation unit generates homework that includes many questions related to that subject. It can also provide more difficult questions for subjects where the student has a high level of understanding. Furthermore, it can generate homework and tests in a visually appealing format to suit the student's learning style. Step 4: The reporting unit reports learning progress to parents based on the homework and test results generated by the generation unit. For example, the reporting unit periodically analyzes each student's learning situation and reports progress to parents. Specifically, it reports learning progress and changes in understanding on a weekly basis. It can also make suggestions to adjust the learning plan as needed.

[0120] 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.

[0121] 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.

[0122] 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.

[0123] The correspondence between each part and the device or control part is not limited to the above example, and various modifications are possible.

[0124] [Second embodiment] FIG. 3 shows an example of the configuration of a data processing system 210 according to the second embodiment.

[0125] 3, the data processing system 210 includes a data processing device 12 and smart glasses 214. An example of the data processing device 12 is a server.

[0126] 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.

[0127] 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.

[0128] 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.

[0129] 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).

[0130] 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.

[0131] 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.

[0132] 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.

[0133] 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.

[0134] 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.

[0135] 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.

[0136] 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.

[0137] The data generation model 58 is a so-called generative AI. An example of the data generation model 58 is a generative AI such as ChatGPT. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 receives a prompt containing an instruction, as well as inference data such as voice data representing speech, text data representing text, and image data representing an image. The data generation model 58 performs inference on the input inference data in accordance with the instruction indicated by the prompt and outputs the inference result in a data format such as voice data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization. The identification processing unit 290 performs the above-mentioned identification processing using the data generation model 58. The data generation model 58 may be a fine-tuned model so as to output an inference result from a prompt that does not include an instruction. In this case, the data generation model 58 can output an inference result from a prompt that does not include an instruction. The data processing device 12 and the like include multiple types of data generation models 58, and the data generation model 58 includes AI other than the generative AI. The AI ​​other than the generative AI may be, for example, linear regression, logistic regression, decision tree, random forest, support vector machine (SVM), k-means clustering, convolutional neural network (CNN), recurrent neural network (RNN), generative adversarial network (GAN), or naive Bayes, and can perform various processes, but is not limited to these examples. The AI ​​may also be an AI agent. When the processes of each of the above-mentioned parts are performed by AI, the processes may be performed in part or entirely by AI, but are not limited to these examples. The processes performed by AI, including the generative AI, may be replaced with rule-based processes.

[0138] 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.

[0139] The correspondence between each part and the device or control part is not limited to the above example, and various modifications are possible.

[0140] [Third embodiment] FIG. 5 shows an example of the configuration of a data processing system 310 according to the third embodiment.

[0141] 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.

[0142] 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.

[0143] 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.

[0144] 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.

[0145] 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).

[0146] 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.

[0147] Fig. 6 shows an example of the main functions of the data processing device 12 and the headset 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.

[0148] The processor 28 reads the specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific processing is realized by the processor 28 operating as a specific processing unit 290 in accordance with the specific processing program 56 executed on the RAM 30.

[0149] The storage 32 stores a data generation model 58 and an emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290. The identification processing unit 290 can estimate a user's emotion using the emotion identification model 59 and perform identification processing using the user's emotion. The emotion estimation function (emotion identification function) using the emotion identification model 59 performs various estimations and predictions regarding the user's emotion, including estimation and prediction of the user's emotion, but is not limited to these examples. Furthermore, the estimation and prediction of emotion also includes, for example, emotion analysis.

[0150] In the 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.

[0151] Note that a device other than the data processing device 12 may have the data generation model 58. For example, a server device may have the data generation model 58. In this case, the data processing device 12 communicates with the server device having the data generation model 58 to obtain a processing result (such as a prediction result) using the data generation model 58. Furthermore, the data processing device 12 may be a server device, or may be a terminal device (for example, a mobile phone, a robot, a home appliance, etc.) owned by a user.

[0152] The specific processing unit 290 transmits the result of the specific processing to the 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.

[0153] The data generation model 58 is a so-called generative AI. An example of the data generation model 58 is a generative AI such as ChatGPT. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 receives a prompt containing an instruction, as well as inference data such as voice data representing speech, text data representing text, and image data representing an image. The data generation model 58 performs inference on the input inference data in accordance with the instruction indicated by the prompt and outputs the inference result in a data format such as voice data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization. The identification processing unit 290 performs the above-mentioned identification processing using the data generation model 58. The data generation model 58 may be a fine-tuned model so as to output an inference result from a prompt that does not include an instruction. In this case, the data generation model 58 can output an inference result from a prompt that does not include an instruction. The data processing device 12 and the like include multiple types of data generation models 58, and the data generation model 58 includes AI other than the generative AI. The AI ​​other than the generative AI may be, for example, linear regression, logistic regression, decision tree, random forest, support vector machine (SVM), k-means clustering, convolutional neural network (CNN), recurrent neural network (RNN), generative adversarial network (GAN), or naive Bayes, and can perform various processes, but is not limited to these examples. The AI ​​may also be an AI agent. When the processes of each of the above-mentioned parts are performed by AI, the processes may be performed in part or entirely by AI, but are not limited to these examples. The processes performed by AI, including the generative AI, may be replaced with rule-based processes.

[0154] 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.

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

[0156] [Fourth embodiment] FIG. 7 shows an example of the configuration of a data processing system 410 according to the fourth embodiment.

[0157] 7, a data processing system 410 includes a data processing device 12 and a robot 414. An example of the data processing device 12 is a server.

[0158] 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.

[0159] 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.

[0160] 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.

[0161] 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).

[0162] 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.

[0163] 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.

[0164] 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.

[0165] 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.

[0166] 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.

[0167] 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.

[0168] 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.

[0169] 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.

[0170] The data generation model 58 is a so-called generative AI. An example of the data generation model 58 is a generative AI such as ChatGPT. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 receives a prompt containing an instruction, as well as inference data such as voice data representing speech, text data representing text, and image data representing an image. The data generation model 58 performs inference on the input inference data in accordance with the instruction indicated by the prompt and outputs the inference result in a data format such as voice data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization. The identification processing unit 290 performs the above-mentioned identification processing using the data generation model 58. The data generation model 58 may be a fine-tuned model so as to output an inference result from a prompt that does not include an instruction. In this case, the data generation model 58 can output an inference result from a prompt that does not include an instruction. The data processing device 12 and the like include multiple types of data generation models 58, and the data generation model 58 includes AI other than the generative AI. The AI ​​other than the generative AI may be, for example, linear regression, logistic regression, decision tree, random forest, support vector machine (SVM), k-means clustering, convolutional neural network (CNN), recurrent neural network (RNN), generative adversarial network (GAN), or naive Bayes, and can perform various processes, but is not limited to these examples. The AI ​​may also be an AI agent. When the processes of each of the above-mentioned parts are performed by AI, the processes may be performed in part or entirely by AI, but are not limited to these examples. The processes performed by AI, including the generative AI, may be replaced with rule-based processes.

[0171] 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.

[0172] The correspondence between each part and the device or control part is not limited to the above example, and various modifications are possible.

[0173] 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.

[0174] 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.

[0175] 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.

[0176] 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).

[0177] 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.

[0178] 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."

[0179] 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.

[0180] 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.

[0181] 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.

[0182] 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.

[0183] 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.

[0184] 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.

[0185] 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.

[0186] 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.

[0187] 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.

[0188] 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.

[0189] 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, in order to avoid confusion and to 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.

[0190] 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.

[0191] [Explanation of symbols]

[0192] 10, 210, 310, 410 Data Processing Systems 12 Data Processing Device 14 Smart Devices 214 Smart Glasses 314 Headset-type terminal 414 Robot

Claims

1. A system comprising: an understanding unit that understands textbook or class content; an understanding unit that understands a student's learning style and level of understanding based on the information understood by the understanding unit; a generation unit that generates customized homework and tests based on the information understood by the understanding unit; and a reporting unit that reports learning progress to parents based on the results of the homework and tests generated by the generation unit.

2. 2. The system according to claim 1, wherein the comprehension unit analyzes the contents of a textbook or a lesson record and extracts important points and concepts.

3. 2. The system according to claim 1, wherein the ascertaining unit analyzes past test results, homework submission status, and comments made during class to identify each student's strengths and weaknesses.

4. The generation unit Generate customized homework and tests based on student comprehension 2. The system of claim 1.

5. The reporting unit Regularly analyze each student's learning status and provide progress reports to parents 2. The system of claim 1.

6. The reporting unit Make suggestions to adjust the study plan as needed 2. The system of claim 1.

7. The understanding unit Estimate student emotions and adjust the analysis of textbooks and lesson content based on the estimated student emotions 2. The system of claim 1.

8. The understanding unit When analyzing the content of a textbook, adjust the level of detail based on the importance of each chapter.

2. The system of claim 1.

Images