System

Abstract

An object of a system according to an embodiment is to efficiently generate test questions according to a learning situation of each student.SOLUTION: A system according to an embodiment includes a learning data collection unit, an analysis unit, and a test generation unit. The learning data collection unit collects learning data of a student. The analysis unit analyzes the learning data collected by the learning data collection unit. The test generation unit generates a test question based on a result analyzed by the analysis 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 had the problem of making it difficult to efficiently generate test questions that correspond to the learning situation of each student.

[0005] The system according to the embodiment aims to efficiently generate test questions that correspond to the learning situation of each student. [Means for solving the problem]

[0006] The system according to the embodiment includes a learning data collection unit, an analysis unit, and a test generation unit. The learning data collection unit collects learning data of students. The analysis unit analyzes the learning data collected by the learning data collection unit. The test generation unit generates test questions based on the results of the analysis by the analysis unit. [Effects of the Invention]

[0007] The system according to the embodiment can efficiently generate test questions that correspond to the learning situation of each student. [Brief explanation of the drawings]

[0008] [Figure 1] 1 is a conceptual diagram showing an example of the configuration of a data processing system according to a first embodiment. [Figure 2] 1 is a conceptual diagram showing an example of main functions of a data processing device and a smart device according to a first embodiment. [Figure 3] FIG. 10 is a conceptual diagram showing an example of the configuration of a data processing system according to a second embodiment. [Figure 4] FIG. 10 is a conceptual diagram showing an example of main functions of a data processing device and smart glasses according to a second embodiment. [Figure 5] FIG. 10 is a conceptual diagram showing an example of the configuration of a data processing system according to a third embodiment. [Figure 6] FIG. 11 is a conceptual diagram showing an example of main functions of a data processing device and a headset-type terminal according to a third embodiment. [Figure 7] FIG. 10 is a conceptual diagram showing an example of the configuration of a data processing system according to a fourth embodiment. [Figure 8] FIG. 10 is a conceptual diagram showing an example of main functions of a data processing device and a robot according to a fourth embodiment. [Figure 9] 1 shows an emotion map onto which multiple emotions are mapped. [Figure 10] 1 shows an emotion map onto which multiple emotions are mapped. DETAILED DESCRIPTION OF THE INVENTION

[0009] An example of an embodiment of a system according to the technology of the present disclosure will be described below with reference to the accompanying drawings.

[0010] First, the terms used in the following description will be explained.

[0011] In the following embodiments, a coded processor (hereinafter simply referred to as a "processor") may be a single arithmetic device or a combination of multiple arithmetic devices. Furthermore, the processor may be a single type of arithmetic device or a combination of multiple types of arithmetic devices. Examples of arithmetic devices include a CPU (Central Processing Unit), a GPU (Graphics Processing Unit), a GPGPU (General-Purpose computing on Graphics Processing Units), an APU (Accelerated Processing Unit), or a TPU (Tensor Processing Unit).

[0012] In the following embodiments, a coded RAM (Random Access Memory) is a memory in which information is temporarily stored and is used as a working memory by a processor.

[0013] In the following embodiments, the coded storage is one or more non-volatile storage devices that store various programs, various parameters, etc. Examples of non-volatile storage devices include flash memory (SSD (Solid State Drive)), magnetic disks (e.g., hard disks), and magnetic tapes.

[0014] In the following embodiments, a communication I / F (Interface) with a symbol is an interface including a communication processor, an antenna, etc. The communication I / F controls communication between multiple computers. Examples of communication standards applied to the communication I / F include wireless communication standards including 5G (5th Generation Mobile Communication System), Wi-Fi (registered trademark), and Bluetooth (registered trademark).

[0015] In the following embodiments, "A and / or B" is synonymous with "at least one of A and B." In other words, "A and / or B" means that it may be only A, only B, or a combination of A and B. Furthermore, in this specification, the same concept as "A and / or B" is also applied when three or more things are expressed connected by "and / or."

[0016] [First embodiment] FIG. 1 shows an example of the configuration of a data processing system 10 according to the first embodiment.

[0017] 1, a data processing system 10 includes a data processing device 12 and a smart device 14. An example of the data processing device 12 is a server.

[0018] The data processing device 12 includes a computer 22, a database 24, and a communication I / F 26. The computer 22 includes a processor 28, a RAM 30, and a storage 32. The processor 28, RAM 30, and storage 32 are connected to a bus 34. The database 24 and the communication I / F 26 are also connected to the bus 34. The communication I / F 26 is connected to a network 54. Examples of the network 54 include a WAN (Wide Area Network) and / or a LAN (Local Area Network).

[0019] The smart device 14 includes a computer 36, a reception device 38, an output device 40, a camera 42, and a communication I / F 44. The computer 36 includes a processor 46, a RAM 48, and a storage 50. The processor 46, the RAM 48, and the storage 50 are connected to a bus 52. The reception device 38, the output device 40, and the camera 42 are also connected to the bus 52.

[0020] The reception device 38 includes a touch panel 38A and a microphone 38B, and receives user input. The touch panel 38A detects contact with a pointer (for example, a pen or a finger) to receive user input by the touch of the pointer. The microphone 38B detects the user's voice to receive user input by voice. The control unit 46A transmits data indicating the user input received by the touch panel 38A and the microphone 38B to the data processing device 12. In the data processing device 12, the specific processing unit 290 (see FIG. 2) acquires the data indicating the user input.

[0021] Output device 40 includes a display 40A and a speaker 40B, and presents data to a user by outputting the data in a form of expression that the user can perceive (e.g., audio and / or text). Display 40A displays visible information such as text and images in accordance with instructions from processor 46. Speaker 40B outputs audio in accordance with instructions from processor 46. Camera 42 is a compact digital camera equipped with an optical system including a lens, aperture, and shutter, and an imaging element such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor.

[0022] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 control the exchange of various information between the processor 46 and the processor 28 via the network 54.

[0023] FIG. 2 shows an example of the main functions of the data processing device 12 and the smart device 14.

[0024] 2, in the data processing device 12, a specific process is performed by the processor 28. A specific processing program 56 is stored in the storage 32. The specific processing program 56 is an example of a "program" according to the technology of the present disclosure. The processor 28 reads the specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific process is realized by the processor 28 operating as a specific processing unit 290 in accordance with the specific processing program 56 executed on the RAM 30.

[0025] The storage 32 stores a data generation model 58 and an emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290. The identification processing unit 290 can estimate the user's emotion using the emotion identification model 59 and perform identification processing using the user's emotion.

[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 may have a data generation model and an emotion identification model similar to the data generation model 58 and the emotion identification model 59.

[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) The test generation system according to the embodiment of the present invention is a system in which a generation AI creates individually optimized tests according to the learning situation and level of understanding of each student, thereby enabling the test generation system to provide effective tests that meet the learning needs of each individual student.

[0029] The test generation system according to the embodiment includes a learning data collection unit, an analysis unit, and a test generation unit. The learning data collection unit collects learning data from students. For example, the learning data collection unit collects past test results. The learning data collection unit can also collect homework grades. The learning data collection unit can also collect comments and questions made during class. For example, the learning data collection unit obtains test results from a database and provides them to the analysis unit. Homework grades are collected as data entered by teachers and provided to the analysis unit. Comments and questions made during class are converted into text using voice recognition technology and provided to the analysis unit. The analysis unit analyzes the learning data collected by the learning data collection unit. For example, the analysis unit analyzes the correct answer rate for questions that students have previously answered. The analysis unit can also analyze the answer time. The analysis unit can also identify areas or topics in which students have strengths and weaknesses. For example, the analysis unit identifies students' strong and weak areas based on the correct answer rate. The analysis unit evaluates the student's response to the difficulty of the questions based on the answer time. Statistical analysis and machine learning algorithms are used to identify strengths and weaknesses. The test generation unit generates test questions based on the results of the analysis by the analysis unit. For example, in a mathematics test, the test generation unit may provide more questions in areas in which the student is weak. The test generation unit may also provide fewer questions in areas in which the student is strong. The test generation unit may also adjust the difficulty of the questions according to the student's level of understanding. For example, the test generation unit automatically generates questions using a generation AI. The generation AI generates questions based on instructions such as the purpose of the test and the target grade and subject. The difficulty of the questions is dynamically adjusted based on the analysis results. This allows the test generation system according to the embodiment to provide an optimized test for each student. For example, the generated tests are customized according to the student's learning needs, providing effective learning support.

[0030] The learning data collection unit can collect behavioral data from students' daily lives and integrate it with the learning data for analysis. The learning data collection unit, for example, collects behavioral data from students' daily lives and integrates it with the learning data for analysis. For example, a smartwatch or fitness tracker can be used to record sleep time and exercise volume, and the impact of this on learning performance can be evaluated. The learning data collection unit can also record dietary content and analyze the impact of nutritional balance on learning performance. For example, meal timing and content can be recorded using an app, and the generation AI can evaluate learning effectiveness based on that data. The learning data collection unit can also monitor students' stress levels and analyze them in association with the learning data. For example, a stress measurement device can be used to record daily stress levels, and the impact of this on learning performance can be evaluated. This allows for a comprehensive evaluation of factors affecting learning performance.

[0031] When analyzing a student's learning data, the analysis unit can use comparative data with other students to evaluate the student's relative learning progress and propose an individualized learning strategy. For example, the analysis unit compares the student's learning data with that of other students to evaluate the student's relative learning progress. For example, it identifies in which areas the student is lagging behind compared to students in the same grade or class. The analysis unit also proposes an individualized learning strategy based on the learning data of other students. For example, it proposes an effective learning method by referring to success stories of students with similar learning patterns. The analysis unit also shares the student's learning data on the cloud and obtains comparative data with other students in real time. For example, it uses an online platform to create a learning plan while comparing the student's progress with that of other students. This makes it possible to evaluate the student's relative learning progress and propose an individualized learning strategy.

[0032] The learning data collection unit can automatically convert comments or questions made during class into text using speech recognition technology and use it for analysis. For example, the learning data collection unit converts comments made by students during class into text using speech recognition technology and collects it as learning data. For example, the content of the comments can be analyzed to identify the level of understanding and topics of interest. The learning data collection unit also converts questions asked by students during class into text using speech recognition technology and uses it for analysis. For example, based on the frequency and content of questions, it can identify areas of weakness and topics of interest. The learning data collection unit also converts discussions made during class into text using speech recognition technology and collects it as learning data. For example, it can analyze the content of the discussion to evaluate the level of understanding and communication ability. This allows the comments and questions made during class to be used for analysis.

[0033] The learning data collection unit can analyze students' facial expressions and postures using visual recognition technology to evaluate their levels of concentration and understanding. For example, the learning data collection unit photographs students' facial expressions during class with a camera and evaluates their levels of concentration using visual recognition technology. For example, it analyzes eye movements and facial direction to determine whether they are concentrating. The learning data collection unit also photographs students' posture with a camera and evaluates their levels of understanding using visual recognition technology. For example, it analyzes their leaning posture and hand movements to determine whether they are understanding. The learning data collection unit also simultaneously analyzes students' facial expressions and postures during class to comprehensively evaluate their levels of concentration and understanding. For example, it analyzes changes in facial expressions and posture to evaluate the learning effect. This makes it possible to evaluate students' levels of concentration and understanding.

[0034] The test generation unit can generate question formats that suit students' learning styles. For example, the test generation unit grasps students' learning styles in advance through questionnaires and tests, and generates question formats that suit them. For example, questions that make extensive use of diagrams and graphs are presented to visually-inclined students. The test generation unit also customizes question formats according to students' learning styles. For example, questions are presented to auditory-inclined students via audio, and answers are also accepted via audio. The test generation unit also analyzes students' learning styles and dynamically adjusts question formats based on the results. For example, questions that include experiments and simulations are presented to experience-oriented students. This makes it possible to provide question formats that suit students' learning styles.

[0035] The test generation unit generates scenario-based questions linked to past learning data, thereby promoting practical understanding. The test generation unit generates scenario-based questions based on, for example, a student's past learning data. For example, a scenario that applies content learned in the past is set and questions are asked within that scenario. In addition, when generating scenario-based questions, the test generation unit links the past learning data. For example, a scenario that includes areas that the student has previously struggled with is set to promote practical understanding. In addition, the test generation unit customizes scenario-based questions based on the student's learning history. For example, a scenario that reflects past test results and homework grades is set and questions are asked. In this way, scenario-based questions that promote practical understanding can be provided.

[0036] The test generation unit can generate a cross-curriculum test that combines questions from different grades and subjects. The test generation unit generates, for example, a cross-curriculum test that combines questions from different grades and subjects. For example, it combines mathematics and science questions to assess overall understanding. The test generation unit also dynamically combines questions from different grades and subjects according to the student's learning progress. For example, it increases the difficulty of questions in subjects the student is good at, and starts with the basics of questions in subjects the student is weak at. The test generation unit also takes into account the student's interests and concerns when generating the cross-curriculum test. For example, it combines questions related to a favorite subject. This makes it possible to provide a cross-curriculum test that combines questions from different grades and subjects.

[0037] The test generation unit can work in conjunction with other educational resources to generate related questions. For example, the generation AI of the test generation unit works in conjunction with online courses and teaching materials to generate related questions. For example, it may ask questions based on the content of a specific online course. The test generation unit also works in conjunction with other educational resources to customize the content of the questions. For example, it may generate questions that match the content of the teaching materials being used. The test generation unit also uses the generation AI to analyze data from educational resources and dynamically generate related questions. For example, it may ask questions that reflect the content of the latest teaching materials or courses. This makes it possible to provide related questions in conjunction with other educational resources.

[0038] The test generation unit can analyze students' answer patterns in real time and provide instant feedback. For example, when a student takes a test, the generation AI in the test generation unit analyzes the answer patterns in real time and provides instant feedback. For example, feedback is provided based on whether the answer was correct or the time it took to answer. The test generation unit also analyzes the student's answer patterns and provides instant explanations for questions that the student got wrong. For example, it displays the reason for the error and the correct answer method in real time. The test generation unit also dynamically adjusts the difficulty of the next question based on the student's answer patterns and provides instant feedback. For example, it increases the difficulty if the student answers correctly in succession, and decreases the difficulty if the student answers incorrectly in succession. This makes it possible to analyze students' answer patterns in real time and provide instant feedback.

[0039] The test generation unit can dynamically adjust the difficulty of the next question based on the student's answer history. The test generation unit, for example, analyzes the student's answer history and dynamically adjusts the difficulty of the next question. For example, the difficulty level is increased if the student answers correctly repeatedly, and decreased if the student answers incorrectly repeatedly. The test generation unit also presents questions based on the student's answer history according to the student's individual learning needs. For example, more questions in areas the student is weak at and fewer questions in areas the student is strong at. The test generation unit also analyzes the student's answer history in real time and builds a system that dynamically adjusts the difficulty of the next question. For example, the difficulty level is adjusted based on the answer time and the percentage of correct answers. This makes it possible to dynamically adjust the difficulty of the next question based on the student's answer history.

[0040] The test generation unit can accept students' answers via voice input and analyze them using voice recognition technology. For example, in the test generation unit, students input answers via voice, and the generation AI analyzes them using voice recognition technology. For example, the test generation unit accepts answers via voice, converts them into text, and analyzes them. The test generation unit also uses voice recognition technology to analyze students' pronunciation and intonation and determine whether their answers are correct. For example, it evaluates the accuracy of pronunciation in a foreign language test. The test generation unit also analyzes students' voice input in real time and provides instant feedback. For example, it accepts answers via voice and displays whether they are correct in real time. This allows students' answers to be accepted via voice input and analyzed using voice recognition technology.

[0041] The test generation unit can visually display the student's answers and provide visual feedback. The test generation unit, for example, visually displays the student's answers and provides visual feedback. For example, correct answers are displayed in green and incorrect answers are displayed in red. The test generation unit also visually displays the student's answers in graphs or charts to evaluate the student's level of understanding. For example, the correct answer rate and answer time are displayed in graphs to provide visual feedback. The test generation unit also provides visual explanations based on the student's answers. For example, explanations using diagrams or illustrations are displayed for questions that were answered incorrectly. In this way, the student's answers can be visually displayed and visual feedback can be provided.

[0042] The analysis unit can set long-term and short-term learning goals in a balanced manner based on the student's learning history. The analysis unit, for example, analyzes the student's learning history and sets long-term and short-term learning goals in a balanced manner. For example, it sets an annual learning plan and weekly learning goals. The analysis unit also sets achievable long-term and short-term learning goals based on the student's learning history. For example, it sets goals taking into consideration past grades and progress. The analysis unit also analyzes the student's learning history in real time and dynamically adjusts the long-term and short-term learning goals. For example, it reviews goals according to progress. This makes it possible to set long-term and short-term learning goals in a balanced manner.

[0043] The analysis unit can propose collaborative learning plans with other students and promote collaborative learning. For example, the generation AI in the analysis unit proposes collaborative learning plans with other students and promotes collaborative learning. For example, it matches students with the same goals and proposes a collaborative learning plan. The analysis unit also identifies areas where collaborative learning is effective based on the student's learning data and proposes a collaborative learning plan. For example, it proposes a plan that includes group discussions and collaborative projects. The analysis unit also allows the generation AI to analyze the student's learning progress with other students in real time and dynamically adjust the collaborative learning plan. For example, it adjusts the content and schedule of the collaborative learning according to the progress. This makes it possible to propose collaborative learning plans with other students and promote collaborative learning.

[0044] The analysis unit can share students' learning progress with parents and teachers, thereby strengthening the support system. For example, the generation AI can share students' learning progress with parents and teachers, thereby strengthening the support system. For example, the generation AI can send learning reports regularly, allowing parents and teachers to understand the progress. The analysis unit can also share students' learning progress with parents and teachers in real time, thereby strengthening the support system. For example, the progress can be shared using an online platform and feedback can be received. The analysis unit can also have the generation AI analyze students' learning progress and suggest specific support methods to parents and teachers. For example, it can suggest learning support at home or additional learning materials. This allows students' learning progress to be shared with parents and teachers, thereby strengthening the support system.

[0045] The analysis unit periodically reanalyzes the student's learning data and can provide support tailored to the student's latest learning needs. For example, the generation AI periodically reanalyzes the student's learning data and provides support tailored to the student's latest learning needs. For example, the learning plan is revised based on monthly test results. The analysis unit also analyzes the student's learning data in real time and provides support tailored to the student's latest learning needs. For example, new teaching materials and resources are suggested based on progress. The analysis unit also periodically reanalyzes the student's learning data and adjusts the support content according to changes in learning needs. For example, if weak areas are improved, new assignments are set. This allows the generation AI to periodically reanalyze the student's learning data and provide support tailored to the student's latest learning needs.

[0046] The analysis unit can introduce a reward system that visualizes students' learning progress and makes them feel a sense of accomplishment. For example, the analysis unit uses the generation AI to visualize students' learning progress and introduce a reward system that makes them feel a sense of accomplishment. For example, badges or points are awarded when learning goals are achieved. The analysis unit also visualizes students' learning progress in graphs and charts to make them feel a sense of accomplishment. For example, the analysis unit visually displays study time and correct answer rate so that progress can be checked. The analysis unit also uses the generation AI to analyze students' learning progress in real time and dynamically adjust the reward system that makes them feel a sense of accomplishment. For example, the analysis unit adjusts the content and timing of rewards according to progress. This makes it possible to introduce a reward system that visualizes students' learning progress and makes them feel a sense of accomplishment.

[0047] The analysis unit can link student learning data with other educational platforms to provide integrated learning support. For example, the generation AI in the analysis unit links with other educational platforms to integrate and analyze student learning data. For example, it can integrate data from online courses and teaching materials to provide comprehensive learning support. The analysis unit also links with other educational platforms to share student learning data and provide integrated learning support. For example, it can create learning plans based on data from different platforms. The analysis unit also allows the generation AI to obtain data from other educational platforms in real time to provide integrated learning support. For example, it can suggest new teaching materials and resources. This allows student learning data to be linked with other educational platforms to provide integrated learning support.

[0048] The analysis unit can suggest the optimal timing for individual or group instruction based on the student's learning data. For example, the generation AI in the analysis unit analyzes the student's learning data and suggests the optimal timing for individual or group instruction. For example, it suggests individual instruction for students whose learning progress is lagging. The analysis unit also evaluates the effectiveness of individual or group instruction based on the student's learning data and suggests the optimal timing. For example, it suggests group instruction if the student's level of understanding in a particular area is low. The analysis unit also uses the generation AI to analyze the student's learning data in real time and dynamically adjust the timing of individual or group instruction. For example, it adjusts the content and timing of instruction according to the student's progress. This makes it possible to suggest the optimal timing for individual or group instruction based on the student's learning data.

[0049] The system according to the embodiment is not limited to the above-described example, and various modifications are possible, for example, as follows.

[0050] The learning data collection unit can collect behavioral data from students' daily lives and integrate it with their learning data for analysis. For example, a smartwatch or fitness tracker can be used to record sleep time and exercise volume, and the impact of this on learning performance can be evaluated. The learning data collection unit can also record dietary content and analyze the impact of nutritional balance on learning performance. For example, meal timing and content can be recorded using an app, and the generation AI can use that data to evaluate learning effectiveness. The learning data collection unit can also monitor students' stress levels and analyze them in association with their learning data. For example, a stress measurement device can be used to record daily stress levels, and the impact of this on learning performance can be evaluated. This allows for a comprehensive evaluation of the factors that affect learning performance.

[0051] When analyzing a student's learning data, the analysis unit can use comparative data with other students to evaluate the student's relative learning progress and propose individualized learning strategies. For example, the analysis unit compares the student's learning data with that of other students to evaluate the student's relative learning progress. For example, it identifies in which areas the student is lagging behind compared to students in the same grade or class. The analysis unit also proposes individualized learning strategies based on the learning data of other students. For example, it refers to success stories of students with similar learning patterns to propose effective learning methods. The analysis unit also shares the student's learning data on the cloud and obtains comparative data with other students in real time. For example, it uses an online platform to create a learning plan while comparing the student's progress with that of other students. This makes it possible to evaluate the student's relative learning progress and propose individualized learning strategies.

[0052] The learning data collection unit can use speech recognition technology to automatically convert comments or questions made during class into text and use it for analysis. For example, student comments during class can be converted into text using speech recognition technology and collected as learning data. For example, the content of the comments can be analyzed to identify the level of understanding and topics of interest. The learning data collection unit can also convert questions asked by students during class into text using speech recognition technology and use it for analysis. For example, based on the frequency and content of questions, it can identify areas of weakness and topics of interest. The learning data collection unit can also convert discussions made during class into text using speech recognition technology and collect it as learning data. For example, it can analyze the content of the discussion to evaluate the level of understanding and communication ability. This allows the comments and questions made during class to be used for analysis.

[0053] The test generation unit can generate question formats that suit students' learning styles. For example, it can understand students' learning styles in advance through questionnaires and tests and generate question formats that suit them. For example, it can present questions that make extensive use of diagrams and graphs to visually-oriented students. The test generation unit also customizes question formats according to students' learning styles. For example, it presents questions to auditory-oriented students via audio and accepts answers via audio as well. The test generation unit also analyzes students' learning styles and dynamically adjusts question formats based on that analysis. For example, it presents questions that include experiments and simulations to experiential-oriented students. This makes it possible to provide question formats that suit students' learning styles.

[0054] The test generation unit generates scenario-based questions linked to past learning data, thereby promoting practical understanding. For example, scenario-based questions are generated based on a student's past learning data. For example, a scenario that applies content learned in the past is set and questions are posed within that setting. In addition, when generating scenario-based questions, the test generation unit links the past learning data. For example, a scenario that includes areas that the student has previously struggled with is set to promote practical understanding. In addition, the test generation unit customizes scenario-based questions based on the student's learning history. For example, a scenario that reflects past test results and homework grades is set and questions are posed. In this way, scenario-based questions that promote practical understanding can be provided.

[0055] The test generation unit can generate cross-curriculum tests that combine questions from different grades and subjects. For example, a cross-curriculum test that combines questions from different grades and subjects may be generated. For example, mathematics and science questions may be combined to assess overall understanding. The test generation unit also dynamically combines questions from different grades and subjects according to the student's learning progress. For example, questions on subjects the student is good at may be presented with increased difficulty, and questions on weaker subjects may be presented starting from the basics. The test generation unit also takes into account the student's interests and concerns when generating cross-curriculum tests. For example, questions related to a student's favorite subject may be presented as a combination. This makes it possible to provide a cross-curriculum test that combines questions from different grades and subjects.

[0056] The processing flow of the first embodiment will be briefly explained below.

[0057] Step 1: The learning data collection unit collects students' learning data. For example, it collects past test results, homework grades, and comments and questions made during class. This data is collected from databases, collected from data entered by teachers, or converted into text using voice recognition technology. Step 2: The analysis unit analyzes the learning data collected by the learning data collection unit. For example, it analyzes the correct answer rate and answer time of problems that the student has previously solved, and identifies which areas and topics the student has strengths and weaknesses in. Using statistical analysis and machine learning algorithms, it identifies strong and weak areas based on the correct answer rate, and evaluates the student's response to the difficulty of the problems based on the answer time. Step 3: The test generation unit generates test questions based on the results of the analysis by the analysis unit. For example, in a mathematics test, more questions will be asked in areas in which the student is weak and fewer questions in areas in which the student is strong. In addition, questions are automatically generated using a generation AI to adjust the difficulty of the questions according to the student's level of understanding. The generated tests are customized according to the student's learning needs, providing effective learning support.

[0058] (Example 2) The test generation system according to the embodiment of the present invention is a system in which a generation AI creates individually optimized tests according to the learning situation and level of understanding of each student, thereby enabling the test generation system to provide effective tests that meet the learning needs of each individual student.

[0059] The test generation system according to the embodiment includes a learning data collection unit, an analysis unit, and a test generation unit. The learning data collection unit collects learning data from students. For example, the learning data collection unit collects past test results. The learning data collection unit can also collect homework grades. The learning data collection unit can also collect comments and questions made during class. For example, the learning data collection unit obtains test results from a database and provides them to the analysis unit. Homework grades are collected as data entered by teachers and provided to the analysis unit. Comments and questions made during class are converted into text using voice recognition technology and provided to the analysis unit. The analysis unit analyzes the learning data collected by the learning data collection unit. For example, the analysis unit analyzes the correct answer rate for questions that students have previously answered. The analysis unit can also analyze the answer time. The analysis unit can also identify areas or topics in which students have strengths and weaknesses. For example, the analysis unit identifies students' strong and weak areas based on the correct answer rate. The analysis unit evaluates the student's response to the difficulty of the questions based on the answer time. Statistical analysis and machine learning algorithms are used to identify strengths and weaknesses. The test generation unit generates test questions based on the results of the analysis by the analysis unit. For example, in a mathematics test, the test generation unit may provide more questions in areas in which the student is weak. The test generation unit may also provide fewer questions in areas in which the student is strong. The test generation unit may also adjust the difficulty of the questions according to the student's level of understanding. For example, the test generation unit automatically generates questions using a generation AI. The generation AI generates questions based on instructions such as the purpose of the test and the target grade and subject. The difficulty of the questions is dynamically adjusted based on the analysis results. This allows the test generation system according to the embodiment to provide an optimized test for each student. For example, the generated tests are customized according to the student's learning needs, providing effective learning support.

[0060] The learning data collection unit can collect behavioral data from students' daily lives and integrate it with the learning data for analysis. The learning data collection unit, for example, collects behavioral data from students' daily lives and integrates it with the learning data for analysis. For example, a smartwatch or fitness tracker can be used to record sleep time and exercise volume, and the impact of this on learning performance can be evaluated. The learning data collection unit can also record dietary content and analyze the impact of nutritional balance on learning performance. For example, meal timing and content can be recorded using an app, and the generation AI can evaluate learning effectiveness based on that data. The learning data collection unit can also monitor students' stress levels and analyze them in association with the learning data. For example, a stress measurement device can be used to record daily stress levels, and the impact of this on learning performance can be evaluated. This allows for a comprehensive evaluation of factors affecting learning performance.

[0061] When analyzing the student's learning data, the analysis unit can use an emotion estimation function to evaluate the student's emotional state during learning and analyze the impact of emotional fluctuations on learning effectiveness. The analysis unit, for example, captures the student's facial expression while studying with a camera and evaluates the emotional state using the emotion estimation function. For example, it analyzes smiling faces and facial expressions of concentration and evaluates their impact on learning effectiveness. The analysis unit also records the student's voice and evaluates the emotional state using voice analysis technology. For example, it analyzes changes in tone of voice and speaking style and evaluates the impact of emotional fluctuations on learning effectiveness. The analysis unit also measures the student's heart rate and electrodermal response and evaluates the emotional state using the emotion estimation function. For example, it analyzes changes in heart rate and skin electrical resistance and evaluates their impact on learning effectiveness. This makes it possible to evaluate the impact of the emotional state on learning effectiveness.

[0062] When analyzing a student's learning data, the analysis unit can use comparative data with other students to evaluate the student's relative learning progress and propose an individualized learning strategy. For example, the analysis unit compares the student's learning data with that of other students to evaluate the student's relative learning progress. For example, it identifies in which areas the student is lagging behind compared to students in the same grade or class. The analysis unit also proposes an individualized learning strategy based on the learning data of other students. For example, it proposes an effective learning method by referring to success stories of students with similar learning patterns. The analysis unit also shares the student's learning data on the cloud and obtains comparative data with other students in real time. For example, it uses an online platform to create a learning plan while comparing the student's progress with that of other students. This makes it possible to evaluate the student's relative learning progress and propose an individualized learning strategy.

[0063] The learning data collection unit can automatically convert comments or questions made during class into text using speech recognition technology and use it for analysis. For example, the learning data collection unit converts comments made by students during class into text using speech recognition technology and collects it as learning data. For example, the content of the comments can be analyzed to identify the level of understanding and topics of interest. The learning data collection unit also converts questions asked by students during class into text using speech recognition technology and uses it for analysis. For example, based on the frequency and content of questions, it can identify areas of weakness and topics of interest. The learning data collection unit also converts discussions made during class into text using speech recognition technology and collects it as learning data. For example, it can analyze the content of the discussion to evaluate the level of understanding and communication ability. This allows the comments and questions made during class to be used for analysis.

[0064] The learning data collection unit can analyze students' facial expressions and postures using visual recognition technology to evaluate their levels of concentration and understanding. For example, the learning data collection unit photographs students' facial expressions during class with a camera and evaluates their levels of concentration using visual recognition technology. For example, it analyzes eye movements and facial direction to determine whether they are concentrating. The learning data collection unit also photographs students' posture with a camera and evaluates their levels of understanding using visual recognition technology. For example, it analyzes their leaning posture and hand movements to determine whether they are understanding. The learning data collection unit also simultaneously analyzes students' facial expressions and postures during class to comprehensively evaluate their levels of concentration and understanding. For example, it analyzes changes in facial expressions and posture to evaluate the learning effect. This makes it possible to evaluate students' levels of concentration and understanding.

[0065] The learning data collection unit uses the emotion estimation function to monitor in real time the stress and motivation fluctuations felt by students while they are studying, and can provide an appropriate learning environment. For example, the learning data collection unit captures the facial expressions of students while they are studying with a camera and uses the emotion estimation function to monitor the stress and motivation fluctuations in real time. For example, it suggests taking a break to relax if stress increases. The learning data collection unit also records the students' voices and uses voice analysis technology to monitor the stress and motivation fluctuations in real time. For example, it analyzes changes in tone of voice and speaking style to provide an appropriate learning environment. The learning data collection unit also measures the students' heart rate and electrodermal response and uses the emotion estimation function to monitor the stress and motivation fluctuations in real time. For example, it analyzes changes in heart rate and skin electrical resistance to provide an appropriate learning environment. In this way, the learning effectiveness is improved by monitoring the stress and motivation fluctuations of students in real time and providing an appropriate learning environment.

[0066] The test generation unit can generate question formats that suit students' learning styles. For example, the test generation unit grasps students' learning styles in advance through questionnaires and tests, and generates question formats that suit them. For example, questions that make extensive use of diagrams and graphs are presented to visually-inclined students. The test generation unit also customizes question formats according to students' learning styles. For example, questions are presented to auditory-inclined students via audio, and answers are also accepted via audio. The test generation unit also analyzes students' learning styles and dynamically adjusts question formats based on the results. For example, questions that include experiments and simulations are presented to experience-oriented students. This makes it possible to provide question formats that suit students' learning styles.

[0067] The test generation unit can use the emotion estimation function to generate questions including topics that students are likely to be interested in. For example, the test generation unit analyzes the student's past learning data to identify topics that students are likely to be interested in. For example, questions related to favorite subjects or themes that interest the student are posed. The test generation unit also uses the emotion estimation function to identify topics that students are likely to be interested in in real time and generate questions based on that. For example, it analyzes facial expressions and voices while studying to pose questions that include topics of interest. The test generation unit also uses the emotion estimation function to customize the content of questions to attract the student's interest. For example, it poses questions related to a favorite character or hobby. This makes it possible to provide questions that include topics that students are likely to be interested in.

[0068] The test generation unit generates scenario-based questions linked to past learning data, thereby promoting practical understanding. The test generation unit generates scenario-based questions based on, for example, a student's past learning data. For example, a scenario that applies content learned in the past is set and questions are asked within that scenario. In addition, when generating scenario-based questions, the test generation unit links the past learning data. For example, a scenario that includes areas that the student has previously struggled with is set to promote practical understanding. In addition, the test generation unit customizes scenario-based questions based on the student's learning history. For example, a scenario that reflects past test results and homework grades is set and questions are asked. In this way, scenario-based questions that promote practical understanding can be provided.

[0069] The test generation unit can generate a cross-curriculum test that combines questions from different grades and subjects. The test generation unit generates, for example, a cross-curriculum test that combines questions from different grades and subjects. For example, it combines mathematics and science questions to assess overall understanding. The test generation unit also dynamically combines questions from different grades and subjects according to the student's learning progress. For example, it increases the difficulty of questions in subjects the student is good at, and starts with the basics of questions in subjects the student is weak at. The test generation unit also takes into account the student's interests and concerns when generating the cross-curriculum test. For example, it combines questions related to a favorite subject. This makes it possible to provide a cross-curriculum test that combines questions from different grades and subjects.

[0070] The test generation unit can work in conjunction with other educational resources to generate related questions. For example, the generation AI of the test generation unit works in conjunction with online courses and teaching materials to generate related questions. For example, it may ask questions based on the content of a specific online course. The test generation unit also works in conjunction with other educational resources to customize the content of the questions. For example, it may generate questions that match the content of the teaching materials being used. The test generation unit also uses the generation AI to analyze data from educational resources and dynamically generate related questions. For example, it may ask questions that reflect the content of the latest teaching materials or courses. This makes it possible to provide related questions in conjunction with other educational resources.

[0071] The test generation unit can use the emotion estimation function to generate a test that includes relaxation questions to reduce the pressure students feel during the test. For example, the test generation unit uses the emotion estimation function to monitor the pressure students feel during the test in real time. For example, it presents relaxation questions when stress levels increase. The test generation unit also inserts relaxation questions into the middle of the test to relieve students' tension. For example, it presents questions that include simple puzzles or relaxing illustrations. The test generation unit also analyzes the student's emotional state and customizes questions to reduce pressure. For example, it presents relaxation questions related to a student's favorite topic or hobby. This makes it possible to provide relaxation questions to reduce the pressure students feel during the test.

[0072] The test generation unit can analyze students' answer patterns in real time and provide instant feedback. For example, when a student takes a test, the generation AI in the test generation unit analyzes the answer patterns in real time and provides instant feedback. For example, feedback is provided based on whether the answer was correct or the time it took to answer. The test generation unit also analyzes the student's answer patterns and provides instant explanations for questions that the student got wrong. For example, it displays the reason for the error and the correct answer method in real time. The test generation unit also dynamically adjusts the difficulty of the next question based on the student's answer patterns and provides instant feedback. For example, it increases the difficulty if the student answers correctly in succession, and decreases the difficulty if the student answers incorrectly in succession. This makes it possible to analyze students' answer patterns in real time and provide instant feedback.

[0073] The test generation unit can monitor the emotional state of students using the emotion estimation function and suggest breaks at appropriate times. For example, the test generation unit captures students' facial expressions with a camera during a test and monitors their emotional state using the emotion estimation function. For example, it suggests taking a break if stress increases. The test generation unit also records the students' voices and monitors their emotional state using voice analysis technology. For example, it analyzes changes in tone of voice and speaking style and suggests taking a break at appropriate times. The test generation unit also measures the students' heart rate and electrodermal response and monitors their emotional state using the emotion estimation function. For example, it analyzes fluctuations in heart rate and changes in skin electrical resistance and suggests taking a break at appropriate times. In this way, it is possible to monitor the students' emotional state and suggest taking a break at appropriate times.

[0074] The test generation unit can dynamically adjust the difficulty of the next question based on the student's answer history. The test generation unit, for example, analyzes the student's answer history and dynamically adjusts the difficulty of the next question. For example, the difficulty level is increased if the student answers correctly repeatedly, and decreased if the student answers incorrectly repeatedly. The test generation unit also presents questions based on the student's answer history according to the student's individual learning needs. For example, more questions in areas the student is weak at and fewer questions in areas the student is strong at. The test generation unit also analyzes the student's answer history in real time and builds a system that dynamically adjusts the difficulty of the next question. For example, the difficulty level is adjusted based on the answer time and the percentage of correct answers. This makes it possible to dynamically adjust the difficulty of the next question based on the student's answer history.

[0075] The test generation unit can accept students' answers via voice input and analyze them using voice recognition technology. For example, in the test generation unit, students input answers via voice, and the generation AI analyzes them using voice recognition technology. For example, the test generation unit accepts answers via voice, converts them into text, and analyzes them. The test generation unit also uses voice recognition technology to analyze students' pronunciation and intonation and determine whether their answers are correct. For example, it evaluates the accuracy of pronunciation in a foreign language test. The test generation unit also analyzes students' voice input in real time and provides instant feedback. For example, it accepts answers via voice and displays whether they are correct in real time. This allows students' answers to be accepted via voice input and analyzed using voice recognition technology.

[0076] The test generation unit can visually display the student's answers and provide visual feedback. The test generation unit, for example, visually displays the student's answers and provides visual feedback. For example, correct answers are displayed in green and incorrect answers are displayed in red. The test generation unit also visually displays the student's answers in graphs or charts to evaluate the student's level of understanding. For example, the correct answer rate and answer time are displayed in graphs to provide visual feedback. The test generation unit also provides visual explanations based on the student's answers. For example, explanations using diagrams or illustrations are displayed for questions that were answered incorrectly. In this way, the student's answers can be visually displayed and visual feedback can be provided.

[0077] The test generation unit can use the emotion estimation function to provide relaxation messages to reduce anxiety and tension felt by students during the test. For example, the test generation unit captures students' facial expressions with a camera during the test and uses the emotion estimation function to monitor anxiety and tension. For example, if anxiety increases, a relaxation message is displayed. The test generation unit also records the students' voices and uses voice analysis technology to monitor anxiety and tension. For example, it analyzes changes in tone of voice and speaking style to provide a relaxation message. The test generation unit also measures the students' heart rate and electrodermal response and uses the emotion estimation function to monitor anxiety and tension. For example, it analyzes fluctuations in heart rate and changes in skin electrical resistance to provide a relaxation message. This makes it possible to provide relaxation messages to reduce anxiety and tension felt by students during the test.

[0078] The analysis unit can set long-term and short-term learning goals in a balanced manner based on the student's learning history. The analysis unit, for example, analyzes the student's learning history and sets long-term and short-term learning goals in a balanced manner. For example, it sets an annual learning plan and weekly learning goals. The analysis unit also sets achievable long-term and short-term learning goals based on the student's learning history. For example, it sets goals taking into consideration past grades and progress. The analysis unit also analyzes the student's learning history in real time and dynamically adjusts the long-term and short-term learning goals. For example, it reviews goals according to progress. This makes it possible to set long-term and short-term learning goals in a balanced manner.

[0079] The analysis unit can propose collaborative learning plans with other students and promote collaborative learning. For example, the generation AI in the analysis unit proposes collaborative learning plans with other students and promotes collaborative learning. For example, it matches students with the same goals and proposes a collaborative learning plan. The analysis unit also identifies areas where collaborative learning is effective based on the student's learning data and proposes a collaborative learning plan. For example, it proposes a plan that includes group discussions and collaborative projects. The analysis unit also allows the generation AI to analyze the student's learning progress with other students in real time and dynamically adjust the collaborative learning plan. For example, it adjusts the content and schedule of the collaborative learning according to the progress. This makes it possible to propose collaborative learning plans with other students and promote collaborative learning.

[0080] The analysis unit can share students' learning progress with parents and teachers, thereby strengthening the support system. For example, the generation AI can share students' learning progress with parents and teachers, thereby strengthening the support system. For example, the generation AI can send learning reports regularly, allowing parents and teachers to understand the progress. The analysis unit can also share students' learning progress with parents and teachers in real time, thereby strengthening the support system. For example, the progress can be shared using an online platform and feedback can be received. The analysis unit can also have the generation AI analyze students' learning progress and suggest specific support methods to parents and teachers. For example, it can suggest learning support at home or additional learning materials. This allows students' learning progress to be shared with parents and teachers, thereby strengthening the support system.

[0081] The analysis unit can use the emotion estimation function to suggest relaxation activities to reduce the stress the student feels about their study plan. For example, the analysis unit uses the emotion estimation function to monitor the stress the student feels about their study plan in real time and suggest relaxation activities. For example, it can suggest taking a break or exercising to relax when stress increases. The analysis unit also analyzes the student's emotional state and suggests specific relaxation activities to reduce stress. For example, it can suggest meditation or deep breathing exercises. The analysis unit also analyzes the student's stress level in real time and dynamically adjusts the relaxation activities. For example, it can incorporate time for relaxation into the study plan. This makes it possible to suggest relaxation activities to reduce the stress the student feels about their study plan.

[0082] The analysis unit periodically reanalyzes the student's learning data and can provide support tailored to the student's latest learning needs. For example, the generation AI periodically reanalyzes the student's learning data and provides support tailored to the student's latest learning needs. For example, the learning plan is revised based on monthly test results. The analysis unit also analyzes the student's learning data in real time and provides support tailored to the student's latest learning needs. For example, new teaching materials and resources are suggested based on progress. The analysis unit also periodically reanalyzes the student's learning data and adjusts the support content according to changes in learning needs. For example, if weak areas are improved, new assignments are set. This allows the generation AI to periodically reanalyze the student's learning data and provide support tailored to the student's latest learning needs.

[0083] The analysis unit can use the emotion estimation function to provide motivational messages to maintain students' motivation to learn. For example, the analysis unit uses the emotion estimation function to monitor students' motivation to learn in real time and provide motivational messages. For example, it sends an encouraging message when students' motivation to learn decreases. The analysis unit also analyzes students' emotional states and provides specific motivational messages to maintain students' motivation to learn. For example, it introduces messages that give students a sense of accomplishment or success stories. The analysis unit also dynamically adjusts motivational messages to maintain students' motivation to learn using the emotion estimation function. For example, it sets challenging goals when students' motivation to learn increases. This makes it possible to provide motivational messages to maintain students' motivation to learn.

[0084] The analysis unit can introduce a reward system that visualizes students' learning progress and makes them feel a sense of accomplishment. For example, the analysis unit uses the generation AI to visualize students' learning progress and introduce a reward system that makes them feel a sense of accomplishment. For example, badges or points are awarded when learning goals are achieved. The analysis unit also visualizes students' learning progress in graphs and charts to make them feel a sense of accomplishment. For example, the analysis unit visually displays study time and correct answer rate so that progress can be checked. The analysis unit also uses the generation AI to analyze students' learning progress in real time and dynamically adjust the reward system that makes them feel a sense of accomplishment. For example, the analysis unit adjusts the content and timing of rewards according to progress. This makes it possible to introduce a reward system that visualizes students' learning progress and makes them feel a sense of accomplishment.

[0085] The analysis unit can link student learning data with other educational platforms to provide integrated learning support. For example, the generation AI in the analysis unit links with other educational platforms to integrate and analyze student learning data. For example, it can integrate data from online courses and teaching materials to provide comprehensive learning support. The analysis unit also links with other educational platforms to share student learning data and provide integrated learning support. For example, it can create learning plans based on data from different platforms. The analysis unit also allows the generation AI to obtain data from other educational platforms in real time to provide integrated learning support. For example, it can suggest new teaching materials and resources. This allows student learning data to be linked with other educational platforms to provide integrated learning support.

[0086] The analysis unit can suggest the optimal timing for individual or group instruction based on the student's learning data. For example, the generation AI in the analysis unit analyzes the student's learning data and suggests the optimal timing for individual or group instruction. For example, it suggests individual instruction for students whose learning progress is lagging. The analysis unit also evaluates the effectiveness of individual or group instruction based on the student's learning data and suggests the optimal timing. For example, it suggests group instruction if the student's level of understanding in a particular area is low. The analysis unit also uses the generation AI to analyze the student's learning data in real time and dynamically adjust the timing of individual or group instruction. For example, it adjusts the content and timing of instruction according to the student's progress. This makes it possible to suggest the optimal timing for individual or group instruction based on the student's learning data.

[0087] The analysis unit can use the emotion estimation function to suggest relaxation activities to reduce the fatigue and stress that students feel from studying. For example, the analysis unit uses the emotion estimation function to monitor the fatigue and stress that students feel from studying in real time and suggest relaxation activities. For example, it suggests taking a break or exercising when fatigue increases. The analysis unit also analyzes the student's emotional state and suggests specific relaxation activities to reduce fatigue and stress. For example, it suggests meditation or deep breathing exercises. The analysis unit also analyzes the student's fatigue and stress levels in real time and dynamically adjusts relaxation activities. For example, it may incorporate time for relaxation into a study plan. This makes it possible to suggest relaxation activities to reduce the fatigue and stress that students feel from studying.

[0088] The system according to the embodiment is not limited to the above-described example, and various modifications are possible, for example, as follows.

[0089] When analyzing the student's learning data, the analysis unit can use an emotion estimation function to evaluate the student's emotional state during learning and analyze the impact of emotional fluctuations on learning effectiveness. For example, the analysis unit can capture the student's facial expression while studying with a camera and evaluate the emotional state using the emotion estimation function. For example, it can analyze smiling or concentrated facial expressions and evaluate the impact it has on learning effectiveness. The analysis unit can also record the student's voice and evaluate the emotional state using voice analysis technology. For example, it can analyze changes in tone of voice and speaking style and evaluate the impact of emotional fluctuations on learning effectiveness. The analysis unit can also measure the student's heart rate and electrodermal response and evaluate the emotional state using the emotion estimation function. For example, it can analyze changes in heart rate and skin electrical resistance and evaluate the impact it has on learning effectiveness. This makes it possible to evaluate the impact of the emotional state on learning effectiveness.

[0090] The learning data collection unit can collect behavioral data from students' daily lives and integrate it with their learning data for analysis. For example, a smartwatch or fitness tracker can be used to record sleep time and exercise volume, and the impact of this on learning performance can be evaluated. The learning data collection unit can also record dietary content and analyze the impact of nutritional balance on learning performance. For example, meal timing and content can be recorded using an app, and the generation AI can use that data to evaluate learning effectiveness. The learning data collection unit can also monitor students' stress levels and analyze them in association with their learning data. For example, a stress measurement device can be used to record daily stress levels, and the impact of this on learning performance can be evaluated. This allows for a comprehensive evaluation of the factors that affect learning performance.

[0091] When analyzing a student's learning data, the analysis unit can use comparative data with other students to evaluate the student's relative learning progress and propose individualized learning strategies. For example, the analysis unit compares the student's learning data with that of other students to evaluate the student's relative learning progress. For example, it identifies in which areas the student is lagging behind compared to students in the same grade or class. The analysis unit also proposes individualized learning strategies based on the learning data of other students. For example, it refers to success stories of students with similar learning patterns to propose effective learning methods. The analysis unit also shares the student's learning data on the cloud and obtains comparative data with other students in real time. For example, it uses an online platform to create a learning plan while comparing the student's progress with that of other students. This makes it possible to evaluate the student's relative learning progress and propose individualized learning strategies.

[0092] The learning data collection unit can use speech recognition technology to automatically convert comments or questions made during class into text and use it for analysis. For example, student comments during class can be converted into text using speech recognition technology and collected as learning data. For example, the content of the comments can be analyzed to identify the level of understanding and topics of interest. The learning data collection unit can also convert questions asked by students during class into text using speech recognition technology and use it for analysis. For example, based on the frequency and content of questions, it can identify areas of weakness and topics of interest. The learning data collection unit can also convert discussions made during class into text using speech recognition technology and collect it as learning data. For example, it can analyze the content of the discussion to evaluate the level of understanding and communication ability. This allows the comments and questions made during class to be used for analysis.

[0093] The learning data collection unit can use visual recognition technology to analyze students' facial expressions and postures to evaluate their levels of concentration and understanding. For example, students' facial expressions during class can be captured with a camera, and their level of concentration can be evaluated using visual recognition technology. For example, eye movements and facial direction can be analyzed to determine whether they are concentrating. The learning data collection unit can also capture students' posture with a camera, and use visual recognition technology to evaluate their level of understanding. For example, forward leaning posture and hand movements can be analyzed to determine whether they are understanding. The learning data collection unit can also simultaneously analyze students' facial expressions and postures during class, and comprehensively evaluate their levels of concentration and understanding. For example, changes in facial expressions and posture can be analyzed to evaluate the learning effect. This makes it possible to evaluate students' levels of concentration and understanding.

[0094] The learning data collection unit can use the emotion estimation function to monitor in real time the stress and motivation fluctuations that students experience while studying and provide an appropriate learning environment. For example, the unit can capture the student's facial expressions while studying with a camera and use the emotion estimation function to monitor the stress and motivation fluctuations in real time. For example, it can suggest a break to relax if stress increases. The learning data collection unit can also record the student's voice and use voice analysis technology to monitor the stress and motivation fluctuations in real time. For example, it can analyze changes in tone of voice and speaking style to provide an appropriate learning environment. The learning data collection unit can also measure the student's heart rate and electrodermal response and use the emotion estimation function to monitor the stress and motivation fluctuations in real time. For example, it can analyze changes in heart rate and skin electrical resistance to provide an appropriate learning environment. In this way, the learning effectiveness can be improved by monitoring the stress and motivation fluctuations of students in real time and providing an appropriate learning environment.

[0095] The test generation unit can generate question formats that suit students' learning styles. For example, it can understand students' learning styles in advance through questionnaires and tests and generate question formats that suit them. For example, it can present questions that make extensive use of diagrams and graphs to visually-oriented students. The test generation unit also customizes question formats according to students' learning styles. For example, it presents questions to auditory-oriented students via audio and accepts answers via audio as well. The test generation unit also analyzes students' learning styles and dynamically adjusts question formats based on that analysis. For example, it presents questions that include experiments and simulations to experiential-oriented students. This makes it possible to provide question formats that suit students' learning styles.

[0096] The test generation unit can use the emotion estimation function to generate questions that include topics that students are likely to be interested in. For example, it can analyze a student's past learning data to identify topics that students are likely to be interested in. For example, it can set questions related to their favorite subjects or themes of interest. The test generation unit can also use the emotion estimation function to identify topics that students are likely to be interested in in real time and generate questions based on that. For example, it can analyze facial expressions and voices while studying to set questions that include topics of interest. The test generation unit can also use the emotion estimation function to customize the content of questions to attract the student's interest. For example, it can set questions related to their favorite characters or hobbies. This makes it possible to provide questions that include topics that students are likely to be interested in.

[0097] The test generation unit generates scenario-based questions linked to past learning data, thereby promoting practical understanding. For example, scenario-based questions are generated based on a student's past learning data. For example, a scenario that applies content learned in the past is set and questions are posed within that setting. In addition, when generating scenario-based questions, the test generation unit links the past learning data. For example, a scenario that includes areas that the student has previously struggled with is set to promote practical understanding. In addition, the test generation unit customizes scenario-based questions based on the student's learning history. For example, a scenario that reflects past test results and homework grades is set and questions are posed. In this way, scenario-based questions that promote practical understanding can be provided.

[0098] The test generation unit can generate cross-curriculum tests that combine questions from different grades and subjects. For example, a cross-curriculum test that combines questions from different grades and subjects may be generated. For example, mathematics and science questions may be combined to assess overall understanding. The test generation unit also dynamically combines questions from different grades and subjects according to the student's learning progress. For example, questions on subjects the student is good at may be presented with increased difficulty, and questions on weaker subjects may be presented starting from the basics. The test generation unit also takes into account the student's interests and concerns when generating cross-curriculum tests. For example, questions related to a student's favorite subject may be presented as a combination. This makes it possible to provide a cross-curriculum test that combines questions from different grades and subjects.

[0099] The processing flow of the second embodiment will be briefly explained below.

[0100] Step 1: The learning data collection unit collects students' learning data. For example, it collects past test results, homework grades, and comments and questions made during class. This data is collected from databases, collected from data entered by teachers, or converted into text using voice recognition technology. Step 2: The analysis unit analyzes the learning data collected by the learning data collection unit. For example, it analyzes the correct answer rate and answer time of problems that the student has previously solved, and identifies which areas and topics the student has strengths and weaknesses in. Using statistical analysis and machine learning algorithms, it identifies strong and weak areas based on the correct answer rate, and evaluates the student's response to the difficulty of the problems based on the answer time. Step 3: The test generation unit generates test questions based on the results of the analysis by the analysis unit. For example, in a mathematics test, more questions will be asked in areas in which the student is weak and fewer questions in areas in which the student is strong. In addition, questions are automatically generated using a generation AI to adjust the difficulty of the questions according to the student's level of understanding. The generated tests are customized according to the student's learning needs, providing effective learning support.

[0101] 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.

[0102] The data generation model 58 is a so-called generative AI (Artificial Intelligence). An example of the data generation model 58 is ChatGPT (Internet Search<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.

[0103] 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.

[0104] [Second embodiment] FIG. 3 shows an example of the configuration of a data processing system 210 according to the second embodiment.

[0105] 3, the data processing system 210 includes the data processing device 12 and smart glasses 214. An example of the data processing device 12 is a server.

[0106] 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.

[0107] 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.

[0108] 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.

[0109] 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).

[0110] 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.

[0111] 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.

[0112] 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.

[0113] 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 the user's emotion using the emotion identification model 59 and perform identification processing using the user's emotion.

[0114] 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. Note that the smart glasses 214 may have a data generation model and an emotion identification model similar to the data generation model 58 and the emotion identification model 59.

[0115] 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.

[0116] 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.

[0117] The data generation model 58 is a so-called generative AI. An example of the data generation model 58 is a generative AI such as ChatGPT. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 receives a prompt containing an instruction, as well as inference data such as voice data representing speech, text data representing text, and image data representing an image. The data generation model 58 performs inference on the input inference data in accordance with the instruction indicated by the prompt and outputs the inference result in a data format such as voice data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization. The identification processing unit 290 performs the above-mentioned identification processing using the data generation model 58. The data generation model 58 may be a fine-tuned model so as to output an inference result from a prompt that does not include an instruction. In this case, the data generation model 58 can output an inference result from a prompt that does not include an instruction. The data processing device 12 and the like include multiple types of data generation models 58, and the data generation model 58 includes AIs other than the generative AI. The AI ​​other than the generative AI may be, for example, linear regression, logistic regression, decision tree, random forest, support vector machine (SVM), k-means clustering, convolutional neural network (CNN), recurrent neural network (RNN), generative adversarial network (GAN), or naive Bayes, and can perform various processes, but is not limited to these examples. The AI ​​may also be an AI agent. When the processes of each of the above-mentioned parts are performed by AI, the processes may be performed in part or entirely by AI, but are not limited to these examples. The processes performed by AI, including the generative AI, may be replaced with rule-based processes.

[0118] 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.

[0119] [Third embodiment] FIG. 5 shows an example of the configuration of a data processing system 310 according to the third embodiment.

[0120] 5, the data processing system 310 includes the data processing device 12 and a headset type terminal 314. An example of the data processing device 12 is a server.

[0121] 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.

[0122] 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.

[0123] 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.

[0124] 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).

[0125] 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.

[0126] Fig. 6 shows an example of the main functions of the data processing device 12 and the headset type terminal 314. As shown in Fig. 6, in the data processing device 12, a specific process is performed by the processor 28. A specific process program 56 is stored in the storage 32.

[0127] 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.

[0128] 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 the user's emotion using the emotion identification model 59 and perform identification processing using the user's emotion.

[0129] 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 may also have a data generation model and an emotion identification model similar to the data generation model 58 and the emotion identification model 59.

[0130] 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.

[0131] 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.

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

[0133] 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.

[0134] [Fourth embodiment] FIG. 7 shows an example of the configuration of a data processing system 410 according to the fourth embodiment.

[0135] 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.

[0136] 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.

[0137] 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.

[0138] 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.

[0139] 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).

[0140] 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.

[0141] 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.

[0142] 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.

[0143] The processor 28 reads the specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific processing is realized by the processor 28 operating as a specific processing unit 290 in accordance with the specific processing program 56 executed on the RAM 30.

[0144] The storage 32 stores a data generation model 58 and an emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290. The identification processing unit 290 can estimate the user's emotion using the emotion identification model 59 and perform identification processing using the user's emotion.

[0145] In the robot 414, the processor 46 performs the identification process. 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. The robot 414 may have a data generation model and an emotion identification model similar to the data generation model 58 and the emotion identification model 59.

[0146] Note that a device other than the data processing device 12 may have the data generation model 58. For example, a server device may have the data generation model 58. In this case, the data processing device 12 communicates with the server device having the data generation model 58 to obtain a processing result (such as a prediction result) using the data generation model 58. Furthermore, the data processing device 12 may be a server device, or may be a terminal device (for example, a mobile phone, a robot, a home appliance, etc.) owned by a user.

[0147] The specific processing unit 290 transmits the result of the specific processing to the 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.

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

[0149] The data processing system 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.

[0150] 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.

[0151] 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.

[0152] 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.

[0153] 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).

[0154] 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.

[0155] 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."

[0156] 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.

[0157] 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.

[0158] 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.

[0159] 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.

[0160] 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.

[0161] 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.

[0162] 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.

[0163] 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.

[0164] 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.

[0165] 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.

[0166] The above-described description and illustrations are a detailed explanation of the parts related to the technology of the present disclosure and are merely an example of the technology of the present disclosure. For example, the above description of the configuration, functions, actions, and effects is an explanation of an example of the configuration, functions, actions, and effects of the parts related to the technology of the present disclosure. Therefore, it goes without saying that unnecessary parts may be deleted, new elements may be added, or replacements may be made to the above-described description and illustrations within the scope of the gist of the technology of the present disclosure. Furthermore, to avoid confusion and facilitate understanding of the parts related to the technology of the present disclosure, the above-described description and illustrations omit explanations of common technical knowledge that do not require particular explanation to enable the implementation of the technology of the present disclosure.

[0167] 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. [Explanation of symbols]

[0168] 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 learning data collection unit that collects learning data of students; an analysis unit that analyzes the learning data collected by the learning data collection unit; a test generation unit that generates test questions based on the results of the analysis by the analysis unit. A system characterized by:

2. The learning data collection unit Using speech recognition technology, comments or questions made during class are automatically converted into text for analysis.

2. The system of claim 1.

3. The test generator Generate question formats that suit the student's learning style 2. The system of claim 1.

4. The test generator Analyze the student's answer patterns in real time and provide immediate feedback 2. The system of claim 1.

5. The analysis unit When analyzing the learning data of the student, the emotional state during learning is evaluated, and the influence of emotional fluctuations on learning effectiveness is analyzed.

2. The system of claim 1.

Images