System

Abstract

An object of a system according to an embodiment is to appropriately evaluate thinking skills and subjective learning.SOLUTION: A system includes an analysis part, an evaluation part, and an indication part. The analysis unit analyzes a sentence of a student. The evaluation unit evaluates thinking ability based on the sentence analyzed by the analysis unit. The pointing unit points out an error or an improvement point based on a result evaluated by the evaluation 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 properly evaluate thinking ability and independent learning, which cannot be assessed by test scores.

[0005] The system according to the embodiment aims to appropriately evaluate thinking ability and independent learning. [Means for solving the problem]

[0006] The system according to the embodiment includes an analysis unit, an evaluation unit, and a commenting unit. The analysis unit analyzes the student's writing. The evaluation unit evaluates the student's thinking ability based on the writing analyzed by the analysis unit. The commenting unit points out errors and areas for improvement based on the results of the evaluation by the evaluation unit. [Effects of the Invention]

[0007] The system according to the embodiment can appropriately evaluate thinking ability and independent learning. [Brief explanation of the drawings]

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

[0025] The storage 32 stores a data generation model 58 and an emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290. The identification processing unit 290 can estimate a user's emotion using the emotion identification model 59 and perform identification processing using the user's emotion. The emotion estimation function (emotion identification function) using the emotion identification model 59 performs various estimations and predictions regarding the user's emotion, including estimation and prediction of the user's emotion, but is not limited to these examples. Furthermore, the estimation and prediction of emotion also includes, for example, emotion analysis.

[0026] In the smart device 14, the specific processing is performed by the processor 46. The storage 50 stores a specific processing program 60. The specific processing program 60 is used together with the specific processing program 56 by the data processing system 10. The processor 46 reads the specific processing program 60 from the storage 50 and executes the read specific processing program 60 on the RAM 48. The specific processing is realized by the processor 46 operating as the control unit 46A in accordance with the specific processing program 60 executed on the RAM 48. Note that the smart device 14 has a data generation model and an emotion identification model similar to the data generation model 58 and the emotion identification model 59, and can also perform processing similar to that of the specific processing unit 290 using these models.

[0027] Note that a device other than the data processing device 12 may have the data generation model 58. For example, a server device (e.g., a generation server) may have the data generation model 58. In this case, the data processing device 12 obtains a processing result (prediction result, etc.) using the data generation model 58 by communicating with the server device having the data generation model 58. Furthermore, the data processing device 12 may be a server device, or may be a terminal device owned by a user (e.g., a mobile phone, a robot, a home appliance, etc.). Next, an example of processing by the data processing system 10 according to the first embodiment will be described.

[0028] (Example 1) The Evaluate generation AI system according to an embodiment of the present invention is a system for evaluating students' thinking ability and independent learning. In this system, the generation AI analyzes students' writing, qualitatively evaluates their thinking ability, and points out errors and areas for improvement. As a result, the Evaluate generation AI system can improve the quality of education by qualitatively evaluating students' thinking ability and pointing out errors and areas for improvement.

[0029] The evaluation generation AI system according to the embodiment includes an analysis unit, an evaluation unit, and a suggestion unit. The analysis unit analyzes a student's writing. For example, the analysis unit analyzes essays and reports written by the student and evaluates their grammar and syntax. The analysis unit can also perform semantic analysis of the writing and evaluate its logical consistency. The analysis unit can also analyze metaphors and rhetorical devices in the writing and evaluate their frequency of use and effectiveness. The evaluation unit evaluates thinking ability based on the writing analyzed by the analysis unit. For example, the evaluation unit evaluates logical thinking ability and creative thinking ability. The evaluation unit can also evaluate critical thinking ability based on the structure and content of the writing. The evaluation unit can also evaluate the development of arguments and logical consistency in the writing. The suggestion unit points out errors and areas for improvement based on the results of the evaluation by the evaluation unit. For example, the suggestion unit points out grammatical errors and logical errors. The suggestion unit can also point out areas for improvement in expression. The suggestion unit can also suggest specific improvement methods based on the structure and content of the writing. As a result, the Evaluate generation AI system according to the embodiment can qualitatively evaluate students' thinking abilities and point out errors and areas for improvement, thereby improving the quality of education.

[0030] When analyzing a student's writing, the analysis unit can evaluate not only the structure of the text but also the metaphors and rhetorical devices used. For example, when the generative AI analyzes a student's writing, the analysis unit evaluates the frequency and type of metaphors and rhetorical devices used. For example, a text that makes heavy use of metaphors may be evaluated as demonstrating creative thinking. The analysis unit also analyzes the use of rhetorical devices and evaluates how those devices affect the logical structure of the entire text. For example, if repetition and contrast are used effectively, the logical thinking ability may be highly evaluated. The analysis unit also evaluates a student's writing ability and creativity based on the use of metaphors and rhetorical devices. For example, if a student uses original metaphors or new rhetorical devices, the creativity may be highly evaluated. This makes it possible to evaluate thinking ability by taking metaphors and rhetorical devices into account.

[0031] When analyzing a student's writing, the analysis unit compares it with the writing of other students and can evaluate the student's relative thinking ability. For example, when the generation AI analyzes a student's writing, the analysis unit compares it with the writing of other students to evaluate it. For example, it compares multiple writings on the same topic and evaluates the logical consistency and depth. It also evaluates the student's relative thinking ability based on the comparison with the writing of other students. For example, among answers to the same task, the most logical and creative writing may be highly rated. Furthermore, by comparing it with the writing of other students, the generation AI can identify the strengths and weaknesses of each student and perform a relative evaluation. For example, if a student has a unique perspective or new ideas compared to other students, it will be highly rated for their thinking ability. This makes it possible to evaluate a student's relative thinking ability through comparison with other students.

[0032] The analysis unit can also analyze the content of students' oral presentations and discussions and include it in the evaluation of their thinking ability. For example, the analysis unit's generation AI analyzes the content of a student's oral presentation and evaluates its logical structure and expressiveness. For example, it evaluates thinking ability based on the flow of the presentation and the choice of words used. The generation AI also analyzes the content of the discussion and evaluates the consistency and logic of the student's comments. For example, it evaluates based on the connection of comments during the discussion and the quality of counterarguments. The generation AI also analyzes recordings of oral presentations and discussions and evaluates the content of the comments and changes in emotions. For example, it identifies points where emotions change in the comments and evaluates that these changes indicate flexibility of thinking. This makes it possible to evaluate thinking ability while taking into account the content of the oral presentation or discussion.

[0033] The analysis unit can also analyze visual data such as diagrams and graphs created by students and include it in the evaluation of thinking ability. For example, the analysis unit uses a generative AI to analyze diagrams and graphs created by students and evaluate the accuracy of the data and the visual expressiveness of the data. For example, it evaluates thinking ability based on how the data is selected and the structure of the graph. It also evaluates students' logical thinking ability and ability to interpret data through the analysis of visual data. For example, it evaluates what patterns and trends they found in the diagrams and graphs. The generative AI also analyzes the visual data and evaluates how the data is related to written or oral presentations. For example, it evaluates whether the visual data is logically consistent. This makes it possible to evaluate thinking ability by taking visual data into consideration.

[0034] When analyzing student notes, reports, essays, and other writings, the analysis unit can also include grammar and vocabulary frequency in its evaluation. For example, when the generation AI analyzes a student's writing, the analysis unit evaluates grammatical accuracy and vocabulary diversity. For example, it gives a high rating to grammatically correct writing and writing with a rich vocabulary. The analysis unit also evaluates a student's writing ability and expressiveness based on the frequency of grammar and vocabulary. For example, if a student uses complex grammatical structures or specialized vocabulary, it will give that writing a high rating. The generation AI also analyzes the frequency of grammar and vocabulary and evaluates the overall quality of the writing based on that data. For example, it evaluates writing that is grammatically correct and has a rich vocabulary as indicating high thinking ability. This makes it possible to evaluate thinking ability while taking into account the frequency of grammar and vocabulary.

[0035] When analyzing texts such as student notes, reports, and essays, the analysis unit can introduce algorithms that evaluate the coherence and logical flow of text. For example, the generation AI can introduce an algorithm that evaluates the coherence of text and analyze the logical flow of the entire text. For example, it can evaluate whether each paragraph is logically connected. It can also use an algorithm that evaluates logical flow to evaluate the structure and logical consistency of the text. For example, it can evaluate whether the introduction, development, and conclusion are clearly separated. The generation AI can also analyze the coherence and logical flow of text and evaluate the quality of the entire text based on that data. For example, it can evaluate logically consistent text as indicating high thinking ability. This makes it possible to evaluate thinking ability by taking into account the coherence and logical flow of text.

[0036] When analyzing student notes, reports, essays, and other writings, the analysis unit can also include in its evaluation the diversity of themes and topics in the writing. For example, when the generation AI analyzes a student's writing, the analysis unit evaluates the diversity of themes and topics. For example, it may highly evaluate writing that deals with multiple different themes and topics. The analysis unit also evaluates the breadth and depth of a student's thinking based on the diversity of themes and topics. For example, it may evaluate writing that incorporates different perspectives and approaches as exhibiting high thinking ability. The generation AI also analyzes the diversity of themes and topics and evaluates the overall quality of the writing based on that data. For example, it may evaluate writing that deals with a variety of themes and topics as exhibiting creative thinking ability. This makes it possible to evaluate thinking ability while taking the diversity of themes and topics into account.

[0037] The analysis unit can also analyze program code and algorithms written by students and include them in the evaluation of logical thinking ability. For example, the analysis unit uses a generative AI to analyze program code written by students and evaluate its logical structure and efficiency. For example, it evaluates thinking ability based on the accuracy and degree of optimization of the code. It also evaluates students' logical thinking and problem-solving abilities through the analysis of algorithms. For example, it evaluates based on the quality of algorithm design and implementation. The generative AI also analyzes program code and algorithms and evaluates logical thinking ability based on that data. For example, it evaluates based on the consistency of the code and the lack of errors. This makes it possible to evaluate logical thinking ability taking program code and algorithms into account.

[0038] The analysis unit can also analyze presentation materials created by students and include them in the evaluation of thinking ability. For example, the analysis unit uses the generation AI to analyze presentation materials created by students and evaluate their logical structure and visual expressiveness. For example, it evaluates thinking ability based on the structure and design of the slides. It also evaluates students' logical thinking and expressiveness through the analysis of presentation materials. For example, it evaluates what data and graphs are used in the materials. The generation AI also analyzes presentation materials and evaluates thinking ability based on that data. For example, it evaluates based on the consistency and visual effect of the materials. This makes it possible to evaluate thinking ability while taking presentation materials into consideration.

[0039] The analysis unit can evaluate branching points and options when analyzing a student's thought flow. For example, when the generation AI analyzes a student's thought flow, the analysis unit identifies branching points and options and evaluates them. For example, if multiple options are presented in a text, the quality of those options is evaluated. The analysis unit also evaluates the student's logical thinking and problem-solving abilities based on branching points in thought. For example, it evaluates whether the choice at the branching point is logical. The generation AI also analyzes branching points and options in thought and evaluates the thought flow based on that data. For example, if the choice at the branching point introduces a new perspective or idea, it will highly evaluate that thinking ability. This makes it possible to evaluate the thought flow taking branching points and options into account.

[0040] The analysis unit can introduce an algorithm that evaluates the depth and breadth of thought when analyzing a student's flow of thought and logical structure. For example, when the generation AI analyzes a student's flow of thought, the analysis unit introduces an algorithm that evaluates the depth and breadth of thought. For example, it evaluates the logical depth and diverse perspectives in the text. Furthermore, it evaluates the student's logical thinking ability and creativity based on the depth and breadth of thought. For example, it highly evaluates texts with deep insights and broad perspectives. Furthermore, the generation AI analyzes the depth and breadth of thought and evaluates the flow of thought based on that data. For example, it evaluates texts with deep logical analysis and diverse perspectives as indicating high thinking ability. This makes it possible to evaluate the flow of thought taking into account the depth and breadth of thought.

[0041] The analysis unit can also analyze the content of students' group discussions and evaluate the flow of thought and logical structure. For example, the generation AI analyzes the content of students' group discussions and evaluates their logical structure and flow of thought. For example, it evaluates the connections between comments during the discussion and the logical consistency. The analysis of group discussions also evaluates students' collaborative thinking and problem-solving abilities. For example, it evaluates based on the quality of exchange of opinions and cooperation during the discussion. The generation AI also analyzes recordings of group discussions and evaluates the content of comments and changes in emotions. For example, it identifies points where emotions change in comments and evaluates that these changes indicate flexibility of thinking. This makes it possible to evaluate the flow of thought while taking the content of the group discussion into account.

[0042] The analysis unit can also analyze the process of experiments and research conducted by students and evaluate the flow of thought and logical structure. For example, the analysis unit uses the generative AI to analyze the process of experiments and research conducted by students and evaluate its logical structure and flow of thought. For example, it evaluates thinking ability based on the design of the experiment and the method of data analysis. It also evaluates students' logical thinking and problem-solving abilities through the analysis of the experiment and research process. For example, it evaluates how the results of the experiment are interpreted and how conclusions are drawn. The generative AI also analyzes the process of the experiment or research and evaluates the flow of thought based on the data. For example, it evaluates whether the design of the experiment and the method of data analysis are logical. This makes it possible to evaluate the flow of thought taking into account the process of the experiment or research.

[0043] When analyzing notes, the analysis unit can automatically point out not only errors and areas for improvement, but also excellent points. For example, when the generation AI analyzes notes, the analysis unit automatically points out not only errors and areas for improvement, but also excellent points. For example, it highly praises logical structure and creative ideas. Furthermore, by pointing out excellent points, it can improve student motivation. For example, it can specifically point out excellent expressions and unique perspectives in the notes. Furthermore, the generation AI analyzes the excellent points of the notes and provides feedback based on that data. For example, by emphasizing the excellent points, it can boost the student's confidence. In this way, by pointing out excellent points, it can improve student motivation.

[0044] When analyzing notes, the analysis unit can provide customized feedback based on the student's learning style and level of comprehension. For example, the analysis unit uses a generation AI to analyze a student's learning style and level of comprehension and provide customized feedback based on that data. For example, feedback that makes extensive use of diagrams and graphs can be provided to visual learners. Also, by providing feedback based on the student's level of comprehension, individualized instruction can be achieved. For example, detailed explanations can be added to parts where comprehension is low. Also, the generation AI analyzes a student's learning style and level of comprehension and provides feedback based on that data. For example, specific advice can be provided based on learning style. This makes it possible to provide individualized instruction based on learning style and level of comprehension.

[0045] The analysis unit can also analyze data from students' digital notebooks and online learning platforms and provide feedback. For example, the analysis unit uses a generation AI to analyze students' digital notebooks and provide feedback based on that data. For example, it can automatically point out errors and areas for improvement in the digital notebooks. It can also analyze data from online learning platforms to understand students' learning status. For example, it can provide feedback based on activity history and submissions on the platform. It can also analyze data from digital notebooks and online learning platforms and provide feedback based on that data. For example, it can integrate and evaluate the contents of digital notebooks and data on online activities. This makes it possible to provide feedback that takes into account data from digital notebooks and online learning platforms.

[0046] The analysis unit can also analyze records of experiments and surveys conducted by students and provide feedback. For example, the generation AI analyzes records of experiments and surveys conducted by students and provides feedback based on that data. For example, evaluations are made based on the experiment design and data analysis methods. The analysis unit also evaluates students' logical thinking and problem-solving abilities through the analysis of experiment and survey records. For example, it evaluates how the results of the experiment are interpreted and how conclusions are drawn. The generation AI also analyzes experiment and survey records and provides feedback based on that data. For example, it evaluates whether the experiment design and data analysis methods are logical. This makes it possible to provide feedback that takes into account the experiment and survey records.

[0047] The analysis unit can provide specific methods for improvement and reference materials when pointing out errors or areas for improvement. For example, when the generation AI points out errors or areas for improvement, the analysis unit provides specific methods for improvement. For example, it explains the cause of the error and specifically shows how to correct it. In addition, when pointing out areas for improvement, it provides reference materials. For example, it presents links to related literature and websites so that students can research and improve on their own. In addition, when the generation AI points out errors or areas for improvement, it supports students' learning by providing specific methods for improvement and reference materials. For example, it provides step-by-step instructions on how to correct errors. This makes it possible to support students' learning by providing specific methods for improvement and reference materials.

[0048] When pointing out errors or areas for improvement, the analysis unit can provide personalized feedback by referring to the student's past errors and areas for improvement. For example, the analysis unit's generation AI can refer to the student's past errors and areas for improvement and provide personalized feedback based on that data. For example, if the student has made the same error repeatedly in the past, the analysis unit can identify the cause and suggest specific ways to improve. The analysis unit can also provide individualized instruction based on the student's past errors and areas for improvement. For example, it can analyze past data and provide feedback on specific areas or skills. The generation AI can also refer to the student's past errors and areas for improvement and provide feedback based on that data. For example, it can provide specific advice for overcoming past errors. This makes it possible to provide personalized feedback by referring to past errors and areas for improvement.

[0049] The analysis unit can also point out errors and areas for improvement in students' program code and algorithms. For example, the generative AI analyzes students' program code and points out errors and areas for improvement. For example, it identifies errors and inefficient parts of the code and suggests ways to correct them. The analysis unit also evaluates students' logical thinking and problem-solving abilities through algorithm analysis. For example, it evaluates based on the quality of the algorithm design and implementation. The generative AI also analyzes program code and algorithms and points out errors and areas for improvement based on that data. For example, it evaluates based on the consistency of the code and the lack of errors. In this way, by pointing out errors and areas for improvement in program code and algorithms, it can help improve logical thinking skills.

[0050] The analysis unit can also point out errors and areas for improvement in students' presentation materials. For example, the generation AI analyzes students' presentation materials and points out errors and areas for improvement. For example, it identifies problems with the structure and design of slides and suggests ways to correct them. The analysis of presentation materials also evaluates students' logical thinking and expressive abilities. For example, it evaluates what data and graphs are used in the materials. The generation AI also analyzes presentation materials and points out errors and areas for improvement based on that data. For example, it evaluates based on the consistency and visual effect of the materials. This allows it to support the improvement of expressive abilities by pointing out errors and areas for improvement in presentation materials.

[0051] When analyzing a student's learning history, the analysis unit can visualize their learning progress and achievement. For example, the generation AI analyzes the student's learning history and visualizes their learning progress and achievement based on that data. For example, it displays learning progress in graphs and charts. Visualizing learning progress and achievement can also improve student motivation. For example, it can highlight areas with high achievement. The generation AI can also analyze learning progress and achievement and provide feedback based on that data. For example, it can provide specific advice on areas where progress is lagging. In this way, visualizing learning progress and achievement can improve student motivation.

[0052] When analyzing a student's learning history, the analysis unit can visualize their learning progress and achievement. For example, the generation AI analyzes the student's learning history and visualizes their learning progress and achievement based on that data. For example, it displays learning progress in graphs and charts. Visualizing learning progress and achievement can also improve student motivation. For example, it can highlight areas with high achievement. The generation AI can also analyze learning progress and achievement and provide feedback based on that data. For example, it can provide specific advice on areas where progress is lagging. In this way, visualizing learning progress and achievement can improve student motivation.

[0053] When analyzing a student's learning history, the analysis unit can extract learning trends and patterns and propose long-term learning plans. For example, the generation AI analyzes a student's learning history and extracts learning trends and patterns based on that data. For example, it analyzes learning effectiveness at specific times and environments. It also proposes long-term learning plans based on learning trends and patterns. For example, it proposes effective learning methods and schedules. The generation AI also analyzes learning trends and patterns and provides feedback based on that data. For example, it provides specific advice based on learning trends. In this way, it is possible to extract learning trends and patterns and propose long-term learning plans, thereby supporting effective learning.

[0054] The analysis unit can also analyze data from students' digital notebooks and online learning platforms to conduct long-term reflections. For example, the analysis unit uses the generation AI to analyze students' digital notebooks and conduct long-term reflections based on that data. For example, it analyzes the learning history and progress in the digital notebooks. It also analyzes data from the online learning platform to understand the student's learning situation. For example, it conducts long-term reflections based on activity history and submissions on the platform. It also uses the generation AI to analyze data from the digital notebooks and online learning platforms and conducts long-term reflections based on that data. For example, it integrates and evaluates the contents of the digital notebooks and data on online activities. This makes it possible to conduct long-term reflections that take into account data from the digital notebooks and online learning platforms.

[0055] The analysis unit can also analyze records of experiments and surveys conducted by students and conduct long-term reflections. For example, the generation AI analyzes records of experiments and surveys conducted by students and conducts long-term reflections based on that data. For example, evaluations are made based on the experiment design and data analysis methods. The analysis unit also evaluates students' logical thinking and problem-solving abilities through the analysis of experiment and survey records. For example, it evaluates how they interpret the results of experiments and draw conclusions. The generation AI also analyzes experiment and survey records and conducts long-term reflections based on that data. For example, it evaluates whether the experiment design and data analysis methods are logical. This makes it possible to conduct long-term reflections that take into account experiment and survey records.

[0056] When visualizing a student's growth and changes, the analysis unit can display learning progress and achievement in graphs and charts. For example, when the generation AI visualizes a student's growth and changes, the analysis unit displays learning progress and achievement in graphs and charts. For example, learning progress is visually shown in line graphs and bar graphs. Visualizing learning progress and achievement also improves student motivation. For example, it highlights areas with high achievement. The generation AI also analyzes learning progress and achievement and provides feedback based on that data. For example, it provides specific advice for areas where progress is lagging. In this way, displaying learning progress and achievement in graphs and charts can improve student motivation.

[0057] When visualizing a student's growth and changes, the analysis unit can extract learning trends and patterns and show the growth process. For example, when the generation AI visualizes a student's growth and changes, the analysis unit extracts learning trends and patterns. For example, it analyzes learning effects at specific times of day or in specific environments. It also shows the growth process based on learning trends and patterns. For example, it displays learning progress and results in chronological order to visually show the growth process. The generation AI also analyzes learning trends and patterns and shows the growth process based on that data. For example, it provides specific advice according to learning trends. In this way, by extracting learning trends and patterns and showing the growth process, it is possible to improve students' learning effectiveness.

[0058] The analysis unit can also analyze data from students' digital notebooks and online learning platforms to visualize growth and change. For example, the analysis unit uses a generation AI to analyze students' digital notebooks and visualize growth and change based on that data. For example, it analyzes learning history and progress in the digital notebooks. It also analyzes data from the online learning platform to understand the student's learning situation. For example, it visualizes growth and change based on activity history and submissions on the platform. It also uses a generation AI to analyze data from the digital notebooks and online learning platform and visualize growth and change based on that data. For example, it integrates and evaluates the contents of the digital notebooks and data on online activities. This makes it possible to visualize growth and change taking into account data from the digital notebooks and online learning platform.

[0059] The analysis unit can also analyze records of experiments and surveys conducted by students and visualize growth and change. For example, the analysis unit uses the generation AI to analyze records of experiments and surveys conducted by students and visualize growth and change based on that data. For example, evaluation is made based on the experiment design and data analysis method. The analysis unit also evaluates students' logical thinking and problem-solving abilities through the analysis of experiment and survey records. For example, it evaluates how they interpret the results of experiments and draw conclusions. The generation AI also analyzes experiment and survey records and visualizes growth and change based on that data. For example, it evaluates whether the experiment design and data analysis method are logical. This makes it possible to visualize growth and change taking into account experiment and survey records.

[0060] When formulating evaluation indicators for thinking ability, the analysis unit can compare them with the data of other students and set relative evaluation indicators. For example, when the generation AI formulates evaluation indicators for thinking ability, the analysis unit sets relative evaluation indicators by comparing them with the data of other students. For example, among answers to the same task, the most logical and creative writing may be given a high rating. Relative evaluation indicators are also set based on comparisons with the data of other students. For example, multiple writings written on the same topic may be compared and the consistency and depth of logic may be evaluated. The generation AI also identifies the strengths and weaknesses of individual students by comparing them with the data of other students and sets relative evaluation indicators. For example, if a student has a unique perspective or new ideas compared to other students, their thinking ability may be given a high rating. This makes it possible to set relative evaluation indicators through comparisons with other students.

[0061] When formulating evaluation indicators for thinking ability, the analysis unit can set evaluation indicators that take learning progress and achievement level into consideration. For example, when the generation AI formulates evaluation indicators for thinking ability, the analysis unit sets evaluation indicators that take learning progress and achievement level into consideration. For example, the analysis unit displays learning progress in a graph or chart, and sets evaluation indicators based on that data. Also, evaluation indicators are set based on learning progress and achievement level. For example, areas with high achievement levels are highlighted, and evaluation indicators are set based on that data. Also, the generation AI analyzes learning progress and achievement level, and sets evaluation indicators based on that data. For example, specific advice is provided for areas where progress is lagging, and evaluation indicators are set based on that data. This makes it possible to set evaluation indicators that take learning progress and achievement level into consideration.

[0062] The analysis unit can analyze data from students in different grades and departments and formulate common evaluation indicators. For example, the generation AI analyzes data from students in different grades and departments and formulates common evaluation indicators based on that data. For example, it compares the thinking abilities of students in different grades and departments and sets common evaluation indicators. It also sets common evaluation indicators based on data from students in different grades and departments. For example, it compares multiple texts written on the same topic and evaluates the consistency and depth of logic. It also analyzes data from students in different grades and departments and formulates common evaluation indicators based on that data. For example, it identifies the strengths and weaknesses of students in different grades and departments and sets common evaluation indicators. This makes it possible to analyze data from students in different grades and departments and formulate common evaluation indicators, thereby enabling fair evaluation.

[0063] The analysis unit can also analyze students' program code and algorithm data to formulate evaluation indicators for thinking ability. For example, the analysis unit uses the generative AI to analyze students' program code and formulate evaluation indicators for thinking ability based on that data. For example, it identifies errors and inefficient parts of the code and suggests ways to correct them. It also evaluates students' logical thinking and problem-solving abilities through algorithm analysis. For example, it evaluates based on the quality of algorithm design and implementation. The generative AI also analyzes program code and algorithms and formulates evaluation indicators for thinking ability based on that data. For example, it evaluates based on the consistency of the code and the lack of errors. This makes it possible to formulate evaluation indicators that take program code and algorithm data into account.

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

[0065] When analyzing students' writing, the analysis department can evaluate not only the structure of the text but also the metaphors and rhetorical devices used. For example, a text that makes extensive use of metaphors can be evaluated as demonstrating creative thinking. The department can also analyze the use of rhetorical devices and evaluate how those devices affect the logical structure of the text as a whole. For example, if repetition and contrast are used effectively, the student's logical thinking ability can be highly evaluated. The department can also evaluate a student's writing ability and creativity based on the use of metaphors and rhetorical devices. For example, if a student uses original metaphors or new rhetorical devices, the student's creativity can be highly evaluated. This makes it possible to evaluate thinking ability by taking metaphors and rhetorical devices into consideration.

[0066] When analyzing a student's writing, the analysis unit can compare it with the writing of other students to evaluate their relative thinking ability. For example, it can compare multiple writings on the same topic and evaluate the logical consistency and depth. It can also evaluate a student's relative thinking ability based on comparisons with other students' writing. For example, among answers to the same task, the most logical and creative writing can be given a higher rating. In addition, by comparing it with the writing of other students, the generation AI can identify the strengths and weaknesses of individual students and perform a relative evaluation. For example, if a student has a unique perspective or new ideas compared to other students, their thinking ability will be given a higher rating. This makes it possible to evaluate a student's relative thinking ability through comparisons with other students.

[0067] The analysis unit can also analyze the content of students' oral presentations and discussions and include it in the evaluation of their thinking ability. For example, the generation AI can analyze the content of a student's oral presentation and evaluate its logical structure and expressiveness. For example, it can evaluate thinking ability based on the flow of the presentation and the choice of words used. The generation AI can also analyze the content of discussions and evaluate the consistency and logic of students' comments. For example, it can evaluate based on the connection of comments during a discussion and the quality of counterarguments. The generation AI can also analyze recordings of oral presentations and discussions and evaluate the content of comments and changes in emotions. For example, it can identify points where emotions change in comments and evaluate these changes as indicating flexibility of thinking. This makes it possible to evaluate thinking ability while taking the content of oral presentations and discussions into account.

[0068] The analysis unit can also analyze visual data such as diagrams and graphs created by students and include it in the evaluation of their thinking ability. For example, the generative AI can analyze diagrams and graphs created by students and evaluate the accuracy of the data and their visual expressiveness. For example, it can evaluate their thinking ability based on how they selected the data and the structure of the graph. Analyzing visual data can also evaluate students' logical thinking ability and ability to interpret data. For example, it can evaluate what patterns and trends they found in the diagrams and graphs. The generative AI can also analyze visual data and evaluate how the data is related to written or oral presentations. For example, it can evaluate whether the visual data is logically consistent. This makes it possible to evaluate thinking ability by taking visual data into account.

[0069] When analyzing student notes, reports, essays, and other writings, the analysis unit can also include grammar and vocabulary frequency in its evaluation. For example, when the generative AI analyzes a student's writing, it can evaluate grammatical accuracy and vocabulary diversity. For example, grammatically correct writing and writing with a rich vocabulary can be highly rated. It can also evaluate a student's writing ability and expressiveness based on grammar and vocabulary frequency. For example, writing that uses complex grammatical structures and specialized vocabulary can be highly rated. The generative AI can also analyze grammar and vocabulary frequency and evaluate the overall quality of the writing based on that data. For example, writing that is grammatically correct and has a rich vocabulary can be evaluated as indicating high thinking ability. This makes it possible to evaluate thinking ability while taking grammar and vocabulary frequency into account.

[0070] When analyzing student notes, reports, essays, and other texts, the analysis unit can introduce algorithms that evaluate the coherence and logical flow of text. For example, the generative AI can introduce an algorithm that evaluates the coherence of text and analyze the logical flow of the entire text. For example, it can evaluate whether each paragraph is logically connected. Algorithms that evaluate logical flow can also be used to evaluate the structure and logical consistency of a text. For example, it can evaluate whether the introduction, development, and conclusion are clearly separated. The generative AI can also analyze the coherence and logical flow of text and evaluate the quality of the entire text based on that data. For example, it can evaluate logically coherent text as indicating high thinking ability. This makes it possible to evaluate thinking ability by taking into account the coherence and logical flow of text.

[0071] When analyzing student notes, reports, essays, and other writings, the analysis unit can also evaluate the diversity of themes and topics in the writing. For example, when the generative AI analyzes a student's writing, it can evaluate the diversity of themes and topics. For example, writings that cover multiple different themes and topics can be highly rated. The breadth and depth of a student's thinking can also be evaluated based on the diversity of themes and topics. For example, writings that incorporate different perspectives and approaches can be evaluated as exhibiting high thinking ability. The generative AI can also analyze the diversity of themes and topics and evaluate the overall quality of the writing based on that data. For example, writings that cover a variety of themes and topics can be evaluated as exhibiting creative thinking ability. This makes it possible to evaluate thinking ability while taking the diversity of themes and topics into account.

[0072] The processing flow of the first embodiment will be briefly explained below.

[0073] Step 1: The analyzer analyzes the student's writing. For example, the analyzer may analyze an essay or report written by a student and evaluate its grammar and syntax. The analyzer may also perform a semantic analysis of the text and evaluate its logical consistency. Furthermore, the analyzer may analyze metaphors and rhetorical devices in the text and evaluate their frequency and effectiveness. Step 2: The evaluation unit evaluates thinking ability based on the text analyzed by the analysis unit. For example, the evaluation unit evaluates logical thinking ability and creative thinking ability. The evaluation unit can also evaluate critical thinking ability based on the structure and content of the text. Furthermore, the evaluation unit can evaluate the development of arguments and logical consistency in the text. Step 3: The pointing unit points out errors and areas for improvement based on the results of the evaluation by the evaluation unit. For example, the pointing unit points out grammatical errors and logical errors. The pointing unit can also point out areas for improvement in expression. Furthermore, the pointing unit can also suggest specific methods for improvement based on the structure and content of the sentence.

[0074] (Example 2) The Evaluate generation AI system according to an embodiment of the present invention is a system for evaluating students' thinking ability and independent learning. In this system, the generation AI analyzes students' writing, qualitatively evaluates their thinking ability, and points out errors and areas for improvement. As a result, the Evaluate generation AI system can improve the quality of education by qualitatively evaluating students' thinking ability and pointing out errors and areas for improvement.

[0075] The evaluation generation AI system according to the embodiment includes an analysis unit, an evaluation unit, and a suggestion unit. The analysis unit analyzes a student's writing. For example, the analysis unit analyzes essays and reports written by the student and evaluates their grammar and syntax. The analysis unit can also perform semantic analysis of the writing and evaluate its logical consistency. The analysis unit can also analyze metaphors and rhetorical devices in the writing and evaluate their frequency of use and effectiveness. The evaluation unit evaluates thinking ability based on the writing analyzed by the analysis unit. For example, the evaluation unit evaluates logical thinking ability and creative thinking ability. The evaluation unit can also evaluate critical thinking ability based on the structure and content of the writing. The evaluation unit can also evaluate the development of arguments and logical consistency in the writing. The suggestion unit points out errors and areas for improvement based on the results of the evaluation by the evaluation unit. For example, the suggestion unit points out grammatical errors and logical errors. The suggestion unit can also point out areas for improvement in expression. The suggestion unit can also suggest specific improvement methods based on the structure and content of the writing. As a result, the Evaluate generation AI system according to the embodiment can qualitatively evaluate students' thinking abilities and point out errors and areas for improvement, thereby improving the quality of education.

[0076] The analysis unit uses the emotion estimation function to grasp the student's emotional state when analyzing the student's writing, and can evaluate their thinking ability based on that emotion. For example, when the generative AI analyzes the student's writing, the analysis unit uses the emotion estimation function to grasp the student's emotional state in real time. For example, it analyzes the emotional expressions and context in the text to identify the emotion the student felt when writing. It also uses the emotion estimation function to quantify the student's emotional state and evaluates their thinking ability based on that data. For example, it evaluates that writing with a strong positive emotion may indicate creative thinking ability. It also evaluates the student's thinking ability based on changes in emotion by grasping the student's emotional state. For example, if emotions change midway through a sentence, it evaluates that this change indicates flexibility and adaptability in thinking. This makes it possible to evaluate thinking ability taking the student's emotional state into account.

[0077] When analyzing a student's writing, the analysis unit can evaluate not only the structure of the text but also the metaphors and rhetorical devices used. For example, when the generative AI analyzes a student's writing, the analysis unit evaluates the frequency and type of metaphors and rhetorical devices used. For example, a text that makes heavy use of metaphors may be evaluated as demonstrating creative thinking. The analysis unit also analyzes the use of rhetorical devices and evaluates how those devices affect the logical structure of the entire text. For example, if repetition and contrast are used effectively, the logical thinking ability may be highly evaluated. The analysis unit also evaluates a student's writing ability and creativity based on the use of metaphors and rhetorical devices. For example, if a student uses original metaphors or new rhetorical devices, the creativity may be highly evaluated. This makes it possible to evaluate thinking ability by taking metaphors and rhetorical devices into account.

[0078] When analyzing a student's writing, the analysis unit compares it with the writing of other students and can evaluate the student's relative thinking ability. For example, when the generation AI analyzes a student's writing, the analysis unit compares it with the writing of other students to evaluate it. For example, it compares multiple writings on the same topic and evaluates the logical consistency and depth. It also evaluates the student's relative thinking ability based on the comparison with the writing of other students. For example, among answers to the same task, the most logical and creative writing may be highly rated. Furthermore, by comparing it with the writing of other students, the generation AI can identify the strengths and weaknesses of each student and perform a relative evaluation. For example, if a student has a unique perspective or new ideas compared to other students, it will be highly rated for their thinking ability. This makes it possible to evaluate a student's relative thinking ability through comparison with other students.

[0079] The analysis unit can also analyze the content of students' oral presentations and discussions and include it in the evaluation of their thinking ability. For example, the analysis unit's generation AI analyzes the content of a student's oral presentation and evaluates its logical structure and expressiveness. For example, it evaluates thinking ability based on the flow of the presentation and the choice of words used. The generation AI also analyzes the content of the discussion and evaluates the consistency and logic of the student's comments. For example, it evaluates based on the connection of comments during the discussion and the quality of counterarguments. The generation AI also analyzes recordings of oral presentations and discussions and evaluates the content of the comments and changes in emotions. For example, it identifies points where emotions change in the comments and evaluates that these changes indicate flexibility of thinking. This makes it possible to evaluate thinking ability while taking into account the content of the oral presentation or discussion.

[0080] The analysis unit can also analyze visual data such as diagrams and graphs created by students and include it in the evaluation of thinking ability. For example, the analysis unit uses a generative AI to analyze diagrams and graphs created by students and evaluate the accuracy of the data and the visual expressiveness of the data. For example, it evaluates thinking ability based on how the data is selected and the structure of the graph. It also evaluates students' logical thinking ability and ability to interpret data through the analysis of visual data. For example, it evaluates what patterns and trends they found in the diagrams and graphs. The generative AI also analyzes the visual data and evaluates how the data is related to written or oral presentations. For example, it evaluates whether the visual data is logically consistent. This makes it possible to evaluate thinking ability by taking visual data into consideration.

[0081] The analysis unit uses the emotion estimation function to track changes in a student's emotions as they compose text and can evaluate their thinking ability based on those changes. For example, the analysis unit uses the emotion estimation function to track changes in a student's emotions in real time as they compose text. For example, it identifies points in a text where emotions change and evaluates those changes as indicating flexibility of thinking. It also quantifies the changes in a student's emotions and evaluates their thinking ability based on that data. For example, if there is a large change in emotion, it evaluates that the change indicates the ability to incorporate new ideas and perspectives. It also uses the emotion estimation function to analyze changes in a student's emotions as they compose text and evaluates how those changes affect the logical structure of the entire text. For example, it evaluates that changes in emotion indicate a logical leap or the introduction of a new perspective. This makes it possible to evaluate thinking ability while taking changes in emotion into account.

[0082] When analyzing student notes, reports, essays, and other writings, the analysis unit can also include grammar and vocabulary frequency in its evaluation. For example, when the generation AI analyzes a student's writing, the analysis unit evaluates grammatical accuracy and vocabulary diversity. For example, it gives a high rating to grammatically correct writing and writing with a rich vocabulary. The analysis unit also evaluates a student's writing ability and expressiveness based on the frequency of grammar and vocabulary. For example, if a student uses complex grammatical structures or specialized vocabulary, it will give that writing a high rating. The generation AI also analyzes the frequency of grammar and vocabulary and evaluates the overall quality of the writing based on that data. For example, it evaluates writing that is grammatically correct and has a rich vocabulary as indicating high thinking ability. This makes it possible to evaluate thinking ability while taking into account the frequency of grammar and vocabulary.

[0083] When analyzing texts such as student notes, reports, and essays, the analysis unit can introduce algorithms that evaluate the coherence and logical flow of text. For example, the generation AI can introduce an algorithm that evaluates the coherence of text and analyze the logical flow of the entire text. For example, it can evaluate whether each paragraph is logically connected. It can also use an algorithm that evaluates logical flow to evaluate the structure and logical consistency of the text. For example, it can evaluate whether the introduction, development, and conclusion are clearly separated. The generation AI can also analyze the coherence and logical flow of text and evaluate the quality of the entire text based on that data. For example, it can evaluate logically consistent text as indicating high thinking ability. This makes it possible to evaluate thinking ability by taking into account the coherence and logical flow of text.

[0084] When analyzing student notes, reports, essays, and other writings, the analysis unit can also include in its evaluation the diversity of themes and topics in the writing. For example, when the generation AI analyzes a student's writing, the analysis unit evaluates the diversity of themes and topics. For example, it may highly evaluate writing that deals with multiple different themes and topics. The analysis unit also evaluates the breadth and depth of a student's thinking based on the diversity of themes and topics. For example, it may evaluate writing that incorporates different perspectives and approaches as exhibiting high thinking ability. The generation AI also analyzes the diversity of themes and topics and evaluates the overall quality of the writing based on that data. For example, it may evaluate writing that deals with a variety of themes and topics as exhibiting creative thinking ability. This makes it possible to evaluate thinking ability while taking the diversity of themes and topics into account.

[0085] The analysis unit can also analyze program code and algorithms written by students and include them in the evaluation of logical thinking ability. For example, the analysis unit uses a generative AI to analyze program code written by students and evaluate its logical structure and efficiency. For example, it evaluates thinking ability based on the accuracy and degree of optimization of the code. It also evaluates students' logical thinking and problem-solving abilities through the analysis of algorithms. For example, it evaluates based on the quality of algorithm design and implementation. The generative AI also analyzes program code and algorithms and evaluates logical thinking ability based on that data. For example, it evaluates based on the consistency of the code and the lack of errors. This makes it possible to evaluate logical thinking ability taking program code and algorithms into account.

[0086] The analysis unit can also analyze presentation materials created by students and include them in the evaluation of thinking ability. For example, the analysis unit uses the generation AI to analyze presentation materials created by students and evaluate their logical structure and visual expressiveness. For example, it evaluates thinking ability based on the structure and design of the slides. It also evaluates students' logical thinking and expressiveness through the analysis of presentation materials. For example, it evaluates what data and graphs are used in the materials. The generation AI also analyzes presentation materials and evaluates thinking ability based on that data. For example, it evaluates based on the consistency and visual effect of the materials. This makes it possible to evaluate thinking ability while taking presentation materials into consideration.

[0087] The analysis unit can use the emotion estimation function to analyze the intensity of emotions expressed by students when they compose text, and evaluate the text based on the emotions. The analysis unit, for example, uses the emotion estimation function to analyze the intensity of emotions expressed by students when they compose text. For example, the intensity of emotions is quantified based on the emotional expressions and context in the text. The analysis unit also evaluates the text based on the intensity of the student's emotions. For example, a text that expresses strong emotions may be evaluated as indicating high passion or interest. The emotion estimation function also analyzes the intensity of emotions expressed by students when they compose text, and evaluates the overall quality of the text based on that data. For example, a text with high emotional intensity may be evaluated as being persuasive and influential. This makes it possible to evaluate texts taking emotional intensity into account.

[0088] When analyzing a student's thought flow and logical structure, the analysis unit can use the emotion estimation function to track changes in emotion and evaluate the thought flow based on those changes. For example, when the generative AI analyzes a student's thought flow, the analysis unit uses the emotion estimation function to track changes in emotion in real time. For example, it analyzes emotional expressions and context in text to identify changes in emotion. It also quantifies changes in emotion and evaluates the thought flow based on that data. For example, if there is a large change in emotion, it can be evaluated as indicating the introduction of a new perspective or idea. The emotion estimation function can also be used to analyze the student's thought flow and evaluate how the change in emotion affects the logical structure. For example, it can evaluate that the change in emotion indicates a logical leap or the introduction of a new perspective. This makes it possible to evaluate the thought flow while taking emotional changes into account.

[0089] The analysis unit can evaluate branching points and options when analyzing a student's thought flow. For example, when the generation AI analyzes a student's thought flow, the analysis unit identifies branching points and options and evaluates them. For example, if multiple options are presented in a text, the quality of those options is evaluated. The analysis unit also evaluates the student's logical thinking and problem-solving abilities based on branching points in thought. For example, it evaluates whether the choice at the branching point is logical. The generation AI also analyzes branching points and options in thought and evaluates the thought flow based on that data. For example, if the choice at the branching point introduces a new perspective or idea, it will highly evaluate that thinking ability. This makes it possible to evaluate the thought flow taking branching points and options into account.

[0090] The analysis unit can introduce an algorithm that evaluates the depth and breadth of thought when analyzing a student's flow of thought and logical structure. For example, when the generation AI analyzes a student's flow of thought, the analysis unit introduces an algorithm that evaluates the depth and breadth of thought. For example, it evaluates the logical depth and diverse perspectives in the text. Furthermore, it evaluates the student's logical thinking ability and creativity based on the depth and breadth of thought. For example, it highly evaluates texts with deep insights and broad perspectives. Furthermore, the generation AI analyzes the depth and breadth of thought and evaluates the flow of thought based on that data. For example, it evaluates texts with deep logical analysis and diverse perspectives as indicating high thinking ability. This makes it possible to evaluate the flow of thought taking into account the depth and breadth of thought.

[0091] The analysis unit can also analyze the content of students' group discussions and evaluate the flow of thought and logical structure. For example, the generation AI analyzes the content of students' group discussions and evaluates their logical structure and flow of thought. For example, it evaluates the connections between comments during the discussion and the logical consistency. The analysis of group discussions also evaluates students' collaborative thinking and problem-solving abilities. For example, it evaluates based on the quality of exchange of opinions and cooperation during the discussion. The generation AI also analyzes recordings of group discussions and evaluates the content of comments and changes in emotions. For example, it identifies points where emotions change in comments and evaluates that these changes indicate flexibility of thinking. This makes it possible to evaluate the flow of thought while taking the content of the group discussion into account.

[0092] The analysis unit can also analyze the process of experiments and research conducted by students and evaluate the flow of thought and logical structure. For example, the analysis unit uses the generative AI to analyze the process of experiments and research conducted by students and evaluate its logical structure and flow of thought. For example, it evaluates thinking ability based on the design of the experiment and the method of data analysis. It also evaluates students' logical thinking and problem-solving abilities through the analysis of the experiment and research process. For example, it evaluates how the results of the experiment are interpreted and how conclusions are drawn. The generative AI also analyzes the process of the experiment or research and evaluates the flow of thought based on the data. For example, it evaluates whether the design of the experiment and the method of data analysis are logical. This makes it possible to evaluate the flow of thought taking into account the process of the experiment or research.

[0093] The analysis unit can use the emotion estimation function to track changes in a student's emotions as they think and evaluate the flow of thought and logical structure based on those changes. For example, the analysis unit uses the emotion estimation function to track changes in a student's emotions as they think in real time. For example, it identifies points where emotions change during thinking and evaluates those changes as indicating flexibility of thinking. It also quantifies the student's emotional changes and evaluates the flow of thought and logical structure based on that data. For example, if there is a large change in emotion, it evaluates that the change indicates the introduction of a new perspective or idea. It also uses the emotion estimation function to analyze changes in a student's emotions as they think and evaluates how those changes affect the flow of thought and logical structure. For example, it evaluates that changes in emotion indicate a logical leap or the introduction of a new perspective. This makes it possible to evaluate the flow of thought and logical structure while taking emotional changes into account.

[0094] When analyzing notes, the analysis unit uses the emotion estimation function to grasp the student's emotional state and can provide feedback based on that emotion. For example, when the generation AI analyzes notes, the analysis unit uses the emotion estimation function to grasp the student's emotional state in real time. For example, it analyzes the emotional expressions and context in the notes to identify the emotion the student felt when writing the notes. It also uses the emotion estimation function to quantify the student's emotional state and provides feedback based on that data. For example, it evaluates notes with strong positive emotions as likely to indicate creative thinking ability. It also understands the student's emotional state and provides feedback based on changes in emotion. For example, if emotions change during the note-taking process, it evaluates that change as indicating flexibility and adaptability of thinking. This makes it possible to provide feedback that takes emotional state into account.

[0095] When analyzing notes, the analysis unit can automatically point out not only errors and areas for improvement, but also excellent points. For example, when the generation AI analyzes notes, the analysis unit automatically points out not only errors and areas for improvement, but also excellent points. For example, it highly praises logical structure and creative ideas. Furthermore, by pointing out excellent points, it can improve student motivation. For example, it can specifically point out excellent expressions and unique perspectives in the notes. Furthermore, the generation AI analyzes the excellent points of the notes and provides feedback based on that data. For example, by emphasizing the excellent points, it can boost the student's confidence. In this way, by pointing out excellent points, it can improve student motivation.

[0096] When analyzing notes, the analysis unit can provide customized feedback based on the student's learning style and level of comprehension. For example, the analysis unit uses a generation AI to analyze a student's learning style and level of comprehension and provide customized feedback based on that data. For example, feedback that makes extensive use of diagrams and graphs can be provided to visual learners. Also, by providing feedback based on the student's level of comprehension, individualized instruction can be achieved. For example, detailed explanations can be added to parts where comprehension is low. Also, the generation AI analyzes a student's learning style and level of comprehension and provides feedback based on that data. For example, specific advice can be provided based on learning style. This makes it possible to provide individualized instruction based on learning style and level of comprehension.

[0097] The analysis unit can also analyze data from students' digital notebooks and online learning platforms and provide feedback. For example, the analysis unit uses a generation AI to analyze students' digital notebooks and provide feedback based on that data. For example, it can automatically point out errors and areas for improvement in the digital notebooks. It can also analyze data from online learning platforms to understand students' learning status. For example, it can provide feedback based on activity history and submissions on the platform. It can also analyze data from digital notebooks and online learning platforms and provide feedback based on that data. For example, it can integrate and evaluate the contents of digital notebooks and data on online activities. This makes it possible to provide feedback that takes into account data from digital notebooks and online learning platforms.

[0098] The analysis unit can also analyze records of experiments and surveys conducted by students and provide feedback. For example, the generation AI analyzes records of experiments and surveys conducted by students and provides feedback based on that data. For example, evaluations are made based on the experiment design and data analysis methods. The analysis unit also evaluates students' logical thinking and problem-solving abilities through the analysis of experiment and survey records. For example, it evaluates how the results of the experiment are interpreted and how conclusions are drawn. The generation AI also analyzes experiment and survey records and provides feedback based on that data. For example, it evaluates whether the experiment design and data analysis methods are logical. This makes it possible to provide feedback that takes into account the experiment and survey records.

[0099] The analysis unit uses the emotion estimation function to track changes in a student's emotions as they write notes and can provide feedback based on those emotions. The analysis unit, for example, uses the emotion estimation function to track changes in a student's emotions in real time as they write notes. For example, it analyzes emotional expressions and context in the notes to identify changes in emotions. It also quantifies changes in a student's emotions and provides feedback based on that data. For example, notes with strong positive emotions may be evaluated as potentially indicative of creative thinking ability. Furthermore, by understanding the student's emotional state, it provides feedback based on changes in emotions. For example, if emotions change during the course of writing notes, it may be evaluated as indicating flexibility and adaptability in thinking. This makes it possible to provide feedback that takes changes in emotions into account.

[0100] When pointing out errors or areas for improvement, the analysis unit uses the emotion estimation function to grasp the student's emotional state and can provide feedback based on that emotion. For example, when the generation AI points out errors or areas for improvement, the analysis unit uses the emotion estimation function to grasp the student's emotional state in real time. For example, it identifies the emotions the student is feeling when pointing out an error. It also uses the emotion estimation function to quantify the student's emotional state and provides feedback based on that data. For example, if the student has strong negative emotions, it can provide feedback in kind words. It also understands the student's emotional state and provides feedback based on changes in emotion. For example, if their emotions change when pointing out an error, it can provide feedback that reflects that change. This makes it possible to provide feedback that takes their emotional state into account.

[0101] The analysis unit can provide specific methods for improvement and reference materials when pointing out errors or areas for improvement. For example, when the generation AI points out errors or areas for improvement, the analysis unit provides specific methods for improvement. For example, it explains the cause of the error and specifically shows how to correct it. In addition, when pointing out areas for improvement, it provides reference materials. For example, it presents links to related literature and websites so that students can research and improve on their own. In addition, when the generation AI points out errors or areas for improvement, it supports students' learning by providing specific methods for improvement and reference materials. For example, it provides step-by-step instructions on how to correct errors. This makes it possible to support students' learning by providing specific methods for improvement and reference materials.

[0102] When pointing out errors or areas for improvement, the analysis unit can provide personalized feedback by referring to the student's past errors and areas for improvement. For example, the analysis unit's generation AI can refer to the student's past errors and areas for improvement and provide personalized feedback based on that data. For example, if the student has made the same error repeatedly in the past, the analysis unit can identify the cause and suggest specific ways to improve. The analysis unit can also provide individualized instruction based on the student's past errors and areas for improvement. For example, it can analyze past data and provide feedback on specific areas or skills. The generation AI can also refer to the student's past errors and areas for improvement and provide feedback based on that data. For example, it can provide specific advice for overcoming past errors. This makes it possible to provide personalized feedback by referring to past errors and areas for improvement.

[0103] The analysis unit can also point out errors and areas for improvement in students' program code and algorithms. For example, the generative AI analyzes students' program code and points out errors and areas for improvement. For example, it identifies errors and inefficient parts of the code and suggests ways to correct them. The analysis unit also evaluates students' logical thinking and problem-solving abilities through algorithm analysis. For example, it evaluates based on the quality of the algorithm design and implementation. The generative AI also analyzes program code and algorithms and points out errors and areas for improvement based on that data. For example, it evaluates based on the consistency of the code and the lack of errors. In this way, by pointing out errors and areas for improvement in program code and algorithms, it can help improve logical thinking skills.

[0104] The analysis unit can also point out errors and areas for improvement in students' presentation materials. For example, the generation AI analyzes students' presentation materials and points out errors and areas for improvement. For example, it identifies problems with the structure and design of slides and suggests ways to correct them. The analysis of presentation materials also evaluates students' logical thinking and expressive abilities. For example, it evaluates what data and graphs are used in the materials. The generation AI also analyzes presentation materials and points out errors and areas for improvement based on that data. For example, it evaluates based on the consistency and visual effect of the materials. This allows it to support the improvement of expressive abilities by pointing out errors and areas for improvement in presentation materials.

[0105] The analysis unit uses the emotion estimation function to track changes in a student's emotions when an error or an area for improvement is pointed out, and can provide feedback based on those emotions. For example, the analysis unit uses the emotion estimation function to track changes in a student's emotions in real time when an error or an area for improvement is pointed out. For example, it identifies the emotions the student felt when the error was pointed out. It also quantifies the changes in the student's emotions and provides feedback based on that data. For example, if the student has strong negative emotions, it provides feedback in kind words. It also understands the student's emotional state and provides feedback based on changes in emotions. For example, if the student's emotions change when an error is pointed out, it provides feedback that corresponds to that change. This makes it possible to provide feedback that takes changes in emotions into account.

[0106] When analyzing a student's learning history, the analysis unit uses the emotion estimation function to track changes in the student's emotions and can provide reflections based on those emotions. For example, when the generative AI analyzes a student's learning history, the analysis unit uses the emotion estimation function to track changes in emotions in real time. For example, it analyzes emotional expressions and context in the learning history to identify changes in emotions. It also quantifies the changes in emotions and provides reflections based on that data. For example, if there is a large change in emotion, it evaluates that this indicates the introduction of a new perspective or idea. It also uses the emotion estimation function to analyze the student's learning history and evaluate how changes in emotion affect learning progress and results. For example, it evaluates whether changes in emotion affect learning motivation and results. This makes it possible to provide reflections that take emotional changes into account.

[0107] When analyzing a student's learning history, the analysis unit can visualize their learning progress and achievement. For example, the generation AI analyzes the student's learning history and visualizes their learning progress and achievement based on that data. For example, it displays learning progress in graphs and charts. Visualizing learning progress and achievement can also improve student motivation. For example, it can highlight areas with high achievement. The generation AI can also analyze learning progress and achievement and provide feedback based on that data. For example, it can provide specific advice on areas where progress is lagging. In this way, visualizing learning progress and achievement can improve student motivation.

[0108] When analyzing a student's learning history, the analysis unit can visualize their learning progress and achievement. For example, the generation AI analyzes the student's learning history and visualizes their learning progress and achievement based on that data. For example, it displays learning progress in graphs and charts. Visualizing learning progress and achievement can also improve student motivation. For example, it can highlight areas with high achievement. The generation AI can also analyze learning progress and achievement and provide feedback based on that data. For example, it can provide specific advice on areas where progress is lagging. In this way, visualizing learning progress and achievement can improve student motivation.

[0109] When analyzing a student's learning history, the analysis unit can extract learning trends and patterns and propose long-term learning plans. For example, the generation AI analyzes a student's learning history and extracts learning trends and patterns based on that data. For example, it analyzes learning effectiveness at specific times and environments. It also proposes long-term learning plans based on learning trends and patterns. For example, it proposes effective learning methods and schedules. The generation AI also analyzes learning trends and patterns and provides feedback based on that data. For example, it provides specific advice based on learning trends. In this way, it is possible to extract learning trends and patterns and propose long-term learning plans, thereby supporting effective learning.

[0110] The analysis unit can also analyze data from students' digital notebooks and online learning platforms to conduct long-term reflections. For example, the analysis unit uses the generation AI to analyze students' digital notebooks and conduct long-term reflections based on that data. For example, it analyzes the learning history and progress in the digital notebooks. It also analyzes data from the online learning platform to understand the student's learning situation. For example, it conducts long-term reflections based on activity history and submissions on the platform. It also uses the generation AI to analyze data from the digital notebooks and online learning platforms and conducts long-term reflections based on that data. For example, it integrates and evaluates the contents of the digital notebooks and data on online activities. This makes it possible to conduct long-term reflections that take into account data from the digital notebooks and online learning platforms.

[0111] The analysis unit can also analyze records of experiments and surveys conducted by students and conduct long-term reflections. For example, the generation AI analyzes records of experiments and surveys conducted by students and conducts long-term reflections based on that data. For example, evaluations are made based on the experiment design and data analysis methods. The analysis unit also evaluates students' logical thinking and problem-solving abilities through the analysis of experiment and survey records. For example, it evaluates how they interpret the results of experiments and draw conclusions. The generation AI also analyzes experiment and survey records and conducts long-term reflections based on that data. For example, it evaluates whether the experiment design and data analysis methods are logical. This makes it possible to conduct long-term reflections that take into account experiment and survey records.

[0112] The analysis unit uses the emotion estimation function to track changes in students' emotions as they study, and can perform long-term reflection based on those emotions. The analysis unit, for example, uses the emotion estimation function to track changes in students' emotions as they study in real time. For example, it analyzes emotional expressions and contexts during study to identify changes in emotions. It also quantifies changes in students' emotions and performs long-term reflection based on that data. For example, if there is a large change in emotion, it evaluates that this indicates the introduction of a new perspective or idea. It also uses the emotion estimation function to analyze changes in students' emotions as they study and evaluates how these changes affect their learning progress and results. For example, it evaluates whether changes in emotion are affecting learning motivation and results. This makes it possible to perform long-term reflection that takes emotional changes into account.

[0113] When visualizing a student's growth and change, the analysis unit uses the emotion estimation function to track changes in the student's emotions and can evaluate growth based on those emotions. For example, when the generative AI visualizes a student's growth and change, the analysis unit uses the emotion estimation function to track emotional changes in real time. For example, it analyzes emotional expressions and context during learning to identify changes in emotions. It also quantifies emotional changes and evaluates growth based on that data. For example, if there is a large change in emotion, it can be evaluated as indicating the introduction of a new perspective or idea. The emotion estimation function can also be used to analyze a student's growth and change and evaluate how emotional changes affect learning progress and results. For example, it evaluates whether emotional changes are affecting learning motivation and results. This makes it possible to evaluate growth while taking emotional changes into account.

[0114] When visualizing a student's growth and changes, the analysis unit can display learning progress and achievement in graphs and charts. For example, when the generation AI visualizes a student's growth and changes, the analysis unit displays learning progress and achievement in graphs and charts. For example, learning progress is visually shown in line graphs and bar graphs. Visualizing learning progress and achievement also improves student motivation. For example, it highlights areas with high achievement. The generation AI also analyzes learning progress and achievement and provides feedback based on that data. For example, it provides specific advice for areas where progress is lagging. In this way, displaying learning progress and achievement in graphs and charts can improve student motivation.

[0115] When visualizing a student's growth and changes, the analysis unit can extract learning trends and patterns and show the growth process. For example, when the generation AI visualizes a student's growth and changes, the analysis unit extracts learning trends and patterns. For example, it analyzes learning effects at specific times of day or in specific environments. It also shows the growth process based on learning trends and patterns. For example, it displays learning progress and results in chronological order to visually show the growth process. The generation AI also analyzes learning trends and patterns and shows the growth process based on that data. For example, it provides specific advice according to learning trends. In this way, by extracting learning trends and patterns and showing the growth process, it is possible to improve students' learning effectiveness.

[0116] The analysis unit can also analyze data from students' digital notebooks and online learning platforms to visualize growth and change. For example, the analysis unit uses a generation AI to analyze students' digital notebooks and visualize growth and change based on that data. For example, it analyzes learning history and progress in the digital notebooks. It also analyzes data from the online learning platform to understand the student's learning situation. For example, it visualizes growth and change based on activity history and submissions on the platform. It also uses a generation AI to analyze data from the digital notebooks and online learning platform and visualize growth and change based on that data. For example, it integrates and evaluates the contents of the digital notebooks and data on online activities. This makes it possible to visualize growth and change taking into account data from the digital notebooks and online learning platform.

[0117] The analysis unit can also analyze records of experiments and surveys conducted by students and visualize growth and change. For example, the analysis unit uses the generation AI to analyze records of experiments and surveys conducted by students and visualize growth and change based on that data. For example, evaluation is made based on the experiment design and data analysis method. The analysis unit also evaluates students' logical thinking and problem-solving abilities through the analysis of experiment and survey records. For example, it evaluates how they interpret the results of experiments and draw conclusions. The generation AI also analyzes experiment and survey records and visualizes growth and change based on that data. For example, it evaluates whether the experiment design and data analysis method are logical. This makes it possible to visualize growth and change taking into account experiment and survey records.

[0118] The analysis unit uses the emotion estimation function to track changes in students' emotions as they study, and can visualize growth and change based on those emotions. The analysis unit, for example, uses the emotion estimation function to track changes in students' emotions as they study in real time. For example, it analyzes emotional expressions and contexts during study to identify changes in emotions. It also quantifies changes in students' emotions and visualizes growth and change based on that data. For example, a large change in emotion can be evaluated as indicating the introduction of a new perspective or idea. It also uses the emotion estimation function to analyze changes in students' emotions as they study and evaluate how those changes affect their learning progress and results. For example, it evaluates whether changes in emotion are affecting learning motivation and results. This makes it possible to visualize growth and change taking emotional changes into account.

[0119] When formulating evaluation indicators for thinking ability, the analysis unit can use the emotion estimation function to grasp the emotional state of students and set evaluation indicators based on those emotions. For example, when the generative AI formulates evaluation indicators for thinking ability, the analysis unit uses the emotion estimation function to grasp the emotional state of students in real time. For example, it analyzes emotional expressions and context during learning to identify changes in emotions. It also quantifies the changes in emotions and sets evaluation indicators based on that data. For example, if there is a large change in emotion, it can be evaluated as indicating the introduction of a new perspective or idea. It also uses the emotion estimation function to analyze the emotional state of students and set evaluation indicators based on that data. For example, it evaluates how emotional changes affect learning progress and results. This makes it possible to set evaluation indicators that take emotional states into account.

[0120] When formulating evaluation indicators for thinking ability, the analysis unit can compare them with the data of other students and set relative evaluation indicators. For example, when the generation AI formulates evaluation indicators for thinking ability, the analysis unit sets relative evaluation indicators by comparing them with the data of other students. For example, among answers to the same task, the most logical and creative writing may be given a high rating. Relative evaluation indicators are also set based on comparisons with the data of other students. For example, multiple writings written on the same topic may be compared and the consistency and depth of logic may be evaluated. The generation AI also identifies the strengths and weaknesses of individual students by comparing them with the data of other students and sets relative evaluation indicators. For example, if a student has a unique perspective or new ideas compared to other students, their thinking ability may be given a high rating. This makes it possible to set relative evaluation indicators through comparisons with other students.

[0121] When formulating evaluation indicators for thinking ability, the analysis unit can set evaluation indicators that take learning progress and achievement level into consideration. For example, when the generation AI formulates evaluation indicators for thinking ability, the analysis unit sets evaluation indicators that take learning progress and achievement level into consideration. For example, the analysis unit displays learning progress in a graph or chart, and sets evaluation indicators based on that data. Also, evaluation indicators are set based on learning progress and achievement level. For example, areas with high achievement levels are highlighted, and evaluation indicators are set based on that data. Also, the generation AI analyzes learning progress and achievement level, and sets evaluation indicators based on that data. For example, specific advice is provided for areas where progress is lagging, and evaluation indicators are set based on that data. This makes it possible to set evaluation indicators that take learning progress and achievement level into consideration.

[0122] The analysis unit can analyze data from students in different grades and departments and formulate common evaluation indicators. For example, the generation AI analyzes data from students in different grades and departments and formulates common evaluation indicators based on that data. For example, it compares the thinking abilities of students in different grades and departments and sets common evaluation indicators. It also sets common evaluation indicators based on data from students in different grades and departments. For example, it compares multiple texts written on the same topic and evaluates the consistency and depth of logic. It also analyzes data from students in different grades and departments and formulates common evaluation indicators based on that data. For example, it identifies the strengths and weaknesses of students in different grades and departments and sets common evaluation indicators. This makes it possible to analyze data from students in different grades and departments and formulate common evaluation indicators, thereby enabling fair evaluation.

[0123] The analysis unit can also analyze students' program code and algorithm data to formulate evaluation indicators for thinking ability. For example, the analysis unit uses the generative AI to analyze students' program code and formulate evaluation indicators for thinking ability based on that data. For example, it identifies errors and inefficient parts of the code and suggests ways to correct them. It also evaluates students' logical thinking and problem-solving abilities through algorithm analysis. For example, it evaluates based on the quality of algorithm design and implementation. The generative AI also analyzes program code and algorithms and formulates evaluation indicators for thinking ability based on that data. For example, it evaluates based on the consistency of the code and the lack of errors. This makes it possible to formulate evaluation indicators that take program code and algorithm data into account.

[0124] The analysis unit can use the emotion estimation function to track changes in students' emotions as they study and formulate evaluation indicators for thinking ability based on those emotions. The analysis unit, for example, uses the emotion estimation function to track changes in students' emotions as they study in real time. For example, it analyzes emotional expressions and contexts during study to identify changes in emotions. It also quantifies changes in students' emotions and formulates evaluation indicators for thinking ability based on that data. For example, if there is a large change in emotion, it is evaluated as indicating the introduction of a new perspective or idea. It also uses the emotion estimation function to analyze changes in students' emotions as they study and evaluate how those changes affect their learning progress and results. For example, it evaluates whether changes in emotion affect learning motivation and results. This makes it possible to formulate evaluation indicators that take emotional changes into account.

[0125] The system according to the embodiment is not limited to the above-described example, and various modifications are possible, for example, as follows.

[0126] When analyzing students' writing, the analysis department can evaluate not only the structure of the text but also the metaphors and rhetorical devices used. For example, a text that makes extensive use of metaphors can be evaluated as demonstrating creative thinking. The department can also analyze the use of rhetorical devices and evaluate how those devices affect the logical structure of the text as a whole. For example, if repetition and contrast are used effectively, the student's logical thinking ability can be highly evaluated. The department can also evaluate a student's writing ability and creativity based on the use of metaphors and rhetorical devices. For example, if a student uses original metaphors or new rhetorical devices, the student's creativity can be highly evaluated. This makes it possible to evaluate thinking ability by taking metaphors and rhetorical devices into consideration.

[0127] When analyzing a student's writing, the analysis unit uses an emotion estimation function to grasp the student's emotional state and can evaluate their thinking ability based on that emotion. For example, it can analyze the emotional expressions and context in the text to determine the emotion the student felt when writing. The emotion estimation function can also be used to quantify the student's emotional state and evaluate their thinking ability based on that data. For example, a text with a strong positive emotion can be evaluated as having the potential to demonstrate creative thinking ability. Furthermore, by grasping the student's emotional state, it is possible to evaluate their thinking ability based on changes in emotion. For example, if their emotion changes midway through a sentence, it can be evaluated as indicating flexibility and adaptability in thinking. This makes it possible to evaluate their thinking ability while taking the student's emotional state into account.

[0128] When analyzing a student's writing, the analysis unit can compare it with the writing of other students to evaluate their relative thinking ability. For example, it can compare multiple writings on the same topic and evaluate the logical consistency and depth. It can also evaluate a student's relative thinking ability based on comparisons with other students' writing. For example, among answers to the same task, the most logical and creative writing can be given a higher rating. In addition, by comparing it with the writing of other students, the generation AI can identify the strengths and weaknesses of individual students and perform a relative evaluation. For example, if a student has a unique perspective or new ideas compared to other students, their thinking ability will be given a higher rating. This makes it possible to evaluate a student's relative thinking ability through comparisons with other students.

[0129] The analysis unit can also analyze the content of students' oral presentations and discussions and include it in the evaluation of their thinking ability. For example, the generation AI can analyze the content of a student's oral presentation and evaluate its logical structure and expressiveness. For example, it can evaluate thinking ability based on the flow of the presentation and the choice of words used. The generation AI can also analyze the content of discussions and evaluate the consistency and logic of students' comments. For example, it can evaluate based on the connection of comments during a discussion and the quality of counterarguments. The generation AI can also analyze recordings of oral presentations and discussions and evaluate the content of comments and changes in emotions. For example, it can identify points where emotions change in comments and evaluate these changes as indicating flexibility of thinking. This makes it possible to evaluate thinking ability while taking the content of oral presentations and discussions into account.

[0130] The analysis unit can also analyze visual data such as diagrams and graphs created by students and include it in the evaluation of their thinking ability. For example, the generative AI can analyze diagrams and graphs created by students and evaluate the accuracy of the data and their visual expressiveness. For example, it can evaluate their thinking ability based on how they selected the data and the structure of the graph. Analyzing visual data can also evaluate students' logical thinking ability and ability to interpret data. For example, it can evaluate what patterns and trends they found in the diagrams and graphs. The generative AI can also analyze visual data and evaluate how the data is related to written or oral presentations. For example, it can evaluate whether the visual data is logically consistent. This makes it possible to evaluate thinking ability by taking visual data into account.

[0131] The analysis unit can use the emotion estimation function to track changes in a student's emotions as they compose text and evaluate their thinking ability based on those changes. For example, the emotion estimation function can be used to track changes in a student's emotions in real time as they compose text. For example, the function can identify points in a text where emotions change and evaluate those changes as indicating flexibility of thinking. The analysis unit can also quantify changes in a student's emotions and evaluate their thinking ability based on that data. For example, if there is a large change in emotion, the function can evaluate that this indicates the ability to incorporate new ideas and perspectives. The emotion estimation function can also be used to analyze changes in a student's emotions as they compose text and evaluate how those changes affect the logical structure of the entire text. For example, the function can evaluate that changes in emotion indicate a logical leap or the introduction of a new perspective. This makes it possible to evaluate thinking ability while taking changes in emotion into account.

[0132] When analyzing student notes, reports, essays, and other writings, the analysis unit can also include grammar and vocabulary frequency in its evaluation. For example, when the generative AI analyzes a student's writing, it can evaluate grammatical accuracy and vocabulary diversity. For example, grammatically correct writing and writing with a rich vocabulary can be highly rated. It can also evaluate a student's writing ability and expressiveness based on grammar and vocabulary frequency. For example, writing that uses complex grammatical structures and specialized vocabulary can be highly rated. The generative AI can also analyze grammar and vocabulary frequency and evaluate the overall quality of the writing based on that data. For example, writing that is grammatically correct and has a rich vocabulary can be evaluated as indicating high thinking ability. This makes it possible to evaluate thinking ability while taking grammar and vocabulary frequency into account.

[0133] When analyzing student notes, reports, essays, and other texts, the analysis unit can introduce algorithms that evaluate the coherence and logical flow of text. For example, the generative AI can introduce an algorithm that evaluates the coherence of text and analyze the logical flow of the entire text. For example, it can evaluate whether each paragraph is logically connected. Algorithms that evaluate logical flow can also be used to evaluate the structure and logical consistency of a text. For example, it can evaluate whether the introduction, development, and conclusion are clearly separated. The generative AI can also analyze the coherence and logical flow of text and evaluate the quality of the entire text based on that data. For example, it can evaluate logically coherent text as indicating high thinking ability. This makes it possible to evaluate thinking ability by taking into account the coherence and logical flow of text.

[0134] When analyzing student notes, reports, essays, and other writings, the analysis unit can also evaluate the diversity of themes and topics in the writing. For example, when the generative AI analyzes a student's writing, it can evaluate the diversity of themes and topics. For example, writings that cover multiple different themes and topics can be highly rated. The breadth and depth of a student's thinking can also be evaluated based on the diversity of themes and topics. For example, writings that incorporate different perspectives and approaches can be evaluated as exhibiting high thinking ability. The generative AI can also analyze the diversity of themes and topics and evaluate the overall quality of the writing based on that data. For example, writings that cover a variety of themes and topics can be evaluated as exhibiting creative thinking ability. This makes it possible to evaluate thinking ability while taking the diversity of themes and topics into account.

[0135] The analysis unit can use the emotion estimation function to track changes in students' emotions as they write notes and provide feedback based on those emotions. For example, the emotion estimation function can be used to track changes in students' emotions in real time as they write notes. For example, it can analyze emotional expressions and context in notes to identify changes in emotion. It can also quantify changes in students' emotions and provide feedback based on that data. For example, notes with strong positive emotions can be evaluated as having the potential to demonstrate creative thinking skills. Furthermore, by understanding a student's emotional state, it can also provide feedback based on changes in emotion. For example, if emotions change during the course of a note-taking session, it can be evaluated as indicating flexibility and adaptability in thinking. This makes it possible to provide feedback that takes changes in emotion into account.

[0136] The processing flow of the second embodiment will be briefly explained below.

[0137] Step 1: The analyzer analyzes the student's writing. For example, the analyzer may analyze an essay or report written by a student and evaluate its grammar and syntax. The analyzer may also perform a semantic analysis of the text and evaluate its logical consistency. Furthermore, the analyzer may analyze metaphors and rhetorical devices in the text and evaluate their frequency and effectiveness. Step 2: The evaluation unit evaluates thinking ability based on the text analyzed by the analysis unit. For example, the evaluation unit evaluates logical thinking ability and creative thinking ability. The evaluation unit can also evaluate critical thinking ability based on the structure and content of the text. Furthermore, the evaluation unit can evaluate the development of arguments and logical consistency in the text. Step 3: The pointing unit points out errors and areas for improvement based on the results of the evaluation by the evaluation unit. For example, the pointing unit points out grammatical errors and logical errors. The pointing unit can also point out areas for improvement in expression. Furthermore, the pointing unit can also suggest specific methods for improvement based on the structure and content of the sentence.

[0138] 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.

[0139] 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.

[0140] 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.

[0141] [Second embodiment] FIG. 3 shows an example of the configuration of a data processing system 210 according to the second embodiment.

[0142] 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.

[0143] 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.

[0144] 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.

[0145] 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.

[0146] 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).

[0147] 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.

[0148] 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.

[0149] 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.

[0150] The storage 32 stores a data generation model 58 and an emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290. The identification processing unit 290 can estimate a user's emotion using the emotion identification model 59 and perform identification processing using the user's emotion. The emotion estimation function (emotion identification function) using the emotion identification model 59 performs various estimations and predictions regarding the user's emotion, including estimation and prediction of the user's emotion, but is not limited to these examples. Furthermore, the estimation and prediction of emotion also includes, for example, emotion analysis.

[0151] In the smart glasses 214, the specific processing is performed by the processor 46. A specific processing program 60 is stored in the storage 50. The processor 46 reads the specific processing program 60 from the storage 50 and executes the read specific processing program 60 on the RAM 48. The specific processing is realized by the processor 46 operating as the control unit 46A in accordance with the specific processing program 60 executed on the RAM 48. The smart glasses 214 also have a data generation model and an emotion identification model similar to the data generation model 58 and the emotion identification model 59, and can perform processing similar to that of the specific processing unit 290 using these models.

[0152] 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.

[0153] 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.

[0154] The data generation model 58 is a so-called generative AI. An example of the data generation model 58 is a generative AI such as ChatGPT. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 receives a prompt containing an instruction, as well as inference data such as voice data representing speech, text data representing text, and image data representing an image. The data generation model 58 performs inference on the input inference data in accordance with the instruction indicated by the prompt and outputs the inference result in a data format such as voice data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization. The identification processing unit 290 performs the above-mentioned identification processing using the data generation model 58. The data generation model 58 may be a fine-tuned model so as to output an inference result from a prompt that does not include an instruction. In this case, the data generation model 58 can output an inference result from a prompt that does not include an instruction. The data processing device 12 and the like include multiple types of data generation models 58, and the data generation model 58 includes AI other than the generative AI. The AI ​​other than the generative AI may be, for example, linear regression, logistic regression, decision tree, random forest, support vector machine (SVM), k-means clustering, convolutional neural network (CNN), recurrent neural network (RNN), generative adversarial network (GAN), or naive Bayes, and can perform various processes, but is not limited to these examples. The AI ​​may also be an AI agent. When the processes of each of the above-mentioned parts are performed by AI, the processes may be performed in part or entirely by AI, but are not limited to these examples. The processes performed by AI, including the generative AI, may be replaced with rule-based processes.

[0155] 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.

[0156] [Third embodiment] FIG. 5 shows an example of the configuration of a data processing system 310 according to the third embodiment.

[0157] 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.

[0158] The data processing device 12 includes a computer 22, a database 24, and a communication I / F 26. The computer 22 includes a processor 28, a RAM 30, and a storage 32. The processor 28, RAM 30, and storage 32 are connected to a bus 34. The database 24 and the communication I / F 26 are also connected to the bus 34. The communication I / F 26 is connected to a network 54. Examples of the network 54 include a WAN and / or a LAN.

[0159] The 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.

[0160] The microphone 238 receives instructions and the like from the user by receiving voice uttered by the user. The microphone 238 captures the voice uttered by the user, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio according to instructions from the processor 46.

[0161] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an imaging element such as a CMOS (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).

[0162] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 are responsible for the exchange of various information between the processor 46 and the processor 28 via the network 54. The exchange of various information between the processor 46 and the processor 28 using the communication I / Fs 44 and 26 is carried out in a secure state.

[0163] 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.

[0164] 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.

[0165] The storage 32 stores a data generation model 58 and an emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290. The identification processing unit 290 can estimate a user's emotion using the emotion identification model 59 and perform identification processing using the user's emotion. The emotion estimation function (emotion identification function) using the emotion identification model 59 performs various estimations and predictions regarding the user's emotion, including estimation and prediction of the user's emotion, but is not limited to these examples. Furthermore, the estimation and prediction of emotion also includes, for example, emotion analysis.

[0166] In the headset type terminal 314, 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 headset type terminal 314 has a data generation model and an emotion identification model similar to the data generation model 58 and the emotion identification model 59, and can also perform processing similar to that of the specific processing unit 290 using these models.

[0167] 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.

[0168] 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.

[0169] The data generation model 58 is a so-called generative AI. An example of the data generation model 58 is a generative AI such as ChatGPT. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 receives a prompt containing an instruction, as well as inference data such as voice data representing speech, text data representing text, and image data representing an image. The data generation model 58 performs inference on the input inference data in accordance with the instruction indicated by the prompt and outputs the inference result in a data format such as voice data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization. The identification processing unit 290 performs the above-mentioned identification processing using the data generation model 58. The data generation model 58 may be a fine-tuned model so as to output an inference result from a prompt that does not include an instruction. In this case, the data generation model 58 can output an inference result from a prompt that does not include an instruction. The data processing device 12 and the like include multiple types of data generation models 58, and the data generation model 58 includes AI other than the generative AI. The AI ​​other than the generative AI may be, for example, linear regression, logistic regression, decision tree, random forest, support vector machine (SVM), k-means clustering, convolutional neural network (CNN), recurrent neural network (RNN), generative adversarial network (GAN), or naive Bayes, and can perform various processes, but is not limited to these examples. The AI ​​may also be an AI agent. When the processes of each of the above-mentioned parts are performed by AI, the processes may be performed in part or entirely by AI, but are not limited to these examples. The processes performed by AI, including the generative AI, may be replaced with rule-based processes.

[0170] 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.

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

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

[0173] The data processing device 12 includes a computer 22, a database 24, and a communication I / F 26. The computer 22 includes a processor 28, a RAM 30, and a storage 32. The processor 28, RAM 30, and storage 32 are connected to a bus 34. The database 24 and the communication I / F 26 are also connected to the bus 34. The communication I / F 26 is connected to a network 54. Examples of the network 54 include a WAN and / or a LAN.

[0174] The robot 414 includes a computer 36, a microphone 238, a speaker 240, a camera 42, a communication I / F 44, and a control target 443. The computer 36 includes a processor 46, a RAM 48, and a storage 50. The processor 46, the RAM 48, and the storage 50 are connected to a bus 52. The microphone 238, the speaker 240, the camera 42, and the control target 443 are also connected to the bus 52.

[0175] The microphone 238 receives instructions and the like from the user by receiving voice uttered by the user. The microphone 238 captures the voice uttered by the user, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio according to instructions from the processor 46.

[0176] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an imaging element such as a CMOS image sensor or a CCD image sensor, and captures images of the user's surroundings (for example, an imaging range defined by an angle of view equivalent to the field of vision of a typical healthy person).

[0177] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 are responsible for the exchange of various information between the processor 46 and the processor 28 via the network 54. The exchange of various information between the processor 46 and the processor 28 using the communication I / Fs 44 and 26 is carried out in a secure state.

[0178] The control object 443 includes a display device, LEDs in the eyes, and motors that drive the arms, hands, and feet. The posture and gestures of the robot 414 are controlled by controlling the motors of the arms, hands, and feet. Some of the emotions of the robot 414 can be expressed by controlling these motors. In addition, the facial expressions of the robot 414 can also be expressed by controlling the light emission state of the LEDs in the eyes of the robot 414.

[0179] Fig. 8 shows an example of the main functions of the data processing device 12 and the robot 414. As shown in Fig. 8, in the data processing device 12, a specific process is performed by the processor 28. A specific process program 56 is stored in the storage 32.

[0180] The processor 28 reads the specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific processing is realized by the processor 28 operating as a specific processing unit 290 in accordance with the specific processing program 56 executed on the RAM 30.

[0181] The storage 32 stores a data generation model 58 and an emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290. The identification processing unit 290 can estimate a user's emotion using the emotion identification model 59 and perform identification processing using the user's emotion. The emotion estimation function (emotion identification function) using the emotion identification model 59 performs various estimations and predictions regarding the user's emotion, including estimation and prediction of the user's emotion, but is not limited to these examples. Furthermore, the estimation and prediction of emotion also includes, for example, emotion analysis.

[0182] In the robot 414, the specific processing is performed by the processor 46. A specific processing program 60 is stored in the storage 50. The processor 46 reads the specific processing program 60 from the storage 50 and executes the read specific processing program 60 on the RAM 48. The specific processing is realized by the processor 46 operating as the control unit 46A in accordance with the specific processing program 60 executed on the RAM 48. The robot 414 also has a data generation model and an emotion identification model similar to the data generation model 58 and the emotion identification model 59, and can perform processing similar to that of the specific processing unit 290 using these models.

[0183] Note that a device other than the data processing device 12 may have the data generation model 58. For example, a server device may have the data generation model 58. In this case, the data processing device 12 communicates with the server device having the data generation model 58 to obtain a processing result (such as a prediction result) using the data generation model 58. Furthermore, the data processing device 12 may be a server device, or may be a terminal device (for example, a mobile phone, a robot, a home appliance, etc.) owned by a user.

[0184] The specific processing unit 290 transmits the result of the specific processing to the robot 414. In the robot 414, the control unit 46A causes the speaker 240 and the control target 443 to output the result of the specific processing. The microphone 238 acquires voice indicating a user input regarding the result of the specific processing. The control unit 46A transmits voice data indicating the user input acquired by the microphone 238 to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the voice data.

[0185] The data generation model 58 is a so-called generative AI. An example of the data generation model 58 is a generative AI such as ChatGPT. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 receives a prompt containing an instruction, as well as inference data such as voice data representing speech, text data representing text, and image data representing an image. The data generation model 58 performs inference on the input inference data in accordance with the instruction indicated by the prompt and outputs the inference result in a data format such as voice data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization. The identification processing unit 290 performs the above-mentioned identification processing using the data generation model 58. The data generation model 58 may be a fine-tuned model so as to output an inference result from a prompt that does not include an instruction. In this case, the data generation model 58 can output an inference result from a prompt that does not include an instruction. The data processing device 12 and the like include multiple types of data generation models 58, and the data generation model 58 includes AI other than the generative AI. The AI ​​other than the generative AI may be, for example, linear regression, logistic regression, decision tree, random forest, support vector machine (SVM), k-means clustering, convolutional neural network (CNN), recurrent neural network (RNN), generative adversarial network (GAN), or naive Bayes, and can perform various processes, but is not limited to these examples. The AI ​​may also be an AI agent. When the processes of each of the above-mentioned parts are performed by AI, the processes may be performed in part or entirely by AI, but are not limited to these examples. The processes performed by AI, including the generative AI, may be replaced with rule-based processes.

[0186] The data processing system 410 according to the fourth embodiment performs the same processing as the data processing system 10 according to the first embodiment. The processing by the data processing system 410 is executed by the specific processing unit 290 of the data processing device 12 or the control unit 46A of the robot 414, but may also be executed by the specific processing unit 290 of the data processing device 12 and the control unit 46A of the robot 414. Furthermore, the specific processing unit 290 of the data processing device 12 acquires or collects information required for processing from the robot 414 or an external device, etc., and the robot 414 acquires or collects information required for processing from the data processing device 12 or an external device, etc.

[0187] The 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.

[0188] 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.

[0189] 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.

[0190] 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).

[0191] 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.

[0192] 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."

[0193] 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.

[0194] 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.

[0195] 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.

[0196] 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.

[0197] 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.

[0198] 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.

[0199] 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.

[0200] 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.

[0201] 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.

[0202] 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.

[0203] 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.

[0204] 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]

[0205] 10, 210, 310, 410 Data Processing Systems 12 Data Processing Device 14 Smart Devices 214 Smart Glasses 314 Headset-type terminal 414 Robot

Claims

1. A system equipped with a generative AI, an analysis section that analyzes students' writing; an evaluation unit that evaluates thinking ability based on the sentence analyzed by the analysis unit; and a pointing out unit that points out errors and points for improvement based on the results of evaluation by the evaluation unit. A system characterized by:

2. The analysis unit When analyzing the student's writing, the emotional state of the student is grasped, and the thinking ability is evaluated based on the emotional state.

2. The system of claim 1.

3. The analysis unit When analyzing the student's writing, evaluate not only the structure of the writing but also the metaphors and rhetorical devices used.

2. The system of claim 1.

4. The analysis unit When analyzing the student's writing, compare it with the writing of other students to evaluate their relative thinking ability.

2. The system of claim 1.

5. The analysis unit The content of the students' oral presentations and discussions will also be analyzed and included in the evaluation of their thinking ability.

2. The system of claim 1.

Images