System

Abstract

An object of a system according to an embodiment is to make it easier for a learner to obtain feedback on his / her answer and to reduce the load of teaching materials.SOLUTION: A system includes an imaging unit, an analysis unit, a question generation unit, a scoring unit, and a feedback unit. The photographing part photographs a specific part of the textbook. The analysis unit analyzes the image captured by the imaging unit. The problem generation unit generates a problem based on the content analyzed by the analysis unit. When the learner answers the generated question, the scoring unit scores the answer. The feedback unit provides feedback based on the answer scored by the scoring 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 drawbacks of making it difficult for learners to receive feedback on their answers, and of requiring a large amount of learning material, which can be burdensome.

[0005] The system according to the embodiment aims to make it easier for learners to get feedback on their answers and reduce the burden of teaching materials. [Means for solving the problem]

[0006] The system according to the embodiment includes a photographing unit, an analysis unit, a question generation unit, a grading unit, and a feedback unit. The photographing unit photographs a specific portion of a textbook. The analysis unit analyzes the image photographed by the photographing unit. The question generation unit creates questions based on the content analyzed by the analysis unit. The grading unit grades the answers of the generated questions when the learner answers them. The feedback unit provides feedback based on the answers graded by the grading unit. [Effects of the Invention]

[0007] The system according to the embodiment makes it easier for learners to get feedback on their answers and reduces the burden of teaching materials. [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) In a learning support system according to an embodiment of the present invention, a learner takes a photo of a specific part of a textbook or reference book with a smartphone, and a generation AI analyzes that photo to create questions and provides feedback on the answers. This allows the learner to receive feedback on their answers and reduces the burden of carrying around learning materials.

[0029] A learning support system according to an embodiment includes a camera unit, an analysis unit, a question generation unit, a scoring unit, and a feedback unit. The camera unit captures a specific portion of a textbook. For example, the camera unit may capture a specific page of the textbook using a smartphone camera. The camera unit can also save the captured image at high resolution. The camera unit can automatically adjust the lighting conditions and angle during capture. For example, the camera unit may automatically adjust the exposure to reduce light reflections. The analysis unit analyzes the image captured by the camera unit. For example, the generation AI may analyze text and diagrams in the image to extract important points. The analysis unit may also analyze handwritten notes and highlighted portions using image processing technology. For example, the analysis unit may extract the contents of handwritten notes as text and prioritize the analysis of highlighted portions. The question generation unit creates questions based on the content analyzed by the analysis unit. For example, the generation AI may generate questions such as "What year did this event occur?" or "What was this person's role?" based on the analysis results. The question generation unit can also create questions in various formats, such as multiple-choice questions and written questions. For example, the question generation unit generates multiple-choice questions and written questions based on the analysis results. When a learner answers the generated questions, the scoring unit scores the answer. For example, the generation AI determines whether the learner's answer is correct or incorrect and calculates a score. The scoring unit can also analyze the answer process and thought process to provide detailed feedback. For example, the scoring unit analyzes each step of the answer and provides feedback for each step. The feedback unit provides feedback based on the answer scored by the scoring unit. For example, the generation AI provides feedback on the correctness of the answer and suggests the next learning step. The feedback unit can also adjust the content and tone of the feedback based on the learner's emotions using an emotion estimation function. For example, if the learner is feeling anxious, the feedback unit provides feedback including encouraging words. This allows the learning support system according to the embodiment to enable learners to efficiently study specific parts of a textbook and receive feedback on their answers.For example, learners can take a photo of a specific section of a textbook, and the generative AI will analyze the content to create questions, grade the answers, and provide feedback, improving their learning effectiveness. It also reduces the amount of luggage required to carry around learning materials.

[0030] The analysis unit analyzes handwritten notes and highlighted sections in an image and can create questions that reflect the learner's focus. For example, when a learner photographs a specific section of a textbook, the generation AI automatically detects handwritten notes and highlighted sections in the image and analyzes their content. For example, if a learner highlights a section they feel is important, the generation AI will prioritize analyzing that section and creating questions. Furthermore, when a specific section of a textbook is photographed, the analysis unit extracts the contents of the handwritten notes as text and creates questions based on that content. For example, it analyzes supplementary information and comments written by the learner and generates related questions. Furthermore, the analysis unit identifies highlighted sections from an image of a specific section of a textbook photographed by the generation AI and analyzes the content of those sections in detail. For example, it extracts important keywords and phrases highlighted and creates questions based on them. This allows questions to be created that reflect the learner's focus.

[0031] The analysis unit analyzes the font and layout in an image and can prioritize the extraction of information with high importance. For example, when a specific section of a textbook is photographed, the generation AI analyzes layout information in the image, such as font size, bold, and italics, and prioritizes the extraction of information with high importance. For example, questions are created based on headings and emphasized text. The analysis unit also analyzes the font type and color from an image of a specific section of a textbook photographed by the generation AI and identifies important information. For example, it extracts important points written in red or parts emphasized in a different font, and creates questions based on that. The analysis unit also analyzes layout information when a specific section of a textbook is photographed, and prioritizes the extraction of important charts and graphs. For example, it creates questions related to charts and graphs based on their position and size on the page. This allows the generation AI to prioritize the extraction of information with high importance.

[0032] The analysis unit accepts voice input and can also add the content of the learner's oral explanation to the analysis. For example, when a specific part of a textbook is photographed, the generation AI accepts the voice input and adds the learner's oral explanation to the analysis. For example, if a learner provides additional verbal explanation about the photographed page, the generation AI also analyzes that content to create questions. The analysis unit also analyzes the learner's voice input along with an image of a specific part of the textbook photographed by the generation AI and creates questions. For example, if a learner orally explains a point that they feel is important, questions are generated based on that content. Furthermore, when a specific part of a textbook is photographed, the generation AI analyzes the voice input and converts the learner's oral explanation into text data. For example, the content of the learner's oral explanation can be extracted as text and questions are created based on that. This allows the learner's oral explanation to be added to the analysis.

[0033] The analysis unit can integrate the contents of multiple textbooks and reference books to create more comprehensive questions. For example, when a specific portion of a textbook is photographed, the generation AI integrates the contents of multiple textbooks and reference books to create comprehensive questions. For example, questions are generated by combining information from different textbooks on the same topic. The analysis unit also analyzes the contents of other reference books along with images of specific portions of textbooks photographed by the generation AI to create integrated questions. For example, questions are generated by combining figures and text from different reference books. Furthermore, when a specific portion of a textbook is photographed, the analysis unit compares the contents of multiple textbooks and reference books, extracts important points, and creates questions. For example, explanations from different textbooks are integrated to create questions that encourage deeper understanding. This makes it possible to integrate the contents of multiple textbooks and reference books to create comprehensive questions.

[0034] The question generation unit can create multiple types of questions, such as multiple-choice questions or essay-style questions, based on the analyzed content. The question generation unit creates multiple-choice questions based on the content analyzed by the generation AI. For example, it generates the question "What year did this event occur?" and its answer options from a specific page in a history textbook. The question generation unit also creates essay-style questions based on the content analyzed by the generation AI. For example, it generates the question "Explain the background to this event" from a specific page in a history textbook. The question generation unit also creates fill-in-the-blank questions based on the content analyzed by the generation AI. For example, it generates the question "The year this event occurred is ( )" from a specific page in a history textbook. This makes it possible to create questions in a variety of formats.

[0035] The question generation unit can refer to related past exam questions and mock exam questions based on the analyzed content and create more practical questions. The question generation unit, for example, refers to related past exam questions based on the content analyzed by the generation AI and creates practical questions. For example, from a specific page in a history textbook, it generates questions similar to past exam questions. The question generation unit also refers to mock exam questions based on the content analyzed by the generation AI and creates practical questions. For example, from a specific page in a history textbook, it generates questions in a similar format to mock exam questions. The question generation unit also refers to a database of past exam questions and mock exam questions based on the content analyzed by the generation AI and creates practical questions. For example, from a specific page in a history textbook, it generates questions in a format that is often asked in exams. This makes it possible to create practical questions.

[0036] The question generation unit can create questions for different grades and levels based on the analyzed content and provide questions that correspond to the learner's level of understanding. For example, the question generation unit creates questions for different grades and levels based on the content analyzed by the generation AI. For example, questions for elementary school students, junior high school students, and high school students are generated from the content of the same history textbook. The question generation unit also analyzes the learner's level of understanding and provides questions at an appropriate level based on the results. For example, if the learner has a basic understanding, basic level questions are provided. The question generation unit also creates questions that correspond to the learner's progress based on the content analyzed by the generation AI. For example, applied questions are provided for content that the learner already understands, and basic questions are provided for content that the learner does not fully understand. This makes it possible to provide questions that correspond to the learner's level of understanding.

[0037] The question generation unit can create cross-curriculum questions that are related to other subjects or fields based on the analyzed content. For example, the question generation unit creates cross-curriculum questions that are related to other subjects or fields based on the content analyzed by the generation AI. For example, it generates questions that combine the content of a history textbook with the content of a geography textbook. The question generation unit also creates questions that integrate knowledge from different fields based on the content analyzed by the generation AI. For example, it generates questions related to historical events and the science and technology of that era. The question generation unit also creates questions that are related to other subjects or fields based on the content analyzed by the generation AI. For example, it generates questions that combine the content of a history textbook with the content of a literary work. This makes it possible to create cross-curriculum questions that are related to other subjects or fields.

[0038] When grading a learner's answer, the grading unit can also analyze the answer process and thought process and provide detailed feedback. For example, when the generation AI grades a learner's answer, the grading unit analyzes the answer process and thought process and provides detailed feedback. For example, it analyzes how the learner arrived at the answer and provides advice on that process. Furthermore, when the generation AI grades a learner's answer, the grading unit analyzes each step of the answer and provides feedback for each step. For example, it points out errors made along the way and shows the correct way to answer. Furthermore, when the generation AI grades a learner's answer, the grading unit analyzes the thought process and provides feedback based on that process. For example, it analyzes the logic used by the learner to answer and evaluates that logic. This makes it possible to analyze the answer process and thought process and provide detailed feedback.

[0039] When grading a learner's answers, the scoring unit can refer to past answer history to evaluate the learner's progress and level of growth. For example, when the generation AI grades a learner's answers, the scoring unit refers to past answer history to evaluate the learner's progress and level of growth. For example, it compares past answers to evaluate the degree of growth. Furthermore, when the generation AI grades a learner's answers, the scoring unit identifies the learner's strengths and weaknesses based on the past answer history and provides feedback based on that. For example, it encourages the learner to retry questions that were previously answered incorrectly. Furthermore, when the generation AI grades a learner's answers, the scoring unit analyzes past answer history to evaluate the learner's progress. For example, it evaluates the learner's level of growth based on the correct answer rate and answer time of past answers. In this way, the progress and level of growth can be evaluated by referring to past answer history.

[0040] When scoring a learner's answer, the scoring unit can compare it with the answers of other learners and provide a relative evaluation. For example, when the generation AI scores a learner's answer, the scoring unit compares it with the answers of other learners and provides a relative evaluation. For example, it evaluates the learner's answer by comparing it with the average score of other learners for the same question. Furthermore, when the generation AI scores a learner's answer, the scoring unit refers to the answer data of other learners and provides a relative evaluation. For example, it evaluates the learner's answer based on the trends in the answers of other learners for the same question. Furthermore, the scoring unit builds a system where, when the generation AI scores a learner's answer, the scoring unit compares it with the answers of other learners and provides a relative evaluation. For example, it evaluates the degree to which the learner's answer matches the answers of other learners. This makes it possible to compare it with the answers of other learners and provide a relative evaluation.

[0041] When grading a learner's answers, the scoring unit can provide related additional questions and supplemental materials based on the content of the answer. For example, when the generation AI grades a learner's answers, the scoring unit provides related additional questions based on the content of the answer. For example, for a question that the learner got wrong, the scoring unit provides additional questions on the same topic. In addition, when the generation AI grades a learner's answers, the scoring unit provides supplemental materials based on the content of the answer. For example, for a topic that the learner is struggling to understand, the scoring unit provides detailed explanatory materials. In addition, the scoring unit builds a system that provides related additional questions and supplemental materials based on the content of the answer when the generation AI grades a learner's answers. For example, it suggests the next content to study depending on the learner's answer. This makes it possible to provide related additional questions and supplemental materials based on the content of the answer.

[0042] The system according to the embodiment is not limited to the above-described example, and various modifications are possible, for example, as follows.

[0043] The learning assistance system may further include a progress tracking unit that tracks the learner's progress. The progress tracking unit records the history of questions answered by the learner and visualizes the learner's progress. For example, the progress tracking unit may record the correct answer rate and answer time of the questions answered by the learner and display them as a graph or chart. The progress tracking unit may also adjust the study plan based on the learner's progress. For example, if a learner has many weak questions in a particular area, the progress tracking unit may propose a study plan that focuses on that area. This allows the learner to understand their own progress and study effectively.

[0044] The learning support system may further include a learning style analysis unit that analyzes the learner's learning style. The learning style analysis unit analyzes the learner's answer patterns and study time, and suggests the most suitable study method for the learner. For example, if the learner prefers visual information, the learning style analysis unit may suggest learning materials that make extensive use of charts and graphs. Furthermore, if the learner tends to study in short bursts of concentration, the learning style analysis unit may provide a problem set that can be completed in a short time. This allows the learner to study effectively in a way that suits their own learning style.

[0045] The learning support system may further include a reward system to improve learners' motivation. The reward system may award points to learners each time they answer a question, allowing them to use the points to acquire virtual items or benefits. For example, the reward system may provide learners with avatar customization items when they acquire a certain number of points. The reward system may also award bonus points to learners who continue to study continuously. This allows learners to continue studying while having fun, thereby maintaining their motivation.

[0046] The learning support system can further include a learning planning unit that analyzes the learner's learning history and proposes a future learning plan. The learning planning unit proposes the next content and goals to be studied based on the learner's past learning history. For example, the learning planning unit proposes a plan to focus on areas in which the learner was weak in the past. The learning planning unit can also dynamically adjust the learning plan according to the learner's progress. For example, if the learner achieves a goal earlier than planned, a new goal will be set. This allows the learner to create an effective learning plan.

[0047] The learning support system may further include a training unit for improving the learning performance of the learner. The training unit identifies the learner's weaknesses and provides a training program to overcome those weaknesses. For example, the training unit may provide training for question formats that the learner finds difficult. The training unit may also provide time trial questions to improve the learner's answering speed. This allows the learner to overcome their weaknesses and improve their learning performance.

[0048] The learning support system may further include a sharing unit for sharing the learning content of a learner with other learners. The sharing unit allows a learner to share the questions he or she has answered and the learning content with other learners, and to advance learning collaboratively. For example, the sharing unit allows a learner to share the questions he or she has answered with other learners and hold discussions. The sharing unit can also share notes and memos created by a learner with other learners. This allows a learner to advance learning collaboratively with other learners.

[0049] The processing flow of the first embodiment will be briefly explained below.

[0050] Step 1: The camera unit captures a specific part of the textbook. For example, a specific page of the textbook can be captured using a smartphone camera. The camera unit can also save the captured image in high resolution. Furthermore, the camera unit can automatically adjust the lighting conditions and angle when capturing the image. For example, the camera unit can automatically adjust the exposure to reduce light reflections. Step 2: The analysis unit analyzes the image captured by the photography unit. For example, the generation AI analyzes the text and diagrams in the image and extracts important points. The analysis unit can also use image processing technology to analyze handwritten notes and parts highlighted with a highlighter. For example, the analysis unit extracts the contents of handwritten notes as text and prioritizes the analysis of parts highlighted with a highlighter. Step 3: The question generation unit creates questions based on the content analyzed by the analysis unit. For example, the generation AI generates questions such as "What year did this event occur?" or "What was this person's role?" based on the analysis results. The question generation unit can also create questions in various formats, such as multiple-choice questions and written questions. For example, the question generation unit generates multiple-choice questions and written questions based on the analysis results. Step 4: When the learner answers the generated questions, the scoring unit scores the answer. For example, the generating AI judges whether the learner's answer is correct or incorrect and calculates a score. The scoring unit can also analyze the answering process and thought process and provide detailed feedback. For example, the scoring unit analyzes each step of the answer and provides feedback for each step. Step 5: The feedback unit provides feedback based on the answers graded by the grading unit. For example, the generation AI provides feedback on whether the answer was correct or incorrect and suggests the next learning step. The feedback unit can also adjust the content and tone of the feedback based on the learner's emotions using an emotion estimation function. For example, if the learner is feeling anxious, the feedback unit provides feedback that includes encouraging words.

[0051] (Example 2) In a learning support system according to an embodiment of the present invention, a learner takes a photo of a specific part of a textbook or reference book with a smartphone, and a generation AI analyzes that photo to create questions and provides feedback on the answers. This allows the learner to receive feedback on their answers and reduces the burden of carrying around learning materials.

[0052] A learning support system according to an embodiment includes a camera unit, an analysis unit, a question generation unit, a scoring unit, and a feedback unit. The camera unit captures a specific portion of a textbook. For example, the camera unit may capture a specific page of the textbook using a smartphone camera. The camera unit can also save the captured image at high resolution. The camera unit can automatically adjust the lighting conditions and angle during capture. For example, the camera unit may automatically adjust the exposure to reduce light reflections. The analysis unit analyzes the image captured by the camera unit. For example, the generation AI may analyze text and diagrams in the image to extract important points. The analysis unit may also analyze handwritten notes and highlighted portions using image processing technology. For example, the analysis unit may extract the contents of handwritten notes as text and prioritize the analysis of highlighted portions. The question generation unit creates questions based on the content analyzed by the analysis unit. For example, the generation AI may generate questions such as "What year did this event occur?" or "What was this person's role?" based on the analysis results. The question generation unit can also create questions in various formats, such as multiple-choice questions and written questions. For example, the question generation unit generates multiple-choice questions and written questions based on the analysis results. When a learner answers the generated questions, the scoring unit scores the answer. For example, the generation AI determines whether the learner's answer is correct or incorrect and calculates a score. The scoring unit can also analyze the answer process and thought process to provide detailed feedback. For example, the scoring unit analyzes each step of the answer and provides feedback for each step. The feedback unit provides feedback based on the answer scored by the scoring unit. For example, the generation AI provides feedback on the correctness of the answer and suggests the next learning step. The feedback unit can also adjust the content and tone of the feedback based on the learner's emotions using an emotion estimation function. For example, if the learner is feeling anxious, the feedback unit provides feedback including encouraging words. This allows the learning support system according to the embodiment to enable learners to efficiently study specific parts of a textbook and receive feedback on their answers.For example, learners can take a photo of a specific section of a textbook, and the generative AI will analyze the content to create questions, grade the answers, and provide feedback, improving their learning effectiveness. It also reduces the amount of luggage required to carry around learning materials.

[0053] The analysis unit analyzes handwritten notes and highlighted sections in an image and can create questions that reflect the learner's focus. For example, when a learner photographs a specific section of a textbook, the generation AI automatically detects handwritten notes and highlighted sections in the image and analyzes their content. For example, if a learner highlights a section they feel is important, the generation AI will prioritize analyzing that section and creating questions. Furthermore, when a specific section of a textbook is photographed, the analysis unit extracts the contents of the handwritten notes as text and creates questions based on that content. For example, it analyzes supplementary information and comments written by the learner and generates related questions. Furthermore, the analysis unit identifies highlighted sections from an image of a specific section of a textbook photographed by the generation AI and analyzes the content of those sections in detail. For example, it extracts important keywords and phrases highlighted and creates questions based on them. This allows questions to be created that reflect the learner's focus.

[0054] The analysis unit analyzes the font and layout in an image and can prioritize the extraction of information with high importance. For example, when a specific section of a textbook is photographed, the generation AI analyzes layout information in the image, such as font size, bold, and italics, and prioritizes the extraction of information with high importance. For example, questions are created based on headings and emphasized text. The analysis unit also analyzes the font type and color from an image of a specific section of a textbook photographed by the generation AI and identifies important information. For example, it extracts important points written in red or parts emphasized in a different font, and creates questions based on that. The analysis unit also analyzes layout information when a specific section of a textbook is photographed, and prioritizes the extraction of important charts and graphs. For example, it creates questions related to charts and graphs based on their position and size on the page. This allows the generation AI to prioritize the extraction of information with high importance.

[0055] The analysis unit uses an emotion estimation function to analyze the emotions felt by the learner when filming and can adjust the difficulty and content of the questions based on those emotions. For example, when a specific part of a textbook is filmed, the generation AI analyzes the learner's facial expressions and voice to estimate their emotions. For example, if the learner is confused, the difficulty of the questions can be adjusted to be lowered. The analysis unit also analyzes the learner's emotions in real time when the generation AI films a specific part of a textbook and adjusts the content of the questions based on that emotion. For example, if the learner is excited, more challenging questions can be provided. The analysis unit also collects emotional data from the learner when a specific part of a textbook is filmed and dynamically adjusts the difficulty and content of the questions based on that data. For example, if the learner is relaxed, questions of standard difficulty can be provided. This makes it possible to adjust the difficulty and content of questions based on the learner's emotions.

[0056] The analysis unit accepts voice input and can also add the content of the learner's oral explanation to the analysis. For example, when a specific part of a textbook is photographed, the generation AI accepts the voice input and adds the learner's oral explanation to the analysis. For example, if a learner provides additional verbal explanation about the photographed page, the generation AI also analyzes that content to create questions. The analysis unit also analyzes the learner's voice input along with an image of a specific part of the textbook photographed by the generation AI and creates questions. For example, if a learner orally explains a point that they feel is important, questions are generated based on that content. Furthermore, when a specific part of a textbook is photographed, the generation AI analyzes the voice input and converts the learner's oral explanation into text data. For example, the content of the learner's oral explanation can be extracted as text and questions are created based on that. This allows the learner's oral explanation to be added to the analysis.

[0057] The analysis unit can integrate the contents of multiple textbooks and reference books to create more comprehensive questions. For example, when a specific portion of a textbook is photographed, the generation AI integrates the contents of multiple textbooks and reference books to create comprehensive questions. For example, questions are generated by combining information from different textbooks on the same topic. The analysis unit also analyzes the contents of other reference books along with images of specific portions of textbooks photographed by the generation AI to create integrated questions. For example, questions are generated by combining figures and text from different reference books. Furthermore, when a specific portion of a textbook is photographed, the analysis unit compares the contents of multiple textbooks and reference books, extracts important points, and creates questions. For example, explanations from different textbooks are integrated to create questions that encourage deeper understanding. This makes it possible to integrate the contents of multiple textbooks and reference books to create comprehensive questions.

[0058] The analysis unit uses the emotion estimation function to analyze the emotions felt by the learner when taking a photo and can provide appropriate study advice to the learner based on those emotions. For example, when a specific part of a textbook is photographed, the generation AI analyzes the learner's emotions and provides study advice based on those emotions. For example, if the learner is feeling anxious, advice to relax is provided. The analysis unit also collects emotional data from the learner when the generation AI photographs a specific part of a textbook and provides study advice based on that data. For example, if the learner is concentrating, advice to dig deeper is provided. The analysis unit also analyzes the learner's emotions in real time when a specific part of a textbook is photographed and provides study advice based on those emotions. For example, if the learner is tired, advice to take a break is provided. This makes it possible to provide appropriate study advice based on the learner's emotions.

[0059] The question generation unit can create multiple types of questions, such as multiple-choice questions or essay-style questions, based on the analyzed content. The question generation unit creates multiple-choice questions based on the content analyzed by the generation AI. For example, it generates the question "What year did this event occur?" and its answer options from a specific page in a history textbook. The question generation unit also creates essay-style questions based on the content analyzed by the generation AI. For example, it generates the question "Explain the background to this event" from a specific page in a history textbook. The question generation unit also creates fill-in-the-blank questions based on the content analyzed by the generation AI. For example, it generates the question "The year this event occurred is ( )" from a specific page in a history textbook. This makes it possible to create questions in a variety of formats.

[0060] The question generation unit can refer to related past exam questions and mock exam questions based on the analyzed content and create more practical questions. The question generation unit, for example, refers to related past exam questions based on the content analyzed by the generation AI and creates practical questions. For example, from a specific page in a history textbook, it generates questions similar to past exam questions. The question generation unit also refers to mock exam questions based on the content analyzed by the generation AI and creates practical questions. For example, from a specific page in a history textbook, it generates questions in a similar format to mock exam questions. The question generation unit also refers to a database of past exam questions and mock exam questions based on the content analyzed by the generation AI and creates practical questions. For example, from a specific page in a history textbook, it generates questions in a format that is often asked in exams. This makes it possible to create practical questions.

[0061] The question generation unit uses the emotion estimation function to analyze a learner's emotional reactions to questions that they have previously answered and can adjust the format and content of questions based on those reactions. For example, the question generation unit uses a generation AI to analyze a learner's emotional reactions to past answers and adjust the format and content of questions based on that data. For example, if a learner has previously responded positively to multiple-choice questions, the question generation unit will prioritize providing multiple-choice questions. The question generation unit also uses the generation AI to analyze the learner's emotional data and adjust the difficulty of questions based on the results. For example, if a learner has previously responded negatively to difficult questions, the question generation unit will provide questions with a lower level of difficulty. The question generation unit also uses the generation AI to analyze the learner's emotional reactions in real time and dynamically adjust the content of questions based on that data. For example, if a learner has previously responded positively to a specific topic, the question generation unit will provide questions related to that topic. This allows the question format and content to be adjusted based on the learner's emotional reactions.

[0062] The question generation unit can create questions for different grades and levels based on the analyzed content and provide questions that correspond to the learner's level of understanding. For example, the question generation unit creates questions for different grades and levels based on the content analyzed by the generation AI. For example, questions for elementary school students, junior high school students, and high school students are generated from the content of the same history textbook. The question generation unit also analyzes the learner's level of understanding and provides questions at an appropriate level based on the results. For example, if the learner has a basic understanding, basic level questions are provided. The question generation unit also creates questions that correspond to the learner's progress based on the content analyzed by the generation AI. For example, applied questions are provided for content that the learner already understands, and basic questions are provided for content that the learner does not fully understand. This makes it possible to provide questions that correspond to the learner's level of understanding.

[0063] The question generation unit can create cross-curriculum questions that are related to other subjects or fields based on the analyzed content. For example, the question generation unit creates cross-curriculum questions that are related to other subjects or fields based on the content analyzed by the generation AI. For example, it generates questions that combine the content of a history textbook with the content of a geography textbook. The question generation unit also creates questions that integrate knowledge from different fields based on the content analyzed by the generation AI. For example, it generates questions related to historical events and the science and technology of that era. The question generation unit also creates questions that are related to other subjects or fields based on the content analyzed by the generation AI. For example, it generates questions that combine the content of a history textbook with the content of a literary work. This makes it possible to create cross-curriculum questions that are related to other subjects or fields.

[0064] The question generation unit uses the emotion estimation function to analyze the learner's emotional responses to questions that the learner has answered in the past, and can propose a study plan appropriate for the learner based on those responses. For example, the question generation unit uses a generation AI to analyze the learner's emotional responses to past answers and propose a study plan based on that data. For example, the study plan may be built around themes that the learner has previously expressed positive emotions about. The question generation unit also uses a generation AI to analyze the learner's emotional data and dynamically adjust the study plan based on the results. For example, the study plan may avoid themes that the learner has previously expressed negative emotions about and prioritize themes that the learner has previously expressed positive emotions about. The question generation unit also uses a generation AI to analyze the learner's emotional responses in real time and propose a study plan based on that data. For example, the study plan may avoid themes that the learner has previously experienced stress and focus on themes that allow the learner to study in a relaxed manner. This makes it possible to propose an appropriate study plan based on the learner's emotional responses.

[0065] When grading a learner's answer, the grading unit can also analyze the answer process and thought process and provide detailed feedback. For example, when the generation AI grades a learner's answer, the grading unit analyzes the answer process and thought process and provides detailed feedback. For example, it analyzes how the learner arrived at the answer and provides advice on that process. Furthermore, when the generation AI grades a learner's answer, the grading unit analyzes each step of the answer and provides feedback for each step. For example, it points out errors made along the way and shows the correct way to answer. Furthermore, when the generation AI grades a learner's answer, the grading unit analyzes the thought process and provides feedback based on that process. For example, it analyzes the logic used by the learner to answer and evaluates that logic. This makes it possible to analyze the answer process and thought process and provide detailed feedback.

[0066] When grading a learner's answers, the scoring unit can refer to past answer history to evaluate the learner's progress and level of growth. For example, when the generation AI grades a learner's answers, the scoring unit refers to past answer history to evaluate the learner's progress and level of growth. For example, it compares past answers to evaluate the degree of growth. Furthermore, when the generation AI grades a learner's answers, the scoring unit identifies the learner's strengths and weaknesses based on the past answer history and provides feedback based on that. For example, it encourages the learner to retry questions that were previously answered incorrectly. Furthermore, when the generation AI grades a learner's answers, the scoring unit analyzes past answer history to evaluate the learner's progress. For example, it evaluates the learner's level of growth based on the correct answer rate and answer time of past answers. In this way, the progress and level of growth can be evaluated by referring to past answer history.

[0067] The scoring unit uses the emotion estimation function to analyze the emotions felt by the learner when answering an answer, and can adjust the content and tone of the feedback based on those emotions. For example, the scoring unit uses the generation AI to analyze the emotions felt by the learner when answering an answer, and adjust the content and tone of the feedback based on those emotions. For example, if the learner is feeling anxious, the scoring unit provides feedback that includes words of encouragement. The scoring unit also uses the generation AI to collect emotional data on the learner and adjust the tone of the feedback based on that data. For example, if the learner is confident, the scoring unit provides positive feedback. The scoring unit also uses the generation AI to analyze the learner's emotions in real time, and adjust the content of the feedback based on those emotions. For example, if the learner is feeling stressed, the scoring unit provides advice on how to relax. This makes it possible to adjust the content and tone of the feedback based on the learner's emotions.

[0068] When scoring a learner's answer, the scoring unit can compare it with the answers of other learners and provide a relative evaluation. For example, when the generation AI scores a learner's answer, the scoring unit compares it with the answers of other learners and provides a relative evaluation. For example, it evaluates the learner's answer by comparing it with the average score of other learners for the same question. Furthermore, when the generation AI scores a learner's answer, the scoring unit refers to the answer data of other learners and provides a relative evaluation. For example, it evaluates the learner's answer based on the trends in the answers of other learners for the same question. Furthermore, the scoring unit builds a system where, when the generation AI scores a learner's answer, the scoring unit compares it with the answers of other learners and provides a relative evaluation. For example, it evaluates the degree to which the learner's answer matches the answers of other learners. This makes it possible to compare it with the answers of other learners and provide a relative evaluation.

[0069] When grading a learner's answers, the scoring unit can provide related additional questions and supplemental materials based on the content of the answer. For example, when the generation AI grades a learner's answers, the scoring unit provides related additional questions based on the content of the answer. For example, for a question that the learner got wrong, the scoring unit provides additional questions on the same topic. In addition, when the generation AI grades a learner's answers, the scoring unit provides supplemental materials based on the content of the answer. For example, for a topic that the learner is struggling to understand, the scoring unit provides detailed explanatory materials. In addition, the scoring unit builds a system that provides related additional questions and supplemental materials based on the content of the answer when the generation AI grades a learner's answers. For example, it suggests the next content to study depending on the learner's answer. This makes it possible to provide related additional questions and supplemental materials based on the content of the answer.

[0070] The scoring unit uses the emotion estimation function to analyze the emotions felt by the learner when answering questions and can suggest appropriate motivation-boosting measures for the learner based on those emotions. For example, the scoring unit uses the generation AI to analyze the emotions felt by the learner when answering questions and suggest motivation-boosting measures based on those emotions. For example, if the learner is tired, the scoring unit advises the learner to take a break. The scoring unit also uses the generation AI to collect learner emotional data and suggest motivation-boosting measures based on that data. For example, if the learner is feeling down, the scoring unit provides an encouraging message. The scoring unit also uses the generation AI to analyze the learner's emotions in real time and suggest motivation-boosting measures based on those emotions. For example, if the learner is losing motivation, the scoring unit provides goal-setting advice. This makes it possible to suggest appropriate motivation-boosting measures based on the learner's emotions.

[0071] The system according to the embodiment is not limited to the above-described example, and various modifications are possible, for example, as follows.

[0072] The learning assistance system may further include a progress tracking unit that tracks the learner's progress. The progress tracking unit records the history of questions answered by the learner and visualizes the learner's progress. For example, the progress tracking unit may record the correct answer rate and answer time of the questions answered by the learner and display them as a graph or chart. The progress tracking unit may also adjust the study plan based on the learner's progress. For example, if a learner has many weak questions in a particular area, the progress tracking unit may propose a study plan that focuses on that area. This allows the learner to understand their own progress and study effectively.

[0073] The learning support system may further include a learning style analysis unit that analyzes the learner's learning style. The learning style analysis unit analyzes the learner's answer patterns and study time, and suggests the most suitable study method for the learner. For example, if the learner prefers visual information, the learning style analysis unit may suggest learning materials that make extensive use of charts and graphs. Furthermore, if the learner tends to study in short bursts of concentration, the learning style analysis unit may provide a problem set that can be completed in a short time. This allows the learner to study effectively in a way that suits their own learning style.

[0074] The learning support system may further include a reward system to improve learners' motivation. The reward system may award points to learners each time they answer a question, allowing them to use the points to acquire virtual items or benefits. For example, the reward system may provide learners with avatar customization items when they acquire a certain number of points. The reward system may also award bonus points to learners who continue to study continuously. This allows learners to continue studying while having fun, thereby maintaining their motivation.

[0075] The learning support system can further include a health management unit that monitors the learner's health condition. The health management unit measures the learner's heart rate and stress level and suggests appropriate breaks during study sessions. For example, if the learner's heart rate rises, the health management unit can provide advice on deep breathing or stretching to relax. In addition, if the learner's stress level is high, the health management unit can provide music or meditation guides to help them relax. This allows the learner to study effectively while maintaining their health.

[0076] The learning support system can further include a learning planning unit that analyzes the learner's learning history and proposes a future learning plan. The learning planning unit proposes the next content and goals to be studied based on the learner's past learning history. For example, the learning planning unit proposes a plan to focus on areas in which the learner was weak in the past. The learning planning unit can also dynamically adjust the learning plan according to the learner's progress. For example, if the learner achieves a goal earlier than planned, a new goal will be set. This allows the learner to create an effective learning plan.

[0077] The learning support system can further include an environment adjustment unit that estimates the learner's emotions and adjusts the learning environment based on those emotions. The environment adjustment unit analyzes the learner's emotions and adjusts the music and lighting in the learning environment. For example, if the learner is relaxed, it plays music to help them concentrate. The environment adjustment unit can also set lighting to help the learner relax if the learner is feeling stressed. This allows the learner to study in a comfortable environment.

[0078] The learning support system may further include a training unit for improving the learning performance of the learner. The training unit identifies the learner's weaknesses and provides a training program to overcome those weaknesses. For example, the training unit may provide training for question formats that the learner finds difficult. The training unit may also provide time trial questions to improve the learner's answering speed. This allows the learner to overcome their weaknesses and improve their learning performance.

[0079] The learning assistance system can further include a progress adjustment unit that estimates the learner's emotions and adjusts the learning progress based on those emotions. The progress adjustment unit analyzes the learner's emotions and adjusts the learning progress. For example, if the learner is tired, it adjusts the learning pace to slow down. The progress adjustment unit can also adjust the learning pace to speed up if the learner is concentrating. This allows the learner to progress in learning at a pace that suits their own emotions.

[0080] The learning support system may further include a sharing unit for sharing the learning content of a learner with other learners. The sharing unit allows a learner to share the questions he or she has answered and the learning content with other learners, and to advance learning collaboratively. For example, the sharing unit allows a learner to share the questions he or she has answered with other learners and hold discussions. The sharing unit can also share notes and memos created by a learner with other learners. This allows a learner to advance learning collaboratively with other learners.

[0081] The learning support system can further include a motivation maintenance unit that estimates the learner's emotions and maintains their motivation to learn based on those emotions. The motivation maintenance unit analyzes the learner's emotions and suggests actions to maintain motivation based on those emotions. For example, if the learner is losing motivation, it can provide an encouraging message. The motivation maintenance unit can also provide feedback to the learner to feel a sense of accomplishment when the learner achieves a goal. This allows the learner to continue learning while maintaining their motivation.

[0082] The processing flow of the second embodiment will be briefly explained below.

[0083] Step 1: The camera unit captures a specific part of the textbook. For example, a specific page of the textbook can be captured using a smartphone camera. The camera unit can also save the captured image in high resolution. Furthermore, the camera unit can automatically adjust the lighting conditions and angle when capturing the image. For example, the camera unit can automatically adjust the exposure to reduce light reflections. Step 2: The analysis unit analyzes the image captured by the photography unit. For example, the generation AI analyzes the text and diagrams in the image and extracts important points. The analysis unit can also use image processing technology to analyze handwritten notes and parts highlighted with a highlighter. For example, the analysis unit extracts the contents of handwritten notes as text and prioritizes the analysis of parts highlighted with a highlighter. Step 3: The question generation unit creates questions based on the content analyzed by the analysis unit. For example, the generation AI generates questions such as "What year did this event occur?" or "What was this person's role?" based on the analysis results. The question generation unit can also create questions in various formats, such as multiple-choice questions and written questions. For example, the question generation unit generates multiple-choice questions and written questions based on the analysis results. Step 4: When the learner answers the generated questions, the scoring unit scores the answer. For example, the generating AI judges whether the learner's answer is correct or incorrect and calculates a score. The scoring unit can also analyze the answering process and thought process and provide detailed feedback. For example, the scoring unit analyzes each step of the answer and provides feedback for each step. Step 5: The feedback unit provides feedback based on the answers graded by the grading unit. For example, the generation AI provides feedback on whether the answer was correct or incorrect and suggests the next learning step. The feedback unit can also adjust the content and tone of the feedback based on the learner's emotions using an emotion estimation function. For example, if the learner is feeling anxious, the feedback unit provides feedback that includes encouraging words.

[0084] 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.

[0085] 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.

[0086] 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.

[0087] [Second embodiment] FIG. 3 shows an example of the configuration of a data processing system 210 according to the second embodiment.

[0088] 3, the data processing system 210 includes a data processing device 12 and smart glasses 214. An example of the data processing device 12 is a server.

[0089] 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.

[0090] 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.

[0091] 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.

[0092] 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).

[0093] 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.

[0094] 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.

[0095] 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.

[0096] 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.

[0097] 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.

[0098] 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.

[0099] 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.

[0100] The data generation model 58 is a so-called generative AI. An example of the data generation model 58 is a generative AI such as ChatGPT. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 receives a prompt containing an instruction, as well as inference data such as voice data representing speech, text data representing text, and image data representing an image. The data generation model 58 performs inference on the input inference data in accordance with the instruction indicated by the prompt and outputs the inference result in a data format such as voice data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization. The identification processing unit 290 performs the above-mentioned identification processing using the data generation model 58. The data generation model 58 may be a fine-tuned model so as to output an inference result from a prompt that does not include an instruction. In this case, the data generation model 58 can output an inference result from a prompt that does not include an instruction. The data processing device 12 and the like include multiple types of data generation models 58, and the data generation model 58 includes AIs other than the generative AI. The AI ​​other than the generative AI may be, for example, linear regression, logistic regression, decision tree, random forest, support vector machine (SVM), k-means clustering, convolutional neural network (CNN), recurrent neural network (RNN), generative adversarial network (GAN), or naive Bayes, and can perform various processes, but is not limited to these examples. The AI ​​may also be an AI agent. When the processes of each of the above-mentioned parts are performed by AI, the processes may be performed in part or entirely by AI, but are not limited to these examples. The processes performed by AI, including the generative AI, may be replaced with rule-based processes.

[0101] 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.

[0102] [Third embodiment] FIG. 5 shows an example of the configuration of a data processing system 310 according to the third embodiment.

[0103] 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.

[0104] 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.

[0105] 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.

[0106] 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.

[0107] 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).

[0108] 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.

[0109] 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.

[0110] 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.

[0111] 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.

[0112] 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.

[0113] 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.

[0114] 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.

[0115] The data generation model 58 is a so-called generative AI. An example of the data generation model 58 is a generative AI such as ChatGPT. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 receives a prompt containing an instruction, as well as inference data such as voice data representing speech, text data representing text, and image data representing an image. The data generation model 58 performs inference on the input inference data in accordance with the instruction indicated by the prompt and outputs the inference result in a data format such as voice data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization. The identification processing unit 290 performs the above-mentioned identification processing using the data generation model 58. The data generation model 58 may be a fine-tuned model so as to output an inference result from a prompt that does not include an instruction. In this case, the data generation model 58 can output an inference result from a prompt that does not include an instruction. The data processing device 12 and the like include multiple types of data generation models 58, and the data generation model 58 includes AIs other than the generative AI. The AI ​​other than the generative AI may be, for example, linear regression, logistic regression, decision tree, random forest, support vector machine (SVM), k-means clustering, convolutional neural network (CNN), recurrent neural network (RNN), generative adversarial network (GAN), or naive Bayes, and can perform various processes, but is not limited to these examples. The AI ​​may also be an AI agent. When the processes of each of the above-mentioned parts are performed by AI, the processes may be performed in part or entirely by AI, but are not limited to these examples. The processes performed by AI, including the generative AI, may be replaced with rule-based processes.

[0116] 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.

[0117] [Fourth embodiment] FIG. 7 shows an example of the configuration of a data processing system 410 according to the fourth embodiment.

[0118] 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.

[0119] 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.

[0120] 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.

[0121] 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.

[0122] 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).

[0123] 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.

[0124] 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.

[0125] 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.

[0126] 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.

[0127] 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.

[0128] 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.

[0129] 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.

[0130] 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.

[0131] The data generation model 58 is a so-called generative AI. An example of the data generation model 58 is a generative AI such as ChatGPT. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 receives a prompt containing an instruction, as well as inference data such as voice data representing speech, text data representing text, and image data representing an image. The data generation model 58 performs inference on the input inference data in accordance with the instruction indicated by the prompt and outputs the inference result in a data format such as voice data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization. The identification processing unit 290 performs the above-mentioned identification processing using the data generation model 58. The data generation model 58 may be a fine-tuned model so as to output an inference result from a prompt that does not include an instruction. In this case, the data generation model 58 can output an inference result from a prompt that does not include an instruction. The data processing device 12 and the like include multiple types of data generation models 58, and the data generation model 58 includes AIs other than the generative AI. The AI ​​other than the generative AI may be, for example, linear regression, logistic regression, decision tree, random forest, support vector machine (SVM), k-means clustering, convolutional neural network (CNN), recurrent neural network (RNN), generative adversarial network (GAN), or naive Bayes, and can perform various processes, but is not limited to these examples. The AI ​​may also be an AI agent. When the processes of each of the above-mentioned parts are performed by AI, the processes may be performed in part or entirely by AI, but are not limited to these examples. The processes performed by AI, including the generative AI, may be replaced with rule-based processes.

[0132] 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.

[0133] 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.

[0134] 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.

[0135] 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.

[0136] 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).

[0137] 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.

[0138] 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."

[0139] 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.

[0140] 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.

[0141] 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.

[0142] 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.

[0143] 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.

[0144] 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.

[0145] 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.

[0146] 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.

[0147] 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.

[0148] 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.

[0149] 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.

[0150] 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]

[0151] 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 photography department that photographs specific parts of textbooks; an analysis unit that analyzes the image captured by the imaging unit; a question generation unit that generates questions based on the content analyzed by the analysis unit; a scoring unit that scores the answers of the learners who answer the generated questions; a feedback unit that provides feedback based on the answers graded by the grading unit. A system characterized by:

2. The analysis unit Analyzes handwritten notes and highlighted parts of the image and creates questions that reflect the learner's focus 2. The system of claim 1.

3. The analysis unit Analyze the font and layout of the image and prioritize extraction of important information.

2. The system of claim 1.

4. The analysis unit Analyze the emotions felt by the learner when taking the photo and adjust the difficulty and content of the questions based on those emotions.

2. The system of claim 1.

5. The analysis unit Accepts voice input and analyzes the content of the learner's verbal explanation.

2. The system of claim 1.

6. The analysis unit Integrate content from multiple textbooks and reference books to create more comprehensive questions 2. The system of claim 1.

Images