System

Abstract

An object of a system according to an embodiment is to efficiently generate new questions and review past questions in an examination study.SOLUTION: A system includes a collection part, a generation part, a provision part, an evaluation part, an adjustment part, and a review part. The collection section collects textbook data or past question data. The generation unit analyzes the data collected by the collection unit and generates a new problem. The providing unit provides the question generated by the generating unit. The evaluation unit evaluates the quality of the question provided by the provision unit. The adjustment unit adjusts the problem on the basis of a result evaluated by the evaluation unit. The review unit generates review questions based on the past question data collected by the collection 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 technologies do not efficiently generate new questions or review past questions when studying for exams, so there is room for improvement.

[0005] The system according to the embodiment aims to efficiently generate new questions and review past questions when studying for an exam. [Means for solving the problem]

[0006] The system according to the embodiment includes a collection unit, a generation unit, a provision unit, an evaluation unit, an adjustment unit, and a review unit. The collection unit collects textbook data or past exam data. The generation unit analyzes the data collected by the collection unit and generates new questions. The provision unit provides the questions generated by the generation unit. The evaluation unit evaluates the quality of the questions provided by the provision unit. The adjustment unit adjusts the questions based on the results of the evaluation by the evaluation unit. The review unit generates review questions based on the past exam data collected by the collection unit. [Effects of the Invention]

[0007] The system according to the embodiment can efficiently generate new questions and review past questions when studying for exams. [Brief explanation of the drawings]

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

[0028] (Example 1) A learning support system according to an embodiment of the present invention uses a generation AI to analyze textbook data and past exam data, thoroughly creating new questions and reviewing past exam questions. The learning support system collects textbook data and past exam data, and the generation AI analyzes this data to generate new questions and provide them to users. The system also generates review questions based on the past exam data, evaluates the quality of the generated questions, and adjusts the difficulty and content of the questions based on the evaluation results. For example, the learning support system collects textbook content and past exam questions as digital data. Next, the generation AI analyzes the collected data to generate new practice questions. The generated questions are provided to users via an online platform, and the users input their answers. The system then evaluates the quality of the generated questions and adjusts the questions based on the evaluation results. Finally, the system generates review questions based on past exam data, and the users review the questions by answering them. This allows the learning support system to improve basic skills and build confidence through repeated practice. This allows the learning support system to improve basic skills and build confidence through repeated practice. For example, in math arithmetic or social studies memorization subjects, the AI ​​can generate new questions and users can answer them to hone their basic skills. Additionally, by answering review questions based on past exam data, users can review past questions and deepen their understanding.

[0029] A learning support system according to an embodiment includes a collection unit, a generation unit, a provision unit, an evaluation unit, an adjustment unit, and a review unit. The collection unit collects textbook data or past exam data. The collection unit, for example, collects textbook content and past exam questions as digital data. The generation unit uses a generation AI to analyze the data collected by the collection unit and generate new questions. The generation unit, for example, generates new practice questions based on the content of a textbook. The generation unit can also analyze patterns of past exam questions to generate similar questions. The provision unit provides the questions generated by the generation unit to a user. The provision unit, for example, provides the questions through an online platform, and the user inputs their answers. The evaluation unit evaluates the quality of the generated questions. For example, the evaluation unit evaluates whether the difficulty and content of the generated questions are appropriate. The adjustment unit adjusts the questions based on the results of the evaluation by the evaluation unit. For example, if a question is too difficult, the adjustment unit adjusts it to be easier. The review unit generates review questions based on the past exam data collected by the collection unit. The review unit generates review questions based on past exam questions, for example, and the user reviews the questions by answering them. This allows the learning support system according to the embodiment to improve the user's basic skills.

[0030] The collection unit can collect textbook contents or past test questions as digital data. Examples of digital data include, but are not limited to, PDF format, text format, and image format. For example, the collection unit can scan textbook contents and collect them as digital data. The collection unit can also collect past test questions as digital data. For example, the collection unit can scan past test questions and save them as digital data. This allows for efficient data collection by collecting textbook contents and past test questions as digital data.

[0031] The generation unit can generate new exercises based on the content of the textbook. The generation unit generates new exercises based on, for example, the content of the textbook. For example, the generation unit analyzes the content of the textbook and generates new exercises based on that content. The generation unit can also generate exercises of different difficulty levels based on the content of the textbook. For example, the generation unit generates beginner, intermediate, and advanced exercises based on the content of the textbook. In this way, by generating new exercises based on the content of the textbook, the user's learning effect can be improved.

[0032] The generation unit can analyze the pattern of past exam questions and generate similar questions. The generation unit, for example, analyzes the pattern of past exam questions and generates similar questions. For example, the generation unit analyzes the pattern of past exam questions and generates similar questions based on the pattern. The generation unit can also analyze the pattern of past exam questions and generate questions in different formats. For example, the generation unit generates questions in different formats, such as multiple choice, written, and fill-in-the-blank, based on the pattern of past exam questions. In this way, by analyzing the pattern of past exam questions and generating similar questions, the effectiveness of user review can be improved.

[0033] The providing unit provides questions through an online platform, and users can input answers. The providing unit, for example, provides questions through an online platform, and users can input answers. For example, the providing unit can provide questions through a website or a mobile app, and users can input answers. The providing unit can also provide questions in real time through the online platform. For example, the providing unit can provide questions in the form of an online test, and users can input answers in real time. This improves learning convenience by providing questions through an online platform and users can input answers.

[0034] The evaluation unit can evaluate whether the difficulty level and content of the generated questions are appropriate. The evaluation unit, for example, evaluates whether the difficulty level and content of the generated questions are appropriate. For example, the evaluation unit evaluates whether the difficulty level of the generated questions is appropriate. The evaluation unit can also evaluate whether the content of the generated questions is appropriate. For example, the evaluation unit evaluates whether the content of the generated questions matches the content of the textbook. In this way, by evaluating whether the difficulty level and content of the generated questions are appropriate, the quality of the questions can be ensured.

[0035] The adjustment unit can adjust the questions based on the evaluation results. The adjustment unit, for example, adjusts the questions based on the evaluation results. For example, the adjustment unit adjusts the difficulty of the questions based on the evaluation results. The adjustment unit can also adjust the content of the questions based on the evaluation results. For example, the adjustment unit modifies the content of the questions based on the evaluation results. In this way, by adjusting the questions based on the evaluation results, the difficulty and content of the questions can be maintained appropriately.

[0036] The review unit can generate review questions based on past exam questions. The review unit, for example, generates review questions based on past exam questions. For example, the review unit analyzes past exam questions and generates review questions based on the content of the questions. The review unit can also generate review questions in different formats based on past exam questions. For example, the review unit generates review questions in different formats, such as multiple choice, essay, and fill-in-the-blank, based on past exam questions. In this way, generating review questions based on past exam questions can improve the effectiveness of the user's review.

[0037] When collecting data from textbooks and past exam questions, the collection unit can adjust the collection range based on the user's learning progress. For example, if the user is studying a specific chapter, the collection unit will prioritize collecting data related to that chapter. In addition, if the user's overall learning progress is slow, the collection unit can also collect more data on basic content. Furthermore, if the user's progress is fast, the collection unit can also collect data on applied questions and advanced content. This allows for efficient data collection by adjusting the collection range based on the user's learning progress. Some or all of the above-mentioned processing in the collection unit may be performed using AI, for example, or may be performed without using AI.

[0038] When collecting data, the collection unit can select the optimal data source by referring to the user's learning history. The collection unit, for example, prioritizes collecting data from textbooks and problem sets that the user has used in the past. The collection unit can also collect a large amount of data in areas in which the user is strong, and also collect data in areas in which the user is weak in a balanced manner. Furthermore, the collection unit can prioritize collecting textbook data from specific publishers based on the user's learning history. This enables efficient data collection by selecting the optimal data source by referring to the user's learning history. Some or all of the above-mentioned processing in the collection unit may be performed, for example, using AI, or may be performed without using AI.

[0039] When collecting data, the collection unit can customize the collection method according to the user's learning style. For example, the collection unit collects textbook data with many charts and illustrations for visual learners. The collection unit can also collect data with audio commentary for auditory learners. Furthermore, the collection unit can collect interactive question set data for tactile learners. This enables efficient data collection by customizing the collection method according to the user's learning style. Some or all of the above-mentioned processing in the collection unit may be performed using, for example, AI, or may be performed without using AI.

[0040] When collecting data, the collection unit can prioritize collecting highly relevant data by taking into account the user's geographical location information. For example, when the user is in a specific area, the collection unit collects data based on the educational curriculum of that area. Furthermore, when the user is traveling, the collection unit can also collect data related to the area to which the user is traveling. Furthermore, when the user is at home, the collection unit can also collect data suitable for home learning. This enables efficient data collection by prioritizing the collection of highly relevant data by taking into account the user's geographical location information. Some or all of the above-mentioned processing in the collection unit may be performed, for example, using AI or without using AI.

[0041] When collecting data, the collection unit can analyze the user's social media activities and collect related data. The collection unit, for example, collects data based on learning content shared by the user on social media. The collection unit can also collect related data by referring to the activities of the user's followers on social media. Furthermore, the collection unit can collect data related to topics in which the user has shown interest on social media. This enables efficient data collection by analyzing the user's social media activities and collecting related data. Some or all of the above-mentioned processing in the collection unit may be performed, for example, using AI, or may be performed without using AI.

[0042] When collecting data, the collection unit can customize the collection method by reflecting the user's past feedback. For example, the collection unit prioritizes collection of data sources that the user has previously rated highly. The collection unit can also avoid collecting data sources that the user has previously rated poorly. Furthermore, the collection unit can adjust the type and format of data to be collected based on the user's feedback. This enables efficient data collection by customizing the collection method by reflecting the user's past feedback. Some or all of the above-mentioned processing in the collection unit may be performed, for example, using AI or without using AI.

[0043] When generating questions, the generation unit can adjust the level of detail of the questions based on the importance of the content of the textbook. For example, the generation unit may include detailed explanations and supplementary information for questions based on important content. The generation unit may also generate questions based on less important content in a concise format. Furthermore, the generation unit may adjust the level of detail of the questions according to the importance of each chapter of the textbook. This allows for efficient question generation by adjusting the level of detail of the questions based on the importance of the content of the textbook. Some or all of the above-described processing in the generation unit may be performed, for example, using AI or without using AI.

[0044] The generation unit can apply different generation algorithms depending on the textbook category when generating questions. For example, the generation unit applies a mathematical expression analysis algorithm to generate mathematics questions. The generation unit can also apply a text analysis algorithm to generate social studies questions. The generation unit can also apply an experimental data analysis algorithm to generate science questions. This allows for efficient question generation by applying different generation algorithms depending on the textbook category. Some or all of the above-mentioned processing in the generation unit may be performed using, for example, AI, or may be performed without using AI.

[0045] When generating questions, the generation unit can improve the accuracy of the questions by referring to the user's past answers. The generation unit, for example, analyzes patterns of questions that the user has answered incorrectly in the past and generates similar questions. The generation unit can also reduce the number of questions in areas in which the user is good and generate more questions in areas in which the user is weak. Furthermore, the generation unit can adjust the difficulty of the questions based on the user's answers. In this way, by referring to the user's past answers and improving the accuracy of the questions, it is possible to provide questions that are suitable for the user. Some or all of the above-mentioned processing in the generation unit may be performed, for example, using AI, or may be performed without using AI.

[0046] When generating questions, the generation unit can determine the priority of questions based on the publication date of the textbook. For example, the generation unit generates questions based on the latest textbook with priority. The generation unit can also generate questions based on older textbooks as needed. Furthermore, the generation unit can determine the priority of questions taking into account the revision history of the textbook. In this way, by determining the priority of questions based on the publication date of the textbook, questions based on the latest information can be provided. Some or all of the above-mentioned processing in the generation unit may be performed, for example, using AI, or may be performed without using AI.

[0047] When generating questions, the generation unit can adjust the order of questions based on the relevance of the textbook. The generation unit determines the order of questions, for example, taking into account the relevance of each chapter in the textbook. Furthermore, if the contents of the textbook are continuous, the generation unit can also generate related questions consecutively. Furthermore, if the contents of the textbook are independent, the generation unit can also randomly generate the order of questions. This enables efficient learning by adjusting the order of questions based on the relevance of the textbook. Some or all of the above-mentioned processing in the generation unit may be performed, for example, using AI, or may be performed without using AI.

[0048] When generating questions, the generation unit can adjust the use of technical terminology in the questions according to the user's level of expertise. For example, the generation unit generates questions using simple language with less technical terminology for beginners. The generation unit can also generate questions using appropriate technical terminology for intermediate learners. Furthermore, the generation unit can generate questions with a high level of difficulty using a lot of technical terminology for advanced learners. In this way, by adjusting the use of technical terminology in the questions according to the user's level of expertise, it is possible to provide questions that are suitable for the user. Some or all of the above-mentioned processing in the generation unit may be performed, for example, using AI, or may be performed without using AI.

[0049] When providing questions, the providing unit can adjust the difficulty of the questions to be provided based on the user's learning progress. For example, if the user's learning progress is slow, the providing unit can provide many basic questions. Also, if the user's learning progress is fast, the providing unit can provide many applied questions and advanced questions. Furthermore, the providing unit can gradually adjust the difficulty of the questions according to the user's learning progress. This enables efficient learning by adjusting the difficulty of the questions to be provided based on the user's learning progress. Some or all of the above-mentioned processing in the providing unit may be performed, for example, using AI, or may be performed without using AI.

[0050] When providing questions, the providing unit can select the optimal timing for providing the questions by referring to the user's learning history. The providing unit, for example, provides new questions at the optimal timing based on the history of questions previously answered by the user. Furthermore, if the user has a habit of studying during a specific time period, the providing unit can also provide questions during that time period. Furthermore, the providing unit can also provide questions during times when the user is most likely to concentrate, based on the user's learning history. This enables efficient learning by selecting the optimal timing for providing questions by referring to the user's learning history. Some or all of the above-described processing by the providing unit may be performed, for example, using AI, or may be performed without using AI.

[0051] When providing questions, the providing unit can customize the method of providing questions according to the user's learning style. For example, the providing unit can provide questions that make extensive use of diagrams and illustrations to visual learners. The providing unit can also provide questions with audio commentary to auditory learners. Furthermore, the providing unit can also provide interactive questions to tactile learners. This enables efficient learning by customizing the method of providing questions according to the user's learning style. Some or all of the above-mentioned processing in the providing unit may be performed, for example, using AI, or may be performed without using AI.

[0052] When providing questions, the providing unit can prioritize providing highly relevant questions by taking into account the user's geographical location information. For example, if the user is in a specific area, the providing unit can provide questions based on the educational curriculum of that area. Furthermore, if the user is traveling, the providing unit can also provide questions related to the area to which the user is traveling. Furthermore, if the user is at home, the providing unit can also provide questions suitable for home study. This enables efficient learning by prioritizing the provision of highly relevant questions by taking into account the user's geographical location information. Some or all of the above-mentioned processing by the providing unit may be performed, for example, using AI or without using AI.

[0053] When providing questions, the providing unit can analyze the user's social media activity and provide related questions. The providing unit can provide questions based on, for example, learning content shared by the user on social media. The providing unit can also provide related questions by referring to the activity of the user's followers on social media. Furthermore, the providing unit can provide questions related to topics in which the user has shown interest on social media. This enables efficient learning by analyzing the user's social media activity and providing related questions. Some or all of the above-mentioned processing by the providing unit can be performed, for example, using AI, or can be performed without using AI.

[0054] When providing questions, the providing unit can customize the method of providing questions by reflecting the user's past feedback. For example, the providing unit can prioritize providing question formats that the user has previously rated highly. The providing unit can also avoid providing question formats that the user has previously rated poorly. Furthermore, the providing unit can adjust the type and format of questions to be provided based on the user's feedback. This enables efficient learning by customizing the method of providing questions by reflecting the user's past feedback. Some or all of the above-mentioned processing in the providing unit may be performed, for example, using AI or without using AI.

[0055] The evaluation unit can improve the accuracy of the evaluation by referring to the user's answer history when evaluating questions. The evaluation unit improves the accuracy of the evaluation, for example, based on the history of questions that the user has previously answered. The evaluation unit can also analyze specific patterns from the user's answer history and adjust the evaluation criteria. Furthermore, the evaluation unit can analyze the user's answer history and apply individual evaluation criteria. This allows for efficient evaluation by improving the accuracy of the evaluation by referring to the user's answer history. Some or all of the above-mentioned processing in the evaluation unit may be performed, for example, using AI or without using AI.

[0056] The evaluation unit can customize the evaluation criteria based on the user's learning progress when evaluating questions. For example, if the user's learning progress is slow, the evaluation unit can apply lenient evaluation criteria. Alternatively, if the user's learning progress is fast, the evaluation unit can apply strict evaluation criteria. Furthermore, the evaluation unit can gradually adjust the evaluation criteria according to the user's learning progress. This enables efficient evaluation by customizing the evaluation criteria based on the user's learning progress. Some or all of the above-mentioned processing in the evaluation unit may be performed, for example, using AI or without using AI.

[0057] The evaluation unit can adjust the evaluation method according to the user's learning style when evaluating questions. For example, the evaluation unit can apply an evaluation method that includes a lot of visual feedback to a visual learner. The evaluation unit can also apply an evaluation method that includes a lot of audio feedback to an auditory learner. Furthermore, the evaluation unit can also apply an evaluation method that includes a lot of interactive feedback to a tactile learner. This allows for efficient evaluation by adjusting the evaluation method according to the user's learning style. Some or all of the above-mentioned processing in the evaluation unit can be performed, for example, using AI or without using AI.

[0058] The evaluation unit can adjust the evaluation criteria when evaluating questions, taking into account the user's geographical location information. For example, if the user is in a specific area, the evaluation unit applies evaluation criteria based on the educational curriculum of that area. Furthermore, if the user is traveling, the evaluation unit can apply evaluation criteria related to the area to which the user is traveling. Furthermore, if the user is at home, the evaluation unit can apply evaluation criteria suitable for home learning. This allows for efficient evaluation by adjusting the evaluation criteria taking into account the user's geographical location information. Some or all of the above-mentioned processing in the evaluation unit may be performed, for example, using AI or without using AI.

[0059] The evaluation unit can analyze the user's social media activity when evaluating questions to improve the accuracy of the evaluation. The evaluation unit, for example, performs evaluation based on the learning content shared by the user on social media. The evaluation unit can also perform evaluation based on the activity of the user's followers on social media. Furthermore, the evaluation unit can perform evaluation related to topics in which the user has shown interest on social media. This allows for efficient evaluation by analyzing the user's social media activity and improving the accuracy of the evaluation. Some or all of the above-mentioned processing in the evaluation unit may be performed using, for example, AI, or may be performed without using AI.

[0060] The evaluation unit can customize the evaluation criteria by reflecting the user's past feedback when evaluating a problem. For example, the evaluation unit preferentially applies evaluation criteria that the user has previously given a high rating to. The evaluation unit can also avoid applying evaluation criteria that the user has previously given a low rating to. Furthermore, the evaluation unit can adjust the evaluation criteria based on the user's feedback. This enables efficient evaluation by customizing the evaluation criteria by reflecting the user's past feedback. Some or all of the above-mentioned processing in the evaluation unit may be performed, for example, using AI or without using AI.

[0061] When adjusting questions, the adjustment unit can improve the accuracy of the adjustment by referring to the user's answer history. The adjustment unit improves the accuracy of the adjustment, for example, based on the history of questions that the user has previously answered. The adjustment unit can also analyze specific patterns from the user's answer history and adjust the adjustment criteria. Furthermore, the adjustment unit can analyze the user's answer history and apply individual adjustment criteria. This enables efficient adjustment by improving the accuracy of the adjustment by referring to the user's answer history. Some or all of the above-mentioned processing in the adjustment unit may be performed, for example, using AI or without using AI.

[0062] The adjustment unit can customize the adjustment criteria based on the user's learning progress when adjusting the questions. For example, the adjustment unit applies lenient adjustment criteria when the user's learning progress is slow. The adjustment unit can also apply strict adjustment criteria when the user's learning progress is fast. Furthermore, the adjustment unit can gradually adjust the adjustment criteria according to the user's learning progress. This enables efficient adjustment by customizing the adjustment criteria based on the user's learning progress. Some or all of the above-mentioned processing in the adjustment unit may be performed using, for example, AI, or may be performed without using AI.

[0063] The adjustment unit can adjust the adjustment method according to the user's learning style when adjusting questions. For example, the adjustment unit applies an adjustment method that includes a lot of visual feedback to a visual learner. The adjustment unit can also apply an adjustment method that includes a lot of audio feedback to an auditory learner. Furthermore, the adjustment unit can also apply an adjustment method that includes a lot of interactive feedback to a tactile learner. This enables efficient adjustment by adjusting the adjustment method according to the user's learning style. Some or all of the above-mentioned processing in the adjustment unit may be performed using AI, for example, or may be performed without using AI.

[0064] The adjustment unit can adjust the adjustment criteria taking into account the user's geographical location information when adjusting the questions. For example, if the user is in a specific area, the adjustment unit applies adjustment criteria based on the educational curriculum of that area. Furthermore, if the user is traveling, the adjustment unit can also apply adjustment criteria related to the area to which the user is traveling. Furthermore, if the user is at home, the adjustment unit can also apply adjustment criteria suitable for home learning. In this way, adjusting the adjustment criteria taking into account the user's geographical location information enables efficient adjustment. Some or all of the above-mentioned processing in the adjustment unit may be performed using AI, for example, or may be performed without using AI.

[0065] When adjusting questions, the adjustment unit can analyze the user's social media activity and improve the accuracy of the adjustment. The adjustment unit makes the adjustment based on, for example, learning content shared by the user on social media. The adjustment unit can also make the adjustment based on the activity of the user's followers on social media. Furthermore, the adjustment unit can make the adjustment related to topics in which the user has shown interest on social media. In this way, analyzing the user's social media activity and improving the accuracy of the adjustment enables efficient adjustment. Some or all of the above-mentioned processing in the adjustment unit may be performed, for example, using AI, or may be performed without using AI.

[0066] When adjusting a problem, the adjustment unit can customize the adjustment criteria by reflecting the user's past feedback. For example, the adjustment unit preferentially applies adjustment criteria that the user has previously rated highly. The adjustment unit can also avoid applying adjustment criteria that the user has previously rated poorly. Furthermore, the adjustment unit can adjust the adjustment criteria based on the user's feedback. This enables efficient adjustment by customizing the adjustment criteria by reflecting the user's past feedback. Some or all of the above-described processing in the adjustment unit may be performed, for example, using AI or without using AI.

[0067] When generating review questions, the review unit can improve the accuracy of the generation by referring to the user's answer history. The review unit, for example, analyzes patterns of questions that the user has answered incorrectly in the past and generates similar review questions. The review unit can also generate fewer review questions for areas in which the user is strong and more review questions for areas in which the user is weak. Furthermore, the review unit can adjust the difficulty of the review questions based on the user's answer history. This allows for efficient review by improving the accuracy of generation by referring to the user's answer history. Some or all of the above-mentioned processing in the review unit may be performed, for example, using AI or without using AI.

[0068] When generating review questions, the review unit can customize the generation criteria based on the user's learning progress. For example, if the user's learning progress is slow, the review unit generates many basic review questions. Also, if the user's learning progress is fast, the review unit can generate many applied and advanced review questions. Furthermore, the review unit can gradually adjust the difficulty of the review questions according to the user's learning progress. This allows for efficient review by customizing the generation criteria based on the user's learning progress. Some or all of the above-mentioned processing in the review unit may be performed, for example, using AI or without using AI.

[0069] When generating review questions, the review unit can adjust the generation method according to the user's learning style. For example, for visual learners, the review unit generates review questions that make extensive use of charts and illustrations. The review unit can also generate review questions with audio commentary for auditory learners. Furthermore, the review unit can also generate interactive review questions for tactile learners. This allows for efficient review by adjusting the generation method according to the user's learning style. Some or all of the above-mentioned processing in the review unit may be performed, for example, using AI or without using AI.

[0070] When generating review questions, the review unit can prioritize generating highly relevant questions by taking into account the user's geographical location information. For example, if the user is in a specific area, the review unit can generate review questions based on the educational curriculum of that area. Furthermore, if the user is traveling, the review unit can also generate review questions related to the area to which the user is traveling. Furthermore, if the user is at home, the review unit can also generate review questions suitable for home study. This enables efficient review by prioritizing the generation of highly relevant questions by taking into account the user's geographical location information. Some or all of the above-mentioned processing in the review unit may be performed, for example, using AI or without using AI.

[0071] When generating review questions, the review unit can analyze the user's social media activity and generate related questions. The review unit can generate review questions based on, for example, the learning content shared by the user on social media. The review unit can also generate related review questions by referring to the activity of the user's followers on social media. Furthermore, the review unit can generate review questions related to topics in which the user has shown interest on social media. This enables efficient review by analyzing the user's social media activity and generating related questions. Some or all of the above-mentioned processing in the review unit can be performed, for example, using AI, or can be performed without using AI.

[0072] When generating review questions, the review unit can customize the generation method by reflecting the user's past feedback. For example, the review unit prioritizes the generation of review question formats that the user has previously rated highly. The review unit can also generate review question formats that the user has previously rated poorly, avoiding them. Furthermore, the review unit can adjust the type and format of the review questions to be generated based on the user's feedback. This allows for efficient review by customizing the generation method by reflecting the user's past feedback. Some or all of the above-mentioned processing in the review unit may be performed, for example, using AI, or may be performed without using AI.

[0073] The system according to the embodiment is not limited to the above-described example, and various modifications are possible, for example, as follows.

[0074] The collection unit can select the optimal data source by referring to the user's learning history. For example, it can prioritize collection of data on textbooks and workbooks that the user has used in the past. The collection unit can also collect a lot of data on areas in which the user is strong, and collect data on areas in which the user is weak in a balanced manner. Furthermore, the collection unit can prioritize collection of textbook data from specific publishers based on the user's learning history. This allows for efficient data collection by selecting the optimal data source by referring to the user's learning history.

[0075] When collecting data, the collection unit can customize the collection method according to the user's learning style. For example, for visual learners, textbook data with many charts and illustrations can be collected. The collection unit can also collect data with audio commentary for auditory learners. Furthermore, the collection unit can collect interactive question set data for tactile learners. This allows for efficient data collection by customizing the collection method according to the user's learning style.

[0076] When generating questions, the generator can adjust the level of detail of the questions based on the importance of the content of the textbook. For example, questions based on important content include detailed explanations and supplementary information. The generator can also generate questions based on less important content in a concise format. Furthermore, the generator can adjust the level of detail of the questions according to the importance of each chapter in the textbook. This allows for efficient question generation by adjusting the level of detail of the questions based on the importance of the content of the textbook.

[0077] When providing questions, the providing unit can adjust the difficulty of the questions to be provided based on the user's learning progress. For example, if the user's learning progress is slow, the providing unit can provide many basic questions. In addition, if the user's learning progress is fast, the providing unit can also provide many applied and advanced questions. Furthermore, the providing unit can gradually adjust the difficulty of the questions according to the user's learning progress. This allows for efficient learning by adjusting the difficulty of the questions to be provided based on the user's learning progress.

[0078] The evaluation unit can improve the accuracy of the evaluation by referring to the user's answer history when evaluating questions. For example, the evaluation unit can improve the accuracy of the evaluation based on the history of questions that the user has previously answered. The evaluation unit can also analyze specific patterns from the user's answer history and adjust the evaluation criteria. Furthermore, the evaluation unit can analyze the user's answer history and apply individual evaluation criteria. This allows for efficient evaluation by improving the accuracy of the evaluation by referring to the user's answer history.

[0079] When generating review questions, the review unit can refer to the user's answer history to improve the accuracy of the generation. For example, it can analyze patterns of questions that the user has answered incorrectly in the past and generate similar review questions. The review unit can also generate fewer review questions for areas in which the user is strong and more review questions for areas in which the user is weak. Furthermore, the review unit can adjust the difficulty level of the review questions based on the user's answer history. This allows for efficient review by improving the accuracy of generation by referring to the user's answer history.

[0080] The processing flow of the first embodiment will be briefly explained below.

[0081] Step 1: The collection unit collects textbook data or past exam data. The collection unit collects, for example, the contents of textbooks or past exam questions as digital data. Step 2: The generator uses a generation AI to analyze the data collected by the collector and generate new questions. For example, the generator generates new practice questions based on the content of a textbook. The generator can also analyze the patterns of past questions to generate similar questions. Step 3: The providing unit provides the questions generated by the generating unit to the user. The providing unit provides the questions via, for example, an online platform, and the user inputs the answers. Step 4: The evaluation unit evaluates the quality of the generated questions. For example, the evaluation unit evaluates whether the difficulty level and content of the generated questions are appropriate. Step 5: The adjustment unit adjusts the questions based on the results of the evaluation by the evaluation unit. For example, if the difficulty level of a question is too high, the adjustment unit adjusts the question to make it easier. Step 6: The review unit generates review questions based on the past exam data collected by the collection unit. For example, the review unit generates review questions based on past exam questions, and the user reviews by answering them.

[0082] (Example 2) A learning support system according to an embodiment of the present invention uses a generation AI to analyze textbook data and past exam data, thoroughly creating new questions and reviewing past exam questions. The learning support system collects textbook data and past exam data, and the generation AI analyzes this data to generate new questions and provide them to users. The system also generates review questions based on the past exam data, evaluates the quality of the generated questions, and adjusts the difficulty and content of the questions based on the evaluation results. For example, the learning support system collects textbook content and past exam questions as digital data. Next, the generation AI analyzes the collected data to generate new practice questions. The generated questions are provided to users via an online platform, and the users input their answers. The system then evaluates the quality of the generated questions and adjusts the questions based on the evaluation results. Finally, the system generates review questions based on past exam data, and the users review the questions by answering them. This allows the learning support system to improve basic skills and build confidence through repeated practice. This allows the learning support system to improve basic skills and build confidence through repeated practice. For example, in math arithmetic or social studies memorization subjects, the AI ​​can generate new questions and users can answer them to hone their basic skills. Additionally, by answering review questions based on past exam data, users can review past questions and deepen their understanding.

[0083] A learning support system according to an embodiment includes a collection unit, a generation unit, a provision unit, an evaluation unit, an adjustment unit, and a review unit. The collection unit collects textbook data or past exam data. The collection unit, for example, collects textbook content and past exam questions as digital data. The generation unit uses a generation AI to analyze the data collected by the collection unit and generate new questions. The generation unit, for example, generates new practice questions based on the content of a textbook. The generation unit can also analyze patterns of past exam questions to generate similar questions. The provision unit provides the questions generated by the generation unit to a user. The provision unit, for example, provides the questions through an online platform, and the user inputs their answers. The evaluation unit evaluates the quality of the generated questions. For example, the evaluation unit evaluates whether the difficulty and content of the generated questions are appropriate. The adjustment unit adjusts the questions based on the results of the evaluation by the evaluation unit. For example, if a question is too difficult, the adjustment unit adjusts it to be easier. The review unit generates review questions based on the past exam data collected by the collection unit. The review unit generates review questions based on past exam questions, for example, and the user reviews the questions by answering them. This allows the learning support system according to the embodiment to improve the user's basic skills.

[0084] The collection unit can collect textbook contents or past test questions as digital data. Examples of digital data include, but are not limited to, PDF format, text format, and image format. For example, the collection unit can scan textbook contents and collect them as digital data. The collection unit can also collect past test questions as digital data. For example, the collection unit can scan past test questions and save them as digital data. This allows for efficient data collection by collecting textbook contents and past test questions as digital data.

[0085] The generation unit can generate new exercises based on the content of the textbook. The generation unit generates new exercises based on, for example, the content of the textbook. For example, the generation unit analyzes the content of the textbook and generates new exercises based on that content. The generation unit can also generate exercises of different difficulty levels based on the content of the textbook. For example, the generation unit generates beginner, intermediate, and advanced exercises based on the content of the textbook. In this way, by generating new exercises based on the content of the textbook, the user's learning effect can be improved.

[0086] The generation unit can analyze the pattern of past exam questions and generate similar questions. The generation unit, for example, analyzes the pattern of past exam questions and generates similar questions. For example, the generation unit analyzes the pattern of past exam questions and generates similar questions based on the pattern. The generation unit can also analyze the pattern of past exam questions and generate questions in different formats. For example, the generation unit generates questions in different formats, such as multiple choice, written, and fill-in-the-blank, based on the pattern of past exam questions. In this way, by analyzing the pattern of past exam questions and generating similar questions, the effectiveness of user review can be improved.

[0087] The providing unit provides questions through an online platform, and users can input answers. The providing unit, for example, provides questions through an online platform, and users can input answers. For example, the providing unit can provide questions through a website or a mobile app, and users can input answers. The providing unit can also provide questions in real time through the online platform. For example, the providing unit can provide questions in the form of an online test, and users can input answers in real time. This improves learning convenience by providing questions through an online platform and users can input answers.

[0088] The evaluation unit can evaluate whether the difficulty level and content of the generated questions are appropriate. The evaluation unit, for example, evaluates whether the difficulty level and content of the generated questions are appropriate. For example, the evaluation unit evaluates whether the difficulty level of the generated questions is appropriate. The evaluation unit can also evaluate whether the content of the generated questions is appropriate. For example, the evaluation unit evaluates whether the content of the generated questions matches the content of the textbook. In this way, by evaluating whether the difficulty level and content of the generated questions are appropriate, the quality of the questions can be ensured.

[0089] The adjustment unit can adjust the questions based on the evaluation results. The adjustment unit, for example, adjusts the questions based on the evaluation results. For example, the adjustment unit adjusts the difficulty of the questions based on the evaluation results. The adjustment unit can also adjust the content of the questions based on the evaluation results. For example, the adjustment unit modifies the content of the questions based on the evaluation results. In this way, by adjusting the questions based on the evaluation results, the difficulty and content of the questions can be maintained appropriately.

[0090] The review unit can generate review questions based on past exam questions. The review unit, for example, generates review questions based on past exam questions. For example, the review unit analyzes past exam questions and generates review questions based on the content of the questions. The review unit can also generate review questions in different formats based on past exam questions. For example, the review unit generates review questions in different formats, such as multiple choice, essay, and fill-in-the-blank, based on past exam questions. In this way, generating review questions based on past exam questions can improve the effectiveness of the user's review.

[0091] The collection unit can estimate the user's emotions and adjust the timing of data collection based on the estimated user emotions. For example, if the user is feeling stressed, the collection unit can reduce the frequency of data collection and collect data when the user is relaxed. The collection unit can also increase the frequency of data collection when the user is concentrating, thereby efficiently collecting data. Furthermore, if the user is tired, the collection unit can temporarily stop data collection and resume it after the user has rested. This allows the user's burden to be reduced by adjusting the timing of data collection based on the user's emotions. Emotion estimation is achieved using an emotion estimation function, for example, using an emotion engine or a generation AI. The generation AI can be, but is not limited to, a text generation AI (e.g., LLM) or a multimodal generation AI.

[0092] When collecting data from textbooks and past exam questions, the collection unit can adjust the collection range based on the user's learning progress. For example, if the user is studying a specific chapter, the collection unit will prioritize collecting data related to that chapter. In addition, if the user's overall learning progress is slow, the collection unit can also collect more data on basic content. Furthermore, if the user's progress is fast, the collection unit can also collect data on applied questions and advanced content. This allows for efficient data collection by adjusting the collection range based on the user's learning progress. Some or all of the above-mentioned processing in the collection unit may be performed using AI, for example, or may be performed without using AI.

[0093] When collecting data, the collection unit can select the optimal data source by referring to the user's learning history. The collection unit, for example, prioritizes collecting data from textbooks and problem sets that the user has used in the past. The collection unit can also collect a large amount of data in areas in which the user is strong, and also collect data in areas in which the user is weak in a balanced manner. Furthermore, the collection unit can prioritize collecting textbook data from specific publishers based on the user's learning history. This enables efficient data collection by selecting the optimal data source by referring to the user's learning history. Some or all of the above-mentioned processing in the collection unit may be performed, for example, using AI, or may be performed without using AI.

[0094] When collecting data, the collection unit can customize the collection method according to the user's learning style. For example, the collection unit collects textbook data with many charts and illustrations for visual learners. The collection unit can also collect data with audio commentary for auditory learners. Furthermore, the collection unit can collect interactive question set data for tactile learners. This enables efficient data collection by customizing the collection method according to the user's learning style. Some or all of the above-mentioned processing in the collection unit may be performed using, for example, AI, or may be performed without using AI.

[0095] The collection unit can estimate the user's emotions and determine the priority of data to be collected based on the estimated user emotions. For example, when the user is feeling stressed, the collection unit can prioritize collecting data with easy questions or relaxing content. Furthermore, when the user is concentrating, the collection unit can prioritize collecting data with difficult questions or challenging content. Furthermore, when the user is tired, the collection unit can prioritize collecting data for review or basic content. This enables efficient data collection by determining the priority of data to be collected based on the user's emotions. Emotion estimation is achieved using an emotion estimation function, for example, using an emotion engine or a generation AI. The generation AI can be, but is not limited to, a text generation AI (e.g., LLM) or a multimodal generation AI.

[0096] When collecting data, the collection unit can prioritize collecting highly relevant data by taking into account the user's geographical location information. For example, when the user is in a specific area, the collection unit collects data based on the educational curriculum of that area. Furthermore, when the user is traveling, the collection unit can also collect data related to the area to which the user is traveling. Furthermore, when the user is at home, the collection unit can also collect data suitable for home learning. This enables efficient data collection by prioritizing the collection of highly relevant data by taking into account the user's geographical location information. Some or all of the above-mentioned processing in the collection unit may be performed, for example, using AI or without using AI.

[0097] When collecting data, the collection unit can analyze the user's social media activities and collect related data. The collection unit, for example, collects data based on learning content shared by the user on social media. The collection unit can also collect related data by referring to the activities of the user's followers on social media. Furthermore, the collection unit can collect data related to topics in which the user has shown interest on social media. This enables efficient data collection by analyzing the user's social media activities and collecting related data. Some or all of the above-mentioned processing in the collection unit may be performed, for example, using AI, or may be performed without using AI.

[0098] When collecting data, the collection unit can customize the collection method by reflecting the user's past feedback. For example, the collection unit prioritizes collection of data sources that the user has previously rated highly. The collection unit can also avoid collecting data sources that the user has previously rated poorly. Furthermore, the collection unit can adjust the type and format of data to be collected based on the user's feedback. This enables efficient data collection by customizing the collection method by reflecting the user's past feedback. Some or all of the above-mentioned processing in the collection unit may be performed, for example, using AI or without using AI.

[0099] The generation unit can estimate the user's emotions and adjust the way the generated questions are presented based on the estimated user emotions. For example, if the user is relaxed, the generation unit generates visually appealing questions. Furthermore, if the user is feeling stressed, the generation unit can also generate simple and intuitive questions. Furthermore, if the user is concentrating, the generation unit can generate questions that include detailed explanations or supplementary information. This allows the user to be provided with questions that are appropriate for the user by adjusting the way the questions are presented based on the user's emotions. Emotion estimation is achieved using an emotion estimation function, for example, using an emotion engine or generation AI. The generation AI can be a text generation AI (e.g., LLM) or a multimodal generation AI, but is not limited to these examples.

[0100] When generating questions, the generation unit can adjust the level of detail of the questions based on the importance of the content of the textbook. For example, the generation unit may include detailed explanations and supplementary information for questions based on important content. The generation unit may also generate questions based on less important content in a concise format. Furthermore, the generation unit may adjust the level of detail of the questions according to the importance of each chapter of the textbook. This allows for efficient question generation by adjusting the level of detail of the questions based on the importance of the content of the textbook. Some or all of the above-described processing in the generation unit may be performed, for example, using AI or without using AI.

[0101] The generation unit can apply different generation algorithms depending on the textbook category when generating questions. For example, the generation unit applies a mathematical expression analysis algorithm to generate mathematics questions. The generation unit can also apply a text analysis algorithm to generate social studies questions. The generation unit can also apply an experimental data analysis algorithm to generate science questions. This allows for efficient question generation by applying different generation algorithms depending on the textbook category. Some or all of the above-mentioned processing in the generation unit may be performed using, for example, AI, or may be performed without using AI.

[0102] When generating questions, the generation unit can improve the accuracy of the questions by referring to the user's past answers. The generation unit, for example, analyzes patterns of questions that the user has answered incorrectly in the past and generates similar questions. The generation unit can also reduce the number of questions in areas in which the user is good and generate more questions in areas in which the user is weak. Furthermore, the generation unit can adjust the difficulty of the questions based on the user's answers. In this way, by referring to the user's past answers and improving the accuracy of the questions, it is possible to provide questions that are suitable for the user. Some or all of the above-mentioned processing in the generation unit may be performed, for example, using AI, or may be performed without using AI.

[0103] The generation unit can estimate the user's emotions and adjust the length of the questions to be generated based on the estimated user emotions. For example, if the user is in a hurry, the generation unit can generate short, to-the-point questions. Furthermore, if the user is relaxed, the generation unit can generate longer questions with detailed explanations. Furthermore, if the user is concentrating, the generation unit can generate questions of an appropriate length. Thus, by adjusting the length of the questions to be generated based on the user's emotions, it is possible to provide questions that are suitable for the user. The emotion estimation is realized using an emotion estimation function, for example, using an emotion engine or generation AI. The generation AI can be, but is not limited to, a text generation AI (e.g., LLM) or a multimodal generation AI.

[0104] When generating questions, the generation unit can determine the priority of questions based on the publication date of the textbook. For example, the generation unit generates questions based on the latest textbook with priority. The generation unit can also generate questions based on older textbooks as needed. Furthermore, the generation unit can determine the priority of questions taking into account the revision history of the textbook. In this way, by determining the priority of questions based on the publication date of the textbook, questions based on the latest information can be provided. Some or all of the above-mentioned processing in the generation unit may be performed, for example, using AI, or may be performed without using AI.

[0105] When generating questions, the generation unit can adjust the order of questions based on the relevance of the textbook. The generation unit determines the order of questions, for example, taking into account the relevance of each chapter in the textbook. Furthermore, if the contents of the textbook are continuous, the generation unit can also generate related questions consecutively. Furthermore, if the contents of the textbook are independent, the generation unit can also randomly generate the order of questions. This enables efficient learning by adjusting the order of questions based on the relevance of the textbook. Some or all of the above-mentioned processing in the generation unit may be performed, for example, using AI, or may be performed without using AI.

[0106] When generating questions, the generation unit can adjust the use of technical terminology in the questions according to the user's level of expertise. For example, the generation unit generates questions using simple language with less technical terminology for beginners. The generation unit can also generate questions using appropriate technical terminology for intermediate learners. Furthermore, the generation unit can generate questions with a high level of difficulty using a lot of technical terminology for advanced learners. In this way, by adjusting the use of technical terminology in the questions according to the user's level of expertise, it is possible to provide questions that are suitable for the user. Some or all of the above-mentioned processing in the generation unit may be performed, for example, using AI, or may be performed without using AI.

[0107] The providing unit can estimate the user's emotions and adjust the way in which questions are presented based on the estimated user emotions. For example, if the user is relaxed, the providing unit can provide questions using a visually appealing interface. Furthermore, if the user is feeling stressed, the providing unit can provide questions using a simple and intuitive interface. Furthermore, if the user is concentrating, the providing unit can provide questions using an interface that includes detailed explanations and supplementary information. In this way, by adjusting the way in which questions are presented based on the user's emotions, questions suitable for the user can be provided. Emotion estimation is realized using an emotion estimation function, for example, using an emotion engine or generation AI. The generation AI can be a text generation AI (e.g., LLM) or a multimodal generation AI, but is not limited to such examples.

[0108] When providing questions, the providing unit can adjust the difficulty of the questions to be provided based on the user's learning progress. For example, if the user's learning progress is slow, the providing unit can provide many basic questions. Also, if the user's learning progress is fast, the providing unit can provide many applied questions and advanced questions. Furthermore, the providing unit can gradually adjust the difficulty of the questions according to the user's learning progress. This enables efficient learning by adjusting the difficulty of the questions to be provided based on the user's learning progress. Some or all of the above-mentioned processing in the providing unit may be performed, for example, using AI, or may be performed without using AI.

[0109] When providing questions, the providing unit can select the optimal timing for providing the questions by referring to the user's learning history. The providing unit, for example, provides new questions at the optimal timing based on the history of questions previously answered by the user. Furthermore, if the user has a habit of studying during a specific time period, the providing unit can also provide questions during that time period. Furthermore, the providing unit can also provide questions during times when the user is most likely to concentrate, based on the user's learning history. This enables efficient learning by selecting the optimal timing for providing questions by referring to the user's learning history. Some or all of the above-described processing by the providing unit may be performed, for example, using AI, or may be performed without using AI.

[0110] When providing questions, the providing unit can customize the method of providing questions according to the user's learning style. For example, the providing unit can provide questions that make extensive use of diagrams and illustrations to visual learners. The providing unit can also provide questions with audio commentary to auditory learners. Furthermore, the providing unit can also provide interactive questions to tactile learners. This enables efficient learning by customizing the method of providing questions according to the user's learning style. Some or all of the above-mentioned processing in the providing unit may be performed, for example, using AI, or may be performed without using AI.

[0111] The providing unit can estimate the user's emotions and determine the priority of questions to be provided based on the estimated user emotions. For example, if the user is feeling stressed, the providing unit can prioritize providing easy questions. Furthermore, if the user is concentrating, the providing unit can also prioritize providing difficult questions. Furthermore, if the user is tired, the providing unit can prioritize providing review questions. This enables efficient learning by determining the priority of questions to be provided based on the user's emotions. Emotion estimation is realized using an emotion estimation function, for example, using an emotion engine or generation AI. The generation AI can be a text generation AI (e.g., LLM) or a multimodal generation AI, but is not limited to these examples.

[0112] When providing questions, the providing unit can prioritize providing highly relevant questions by taking into account the user's geographical location information. For example, if the user is in a specific area, the providing unit can provide questions based on the educational curriculum of that area. Furthermore, if the user is traveling, the providing unit can also provide questions related to the area to which the user is traveling. Furthermore, if the user is at home, the providing unit can also provide questions suitable for home study. This enables efficient learning by prioritizing the provision of highly relevant questions by taking into account the user's geographical location information. Some or all of the above-mentioned processing by the providing unit may be performed, for example, using AI or without using AI.

[0113] When providing questions, the providing unit can analyze the user's social media activity and provide related questions. The providing unit can provide questions based on, for example, learning content shared by the user on social media. The providing unit can also provide related questions by referring to the activity of the user's followers on social media. Furthermore, the providing unit can provide questions related to topics in which the user has shown interest on social media. This enables efficient learning by analyzing the user's social media activity and providing related questions. Some or all of the above-mentioned processing by the providing unit can be performed, for example, using AI, or can be performed without using AI.

[0114] When providing questions, the providing unit can customize the method of providing questions by reflecting the user's past feedback. For example, the providing unit can prioritize providing question formats that the user has previously rated highly. The providing unit can also avoid providing question formats that the user has previously rated poorly. Furthermore, the providing unit can adjust the type and format of questions to be provided based on the user's feedback. This enables efficient learning by customizing the method of providing questions by reflecting the user's past feedback. Some or all of the above-mentioned processing in the providing unit may be performed, for example, using AI or without using AI.

[0115] The evaluation unit can estimate the user's emotions and adjust the evaluation criteria for the questions based on the estimated user emotions. For example, the evaluation unit can apply strict evaluation criteria when the user is relaxed. The evaluation unit can also apply lenient evaluation criteria when the user is stressed. Furthermore, the evaluation unit can apply evaluation criteria that include detailed feedback when the user is focused. This enables efficient evaluation by adjusting the evaluation criteria for the questions based on the user's emotions. Emotion estimation is achieved using an emotion estimation function, for example, using an emotion engine or generative AI. The generative AI can be a text generation AI (e.g., LLM) or a multimodal generation AI, but is not limited to these examples.

[0116] The evaluation unit can improve the accuracy of the evaluation by referring to the user's answer history when evaluating questions. The evaluation unit improves the accuracy of the evaluation, for example, based on the history of questions that the user has previously answered. The evaluation unit can also analyze specific patterns from the user's answer history and adjust the evaluation criteria. Furthermore, the evaluation unit can analyze the user's answer history and apply individual evaluation criteria. This allows for efficient evaluation by improving the accuracy of the evaluation by referring to the user's answer history. Some or all of the above-mentioned processing in the evaluation unit may be performed, for example, using AI or without using AI.

[0117] The evaluation unit can customize the evaluation criteria based on the user's learning progress when evaluating questions. For example, if the user's learning progress is slow, the evaluation unit can apply lenient evaluation criteria. Alternatively, if the user's learning progress is fast, the evaluation unit can apply strict evaluation criteria. Furthermore, the evaluation unit can gradually adjust the evaluation criteria according to the user's learning progress. This enables efficient evaluation by customizing the evaluation criteria based on the user's learning progress. Some or all of the above-mentioned processing in the evaluation unit may be performed, for example, using AI or without using AI.

[0118] The evaluation unit can adjust the evaluation method according to the user's learning style when evaluating questions. For example, the evaluation unit can apply an evaluation method that includes a lot of visual feedback to a visual learner. The evaluation unit can also apply an evaluation method that includes a lot of audio feedback to an auditory learner. Furthermore, the evaluation unit can also apply an evaluation method that includes a lot of interactive feedback to a tactile learner. This allows for efficient evaluation by adjusting the evaluation method according to the user's learning style. Some or all of the above-mentioned processing in the evaluation unit can be performed, for example, using AI or without using AI.

[0119] The evaluation unit can estimate the user's emotions and adjust the display method of the evaluation results based on the estimated user emotions. For example, when the user is relaxed, the evaluation unit displays detailed evaluation results. Furthermore, when the user is stressed, the evaluation unit can also display concise evaluation results. Furthermore, when the user is concentrating, the evaluation unit can display evaluation results including detailed feedback. This enables efficient evaluation by adjusting the display method of the evaluation results based on the user's emotions. Emotion estimation is realized using an emotion estimation function, for example, using an emotion engine or generation AI. The generation AI can be a text generation AI (e.g., LLM) or a multimodal generation AI, but is not limited to such examples.

[0120] The evaluation unit can adjust the evaluation criteria when evaluating questions, taking into account the user's geographical location information. For example, if the user is in a specific area, the evaluation unit applies evaluation criteria based on the educational curriculum of that area. Furthermore, if the user is traveling, the evaluation unit can apply evaluation criteria related to the area to which the user is traveling. Furthermore, if the user is at home, the evaluation unit can apply evaluation criteria suitable for home learning. This allows for efficient evaluation by adjusting the evaluation criteria taking into account the user's geographical location information. Some or all of the above-mentioned processing in the evaluation unit may be performed, for example, using AI or without using AI.

[0121] The evaluation unit can analyze the user's social media activity when evaluating questions to improve the accuracy of the evaluation. The evaluation unit, for example, performs evaluation based on the learning content shared by the user on social media. The evaluation unit can also perform evaluation based on the activity of the user's followers on social media. Furthermore, the evaluation unit can perform evaluation related to topics in which the user has shown interest on social media. This allows for efficient evaluation by analyzing the user's social media activity and improving the accuracy of the evaluation. Some or all of the above-mentioned processing in the evaluation unit may be performed using, for example, AI, or may be performed without using AI.

[0122] The evaluation unit can customize the evaluation criteria by reflecting the user's past feedback when evaluating a problem. For example, the evaluation unit preferentially applies evaluation criteria that the user has previously given a high rating to. The evaluation unit can also avoid applying evaluation criteria that the user has previously given a low rating to. Furthermore, the evaluation unit can adjust the evaluation criteria based on the user's feedback. This enables efficient evaluation by customizing the evaluation criteria by reflecting the user's past feedback. Some or all of the above-mentioned processing in the evaluation unit may be performed, for example, using AI or without using AI.

[0123] The adjustment unit can estimate the user's emotions and determine how to adjust the questions based on the estimated user emotions. For example, the adjustment unit can make detailed adjustments when the user is relaxed. The adjustment unit can also make simple adjustments when the user is stressed. Furthermore, the adjustment unit can make adjustments that include detailed feedback when the user is concentrating. This enables efficient adjustments by determining how to adjust the questions based on the user's emotions. Emotion estimation is achieved using an emotion estimation function, for example, using an emotion engine or a generation AI. The generation AI can be a text generation AI (e.g., LLM) or a multimodal generation AI, but is not limited to these examples.

[0124] When adjusting questions, the adjustment unit can improve the accuracy of the adjustment by referring to the user's answer history. The adjustment unit improves the accuracy of the adjustment, for example, based on the history of questions that the user has previously answered. The adjustment unit can also analyze specific patterns from the user's answer history and adjust the adjustment criteria. Furthermore, the adjustment unit can analyze the user's answer history and apply individual adjustment criteria. This enables efficient adjustment by improving the accuracy of the adjustment by referring to the user's answer history. Some or all of the above-mentioned processing in the adjustment unit may be performed, for example, using AI or without using AI.

[0125] The adjustment unit can customize the adjustment criteria based on the user's learning progress when adjusting the questions. For example, the adjustment unit applies lenient adjustment criteria when the user's learning progress is slow. The adjustment unit can also apply strict adjustment criteria when the user's learning progress is fast. Furthermore, the adjustment unit can gradually adjust the adjustment criteria according to the user's learning progress. This enables efficient adjustment by customizing the adjustment criteria based on the user's learning progress. Some or all of the above-mentioned processing in the adjustment unit may be performed using, for example, AI, or may be performed without using AI.

[0126] The adjustment unit can adjust the adjustment method according to the user's learning style when adjusting questions. For example, the adjustment unit applies an adjustment method that includes a lot of visual feedback to a visual learner. The adjustment unit can also apply an adjustment method that includes a lot of audio feedback to an auditory learner. Furthermore, the adjustment unit can also apply an adjustment method that includes a lot of interactive feedback to a tactile learner. This enables efficient adjustment by adjusting the adjustment method according to the user's learning style. Some or all of the above-mentioned processing in the adjustment unit may be performed using AI, for example, or may be performed without using AI.

[0127] The adjustment unit can estimate the user's emotion and adjust the display method of the adjustment result based on the estimated user's emotion. For example, when the user is relaxed, the adjustment unit displays a detailed adjustment result. Furthermore, when the user is stressed, the adjustment unit can also display a concise adjustment result. Furthermore, when the user is concentrating, the adjustment unit can also display an adjustment result including detailed feedback. This enables efficient adjustment by adjusting the display method of the adjustment result based on the user's emotion. Emotion estimation is realized using an emotion estimation function, for example, using an emotion engine or generation AI. The generation AI can be a text generation AI (e.g., LLM) or a multimodal generation AI, but is not limited to these examples.

[0128] The adjustment unit can adjust the adjustment criteria taking into account the user's geographical location information when adjusting the questions. For example, if the user is in a specific area, the adjustment unit applies adjustment criteria based on the educational curriculum of that area. Furthermore, if the user is traveling, the adjustment unit can also apply adjustment criteria related to the area to which the user is traveling. Furthermore, if the user is at home, the adjustment unit can also apply adjustment criteria suitable for home learning. In this way, adjusting the adjustment criteria taking into account the user's geographical location information enables efficient adjustment. Some or all of the above-mentioned processing in the adjustment unit may be performed using AI, for example, or may be performed without using AI.

[0129] When adjusting questions, the adjustment unit can analyze the user's social media activity and improve the accuracy of the adjustment. The adjustment unit makes the adjustment based on, for example, learning content shared by the user on social media. The adjustment unit can also make the adjustment based on the activity of the user's followers on social media. Furthermore, the adjustment unit can make the adjustment related to topics in which the user has shown interest on social media. In this way, analyzing the user's social media activity and improving the accuracy of the adjustment enables efficient adjustment. Some or all of the above-mentioned processing in the adjustment unit may be performed, for example, using AI, or may be performed without using AI.

[0130] When adjusting a problem, the adjustment unit can customize the adjustment criteria by reflecting the user's past feedback. For example, the adjustment unit preferentially applies adjustment criteria that the user has previously rated highly. The adjustment unit can also avoid applying adjustment criteria that the user has previously rated poorly. Furthermore, the adjustment unit can adjust the adjustment criteria based on the user's feedback. This enables efficient adjustment by customizing the adjustment criteria by reflecting the user's past feedback. Some or all of the above-described processing in the adjustment unit may be performed, for example, using AI or without using AI.

[0131] The review unit can estimate the user's emotions and adjust the method for generating review questions based on the estimated user emotions. For example, if the user is relaxed, the review unit can generate review questions with detailed explanations. Furthermore, if the user is feeling stressed, the review unit can generate simple and intuitive review questions. Furthermore, if the user is concentrating, the review unit can generate review questions with detailed feedback. This allows for efficient review by adjusting the method for generating review questions based on the user's emotions. Emotion estimation is achieved using an emotion estimation function, for example, using an emotion engine or generation AI. The generation AI can be a text generation AI (e.g., LLM) or a multimodal generation AI, but is not limited to these examples.

[0132] When generating review questions, the review unit can improve the accuracy of the generation by referring to the user's answer history. The review unit, for example, analyzes patterns of questions that the user has answered incorrectly in the past and generates similar review questions. The review unit can also generate fewer review questions for areas in which the user is strong and more review questions for areas in which the user is weak. Furthermore, the review unit can adjust the difficulty of the review questions based on the user's answer history. This allows for efficient review by improving the accuracy of generation by referring to the user's answer history. Some or all of the above-mentioned processing in the review unit may be performed, for example, using AI or without using AI.

[0133] When generating review questions, the review unit can customize the generation criteria based on the user's learning progress. For example, if the user's learning progress is slow, the review unit generates many basic review questions. Also, if the user's learning progress is fast, the review unit can generate many applied and advanced review questions. Furthermore, the review unit can gradually adjust the difficulty of the review questions according to the user's learning progress. This allows for efficient review by customizing the generation criteria based on the user's learning progress. Some or all of the above-mentioned processing in the review unit may be performed, for example, using AI or without using AI.

[0134] When generating review questions, the review unit can adjust the generation method according to the user's learning style. For example, for visual learners, the review unit generates review questions that make extensive use of charts and illustrations. The review unit can also generate review questions with audio commentary for auditory learners. Furthermore, the review unit can also generate interactive review questions for tactile learners. This allows for efficient review by adjusting the generation method according to the user's learning style. Some or all of the above-mentioned processing in the review unit may be performed, for example, using AI or without using AI.

[0135] The review unit can estimate the user's emotions and prioritize review questions based on the estimated user emotions. For example, if the user is feeling stressed, the review unit can prioritize generating easy review questions. Furthermore, if the user is concentrating, the review unit can also prioritize generating difficult review questions. Furthermore, if the user is tired, the review unit can prioritize generating review questions. This enables efficient review by prioritizing review questions based on the user's emotions. Emotion estimation is achieved using an emotion estimation function, for example, using an emotion engine or generation AI. The generation AI can be, but is not limited to, a text generation AI (e.g., LLM) or a multimodal generation AI.

[0136] When generating review questions, the review unit can prioritize generating highly relevant questions by taking into account the user's geographical location information. For example, if the user is in a specific area, the review unit can generate review questions based on the educational curriculum of that area. Furthermore, if the user is traveling, the review unit can also generate review questions related to the area to which the user is traveling. Furthermore, if the user is at home, the review unit can also generate review questions suitable for home study. This enables efficient review by prioritizing the generation of highly relevant questions by taking into account the user's geographical location information. Some or all of the above-mentioned processing in the review unit may be performed, for example, using AI or without using AI.

[0137] When generating review questions, the review unit can analyze the user's social media activity and generate related questions. The review unit can generate review questions based on, for example, the learning content shared by the user on social media. The review unit can also generate related review questions by referring to the activity of the user's followers on social media. Furthermore, the review unit can generate review questions related to topics in which the user has shown interest on social media. This enables efficient review by analyzing the user's social media activity and generating related questions. Some or all of the above-mentioned processing in the review unit can be performed, for example, using AI, or can be performed without using AI.

[0138] When generating review questions, the review unit can customize the generation method by reflecting the user's past feedback. For example, the review unit prioritizes the generation of review question formats that the user has previously rated highly. The review unit can also generate review question formats that the user has previously rated poorly, avoiding them. Furthermore, the review unit can adjust the type and format of the review questions to be generated based on the user's feedback. This allows for efficient review by customizing the generation method by reflecting the user's past feedback. Some or all of the above-mentioned processing in the review unit may be performed, for example, using AI, or may be performed without using AI. === Hard Collateral 1-1 === Each of the multiple elements, including the collection unit, generation unit, provision unit, evaluation unit, adjustment unit, and review unit, is realized, for example, by at least one of the smart device 14 and the data processing device 12. For example, the collection unit collects textbook data and past exam data using the camera 42 and microphone 38B of the smart device 14, and the collected data is analyzed by the specific processing unit 290 of the data processing device 12. The generation unit, realized, for example, by the specific processing unit 290 of the data processing device 12, generates new questions based on the collected data. The provision unit, realized, for example, by the control unit 46A of the smart device 14, provides the generated questions to the user via an online platform. The evaluation unit, realized, for example, by the specific processing unit 290 of the data processing device 12, evaluates the quality of the generated questions. The adjustment unit, realized, for example, by the specific processing unit 290 of the data processing device 12, adjusts the difficulty and content of the questions based on the evaluation results. The review unit, realized, for example, by the control unit 46A of the smart device 14, generates review questions based on past exam data, and the user reviews by answering them. === Hard Collateral 1-2 === Each of the multiple elements, including the collection unit, generation unit, provision unit, evaluation unit, adjustment unit, and review unit, is realized, for example, by at least one of the smart glasses 214 and the data processing device 12. For example, the collection unit collects textbook data and past exam data using the camera 42 and microphone 238 of the smart glasses 214, which is analyzed by the specific processing unit 290 of the data processing device 12. The generation unit, realized, for example, by the specific processing unit 290 of the data processing device 12, generates new questions based on the collected data. The provision unit, realized, for example, by the control unit 46A of the smart glasses 214, provides the generated questions to the user via an online platform. The evaluation unit, realized, for example, by the specific processing unit 290 of the data processing device 12, evaluates the quality of the generated questions. The adjustment unit, realized, for example, by the specific processing unit 290 of the data processing device 12, adjusts the difficulty and content of the questions based on the evaluation results. The review unit, realized, for example, by the control unit 46A of the smart glasses 214, generates review questions based on past exam data, and the user reviews by answering them. === Hard Collateral 1-3 === Each of the multiple elements, including the collection unit, generation unit, provision unit, evaluation unit, adjustment unit, and review unit, is realized, for example, by at least one of the headset-type terminal 314 and the data processing device 12. For example, the collection unit collects textbook data and past exam data using the camera 42 and microphone 238 of the headset-type terminal 314, and the collected data is analyzed by the specific processing unit 290 of the data processing device 12. The generation unit, realized, for example, by the specific processing unit 290 of the data processing device 12, generates new questions based on the collected data. The provision unit, realized, for example, by the control unit 46A of the headset-type terminal 314, provides the generated questions to the user via an online platform. The evaluation unit, realized, for example, by the specific processing unit 290 of the data processing device 12, evaluates the quality of the generated questions. The adjustment unit, realized, for example, by the specific processing unit 290 of the data processing device 12, adjusts the difficulty and content of the questions based on the evaluation results. The review unit is realized by, for example, the control unit 46A of the headset terminal 314, and generates review questions based on past exam data, and the user reviews by answering them. === Hard Collateral 1-4 === Each of the multiple elements, including the collection unit, generation unit, provision unit, evaluation unit, adjustment unit, and review unit, is realized, for example, by at least one of the robot 414 and the data processing device 12. For example, the collection unit collects textbook data and past exam data using the camera 42 and microphone 238 of the robot 414, which is analyzed by the specific processing unit 290 of the data processing device 12. The generation unit, realized, for example, by the specific processing unit 290 of the data processing device 12, generates new questions based on the collected data. The provision unit, realized, for example, by the control unit 46A of the robot 414, provides the generated questions to the user via an online platform. The evaluation unit, realized, for example, by the specific processing unit 290 of the data processing device 12, evaluates the quality of the generated questions. The adjustment unit, realized, for example, by the specific processing unit 290 of the data processing device 12, adjusts the difficulty and content of the questions based on the evaluation results. The review unit, realized, for example, by the control unit 46A of the robot 414, generates review questions based on past exam data, and the user reviews by answering them.

[0139] The system according to the embodiment is not limited to the above-described example, and various modifications are possible, for example, as follows.

[0140] The collection unit can select the optimal data source by referring to the user's learning history. For example, it can prioritize collection of data on textbooks and workbooks that the user has used in the past. The collection unit can also collect a lot of data on areas in which the user is strong, and collect data on areas in which the user is weak in a balanced manner. Furthermore, the collection unit can prioritize collection of textbook data from specific publishers based on the user's learning history. This allows for efficient data collection by selecting the optimal data source by referring to the user's learning history.

[0141] The generation unit can estimate the user's emotions and adjust the way in which questions are presented based on the estimated user emotions. For example, if the user is relaxed, visually appealing questions can be generated. If the user is stressed, simple and intuitive questions can be generated. Furthermore, if the user is concentrating, questions that include detailed explanations and supplementary information can be generated. In this way, by adjusting the way in which questions are presented based on the user's emotions, questions that are suitable for the user can be provided.

[0142] The providing unit can estimate the user's emotions and adjust the way in which questions are provided based on the estimated user emotions. For example, if the user is relaxed, questions can be provided using a visually appealing interface. If the user is stressed, questions can be provided using a simple and intuitive interface. Furthermore, if the user is concentrating, questions can be provided using an interface that includes detailed explanations and supplementary information. In this way, by adjusting the way in which questions are provided based on the user's emotions, questions that are suitable for the user can be provided.

[0143] The evaluation unit can estimate the user's emotions and adjust the evaluation criteria for questions based on the estimated user emotions. For example, if the user is relaxed, strict evaluation criteria can be applied. If the user is stressed, lenient evaluation criteria can be applied. Furthermore, if the user is concentrating, evaluation criteria including detailed feedback can be applied. This allows for efficient evaluation by adjusting the evaluation criteria for questions based on the user's emotions.

[0144] The adjustment unit can estimate the user's emotions and determine how to adjust the questions based on the estimated user's emotions. For example, if the user is relaxed, detailed adjustments can be made. If the user is stressed, simple adjustments can be made. Furthermore, if the user is concentrating, adjustments can be made that include detailed feedback. This allows for efficient adjustments by determining how to adjust the questions based on the user's emotions.

[0145] When collecting data, the collection unit can customize the collection method according to the user's learning style. For example, for visual learners, textbook data with many charts and illustrations can be collected. The collection unit can also collect data with audio commentary for auditory learners. Furthermore, the collection unit can collect interactive question set data for tactile learners. This allows for efficient data collection by customizing the collection method according to the user's learning style.

[0146] When generating questions, the generator can adjust the level of detail of the questions based on the importance of the content of the textbook. For example, questions based on important content include detailed explanations and supplementary information. The generator can also generate questions based on less important content in a concise format. Furthermore, the generator can adjust the level of detail of the questions according to the importance of each chapter in the textbook. This allows for efficient question generation by adjusting the level of detail of the questions based on the importance of the content of the textbook.

[0147] When providing questions, the providing unit can adjust the difficulty of the questions to be provided based on the user's learning progress. For example, if the user's learning progress is slow, the providing unit can provide many basic questions. In addition, if the user's learning progress is fast, the providing unit can also provide many applied and advanced questions. Furthermore, the providing unit can gradually adjust the difficulty of the questions according to the user's learning progress. This allows for efficient learning by adjusting the difficulty of the questions to be provided based on the user's learning progress.

[0148] The evaluation unit can improve the accuracy of the evaluation by referring to the user's answer history when evaluating questions. For example, the evaluation unit can improve the accuracy of the evaluation based on the history of questions that the user has previously answered. The evaluation unit can also analyze specific patterns from the user's answer history and adjust the evaluation criteria. Furthermore, the evaluation unit can analyze the user's answer history and apply individual evaluation criteria. This allows for efficient evaluation by improving the accuracy of the evaluation by referring to the user's answer history.

[0149] When generating review questions, the review unit can refer to the user's answer history to improve the accuracy of the generation. For example, it can analyze patterns of questions that the user has answered incorrectly in the past and generate similar review questions. The review unit can also generate fewer review questions for areas in which the user is strong and more review questions for areas in which the user is weak. Furthermore, the review unit can adjust the difficulty level of the review questions based on the user's answer history. This allows for efficient review by improving the accuracy of generation by referring to the user's answer history.

[0150] The processing flow of the second embodiment will be briefly explained below.

[0151] Step 1: The collection unit collects textbook data or past exam data. The collection unit collects, for example, the contents of textbooks or past exam questions as digital data. Step 2: The generator uses a generation AI to analyze the data collected by the collector and generate new questions. For example, the generator generates new practice questions based on the content of a textbook. The generator can also analyze the patterns of past questions to generate similar questions. Step 3: The providing unit provides the questions generated by the generating unit to the user. The providing unit provides the questions via, for example, an online platform, and the user inputs the answers. Step 4: The evaluation unit evaluates the quality of the generated questions. For example, the evaluation unit evaluates whether the difficulty level and content of the generated questions are appropriate. Step 5: The adjustment unit adjusts the questions based on the results of the evaluation by the evaluation unit. For example, if the difficulty level of a question is too high, the adjustment unit adjusts the question to make it easier. Step 6: The review unit generates review questions based on the past exam data collected by the collection unit. For example, the review unit generates review questions based on past exam questions, and the user reviews by answering them.

[0152] 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.

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

[0154] 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.

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

[0156] [Second embodiment] FIG. 3 shows an example of the configuration of a data processing system 210 according to the second embodiment.

[0157] 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.

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

[0159] The 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.

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

[0161] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an imaging element such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, and captures images of the user's surroundings (for example, an imaging range defined by an angle of view equivalent to the field of vision of a typical healthy person).

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

[0163] Fig. 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.

[0164] The processor 28 reads the specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific processing is realized by the processor 28 operating as a specific processing unit 290 in accordance with the specific processing program 56 executed on the RAM 30.

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

[0166] In the 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.

[0167] Note that a device other than the data processing device 12 may have the data generation model 58. For example, a server device may have the data generation model 58. In this case, the data processing device 12 communicates with the server device having the data generation model 58 to obtain a processing result (such as a prediction result) using the data generation model 58. Furthermore, the data processing device 12 may be a server device, or may be a terminal device (for example, a mobile phone, a robot, a home appliance, etc.) owned by a user.

[0168] The specific processing unit 290 transmits the result of the specific processing to the 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.

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

[0170] The data processing system 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.

[0171] The correspondence between each part and the device or control part is not limited to the above example, and various modifications are possible.

[0172] [Third embodiment] FIG. 5 shows an example of the configuration of a data processing system 310 according to the third embodiment.

[0173] 5, the data processing system 310 includes the data processing device 12 and a headset terminal 314. An example of the data processing device 12 is a server.

[0174] 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.

[0175] 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.

[0176] 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.

[0177] 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).

[0178] 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.

[0179] Fig. 6 shows an example of the main functions of the data processing device 12 and the headset terminal 314. As shown in Fig. 6, in the data processing device 12, a specific process is performed by the processor 28. A specific process program 56 is stored in the storage 32.

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

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

[0182] In the headset type terminal 314, the identification process is performed by the processor 46. A identification program 60 is stored in the storage 50. The processor 46 reads the identification program 60 from the storage 50 and executes the read identification program 60 on the RAM 48. The identification process is realized by the processor 46 operating as a control unit 46A in accordance with the identification program 60 executed on the RAM 48. Note that the headset type terminal 314 has a data generation model and an emotion identification model similar to the data generation model 58 and the emotion identification model 59, and can also perform processing similar to that of the identification processing unit 290 using these models.

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

[0184] The specific processing unit 290 transmits the result of the specific processing to the 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.

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

[0186] The data processing system 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.

[0187] The correspondence between each part and the device or control part is not limited to the above example, and various modifications are possible.

[0188] [Fourth embodiment] FIG. 7 shows an example of the configuration of a data processing system 410 according to the fourth embodiment.

[0189] 7, a data processing system 410 includes a data processing device 12 and a robot 414. An example of the data processing device 12 is a server.

[0190] 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.

[0191] 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.

[0192] 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.

[0193] 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).

[0194] 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.

[0195] 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.

[0196] 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.

[0197] 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.

[0198] 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.

[0199] In the robot 414, the processor 46 performs the identification process. The storage 50 stores the identification program 60. The processor 46 reads the identification program 60 from the storage 50 and executes the read identification program 60 on the RAM 48. The identification process is realized by the processor 46 operating as the control unit 46A in accordance with the identification program 60 executed on the RAM 48. The robot 414 also has a data generation model and an emotion identification model similar to the data generation model 58 and the emotion identification model 59, and can perform the same process as the identification processing unit 290 using these models.

[0200] 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.

[0201] 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.

[0202] The data generation model 58 is a so-called generative AI. An example of the data generation model 58 is a generative AI such as ChatGPT. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 receives a prompt containing an instruction, as well as inference data such as voice data representing speech, text data representing text, and image data representing an image. The data generation model 58 performs inference on the input inference data in accordance with the instruction indicated by the prompt and outputs the inference result in a data format such as voice data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization. The identification processing unit 290 performs the above-mentioned identification processing using the data generation model 58. The data generation model 58 may be a fine-tuned model so as to output an inference result from a prompt that does not include an instruction. In this case, the data generation model 58 can output an inference result from a prompt that does not include an instruction. The data processing device 12 and the like include multiple types of data generation models 58, and the data generation model 58 includes AI other than the generative AI. The AI ​​other than the generative AI may be, for example, linear regression, logistic regression, decision tree, random forest, support vector machine (SVM), k-means clustering, convolutional neural network (CNN), recurrent neural network (RNN), generative adversarial network (GAN), or naive Bayes, and can perform various processes, but is not limited to these examples. The AI ​​may also be an AI agent. When the processes of each of the above-mentioned parts are performed by AI, the processes may be performed in part or entirely by AI, but are not limited to these examples. The processes performed by AI, including the generative AI, may be replaced with rule-based processes.

[0203] 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.

[0204] The correspondence between each part and the device or control part is not limited to the above example, and various modifications are possible.

[0205] 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.

[0206] 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.

[0207] 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.

[0208] 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).

[0209] 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.

[0210] 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."

[0211] 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.

[0212] 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.

[0213] 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.

[0214] 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.

[0215] 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.

[0216] 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.

[0217] 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.

[0218] 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.

[0219] 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.

[0220] 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.

[0221] The above-described description and illustrations are a detailed explanation of the parts related to the technology of the present disclosure and are merely an example of the technology of the present disclosure. For example, the above description of the configuration, functions, actions, and effects is an explanation of an example of the configuration, functions, actions, and effects of the parts related to the technology of the present disclosure. Therefore, it goes without saying that unnecessary parts may be deleted, new elements may be added, or replacements may be made to the above-described description and illustrations within the scope of the gist of the technology of the present disclosure. Furthermore, in order to avoid confusion and to facilitate understanding of the parts related to the technology of the present disclosure, the above-described description and illustrations omit explanations of common technical knowledge that do not require particular explanation to enable the implementation of the technology of the present disclosure.

[0222] 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.

[0223] [Explanation of symbols]

[0224] 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 collection unit that collects textbook data or past exam data; a generation unit that analyzes the data collected by the collection unit and generates new questions; a providing unit that provides the questions generated by the generating unit; an evaluation unit that evaluates the quality of the questions provided by the providing unit; an adjustment unit that adjusts the problem based on the result of the evaluation by the evaluation unit; a review unit that generates review questions based on the past exam question data collected by the collection unit. A system characterized by:

2. The collecting unit Collect textbook content or past exam questions as digital data 2. The system of claim 1.

3. The generation unit Generate new exercises based on textbook content 2. The system of claim 1.

4. The generation unit Analyze patterns of past exam questions and generate similar questions 2. The system of claim 1.

5. The providing unit Questions are provided through an online platform and users enter their answers 2. The system of claim 1.

6. The evaluation unit Evaluate whether the difficulty and content of the generated questions are appropriate 2. The system of claim 1.

7. The adjustment unit Adjust the problem based on the evaluation results 2. The system of claim 1.

8. The review section Generate review questions based on past exam questions 2. The system of claim 1.

Images