system

Abstract

We provide the system. [Solution] Means for collecting and accumulating educational data, A means of analyzing collected data and automatically generating educational plans, A means for optimizing educational materials and assessment tests based on the generated educational plan, A means of displaying an interface for managing educational progress and providing individualized instruction, A means of updating educational data in real time, A means for controlling an automated device equipped with an educational support device that includes means for providing customized educational materials based on the progress of the students, A system that includes this.

Description

Technical Field

[0001] The technology of the present disclosure relates to a system.

Background Art

[0002] Patent Document 1 discloses a persona chatbot control method performed by at least one processor, including steps of receiving a user utterance, adding the user utterance to a prompt including an instruction sentence related to an explanation of a 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

Summary of the Invention

Problems to be Solved by the Invention

[0004] In the educational field, each teacher independently creates lesson plans, teaching materials, and tests, which takes time and effort and causes variations in the quality of education. There is also a problem of insufficient resources for accurately grasping the strengths and weaknesses of each child and providing individual guidance.

Means for Solving the Problems

[0005] The present invention provides means for collecting and storing educational data, and means for analyzing the collected data to automatically generate educational plans. It also provides means for optimizing educational materials and assessment tests based on the generated educational plans. Furthermore, it provides a system that solves these problems by including means for managing educational progress, displaying an interface for providing individualized instruction, and updating educational data in real time.

[0006] "Educational data" refers to a collection of information related to educational activities, such as lesson plans, teaching materials, test results, student learning progress, and achievement reports from other schools.

[0007] "Means of collection and storage" refers to methods and devices for collecting and storing educational data and keeping it available for later analysis and educational planning.

[0008] "Means of analysis" refer to methods and techniques for processing collected educational data and deriving useful information and trends from it.

[0009] "Methods for automatically generating educational plans" refer to methods or processes for programmatically creating annual lesson and activity schedules based on analyzed data.

[0010] "Optimization methods" refer to ways of making adjustments to maximize the quality and efficiency of educational materials and assessment tests in relation to a given objective.

[0011] An "interface for managing educational progress" is a display method or platform that allows teachers and students to visually check and manage the progress and results of educational activities.

[0012] "Methods for updating in real time" refer to technologies and mechanisms that instantly update databases and systems to the latest state when new information or data becomes available. [Brief explanation of the drawing]

[0013] [Figure 1]This is a conceptual diagram showing an example of the configuration of a data processing system according to the first embodiment. [Figure 2] This is a conceptual diagram showing an example of the essential functions of a data processing device and a smart device according to the first embodiment. [Figure 3] This is a conceptual diagram showing an example of the configuration of a data processing system according to the second embodiment. [Figure 4] This is a conceptual diagram showing an example of the main functions of a data processing device and smart glasses according to the second embodiment. [Figure 5] This is a conceptual diagram showing an example of the configuration of a data processing system according to the third embodiment. [Figure 6] This is a conceptual diagram showing an example of the main functions of a data processing device and a headset-type terminal according to the third embodiment. [Figure 7] This is a conceptual diagram showing an example of the configuration of a data processing system according to the fourth embodiment. [Figure 8] This is a conceptual diagram showing an example of the main functions of a data processing device and a robot according to the fourth embodiment. [Figure 9] This shows an emotion map where multiple emotions are mapped. [Figure 10] This shows an emotion map where multiple emotions are mapped. [Figure 11] This is a sequence diagram showing the processing flow of the data processing system in Example 1. [Figure 12] This is a sequence diagram showing the processing flow of the data processing system in Application Example 1. [Figure 13] This is a sequence diagram showing the processing flow of the data processing system in Example 2, which incorporates an emotion engine. [Figure 14] This is a sequence diagram showing the processing flow of the data processing system in Application Example 2, which combines an emotion engine. [Modes for carrying out the invention]

[0014] Hereinafter, an example of an embodiment of the system relating to the technology of this disclosure will be described with reference to the attached drawings.

[0015] First, the terms used in the following description will be explained.

[0016] In the following embodiments, the labeled processor (hereinafter simply referred to as "processor") may be a single arithmetic unit or a combination of multiple arithmetic units. Also, the processor may be a single type of arithmetic unit or a combination of multiple types of arithmetic units. Examples of arithmetic units 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), and the like.

[0017] In the following embodiments, the labeled RAM (Random Access Memory) is a memory in which information is temporarily stored and is used as a work memory by the processor.

[0018] In the following embodiments, the labeled storage is one or more non-volatile storage devices that store various programs and various parameters, etc. Examples of non-volatile storage devices include flash memory (SSD (Solid State Drive)), magnetic disks (e.g., hard disks), or magnetic tapes, and the like.

[0019] In the following embodiments, the labeled communication I / F (Interface) is an interface including a communication processor and 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), or Bluetooth (registered trademark), and the like.

[0020] In the following embodiments, "A and / or B" is synonymous with "at least one of A and B." That is, "A and / or B" means that it may be A alone, or B alone, or a combination of A and B. Furthermore, in this specification, the same concept as "A and / or B" applies when expressing three or more things linked by "and / or."

[0021] [First Embodiment]

[0022] Figure 1 shows an example of the configuration of the data processing system 10 according to the first embodiment.

[0023] As shown in Figure 1, the 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.

[0024] The data processing device 12 comprises a computer 22, a database 24, and a communication interface 26. The computer 22 is an example of a "computer" related to the technology of this disclosure. The computer 22 comprises a processor 28, RAM 30, and storage 32. The processor 28, RAM 30, and storage 32 are connected to a bus 34. The database 24 and the communication interface 26 are also connected to the bus 34. The communication interface 26 is connected to a network 54. An example of the network 54 is a WAN (Wide Area Network) and / or a LAN (Local Area Network).

[0025] The smart device 14 comprises a computer 36, a reception device 38, an output device 40, a camera 42, and a communication interface 44. The computer 36 comprises a processor 46, RAM 48, and storage 50. The processor 46, RAM 48, and storage 50 are connected to a bus 52. The reception device 38, output device 40, and camera 42 are also connected to the bus 52.

[0026] The reception device 38 is equipped with a touch panel 38A and a microphone 38B, etc., and receives user input. The touch panel 38A receives user input by detecting contact with an object (e.g., a pen or finger). The microphone 38B receives user input by detecting the user's voice. The control unit 46A transmits data indicating the user input received by the touch panel 38A and microphone 38B to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the data indicating the user input.

[0027] The output device 40 includes a display 40A and a speaker 40B, and presents data to the user 20 by outputting the data in a form perceptible to the user 20 (e.g., audio and / or text). The display 40A displays visible information such as text and images according to instructions from the processor 46. The speaker 40B outputs audio according to instructions from the processor 46. The camera 42 is a small digital camera equipped with an optical system such as a lens, aperture, and shutter, and an image sensor such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor.

[0028] Communication interface 44 is connected to network 54. Communication interfaces 44 and 26 are responsible for the exchange of various types of information between processor 46 and processor 28 via network 54.

[0029] Figure 2 shows an example of the main functions of the data processing device 12 and the smart device 14.

[0030] As shown in Figure 2, in the data processing device 12, a specific processing 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" related to the technology of this 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 processing is realized by the processor 28 operating as a specific processing unit 290 according to the specific processing program 56 executed on the RAM 30.

[0031] The storage 32 stores the data generation model 58 and the emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290.

[0032] In the smart device 14, the processor 46 performs the reception output processing. The storage 50 stores the reception output program 60. The reception output program 60 is used in conjunction with a specific processing program 56 by the data processing system 10. The processor 46 reads the reception output program 60 from the storage 50 and executes the read reception output program 60 on the RAM 48. The reception output processing is realized by the processor 46 operating as a control unit 46A according to the reception output program 60 executed on the RAM 48.

[0033] Next, the specific processing performed by the specific processing unit 290 of the data processing device 12 will be described. In the following description, the data processing device 12 will be referred to as the "server" and the smart device 14 as the "terminal".

[0034] This invention provides a system for improving the efficiency and standardization of lesson planning in educational settings. It consists of three main components: a server, a terminal, and a user, each playing a specific role.

[0035] First, the server collects and stores educational data. This includes past lesson plans, teaching materials, test results, and success stories from other schools for each school and region. The server analyzes this data using AI algorithms and automatically generates educational plans to achieve a unified educational level. The generated plans are then adjusted according to the specific events and activities of each grade level and school.

[0036] Furthermore, the server optimizes teaching materials and assessment tests based on the analysis results. In this process, it refers to past student performance data and comprehension levels to provide materials and test questions of appropriate difficulty. For example, for units in mathematics where the average score was low in the past, supplementary materials might be recommended.

[0037] Next, the device provides a user interface for teachers and students. Through this interface, teachers can intuitively check the annual lesson plan and students' progress. In addition, the device sends the test results taken by students to the server in real time, so the database on the server is always kept up-to-date.

[0038] Finally, based on the information provided, the user (teacher) identifies each student's strengths and weaknesses and provides individualized instruction. For example, if a student performs poorly in reading comprehension in Japanese, the teacher can support that student using additional materials recommended by the system. This system allows teachers to reduce their preparation workload and provide higher quality education while tailoring instruction to each individual student.

[0039] As a concrete example, one elementary school implemented this system to standardize the curriculum content for each grade level and to flexibly adjust the curriculum even when there are common events or activities at specific times. In this way, the quality of education is improved, and effective support for human resource development is realized.

[0040] The following describes the processing flow.

[0041] Step 1:

[0042] The server collects educational data such as lesson plans, teaching materials, and test results from educational settings and stores them in a database. This process is automated and regularly updated, ensuring that new information is always reflected.

[0043] Step 2:

[0044] The server analyzes accumulated data using AI algorithms and generates an optimal educational plan derived from past performance and successful examples from other schools. This plan includes a list of lesson themes and teaching materials to be used each month.

[0045] Step 3:

[0046] The server optimizes educational materials and assessment tests based on the generated lesson plan. It automatically selects the most suitable materials and test questions for each lesson, taking into account difficulty levels and student comprehension.

[0047] Step 4:

[0048] The device provides teachers with an interface to monitor teaching plans and student progress. The interface is designed to be visually intuitive and easy to access.

[0049] Step 5:

[0050] The terminal transmits the results of tests taken by students and their class attendance records to the server in real time. This communication ensures that the server's database is always updated with the latest information.

[0051] Step 6:

[0052] Based on information provided by the server, users (teachers) analyze each student's strengths and weaknesses and provide individualized instruction. Users utilize the system-recommended teaching materials and supplementary resources to provide education tailored to each student.

[0053] Step 7:

[0054] Users (teachers) can adjust the generated lesson plans as needed and customize the content to suit specific events and occasions. This flexibility allows the plans to be optimized to the specific needs and circumstances of the school.

[0055] (Example 1)

[0056] Next, we will describe Example 1. In the following description, the data processing device 12 will be referred to as the "server," and the smart device 14 will be referred to as the "terminal."

[0057] Improving the quality and efficiency of individualized instruction is a crucial challenge in modern education. Traditional methods require teachers to spend a significant amount of time creating lesson plans, making it difficult to provide instruction tailored to the individual needs of each student. Furthermore, developing flexible educational plans that take into account the educational standards and characteristics of each school and region is also challenging.

[0058] The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 1 is realized by the following means.

[0059] In this invention, the server includes means for collecting and storing educational information, means for analyzing the collected information and utilizing a generative model for automatically generating educational plans, and means for analyzing student performance data and recommending additional teaching materials according to the student's level of understanding. This enables teachers to provide flexible and effective instruction tailored to individual students.

[0060] "Educational information" refers to information related to education, such as past lesson plans, teaching materials, test results, and success stories from schools and communities.

[0061] A "generative model" refers to a computational algorithm or artificial intelligence structure that automatically creates educational plans based on accumulated educational information.

[0062] "Educational materials" refer to teaching materials, reference materials, and other items and digital content used to support learning in classes and instruction.

[0063] "Evaluation methods" refer to tests, questionnaires, and other assessment methods used to measure students' learning progress and understanding.

[0064] A "display device" refers to a screen or device used to visually display educational information, lesson plans, student progress, and so on.

[0065] "Supplementary materials" are materials provided in addition to standard materials to reinforce learning, tailored to each student's individual level of understanding and academic performance.

[0066] This invention is a system for improving the efficiency and standardization of lesson planning in educational settings. The system mainly consists of three components: a server, a terminal, and a user.

[0067] The server collects and stores educational information, including past performance data, lesson plans, and success stories from each educational institution. The server stores this information in a database and uses a generative model to automatically generate lesson plans. The software used includes a database management system and an AI model. For example, when creating a math lesson plan, it recommends appropriate units based on past performance data.

[0068] The generation of educational plans is performed by analyzing data collected by the server and inputting it into a generation AI model using prompt messages. For example, a prompt message such as, "Please create a lesson plan for third-grade elementary school math for the next academic year. Consider past test results and successful examples, and suggest additional materials for units that need reinforcement," might be used.

[0069] The terminal provides a user interface for teachers and students. Through this interface, teachers can view generated lesson plans and student progress. The terminal provides a dashboard-style display via a web browser and plays a role in synchronizing data with the server in real time.

[0070] The teacher, as a user, provides individualized instruction based on information obtained through the device. For example, a student who performs poorly in reading comprehension in Japanese language arts can be given additional materials to improve their understanding. In this way, teachers can reduce the burden of creating lesson plans while providing high-quality individualized instruction.

[0071] The flow of the specific processing in Example 1 will be explained using Figure 11.

[0072] Step 1:

[0073] The server collects educational information from each educational institution and stores it in a database. It receives educational information such as past grade data, lesson plans, teaching materials, and test results as input. This data is collected using data ingestion scripts via CSV files or APIs. As output, the complete dataset is stored in the database, ready for subsequent processing.

[0074] Step 2:

[0075] The server analyzes the accumulated educational information and inputs it into the generating AI model using prompt statements. These prompt statements describe in detail the conditions necessary for automatically generating educational plans. The AI ​​model receives educational data stored in the database and prompt statements as input. As output, it proposes educational plans tailored to specific grades and subjects. Specifically, to generate a math lesson plan, a prompt statement such as "Please create a math lesson plan for third grade elementary school students for the next academic year" is used.

[0076] Step 3:

[0077] The server optimizes teaching materials and assessment methods based on the generated educational plan. It receives an educational plan created by a generating AI model as input. The server analyzes past performance data and generates teaching materials and test questions tailored to the student's level of understanding. As output, appropriate teaching materials and tests are prepared for each unit. Specifically, if a student performs poorly in a particular unit, the server automatically suggests supplementary materials to reinforce that unit.

[0078] Step 4:

[0079] The terminal provides a user interface for teachers and students. It receives lesson plans, teaching materials, and student progress data from the server as input. The terminal displays this information in a dashboard format for intuitive operation. However, since each user interface is provided via a web browser, real-time data synchronization with the server is necessary. As output, teachers can link lesson plans and monitor student progress.

[0080] Step 5:

[0081] The teacher, as the user, provides instruction tailored to each student's level of understanding based on information obtained through the device. Inputs include the displayed educational plan and student progress data. Next, the teacher provides additional materials and individual advice. Output is that the teacher supports and improves student learning through appropriate instruction. Specifically, the teacher improves the quality of instruction by preparing additional materials for students who have insufficient understanding of reading comprehension in Japanese.

[0082] (Application Example 1)

[0083] Next, we will explain Application Example 1. In the following explanation, the data processing device 12 will be referred to as the "server," and the smart device 14 will be referred to as the "terminal."

[0084] To reduce the burden of developing and implementing lesson plans in educational settings and to strengthen individualized instruction, efficient and standardized educational plans are necessary. However, currently, creating and managing educational plans requires significant time and resources, and there are challenges, particularly in providing education tailored to the individual characteristics of each student. Furthermore, there is a lack of individually customized teaching materials based on students' learning progress, so the introduction of a more immediate and effective educational support system is needed.

[0085] The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 1 is realized by the following means.

[0086] In this invention, the server includes means for collecting and storing educational data, means for analyzing the collected data and automatically generating educational plans, means for optimizing educational materials and assessment tests based on the generated educational plans, and means for providing customized educational materials based on the progress of the students. This not only enables the streamlining and standardization of lesson plans in educational settings, but also enables the provision of educational materials tailored to each student, thereby improving the quality of individualized instruction.

[0087] "Educational data" refers to information about the educational process, including lesson plans, teaching materials, test results, student performance and comprehension levels, and success stories from other schools.

[0088] "Means for automatically generating educational plans" refers to devices or programs that analyze collected educational data using AI algorithms, etc., and automatically create lesson plans suitable for each educational institution with a unified educational level.

[0089] "Means for optimizing educational materials and assessment tests" refers to devices or systems that have the function of automatically selecting and distributing educational materials and test questions of appropriate difficulty levels based on past performance data and comprehension information.

[0090] "Means of managing educational progress" refers to systems and devices that grasp students' learning progress and understanding in real time and provide this information in a visualized format.

[0091] "Means for displaying an interface for providing individualized instruction" refers to devices or methods that provide a user interface for teachers to identify each student's strengths and weaknesses and display information for use when providing individualized instruction.

[0092] "Means of providing customized educational materials based on the student's progress" refers to a system that has the function of dynamically selecting and outputting educational materials based on learning history in order to provide materials whose content is adjusted according to the student's learning situation.

[0093] "Means for controlling automated devices equipped with educational support devices" refers to a system that uses programming to control robots or digital devices with educational support functions and execute specified educational content.

[0094] To realize this invention, it is necessary to build an educational support system. This system will operate through the interaction of a server, terminals, and users (primarily teachers).

[0095] The server is responsible for collecting and storing educational data. High-performance cloud servers are used as hardware, and a database management system such as AWS® DynamoDB is employed as software. Furthermore, AI libraries such as TENSORFLOW® are used to analyze the collected data and automatically generate educational plans tailored to each educational institution. The generated educational plans are transmitted to educational terminals in real time.

[0096] Next, the educational devices primarily function as interfaces for teachers and students. Small computing devices such as Raspberry Pi and Jetson Nano are employed to support the execution of lesson plans both in the classroom and remotely. The devices provide teachers with generated lesson plans and optimized teaching materials, and keep all information up-to-date by sending student progress data to a server.

[0097] Through the interface of this educational system, users can understand each student's strengths and weaknesses and provide individualized instruction. For example, if a teacher needs additional instruction for a particular student, they can use customized teaching materials suggested by the system.

[0098] For example, if it is determined that a student is struggling with a particular unit in mathematics, the server will generate appropriate supplementary materials based on past data and provide them to the student via their device. The teacher will then follow up as needed based on these materials.

[0099] In this scenario, a generative AI model can be used to create prompts and suggest problems tailored to the students' level of understanding. For example, a prompt such as, "Please provide video materials to concretely explain mathematical concepts that students find difficult to understand," could be used.

[0100] The flow of a specific process in Application Example 1 will be explained using Figure 12.

[0101] Step 1:

[0102] The server collects educational data from various educational institutions and stores it in AWS DynamoDB. Inputs include past lesson plans, teaching materials, and test results submitted from schools and regions, while output is the storage of these datasets in the database. Data processing is performed here to verify data validity and convert it to a specified format.

[0103] Step 2:

[0104] The server analyzes the accumulated data using an AI algorithm (TensorFlow) and automatically generates an educational plan tailored to each school. The input is the educational data saved in Step 1, and the output is an integrated educational plan that takes into account events specific to each grade and school. This involves data analysis and data calculations for pattern recognition using AI.

[0105] Step 3:

[0106] The server optimizes educational materials and assessment tests based on the generated educational plan. The input is the integrated educational plan, and the output is workbooks and materials tailored to the students' level of understanding. Past performance data is referenced to process the data and select appropriate materials.

[0107] Step 4:

[0108] The terminal provides teachers with optimized teaching materials and tests received from the server. The input is information about the optimized teaching materials from the server, and the output is displayed to the teacher as teaching materials and tests that can be used in class. Information visualization is performed on the user interface.

[0109] Step 5:

[0110] The user (teacher) checks students' learning progress through the device and identifies each student's strengths and weaknesses. The input is the student's test results and progress displayed on the device, and the output is an individualized instruction plan. Here, specific instructional policies are determined based on the delivered content.

[0111] Step 6:

[0112] The server updates the database in real time with student test results and learning progress received from terminals. The input is learning data sent from terminals, and the output is the updated educational dataset. Data synchronization and consistency checks are performed here.

[0113] Step 7:

[0114] The terminal uses an AI model to generate solutions and teaching materials based on prompts generated by the server, thereby supporting student learning. The input is a prompt from the teacher, and the output is the optimal solution and teaching materials generated by the AI. For example, the prompt "Please provide video teaching materials to concretely explain mathematical concepts that students find difficult to understand" is entered, and the system displays the video teaching materials.

[0115] Furthermore, an emotion engine that estimates the user's emotions may be incorporated. That is, the identification processing unit 290 may use the emotion identification model 59 to estimate the user's emotions and perform identification processing using the user's emotions.

[0116] This invention provides an educational support system that combines an emotion engine to optimize instruction in educational settings. It consists of four main components: a server, a terminal, a user, and an emotion engine.

[0117] First, the server collects and stores educational data. This includes lesson plans, teaching materials, test results, and student response data obtained from the classroom. Emotional data recognized by the emotion engine is also sent to the server and stored in the database. The server analyzes this data and automatically generates educational plans tailored to individual needs while maintaining a consistent educational standard. These plans include general lesson themes as well as adjustments based on emotional data.

[0118] The emotion engine analyzes the user's (student or teacher's) facial expressions and tone of voice to recognize their emotional state in real time. This data is used to help teachers understand students' comprehension levels and interest levels. For example, if a student appears bored during class, the system will suggest new teaching materials or activities to capture their attention.

[0119] Next, the device provides a user interface, allowing teachers and students to easily understand the plan and any associated changes. Teachers can then use this information to provide personalized instruction to individual students. The device also transmits test results and student emotional states observed during lessons to the server in real time.

[0120] Users (teachers) can make the most of the educational plans and emotion-based information provided by the server to provide individualized instruction. For example, if a student shows anxiety in a particular subject class, the teacher can understand the situation and adjust their teaching methods with additional support or a different approach.

[0121] This invention not only streamlines educational planning but also enables more individualized instruction by considering emotional aspects. As a concrete example, one middle school successfully improved students' motivation by using this system to record their daily emotional changes and adjusting weekly instructional plans based on those changes. In this way, the invention provides effective educational support and promotes the growth of individual students.

[0122] The following describes the processing flow.

[0123] Step 1:

[0124] The server collects lesson plans, teaching materials, test results, and student behavior data from educational settings and stores them in a database. This collection is performed regularly through an automated process, ensuring that the educational data is always up-to-date.

[0125] Step 2:

[0126] The device analyzes students' facial expressions and voice tone via an emotion engine, recognizing their emotional state in real time. This recognized emotional data is continuously transmitted to the server.

[0127] Step 3:

[0128] The server uses AI algorithms to analyze collected educational and emotional data and generate optimal educational plans tailored to the individual needs of each student. These plans include not only standard lesson topics but also teaching methods that take emotional data into consideration.

[0129] Step 4:

[0130] The device displays generated lesson plans and up-to-date sentiment data to teachers via a user interface. This allows teachers to obtain information to provide instruction that considers both student progress and emotional aspects.

[0131] Step 5:

[0132] The user (teacher) provides instruction based on information from the device, adjusting the lesson content and teaching methods to suit the individual student's needs. For example, if a student shows signs of misunderstanding during class, time will be allocated to supplement that information.

[0133] Step 6:

[0134] The terminal reports test results and emotional state data obtained during class to the server for further analysis. This allows the server to determine if adjustments to the teaching plan are necessary and to make corrections in real time as needed.

[0135] Step 7:

[0136] The server re-evaluates all data and makes a new assessment of the educational standards. Based on this, it generates feedback on the next day's lesson plan and teaching materials, and provides it to teachers and administrators via terminals.

[0137] This entire process enables educational support that responds quickly to changes in students' learning progress and emotions, resulting in effective individualized instruction.

[0138] (Example 2)

[0139] Next, we will describe Example 2. In the following description, the data processing device 12 will be referred to as the "server" and the smart device 14 as the "terminal".

[0140] In today's educational setting, providing effective education tailored to the individual needs of learners requires not only transmitting learning content but also understanding learners' emotional states and developing flexible educational plans based on those states. However, traditional educational systems have struggled to grasp students' emotional states in real time and quickly provide individualized educational plans accordingly. Furthermore, there has been a lack of means to automatically adjust plans to take into account the different learning progress and educational environments of different regions and individuals.

[0141] The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 2 is realized by the following means.

[0142] In this invention, the server includes means for collecting and storing information in the field of education, means for analyzing the stored information and automatically generating educational plans, and means for optimizing teaching materials and evaluation means based on the generated educational plans. This makes it possible to provide flexible and effective education in real time that is tailored to the individual needs of learners.

[0143] "Information in the field of education" is a general term for data that includes various types of information such as lesson plans, teaching materials, assessment results, and learner responses.

[0144] "Means of storage" refers to the technical means of recording and preserving collected data.

[0145] "Methods for analyzing and automatically generating educational plans" refers to methods for analyzing collected data and automatically constructing educational plans tailored to individual educational goals and learning progress.

[0146] "Means for optimizing teaching materials and assessment methods" refers to means of adjusting the teaching materials and assessment methods used based on the learners' needs and emotional states in order to provide more effective education.

[0147] "Means of recognizing emotional states and reflecting that information in educational plans" refers to technical methods for analyzing emotions from learners' facial expressions and voices and adjusting educational content accordingly.

[0148] "Means equipped with display functions for providing customized instruction" refers to functions that display individual learning plans and progress of learners through an interface and provide instruction based on them.

[0149] "Means of updating educational information in real time" refers to means of instantly updating educational plans and learner status based on the latest data.

[0150] This invention provides a concrete model for building a system that provides individualized education based on the emotional state of learners in educational settings. This system consists of four main components: a server, a terminal, a user, and an emotion engine.

[0151] The server collects and stores information in the field of education. Specifically, data including lesson plans, teaching materials, evaluation results, and student responses are automatically collected through online platforms and databases. This data is stored in a database on the server.

[0152] The server analyzes collected data and generates personalized learning plans for each learner. Using programming languages ​​such as Python and machine learning algorithms, it analyzes learners' performance trends and emotional patterns, providing flexible learning plans based on this analysis. These plans optimize teaching materials and assessment methods, ensuring they meet individual needs.

[0153] The emotion engine analyzes the learner's facial expressions and voice to recognize their emotional state in real time. By using an open-source emotion recognition library, it identifies emotions such as "joy" and "anxiety" from the learner's facial expressions and tone of voice, and sends that information to the server.

[0154] The device provides a user interface that allows learners and teachers to view generated lesson plans and sentiment analysis results. Through this interface, teachers can provide individualized instruction and customized learning materials. The device also transmits the latest educational information to the server in real time, ensuring that the most up-to-date data is always shared.

[0155] Teachers, as users of the system, can utilize the data provided by the server to tailor instruction to the individual needs of their students. For example, if analysis of emotional data reveals that a particular student is showing anxiety during class, they can plan additional support accordingly.

[0156] As a concrete example, one could consider creating an individualized educational plan by inputting a prompt message such as, "Propose appropriate guidance based on a student's emotional data," into an AI model. This system is expected to promote learner growth by providing effective education tailored to individual needs.

[0157] The flow of the specific processing in Example 2 will be explained using Figure 13.

[0158] Step 1:

[0159] The server collects information in the field of education. Specifically, it retrieves lesson plans, teaching materials, test results, and student response data from online platforms and stores them in a database. The input to this process is digital data from various educational institutions and tools, and the output is structured educational information stored in the database.

[0160] Step 2:

[0161] The server analyzes the accumulated data. Using programming languages ​​such as Python, it processes the data with machine learning algorithms to analyze student performance trends and emotional patterns. The input data is education-related information stored in a database, and the output is an education plan optimized for individual learners.

[0162] Step 3:

[0163] The emotion engine captures the user's facial expressions and voice tone in real time via the camera and microphone built into the device. This allows it to analyze and determine the student's emotional state. The input is the student's facial expressions and voice data, and the output is an emotion label such as "joy" or "anxiety."

[0164] Step 4:

[0165] The server adjusts the educational plan using the results of emotion recognition. Based on the emotion data, it adjusts the teaching materials and assessment methods in the existing educational plan. In this step, the emotion data and the existing educational plan are used as input, and a new, adjusted educational plan is output.

[0166] Step 5:

[0167] The device displays the generated educational plan and sentiment analysis results on its interface. This allows teachers and students to review the information and use it in their learning activities. The input is the adjusted educational plan data, and the output is the information displayed on the device's screen.

[0168] Step 6:

[0169] The user, acting as the teacher, provides individualized instruction based on the provided educational plan and emotional data. The teacher adjusts their approach during lessons, referencing the information displayed on the screen, to support students according to their needs. Input consists of the educational plan and emotional information viewable on the terminal screen, while output is the specific instruction and material preparation undertaken by the teacher.

[0170] (Application Example 2)

[0171] Next, we will explain application example 2. In the following explanation, the data processing device 12 will be referred to as a "server" and the smart device 14 as a "terminal".

[0172] In educational settings, it is crucial to provide optimal educational plans that take into account the individual feelings and learning progress of each student, but achieving this presents many challenges. Traditional methods make it difficult to address the individual feelings and needs of students while ensuring unified educational standards, and efficiently utilizing resources across educational institutions in the region is also a challenge.

[0173] The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means.

[0174] In this invention, the server includes means for collecting and storing educational and emotional data, means for analyzing the collected data and automatically generating educational plans, and means for sharing optimal educational resources across all educational institutions in the region. This makes it possible to provide individualized educational plans based on each student's emotional state and learning progress. Furthermore, by efficiently utilizing educational resources across the region, an overall improvement in educational standards can be expected.

[0175] "Educational data" refers to information regarding lesson plans, teaching materials, test results, and student learning progress in educational settings.

[0176] "Emotional data" refers to information about the emotional state obtained by analyzing the facial expressions and tone of voice of students and teachers.

[0177] An "educational plan" refers to a teaching plan generated based on collected educational and emotional data, optimized to meet the individual learning needs of each student.

[0178] "Educational materials" refer to teaching materials and information resources for learning activities provided based on the educational plan.

[0179] "Measurement methods" refer to tests and assessment methods used to evaluate students' learning outcomes and educational progress.

[0180] "Display means" refers to an interface that allows teachers and students to check educational progress, individualized instruction plans, and other information.

[0181] "Educational institutions within a region" refers to a collection of educational facilities, such as schools and educational centers, located in a specific area.

[0182] "Educational standards" refer to indicators that serve as criteria for measuring the quality and outcomes of education.

[0183] "Efficient use of resources" refers to managing and allocating the necessary personnel, teaching materials, information, etc., for educational activities in the most optimal way, and using them effectively without waste.

[0184] To implement this invention, a system will be constructed in which a server, terminals, and users play important roles. The server will have the function of collecting and storing educational data and emotional data. Educational data will include lesson plans, teaching materials, and test results, while emotional data will include information on the emotional state based on the facial expressions and tone of voice of students and teachers. This data will be analyzed using Python or JavaScript (registered trademark), and a means will be constructed to automatically generate individualized educational plans for students using a generative AI model.

[0185] The server also functions as a platform for sharing optimal educational resources across educational institutions within the region. A smartphone app built with React Native allows teachers to manage teaching progress and provides personalized educational materials and metrics through various display methods.

[0186] As a concrete example, a smartphone device uses OpenCV and the dlib library to analyze students' facial expressions and send emotional data to a server in real time. Based on this emotional data, if a student is losing interest in a particular subject, the system can help teachers suggest a new teaching plan. As a result, students' motivation to learn is maintained, and efficient education is achieved throughout the community.

[0187] An example of a prompt would be, "Based on data on students' emotional changes, please suggest teaching methods for students who have lost interest in math class." This prompt serves as a basis for a generative AI model to generate specific teaching plans, which are then provided to teachers.

[0188] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[0189] Step 1:

[0190] The server receives lesson plans, teaching materials, test results, and emotional data based on students' facial expressions and tone of voice from educational institutions. This educational and emotional data is stored in a database for accumulation. The input for this step is data from educational institutions, and the output is the information stored in the database.

[0191] Step 2:

[0192] The device uses the smartphone's camera and microphone to capture real-time emotional data from students. OpenCV and the dlib library are used to analyze facial expressions and voices and identify emotional states. The input for this step is the student's facial expressions and voice, and the output is the identified emotional data.

[0193] Step 3:

[0194] The server uses a generative AI model to analyze accumulated educational data and emotional data transmitted from terminals. The generative AI model automatically generates personalized educational plans using prompt messages. The input for this step is the educational data and emotional data to be analyzed, and the output is the automatically generated educational plan.

[0195] Step 4:

[0196] The server sends the generated lesson plan to the terminal. The lesson plan is displayed on the terminal in real time and can be viewed by the user (teacher). The input for this step is the lesson plan, and the output is the updated instructional information displayed on the terminal.

[0197] Step 5:

[0198] Based on the educational plan and emotional data provided through the device, users make decisions to support the progress of lessons and individual instruction. They adjust the specific teaching materials and methods used to optimize the students' learning experience. The input for this step is instructional information from the device, and the output is the concrete implementation of optimized lessons and learning support.

[0199] 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 user input for the result of the specific processing. The control unit 46A transmits the audio data indicating 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.

[0200] Data generation model 58 is a so-called generative AI (Artificial Intelligence). An example of data generation model 58 is ChatGPT (registered trademark) (Internet search).<URL: https: / / openai.com / blog / chatgpt> ), Gemini (registered trademark) (Internet search)<url: https: gemini.google.com ?hl="ja">Examples of generative AI include the following. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 is input with prompts containing instructions, and with inference data such as audio data representing speech, text data representing text, and image data representing images. The data generation model 58 infers from the input inference data according to the instructions indicated by the prompts, and outputs the inference results in data formats such as audio data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[0201] In the above embodiment, an example was given in which specific processing is performed by the data processing device 12, but the technology of this disclosure is not limited thereto, and the specific processing may also be performed by the smart device 14.

[0202] [Second Embodiment]

[0203] Figure 3 shows an example of the configuration of the data processing system 210 according to the second embodiment.

[0204] As shown in Figure 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.

[0205] The data processing device 12 comprises a computer 22, a database 24, and a communication interface 26. The computer 22 is an example of a "computer" related to the technology of this disclosure. The computer 22 comprises a processor 28, RAM 30, and storage 32. The processor 28, RAM 30, and storage 32 are connected to a bus 34. The database 24 and the communication interface 26 are also connected to the bus 34. The communication interface 26 is connected to a network 54. An example of the network 54 is a WAN (Wide Area Network) and / or a LAN (Local Area Network).

[0206] The smart glasses 214 include a computer 36, a microphone 238, a speaker 240, a camera 42, and a communication interface 44. The computer 36 includes a processor 46, RAM 48, and storage 50. The processor 46, RAM 48, and storage 50 are connected to a bus 52. The microphone 238, speaker 240, and camera 42 are also connected to the bus 52.

[0207] The microphone 238 receives voice signals from the user 20 and receives instructions from the user 20. The microphone 238 captures the voice signals from the user 20, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio according to the instructions from the processor 46.

[0208] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an image sensor such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, and captures images of the area around the user 20 (for example, an imaging range defined by a field of view equivalent to the width of a typical healthy person's field of vision).

[0209] Communication interface 44 is connected to network 54. Communication interfaces 44 and 26 are responsible for the exchange of various information between processor 46 and processor 28 via network 54. The exchange of various information between processor 46 and processor 28 using communication interfaces 44 and 26 is performed in a secure manner.

[0210] Figure 4 shows an example of the main functions of the data processing device 12 and the smart glasses 214. As shown in Figure 4, the data processing device 12 performs specific processing using the processor 28. The storage 32 stores the specific processing program 56.

[0211] The specific processing program 56 is an example of a "program" relating to the technology of this 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 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.

[0212] The storage 32 stores the data generation model 58 and the emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290.

[0213] In the smart glasses 214, the processor 46 performs the reception output processing. The storage 50 stores the reception output program 60. The processor 46 reads the reception output program 60 from the storage 50 and executes the read reception output program 60 on the RAM 48. The reception output processing is realized by the processor 46 operating as a control unit 46A according to the reception output program 60 executed on the RAM 48.

[0214] Next, the identification processing performed by the identification processing unit 290 of the data processing device 12 will be described. In the following description, the data processing device 12 will be referred to as the "server" and the smart glasses 214 will be referred to as the "terminal".

[0215] This invention provides a system for improving the efficiency and standardization of lesson planning in educational settings. It consists of three main components: a server, a terminal, and a user, each playing a specific role.

[0216] First, the server collects and stores educational data. This includes past lesson plans, teaching materials, test results, and success stories from other schools for each school and region. The server analyzes this data using AI algorithms and automatically generates educational plans to achieve a unified educational level. The generated plans are then adjusted according to the specific events and activities of each grade level and school.

[0217] Furthermore, the server optimizes teaching materials and assessment tests based on the analysis results. In this process, it refers to past student performance data and comprehension levels to provide materials and test questions of appropriate difficulty. For example, for units in mathematics where the average score was low in the past, supplementary materials might be recommended.

[0218] Next, the device provides a user interface for teachers and students. Through this interface, teachers can intuitively check the annual lesson plan and students' progress. In addition, the device sends the test results taken by students to the server in real time, so the database on the server is always kept up-to-date.

[0219] Finally, based on the information provided, the user (teacher) identifies each student's strengths and weaknesses and provides individualized instruction. For example, if a student performs poorly in reading comprehension in Japanese, the teacher can support that student using additional materials recommended by the system. This system allows teachers to reduce their preparation workload and provide higher quality education while tailoring instruction to each individual student.

[0220] As a concrete example, one elementary school implemented this system to standardize the curriculum content for each grade level and to flexibly adjust the curriculum even when there are common events or activities at specific times. In this way, the quality of education is improved, and effective support for human resource development is realized.

[0221] The following describes the processing flow.

[0222] Step 1:

[0223] The server collects educational data such as lesson plans, teaching materials, and test results from educational settings and stores them in a database. This process is automated and regularly updated, ensuring that new information is always reflected.

[0224] Step 2:

[0225] The server analyzes accumulated data using AI algorithms and generates an optimal educational plan derived from past performance and successful examples from other schools. This plan includes a list of lesson themes and teaching materials to be used each month.

[0226] Step 3:

[0227] The server optimizes educational materials and assessment tests based on the generated lesson plan. It automatically selects the most suitable materials and test questions for each lesson, taking into account difficulty levels and student comprehension.

[0228] Step 4:

[0229] The device provides teachers with an interface to monitor teaching plans and student progress. The interface is designed to be visually intuitive and easy to access.

[0230] Step 5:

[0231] The terminal transmits the results of tests taken by students and their class attendance records to the server in real time. This communication ensures that the server's database is always updated with the latest information.

[0232] Step 6:

[0233] Based on information provided by the server, users (teachers) analyze each student's strengths and weaknesses and provide individualized instruction. Users utilize the system-recommended teaching materials and supplementary resources to provide education tailored to each student.

[0234] Step 7:

[0235] Users (teachers) can adjust the generated lesson plans as needed and customize the content to suit specific events and occasions. This flexibility allows the plans to be optimized to the specific needs and circumstances of the school.

[0236] (Example 1)

[0237] Next, we will describe Example 1. In the following description, the data processing device 12 will be referred to as the "server," and the smart glasses 214 will be referred to as the "terminal."

[0238] Improving the quality and efficiency of individualized instruction is a crucial challenge in modern education. Traditional methods require teachers to spend a significant amount of time creating lesson plans, making it difficult to provide instruction tailored to the individual needs of each student. Furthermore, developing flexible educational plans that take into account the educational standards and characteristics of each school and region is also challenging.

[0239] The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 1 is realized by the following means.

[0240] In this invention, the server includes means for collecting and storing educational information, means for analyzing the collected information and utilizing a generative model for automatically generating educational plans, and means for analyzing student performance data and recommending additional teaching materials according to the student's level of understanding. This enables teachers to provide flexible and effective instruction tailored to individual students.

[0241] "Educational information" refers to information related to education, such as past lesson plans, teaching materials, test results, and success stories from schools and communities.

[0242] A "generative model" refers to a computational algorithm or artificial intelligence structure that automatically creates educational plans based on accumulated educational information.

[0243] "Educational materials" refer to teaching materials, reference materials, and other items and digital content used to support learning in classes and instruction.

[0244] "Evaluation methods" refer to tests, questionnaires, and other assessment methods used to measure students' learning progress and understanding.

[0245] A "display device" refers to a screen or device used to visually display educational information, lesson plans, student progress, and so on.

[0246] "Supplementary materials" are materials provided in addition to standard materials to reinforce learning, tailored to each student's individual level of understanding and academic performance.

[0247] This invention is a system for improving the efficiency and standardization of lesson planning in educational settings. The system mainly consists of three components: a server, a terminal, and a user.

[0248] The server collects and stores educational information, including past performance data, lesson plans, and success stories from each educational institution. The server stores this information in a database and uses a generative model to automatically generate lesson plans. The software used includes a database management system and an AI model. For example, when creating a math lesson plan, it recommends appropriate units based on past performance data.

[0249] The generation of educational plans is performed by analyzing data collected by the server and inputting it into a generation AI model using prompt messages. For example, a prompt message such as, "Please create a lesson plan for third-grade elementary school math for the next academic year. Consider past test results and successful examples, and suggest additional materials for units that need reinforcement," might be used.

[0250] The terminal provides a user interface for teachers and students. Through this interface, teachers can view generated lesson plans and student progress. The terminal provides a dashboard-style display via a web browser and plays a role in synchronizing data with the server in real time.

[0251] The teacher, as a user, provides individualized instruction based on information obtained through the device. For example, a student who performs poorly in reading comprehension in Japanese language arts can be given additional materials to improve their understanding. In this way, teachers can reduce the burden of creating lesson plans while providing high-quality individualized instruction.

[0252] The flow of the specific processing in Example 1 will be explained using Figure 11.

[0253] Step 1:

[0254] The server collects educational information from each educational institution and stores it in a database. It receives educational information such as past grade data, lesson plans, teaching materials, and test results as input. This data is collected using data ingestion scripts via CSV files or APIs. As output, the complete dataset is stored in the database, ready for subsequent processing.

[0255] Step 2:

[0256] The server analyzes the accumulated educational information and inputs it into the generating AI model using prompt statements. These prompt statements describe in detail the conditions necessary for automatically generating educational plans. The AI ​​model receives educational data stored in the database and prompt statements as input. As output, it proposes educational plans tailored to specific grades and subjects. Specifically, to generate a math lesson plan, a prompt statement such as "Please create a math lesson plan for third grade elementary school students for the next academic year" is used.

[0257] Step 3:

[0258] The server optimizes teaching materials and assessment methods based on the generated educational plan. It receives an educational plan created by a generating AI model as input. The server analyzes past performance data and generates teaching materials and test questions tailored to the student's level of understanding. As output, appropriate teaching materials and tests are prepared for each unit. Specifically, if a student performs poorly in a particular unit, the server automatically suggests supplementary materials to reinforce that unit.

[0259] Step 4:

[0260] The terminal provides a user interface for teachers and students. It receives lesson plans, teaching materials, and student progress data from the server as input. The terminal displays this information in a dashboard format for intuitive operation. However, since each user interface is provided via a web browser, real-time data synchronization with the server is necessary. As output, teachers can link lesson plans and monitor student progress.

[0261] Step 5:

[0262] The teacher, as the user, provides instruction tailored to each student's level of understanding based on information obtained through the device. Inputs include the displayed educational plan and student progress data. Next, the teacher provides additional materials and individual advice. Output is that the teacher supports and improves student learning through appropriate instruction. Specifically, the teacher improves the quality of instruction by preparing additional materials for students who have insufficient understanding of reading comprehension in Japanese.

[0263] (Application Example 1)

[0264] Next, we will explain Application Example 1. In the following explanation, the data processing device 12 will be referred to as the "server," and the smart glasses 214 will be referred to as the "terminal."

[0265] To reduce the burden of developing and implementing lesson plans in educational settings and to strengthen individualized instruction, efficient and standardized educational plans are necessary. However, currently, creating and managing educational plans requires significant time and resources, and there are challenges, particularly in providing education tailored to the individual characteristics of each student. Furthermore, there is a lack of individually customized teaching materials based on students' learning progress, so the introduction of a more immediate and effective educational support system is needed.

[0266] The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 1 is realized by the following means.

[0267] In this invention, the server includes means for collecting and storing educational data, means for analyzing the collected data and automatically generating educational plans, means for optimizing educational materials and assessment tests based on the generated educational plans, and means for providing customized educational materials based on the progress of the students. This not only enables the streamlining and standardization of lesson plans in educational settings, but also enables the provision of educational materials tailored to each student, thereby improving the quality of individualized instruction.

[0268] "Educational data" refers to information about the educational process, including lesson plans, teaching materials, test results, student performance and comprehension levels, and success stories from other schools.

[0269] "Means for automatically generating educational plans" refers to devices or programs that analyze collected educational data using AI algorithms, etc., and automatically create lesson plans suitable for each educational institution with a unified educational level.

[0270] "Means for optimizing educational materials and assessment tests" refers to devices or systems that have the function of automatically selecting and distributing educational materials and test questions of appropriate difficulty levels based on past performance data and comprehension information.

[0271] "Means of managing educational progress" refers to systems and devices that grasp students' learning progress and understanding in real time and provide this information in a visualized format.

[0272] "Means for displaying an interface for providing individualized instruction" refers to devices or methods that provide a user interface for teachers to identify each student's strengths and weaknesses and display information for use when providing individualized instruction.

[0273] "Means of providing customized educational materials based on the student's progress" refers to a system that has the function of dynamically selecting and outputting educational materials based on learning history in order to provide materials whose content is adjusted according to the student's learning situation.

[0274] "Means for controlling automated devices equipped with educational support devices" refers to a system that uses programming to control robots or digital devices with educational support functions and execute specified educational content.

[0275] To realize this invention, it is necessary to build an educational support system. This system will operate through the interaction of a server, terminals, and users (primarily teachers).

[0276] The server is responsible for collecting and storing educational data. High-performance cloud servers are used as hardware, and a database management system such as AWS DynamoDB is employed as software. Furthermore, AI libraries such as TensorFlow are used to analyze the collected data and automatically generate educational plans tailored to each educational institution. The generated educational plans are transmitted to educational terminals in real time.

[0277] Next, the educational terminal mainly functions as an interface for teachers and students. It adopts small computing devices such as Raspberry Pi and Jetson Nano to assist in the execution of teaching plans in the classroom and remotely. The terminal provides the generated teaching plans and optimized teaching materials to teachers, and keeps all information up-to-date by sending students' progress data to the server.

[0278] Through the interface of this education system, users can understand the strengths and weaknesses of each student and provide individualized guidance. For example, when a teacher needs to provide additional guidance to a specific student, the teacher can use the customized teaching materials proposed by the system for guidance.

[0279] As a specific example, if it is found that a certain student is having trouble with a specific unit of mathematics, the server generates appropriate reinforcement teaching materials based on past data and provides them to that student through the terminal. The teacher then follows up as appropriate based on the teaching materials.

[0280] At this time, a prompt sentence can be created using the generative AI model to propose questions according to the student's comprehension level. For example, it is assumed that a prompt sentence such as "Please provide a video teaching material for specifically explaining an arithmetic concept that is difficult for students to understand" is used.

[0281] The flow of the specific process in Application Example 1 will be described using FIG. 12.

[0282] Step 1:

[0283] The server collects educational data from each educational institution and stores it in AWS DynamoDB. The input is past teaching plans, teaching materials, test results, etc. sent from each school or region, and the output is that these datasets are saved in the database. Here, data processing is performed to confirm the validity of the data and convert it into the specified format.

[0284] Step 2:

[0285] The server analyzes the accumulated data using an AI algorithm (TensorFlow) and automatically generates an educational plan suitable for each school. The input is the educational data saved in Step 1, and the output is an integrated educational plan considering the events specific to each academic year and school. Here, data operations for data analysis and pattern recognition by AI are included.

[0286] Step 3:

[0287] The server optimizes educational materials and evaluation tests based on the generated educational plan. The input is the integrated educational plan, and the output is a question set and teaching materials according to the students' understanding level. Data processing is performed to select suitable teaching materials by referring to past performance data.

[0288] Step 4:

[0289] The terminal provides the optimized teaching materials and tests received from the server to the teacher. The input is the information of the optimized teaching materials from the server, and the output is displayed as teaching materials and tests that can be used by the teacher in class. Here, information visualization on the user interface is performed.

[0290] Step 5:

[0291] The user (teacher) checks the learning progress of the students through the terminal and identifies the strengths and weaknesses of each student. The input is the test results and progress status of the students displayed on the terminal, and the output is a plan for individual guidance. Here, specific guidance guidelines are determined based on the delivered content.

[0292] Step 6:

[0293] The server updates the test results and learning progress of the students received from the terminal in the database in real time. The input is the learning data transmitted from the terminal, and the output is an updated educational data set. Here, data synchronization and consistency verification are performed.

[0294] Step 7:

[0295] The terminal uses an AI model to generate solutions and teaching materials based on prompts generated by the server, thereby supporting student learning. The input is a prompt from the teacher, and the output is the optimal solution and teaching materials generated by the AI. For example, the prompt "Please provide video teaching materials to concretely explain mathematical concepts that students find difficult to understand" is entered, and the system displays the video teaching materials.

[0296] Furthermore, an emotion engine that estimates the user's emotions may be incorporated. That is, the identification processing unit 290 may use the emotion identification model 59 to estimate the user's emotions and perform identification processing using the user's emotions.

[0297] This invention provides an educational support system that combines an emotion engine to optimize instruction in educational settings. It consists of four main components: a server, a terminal, a user, and an emotion engine.

[0298] First, the server collects and stores educational data. This includes lesson plans, teaching materials, test results, and student response data obtained from the classroom. Emotional data recognized by the emotion engine is also sent to the server and stored in the database. The server analyzes this data and automatically generates educational plans tailored to individual needs while maintaining a consistent educational standard. These plans include general lesson themes as well as adjustments based on emotional data.

[0299] The emotion engine analyzes the user's (student or teacher's) facial expressions and tone of voice to recognize their emotional state in real time. This data is used to help teachers understand students' comprehension levels and interest levels. For example, if a student appears bored during class, the system will suggest new teaching materials or activities to capture their attention.

[0300] Next, the terminal provides a user interface to enable teachers and students to easily understand this plan and the accompanying changes. Based on the information obtained here, the teacher conducts individualized guidance for each student. Also, the terminal transmits the test results and the emotional status of the students obtained during the class to the server in real time.

[0301] The user (teacher) can make the most of the educational plan and emotion-based information provided by the server to conduct individualized guidance. For example, if a student shows uneasiness during a particular subject class, the teacher can grasp the situation and adjust the teaching method with additional support or a different approach.

[0302] This invention not only streamlines the educational plan but also realizes more individualized guidance by considering the emotional aspect. As a specific example, in a certain junior high school, this system was utilized to record the daily emotional changes of students and adjust the weekly guidance plan based on them, resulting in a successful improvement in learning motivation. In this way, the invention provides effective educational support and promotes the growth of individual students.

[0303] The following describes the processing flow.

[0304] Step 1:

[0305] The server collects the class plan, teaching materials, test results, and the operation data of students from the educational site and stores them in the database. This collection is carried out through a periodically automated process and is always maintained as the latest educational data.

[0306] Step 2:

[0307] The terminal analyzes the expressions and voice tones of the students via the emotion engine and recognizes the emotional status in real time. This recognized emotion data is continuously transmitted to the server.

[0308] Step 3:

[0309] The server uses AI algorithms to analyze collected educational and emotional data and generate optimal educational plans tailored to the individual needs of each student. These plans include not only standard lesson topics but also teaching methods that take emotional data into consideration.

[0310] Step 4:

[0311] The device displays generated lesson plans and up-to-date sentiment data to teachers via a user interface. This allows teachers to obtain information to provide instruction that considers both student progress and emotional aspects.

[0312] Step 5:

[0313] The user (teacher) provides instruction based on information from the device, adjusting the lesson content and teaching methods to suit the individual student's needs. For example, if a student shows signs of misunderstanding during class, time will be allocated to supplement that information.

[0314] Step 6:

[0315] The terminal reports test results and emotional state data obtained during class to the server for further analysis. This allows the server to determine if adjustments to the teaching plan are necessary and to make corrections in real time as needed.

[0316] Step 7:

[0317] The server re-evaluates all data and makes a new assessment of the educational standards. Based on this, it generates feedback on the next day's lesson plan and teaching materials, and provides it to teachers and administrators via terminals.

[0318] This entire process enables educational support that responds quickly to changes in students' learning progress and emotions, resulting in effective individualized instruction.

[0319] (Example 2)

[0320] Next, we will describe Example 2. In the following description, the data processing device 12 will be referred to as the "server" and the smart glasses 214 will be referred to as the "terminal".

[0321] In today's educational setting, providing effective education tailored to the individual needs of learners requires not only transmitting learning content but also understanding learners' emotional states and developing flexible educational plans based on those states. However, traditional educational systems have struggled to grasp students' emotional states in real time and quickly provide individualized educational plans accordingly. Furthermore, there has been a lack of means to automatically adjust plans to take into account the different learning progress and educational environments of different regions and individuals.

[0322] The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 2 is realized by the following means.

[0323] In this invention, the server includes means for collecting and storing information in the field of education, means for analyzing the stored information and automatically generating educational plans, and means for optimizing teaching materials and evaluation means based on the generated educational plans. This makes it possible to provide flexible and effective education in real time that is tailored to the individual needs of learners.

[0324] "Information in the field of education" is a general term for data that includes various types of information such as lesson plans, teaching materials, assessment results, and learner responses.

[0325] "Means of storage" refers to the technical means of recording and preserving collected data.

[0326] "Methods for analyzing and automatically generating educational plans" refers to methods for analyzing collected data and automatically constructing educational plans tailored to individual educational goals and learning progress.

[0327] "Means for optimizing teaching materials and assessment methods" refers to means of adjusting the teaching materials and assessment methods used based on the learners' needs and emotional states in order to provide more effective education.

[0328] "Means of recognizing emotional states and reflecting that information in educational plans" refers to technical methods for analyzing emotions from learners' facial expressions and voices and adjusting educational content accordingly.

[0329] "Means equipped with display functions for providing customized instruction" refers to functions that display individual learning plans and progress of learners through an interface and provide instruction based on them.

[0330] "Means of updating educational information in real time" refers to means of instantly updating educational plans and learner status based on the latest data.

[0331] This invention provides a concrete model for building a system that provides individualized education based on the emotional state of learners in educational settings. This system consists of four main components: a server, a terminal, a user, and an emotion engine.

[0332] The server collects and stores information in the field of education. Specifically, data including lesson plans, teaching materials, evaluation results, and student responses are automatically collected through online platforms and databases. This data is stored in a database on the server.

[0333] The server analyzes collected data and generates personalized learning plans for each learner. Using programming languages ​​such as Python and machine learning algorithms, it analyzes learners' performance trends and emotional patterns, providing flexible learning plans based on this analysis. These plans optimize teaching materials and assessment methods, ensuring they meet individual needs.

[0334] The emotion engine analyzes the learner's facial expressions and voice to recognize their emotional state in real time. By using an open-source emotion recognition library, it identifies emotions such as "joy" and "anxiety" from the learner's facial expressions and tone of voice, and sends that information to the server.

[0335] The device provides a user interface that allows learners and teachers to view generated lesson plans and sentiment analysis results. Through this interface, teachers can provide individualized instruction and customized learning materials. The device also transmits the latest educational information to the server in real time, ensuring that the most up-to-date data is always shared.

[0336] Teachers, as users of the system, can utilize the data provided by the server to tailor instruction to the individual needs of their students. For example, if analysis of emotional data reveals that a particular student is showing anxiety during class, they can plan additional support accordingly.

[0337] As a concrete example, one could consider creating an individualized educational plan by inputting a prompt message such as, "Propose appropriate guidance based on a student's emotional data," into an AI model. This system is expected to promote learner growth by providing effective education tailored to individual needs.

[0338] The flow of the specific processing in Example 2 will be explained using Figure 13.

[0339] Step 1:

[0340] The server collects information in the field of education. Specifically, it retrieves lesson plans, teaching materials, test results, and student response data from online platforms and stores them in a database. The input to this process is digital data from various educational institutions and tools, and the output is structured educational information stored in the database.

[0341] Step 2:

[0342] The server analyzes the accumulated data. Using programming languages ​​such as Python, it processes the data with machine learning algorithms to analyze student performance trends and emotional patterns. The input data is education-related information stored in a database, and the output is an education plan optimized for individual learners.

[0343] Step 3:

[0344] The emotion engine captures the user's facial expressions and voice tone in real time via the camera and microphone built into the device. This allows it to analyze and determine the student's emotional state. The input is the student's facial expressions and voice data, and the output is an emotion label such as "joy" or "anxiety."

[0345] Step 4:

[0346] The server adjusts the educational plan using the results of emotion recognition. Based on the emotion data, it adjusts the teaching materials and assessment methods in the existing educational plan. In this step, the emotion data and the existing educational plan are used as input, and a new, adjusted educational plan is output.

[0347] Step 5:

[0348] The device displays the generated educational plan and sentiment analysis results on its interface. This allows teachers and students to review the information and use it in their learning activities. The input is the adjusted educational plan data, and the output is the information displayed on the device's screen.

[0349] Step 6:

[0350] The user, acting as the teacher, provides individualized instruction based on the provided educational plan and emotional data. The teacher adjusts their approach during lessons, referencing the information displayed on the screen, to support students according to their needs. Input consists of the educational plan and emotional information viewable on the terminal screen, while output is the specific instruction and material preparation undertaken by the teacher.

[0351] (Application Example 2)

[0352] Next, we will explain application example 2. In the following explanation, the data processing device 12 will be referred to as the "server," and the smart glasses 214 will be referred to as the "terminal."

[0353] In educational settings, it is crucial to provide optimal educational plans that take into account the individual feelings and learning progress of each student, but achieving this presents many challenges. Traditional methods make it difficult to address the individual feelings and needs of students while ensuring unified educational standards, and efficiently utilizing resources across educational institutions in the region is also a challenge.

[0354] The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means.

[0355] In this invention, the server includes means for collecting and storing educational and emotional data, means for analyzing the collected data and automatically generating educational plans, and means for sharing optimal educational resources across all educational institutions in the region. This makes it possible to provide individualized educational plans based on each student's emotional state and learning progress. Furthermore, by efficiently utilizing educational resources across the region, an overall improvement in educational standards can be expected.

[0356] "Educational data" refers to information regarding lesson plans, teaching materials, test results, and student learning progress in educational settings.

[0357] "Emotional data" refers to information about the emotional state obtained by analyzing the facial expressions and tone of voice of students and teachers.

[0358] An "educational plan" refers to a teaching plan generated based on collected educational and emotional data, optimized to meet the individual learning needs of each student.

[0359] "Educational materials" refer to teaching materials and information resources for learning activities provided based on the educational plan.

[0360] "Measurement methods" refer to tests and assessment methods used to evaluate students' learning outcomes and educational progress.

[0361] "Display means" refers to an interface that allows teachers and students to check educational progress, individualized instruction plans, and other information.

[0362] "Educational institutions within a region" refers to a collection of educational facilities, such as schools and educational centers, located in a specific area.

[0363] "Educational standards" refer to indicators that serve as criteria for measuring the quality and outcomes of education.

[0364] "Efficient use of resources" refers to managing and allocating the necessary personnel, teaching materials, information, etc., for educational activities in the most optimal way, and using them effectively without waste.

[0365] To implement this invention, a system will be constructed in which a server, terminals, and users play important roles. The server will have the function of collecting and storing educational data and emotional data. Educational data will include lesson plans, teaching materials, and test results, while emotional data will include information on the emotional state based on the facial expressions and tone of voice of students and teachers. This data will be analyzed using Python or JavaScript, and a means will be constructed to automatically generate individualized educational plans for students using a generative AI model.

[0366] The server also functions as a platform for sharing optimal educational resources across educational institutions within the region. A smartphone app built with React Native allows teachers to manage teaching progress and provides personalized educational materials and metrics through various display methods.

[0367] As a concrete example, a smartphone device uses OpenCV and the dlib library to analyze students' facial expressions and send emotional data to a server in real time. Based on this emotional data, if a student is losing interest in a particular subject, the system can help teachers suggest a new teaching plan. As a result, students' motivation to learn is maintained, and efficient education is achieved throughout the community.

[0368] An example of a prompt would be, "Based on data on students' emotional changes, please suggest teaching methods for students who have lost interest in math class." This prompt serves as a basis for a generative AI model to generate specific teaching plans, which are then provided to teachers.

[0369] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[0370] Step 1:

[0371] The server receives lesson plans, teaching materials, test results, and emotional data based on students' facial expressions and tone of voice from educational institutions. This educational and emotional data is stored in a database for accumulation. The input for this step is data from educational institutions, and the output is the information stored in the database.

[0372] Step 2:

[0373] The device uses the smartphone's camera and microphone to capture real-time emotional data from students. OpenCV and the dlib library are used to analyze facial expressions and voices and identify emotional states. The input for this step is the student's facial expressions and voice, and the output is the identified emotional data.

[0374] Step 3:

[0375] The server uses a generative AI model to analyze accumulated educational data and emotional data transmitted from terminals. The generative AI model automatically generates personalized educational plans using prompt messages. The input for this step is the educational data and emotional data to be analyzed, and the output is the automatically generated educational plan.

[0376] Step 4:

[0377] The server sends the generated lesson plan to the terminal. The lesson plan is displayed on the terminal in real time and can be viewed by the user (teacher). The input for this step is the lesson plan, and the output is the updated instructional information displayed on the terminal.

[0378] Step 5:

[0379] Based on the educational plan and emotional data provided through the device, users make decisions to support the progress of lessons and individual instruction. They adjust the specific teaching materials and methods used to optimize the students' learning experience. The input for this step is instructional information from the device, and the output is the concrete implementation of optimized lessons and learning support.

[0380] 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 user input for the result of the specific processing. The control unit 46A transmits the audio data indicating user input acquired by the microphone 238 to the data processing unit 12. In the data processing unit 12, the specific processing unit 290 acquires the audio data.

[0381] Data generation model 58 is a type of so-called generative AI (Artificial Intelligence). One example of data generation model 58 is ChatGPT (Internet search<URL: https: / / openai.com / blog / chatgpt> ), Gemini (Internet search) <url: https: gemini.google.com ?hl="ja">Examples of generative AI include the following. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 is input with prompts containing instructions, and with inference data such as audio data representing speech, text data representing text, and image data representing images. The data generation model 58 infers from the input inference data according to the instructions indicated by the prompts, and outputs the inference results in data formats such as audio data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[0382] In the above embodiment, an example was given in which specific processing is performed by the data processing device 12, but the technology of this disclosure is not limited thereto, and the specific processing may also be performed by the smart glasses 214.

[0383] [Third Embodiment]

[0384] Figure 5 shows an example of the configuration of the data processing system 310 according to the third embodiment.

[0385] As shown in Figure 5, the data processing system 310 includes a data processing device 12 and a headset terminal 314. An example of the data processing device 12 is a server.

[0386] The data processing device 12 comprises a computer 22, a database 24, and a communication interface 26. The computer 22 is an example of a "computer" related to the technology of this disclosure. The computer 22 comprises a processor 28, RAM 30, and storage 32. The processor 28, RAM 30, and storage 32 are connected to a bus 34. The database 24 and the communication interface 26 are also connected to the bus 34. The communication interface 26 is connected to a network 54. An example of the network 54 is a WAN (Wide Area Network) and / or a LAN (Local Area Network).

[0387] The headset terminal 314 includes a computer 36, a microphone 238, a speaker 240, a camera 42, a communication interface 44, and a display 343. The computer 36 includes a processor 46, RAM 48, and storage 50. The processor 46, RAM 48, and storage 50 are connected to a bus 52. The microphone 238, speaker 240, camera 42, and display 343 are also connected to the bus 52.

[0388] The microphone 238 receives voice signals from the user 20 and receives instructions from the user 20. The microphone 238 captures the voice signals from the user 20, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio according to the instructions from the processor 46.

[0389] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an image sensor such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, and captures images of the area around the user 20 (for example, an imaging range defined by a field of view equivalent to the width of a typical healthy person's field of vision).

[0390] Communication interface 44 is connected to network 54. Communication interfaces 44 and 26 are responsible for the exchange of various information between processor 46 and processor 28 via network 54. The exchange of various information between processor 46 and processor 28 using communication interfaces 44 and 26 is performed in a secure manner.

[0391] Figure 6 shows an example of the main functions of the data processing device 12 and the headset terminal 314. As shown in Figure 6, the data processing device 12 performs specific processing using the processor 28. The storage 32 stores the specific processing program 56.

[0392] The specific processing program 56 is an example of a "program" relating to the technology of this 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 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.

[0393] The storage 32 stores the data generation model 58 and the emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290.

[0394] In the headset terminal 314, the processor 46 performs the reception output processing. The storage 50 stores the reception output program 60. The processor 46 reads the reception output program 60 from the storage 50 and executes the read reception output program 60 on the RAM 48. The reception output processing is realized by the processor 46 operating as a control unit 46A according to the reception output program 60 executed on the RAM 48.

[0395] Next, the specific processing performed by the specific processing unit 290 of the data processing device 12 will be described. In the following description, the data processing device 12 will be referred to as the "server" and the headset terminal 314 will be referred to as the "terminal".

[0396] This invention provides a system for improving the efficiency and standardization of lesson planning in educational settings. It consists of three main components: a server, a terminal, and a user, each playing a specific role.

[0397] First, the server collects and stores educational data. This includes past lesson plans, teaching materials, test results, and success stories from other schools for each school and region. The server analyzes this data using AI algorithms and automatically generates educational plans to achieve a unified educational level. The generated plans are then adjusted according to the specific events and activities of each grade level and school.

[0398] Furthermore, the server optimizes teaching materials and assessment tests based on the analysis results. In this process, it refers to past student performance data and comprehension levels to provide materials and test questions of appropriate difficulty. For example, for units in mathematics where the average score was low in the past, supplementary materials might be recommended.

[0399] Next, the device provides a user interface for teachers and students. Through this interface, teachers can intuitively check the annual lesson plan and students' progress. In addition, the device sends the test results taken by students to the server in real time, so the database on the server is always kept up-to-date.

[0400] Finally, based on the information provided, the user (teacher) identifies each student's strengths and weaknesses and provides individualized instruction. For example, if a student performs poorly in reading comprehension in Japanese, the teacher can support that student using additional materials recommended by the system. This system allows teachers to reduce their preparation workload and provide higher quality education while tailoring instruction to each individual student.

[0401] As a concrete example, one elementary school implemented this system to standardize the curriculum content for each grade level and to flexibly adjust the curriculum even when there are common events or activities at specific times. In this way, the quality of education is improved, and effective support for human resource development is realized.

[0402] The following describes the processing flow.

[0403] Step 1:

[0404] The server collects educational data such as lesson plans, teaching materials, and test results from educational settings and stores them in a database. This process is automated and regularly updated, ensuring that new information is always reflected.

[0405] Step 2:

[0406] The server analyzes accumulated data using AI algorithms and generates an optimal educational plan derived from past performance and successful examples from other schools. This plan includes a list of lesson themes and teaching materials to be used each month.

[0407] Step 3:

[0408] The server optimizes educational materials and assessment tests based on the generated lesson plan. It automatically selects the most suitable materials and test questions for each lesson, taking into account difficulty levels and student comprehension.

[0409] Step 4:

[0410] The device provides teachers with an interface to monitor teaching plans and student progress. The interface is designed to be visually intuitive and easy to access.

[0411] Step 5:

[0412] The terminal transmits the results of tests taken by students and their class attendance records to the server in real time. This communication ensures that the server's database is always updated with the latest information.

[0413] Step 6:

[0414] Based on information provided by the server, users (teachers) analyze each student's strengths and weaknesses and provide individualized instruction. Users utilize the system-recommended teaching materials and supplementary resources to provide education tailored to each student.

[0415] Step 7:

[0416] Users (teachers) can adjust the generated lesson plans as needed and customize the content to suit specific events and occasions. This flexibility allows the plans to be optimized to the specific needs and circumstances of the school.

[0417] (Example 1)

[0418] Next, we will describe Example 1. In the following description, the data processing device 12 will be referred to as the "server," and the headset-type terminal 314 will be referred to as the "terminal."

[0419] Improving the quality and efficiency of individualized instruction is a crucial challenge in modern education. Traditional methods require teachers to spend a significant amount of time creating lesson plans, making it difficult to provide instruction tailored to the individual needs of each student. Furthermore, developing flexible educational plans that take into account the educational standards and characteristics of each school and region is also challenging.

[0420] The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 1 is realized by the following means.

[0421] In this invention, the server includes means for collecting and storing educational information, means for analyzing the collected information and utilizing a generative model for automatically generating educational plans, and means for analyzing student performance data and recommending additional teaching materials according to the student's level of understanding. This enables teachers to provide flexible and effective instruction tailored to individual students.

[0422] "Educational information" refers to information related to education, such as past lesson plans, teaching materials, test results, and success stories from schools and communities.

[0423] A "generative model" refers to a computational algorithm or artificial intelligence structure that automatically creates educational plans based on accumulated educational information.

[0424] "Educational materials" refer to teaching materials, reference materials, and other items and digital content used to support learning in classes and instruction.

[0425] "Evaluation methods" refer to tests, questionnaires, and other assessment methods used to measure students' learning progress and understanding.

[0426] A "display device" refers to a screen or device used to visually display educational information, lesson plans, student progress, and so on.

[0427] "Supplementary materials" are materials provided in addition to standard materials to reinforce learning, tailored to each student's individual level of understanding and academic performance.

[0428] This invention is a system for improving the efficiency and standardization of lesson planning in educational settings. The system mainly consists of three components: a server, a terminal, and a user.

[0429] The server collects and stores educational information, including past performance data, lesson plans, and success stories from each educational institution. The server stores this information in a database and uses a generative model to automatically generate lesson plans. The software used includes a database management system and an AI model. For example, when creating a math lesson plan, it recommends appropriate units based on past performance data.

[0430] The generation of educational plans is performed by analyzing data collected by the server and inputting it into a generation AI model using prompt messages. For example, a prompt message such as, "Please create a lesson plan for third-grade elementary school math for the next academic year. Consider past test results and successful examples, and suggest additional materials for units that need reinforcement," might be used.

[0431] The terminal provides a user interface for teachers and students. Through this interface, teachers can view generated lesson plans and student progress. The terminal provides a dashboard-style display via a web browser and plays a role in synchronizing data with the server in real time.

[0432] The teacher, as a user, provides individualized instruction based on information obtained through the device. For example, a student who performs poorly in reading comprehension in Japanese language arts can be given additional materials to improve their understanding. In this way, teachers can reduce the burden of creating lesson plans while providing high-quality individualized instruction.

[0433] The flow of the specific processing in Example 1 will be explained using Figure 11.

[0434] Step 1:

[0435] The server collects educational information from each educational institution and stores it in a database. It receives educational information such as past grade data, lesson plans, teaching materials, and test results as input. This data is collected using data ingestion scripts via CSV files or APIs. As output, the complete dataset is stored in the database, ready for subsequent processing.

[0436] Step 2:

[0437] The server analyzes the accumulated educational information and inputs it into the generating AI model using prompt statements. These prompt statements describe in detail the conditions necessary for automatically generating educational plans. The AI ​​model receives educational data stored in the database and prompt statements as input. As output, it proposes educational plans tailored to specific grades and subjects. Specifically, to generate a math lesson plan, a prompt statement such as "Please create a math lesson plan for third grade elementary school students for the next academic year" is used.

[0438] Step 3:

[0439] The server optimizes teaching materials and assessment methods based on the generated educational plan. It receives an educational plan created by a generating AI model as input. The server analyzes past performance data and generates teaching materials and test questions tailored to the student's level of understanding. As output, appropriate teaching materials and tests are prepared for each unit. Specifically, if a student performs poorly in a particular unit, the server automatically suggests supplementary materials to reinforce that unit.

[0440] Step 4:

[0441] The terminal provides a user interface for teachers and students. It receives lesson plans, teaching materials, and student progress data from the server as input. The terminal displays this information in a dashboard format for intuitive operation. However, since each user interface is provided via a web browser, real-time data synchronization with the server is necessary. As output, teachers can link lesson plans and monitor student progress.

[0442] Step 5:

[0443] The teacher, as the user, provides instruction tailored to each student's level of understanding based on information obtained through the device. Inputs include the displayed educational plan and student progress data. Next, the teacher provides additional materials and individual advice. Output is that the teacher supports and improves student learning through appropriate instruction. Specifically, the teacher improves the quality of instruction by preparing additional materials for students who have insufficient understanding of reading comprehension in Japanese.

[0444] (Application Example 1)

[0445] Next, we will explain Application Example 1. In the following explanation, the data processing device 12 will be referred to as the "server," and the headset-type terminal 314 will be referred to as the "terminal."

[0446] To reduce the burden of developing and implementing lesson plans in educational settings and to strengthen individualized instruction, efficient and standardized educational plans are necessary. However, currently, creating and managing educational plans requires significant time and resources, and there are challenges, particularly in providing education tailored to the individual characteristics of each student. Furthermore, there is a lack of individually customized teaching materials based on students' learning progress, so the introduction of a more immediate and effective educational support system is needed.

[0447] The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 1 is realized by the following means.

[0448] In this invention, the server includes means for collecting and storing educational data, means for analyzing the collected data and automatically generating educational plans, means for optimizing educational materials and assessment tests based on the generated educational plans, and means for providing customized educational materials based on the progress of the students. This not only enables the streamlining and standardization of lesson plans in educational settings, but also enables the provision of educational materials tailored to each student, thereby improving the quality of individualized instruction.

[0449] "Educational data" refers to information about the educational process, including lesson plans, teaching materials, test results, student performance and comprehension levels, and success stories from other schools.

[0450] "Means for automatically generating educational plans" refers to devices or programs that analyze collected educational data using AI algorithms, etc., and automatically create lesson plans suitable for each educational institution with a unified educational level.

[0451] "Means for optimizing educational materials and assessment tests" refers to devices or systems that have the function of automatically selecting and distributing educational materials and test questions of appropriate difficulty levels based on past performance data and comprehension information.

[0452] "Means of managing educational progress" refers to systems and devices that grasp students' learning progress and understanding in real time and provide this information in a visualized format.

[0453] "Means for displaying an interface for providing individualized instruction" refers to devices or methods that provide a user interface for teachers to identify each student's strengths and weaknesses and display information for use when providing individualized instruction.

[0454] "Means of providing customized educational materials based on the student's progress" refers to a system that has the function of dynamically selecting and outputting educational materials based on learning history in order to provide materials whose content is adjusted according to the student's learning situation.

[0455] "Means for controlling automated devices equipped with educational support devices" refers to a system that uses programming to control robots or digital devices with educational support functions and execute specified educational content.

[0456] To realize this invention, it is necessary to build an educational support system. This system will operate through the interaction of a server, terminals, and users (primarily teachers).

[0457] The server is responsible for collecting and storing educational data. High-performance cloud servers are used as hardware, and a database management system such as AWS DynamoDB is employed as software. Furthermore, AI libraries such as TensorFlow are used to analyze the collected data and automatically generate educational plans tailored to each educational institution. The generated educational plans are transmitted to educational terminals in real time.

[0458] Next, the educational devices primarily function as interfaces for teachers and students. Small computing devices such as Raspberry Pi and Jetson Nano are employed to support the execution of lesson plans both in the classroom and remotely. The devices provide teachers with generated lesson plans and optimized teaching materials, and keep all information up-to-date by sending student progress data to a server.

[0459] Through the interface of this educational system, users can understand each student's strengths and weaknesses and provide individualized instruction. For example, if a teacher needs additional instruction for a particular student, they can use customized teaching materials suggested by the system.

[0460] For example, if it is determined that a student is struggling with a particular unit in mathematics, the server will generate appropriate supplementary materials based on past data and provide them to the student via their device. The teacher will then follow up as needed based on these materials.

[0461] In this scenario, a generative AI model can be used to create prompts and suggest problems tailored to the students' level of understanding. For example, a prompt such as, "Please provide video materials to concretely explain mathematical concepts that students find difficult to understand," could be used.

[0462] The flow of a specific process in Application Example 1 will be explained using Figure 12.

[0463] Step 1:

[0464] The server collects educational data from various educational institutions and stores it in AWS DynamoDB. Inputs include past lesson plans, teaching materials, and test results submitted from schools and regions, while output is the storage of these datasets in the database. Data processing is performed here to verify data validity and convert it to a specified format.

[0465] Step 2:

[0466] The server analyzes the accumulated data using an AI algorithm (TensorFlow) and automatically generates an educational plan tailored to each school. The input is the educational data saved in Step 1, and the output is an integrated educational plan that takes into account events specific to each grade and school. This involves data analysis and data calculations for pattern recognition using AI.

[0467] Step 3:

[0468] The server optimizes educational materials and assessment tests based on the generated educational plan. The input is the integrated educational plan, and the output is workbooks and materials tailored to the students' level of understanding. Past performance data is referenced to process the data and select appropriate materials.

[0469] Step 4:

[0470] The terminal provides teachers with optimized teaching materials and tests received from the server. The input is information about the optimized teaching materials from the server, and the output is displayed to the teacher as teaching materials and tests that can be used in class. Information visualization is performed on the user interface.

[0471] Step 5:

[0472] The user (teacher) checks students' learning progress through the device and identifies each student's strengths and weaknesses. The input is the student's test results and progress displayed on the device, and the output is an individualized instruction plan. Here, specific instructional policies are determined based on the delivered content.

[0473] Step 6:

[0474] The server updates the database in real time with student test results and learning progress received from terminals. The input is learning data sent from terminals, and the output is the updated educational dataset. Data synchronization and consistency checks are performed here.

[0475] Step 7:

[0476] The terminal uses an AI model to generate solutions and teaching materials based on prompts generated by the server, thereby supporting student learning. The input is a prompt from the teacher, and the output is the optimal solution and teaching materials generated by the AI. For example, the prompt "Please provide video teaching materials to concretely explain mathematical concepts that students find difficult to understand" is entered, and the system displays the video teaching materials.

[0477] Furthermore, an emotion engine that estimates the user's emotions may be incorporated. That is, the identification processing unit 290 may use the emotion identification model 59 to estimate the user's emotions and perform identification processing using the user's emotions.

[0478] This invention provides an educational support system that combines an emotion engine to optimize instruction in educational settings. It consists of four main components: a server, a terminal, a user, and an emotion engine.

[0479] First, the server collects and stores educational data. This includes lesson plans, teaching materials, test results, and student response data obtained from the classroom. Emotional data recognized by the emotion engine is also sent to the server and stored in the database. The server analyzes this data and automatically generates educational plans tailored to individual needs while maintaining a consistent educational standard. These plans include general lesson themes as well as adjustments based on emotional data.

[0480] The emotion engine analyzes the user's (student or teacher's) facial expressions and tone of voice to recognize their emotional state in real time. This data is used to help teachers understand students' comprehension levels and interest levels. For example, if a student appears bored during class, the system will suggest new teaching materials or activities to capture their attention.

[0481] Next, the device provides a user interface, allowing teachers and students to easily understand the plan and any associated changes. Teachers can then use this information to provide personalized instruction to individual students. The device also transmits test results and student emotional states observed during lessons to the server in real time.

[0482] Users (teachers) can make the most of the educational plans and emotion-based information provided by the server to provide individualized instruction. For example, if a student shows anxiety in a particular subject class, the teacher can understand the situation and adjust their teaching methods with additional support or a different approach.

[0483] This invention not only streamlines educational planning but also enables more individualized instruction by considering emotional aspects. As a concrete example, one middle school successfully improved students' motivation by using this system to record their daily emotional changes and adjusting weekly instructional plans based on those changes. In this way, the invention provides effective educational support and promotes the growth of individual students.

[0484] The following describes the processing flow.

[0485] Step 1:

[0486] The server collects lesson plans, teaching materials, test results, and student behavior data from educational settings and stores them in a database. This collection is performed regularly through an automated process, ensuring that the educational data is always up-to-date.

[0487] Step 2:

[0488] The device analyzes students' facial expressions and voice tone via an emotion engine, recognizing their emotional state in real time. This recognized emotional data is continuously transmitted to the server.

[0489] Step 3:

[0490] The server uses AI algorithms to analyze collected educational and emotional data and generate optimal educational plans tailored to the individual needs of each student. These plans include not only standard lesson topics but also teaching methods that take emotional data into consideration.

[0491] Step 4:

[0492] The device displays generated lesson plans and up-to-date sentiment data to teachers via a user interface. This allows teachers to obtain information to provide instruction that considers both student progress and emotional aspects.

[0493] Step 5:

[0494] The user (teacher) provides instruction based on information from the device, adjusting the lesson content and teaching methods to suit the individual student's needs. For example, if a student shows signs of misunderstanding during class, time will be allocated to supplement that information.

[0495] Step 6:

[0496] The terminal reports test results and emotional state data obtained during class to the server for further analysis. This allows the server to determine if adjustments to the teaching plan are necessary and to make corrections in real time as needed.

[0497] Step 7:

[0498] The server re-evaluates all data and makes a new assessment of the educational standards. Based on this, it generates feedback on the next day's lesson plan and teaching materials, and provides it to teachers and administrators via terminals.

[0499] This entire process enables educational support that responds quickly to changes in students' learning progress and emotions, resulting in effective individualized instruction.

[0500] (Example 2)

[0501] Next, we will describe Example 2. In the following description, the data processing device 12 will be referred to as the "server," and the headset-type terminal 314 will be referred to as the "terminal."

[0502] In today's educational setting, providing effective education tailored to the individual needs of learners requires not only transmitting learning content but also understanding learners' emotional states and developing flexible educational plans based on those states. However, traditional educational systems have struggled to grasp students' emotional states in real time and quickly provide individualized educational plans accordingly. Furthermore, there has been a lack of means to automatically adjust plans to take into account the different learning progress and educational environments of different regions and individuals.

[0503] The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 2 is realized by the following means.

[0504] In this invention, the server includes means for collecting and storing information in the field of education, means for analyzing the stored information and automatically generating educational plans, and means for optimizing teaching materials and evaluation means based on the generated educational plans. This makes it possible to provide flexible and effective education in real time that is tailored to the individual needs of learners.

[0505] "Information in the field of education" is a general term for data that includes various types of information such as lesson plans, teaching materials, assessment results, and learner responses.

[0506] "Means of storage" refers to the technical means of recording and preserving collected data.

[0507] "Methods for analyzing and automatically generating educational plans" refers to methods for analyzing collected data and automatically constructing educational plans tailored to individual educational goals and learning progress.

[0508] "Means for optimizing teaching materials and assessment methods" refers to means of adjusting the teaching materials and assessment methods used based on the learners' needs and emotional states in order to provide more effective education.

[0509] "Means of recognizing emotional states and reflecting that information in educational plans" refers to technical methods for analyzing emotions from learners' facial expressions and voices and adjusting educational content accordingly.

[0510] "Means equipped with display functions for providing customized instruction" refers to functions that display individual learning plans and progress of learners through an interface and provide instruction based on them.

[0511] "Means of updating educational information in real time" refers to means of instantly updating educational plans and learner status based on the latest data.

[0512] This invention provides a concrete model for building a system that provides individualized education based on the emotional state of learners in educational settings. This system consists of four main components: a server, a terminal, a user, and an emotion engine.

[0513] The server collects and stores information in the field of education. Specifically, data including lesson plans, teaching materials, evaluation results, and student responses are automatically collected through online platforms and databases. This data is stored in a database on the server.

[0514] The server analyzes collected data and generates personalized learning plans for each learner. Using programming languages ​​such as Python and machine learning algorithms, it analyzes learners' performance trends and emotional patterns, providing flexible learning plans based on this analysis. These plans optimize teaching materials and assessment methods, ensuring they meet individual needs.

[0515] The emotion engine analyzes the learner's facial expressions and voice to recognize their emotional state in real time. By using an open-source emotion recognition library, it identifies emotions such as "joy" and "anxiety" from the learner's facial expressions and tone of voice, and sends that information to the server.

[0516] The device provides a user interface that allows learners and teachers to view generated lesson plans and sentiment analysis results. Through this interface, teachers can provide individualized instruction and customized learning materials. The device also transmits the latest educational information to the server in real time, ensuring that the most up-to-date data is always shared.

[0517] Teachers, as users of the system, can utilize the data provided by the server to tailor instruction to the individual needs of their students. For example, if analysis of emotional data reveals that a particular student is showing anxiety during class, they can plan additional support accordingly.

[0518] As a concrete example, one could consider creating an individualized educational plan by inputting a prompt message such as, "Propose appropriate guidance based on a student's emotional data," into an AI model. This system is expected to promote learner growth by providing effective education tailored to individual needs.

[0519] The flow of the specific processing in Example 2 will be explained using Figure 13.

[0520] Step 1:

[0521] The server collects information in the field of education. Specifically, it retrieves lesson plans, teaching materials, test results, and student response data from online platforms and stores them in a database. The input to this process is digital data from various educational institutions and tools, and the output is structured educational information stored in the database.

[0522] Step 2:

[0523] The server analyzes the accumulated data. Using programming languages ​​such as Python, it processes the data with machine learning algorithms to analyze student performance trends and emotional patterns. The input data is education-related information stored in a database, and the output is an education plan optimized for individual learners.

[0524] Step 3:

[0525] The emotion engine captures the user's facial expressions and voice tone in real time via the camera and microphone built into the device. This allows it to analyze and determine the student's emotional state. The input is the student's facial expressions and voice data, and the output is an emotion label such as "joy" or "anxiety."

[0526] Step 4:

[0527] The server adjusts the educational plan using the results of emotion recognition. Based on the emotion data, it adjusts the teaching materials and assessment methods in the existing educational plan. In this step, the emotion data and the existing educational plan are used as input, and a new, adjusted educational plan is output.

[0528] Step 5:

[0529] The device displays the generated educational plan and sentiment analysis results on its interface. This allows teachers and students to review the information and use it in their learning activities. The input is the adjusted educational plan data, and the output is the information displayed on the device's screen.

[0530] Step 6:

[0531] The user, acting as the teacher, provides individualized instruction based on the provided educational plan and emotional data. The teacher adjusts their approach during lessons, referencing the information displayed on the screen, to support students according to their needs. Input consists of the educational plan and emotional information viewable on the terminal screen, while output is the specific instruction and material preparation undertaken by the teacher.

[0532] (Application Example 2)

[0533] Next, we will explain application example 2. In the following explanation, the data processing device 12 will be referred to as the "server," and the headset-type terminal 314 will be referred to as the "terminal."

[0534] In educational settings, it is crucial to provide optimal educational plans that take into account the individual feelings and learning progress of each student, but achieving this presents many challenges. Traditional methods make it difficult to address the individual feelings and needs of students while ensuring unified educational standards, and efficiently utilizing resources across educational institutions in the region is also a challenge.

[0535] The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means.

[0536] In this invention, the server includes means for collecting and storing educational and emotional data, means for analyzing the collected data and automatically generating educational plans, and means for sharing optimal educational resources across all educational institutions in the region. This makes it possible to provide individualized educational plans based on each student's emotional state and learning progress. Furthermore, by efficiently utilizing educational resources across the region, an overall improvement in educational standards can be expected.

[0537] "Educational data" refers to information regarding lesson plans, teaching materials, test results, and student learning progress in educational settings.

[0538] "Emotional data" refers to information about the emotional state obtained by analyzing the facial expressions and tone of voice of students and teachers.

[0539] An "educational plan" refers to a teaching plan generated based on collected educational and emotional data, optimized to meet the individual learning needs of each student.

[0540] "Educational materials" refer to teaching materials and information resources for learning activities provided based on the educational plan.

[0541] "Measurement methods" refer to tests and assessment methods used to evaluate students' learning outcomes and educational progress.

[0542] "Display means" refers to an interface that allows teachers and students to check educational progress, individualized instruction plans, and other information.

[0543] "Educational institutions within a region" refers to a collection of educational facilities, such as schools and educational centers, located in a specific area.

[0544] "Educational standards" refer to indicators that serve as criteria for measuring the quality and outcomes of education.

[0545] "Efficient use of resources" refers to managing and allocating the necessary personnel, teaching materials, information, etc., for educational activities in the most optimal way, and using them effectively without waste.

[0546] To implement this invention, a system will be constructed in which a server, terminals, and users play important roles. The server will have the function of collecting and storing educational data and emotional data. Educational data will include lesson plans, teaching materials, and test results, while emotional data will include information on the emotional state based on the facial expressions and tone of voice of students and teachers. This data will be analyzed using Python or JavaScript, and a means will be constructed to automatically generate individualized educational plans for students using a generative AI model.

[0547] The server also functions as a platform for sharing optimal educational resources across educational institutions within the region. A smartphone app built with React Native allows teachers to manage teaching progress and provides personalized educational materials and metrics through various display methods.

[0548] As a concrete example, a smartphone device uses OpenCV and the dlib library to analyze students' facial expressions and send emotional data to a server in real time. Based on this emotional data, if a student is losing interest in a particular subject, the system can help teachers suggest a new teaching plan. As a result, students' motivation to learn is maintained, and efficient education is achieved throughout the community.

[0549] An example of a prompt would be, "Based on data on students' emotional changes, please suggest teaching methods for students who have lost interest in math class." This prompt serves as a basis for a generative AI model to generate specific teaching plans, which are then provided to teachers.

[0550] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[0551] Step 1:

[0552] The server receives lesson plans, teaching materials, test results, and emotional data based on students' facial expressions and tone of voice from educational institutions. This educational and emotional data is stored in a database for accumulation. The input for this step is data from educational institutions, and the output is the information stored in the database.

[0553] Step 2:

[0554] The device uses the smartphone's camera and microphone to capture real-time emotional data from students. OpenCV and the dlib library are used to analyze facial expressions and voices and identify emotional states. The input for this step is the student's facial expressions and voice, and the output is the identified emotional data.

[0555] Step 3:

[0556] The server uses a generative AI model to analyze accumulated educational data and emotional data transmitted from terminals. The generative AI model automatically generates personalized educational plans using prompt messages. The input for this step is the educational data and emotional data to be analyzed, and the output is the automatically generated educational plan.

[0557] Step 4:

[0558] The server sends the generated lesson plan to the terminal. The lesson plan is displayed on the terminal in real time, and the user (teacher) can refer to it. The input for this step is the lesson plan, and the output is the updated instructional information displayed on the terminal.

[0559] Step 5:

[0560] Based on the educational plan and emotional data provided through the device, users make decisions to support the progress of lessons and individual instruction. They adjust the specific teaching materials and methods used to optimize the students' learning experience. The input for this step is instructional information from the device, and the output is the concrete implementation of optimized lessons and learning support.

[0561] The specific processing unit 290 transmits the result of the specific processing to the headset terminal 314. In the headset terminal 314, the control unit 46A causes the speaker 240 and display 343 to output the result of the specific processing. The microphone 238 acquires audio indicating user input for the result of the specific processing. The control unit 46A transmits the audio data indicating user input acquired by the microphone 238 to the data processing unit 12. In the data processing unit 12, the specific processing unit 290 acquires the audio data.

[0562] Data generation model 58 is a type of so-called generative AI (Artificial Intelligence). One example of data generation model 58 is ChatGPT (Internet search<URL: https: / / openai.com / blog / chatgpt> ), Gemini (Internet search) <url: https: gemini.google.com ?hl="ja">Examples of generative AI include the following. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 is input with prompts containing instructions, and with inference data such as audio data representing speech, text data representing text, and image data representing images. The data generation model 58 infers from the input inference data according to the instructions indicated by the prompts, and outputs the inference results in data formats such as audio data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[0563] In the above embodiment, an example was given in which specific processing is performed by the data processing device 12, but the technology of this disclosure is not limited thereto, and specific processing may also be performed by the headset terminal 314.

[0564] [Fourth Embodiment]

[0565] Figure 7 shows an example of the configuration of the data processing system 410 according to the fourth embodiment.

[0566] As shown in Figure 7, the data processing system 410 includes a data processing device 12 and a robot 414. An example of the data processing device 12 is a server.

[0567] The data processing device 12 comprises a computer 22, a database 24, and a communication interface 26. The computer 22 is an example of a "computer" related to the technology of this disclosure. The computer 22 comprises a processor 28, RAM 30, and storage 32. The processor 28, RAM 30, and storage 32 are connected to a bus 34. The database 24 and the communication interface 26 are also connected to the bus 34. The communication interface 26 is connected to a network 54. An example of the network 54 is a WAN (Wide Area Network) and / or a LAN (Local Area Network).

[0568] The robot 414 includes a computer 36, a microphone 238, a speaker 240, a camera 42, a communication interface 44, and a controlled object 443. The computer 36 includes a processor 46, RAM 48, and storage 50. The processor 46, RAM 48, and storage 50 are connected to a bus 52. The microphone 238, speaker 240, camera 42, and controlled object 443 are also connected to the bus 52.

[0569] The microphone 238 receives voice signals from the user 20 and receives instructions from the user 20. The microphone 238 captures the voice signals from the user 20, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio according to the instructions from the processor 46.

[0570] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an image sensor such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, and captures images of the area around the user 20 (for example, an imaging range defined by a field of view equivalent to the width of a typical healthy person's field of vision).

[0571] Communication interface 44 is connected to network 54. Communication interfaces 44 and 26 are responsible for the exchange of various information between processor 46 and processor 28 via network 54. The exchange of various information between processor 46 and processor 28 using communication interfaces 44 and 26 is performed in a secure manner.

[0572] The controlled 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 robot 414's emotions can be expressed by controlling these motors. Furthermore, the robot 414's facial expressions can also be expressed by controlling the illumination state of the LEDs in its eyes.

[0573] Figure 8 shows an example of the main functions of the data processing device 12 and the robot 414. As shown in Figure 8, the data processing device 12 performs specific processing using the processor 28. The storage 32 stores the specific processing program 56.

[0574] The specific processing program 56 is an example of a "program" relating to the technology of this 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 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.

[0575] The storage 32 stores the data generation model 58 and the emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290.

[0576] In robot 414, the processor 46 performs the reception output processing. The storage 50 stores the reception output program 60. The processor 46 reads the reception output program 60 from the storage 50 and executes the read reception output program 60 on the RAM 48. The reception output processing is realized by the processor 46 operating as a control unit 46A according to the reception output program 60 executed on the RAM 48.

[0577] Next, the specific processing performed by the specific processing unit 290 of the data processing device 12 will be described. In the following description, the data processing device 12 will be referred to as the "server" and the robot 414 as the "terminal".

[0578] This invention provides a system for improving the efficiency and standardization of lesson planning in educational settings. It consists of three main components: a server, a terminal, and a user, each playing a specific role.

[0579] First, the server collects and stores educational data. This includes past lesson plans, teaching materials, test results, and success stories from other schools for each school and region. The server analyzes this data using AI algorithms and automatically generates educational plans to achieve a unified educational level. The generated plans are then adjusted according to the specific events and activities of each grade level and school.

[0580] Furthermore, the server optimizes teaching materials and assessment tests based on the analysis results. In this process, it refers to past student performance data and comprehension levels to provide materials and test questions of appropriate difficulty. For example, for units in mathematics where the average score was low in the past, supplementary materials might be recommended.

[0581] Next, the device provides a user interface for teachers and students. Through this interface, teachers can intuitively check the annual lesson plan and students' progress. In addition, the device sends the test results taken by students to the server in real time, so the database on the server is always kept up-to-date.

[0582] Finally, based on the information provided, the user (teacher) identifies each student's strengths and weaknesses and provides individualized instruction. For example, if a student performs poorly in reading comprehension in Japanese, the teacher can support that student using additional materials recommended by the system. This system allows teachers to reduce their preparation workload and provide higher quality education while tailoring instruction to each individual student.

[0583] As a concrete example, one elementary school implemented this system to standardize the curriculum content for each grade level and to flexibly adjust the curriculum even when there are common events or activities at specific times. In this way, the quality of education is improved, and effective support for human resource development is realized.

[0584] The following describes the processing flow.

[0585] Step 1:

[0586] The server collects educational data such as lesson plans, teaching materials, and test results from educational settings and stores them in a database. This process is automated and regularly updated, ensuring that new information is always reflected.

[0587] Step 2:

[0588] The server analyzes accumulated data using AI algorithms and generates an optimal educational plan derived from past performance and successful examples from other schools. This plan includes a list of lesson themes and teaching materials to be used each month.

[0589] Step 3:

[0590] The server optimizes educational materials and assessment tests based on the generated lesson plan. It automatically selects the most suitable materials and test questions for each lesson, taking into account difficulty levels and student comprehension.

[0591] Step 4:

[0592] The device provides teachers with an interface to monitor teaching plans and student progress. The interface is designed to be visually intuitive and easy to access.

[0593] Step 5:

[0594] The terminal transmits the results of tests taken by students and their class attendance records to the server in real time. This communication ensures that the server's database is always updated with the latest information.

[0595] Step 6:

[0596] Based on information provided by the server, users (teachers) analyze each student's strengths and weaknesses and provide individualized instruction. Users utilize the system-recommended teaching materials and supplementary resources to provide education tailored to each student.

[0597] Step 7:

[0598] Users (teachers) can adjust the generated lesson plans as needed and customize the content to suit specific events and occasions. This flexibility allows the plans to be optimized to the specific needs and circumstances of the school.

[0599] (Example 1)

[0600] Next, we will describe Example 1. In the following description, the data processing device 12 will be referred to as the "server" and the robot 414 as the "terminal".

[0601] Improving the quality and efficiency of individualized instruction is a crucial challenge in modern education. Traditional methods require teachers to spend a significant amount of time creating lesson plans, making it difficult to provide instruction tailored to the individual needs of each student. Furthermore, developing flexible educational plans that take into account the educational standards and characteristics of each school and region is also challenging.

[0602] The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 1 is realized by the following means.

[0603] In this invention, the server includes means for collecting and storing educational information, means for analyzing the collected information and utilizing a generative model for automatically generating educational plans, and means for analyzing student performance data and recommending additional teaching materials according to the student's level of understanding. This enables teachers to provide flexible and effective instruction tailored to individual students.

[0604] "Educational information" refers to information related to education, such as past lesson plans, teaching materials, test results, and success stories from schools and communities.

[0605] A "generative model" refers to a computational algorithm or artificial intelligence structure that automatically creates educational plans based on accumulated educational information.

[0606] "Educational materials" refer to teaching materials, reference materials, and other items and digital content used to support learning in classes and instruction.

[0607] "Evaluation methods" refer to tests, questionnaires, and other assessment methods used to measure students' learning progress and understanding.

[0608] A "display device" refers to a screen or device used to visually display educational information, lesson plans, student progress, and so on.

[0609] "Supplementary materials" are materials provided in addition to standard materials to reinforce learning, tailored to each student's individual level of understanding and academic performance.

[0610] This invention is a system for improving the efficiency and standardization of lesson planning in educational settings. The system mainly consists of three components: a server, a terminal, and a user.

[0611] The server collects and stores educational information, including past performance data, lesson plans, and success stories from each educational institution. The server stores this information in a database and uses a generative model to automatically generate lesson plans. The software used includes a database management system and an AI model. For example, when creating a math lesson plan, it recommends appropriate units based on past performance data.

[0612] The generation of educational plans is performed by analyzing data collected by the server and inputting it into a generation AI model using prompt messages. For example, a prompt message such as, "Please create a lesson plan for third-grade elementary school math for the next academic year. Consider past test results and successful examples, and suggest additional materials for units that need reinforcement," might be used.

[0613] The terminal provides a user interface for teachers and students. Through this interface, teachers can view generated lesson plans and student progress. The terminal provides a dashboard-style display via a web browser and plays a role in synchronizing data with the server in real time.

[0614] The teacher, as a user, provides individualized instruction based on information obtained through the device. For example, a student who performs poorly in reading comprehension in Japanese language arts can be given additional materials to improve their understanding. In this way, teachers can reduce the burden of creating lesson plans while providing high-quality individualized instruction.

[0615] The flow of the specific processing in Example 1 will be explained using Figure 11.

[0616] Step 1:

[0617] The server collects educational information from each educational institution and stores it in a database. It receives educational information such as past grade data, lesson plans, teaching materials, and test results as input. This data is collected using data ingestion scripts via CSV files or APIs. As output, the complete dataset is stored in the database, ready for subsequent processing.

[0618] Step 2:

[0619] The server analyzes the accumulated educational information and inputs it into the generating AI model using prompt statements. These prompt statements describe in detail the conditions necessary for automatically generating educational plans. The AI ​​model receives educational data stored in the database and prompt statements as input. As output, it proposes educational plans tailored to specific grades and subjects. Specifically, to generate a math lesson plan, a prompt statement such as "Please create a math lesson plan for third grade elementary school students for the next academic year" is used.

[0620] Step 3:

[0621] The server optimizes teaching materials and assessment methods based on the generated educational plan. It receives an educational plan created by a generating AI model as input. The server analyzes past performance data and generates teaching materials and test questions tailored to the student's level of understanding. As output, appropriate teaching materials and tests are prepared for each unit. Specifically, if a student performs poorly in a particular unit, the server automatically suggests supplementary materials to reinforce that unit.

[0622] Step 4:

[0623] The terminal provides a user interface for teachers and students. It receives lesson plans, teaching materials, and student progress data from the server as input. The terminal displays this information in a dashboard format for intuitive operation. However, since each user interface is provided via a web browser, real-time data synchronization with the server is necessary. As output, teachers can link lesson plans and monitor student progress.

[0624] Step 5:

[0625] The teacher, as the user, provides instruction tailored to each student's level of understanding based on information obtained through the device. Inputs include the displayed educational plan and student progress data. Next, the teacher provides additional materials and individual advice. Output is that the teacher supports and improves student learning through appropriate instruction. Specifically, the teacher improves the quality of instruction by preparing additional materials for students who have insufficient understanding of reading comprehension in Japanese.

[0626] (Application Example 1)

[0627] Next, we will explain Application Example 1. In the following explanation, the data processing device 12 will be referred to as the "server" and the robot 414 as the "terminal".

[0628] To reduce the burden of developing and implementing lesson plans in educational settings and to strengthen individualized instruction, efficient and standardized educational plans are necessary. However, currently, creating and managing educational plans requires significant time and resources, and there are challenges, particularly in providing education tailored to the individual characteristics of each student. Furthermore, there is a lack of individually customized teaching materials based on students' learning progress, so the introduction of a more immediate and effective educational support system is needed.

[0629] The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 1 is realized by the following means.

[0630] In this invention, the server includes means for collecting and storing educational data, means for analyzing the collected data and automatically generating educational plans, means for optimizing educational materials and assessment tests based on the generated educational plans, and means for providing customized educational materials based on the progress of the students. This not only enables the streamlining and standardization of lesson plans in educational settings, but also enables the provision of educational materials tailored to each student, thereby improving the quality of individualized instruction.

[0631] "Educational data" refers to information about the educational process, including lesson plans, teaching materials, test results, student performance and comprehension levels, and success stories from other schools.

[0632] "Means for automatically generating educational plans" refers to devices or programs that analyze collected educational data using AI algorithms, etc., and automatically create lesson plans suitable for each educational institution with a unified educational level.

[0633] "Means for optimizing educational materials and assessment tests" refers to devices or systems that have the function of automatically selecting and distributing educational materials and test questions of appropriate difficulty levels based on past performance data and comprehension information.

[0634] "Means of managing educational progress" refers to systems and devices that grasp students' learning progress and understanding in real time and provide this information in a visualized format.

[0635] "Means for displaying an interface for providing individualized instruction" refers to devices or methods that provide a user interface for teachers to identify each student's strengths and weaknesses and display information for use when providing individualized instruction.

[0636] "Means of providing customized educational materials based on the student's progress" refers to a system that has the function of dynamically selecting and outputting educational materials based on learning history in order to provide materials whose content is adjusted according to the student's learning situation.

[0637] "Means for controlling automated devices equipped with educational support devices" refers to a system that uses programming to control robots or digital devices with educational support functions and execute specified educational content.

[0638] To realize this invention, it is necessary to build an educational support system. This system will operate through the interaction of a server, terminals, and users (primarily teachers).

[0639] The server is responsible for collecting and storing educational data. High-performance cloud servers are used as hardware, and a database management system such as AWS DynamoDB is employed as software. Furthermore, AI libraries such as TensorFlow are used to analyze the collected data and automatically generate educational plans tailored to each educational institution. The generated educational plans are transmitted to educational terminals in real time.

[0640] Next, the educational devices primarily function as interfaces for teachers and students. Small computing devices such as Raspberry Pi and Jetson Nano are employed to support the execution of lesson plans both in the classroom and remotely. The devices provide teachers with generated lesson plans and optimized teaching materials, and keep all information up-to-date by sending student progress data to a server.

[0641] Through the interface of this educational system, users can understand each student's strengths and weaknesses and provide individualized instruction. For example, if a teacher needs additional instruction for a particular student, they can use customized teaching materials suggested by the system.

[0642] For example, if it is determined that a student is struggling with a particular unit in mathematics, the server will generate appropriate supplementary materials based on past data and provide them to the student via their device. The teacher will then follow up as needed based on these materials.

[0643] In this scenario, a generative AI model can be used to create prompts and suggest problems tailored to the students' level of understanding. For example, a prompt such as, "Please provide video materials to concretely explain mathematical concepts that students find difficult to understand," could be used.

[0644] The flow of a specific process in Application Example 1 will be explained using Figure 12.

[0645] Step 1:

[0646] The server collects educational data from various educational institutions and stores it in AWS DynamoDB. Inputs include past lesson plans, teaching materials, and test results submitted from schools and regions, while output is the storage of these datasets in the database. Data processing is performed here to verify data validity and convert it to a specified format.

[0647] Step 2:

[0648] The server analyzes the accumulated data using an AI algorithm (TensorFlow) and automatically generates an educational plan tailored to each school. The input is the educational data saved in Step 1, and the output is an integrated educational plan that takes into account events specific to each grade and school. This involves data analysis and data calculations for pattern recognition using AI.

[0649] Step 3:

[0650] The server optimizes educational materials and assessment tests based on the generated educational plan. The input is the integrated educational plan, and the output is workbooks and materials tailored to the students' level of understanding. Past performance data is referenced to process the data and select appropriate materials.

[0651] Step 4:

[0652] The terminal provides teachers with optimized teaching materials and tests received from the server. The input is information about the optimized teaching materials from the server, and the output is displayed to the teacher as teaching materials and tests that can be used in class. Information visualization is performed on the user interface.

[0653] Step 5:

[0654] The user (teacher) checks students' learning progress through the device and identifies each student's strengths and weaknesses. The input is the student's test results and progress displayed on the device, and the output is an individualized instruction plan. Here, specific instructional policies are determined based on the delivered content.

[0655] Step 6:

[0656] The server updates the database in real time with student test results and learning progress received from terminals. The input is learning data sent from terminals, and the output is the updated educational dataset. Data synchronization and consistency checks are performed here.

[0657] Step 7:

[0658] The terminal uses an AI model to generate solutions and teaching materials based on prompts generated by the server, thereby supporting student learning. The input is a prompt from the teacher, and the output is the optimal solution and teaching materials generated by the AI. For example, the prompt "Please provide video teaching materials to concretely explain mathematical concepts that students find difficult to understand" is entered, and the system displays the video teaching materials.

[0659] Furthermore, an emotion engine that estimates the user's emotions may be incorporated. That is, the identification processing unit 290 may use the emotion identification model 59 to estimate the user's emotions and perform identification processing using the user's emotions.

[0660] This invention provides an educational support system that combines an emotion engine to optimize instruction in educational settings. It consists of four main components: a server, a terminal, a user, and an emotion engine.

[0661] First, the server collects and stores educational data. This includes lesson plans, teaching materials, test results, and student response data obtained from the classroom. Emotional data recognized by the emotion engine is also sent to the server and stored in the database. The server analyzes this data and automatically generates educational plans tailored to individual needs while maintaining a consistent educational standard. These plans include general lesson themes as well as adjustments based on emotional data.

[0662] The emotion engine analyzes the user's (student or teacher's) facial expressions and tone of voice to recognize their emotional state in real time. This data is used to help teachers understand students' comprehension levels and interest levels. For example, if a student appears bored during class, the system will suggest new teaching materials or activities to capture their attention.

[0663] Next, the device provides a user interface, allowing teachers and students to easily understand the plan and any associated changes. Teachers can then use this information to provide personalized instruction to individual students. The device also transmits test results and student emotional states observed during lessons to the server in real time.

[0664] Users (teachers) can make the most of the educational plans and emotion-based information provided by the server to provide individualized instruction. For example, if a student shows anxiety in a particular subject class, the teacher can understand the situation and adjust their teaching methods with additional support or a different approach.

[0665] This invention not only streamlines educational planning but also enables more individualized instruction by considering emotional aspects. As a concrete example, one middle school successfully improved students' motivation by using this system to record their daily emotional changes and adjusting weekly instructional plans based on those changes. In this way, the invention provides effective educational support and promotes the growth of individual students.

[0666] The following describes the processing flow.

[0667] Step 1:

[0668] The server collects lesson plans, teaching materials, test results, and student behavior data from educational settings and stores them in a database. This collection is performed regularly through an automated process, ensuring that the educational data is always up-to-date.

[0669] Step 2:

[0670] The device analyzes students' facial expressions and voice tone via an emotion engine, recognizing their emotional state in real time. This recognized emotional data is continuously transmitted to the server.

[0671] Step 3:

[0672] The server uses AI algorithms to analyze collected educational and emotional data and generate optimal educational plans tailored to the individual needs of each student. These plans include not only standard lesson topics but also teaching methods that take emotional data into account.

[0673] Step 4:

[0674] The device displays generated lesson plans and up-to-date sentiment data to teachers via a user interface. This allows teachers to obtain information to provide instruction that considers both student progress and emotional aspects.

[0675] Step 5:

[0676] The user (teacher) provides instruction based on information from the device, adjusting the lesson content and teaching methods to suit the individual student's needs. For example, if a student shows signs of misunderstanding during class, time will be allocated to supplement that information.

[0677] Step 6:

[0678] The terminal reports test results and emotional state data obtained during class to the server for further analysis. This allows the server to determine if adjustments to the teaching plan are necessary and to make corrections in real time as needed.

[0679] Step 7:

[0680] The server re-evaluates all data and makes a new assessment of the educational standards. Based on this, it generates feedback on the next day's lesson plan and teaching materials, and provides it to teachers and administrators via terminals.

[0681] This entire process enables educational support that responds quickly to changes in students' learning progress and emotions, resulting in effective individualized instruction.

[0682] (Example 2)

[0683] Next, we will describe Example 2. In the following description, the data processing device 12 will be referred to as the "server" and the robot 414 as the "terminal".

[0684] In today's educational setting, providing effective education tailored to the individual needs of learners requires not only transmitting learning content but also understanding learners' emotional states and developing flexible educational plans based on those states. However, traditional educational systems have struggled to grasp students' emotional states in real time and quickly provide individualized educational plans accordingly. Furthermore, there has been a lack of means to automatically adjust plans to take into account the different learning progress and educational environments of different regions and individuals.

[0685] The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 2 is realized by the following means.

[0686] In this invention, the server includes means for collecting and storing information in the field of education, means for analyzing the stored information and automatically generating educational plans, and means for optimizing teaching materials and evaluation means based on the generated educational plans. This makes it possible to provide flexible and effective education in real time that is tailored to the individual needs of learners.

[0687] "Information in the field of education" is a general term for data that includes various types of information such as lesson plans, teaching materials, assessment results, and learner responses.

[0688] "Means of storage" refers to the technical means of recording and preserving collected data.

[0689] "Methods for analyzing and automatically generating educational plans" refers to methods for analyzing collected data and automatically constructing educational plans tailored to individual educational goals and learning progress.

[0690] "Means for optimizing teaching materials and assessment methods" refers to means of adjusting the teaching materials and assessment methods used based on the learners' needs and emotional states in order to provide more effective education.

[0691] "Means of recognizing emotional states and reflecting that information in educational plans" refers to technical methods for analyzing emotions from learners' facial expressions and voices and adjusting educational content accordingly.

[0692] "Means of providing a display function for delivering customized instruction" refers to a function that displays a learner's individual educational plan and progress through an interface and provides instruction based on that.

[0693] "Means of updating educational information in real time" refers to means of instantly updating educational plans and learner status based on the latest data.

[0694] This invention provides a concrete model for constructing a system that provides individualized education based on the emotional state of learners in educational settings. This system consists of four main components: a server, a terminal, a user, and an emotion engine.

[0695] The server collects and stores information in the field of education. Specifically, data including lesson plans, teaching materials, evaluation results, and student responses are automatically collected through online platforms and databases. This data is stored in a database on the server.

[0696] The server analyzes collected data and generates personalized learning plans for each learner. Using programming languages ​​such as Python and machine learning algorithms, it analyzes learners' performance trends and emotional patterns, providing flexible learning plans based on this analysis. These plans optimize teaching materials and assessment methods, ensuring they meet individual needs.

[0697] The emotion engine analyzes the learner's facial expressions and voice to recognize their emotional state in real time. By using an open-source emotion recognition library, it identifies emotions such as "joy" and "anxiety" from the learner's facial expressions and tone of voice, and sends that information to the server.

[0698] The device provides a user interface that allows learners and teachers to view generated lesson plans and sentiment analysis results. Through this interface, teachers can provide individualized instruction and customized learning materials. The device also transmits the latest educational information to the server in real time, ensuring that the most up-to-date data is always shared.

[0699] Teachers, as users of the system, can utilize the data provided by the server to tailor instruction to the individual needs of their students. For example, if analysis of emotional data reveals that a particular student is showing anxiety during class, they can plan additional support accordingly.

[0700] As a concrete example, one could consider creating an individualized educational plan by inputting a prompt message such as, "Propose appropriate guidance based on a student's emotional data," into an AI model. This system is expected to promote learner growth by providing effective education tailored to individual needs.

[0701] The flow of the specific processing in Example 2 will be explained using Figure 13.

[0702] Step 1:

[0703] The server collects information in the field of education. Specifically, it retrieves lesson plans, teaching materials, test results, and student response data from online platforms and stores them in a database. The input to this process is digital data from various educational institutions and tools, and the output is structured educational information stored in the database.

[0704] Step 2:

[0705] The server analyzes the accumulated data. Using programming languages ​​such as Python, it processes the data with machine learning algorithms to analyze student performance trends and emotional patterns. The input data is education-related information stored in a database, and the output is an education plan optimized for individual learners.

[0706] Step 3:

[0707] The emotion engine captures the user's facial expressions and voice tone in real time via the camera and microphone built into the device. This allows it to analyze and determine the student's emotional state. The input is the student's facial expressions and voice data, and the output is an emotion label such as "joy" or "anxiety."

[0708] Step 4:

[0709] The server adjusts the educational plan using the results of emotion recognition. Based on the emotion data, it adjusts the teaching materials and assessment methods in the existing educational plan. In this step, the emotion data and the existing educational plan are used as input, and a new, adjusted educational plan is output.

[0710] Step 5:

[0711] The device displays the generated educational plan and sentiment analysis results on its interface. This allows teachers and students to review the information and use it in their learning activities. The input is the adjusted educational plan data, and the output is the information displayed on the device's screen.

[0712] Step 6:

[0713] The user, acting as the teacher, provides individualized instruction based on the provided educational plan and emotional data. The teacher adjusts their approach during lessons, referencing the information displayed on the screen, to support students according to their needs. Input consists of the educational plan and emotional information viewable on the terminal screen, while output is the specific instruction and material preparation undertaken by the teacher.

[0714] (Application Example 2)

[0715] Next, we will explain application example 2. In the following explanation, the data processing device 12 will be referred to as the "server" and the robot 414 as the "terminal".

[0716] In educational settings, it is crucial to provide optimal educational plans that take into account the individual feelings and learning progress of each student, but achieving this presents many challenges. Traditional methods make it difficult to address the individual feelings and needs of students while ensuring unified educational standards, and efficiently utilizing resources across educational institutions in the region is also a challenge.

[0717] The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means.

[0718] In this invention, the server includes means for collecting and storing educational and emotional data, means for analyzing the collected data and automatically generating educational plans, and means for sharing optimal educational resources across all educational institutions in the region. This makes it possible to provide individualized educational plans based on each student's emotional state and learning progress. Furthermore, by efficiently utilizing educational resources across the region, an overall improvement in educational standards can be expected.

[0719] "Educational data" refers to information regarding lesson plans, teaching materials, test results, and student learning progress in educational settings.

[0720] "Emotional data" refers to information about the emotional state obtained by analyzing the facial expressions and tone of voice of students and teachers.

[0721] An "educational plan" refers to a teaching plan generated based on collected educational and emotional data, optimized to meet the individual learning needs of each student.

[0722] "Educational materials" refer to teaching materials and information resources for learning activities provided based on the educational plan.

[0723] "Measurement methods" refer to tests and assessment methods used to evaluate students' learning outcomes and educational progress.

[0724] "Display means" refers to an interface that allows teachers and students to check educational progress, individualized instruction plans, and other information.

[0725] "Educational institutions within a region" refers to a collection of educational facilities, such as schools and educational centers, located in a specific area.

[0726] "Educational standards" refer to indicators that serve as criteria for measuring the quality and outcomes of education.

[0727] "Efficient use of resources" refers to managing and allocating the necessary personnel, teaching materials, information, etc., for educational activities in the most optimal way, and using them effectively without waste.

[0728] To implement this invention, a system will be constructed in which a server, terminals, and users play important roles. The server will have the function of collecting and storing educational data and emotional data. Educational data will include lesson plans, teaching materials, and test results, while emotional data will include information on the emotional state based on the facial expressions and tone of voice of students and teachers. This data will be analyzed using Python or JavaScript, and a means will be constructed to automatically generate individualized educational plans for students using a generative AI model.

[0729] The server also functions as a platform for sharing optimal educational resources across educational institutions within the region. A smartphone app built with React Native allows teachers to manage teaching progress and provides personalized educational materials and metrics through various display methods.

[0730] As a concrete example, a smartphone device uses OpenCV and the dlib library to analyze students' facial expressions and send emotional data to a server in real time. Based on this emotional data, if a student is losing interest in a particular subject, the system can help teachers suggest a new teaching plan. As a result, students' motivation to learn is maintained, and efficient education is achieved throughout the community.

[0731] An example of a prompt would be, "Based on data on students' emotional changes, please suggest teaching methods for students who have lost interest in math class." This prompt serves as a basis for a generative AI model to generate specific teaching plans, which are then provided to teachers.

[0732] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[0733] Step 1:

[0734] The server receives lesson plans, teaching materials, test results, and emotional data based on students' facial expressions and tone of voice from educational institutions. This educational and emotional data is stored in a database for accumulation. The input for this step is data from educational institutions, and the output is the information stored in the database.

[0735] Step 2:

[0736] The device uses the smartphone's camera and microphone to capture real-time emotional data from students. OpenCV and the dlib library are used to analyze facial expressions and voices and identify emotional states. The input for this step is the student's facial expressions and voice, and the output is the identified emotional data.

[0737] Step 3:

[0738] The server uses a generative AI model to analyze accumulated educational data and emotional data transmitted from terminals. The generative AI model automatically generates personalized educational plans using prompt messages. The input for this step is the educational data and emotional data to be analyzed, and the output is the automatically generated educational plan.

[0739] Step 4:

[0740] The server sends the generated lesson plan to the terminal. The lesson plan is displayed on the terminal in real time and can be viewed by the user (teacher). The input for this step is the lesson plan, and the output is the updated instructional information displayed on the terminal.

[0741] Step 5:

[0742] Based on the educational plan and emotional data provided through the device, users make decisions to support the progress of lessons and individual instruction. They adjust the specific teaching materials and methods used to optimize the students' learning experience. The input for this step is instructional information from the device, and the output is the concrete implementation of optimized lessons and learning support.

[0743] 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 controlled object 443 to output the result of the specific processing. The microphone 238 acquires audio indicating user input for the result of the specific processing. The control unit 46A transmits the audio data indicating user input acquired by the microphone 238 to the data processing unit 12. In the data processing unit 12, the specific processing unit 290 acquires the audio data.

[0744] Data generation model 58 is a type of so-called generative AI (Artificial Intelligence). One example of data generation model 58 is ChatGPT (Internet search<URL: https: / / openai.com / blog / chatgpt> ), Gemini (Internet search) <url: https: gemini.google.com ?hl="ja">Examples of generative AI include the following. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 is input with prompts containing instructions, and with inference data such as audio data representing speech, text data representing text, and image data representing images. The data generation model 58 infers from the input inference data according to the instructions indicated by the prompts, and outputs the inference results in data formats such as audio data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[0745] In the above embodiment, an example was given in which the specific processing is performed by the data processing device 12, but the technology of this disclosure is not limited thereto, and the specific processing may also be performed by the robot 414.

[0746] Furthermore, the emotion identification model 59, acting 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 a specific mapping, which is an emotion map (see Figure 9). Similarly, the emotion identification model 59 may also determine the robot's emotion, and the identification processing unit 290 may perform identification processing using the robot's emotion.

[0747] Figure 9 shows an emotion map 400 in which multiple emotions are mapped. In the emotion map 400, emotions are arranged in concentric circles radiating from the center. The closer to the center of the concentric circles, the more primitive the emotions are located. Further out of the concentric circles, emotions representing states and actions arising from mental states are located. Emotion is a concept that includes feelings and mental states. On the left side of the concentric circles, emotions that are generally generated from reactions occurring in the brain are located. On the right side of the concentric circles, emotions that are generally induced by situational judgment are located. Above and below the concentric circles, emotions that are generally generated from reactions occurring in the brain and induced by situational judgment are located. In addition, the emotion of "pleasure" is located on the upper side of the concentric circles, and the emotion of "displeasure" is located on the lower side. Thus, in the emotion map 400, multiple emotions are mapped based on the structure in which emotions arise, and emotions that are likely to occur simultaneously are mapped close together.

[0748] These emotions are distributed at the 3 o'clock position on the Emotion Map 400, and usually fluctuate between feelings of security and anxiety. In the right half of the Emotion Map 400, situational awareness takes precedence over internal feelings, resulting in a calm impression.

[0749] The inside of the Emotion Map 400 represents inner thoughts, while the outside represents actions. Therefore, the further you go from the outside of the Emotion Map 400, the more visible (expressed in actions) your emotions become.

[0750] Here, human emotions are based on various balances, such as posture and blood sugar levels. When these balances deviate from the ideal, it results in discomfort, and when they approach the ideal, it results in pleasure. Similarly, in robots, cars, motorcycles, etc., emotions can be created based on various balances, such as posture and battery level. When these balances deviate from the ideal, it results in discomfort, and when they approach the ideal, it results in pleasure. The emotion map can be generated, for example, based on Dr. Mitsuyoshi's emotion map (Research on a system for analyzing brain physiological signals of speech emotion recognition and emotion, Tokushima University, doctoral dissertation: https: / / ci.nii.ac.jp / naid / 500000375379). The left half of the emotion map contains emotions belonging to a region called "response," where sensation is dominant. The right half of the emotion map contains emotions belonging to a region called "situation," where situational awareness is dominant.

[0751] The emotion map defines two emotions that promote learning. One is the emotion around the middle of the negative "repentance" and "reflection" on the situation side. In other words, it is 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 the emotion around the positive "desire" on the reaction side. In other words, it is when the robot has positive feelings such as "I want more" or "I want to know more."

[0752] The emotion identification model 59 inputs user input into a pre-trained neural network, obtains emotion values ​​representing each emotion shown in the emotion map 400, and determines the user's emotion. This neural network is pre-trained based on multiple training data sets, which are combinations of user input and emotion values ​​representing each emotion shown in the emotion map 400. Furthermore, this neural network is trained so that emotions located close together have similar values, as shown in the emotion map 900 in Figure 10. Figure 10 shows an example where multiple emotions such as "reassured," "calm," and "confident" have similar emotion values.

[0753] The above description primarily focuses on the functions of the data processing device 12 in relation to this disclosure. However, the system related to this disclosure is not necessarily implemented on a server. The system related to this disclosure may be implemented as a general information processing system. This disclosure may be implemented, for example, as a software program that runs on a personal computer or as an application that runs on a smartphone. The method related to this disclosure may be provided to users in SaaS (Software as a Service) format.

[0754] In the above embodiment, an example was given in which a specific process is performed by a single computer 22. However, the technology of this disclosure is not limited thereto, and a distributed processing of the specific process may be performed by multiple computers, including computer 22. For example, a data generation model 58 may be provided in an external device of the data processing device 12, and the external device may generate data according to the input data.

[0755] In the above embodiment, an example was given in which the specific processing program 56 is stored in the storage 32, but the technology of this disclosure is not limited thereto. For example, the specific processing program 56 may be stored in a portable, computer-readable, non-temporary storage medium such as a USB (Universal Serial Bus) memory. The specific processing program 56 stored in the non-temporary storage medium is installed in the computer 22 of the data processing device 12. The processor 28 executes specific processing according to the specific processing program 56.

[0756] 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.

[0757] Furthermore, it is not necessary to store the entirety 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 the entirety of the specific processing program 56 in the storage 32; it is acceptable to store only a portion of the specific processing program 56.

[0758] The following types of processors can be used as hardware resources to perform specific processing. Examples of processors include a CPU, a general-purpose processor that functions as a hardware resource to perform specific processing by executing software, i.e., a program. Other examples of processors include dedicated electrical circuits, such as FPGAs (Field-Programmable Gate Arrays), PLDs (Programmable Logic Devices), or ASICs (Application Specific Integrated Circuits), which have circuit configurations specifically designed to perform specific processing. All of these processors have built-in or connected memory, and all of them perform specific processing by using memory.

[0759] The hardware resource that performs a specific process may consist of one of these various processors, or it may consist of 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). Alternatively, the hardware resource that performs a specific process may consist of a single processor.

[0760] Examples of configurations using a single processor include, firstly, a configuration in which one or more CPUs and software are combined to form a single processor, and this processor functions as a hardware resource that performs a specific process. Secondly, there is a configuration using a processor that realizes the functions of the entire system, including multiple hardware resources that perform a specific process, on a single IC chip, as exemplified by SoCs (System-on-a-chip). In this way, a specific process is realized using one or more of the above types of processors as hardware resources.

[0761] Furthermore, the hardware structure of these various processors can more specifically utilize electrical circuits that combine circuit elements such as semiconductor devices. Also, the specific processing described above is merely an example. Therefore, it goes without saying that unnecessary steps can be deleted, new steps added, or the processing order rearranged, as long as it does not deviate from the main purpose.

[0762] The descriptions and illustrations presented above are detailed explanations of the technical aspects of this disclosure and are merely examples of the technical aspects. For example, the above descriptions of the structure, function, operation, and effect are examples of the structure, function, operation, and effect of the technical aspects of this disclosure. Therefore, it goes without saying that you may delete unnecessary parts, add new elements, or replace elements in the descriptions and illustrations presented above, as long as you do not deviate from the essence of the technical aspects of this disclosure. Furthermore, in order to avoid confusion and facilitate understanding of the technical aspects of this disclosure, explanations of common technical knowledge and the like that do not require special explanation to enable the implementation of the technical aspects of this disclosure have been omitted from the descriptions and illustrations presented above.

[0763] All documents, patent applications, and technical standards described herein are incorporated by reference to the same extent as if each individual document, patent application, and technical standard were specifically and individually noted to be incorporated by reference.

[0764] The following is further disclosed regarding the embodiments described above.

[0765] (Claim 1)

[0766] Means for collecting and accumulating educational data,

[0767] A means of analyzing collected data and automatically generating educational plans,

[0768] A means for optimizing educational materials and assessment tests based on the generated educational plan,

[0769] A means of displaying an interface for managing educational progress and providing individualized instruction,

[0770] A means of updating educational data in real time,

[0771] A system that includes this.

[0772] (Claim 2)

[0773] The system according to claim 1, which includes means for evaluating educational standards based on accumulated data.

[0774] (Claim 3)

[0775] The system according to claim 1, comprising means for adjusting educational plans to take regional differences into account based on analyzed data.

[0776] "Example 1"

[0777] (Claim 1)

[0778] Means for collecting and accumulating educational information,

[0779] A means of analyzing collected information and using a generative model to automatically generate educational plans,

[0780] A means for optimizing educational materials and evaluation methods based on the generated educational plan,

[0781] A means of providing a display device for managing educational progress and providing individualized instruction,

[0782] A means of updating educational information in real time,

[0783] A method for analyzing student performance data and recommending additional materials according to their level of understanding,

[0784] A system that includes this.

[0785] (Claim 2)

[0786] The system according to claim 1, which includes means for evaluating educational standards based on accumulated information.

[0787] (Claim 3)

[0788] The system according to claim 1, which includes means for adjusting educational plans to take regional differences into account based on the analyzed information.

[0789] "Application Example 1"

[0790] (Claim 1)

[0791] Means for collecting and accumulating educational data,

[0792] A means of analyzing collected data and automatically generating educational plans,

[0793] A means for optimizing educational materials and assessment tests based on the generated educational plan,

[0794] A means of displaying an interface for managing educational progress and providing individualized instruction,

[0795] A means of updating educational data in real time,

[0796] A means for controlling an automated device equipped with an educational support device that includes means for providing customized educational materials based on the progress of the students,

[0797] A system that includes this.

[0798] (Claim 2)

[0799] The system according to claim 1, which includes means for evaluating educational standards based on accumulated data.

[0800] (Claim 3)

[0801] The system according to claim 1, comprising means for adjusting educational plans to take regional differences into account based on analyzed data.

[0802] "Example 2 of combining an emotion engine"

[0803] (Claim 1)

[0804] Means for collecting and accumulating information in the field of education,

[0805] A means of analyzing accumulated information and automatically generating educational plans,

[0806] A means to optimize teaching materials and assessment methods based on the generated educational plan,

[0807] A means of recognizing the emotional state of users and reflecting that information in educational plans,

[0808] A means of managing educational progress and providing a display function for delivering customized instruction,

[0809] A means of updating educational information in real time,

[0810] A system that includes this.

[0811] (Claim 2)

[0812] The system according to claim 1, which includes means for evaluating the level of education based on accumulated information and responding to the needs of individual learners.

[0813] (Claim 3)

[0814] The system according to claim 1, comprising means for adjusting educational plans to take regional differences into account based on analyzed information.

[0815] "Application example 2 when combining with an emotional engine"

[0816] (Claim 1)

[0817] Means for collecting and accumulating educational data and emotional data,

[0818] A means of analyzing collected data and automatically generating educational plans,

[0819] A means for optimizing educational materials and measurement methods based on the generated educational plan,

[0820] A means of displaying information to manage educational progress and provide individualized instruction,

[0821] A means of updating educational data in real time,

[0822] A means of sharing optimal educational resources across all educational institutions in the region,

[0823] A system that includes this.

[0824] (Claim 2)

[0825] The system according to claim 1, which includes means for evaluating educational standards based on accumulated data.

[0826] (Claim 3)

[0827] The system according to claim 1, comprising means for adjusting the educational plan to take regional differences based on the analyzed data. [Explanation of Symbols]

[0828] 10, 210, 310, 410 Data Processing Systems 12 Data Processing Devices 14 Smart Devices 214 Smart Glasses 314 Headset-type terminal 414 Robots< / url:> < / url:> < / url:> < / url:>

Claims

1. Means for collecting and accumulating educational data, A means of analyzing collected data and automatically generating educational plans, A means for optimizing educational materials and assessment tests based on the generated educational plan, A means of displaying an interface for managing educational progress and providing individualized instruction, A means of updating educational data in real time, A means for controlling an automated device equipped with an educational support device that includes means for providing customized educational materials based on the progress of the students, A system that includes this.

2. The system according to claim 1, which includes means for evaluating educational standards based on accumulated data.

3. The system according to claim 1, comprising means for adjusting educational plans to take regional differences into account based on analyzed data.

Images