system

Abstract

We provide the system. [Solution] A database means for receiving and storing educational progress information from educators, An analysis means that performs analysis by comparing educational progress information stored in the aforementioned database means with educational guidance standards information and entrance examination question trend information, A plan generation means that automatically generates the next educational plan based on the results of the analysis means, A means for presenting the generated educational plan to the educator, and if revisions are made, for saving the revised information back to the database means, 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 as a 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] There is a problem that educators spend a lot of time on lesson preparation and the quality of education depends on the individual abilities and experiences of educators. Especially in junior high school classes, progress management and entrance examination countermeasures have become complicated, increasing the burden on educators. Therefore, it is necessary to create an environment in which educators can prepare lessons efficiently and effectively and concentrate on improving students' academic abilities.

Means for Solving the Problems

[0005] This invention provides a system that receives educational progress information from educators and stores it in a database. Furthermore, this system analyzes the stored information by comparing it with educational guidance standards information and entrance examination question trend information. This enables the system to automatically generate the next lesson plan and provide it to educators, thereby improving the efficiency and quality of lesson preparation. In addition, the generated lesson plan can be modified by the educator, and the modified information is also stored in the database, forming a feedback loop that can be used as a reference for future lessons. This system realizes practical education, in particular, by generating plans that take into account the trends in high school entrance examination questions.

[0006] An "educator" is a person who is responsible for instructing students and teaching classes in an educational institution.

[0007] "Educational progress information" refers to data that shows the content achieved to date and the level of student understanding in a particular lesson or learning activity.

[0008] A "database system" is a system that has the function of storing received information and managing it in a format that can be quickly accessed as needed.

[0009] "Educational guidance standards information" refers to information that indicates standards for educational content and progress, established based on educational institutions and educational policies.

[0010] "Entrance examination question trend information" refers to information that shows the trends in the format, content, and difficulty level of questions in past entrance examinations.

[0011] "Analysis tools" refer to functions within a system that analyze data using specific methods and derive insights and decision-making based on the results.

[0012] The "plan generation means" is a function that automatically creates an efficient and effective educational plan based on the analysis results.

[0013] "Correction information" refers to data that shows changes or additions made by educators to plans or processes. [Brief explanation of the drawing]

[0014] [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]

[0015] Hereinafter, an example of an embodiment of a system according to the technology of the present disclosure will be described with reference to the accompanying drawings.

[0016] First, the terms used in the following description will be explained.

[0017] In the following embodiments, a 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.

[0018] In the following embodiments, a labeled RAM (Random Access Memory) is a memory in which information is temporarily stored and is used as a work memory by the processor.

[0019] In the following embodiments, a 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, etc.

[0020] In the following embodiments, the signed communication interface (I / F) is an interface that includes a communication processor and an antenna, etc. The communication interface manages communication between multiple computers. Examples of communication standards applicable to the communication interface include wireless communication standards such as 5G (5th Generation Mobile Communication System), Wi-Fi (registered trademark), or Bluetooth (registered trademark).

[0021] 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."

[0022] [First Embodiment]

[0023] Figure 1 shows an example of the configuration of the data processing system 10 according to the first embodiment.

[0024] 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.

[0025] 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).

[0026] 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.

[0027] 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.

[0028] 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.

[0029] 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.

[0030] Figure 2 shows an example of the main functions of the data processing device 12 and the smart device 14.

[0031] 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.

[0032] 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.

[0033] 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.

[0034] 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".

[0035] This invention provides a system that enables educators to efficiently prepare for lessons and improve the quality of education. This system reduces the burden on educators and supports effective teaching by using a database that receives and stores educational progress information from educators.

[0036] First, educators input educational progress information using a terminal after each lesson. This information includes data such as lesson content, progress, comprehension indicators, and questions and answers. The terminal then sends this information to a server.

[0037] The server stores the received educational progress information in a database. The server then compares the information in the database with educational guidance standards and high school entrance exam question trends. This clarifies which areas need reinforcement and which types of questions should be prioritized in teaching.

[0038] Based on the analysis results, the server automatically generates an educational plan for the next lesson. This plan includes suggestions for new topics, key points, and supplementary explanations for solving past problems. In particular, practice problems that take into account the trends in entrance exam questions are also incorporated into this plan.

[0039] The generated plan is presented to the educator on their device. The educator can review the presented plan and make modifications or additions as needed. The modified or added plan is sent back to the server and saved in the database. This information is then used as feedback to help generate future plans.

[0040] For example, when teaching quadratic equations in a math class, if the lesson progress information indicates that the teacher "explained the method of solving using factorization," the server will generate a "next lesson plan to deepen understanding of the completing the square method" based on that information. It can also create links to "maximum / minimum problems," which have frequently appeared in past entrance exams, and include specific practice problems in the plan.

[0041] In this way, the system of the present invention automatically aggregates the elements that educators should consider when preparing lessons, and supports effective lesson planning. As a result, educators can reduce the amount of time spent on rote instruction and concentrate on improving students' understanding.

[0042] The following describes the processing flow.

[0043] Step 1:

[0044] After class, users use a terminal to input class progress information. This information includes topics covered in the day's lesson, student comprehension levels, questions asked, and progress made. The terminal reviews the entered data and prepares it to be sent to the server in the appropriate format.

[0045] Step 2:

[0046] The server receives the data sent from the terminal. The server saves this lesson progress information to the database along with past information stored in the existing database. The saved data plays an important role in understanding the progress of lessons over time.

[0047] Step 3:

[0048] The server compares stored educational progress information with educational guidance standards and high school entrance exam question trends. Based on this comparison, the server utilizes machine learning models and other tools to analyze which areas should be prioritized in education.

[0049] Step 4:

[0050] The server automatically generates a lesson plan for the next class based on the analysis results. This generation process includes suggesting new learning topics, highlighting key points to be emphasized, and selecting practice problems that are particularly suited to entrance exam preparation. This plan helps educators prepare for lessons efficiently.

[0051] Step 5:

[0052] The generated lesson plan is sent to the device and presented to the user. The user can review the presented plan and make modifications or additions as needed. Modifications and additions are at the educator's discretion, based on the characteristics of the students and the progress of the class.

[0053] Step 6:

[0054] The lesson plan, modified by the user, is sent back to the server from the terminal. The server stores this modified information in a database and uses it as reference information for improvements in future lesson plan generation. In this way, the educational system continuously receives feedback and is continuously optimized.

[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] In modern education, efficiently preparing lessons and improving the quality of education are crucial challenges. However, especially in entrance exam preparation, educators must dedicate considerable time and effort to gathering information and planning lesson content. A system is needed to alleviate the burden of this process and provide effective educational plans tailored to the individual needs of each student.

[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 data storage means for receiving and storing educational progress information from educators, information analysis means for performing comparative analysis with exam question trend information based on the educational progress information, and plan generation means for generating the next educational plan using a generated AI model. This enables educators to quickly create effective and optimized educational plans and improve the quality of education.

[0060] "Educational progress information" refers to various data collected by educators after lessons, such as lesson content, lesson progress, student comprehension, and question-and-answer sessions.

[0061] A "data storage means" is a component within a system for receiving and appropriately storing educational progress information.

[0062] "Information analysis means" refers to devices or programs that perform cross-referencing and analysis of educational progress information stored in data storage means with educational guidance standards information and examination question trend information.

[0063] A "plan generation means" is a component that has the function of generating an educational plan for the next lesson using the results of an information analysis means.

[0064] A "generative AI model" refers to an algorithm or program that uses machine learning to generate educational plans based on a large amount of data.

[0065] "Communication means" refers to equipment and programs that have protocols and functions for transmitting information from terminals used by educators to a server.

[0066] An "information update mechanism" is a component that has the function of saving revised educational plans by educators back into the database and using them to generate future plans.

[0067] This invention is a system designed to support educators in efficiently preparing lessons and to improve the quality of education. This system automates the process of receiving and analyzing educational progress information to generate the next lesson plan. Details regarding the implementation of this system are provided below.

[0068] First, the educator, as the user, enters the lesson progress into a terminal after the lesson ends. This terminal is equipped with appropriate software to convert the information into a standardized format and securely transmit it to the server. The information includes the lesson topics, progress, student comprehension, and the content of the question and answer session.

[0069] Next, the server verifies the educational progress information received from the terminal and stores it in a database. This database has a structure that stores information in association with dates and class information, preparing it for future analysis.

[0070] The server uses a generative AI model to compare information stored in the database with educational guidance standards and exam question trends. This generative AI model employs machine learning techniques and incorporates algorithms to generate the most effective educational plans from the analysis results.

[0071] Once a lesson plan is generated, the server sends it to the terminal. The terminal presents the lesson plan to the educator in an easy-to-understand format, allowing the user to review and modify the content as needed. The modified information is sent back to the server and stored in the database, where it is used as feedback for future plan generation.

[0072] For example, if a teacher enters educational progress information indicating that they "explained the method of solving quadratic equations using factorization" during a math lesson, the server will generate a "next lesson plan to deepen understanding of the completing the square method" based on that information. It can also create links to "maximum / minimum problems" that frequently appeared in past exams, and include specific practice problems in the plan.

[0073] An example of a prompt message might be, "Send the lesson progress information on quadratic equations to the server and request the automatic generation of the next lesson plan." Through this prompt message, the system can efficiently formulate educational plans and support educators in preparing for lessons.

[0074] The flow of the specific processing in Example 1 will be explained using Figure 11.

[0075] Step 1:

[0076] The educator, as the user, enters teaching progress information into the terminal after each lesson. Specifically, they fill in a form with the lesson topic, progress, student understanding, and Q&A content. The entered data is converted into a standardized format to maintain consistency on the terminal and is ready to be sent to the server.

[0077] Step 2:

[0078] The terminal sends standardized educational progress information to the server. Secure communication protocols such as HTTPS are used to ensure the reliability and confidentiality of the data. Upon receiving the information, the server performs data verification to confirm that there are no problems with the content.

[0079] Step 3:

[0080] The server stores the received educational progress information in a database. The information is linked to dates and class information, and structured to allow for efficient retrieval in subsequent analysis. This prepares the system for subsequent analysis processes.

[0081] Step 4:

[0082] The server retrieves stored educational progress information and uses a generating AI model to compare it with educational guidance standards information and exam question trend information. The information analysis system then runs the AI ​​model, performing data processing and calculations to generate an optimal educational plan. As a result, it determines which topics should be strengthened and which issues should be focused on.

[0083] Step 5:

[0084] The server sends the generated lesson plan to the terminal. This plan includes suggestions for new topics, key points, and practice exercises related to those topics. The terminal then presents it to the educator in a visually easy-to-understand format.

[0085] Step 6:

[0086] The user, the educator, reviews the presented lesson plan and makes modifications or additions as needed. The educator can add or modify specific content on their device and then resend that information to the server.

[0087] Step 7:

[0088] The server receives correction information from educators and stores it in a database. This correction information is used as feedback for future plan generation and is utilized to improve the accuracy of the AI ​​model.

[0089] (Application Example 1)

[0090] 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."

[0091] Given that educators currently spend considerable time and effort preparing lessons and improving student comprehension, there is a need to efficiently create educational plans and provide effective teaching methods, particularly to support homework. Furthermore, the effort required to create learning plans tailored to each student's progress and level of understanding must be minimized. To address these challenges, it is crucial to effectively utilize information within the educational setting, reduce the burden on educators, and provide high-quality learning support.

[0092] 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.

[0093] In this invention, the server includes a storage means for receiving and storing educational progress information from educators; a processing means for analyzing the educational progress information stored in the storage means by comparing it with educational guidance standards information and test trend information; and a plan generation means for automatically generating the next educational plan based on the results of the processing means, including a plan to support home learning. This enables educators to efficiently create lesson plans and to provide effective guidance to support students' home learning.

[0094] "Educational progress information" refers to information entered by educators after each lesson, such as lesson content, progress, comprehension indicators, and Q&A.

[0095] A "memory device" refers to a database or storage device used to store received educational progress information.

[0096] "Processing means" refers to algorithms and programs for analyzing data by comparing educational progress information stored in memory means with educational guidance standards information and examination trend information.

[0097] The "plan generation means" is a mechanism that automatically generates the next lesson plan based on the analysis results from the processing means, and constructs a plan to support students' home education.

[0098] A "display device" is an interface or device that presents a generated educational plan and provides information to the user visually.

[0099] "Correction information" refers to information that educators have modified or added to the generated educational plan, and which is then stored again in memory.

[0100] A "machine learning model" is a form of artificial intelligence used to analyze educational progress information and propose the optimal learning plan.

[0101] A "generative AI model" is a model used as part of machine learning to propose new home learning plans and teaching methods based on educational data.

[0102] This invention is a system aimed at enabling educators to prepare lessons efficiently and supporting students' homework. Its main components are a server, a terminal used by educators, and a display device accessed by students.

[0103] The server receives educational progress information sent from educators and stores this information in a database such as MySQL® or PostgreSQL. The stored information is processed using a Python script and analyzed by comparing it with educational guidance standards information and entrance examination trend information. Based on the results of this analysis, a machine learning model generates an AI model to automatically generate the next lesson plan. The plan generation method can construct a concrete plan to support home study and suggest practice problems and review topics.

[0104] The terminal provides an interface for educators to input progress information and sends and receives information through communication with the server. The generated lesson plans are presented to educators through a user interface using React or Vue.js. If educators make revisions to the plan, this revision information is saved again to the database by the server and used for future plan generation.

[0105] As a concrete example, after checking students' understanding of quadratic equations in a math class, the educator inputs progress information via a device. Based on this information, an AI model generates practice problems, including links to problems on completing the square and finding maximum / minimum values, and provides them to students as part of their next homework plan.

[0106] An example of a prompt message is shown: "Enter the math topics you learned in today's lesson, and let the AI ​​generate your next homework plan. Please fill in the lesson content and your level of understanding."

[0107] The flow of a specific process in Application Example 1 will be explained using Figure 12.

[0108] Step 1:

[0109] The terminal provides an interface for educators to input progress information after class. Educators input information such as lesson content, progress, comprehension indicators, and questions and answers. The entered information is then prepared for transmission to the server.

[0110] Step 2:

[0111] The server receives educational progress information sent from the terminal. The received data is stored in a database such as MySQL or PostgreSQL. The input here is information from the educator, and the output is a notification that the data has been saved to the database.

[0112] Step 3:

[0113] The server retrieves educational progress information stored in the database and analyzes the data by comparing it with educational guidance standards and exam trend information using a Python script. The input is the stored progress information, and the output is the analysis results. Data mining techniques are used to extract information for designing the next steps based on the level of understanding.

[0114] Step 4:

[0115] The server uses a machine learning-based AI model generated from the analysis results to automatically generate the next lesson plan. The generated plan includes specific practice problems and review topics to support homework. The input is the analysis results, and the output is the generated lesson plan. Here, the model develops an effective learning plan based on educational data.

[0116] Step 5:

[0117] The generated lesson plans are displayed on the device through an interface built with React or Vue.js. Educators review the plans and make revisions as needed. The input is the generated lesson plan, and the output is the educator's feedback and revision information. The interface is user-friendly and incorporates educator feedback.

[0118] Step 6:

[0119] When a user makes a correction, that correction information is sent back to the server via the terminal and stored in the database. The input is the correction information from the educator, and the output is the updated database information. This allows for the accumulation of feedback necessary for future plan generation.

[0120] 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.

[0121] This invention is a system aimed at reducing the burden on educators in lesson preparation and improving the quality of education. By combining it with an emotion engine, it understands the emotions of educators and provides flexible educational plans that respond accordingly.

[0122] After class, users input their class progress information using a terminal. The terminal uses an emotion engine to recognize the user's emotional state, for example, determining whether they are stressed or relaxed. This information, along with the class progress data, is sent to the server.

[0123] The server stores the received educational progress information and emotional information in a database. Next, the server analyzes the progress information, taking the emotional information into consideration. The analysis method compares it with educational guidance standards information and entrance examination question trend information, and, taking the emotional information into account, selects the optimal educational guidance content.

[0124] Based on the analysis results, the server automatically generates the next lesson plan. The emotion engine can then include suggestions for making the lesson more flexible or adaptable if the user was experiencing stress. The generated plan may include points to focus on, as well as elements for relaxation and encouraging messages.

[0125] The generated educational plan is displayed on the device and presented to the user. The user can review the presented plan and make revisions if necessary. During the review process, the emotion engine also operates, reassessing the user's emotional state and prompting adjustments to the plan.

[0126] For example, in a math class, when dealing with "problem solving using factorization," if a user feels overwhelmed during the process, the server can generate a "plan that provides detailed explanations and step-by-step practice problems." It can also strengthen links to frequently appearing "problem formats" in entrance exams and suggest lesson plans that are easy to follow.

[0127] Thus, by taking into account the emotions of educators, the system of the present invention provides more personalized and effective support for lesson preparation, and creates an environment in which educators can concentrate on instructing students.

[0128] The following describes the processing flow.

[0129] Step 1:

[0130] After class ends, users use a terminal to input information about the day's class progress. The terminal activates an emotion engine during the input process, extracting emotional information from the user's facial expressions and tone of voice. This data includes topics covered in class, student reactions, and the user's stress level and motivation at that time.

[0131] Step 2:

[0132] The terminal sends collected progress data and emotional information to the server. The server stores the received information in a database, accumulating user emotional state data along with chronological progress records. This data will be used as foundational data for future lesson planning.

[0133] Step 3:

[0134] The server begins analysis based on educational progress information and sentiment information stored in the database. The analysis method uses machine learning algorithms to compare educational guidance standards information with entrance examination question trends information and derives an adaptive approach based on sentiment information. As a result, it identifies topics that need reinforcement and areas of instruction that need to be focused in the next lesson.

[0135] Step 4:

[0136] The server automatically generates the next lesson plan based on the analysis results. The plan generation method utilizes emotional information and flexibly adjusts the content, for example, by simplifying the content if the user is experiencing stress and incorporating positive feedback. This plan includes specific lesson objectives, necessary teaching materials, and practice problems that take entrance exam preparation into consideration.

[0137] Step 5:

[0138] The generated lesson plan is sent to the device and presented to the user. The user can review the plan and make adjustments or additions, taking into account their teaching style and the characteristics of their class. The emotion engine also operates during this process, and can suggest further adjustments based on the user's reactions.

[0139] Step 6:

[0140] The lesson plan, revised by the user, is sent back to the server via the terminal. The server saves the revised plan to its database and uses it as feedback. This feedback loop continuously improves the quality of future lesson plans.

[0141] Through this series of processes, the system of the present invention enables adaptive lesson preparation that takes into account the emotions of educators, and provides an environment in which they can concentrate on student guidance.

[0142] (Example 2)

[0143] 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 will be referred to as the "terminal."

[0144] Traditionally, educators have expended considerable effort preparing lessons, and it has been particularly difficult to create flexible plans based on progress information and students' emotions. Furthermore, emotional stress has negatively impacted the quality of education, and the one-sided nature of educational planning has been a cause for concern. This invention aims to solve these problems and improve the quality of education while reducing the burden on educators.

[0145] 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.

[0146] In this invention, the server includes data storage means for receiving and storing progress information from educators, analysis means for comparing and analyzing the progress information stored in the data storage means with educational standards information and evaluation trend information, and emotion analysis means for recognizing the emotional state of educators and adjusting the educational plan taking those emotions into consideration. This makes it possible to automatically generate flexible and effective educational plans that take into account not only progress information but also emotional information.

[0147] "Data storage means" refers to a method or system for accumulating and storing progress information and correction information received from educators.

[0148] "Analysis means" refers to a system or method for comparing stored progress information with educational standards information and evaluation trend information and performing analysis.

[0149] "Plan generation means" refers to a function or process that automatically generates the next educational plan based on the results obtained from the analysis means.

[0150] "Emotional analysis tools" refer to functions or methods for recognizing the emotional state of educators and adjusting educational plans while taking those emotions into consideration.

[0151] "Educational standards information" refers to a collection of information that includes standards and guidelines established regarding the instruction of educational content.

[0152] "Evaluation trend information" refers to information that shows trends and patterns related to educational evaluation, and serves as one reference material when creating educational plans.

[0153] "Progress information" refers to data that educators report after a lesson, indicating the progress and achievement level of the educational content.

[0154] This invention aims to build a system designed to improve the quality of education while reducing the burden on educators. Users input lesson progress information using a terminal after class. The terminal is equipped with emotion analysis software that highly analyzes the user's emotional state. This makes it possible to determine whether the user is relaxed or stressed.

[0155] Information collected by the terminal is transmitted to a server via the internet. The server stores emotional information along with progress information in a database, and then analysis software analyzes this information. Educational standards data and evaluation trend data are used in the analysis. This data is compared with past data using a generative AI model to obtain analysis results. Based on these results, the server has the ability to automatically generate the next educational plan.

[0156] The generated lesson plans include emphasis and methods for teaching content. Furthermore, they may incorporate relaxing elements and encouraging messages, flexibly adjusted based on the results of emotion analysis. This allows educators to conduct lessons that address the individual emotional needs of students.

[0157] For example, when a user is teaching "factorization" in a math class, if the sentiment analysis software detects the user's anxiety, the server generates a plan that includes detailed explanations and step-by-step practice problems. Furthermore, it strengthens the links to example problems that match the format of questions that appear on entrance exams, and proposes lesson plans that are easy for students to follow.

[0158] An example of a prompt message would be: "Please automatically generate the next lesson plan. The user is feeling anxious about preparing for the factorization lesson. Please suggest a flexible lesson plan that includes detailed explanations and step-by-step practice problems."

[0159] The flow of the specific processing in Example 2 will be explained using Figure 13.

[0160] Step 1:

[0161] After class, the user uses a terminal to input information about their class progress. This data includes information about the class content, understanding, and progress. The terminal then activates emotion analysis software, which analyzes the user's voice and facial expressions to recognize their emotional state. The output consists of progress information and emotion information.

[0162] Step 2:

[0163] The device sends collected progress and sentiment information to the server. The data is encrypted before transmission to ensure security. Once the transmitted data reaches the server, the server records it in its database.

[0164] Step 3:

[0165] The server inputs information stored in the database into analysis software and performs the analysis. This analysis compares and matches progress information with sentiment information, referencing educational standards data and evaluation trend data. The output provides the analysis results, which serve as the basis for future educational planning.

[0166] Step 4:

[0167] The server uses a generation AI model to automatically generate the next lesson plan based on the analysis results. The plan generation is tailored to include key educational content, teaching methods, and emotionally appropriate elements such as relaxation and encouragement. The output is provided as a complete lesson plan.

[0168] Step 5:

[0169] The terminal receives the educational plan sent from the server and displays it to the user. The user can review the presented plan and make modifications if necessary. During this time, sentiment analysis software runs, reassessing the user's emotional state. The review results are sent to the server and recorded as update information in the database.

[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] For educators, lesson preparation is stressful, and there is a need to reduce this burden while maintaining the quality of instruction. However, conventional systems only generate uniform plans without considering the emotional state of educators, and do not adequately provide flexible educational support tailored to individual circumstances. Therefore, there is a need for a means to generate personalized educational plans based on educators' emotional information.

[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 recording means for receiving and storing educational progress information and emotional information from educators; analysis means for comparing and analyzing the educational progress information and emotional information stored in the recording means with educational guidance standard information and evaluation standard information; and plan generation means for automatically generating the next educational plan based on the results of the analysis means, and generating a plan that includes flexible suggestions according to the emotional state. This makes it possible to create more personalized educational plans that take into account the emotional state of educators.

[0175] "Educational progress information" refers to information recorded by educators regarding the progress of lessons and learning activities, and is used to evaluate the quality and effectiveness of educational guidance.

[0176] "Emotional information" refers to information that represents the mental state of educators, and involves acquiring data on emotional states such as stress levels and relaxation levels.

[0177] "Recording means" refers to a device or software that has the function of receiving and storing educational progress information and emotional information.

[0178] "Analysis means" refers to a device or program that performs analysis based on information stored in a recording means, while comparing it with educational guidance standards information and evaluation standards information.

[0179] A "plan generation means" is a system or device that has the function of automatically generating the next educational plan based on the results of the analysis means.

[0180] "Educational guidance standards information" refers to information that outlines the basic guidance policies and content for educational activities, and is referenced when creating educational plans.

[0181] "Evaluation criteria information" refers to information that shows the standards used to evaluate the outcomes of education, and functions as an indicator for measuring the effectiveness of education.

[0182] This invention is a system designed to help educators prepare lessons efficiently. The system collects information on educational progress and student sentiment from educators and automatically generates the next lesson plan based on this information, thereby reducing the burden on educators.

[0183] The server receives educational progress and sentiment information transmitted from educators' terminals and stores them in a recording system. A cloud database (e.g., AWS® RDS) is used as the recording system, enabling secure and efficient storage of the information.

[0184] The analysis method uses machine learning algorithms to perform detailed analysis based on stored information. Specifically, it uses Emotion AI (e.g., Affectiva SDK) to evaluate the emotional state of educators and compares it with educational guidance standards and evaluation standards. This analysis quantifies the stress levels and relaxation levels of educators and reflects them in educational plans.

[0185] The plan generation mechanism utilizes the results of the analysis mechanism to generate lesson plans that are tailored to the educator's emotional state. These plans include not only standard educational content, but also flexible lesson suggestions that respond to emotional changes, elements to promote relaxation, and encouraging messages. This enables educators to provide more individualized instruction to students.

[0186] As a concrete example, in a mathematics class, if emotional information indicates stress when an educator is working on "problem solving using factorization," the server generates a plan that provides detailed explanations and step-by-step practice problems. This plan is then presented to the educator on their device for review and modification.

[0187] An example of a prompt is: "Use the emotion engine to create suggestions that personalize math lesson plans and help educators prepare better lesson plans."

[0188] This allows educators to prepare lessons effectively while being aware of their own emotional state.

[0189] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[0190] Step 1:

[0191] The device receives educational progress information and emotional information from the user as input. Educational progress information includes the progress of the lesson content and the students' level of understanding, while emotional information is recognized and quantified using Emotion AI to determine the user's mental state. This input data is sent from the device to the server.

[0192] Step 2:

[0193] The server stores received educational progress and sentiment information in a recording medium. This recording medium is a cloud database (e.g., AWS RDS), enabling secure and efficient data storage. After verifying the integrity of the data, the server proceeds to the next analysis stage.

[0194] Step 3:

[0195] The server processes the stored information using analytical tools. Here, machine learning algorithms are used to analyze educational progress information and emotional information, comparing them with educational guidance standards and evaluation standards. The input is a set of stored data, and the output is the analysis result, which includes detailed emotional states of educators and detailed information on educational progress.

[0196] Step 4:

[0197] The server generates the next educational plan using a plan generation mechanism based on the analysis results. This step incorporates flexible and personalized suggestions tailored to the user's emotional state. Specifically, detailed explanations, step-by-step exercises, and elements to promote relaxation are added to the plan. The analysis results are used as input, and the generated educational plan is obtained as output.

[0198] Step 5:

[0199] The server sends the generated lesson plan to the terminal. The terminal displays the plan to the user, allowing them to review and modify its contents. The user can then review the plan and make any necessary changes, and these changes are sent back to the server.

[0200] Step 6:

[0201] The server receives the correction information from the user and saves it again in the recording system. This process allows for more accurate suggestions when generating plans in the future. The input is the correction information, and the output is an updated database entry.

[0202] 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.

[0203] 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.

[0204] 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.

[0205] [Second Embodiment]

[0206] Figure 3 shows an example of the configuration of the data processing system 210 according to the second embodiment.

[0207] 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.

[0208] 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).

[0209] 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.

[0210] 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.

[0211] 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).

[0212] 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.

[0213] 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.

[0214] 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.

[0215] 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.

[0216] 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.

[0217] 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".

[0218] This invention provides a system that enables educators to efficiently prepare for lessons and improve the quality of education. This system reduces the burden on educators and supports effective teaching by using a database that receives and stores educational progress information from educators.

[0219] First, educators input educational progress information using a terminal after each lesson. This information includes data such as lesson content, progress, comprehension indicators, and questions and answers. The terminal then sends this information to a server.

[0220] The server stores the received educational progress information in a database. The server then compares the information in the database with educational guidance standards and high school entrance exam question trends. This clarifies which areas need reinforcement and which types of questions should be prioritized in teaching.

[0221] Based on the analysis results, the server automatically generates an educational plan for the next lesson. This plan includes suggestions for new topics, key points, and supplementary explanations for solving past problems. In particular, practice problems that take into account the trends in entrance exam questions are also incorporated into this plan.

[0222] The generated plan is presented to the educator on their device. The educator can review the presented plan and make modifications or additions as needed. The modified or added plan is sent back to the server and saved in the database. This information is then used as feedback to help generate future plans.

[0223] For example, when teaching quadratic equations in a math class, if the lesson progress information indicates that the teacher "explained the method of solving using factorization," the server will generate a "next lesson plan to deepen understanding of the completing the square method" based on that information. It can also create links to "maximum / minimum problems," which have frequently appeared in past entrance exams, and include specific practice problems in the plan.

[0224] In this way, the system of the present invention automatically aggregates the elements that educators should consider when preparing lessons, and supports effective lesson planning. As a result, educators can reduce the amount of time spent on rote instruction and concentrate on improving students' understanding.

[0225] The following describes the processing flow.

[0226] Step 1:

[0227] After class, users use a terminal to input class progress information. This information includes topics covered in the day's lesson, student comprehension levels, questions asked, and progress made. The terminal reviews the entered data and prepares it to be sent to the server in the appropriate format.

[0228] Step 2:

[0229] The server receives the data sent from the terminal. The server saves this lesson progress information to the database along with past information stored in the existing database. The saved data plays an important role in understanding the progress of lessons over time.

[0230] Step 3:

[0231] The server compares stored educational progress information with educational guidance standards and high school entrance exam question trends. Based on this comparison, the server utilizes machine learning models and other tools to analyze which areas should be prioritized in education.

[0232] Step 4:

[0233] The server automatically generates a lesson plan for the next class based on the analysis results. This generation process includes suggesting new learning topics, highlighting key points to be emphasized, and selecting practice problems that are particularly suited to entrance exam preparation. This plan helps educators prepare for lessons efficiently.

[0234] Step 5:

[0235] The generated lesson plan is sent to the device and presented to the user. The user can review the presented plan and make modifications or additions as needed. Modifications and additions are at the educator's discretion, based on the characteristics of the students and the progress of the class.

[0236] Step 6:

[0237] The lesson plan, modified by the user, is sent back to the server from the terminal. The server stores this modified information in a database and uses it as reference information for improvements in future lesson plan generation. In this way, the educational system continuously receives feedback and is continuously optimized.

[0238] (Example 1)

[0239] 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."

[0240] In modern education, efficiently preparing lessons and improving the quality of education are crucial challenges. However, especially in entrance exam preparation, educators must dedicate considerable time and effort to gathering information and planning lesson content. A system is needed to alleviate the burden of this process and provide effective educational plans tailored to the individual needs of each student.

[0241] 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.

[0242] In this invention, the server includes data storage means for receiving and storing educational progress information from educators, information analysis means for performing comparative analysis with exam question trend information based on the educational progress information, and plan generation means for generating the next educational plan using a generated AI model. This enables educators to quickly create effective and optimized educational plans and improve the quality of education.

[0243] "Educational progress information" refers to various data collected by educators after lessons, such as lesson content, lesson progress, student comprehension, and question-and-answer sessions.

[0244] A "data storage means" is a component within a system for receiving and appropriately storing educational progress information.

[0245] "Information analysis means" refers to devices or programs that perform cross-referencing and analysis of educational progress information stored in data storage means with educational guidance standards information and examination question trend information.

[0246] A "plan generation means" is a component that has the function of generating an educational plan for the next lesson using the results of an information analysis means.

[0247] A "generative AI model" refers to an algorithm or program that uses machine learning to generate educational plans based on a large amount of data.

[0248] "Communication means" refers to equipment and programs that have protocols and functions for transmitting information from terminals used by educators to a server.

[0249] An "information update mechanism" is a component that has the function of saving revised educational plans by educators back into the database and using them to generate future plans.

[0250] This invention is a system designed to support educators in efficiently preparing lessons and to improve the quality of education. This system automates the process of receiving and analyzing educational progress information to generate the next lesson plan. Details regarding the implementation of this system are provided below.

[0251] First, the educator, as the user, enters the lesson progress into a terminal after the lesson ends. This terminal is equipped with appropriate software to convert the information into a standardized format and securely transmit it to the server. The information includes the lesson topics, progress, student comprehension, and the content of the question and answer session.

[0252] Next, the server verifies the educational progress information received from the terminal and stores it in a database. This database has a structure that stores information in association with dates and class information, preparing it for future analysis.

[0253] The server uses a generative AI model to compare information stored in the database with educational guidance standards and exam question trends. This generative AI model employs machine learning techniques and incorporates algorithms to generate the most effective educational plans from the analysis results.

[0254] Once a lesson plan is generated, the server sends it to the terminal. The terminal presents the lesson plan to the educator in an easy-to-understand format, allowing the user to review and modify the content as needed. The modified information is sent back to the server and stored in the database, where it is used as feedback for future plan generation.

[0255] For example, if a teacher enters educational progress information indicating that they "explained the method of solving quadratic equations using factorization" during a math lesson, the server will generate a "next lesson plan to deepen understanding of the completing the square method" based on that information. It can also create links to "maximum / minimum problems" that frequently appeared in past exams, and include specific practice problems in the plan.

[0256] An example of a prompt message might be, "Send the lesson progress information on quadratic equations to the server and request the automatic generation of the next lesson plan." Through this prompt message, the system can efficiently formulate educational plans and support educators in preparing for lessons.

[0257] The flow of the specific processing in Example 1 will be explained using Figure 11.

[0258] Step 1:

[0259] The educator, as the user, enters teaching progress information into the terminal after each lesson. Specifically, they fill in a form with the lesson topic, progress, student understanding, and Q&A content. The entered data is converted into a standardized format to maintain consistency on the terminal and is ready to be sent to the server.

[0260] Step 2:

[0261] The terminal sends standardized educational progress information to the server. Secure communication protocols such as HTTPS are used to ensure the reliability and confidentiality of the data. Upon receiving the information, the server performs data verification to confirm that there are no problems with the content.

[0262] Step 3:

[0263] The server stores the received educational progress information in a database. The information is linked to dates and class information, and structured to allow for efficient retrieval in subsequent analysis. This prepares the system for subsequent analysis processes.

[0264] Step 4:

[0265] The server retrieves stored educational progress information and uses a generating AI model to compare it with educational guidance standards information and exam question trend information. The information analysis system then runs the AI ​​model, performing data processing and calculations to generate an optimal educational plan. As a result, it determines which topics should be strengthened and which issues should be focused on.

[0266] Step 5:

[0267] The server sends the generated lesson plan to the terminal. This plan includes suggestions for new topics, key points, and practice exercises related to those topics. The terminal then presents it to the educator in a visually easy-to-understand format.

[0268] Step 6:

[0269] The user, the educator, reviews the presented lesson plan and makes modifications or additions as needed. The educator can add or modify specific content on their device and then resend that information to the server.

[0270] Step 7:

[0271] The server receives correction information from educators and stores it in a database. This correction information is used as feedback for future plan generation and is utilized to improve the accuracy of the AI ​​model.

[0272] (Application Example 1)

[0273] 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."

[0274] Given that educators currently spend considerable time and effort preparing lessons and improving student comprehension, there is a need to efficiently create educational plans and provide effective teaching methods, particularly to support homework. Furthermore, the effort required to create learning plans tailored to each student's progress and level of understanding must be minimized. To address these challenges, it is crucial to effectively utilize information within the educational setting, reduce the burden on educators, and provide high-quality learning support.

[0275] 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.

[0276] In this invention, the server includes a storage means for receiving and storing educational progress information from educators; a processing means for analyzing the educational progress information stored in the storage means by comparing it with educational guidance standards information and test trend information; and a plan generation means for automatically generating the next educational plan based on the results of the processing means, including a plan to support home learning. This enables educators to efficiently create lesson plans and to provide effective guidance to support students' home learning.

[0277] "Educational progress information" refers to information entered by educators after each lesson, such as lesson content, progress, comprehension indicators, and Q&A.

[0278] A "memory device" refers to a database or storage device used to store received educational progress information.

[0279] The "processing means" is an algorithm or program for collating educational progress information stored in the storage means with educational guidance standard information and examination trend information and analyzing the data.

[0280] The "plan generation means" is a mechanism that automatically generates the next lesson plan based on the analysis result by the processing means and constructs a plan for supporting the home education of students.

[0281] The "display device" is an interface or device for presenting the generated educational plan and visually providing information to the user.

[0282] The "correction information" is information on corrections and additions made to the educational plan generated by the educator, and is information that is stored in the storage means again.

[0283] The "machine learning model" is a form of artificial intelligence used to analyze educational progress information and propose an optimal learning plan.

[0284] The "generation AI model" is a model for proposing a new home learning plan and teaching method based on educational data as part of machine learning.

[0285] This invention is a system aimed at efficient lesson preparation for educators and support for students' home learning. The main components are a server, a terminal used by educators, and a display device accessed by students.

[0286] The server receives educational progress information transmitted from the educator and stores this information in a database such as MySQL or PostgreSQL. The stored information is processed using a Python script and analyzed by collating it with educational guidance standard information and examination trend information for entrance examinations. Based on the result of this analysis, the machine learning model utilizes the generation AI model to automatically generate the next lesson plan. The plan generation means can construct a specific plan for supporting home learning and propose practice problems and review topics.

[0287] The terminal provides an interface for educators to input progress information and transmits and receives information through communication with the server. Also, the generated teaching plan is presented to the educator through a user interface using React or Vue.js. When the educator makes a modification to the plan, the modification information is saved again to the database by the server and utilized for the next plan generation.

[0288] As a specific example, after checking the understanding level of "quadratic equations" in a math class, the educator inputs progress information through the terminal. Based on that information, the AI model generates practice questions including links to "completing the square" and "maximum and minimum problems" and provides them to the students as the next home learning plan.

[0289] As an example of a prompt sentence, "Enter the math topic learned in today's class and ask the AI to generate the next home learning plan. Please fill in the class content and understanding level." is shown.

[0290] The flow of the specific process in Application Example 1 will be described using FIG. 12.

[0291] Step 1:

[0292] The terminal provides an interface for the educator to input progress information after the class. The educator inputs information such as class content, progress, understanding level indicators, and question-and-answer. The input information is prepared to be transmitted to the server.

[0293] Step 2:

[0294] The server receives the educational progress information transmitted from the terminal. The received data is stored in a database such as MySQL or PostgreSQL. The input here is information from the educator, and the output is a notification of successful storage in the database.

[0295] Step 3:

[0296] The server retrieves educational progress information stored in the database and analyzes the data by comparing it with educational guidance standards and exam trend information using a Python script. The input is the stored progress information, and the output is the analysis results. Data mining techniques are used to extract information for designing the next steps based on the level of understanding.

[0297] Step 4:

[0298] The server uses a machine learning-based AI model generated from the analysis results to automatically generate the next lesson plan. The generated plan includes specific practice problems and review topics to support homework. The input is the analysis results, and the output is the generated lesson plan. Here, the model develops an effective learning plan based on educational data.

[0299] Step 5:

[0300] The generated lesson plans are displayed on the device through an interface built with React or Vue.js. Educators review the plans and make revisions as needed. The input is the generated lesson plan, and the output is the educator's feedback and revision information. The interface is user-friendly and incorporates educator feedback.

[0301] Step 6:

[0302] When a user makes a correction, that correction information is sent back to the server via the terminal and stored in the database. The input is the correction information from the educator, and the output is the updated database information. This allows for the accumulation of feedback necessary for future plan generation.

[0303] 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.

[0304] The present invention is a system aimed at reducing the burden on educators in lesson preparation and improving the quality of education. By combining an emotion engine, it understands the emotions of educators and realizes the provision of a flexible educational plan accordingly.

[0305] After the class, the user uses the terminal to input the progress information of the class. At this time, the terminal uses the emotion engine to recognize the user's emotional state. For example, it determines whether the user is feeling stressed or relaxed. This information is sent to the server together with the class progress data.

[0306] The server stores the received educational progress information and emotion information in a database. Next, the server analyzes the progress information considering the emotion information. The analysis means collates with educational guidance standard information and entrance examination question tendency information, and selects the optimal educational guidance content taking into account the emotion information.

[0307] Based on the analysis results, the server automatically generates the next class plan. Here, the emotion engine can include proposals for making the class content more flexible or devising it when the user is under stress. The generated plan may also include points to focus on, elements for relaxation, and encouraging messages.

[0308] The generated educational plan is displayed on the terminal and presented to the user. The user can review the presented plan and make corrections if necessary. The emotion engine also operates during the review to re-evaluate the user's emotional state and prompt adjustment of the plan.

[0309] For example, when dealing with "problem-solving using factorization" in a math class, if the user feels anxious during the process, the server generates a plan to "provide detailed explanations and step-by-step practice problems". Also, it can strengthen the link with the "problem format" frequently appearing in entrance examinations and propose teaching plans that are easy to tackle.

[0310] Thus, by taking into account the emotions of educators, the system of the present invention provides more personalized and effective support for lesson preparation, and creates an environment in which educators can concentrate on instructing students.

[0311] The following describes the processing flow.

[0312] Step 1:

[0313] After class ends, users use a terminal to input information about the day's class progress. The terminal activates an emotion engine during the input process, extracting emotional information from the user's facial expressions and tone of voice. This data includes topics covered in class, student reactions, and the user's stress level and motivation at that time.

[0314] Step 2:

[0315] The terminal sends collected progress data and emotional information to the server. The server stores the received information in a database, accumulating user emotional state data along with chronological progress records. This data will be used as foundational data for future lesson planning.

[0316] Step 3:

[0317] The server begins analysis based on educational progress information and sentiment information stored in the database. The analysis method uses machine learning algorithms to compare educational guidance standards information with entrance examination question trends information and derives an adaptive approach based on sentiment information. As a result, it identifies topics that need reinforcement and areas of instruction that need to be focused in the next lesson.

[0318] Step 4:

[0319] The server automatically generates the next lesson plan based on the analysis results. The plan generation method utilizes emotional information and flexibly adjusts the content, for example, by simplifying the content if the user is experiencing stress and incorporating positive feedback. This plan includes specific lesson objectives, necessary teaching materials, and practice problems that take entrance exam preparation into consideration.

[0320] Step 5:

[0321] The generated lesson plan is sent to the device and presented to the user. The user can review the plan and make adjustments or additions, taking into account their teaching style and the characteristics of their class. The emotion engine also operates during this process, and can suggest further adjustments based on the user's reactions.

[0322] Step 6:

[0323] The lesson plan, revised by the user, is sent back to the server via the terminal. The server saves the revised plan to its database and uses it as feedback. This feedback loop continuously improves the quality of future lesson plans.

[0324] Through this series of processes, the system of the present invention enables adaptive lesson preparation that takes into account the emotions of educators, and provides an environment in which they can concentrate on student guidance.

[0325] (Example 2)

[0326] 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".

[0327] Traditionally, educators have expended considerable effort preparing lessons, and it has been particularly difficult to create flexible plans based on progress information and students' emotions. Furthermore, emotional stress has negatively impacted the quality of education, and the one-sided nature of educational planning has been a cause for concern. This invention aims to solve these problems and improve the quality of education while reducing the burden on educators.

[0328] 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.

[0329] In this invention, the server includes data storage means for receiving and storing progress information from educators, analysis means for comparing and analyzing the progress information stored in the data storage means with educational standards information and evaluation trend information, and emotion analysis means for recognizing the emotional state of educators and adjusting the educational plan taking those emotions into consideration. This makes it possible to automatically generate flexible and effective educational plans that take into account not only progress information but also emotional information.

[0330] "Data storage means" refers to a method or system for accumulating and storing progress information and correction information received from educators.

[0331] "Analysis means" refers to a system or method for comparing stored progress information with educational standards information and evaluation trend information and performing analysis.

[0332] "Plan generation means" refers to a function or process that automatically generates the next educational plan based on the results obtained from the analysis means.

[0333] "Emotional analysis tools" refer to functions or methods for recognizing the emotional state of educators and adjusting educational plans while taking those emotions into consideration.

[0334] "Educational standards information" refers to a collection of information that includes standards and guidelines established regarding the instruction of educational content.

[0335] "Evaluation trend information" refers to information that shows trends and patterns related to educational evaluation, and serves as one reference material when creating educational plans.

[0336] "Progress information" refers to data that educators report after a lesson, indicating the progress and achievement level of the educational content.

[0337] This invention aims to build a system designed to improve the quality of education while reducing the burden on educators. Users input lesson progress information using a terminal after class. The terminal is equipped with emotion analysis software that highly analyzes the user's emotional state. This makes it possible to determine whether the user is relaxed or stressed.

[0338] Information collected by the terminal is transmitted to a server via the internet. The server stores emotional information along with progress information in a database, and then analysis software analyzes this information. Educational standards data and evaluation trend data are used in the analysis. This data is compared with past data using a generative AI model to obtain analysis results. Based on these results, the server has the ability to automatically generate the next educational plan.

[0339] The generated lesson plans include emphasis and methods for teaching content. Furthermore, they may incorporate relaxing elements and encouraging messages, flexibly adjusted based on the results of emotion analysis. This allows educators to conduct lessons that address the individual emotional needs of students.

[0340] For example, when a user is teaching "factorization" in a math class, if the sentiment analysis software detects the user's anxiety, the server generates a plan that includes detailed explanations and step-by-step practice problems. Furthermore, it strengthens the links to example problems that match the format of questions that appear on entrance exams, and proposes lesson plans that are easy for students to follow.

[0341] An example of a prompt message would be: "Please automatically generate the next lesson plan. The user is feeling anxious about preparing for the factorization lesson. Please suggest a flexible lesson plan that includes detailed explanations and step-by-step practice problems."

[0342] The flow of the specific processing in Example 2 will be explained using Figure 13.

[0343] Step 1:

[0344] After class, the user uses a terminal to input information about their class progress. This data includes information about the class content, understanding, and progress. The terminal then activates emotion analysis software, which analyzes the user's voice and facial expressions to recognize their emotional state. The output consists of progress information and emotion information.

[0345] Step 2:

[0346] The device sends collected progress and sentiment information to the server. The data is encrypted before transmission to ensure security. Once the transmitted data reaches the server, the server records it in its database.

[0347] Step 3:

[0348] The server inputs information stored in the database into analysis software and performs the analysis. This analysis compares and matches progress information with sentiment information, referencing educational standards data and evaluation trend data. The output provides the analysis results, which serve as the basis for future educational planning.

[0349] Step 4:

[0350] The server uses a generation AI model to automatically generate the next lesson plan based on the analysis results. The plan generation is tailored to include key educational content, teaching methods, and emotionally appropriate elements such as relaxation and encouragement. The output is provided as a complete lesson plan.

[0351] Step 5:

[0352] The terminal receives the educational plan sent from the server and displays it to the user. The user can review the presented plan and make modifications if necessary. During this time, sentiment analysis software runs, reassessing the user's emotional state. The review results are sent to the server and recorded as update information in the database.

[0353] (Application Example 2)

[0354] 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."

[0355] For educators, lesson preparation is stressful, and there is a need to reduce this burden while maintaining the quality of instruction. However, conventional systems only generate uniform plans without considering the emotional state of educators, and do not adequately provide flexible educational support tailored to individual circumstances. Therefore, there is a need for a means to generate personalized educational plans based on educators' emotional information.

[0356] 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.

[0357] In this invention, the server includes recording means for receiving and storing educational progress information and emotional information from educators; analysis means for comparing and analyzing the educational progress information and emotional information stored in the recording means with educational guidance standard information and evaluation standard information; and plan generation means for automatically generating the next educational plan based on the results of the analysis means, and generating a plan that includes flexible suggestions according to the emotional state. This makes it possible to create more personalized educational plans that take into account the emotional state of educators.

[0358] "Educational progress information" refers to information recorded by educators regarding the progress of lessons and learning activities, and is used to evaluate the quality and effectiveness of educational guidance.

[0359] "Emotional information" refers to information that represents the mental state of educators, and involves acquiring data on emotional states such as stress levels and relaxation levels.

[0360] "Recording means" refers to a device or software that has the function of receiving and storing educational progress information and emotional information.

[0361] "Analysis means" refers to a device or program that performs analysis based on information stored in a recording means, while comparing it with educational guidance standards information and evaluation standards information.

[0362] A "plan generation means" is a system or device that has the function of automatically generating the next educational plan based on the results of the analysis means.

[0363] "Educational guidance standards information" refers to information that outlines the basic guidance policies and content for educational activities, and is referenced when creating educational plans.

[0364] "Evaluation criteria information" refers to information that shows the standards used to evaluate the outcomes of education, and functions as an indicator for measuring the effectiveness of education.

[0365] This invention is a system designed to help educators prepare lessons efficiently. The system collects information on educational progress and student sentiment from educators and automatically generates the next lesson plan based on this information, thereby reducing the burden on educators.

[0366] The server receives educational progress and sentiment information transmitted from educators' terminals and stores them in a recording system. A cloud database (e.g., AWS RDS) is used as the recording system, enabling secure and efficient storage of the information.

[0367] The analysis method uses machine learning algorithms to perform detailed analysis based on stored information. Specifically, it uses Emotion AI (e.g., Affectiva SDK) to evaluate the emotional state of educators and compares it with educational guidance standards and evaluation standards. This analysis quantifies the stress levels and relaxation levels of educators and reflects them in educational plans.

[0368] The plan generation mechanism utilizes the results of the analysis mechanism to generate lesson plans that are tailored to the educator's emotional state. These plans include not only standard educational content, but also flexible lesson suggestions that respond to emotional changes, elements to promote relaxation, and encouraging messages. This enables educators to provide more individualized instruction to students.

[0369] As a concrete example, in a mathematics class, if emotional information indicates stress when an educator is working on "problem solving using factorization," the server generates a plan that provides detailed explanations and step-by-step practice problems. This plan is then presented to the educator on their device for review and modification.

[0370] An example of a prompt is: "Use the emotion engine to create suggestions that personalize math lesson plans and help educators prepare better lesson plans."

[0371] This allows educators to prepare lessons effectively while being aware of their own emotional state.

[0372] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[0373] Step 1:

[0374] The device receives educational progress information and emotional information from the user as input. Educational progress information includes the progress of the lesson content and the students' level of understanding, while emotional information is recognized and quantified using Emotion AI to determine the user's mental state. This input data is sent from the device to the server.

[0375] Step 2:

[0376] The server stores received educational progress and sentiment information in a recording medium. This recording medium is a cloud database (e.g., AWS RDS), enabling secure and efficient data storage. After verifying the integrity of the data, the server proceeds to the next analysis stage.

[0377] Step 3:

[0378] The server processes the stored information using analytical tools. Here, machine learning algorithms are used to analyze educational progress information and emotional information, comparing them with educational guidance standards and evaluation standards. The input is a set of stored data, and the output is the analysis result, which includes detailed emotional states of educators and detailed information on educational progress.

[0379] Step 4:

[0380] The server generates the next educational plan using a plan generation mechanism based on the analysis results. This step incorporates flexible and personalized suggestions tailored to the user's emotional state. Specifically, detailed explanations, step-by-step exercises, and elements to promote relaxation are added to the plan. The analysis results are used as input, and the generated educational plan is obtained as output.

[0381] Step 5:

[0382] The server sends the generated lesson plan to the terminal. The terminal displays the plan to the user, allowing them to review and modify its contents. The user can then review the plan and make any necessary changes, and these changes are sent back to the server.

[0383] Step 6:

[0384] The server receives the correction information from the user and saves it again in the recording system. This process allows for more accurate suggestions when generating plans in the future. The input is the correction information, and the output is an updated database entry.

[0385] 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.

[0386] 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.

[0387] 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.

[0388] [Third Embodiment]

[0389] Figure 5 shows an example of the configuration of the data processing system 310 according to the third embodiment.

[0390] 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.

[0391] 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).

[0392] 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.

[0393] 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.

[0394] 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).

[0395] 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.

[0396] 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.

[0397] 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.

[0398] 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.

[0399] 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.

[0400] 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".

[0401] This invention provides a system that enables educators to efficiently prepare for lessons and improve the quality of education. This system reduces the burden on educators and supports effective teaching by using a database that receives and stores educational progress information from educators.

[0402] First, educators input educational progress information using a terminal after each lesson. This information includes data such as lesson content, progress, comprehension indicators, and questions and answers. The terminal then sends this information to a server.

[0403] The server stores the received educational progress information in a database. The server then compares the information in the database with educational guidance standards and high school entrance exam question trends. This clarifies which areas need reinforcement and which types of questions should be prioritized in teaching.

[0404] Based on the analysis results, the server automatically generates an educational plan for the next lesson. This plan includes suggestions for new topics, key points, and supplementary explanations for solving past problems. In particular, practice problems that take into account the trends in entrance exam questions are also incorporated into this plan.

[0405] The generated plan is presented to the educator on their device. The educator can review the presented plan and make modifications or additions as needed. The modified or added plan is sent back to the server and saved in the database. This information is then used as feedback to help generate future plans.

[0406] For example, when teaching quadratic equations in a math class, if the lesson progress information indicates that the teacher "explained the method of solving using factorization," the server will generate a "next lesson plan to deepen understanding of the completing the square method" based on that information. It can also create links to "maximum / minimum problems," which have frequently appeared in past entrance exams, and include specific practice problems in the plan.

[0407] In this way, the system of the present invention automatically aggregates the elements that educators should consider when preparing lessons, and supports effective lesson planning. As a result, educators can reduce the amount of time spent on rote instruction and concentrate on improving students' understanding.

[0408] The following describes the processing flow.

[0409] Step 1:

[0410] After class, users use a terminal to input class progress information. This information includes topics covered in the day's lesson, student comprehension levels, questions asked, and progress made. The terminal reviews the entered data and prepares it to be sent to the server in the appropriate format.

[0411] Step 2:

[0412] The server receives the data sent from the terminal. The server saves this lesson progress information to the database along with past information stored in the existing database. The saved data plays an important role in understanding the progress of lessons over time.

[0413] Step 3:

[0414] The server compares stored educational progress information with educational guidance standards and high school entrance exam question trends. Based on this comparison, the server utilizes machine learning models and other tools to analyze which areas should be prioritized in education.

[0415] Step 4:

[0416] The server automatically generates a lesson plan for the next class based on the analysis results. This generation process includes suggesting new learning topics, highlighting key points to be emphasized, and selecting practice problems that are particularly suited to entrance exam preparation. This plan helps educators prepare for lessons efficiently.

[0417] Step 5:

[0418] The generated lesson plan is sent to the device and presented to the user. The user can review the presented plan and make modifications or additions as needed. Modifications and additions are at the educator's discretion, based on the characteristics of the students and the progress of the class.

[0419] Step 6:

[0420] The lesson plan, modified by the user, is sent back to the server from the terminal. The server stores this modified information in a database and uses it as reference information for improvements in future lesson plan generation. In this way, the educational system continuously receives feedback and is continuously optimized.

[0421] (Example 1)

[0422] 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."

[0423] In modern education, efficiently preparing lessons and improving the quality of education are crucial challenges. However, especially in entrance exam preparation, educators must dedicate considerable time and effort to gathering information and planning lesson content. A system is needed to alleviate the burden of this process and provide effective educational plans tailored to the individual needs of each student.

[0424] 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.

[0425] In this invention, the server includes data storage means for receiving and storing educational progress information from educators, information analysis means for performing comparative analysis with exam question trend information based on the educational progress information, and plan generation means for generating the next educational plan using a generated AI model. This enables educators to quickly create effective and optimized educational plans and improve the quality of education.

[0426] "Educational progress information" refers to various data collected by educators after lessons, such as lesson content, lesson progress, student comprehension, and question-and-answer sessions.

[0427] A "data storage means" is a component within a system for receiving and appropriately storing educational progress information.

[0428] "Information analysis means" refers to devices or programs that perform cross-referencing and analysis of educational progress information stored in data storage means with educational guidance standards information and examination question trend information.

[0429] A "plan generation means" is a component that has the function of generating an educational plan for the next lesson using the results of an information analysis means.

[0430] A "generative AI model" refers to an algorithm or program that uses machine learning to generate educational plans based on a large amount of data.

[0431] "Communication means" refers to equipment and programs that have protocols and functions for transmitting information from terminals used by educators to a server.

[0432] An "information update mechanism" is a component that has the function of saving revised educational plans by educators back into the database and using them to generate future plans.

[0433] This invention is a system designed to support educators in efficiently preparing lessons and to improve the quality of education. This system automates the process of receiving and analyzing educational progress information to generate the next lesson plan. Details regarding the implementation of this system are provided below.

[0434] First, the educator, as the user, enters the lesson progress into a terminal after the lesson ends. This terminal is equipped with appropriate software to convert the information into a standardized format and securely transmit it to the server. The information includes the lesson topics, progress, student comprehension, and the content of the question and answer session.

[0435] Next, the server verifies the educational progress information received from the terminal and stores it in a database. This database has a structure that stores information in association with dates and class information, preparing it for future analysis.

[0436] The server uses a generative AI model to compare information stored in the database with educational guidance standards and exam question trends. This generative AI model employs machine learning techniques and incorporates algorithms to generate the most effective educational plans from the analysis results.

[0437] Once a lesson plan is generated, the server sends it to the terminal. The terminal presents the lesson plan to the educator in an easy-to-understand format, allowing the user to review and modify the content as needed. The modified information is sent back to the server and stored in the database, where it is used as feedback for future plan generation.

[0438] For example, if a teacher enters educational progress information indicating that they "explained the method of solving quadratic equations using factorization" during a math lesson, the server will generate a "next lesson plan to deepen understanding of the completing the square method" based on that information. It can also create links to "maximum / minimum problems" that frequently appeared in past exams, and include specific practice problems in the plan.

[0439] An example of a prompt message might be, "Send the lesson progress information on quadratic equations to the server and request the automatic generation of the next lesson plan." Through this prompt message, the system can efficiently formulate educational plans and support educators in preparing for lessons.

[0440] The flow of the specific processing in Example 1 will be explained using Figure 11.

[0441] Step 1:

[0442] The educator, as the user, enters teaching progress information into the terminal after each lesson. Specifically, they fill in a form with the lesson topic, progress, student understanding, and Q&A content. The entered data is converted into a standardized format to maintain consistency on the terminal and is ready to be sent to the server.

[0443] Step 2:

[0444] The terminal sends standardized educational progress information to the server. Secure communication protocols such as HTTPS are used to ensure the reliability and confidentiality of the data. Upon receiving the information, the server performs data verification to confirm that there are no problems with the content.

[0445] Step 3:

[0446] The server stores the received educational progress information in a database. The information is linked to dates and class information, and structured to allow for efficient retrieval in subsequent analysis. This prepares the system for subsequent analysis processes.

[0447] Step 4:

[0448] The server retrieves stored educational progress information and uses a generating AI model to compare it with educational guidance standards information and exam question trend information. The information analysis system then runs the AI ​​model, performing data processing and calculations to generate an optimal educational plan. As a result, it determines which topics should be strengthened and which issues should be focused on.

[0449] Step 5:

[0450] The server sends the generated lesson plan to the terminal. This plan includes suggestions for new topics, key points, and practice exercises related to those topics. The terminal then presents it to the educator in a visually easy-to-understand format.

[0451] Step 6:

[0452] The user, the educator, reviews the presented lesson plan and makes modifications or additions as needed. The educator can add or modify specific content on their device and then resend that information to the server.

[0453] Step 7:

[0454] The server receives correction information from educators and stores it in a database. This correction information is used as feedback for future plan generation and is utilized to improve the accuracy of the AI ​​model.

[0455] (Application Example 1)

[0456] 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."

[0457] Given that educators currently spend considerable time and effort preparing lessons and improving student comprehension, there is a need to efficiently create educational plans and provide effective teaching methods, particularly to support homework. Furthermore, the effort required to create learning plans tailored to each student's progress and level of understanding must be minimized. To address these challenges, it is crucial to effectively utilize information within the educational setting, reduce the burden on educators, and provide high-quality learning support.

[0458] 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.

[0459] In this invention, the server includes a storage means for receiving and storing educational progress information from educators; a processing means for analyzing the educational progress information stored in the storage means by comparing it with educational guidance standards information and test trend information; and a plan generation means for automatically generating the next educational plan based on the results of the processing means, including a plan to support home learning. This enables educators to efficiently create lesson plans and to provide effective guidance to support students' home learning.

[0460] "Educational progress information" refers to information entered by educators after each lesson, such as lesson content, progress, comprehension indicators, and Q&A.

[0461] A "memory device" refers to a database or storage device used to store received educational progress information.

[0462] "Processing means" refers to algorithms and programs for analyzing data by comparing educational progress information stored in memory means with educational guidance standards information and examination trend information.

[0463] The "plan generation means" is a mechanism that automatically generates the next lesson plan based on the analysis results from the processing means, and constructs a plan to support students' home education.

[0464] A "display device" is an interface or device that presents a generated educational plan and provides information to the user visually.

[0465] "Correction information" refers to information that educators have modified or added to the generated educational plan, and which is then stored again in memory.

[0466] A "machine learning model" is a form of artificial intelligence used to analyze educational progress information and propose the optimal learning plan.

[0467] A "generative AI model" is a model used as part of machine learning to propose new home learning plans and teaching methods based on educational data.

[0468] This invention is a system aimed at enabling educators to prepare lessons efficiently and supporting students' homework. Its main components are a server, a terminal used by educators, and a display device accessed by students.

[0469] The server receives educational progress information sent from educators and stores this information in a database such as MySQL or PostgreSQL. The stored information is processed using a Python script and analyzed by comparing it with educational guidance standards and entrance examination trend information. Based on the results of this analysis, a machine learning model generates an AI model to automatically generate the next lesson plan. The plan generation method can construct a concrete plan to support home study and suggest practice problems and review topics.

[0470] The terminal provides an interface for educators to input progress information and sends and receives information through communication with the server. The generated lesson plans are presented to educators through a user interface using React or Vue.js. If educators make revisions to the plan, this revision information is saved again to the database by the server and used for future plan generation.

[0471] As a concrete example, after checking students' understanding of quadratic equations in a math class, the educator inputs progress information via a device. Based on this information, an AI model generates practice problems, including links to problems on completing the square and finding maximum / minimum values, and provides them to students as part of their next homework plan.

[0472] An example of a prompt message is shown: "Enter the math topics you learned in today's lesson, and let the AI ​​generate your next homework plan. Please fill in the lesson content and your level of understanding."

[0473] The flow of a specific process in Application Example 1 will be explained using Figure 12.

[0474] Step 1:

[0475] The terminal provides an interface for educators to input progress information after class. Educators input information such as lesson content, progress, comprehension indicators, and questions and answers. The entered information is then prepared for transmission to the server.

[0476] Step 2:

[0477] The server receives educational progress information sent from the terminal. The received data is stored in a database such as MySQL or PostgreSQL. The input here is information from the educator, and the output is a notification that the data has been saved to the database.

[0478] Step 3:

[0479] The server retrieves educational progress information stored in the database and analyzes the data by comparing it with educational guidance standards and exam trend information using a Python script. The input is the stored progress information, and the output is the analysis results. Data mining techniques are used to extract information for designing the next steps based on the level of understanding.

[0480] Step 4:

[0481] The server uses a machine learning-based AI model generated from the analysis results to automatically generate the next lesson plan. The generated plan includes specific practice problems and review topics to support homework. The input is the analysis results, and the output is the generated lesson plan. Here, the model develops an effective learning plan based on educational data.

[0482] Step 5:

[0483] The generated lesson plans are displayed on the device through an interface built with React or Vue.js. Educators review the plans and make revisions as needed. The input is the generated lesson plan, and the output is the educator's feedback and revision information. The interface is user-friendly and incorporates educator feedback.

[0484] Step 6:

[0485] When a user makes a correction, that correction information is sent back to the server via the terminal and stored in the database. The input is the correction information from the educator, and the output is the updated database information. This allows for the accumulation of feedback necessary for future plan generation.

[0486] 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.

[0487] This invention is a system aimed at reducing the burden on educators in lesson preparation and improving the quality of education. By combining it with an emotion engine, it understands the emotions of educators and provides flexible educational plans that respond accordingly.

[0488] After class, users input their class progress information using a terminal. The terminal uses an emotion engine to recognize the user's emotional state, for example, determining whether they are stressed or relaxed. This information, along with the class progress data, is sent to the server.

[0489] The server stores the received educational progress information and emotional information in a database. Next, the server analyzes the progress information, taking the emotional information into consideration. The analysis method compares it with educational guidance standards information and entrance examination question trend information, and, taking the emotional information into account, selects the optimal educational guidance content.

[0490] Based on the analysis results, the server automatically generates the next lesson plan. The emotion engine can then include suggestions for making the lesson more flexible or adaptable if the user was experiencing stress. The generated plan may include points to focus on, as well as elements for relaxation and encouraging messages.

[0491] The generated educational plan is displayed on the device and presented to the user. The user can review the presented plan and make revisions if necessary. During the review process, the emotion engine also operates, reassessing the user's emotional state and prompting adjustments to the plan.

[0492] For example, in a math class, when dealing with "problem solving using factorization," if a user feels overwhelmed during the process, the server can generate a "plan that provides detailed explanations and step-by-step practice problems." It can also strengthen links to frequently appearing "problem formats" in entrance exams and suggest lesson plans that are easy to follow.

[0493] Thus, by taking into account the emotions of educators, the system of the present invention provides more personalized and effective support for lesson preparation, and creates an environment in which educators can concentrate on instructing students.

[0494] The following describes the processing flow.

[0495] Step 1:

[0496] After class ends, users use a terminal to input information about the day's class progress. The terminal activates an emotion engine during the input process, extracting emotional information from the user's facial expressions and tone of voice. This data includes topics covered in class, student reactions, and the user's stress level and motivation at that time.

[0497] Step 2:

[0498] The terminal sends collected progress data and emotional information to the server. The server stores the received information in a database, accumulating user emotional state data along with chronological progress records. This data will be used as foundational data for future lesson planning.

[0499] Step 3:

[0500] The server begins analysis based on educational progress information and sentiment information stored in the database. The analysis method uses machine learning algorithms to compare educational guidance standards information with entrance examination question trends information and derives an adaptive approach based on sentiment information. As a result, it identifies topics that need reinforcement and areas of instruction that need to be focused in the next lesson.

[0501] Step 4:

[0502] The server automatically generates the next lesson plan based on the analysis results. The plan generation method utilizes emotional information and flexibly adjusts the content, for example, by simplifying the content if the user is experiencing stress and incorporating positive feedback. This plan includes specific lesson objectives, necessary teaching materials, and practice problems that take entrance exam preparation into consideration.

[0503] Step 5:

[0504] The generated lesson plan is sent to the device and presented to the user. The user can review the plan and make adjustments or additions, taking into account their teaching style and the characteristics of their class. The emotion engine also operates during this process, and can suggest further adjustments based on the user's reactions.

[0505] Step 6:

[0506] The lesson plan, revised by the user, is sent back to the server via the terminal. The server saves the revised plan to its database and uses it as feedback. This feedback loop continuously improves the quality of future lesson plans.

[0507] Through this series of processes, the system of the present invention enables adaptive lesson preparation that takes into account the emotions of educators, and provides an environment in which they can concentrate on student guidance.

[0508] (Example 2)

[0509] 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."

[0510] Traditionally, educators have expended considerable effort preparing lessons, and it has been particularly difficult to create flexible plans based on progress information and students' emotions. Furthermore, emotional stress has negatively impacted the quality of education, and the one-sided nature of educational planning has been a cause for concern. This invention aims to solve these problems and improve the quality of education while reducing the burden on educators.

[0511] 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.

[0512] In this invention, the server includes data storage means for receiving and storing progress information from educators, analysis means for comparing and analyzing the progress information stored in the data storage means with educational standards information and evaluation trend information, and emotion analysis means for recognizing the emotional state of educators and adjusting the educational plan taking those emotions into consideration. This makes it possible to automatically generate flexible and effective educational plans that take into account not only progress information but also emotional information.

[0513] "Data storage means" refers to a method or system for accumulating and storing progress information and correction information received from educators.

[0514] "Analysis means" refers to a system or method for comparing stored progress information with educational standards information and evaluation trend information and performing analysis.

[0515] "Plan generation means" refers to a function or process that automatically generates the next educational plan based on the results obtained from the analysis means.

[0516] "Emotional analysis tools" refer to functions or methods for recognizing the emotional state of educators and adjusting educational plans while taking those emotions into consideration.

[0517] "Educational standards information" refers to a collection of information that includes standards and guidelines established regarding the instruction of educational content.

[0518] "Evaluation trend information" refers to information that shows trends and patterns related to educational evaluation, and serves as one reference material when creating educational plans.

[0519] "Progress information" refers to data that educators report after a lesson, indicating the progress and achievement level of the educational content.

[0520] This invention aims to build a system designed to improve the quality of education while reducing the burden on educators. Users input lesson progress information using a terminal after class. The terminal is equipped with emotion analysis software that highly analyzes the user's emotional state. This makes it possible to determine whether the user is relaxed or stressed.

[0521] Information collected by the terminal is transmitted to a server via the internet. The server stores emotional information along with progress information in a database, and then analysis software analyzes this information. Educational standards data and evaluation trend data are used in the analysis. This data is compared with past data using a generative AI model to obtain analysis results. Based on these results, the server has the ability to automatically generate the next educational plan.

[0522] The generated lesson plans include emphasis and methods for teaching content. Furthermore, they may incorporate relaxing elements and encouraging messages, flexibly adjusted based on the results of emotion analysis. This allows educators to conduct lessons that address the individual emotional needs of students.

[0523] For example, when a user is teaching "factorization" in a math class, if the sentiment analysis software detects the user's anxiety, the server generates a plan that includes detailed explanations and step-by-step practice problems. Furthermore, it strengthens the links to example problems that match the format of questions that appear on entrance exams, and proposes lesson plans that are easy for students to follow.

[0524] An example of a prompt message would be: "Please automatically generate the next lesson plan. The user is feeling anxious about preparing for the factorization lesson. Please suggest a flexible lesson plan that includes detailed explanations and step-by-step practice problems."

[0525] The flow of the specific processing in Example 2 will be explained using Figure 13.

[0526] Step 1:

[0527] After class, the user uses a terminal to input information about their class progress. This data includes information about the class content, understanding, and progress. The terminal then activates emotion analysis software, which analyzes the user's voice and facial expressions to recognize their emotional state. The output consists of progress information and emotion information.

[0528] Step 2:

[0529] The device sends collected progress and sentiment information to the server. The data is encrypted before transmission to ensure security. Once the transmitted data reaches the server, the server records it in its database.

[0530] Step 3:

[0531] The server inputs information stored in the database into analysis software and performs the analysis. This analysis compares and matches progress information with sentiment information, referencing educational standards data and evaluation trend data. The output provides the analysis results, which serve as the basis for future educational planning.

[0532] Step 4:

[0533] The server uses a generation AI model to automatically generate the next lesson plan based on the analysis results. The plan generation is tailored to include key educational content, teaching methods, and emotionally appropriate elements such as relaxation and encouragement. The output is provided as a complete lesson plan.

[0534] Step 5:

[0535] The terminal receives the educational plan sent from the server and displays it to the user. The user can review the presented plan and make modifications if necessary. During this time, sentiment analysis software runs, reassessing the user's emotional state. The review results are sent to the server and recorded as update information in the database.

[0536] (Application Example 2)

[0537] 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."

[0538] For educators, lesson preparation is stressful, and there is a need to reduce this burden while maintaining the quality of instruction. However, conventional systems only generate uniform plans without considering the emotional state of educators, and do not adequately provide flexible educational support tailored to individual circumstances. Therefore, there is a need for a means to generate personalized educational plans based on educators' emotional information.

[0539] 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.

[0540] In this invention, the server includes recording means for receiving and storing educational progress information and emotional information from educators; analysis means for comparing and analyzing the educational progress information and emotional information stored in the recording means with educational guidance standard information and evaluation standard information; and plan generation means for automatically generating the next educational plan based on the results of the analysis means, and generating a plan that includes flexible suggestions according to the emotional state. This makes it possible to create more personalized educational plans that take into account the emotional state of educators.

[0541] "Educational progress information" refers to information recorded by educators regarding the progress of lessons and learning activities, and is used to evaluate the quality and effectiveness of educational guidance.

[0542] "Emotional information" refers to information that represents the mental state of educators, and involves acquiring data on emotional states such as stress levels and relaxation levels.

[0543] "Recording means" refers to a device or software that has the function of receiving and storing educational progress information and emotional information.

[0544] "Analysis means" refers to a device or program that performs analysis based on information stored in a recording means, while comparing it with educational guidance standards information and evaluation standards information.

[0545] A "plan generation means" is a system or device that has the function of automatically generating the next educational plan based on the results of the analysis means.

[0546] "Educational guidance standards information" refers to information that outlines the basic guidance policies and content for educational activities, and is referenced when creating educational plans.

[0547] "Evaluation criteria information" refers to information that shows the standards used to evaluate the outcomes of education, and functions as an indicator for measuring the effectiveness of education.

[0548] This invention is a system designed to help educators prepare lessons efficiently. The system collects information on educational progress and student sentiment from educators and automatically generates the next lesson plan based on this information, thereby reducing the burden on educators.

[0549] The server receives educational progress and sentiment information transmitted from educators' terminals and stores them in a recording system. A cloud database (e.g., AWS RDS) is used as the recording system, enabling secure and efficient storage of the information.

[0550] The analysis method uses machine learning algorithms to perform detailed analysis based on stored information. Specifically, it uses Emotion AI (e.g., Affectiva SDK) to evaluate the emotional state of educators and compares it with educational guidance standards and evaluation standards. This analysis quantifies the stress levels and relaxation levels of educators and reflects them in educational plans.

[0551] The plan generation mechanism utilizes the results of the analysis mechanism to generate lesson plans that are tailored to the educator's emotional state. These plans include not only standard educational content, but also flexible lesson suggestions that respond to emotional changes, elements to promote relaxation, and encouraging messages. This enables educators to provide more individualized instruction to students.

[0552] As a concrete example, in a mathematics class, if emotional information indicates stress when an educator is working on "problem solving using factorization," the server generates a plan that provides detailed explanations and step-by-step practice problems. This plan is then presented to the educator on their device for review and modification.

[0553] An example of a prompt is: "Use the emotion engine to create suggestions that personalize math lesson plans and help educators prepare better lesson plans."

[0554] This allows educators to prepare lessons effectively while being aware of their own emotional state.

[0555] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[0556] Step 1:

[0557] The device receives educational progress information and emotional information from the user as input. Educational progress information includes the progress of the lesson content and the students' level of understanding, while emotional information is recognized and quantified using Emotion AI to determine the user's mental state. This input data is sent from the device to the server.

[0558] Step 2:

[0559] The server stores received educational progress and sentiment information in a recording medium. This recording medium is a cloud database (e.g., AWS RDS), enabling secure and efficient data storage. After verifying the integrity of the data, the server proceeds to the next analysis stage.

[0560] Step 3:

[0561] The server processes the stored information using analytical tools. Here, machine learning algorithms are used to analyze educational progress information and emotional information, comparing them with educational guidance standards and evaluation standards. The input is a set of stored data, and the output is the analysis result, which includes detailed emotional states of educators and detailed information on educational progress.

[0562] Step 4:

[0563] The server generates the next educational plan using a plan generation mechanism based on the analysis results. This step incorporates flexible and personalized suggestions tailored to the user's emotional state. Specifically, detailed explanations, step-by-step exercises, and elements to promote relaxation are added to the plan. The analysis results are used as input, and the generated educational plan is obtained as output.

[0564] Step 5:

[0565] The server sends the generated lesson plan to the terminal. The terminal displays the plan to the user, allowing them to review and modify its contents. The user can then review the plan and make any necessary changes, and these changes are sent back to the server.

[0566] Step 6:

[0567] The server receives the correction information from the user and saves it again in the recording system. This process allows for more accurate suggestions when generating plans in the future. The input is the correction information, and the output is an updated database entry.

[0568] 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.

[0569] 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.

[0570] 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.

[0571] [Fourth Embodiment]

[0572] Figure 7 shows an example of the configuration of the data processing system 410 according to the fourth embodiment.

[0573] 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.

[0574] 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).

[0575] 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.

[0576] 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.

[0577] 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).

[0578] 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.

[0579] 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.

[0580] 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.

[0581] 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.

[0582] 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.

[0583] 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.

[0584] 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".

[0585] This invention provides a system that enables educators to efficiently prepare for lessons and improve the quality of education. This system reduces the burden on educators and supports effective teaching by using a database that receives and stores educational progress information from educators.

[0586] First, educators input educational progress information using a terminal after each lesson. This information includes data such as lesson content, progress, comprehension indicators, and questions and answers. The terminal then sends this information to a server.

[0587] The server stores the received educational progress information in a database. The server then compares the information in the database with educational guidance standards and high school entrance exam question trends. This clarifies which areas need reinforcement and which types of questions should be prioritized in teaching.

[0588] Based on the analysis results, the server automatically generates an educational plan for the next lesson. This plan includes suggestions for new topics, key points, and supplementary explanations for solving past problems. In particular, practice problems that take into account the trends in entrance exam questions are also incorporated into this plan.

[0589] The generated plan is presented to the educator on their device. The educator can review the presented plan and make modifications or additions as needed. The modified or added plan is sent back to the server and saved in the database. This information is then used as feedback to help generate future plans.

[0590] For example, when teaching quadratic equations in a math class, if the lesson progress information indicates that the teacher "explained the method of solving using factorization," the server will generate a "next lesson plan to deepen understanding of the completing the square method" based on that information. It can also create links to "maximum / minimum problems," which have frequently appeared in past entrance exams, and include specific practice problems in the plan.

[0591] In this way, the system of the present invention automatically aggregates the elements that educators should consider when preparing lessons, and supports effective lesson planning. As a result, educators can reduce the amount of time spent on rote instruction and concentrate on improving students' understanding.

[0592] The following describes the processing flow.

[0593] Step 1:

[0594] After class, users use a terminal to input class progress information. This information includes topics covered in the day's lesson, student comprehension levels, questions asked, and progress made. The terminal reviews the entered data and prepares it to be sent to the server in the appropriate format.

[0595] Step 2:

[0596] The server receives the data sent from the terminal. The server saves this lesson progress information to the database along with past information stored in the existing database. The saved data plays an important role in understanding the progress of lessons over time.

[0597] Step 3:

[0598] The server compares stored educational progress information with educational guidance standards and high school entrance exam question trends. Based on this comparison, the server utilizes machine learning models and other tools to analyze which areas should be prioritized in education.

[0599] Step 4:

[0600] The server automatically generates a lesson plan for the next class based on the analysis results. This generation process includes suggesting new learning topics, highlighting key points to be emphasized, and selecting practice problems that are particularly suited to entrance exam preparation. This plan helps educators prepare for lessons efficiently.

[0601] Step 5:

[0602] The generated lesson plan is sent to the device and presented to the user. The user can review the presented plan and make modifications or additions as needed. Modifications and additions are at the educator's discretion, based on the characteristics of the students and the progress of the class.

[0603] Step 6:

[0604] The lesson plan, modified by the user, is sent back to the server from the terminal. The server stores this modified information in a database and uses it as reference information for improvements in future lesson plan generation. In this way, the educational system continuously receives feedback and is continuously optimized.

[0605] (Example 1)

[0606] 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".

[0607] In modern education, efficiently preparing lessons and improving the quality of education are crucial challenges. However, especially in entrance exam preparation, educators must dedicate considerable time and effort to gathering information and planning lesson content. A system is needed to alleviate the burden of this process and provide effective educational plans tailored to the individual needs of each student.

[0608] 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.

[0609] In this invention, the server includes data storage means for receiving and storing educational progress information from educators, information analysis means for performing comparative analysis with exam question trend information based on the educational progress information, and plan generation means for generating the next educational plan using a generated AI model. This enables educators to quickly create effective and optimized educational plans and improve the quality of education.

[0610] "Educational progress information" refers to various data collected by educators after lessons, such as lesson content, lesson progress, student comprehension, and question-and-answer sessions.

[0611] A "data storage means" is a component within a system for receiving and appropriately storing educational progress information.

[0612] "Information analysis means" refers to devices or programs that perform cross-referencing and analysis of educational progress information stored in data storage means with educational guidance standards information and examination question trend information.

[0613] A "plan generation means" is a component that has the function of generating an educational plan for the next lesson using the results of an information analysis means.

[0614] A "generative AI model" refers to an algorithm or program that uses machine learning to generate educational plans based on a large amount of data.

[0615] "Communication means" refers to equipment and programs that have protocols and functions for transmitting information from terminals used by educators to a server.

[0616] An "information update mechanism" is a component that has the function of saving revised educational plans by educators back into the database and using them to generate future plans.

[0617] This invention is a system designed to support educators in efficiently preparing lessons and to improve the quality of education. This system automates the process of receiving and analyzing educational progress information to generate the next lesson plan. Details regarding the implementation of this system are provided below.

[0618] First, the educator, as the user, enters the lesson progress into a terminal after the lesson ends. This terminal is equipped with appropriate software to convert the information into a standardized format and securely transmit it to the server. The information includes the lesson topics, progress, student comprehension, and the content of the question and answer session.

[0619] Next, the server verifies the educational progress information received from the terminal and stores it in a database. This database has a structure that stores information in association with dates and class information, preparing it for future analysis.

[0620] The server uses a generative AI model to compare information stored in the database with educational guidance standards and exam question trends. This generative AI model employs machine learning techniques and incorporates algorithms to generate the most effective educational plans from the analysis results.

[0621] Once a lesson plan is generated, the server sends it to the terminal. The terminal presents the lesson plan to the educator in an easy-to-understand format, allowing the user to review and modify the content as needed. The modified information is sent back to the server and stored in the database, where it is used as feedback for future plan generation.

[0622] For example, if a teacher enters educational progress information indicating that they "explained the method of solving quadratic equations using factorization" during a math lesson, the server will generate a "next lesson plan to deepen understanding of the completing the square method" based on that information. It can also create links to "maximum / minimum problems" that frequently appeared in past exams, and include specific practice problems in the plan.

[0623] An example of a prompt message might be, "Send the lesson progress information on quadratic equations to the server and request the automatic generation of the next lesson plan." Through this prompt message, the system can efficiently formulate educational plans and support educators in preparing for lessons.

[0624] The flow of the specific processing in Example 1 will be explained using Figure 11.

[0625] Step 1:

[0626] The educator, as the user, enters teaching progress information into the terminal after each lesson. Specifically, they fill in a form with the lesson topic, progress, student understanding, and Q&A content. The entered data is converted into a standardized format to maintain consistency on the terminal and is ready to be sent to the server.

[0627] Step 2:

[0628] The terminal sends standardized educational progress information to the server. Secure communication protocols such as HTTPS are used to ensure the reliability and confidentiality of the data. Upon receiving the information, the server performs data verification to confirm that there are no problems with the content.

[0629] Step 3:

[0630] The server stores the received educational progress information in a database. The information is linked to dates and class information, and structured to allow for efficient retrieval in subsequent analysis. This prepares the system for subsequent analysis processes.

[0631] Step 4:

[0632] The server retrieves stored educational progress information and uses a generating AI model to compare it with educational guidance standards information and exam question trend information. The information analysis system then runs the AI ​​model, performing data processing and calculations to generate an optimal educational plan. As a result, it determines which topics should be strengthened and which issues should be focused on.

[0633] Step 5:

[0634] The server sends the generated lesson plan to the terminal. This plan includes suggestions for new topics, key points, and practice exercises related to those topics. The terminal then presents it to the educator in a visually easy-to-understand format.

[0635] Step 6:

[0636] The user, the educator, reviews the presented lesson plan and makes modifications or additions as needed. The educator can add or modify specific content on their device and then resend that information to the server.

[0637] Step 7:

[0638] The server receives correction information from educators and stores it in a database. This correction information is used as feedback for future plan generation and is utilized to improve the accuracy of the AI ​​model.

[0639] (Application Example 1)

[0640] 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".

[0641] Given that educators currently spend considerable time and effort preparing lessons and improving student comprehension, there is a need to efficiently create educational plans and provide effective teaching methods, particularly to support homework. Furthermore, the effort required to create learning plans tailored to each student's progress and level of understanding must be minimized. To address these challenges, it is crucial to effectively utilize information within the educational setting, reduce the burden on educators, and provide high-quality learning support.

[0642] 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.

[0643] In this invention, the server includes a storage means for receiving and storing educational progress information from educators; a processing means for analyzing the educational progress information stored in the storage means by comparing it with educational guidance standards information and test trend information; and a plan generation means for automatically generating the next educational plan based on the results of the processing means, including a plan to support home learning. This enables educators to efficiently create lesson plans and to provide effective guidance to support students' home learning.

[0644] "Educational progress information" refers to information entered by educators after each lesson, such as lesson content, progress, comprehension indicators, and Q&A.

[0645] A "memory device" refers to a database or storage device used to store received educational progress information.

[0646] "Processing means" refers to algorithms and programs for analyzing data by comparing educational progress information stored in memory means with educational guidance standards information and examination trend information.

[0647] The "plan generation means" is a mechanism that automatically generates the next lesson plan based on the analysis results from the processing means, and constructs a plan to support students' home education.

[0648] A "display device" is an interface or device that presents a generated educational plan and provides information to the user visually.

[0649] "Correction information" refers to information that educators have modified or added to the generated educational plan, and which is then stored again in memory.

[0650] A "machine learning model" is a form of artificial intelligence used to analyze educational progress information and propose the optimal learning plan.

[0651] A "generative AI model" is a model used as part of machine learning to propose new home learning plans and teaching methods based on educational data.

[0652] This invention is a system aimed at enabling educators to prepare lessons efficiently and supporting students' homework. Its main components are a server, a terminal used by educators, and a display device accessed by students.

[0653] The server receives educational progress information sent from educators and stores this information in a database such as MySQL or PostgreSQL. The stored information is processed using a Python script and analyzed by comparing it with educational guidance standards and entrance examination trend information. Based on the results of this analysis, a machine learning model generates an AI model to automatically generate the next lesson plan. The plan generation method can construct a concrete plan to support home study and suggest practice problems and review topics.

[0654] The terminal provides an interface for educators to input progress information and sends and receives information through communication with the server. The generated lesson plans are presented to educators through a user interface using React or Vue.js. If educators make revisions to the plan, this revision information is saved again to the database by the server and used for future plan generation.

[0655] As a concrete example, after checking students' understanding of quadratic equations in a math class, the educator inputs progress information via a device. Based on this information, an AI model generates practice problems, including links to problems on completing the square and finding maximum / minimum values, and provides them to students as part of their next homework plan.

[0656] An example of a prompt message is shown: "Enter the math topics you learned in today's lesson, and let the AI ​​generate your next homework plan. Please fill in the lesson content and your level of understanding."

[0657] The flow of a specific process in Application Example 1 will be explained using Figure 12.

[0658] Step 1:

[0659] The terminal provides an interface for educators to input progress information after class. Educators input information such as lesson content, progress, comprehension indicators, and questions and answers. The entered information is then prepared for transmission to the server.

[0660] Step 2:

[0661] The server receives educational progress information sent from the terminal. The received data is stored in a database such as MySQL or PostgreSQL. The input here is information from the educator, and the output is a notification that the data has been saved to the database.

[0662] Step 3:

[0663] The server retrieves educational progress information stored in the database and analyzes the data by comparing it with educational guidance standards and exam trend information using a Python script. The input is the stored progress information, and the output is the analysis results. Data mining techniques are used to extract information for designing the next steps based on the level of understanding.

[0664] Step 4:

[0665] The server uses a machine learning-based AI model generated from the analysis results to automatically generate the next lesson plan. The generated plan includes specific practice problems and review topics to support homework. The input is the analysis results, and the output is the generated lesson plan. Here, the model develops an effective learning plan based on educational data.

[0666] Step 5:

[0667] The generated lesson plans are displayed on the device through an interface built with React or Vue.js. Educators review the plans and make revisions as needed. The input is the generated lesson plan, and the output is the educator's feedback and revision information. The interface is user-friendly and incorporates educator feedback.

[0668] Step 6:

[0669] When a user makes a correction, that correction information is sent back to the server via the terminal and stored in the database. The input is the correction information from the educator, and the output is the updated database information. This allows for the accumulation of feedback necessary for future plan generation.

[0670] 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.

[0671] This invention is a system aimed at reducing the burden on educators in lesson preparation and improving the quality of education. By combining it with an emotion engine, it understands the emotions of educators and provides flexible educational plans that respond accordingly.

[0672] After class, users input their class progress information using a terminal. The terminal uses an emotion engine to recognize the user's emotional state, for example, determining whether they are stressed or relaxed. This information, along with the class progress data, is sent to the server.

[0673] The server stores the received educational progress information and emotional information in a database. Next, the server analyzes the progress information, taking the emotional information into consideration. The analysis method compares it with educational guidance standards information and entrance examination question trend information, and, taking the emotional information into account, selects the optimal educational guidance content.

[0674] Based on the analysis results, the server automatically generates the next lesson plan. The emotion engine can then include suggestions for making the lesson more flexible or adaptable if the user was experiencing stress. The generated plan may include points to focus on, as well as elements for relaxation and encouraging messages.

[0675] The generated educational plan is displayed on the device and presented to the user. The user can review the presented plan and make revisions if necessary. During the review process, the emotion engine also operates, reassessing the user's emotional state and prompting adjustments to the plan.

[0676] For example, in a math class, when dealing with "problem solving using factorization," if a user feels overwhelmed during the process, the server can generate a "plan that provides detailed explanations and step-by-step practice problems." It can also strengthen links to frequently appearing "problem formats" in entrance exams and suggest lesson plans that are easy to follow.

[0677] Thus, by taking into account the emotions of educators, the system of the present invention provides more personalized and effective support for lesson preparation, and creates an environment in which educators can concentrate on instructing students.

[0678] The following describes the processing flow.

[0679] Step 1:

[0680] After class ends, users use a terminal to input information about the day's class progress. The terminal activates an emotion engine during the input process, extracting emotional information from the user's facial expressions and tone of voice. This data includes topics covered in class, student reactions, and the user's stress level and motivation at that time.

[0681] Step 2:

[0682] The terminal sends collected progress data and emotional information to the server. The server stores the received information in a database, accumulating user emotional state data along with chronological progress records. This data will be used as foundational data for future lesson planning.

[0683] Step 3:

[0684] The server begins analysis based on educational progress information and sentiment information stored in the database. The analysis method uses machine learning algorithms to compare educational guidance standards information with entrance examination question trends information and derives an adaptive approach based on sentiment information. As a result, it identifies topics that need reinforcement and areas of instruction that need to be focused in the next lesson.

[0685] Step 4:

[0686] The server automatically generates the next lesson plan based on the analysis results. The plan generation method utilizes emotional information and flexibly adjusts the content, for example, by simplifying the content if the user is experiencing stress and incorporating positive feedback. This plan includes specific lesson objectives, necessary teaching materials, and practice problems that take entrance exam preparation into consideration.

[0687] Step 5:

[0688] The generated lesson plan is sent to the device and presented to the user. The user can review the plan and make adjustments or additions, taking into account their teaching style and the characteristics of their class. The emotion engine also operates during this process, and can suggest further adjustments based on the user's reactions.

[0689] Step 6:

[0690] The lesson plan, revised by the user, is sent back to the server via the terminal. The server saves the revised plan to its database and uses it as feedback. This feedback loop continuously improves the quality of future lesson plans.

[0691] Through this series of processes, the system of the present invention enables adaptive lesson preparation that takes into account the emotions of educators, and provides an environment in which they can concentrate on student guidance.

[0692] (Example 2)

[0693] 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".

[0694] Traditionally, educators have expended considerable effort preparing lessons, and it has been particularly difficult to create flexible plans based on progress information and students' emotions. Furthermore, emotional stress has negatively impacted the quality of education, and the one-sided nature of educational planning has been a cause for concern. This invention aims to solve these problems and improve the quality of education while reducing the burden on educators.

[0695] 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.

[0696] In this invention, the server includes data storage means for receiving and storing progress information from educators, analysis means for comparing and analyzing the progress information stored in the data storage means with educational standards information and evaluation trend information, and emotion analysis means for recognizing the emotional state of educators and adjusting the educational plan taking those emotions into consideration. This makes it possible to automatically generate flexible and effective educational plans that take into account not only progress information but also emotional information.

[0697] "Data storage means" refers to a method or system for accumulating and storing progress information and correction information received from educators.

[0698] "Analysis means" refers to a system or method for comparing stored progress information with educational standards information and evaluation trend information and performing analysis.

[0699] "Plan generation means" refers to a function or process that automatically generates the next educational plan based on the results obtained from the analysis means.

[0700] "Emotional analysis tools" refer to functions or methods for recognizing the emotional state of educators and adjusting educational plans while taking those emotions into consideration.

[0701] "Educational standards information" refers to a collection of information that includes standards and guidelines established regarding the instruction of educational content.

[0702] "Evaluation trend information" refers to information that shows trends and patterns related to educational evaluation, and serves as one reference material when creating educational plans.

[0703] "Progress information" refers to data that educators report after a lesson, indicating the progress and achievement level of the educational content.

[0704] This invention aims to build a system designed to improve the quality of education while reducing the burden on educators. Users input lesson progress information using a terminal after class. The terminal is equipped with emotion analysis software that highly analyzes the user's emotional state. This makes it possible to determine whether the user is relaxed or stressed.

[0705] Information collected by the terminal is transmitted to a server via the internet. The server stores emotional information along with progress information in a database, and then analysis software analyzes this information. Educational standards data and evaluation trend data are used in the analysis. This data is compared with past data using a generative AI model to obtain analysis results. Based on these results, the server has the ability to automatically generate the next educational plan.

[0706] The generated lesson plans include emphasis and methods for teaching content. Furthermore, they may incorporate relaxing elements and encouraging messages, flexibly adjusted based on the results of emotion analysis. This allows educators to conduct lessons that address the individual emotional needs of students.

[0707] For example, when a user is teaching "factorization" in a math class, if the sentiment analysis software detects the user's anxiety, the server generates a plan that includes detailed explanations and step-by-step practice problems. Furthermore, it strengthens the links to example problems that match the format of questions that appear on entrance exams, and proposes lesson plans that are easy for students to follow.

[0708] An example of a prompt message would be: "Please automatically generate the next lesson plan. The user is feeling anxious about preparing for the factorization lesson. Please suggest a flexible lesson plan that includes detailed explanations and step-by-step practice problems."

[0709] The flow of the specific processing in Example 2 will be explained using Figure 13.

[0710] Step 1:

[0711] After class, the user uses a terminal to input information about their class progress. This data includes information about the class content, understanding, and progress. The terminal then activates emotion analysis software, which analyzes the user's voice and facial expressions to recognize their emotional state. The output consists of progress information and emotion information.

[0712] Step 2:

[0713] The device sends collected progress and sentiment information to the server. The data is encrypted before transmission to ensure security. Once the transmitted data reaches the server, the server records it in its database.

[0714] Step 3:

[0715] The server inputs information stored in the database into analysis software and performs the analysis. This analysis compares and matches progress information with sentiment information, referencing educational standards data and evaluation trend data. The output provides the analysis results, which serve as the basis for future educational planning.

[0716] Step 4:

[0717] The server uses a generation AI model to automatically generate the next lesson plan based on the analysis results. The plan generation is tailored to include key educational content, teaching methods, and emotionally appropriate elements such as relaxation and encouragement. The output is provided as a complete lesson plan.

[0718] Step 5:

[0719] The terminal receives the educational plan sent from the server and displays it to the user. The user can review the presented plan and make modifications if necessary. During this time, sentiment analysis software runs, reassessing the user's emotional state. The review results are sent to the server and recorded as update information in the database.

[0720] (Application Example 2)

[0721] 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".

[0722] For educators, lesson preparation is stressful, and there is a need to reduce this burden while maintaining the quality of instruction. However, conventional systems only generate uniform plans without considering the emotional state of educators, and do not adequately provide flexible educational support tailored to individual circumstances. Therefore, there is a need for a means to generate personalized educational plans based on educators' emotional information.

[0723] 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.

[0724] In this invention, the server includes recording means for receiving and storing educational progress information and emotional information from educators; analysis means for comparing and analyzing the educational progress information and emotional information stored in the recording means with educational guidance standard information and evaluation standard information; and plan generation means for automatically generating the next educational plan based on the results of the analysis means, and generating a plan that includes flexible suggestions according to the emotional state. This makes it possible to create more personalized educational plans that take into account the emotional state of educators.

[0725] "Educational progress information" refers to information recorded by educators regarding the progress of lessons and learning activities, and is used to evaluate the quality and effectiveness of educational guidance.

[0726] "Emotional information" refers to information that represents the mental state of educators, and involves acquiring data on emotional states such as stress levels and relaxation levels.

[0727] "Recording means" refers to a device or software that has the function of receiving and storing educational progress information and emotional information.

[0728] "Analysis means" refers to a device or program that performs analysis based on information stored in a recording means, while comparing it with educational guidance standards information and evaluation standards information.

[0729] A "plan generation means" is a system or device that has the function of automatically generating the next educational plan based on the results of the analysis means.

[0730] "Educational guidance standards information" refers to information that outlines the basic guidance policies and content for educational activities, and is referenced when creating educational plans.

[0731] "Evaluation criteria information" refers to information that shows the standards used to evaluate the outcomes of education, and functions as an indicator for measuring the effectiveness of education.

[0732] This invention is a system designed to help educators prepare lessons efficiently. The system collects information on educational progress and student sentiment from educators and automatically generates the next lesson plan based on this information, thereby reducing the burden on educators.

[0733] The server receives educational progress and sentiment information transmitted from educators' terminals and stores them in a recording system. A cloud database (e.g., AWS RDS) is used as the recording system, enabling secure and efficient storage of the information.

[0734] The analysis method uses machine learning algorithms to perform detailed analysis based on stored information. Specifically, it uses Emotion AI (e.g., Affectiva SDK) to evaluate the emotional state of educators and compares it with educational guidance standards and evaluation standards. This analysis quantifies the stress levels and relaxation levels of educators and reflects them in educational plans.

[0735] The plan generation mechanism utilizes the results of the analysis mechanism to generate lesson plans that are tailored to the educator's emotional state. These plans include not only standard educational content, but also flexible lesson suggestions that respond to emotional changes, elements to promote relaxation, and encouraging messages. This enables educators to provide more individualized instruction to students.

[0736] As a concrete example, in a mathematics class, if emotional information indicates stress when an educator is working on "problem solving using factorization," the server generates a plan that provides detailed explanations and step-by-step practice problems. This plan is then presented to the educator on their device for review and modification.

[0737] An example of a prompt is: "Use the emotion engine to create suggestions that personalize math lesson plans and help educators prepare better lesson plans."

[0738] This allows educators to prepare lessons effectively while being aware of their own emotional state.

[0739] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[0740] Step 1:

[0741] The device receives educational progress information and emotional information from the user as input. Educational progress information includes the progress of the lesson content and the students' level of understanding, while emotional information is recognized and quantified using Emotion AI to determine the user's mental state. This input data is sent from the device to the server.

[0742] Step 2:

[0743] The server stores received educational progress and sentiment information in a recording medium. This recording medium is a cloud database (e.g., AWS RDS), enabling secure and efficient data storage. After verifying the integrity of the data, the server proceeds to the next analysis stage.

[0744] Step 3:

[0745] The server processes the stored information using analytical tools. Here, machine learning algorithms are used to analyze educational progress information and emotional information, comparing them with educational guidance standards and evaluation standards. The input is a set of stored data, and the output is the analysis result, which includes detailed emotional states of educators and detailed information on educational progress.

[0746] Step 4:

[0747] The server generates the next educational plan using a plan generation mechanism based on the analysis results. This step incorporates flexible and personalized suggestions tailored to the user's emotional state. Specifically, detailed explanations, step-by-step exercises, and elements to promote relaxation are added to the plan. The analysis results are used as input, and the generated educational plan is obtained as output.

[0748] Step 5:

[0749] The server sends the generated lesson plan to the terminal. The terminal displays the plan to the user, allowing them to review and modify its contents. The user can then review the plan and make any necessary changes, and these changes are sent back to the server.

[0750] Step 6:

[0751] The server receives the correction information from the user and saves it again in the recording system. This process allows for more accurate suggestions when generating plans in the future. The input is the correction information, and the output is an updated database entry.

[0752] 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.

[0753] 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.

[0754] 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.

[0755] 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.

[0756] 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.

[0757] 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.

[0758] 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.

[0759] 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.

[0760] 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."

[0761] 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.

[0762] 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.

[0763] 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.

[0764] 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.

[0765] 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.

[0766] 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.

[0767] 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.

[0768] 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.

[0769] 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.

[0770] 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.

[0771] 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.

[0772] 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.

[0773] The following is further disclosed regarding the embodiments described above.

[0774] (Claim 1)

[0775] A database means for receiving and storing educational progress information from educators,

[0776] An analysis means that performs analysis by comparing educational progress information stored in the aforementioned database means with educational guidance standards information and entrance examination question trend information,

[0777] A plan generation means that automatically generates the next educational plan based on the results of the analysis means,

[0778] A means for presenting the generated educational plan to the educator, and if revisions are made, for saving the revised information back to the database means,

[0779] A system that includes this.

[0780] (Claim 2)

[0781] The system according to claim 1, wherein the plan generation means generates an educational plan that includes questions corresponding to the trends in high school entrance examinations, based on the results of the analysis means.

[0782] (Claim 3)

[0783] The system according to claim 1, wherein the analysis means analyzes educational progress information using a machine learning model.

[0784] "Example 1"

[0785] (Claim 1)

[0786] A data storage means for receiving and storing educational progress information from educators,

[0787] An information analysis means that performs analysis by comparing educational progress information stored in the aforementioned data storage means with educational guidance standards information and examination question trend information,

[0788] A plan generation means that uses a generation AI model to automatically generate the next educational plan based on the results of the information analysis means,

[0789] Information update means that presents the generated educational plan to the educator and, if revisions are made, saves the revised information back to the data storage means.

[0790] A communication method in which an educator inputs information from a terminal and the terminal sends that information to a server,

[0791] A system that includes this.

[0792] (Claim 2)

[0793] The system according to claim 1, wherein the plan generation means generates an educational plan including practice problems that correspond to the trends in entrance examination questions, based on the results of the information analysis means.

[0794] (Claim 3)

[0795] The system according to claim 1, wherein the information analysis means analyzes educational progress information using a generated AI model.

[0796] "Application Example 1"

[0797] (Claim 1)

[0798] A storage means for receiving and storing educational progress information from educators,

[0799] A processing means that performs analysis by comparing educational progress information stored in the aforementioned storage means with educational guidance standards information and examination trend information,

[0800] A plan generation means that automatically generates the next educational plan based on the results of the processing means, and includes a plan to support home education,

[0801] The generated educational plan is displayed on a presentation device, and if any modifications are made, the modified information is saved again to the storage means.

[0802] A system that includes this.

[0803] (Claim 2)

[0804] The system according to claim 1, wherein the plan generation means generates an educational plan including practice problems and schedules to support learners' home study, based on the results of the processing means.

[0805] (Claim 3)

[0806] The system according to claim 1, wherein the processing means analyzes educational progress information using a machine learning model and proposes a home learning plan using a generative AI model.

[0807] "Example 2 of combining an emotion engine"

[0808] (Claim 1)

[0809] A data storage means for receiving progress information from educators and storing such information,

[0810] An analysis means that performs analysis by comparing progress information stored in the aforementioned data storage means with educational standards information and evaluation trend information,

[0811] A plan generation means that automatically generates the next educational plan based on the results of the analysis means,

[0812] A means for presenting the generated educational plan to educators and, if revisions are made, for storing the revised information again in the data storage means,

[0813] An emotion analysis tool that recognizes the emotional state of educators and adjusts educational plans considering those emotions,

[0814] A system that includes this.

[0815] (Claim 2)

[0816] The system according to claim 1, wherein the plan generation means generates an educational plan that includes tasks corresponding to the evaluation trends of higher education based on the results of the analysis means, and further incorporates information from the emotion analysis means to make the lesson content more flexible.

[0817] (Claim 3)

[0818] The system according to claim 1, wherein the analysis means and the emotion analysis means analyze progress information and emotion information using machine learning.

[0819] "Application example 2 when combining with an emotional engine"

[0820] (Claim 1)

[0821] A recording means for receiving and storing educational progress information and emotional information from educators,

[0822] An analysis means that performs analysis by comparing educational progress information and emotional information stored in the recording means with educational guidance standards information and evaluation standards information,

[0823] A plan generation means that automatically generates the next educational plan based on the results of the analysis means, and generates a plan that includes flexible suggestions according to the emotional state,

[0824] A means for presenting the generated educational plan, and if the educator makes modifications based on emotional information, for saving the modified information back to the recording means,

[0825] A system that includes this.

[0826] (Claim 2)

[0827] The system according to claim 1, wherein the plan generation means generates an educational plan that includes relaxation elements and encouraging messages corresponding to the emotional state, based on the results of the analysis means.

[0828] (Claim 3)

[0829] The system according to claim 1, wherein the analysis means analyzes educational progress information and sentiment information using a machine learning algorithm. [Explanation of symbols]

[0830] 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. A database means for receiving and storing educational progress information from educators, An analysis means that performs analysis by comparing educational progress information stored in the aforementioned database means with educational guidance standards information and entrance examination question trend information, A plan generation means that automatically generates the next educational plan based on the results of the analysis means, A means for presenting the generated educational plan to the educator, and if revisions are made, for saving the revised information back to the database means, A system that includes this.

2. The system according to claim 1, wherein the plan generation means generates an educational plan that includes questions corresponding to the trends in high school entrance examinations, based on the results of the analysis means.

3. The system according to claim 1, wherein the analysis means analyzes educational progress information using a machine learning model.

Images