system

Abstract

We provide a system that improves efficiency and digitalizes the entire educational environment. [Solution] A system including: a means for storing learning data collected from elementary schools across the country in a database; a means for analyzing the learning data stored in the database; a means for generating learning content appropriate for each student based on the analysis results; a means for distributing the generated learning content to each student's terminal; a means for generating questions to test each student's level of comprehension; a means for distributing the generated comprehension test questions to the terminal and collecting students' answer data; a means for re-analyzing students' learning status based on the collected answer data; a means for generating an optimal timetable based on classroom usage, teaching staff schedules, and student grades and progress data; and a means for distributing the generated timetable to teaching staff and student terminals.

Description

[Technical Field]

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

[0002] Patent document 1 discloses a persona chatbot control method performed by at least one processor, the method including the steps of receiving a user utterance, adding the user utterance to a prompt including an instruction sentence related to a description of the chatbot character, encoding the prompt, and inputting the encoded prompt into a language model to generate a chatbot utterance in response to the user utterance. [Prior art documents] [Patent documents]

[0003] [Patent Document 1] Japanese Patent Publication No. 2022-180282 Summary of the Invention [Problem to be solved by the invention]

[0004] In the traditional education system, it is difficult to provide instruction tailored to each student's learning situation and progress, and they are forced to rely on a uniform curriculum, which results in a decrease in learning efficiency. Furthermore, the workload for teachers and staff is heavy, and creating timetables and understanding students' levels of understanding requires a great deal of effort, so there is a need to improve the efficiency of the entire educational environment. Furthermore, this traditional educational environment is not sufficiently digitalized, making it difficult to flexibly adapt to changes in the times. [Means for solving the problem]

[0005] The present invention provides a system that includes a means for storing learning data collected from elementary schools across the country in a database and analyzing the stored learning data; a means for generating learning content appropriate for each student based on the analysis results and a means for distributing the generated learning content to each student's device; a means for generating questions to test each student's level of comprehension; a means for distributing the generated comprehension test questions to the device and collecting student answer data; a means for re-analyzing students' learning status based on the collected answer data; a means for generating an optimal timetable based on classroom usage, faculty schedules, and student grades and progress data; and a means for distributing the generated timetable to faculty and student devices, thereby solving the above-mentioned problems and realizing a more efficient and digitalized educational environment overall.

[0006] "Learning data" refers to various data related to learning, such as student grades, learning progress, and comprehension test results.

[0007] A "database" refers to a collection of collected learning data that is stored in an organized manner and can be searched and analyzed as needed.

[0008] "Analysis means" refers to algorithms and software used to analyze collected learning data and understand each student's learning situation and level of understanding.

[0009] "Learning content" refers to educational materials and teaching materials tailored to each student's learning situation, including videos, textbooks, and workbooks.

[0010] "Device" refers to a computing device such as a tablet or PC used by students and faculty.

[0011] "Comprehension test" refers to test questions used to assess a student's learning comprehension, which are designed to address weaknesses in the student.

[0012] "Answer data" refers to the results of students' answers to comprehension test questions, including the content of their answers and the time it took to answer them.

[0013] A "timetable" refers to a list showing class times, classroom usage schedules, and the schedules of students and faculty.

[0014] "Delivery means" refers to the software and network functions used to send the generated learning content, comprehension tests, and timetables to each device.

[0015] "Machine learning algorithm" refers to an artificial intelligence technology that automatically learns from collected data and performs data analysis and predictions. [Brief explanation of the drawings]

[0016] [Figure 1] 1 is a conceptual diagram showing an example of the configuration of a data processing system according to a first embodiment. [Figure 2] 1 is a conceptual diagram showing an example of main functions of a data processing device and a smart device according to a first embodiment. [Figure 3] FIG. 10 is a conceptual diagram showing an example of the configuration of a data processing system according to a second embodiment. [Figure 4] FIG. 10 is a conceptual diagram showing an example of main functions of a data processing device and smart glasses according to a second embodiment. [Figure 5] FIG. 10 is a conceptual diagram showing an example of the configuration of a data processing system according to a third embodiment. [Figure 6] FIG. 11 is a conceptual diagram showing an example of main functions of a data processing device and a headset-type terminal according to a third embodiment. [Figure 7] FIG. 10 is a conceptual diagram showing an example of the configuration of a data processing system according to a fourth embodiment. [Figure 8] FIG. 10 is a conceptual diagram showing an example of main functions of a data processing device and a robot according to a fourth embodiment. [Figure 9] 1 shows an emotion map onto which multiple emotions are mapped. [Figure 10]1 shows an emotion map onto which multiple emotions are mapped. [Figure 11] FIG. 3 is a sequence diagram showing a processing flow of the data processing system according to the first embodiment. [Figure 12] FIG. 10 is a sequence diagram showing the flow of processing in the data processing system in Application Example 1. [Figure 13] FIG. 10 is a sequence diagram showing the flow of processing in the data processing system according to the second embodiment when an emotion engine is combined. [Figure 14] FIG. 10 is a sequence diagram showing the flow of processing in the data processing system in Application Example 2 when an emotion engine is combined. DETAILED DESCRIPTION OF THE INVENTION

[0017] An example of an embodiment of a system according to the technology of the present disclosure will be described below with reference to the accompanying drawings.

[0018] First, the terms used in the following description will be explained.

[0019] In the following embodiments, a coded processor (hereinafter simply referred to as a "processor") may be a single arithmetic device or a combination of multiple arithmetic devices. Furthermore, a processor may be a single type of arithmetic device or a combination of multiple types of arithmetic devices. Examples of arithmetic devices include a CPU (Central Processing Unit), a GPU (Graphics Processing Unit), a GPGPU (General-Purpose computing on Graphics Processing Units), and an APU (Accelerated Processing Unit).

[0020] In the following embodiments, a coded RAM (Random Access Memory) is a memory in which information is temporarily stored and is used as a working memory by a processor.

[0021] In the following embodiments, the coded storage is one or more non-volatile storage devices that store various programs, various parameters, etc. Examples of non-volatile storage devices include flash memory (SSD (Solid State Drive)), magnetic disks (e.g., hard disks), and magnetic tapes.

[0022] In the following embodiments, a communication I / F (Interface) with a symbol is an interface including a communication processor, an antenna, etc. The communication I / F controls communication between multiple computers. Examples of communication standards applied to the communication I / F include wireless communication standards including 5G (5th Generation Mobile Communication System), Wi-Fi (registered trademark), Bluetooth (registered trademark), etc.

[0023] In the following embodiments, "A and / or B" is synonymous with "at least one of A and B." In other words, "A and / or B" means that it may be only A, only B, or a combination of A and B. Furthermore, in this specification, the same concept as "A and / or B" is also applied when three or more things are expressed connected by "and / or."

[0024] [First embodiment]

[0025] FIG. 1 shows an example of the configuration of a data processing system 10 according to the first embodiment.

[0026] 1, a data processing system 10 includes a data processing device 12 and a smart device 14. An example of the data processing device 12 is a server.

[0027] The data processing device 12 includes a computer 22, a database 24, and a communication I / F 26. The computer 22 is an example of a "computer" according to the technology of the present disclosure. The computer 22 includes a processor 28, a RAM 30, and a storage 32. The processor 28, the RAM 30, and the storage 32 are connected to a bus 34. The database 24 and the communication I / F 26 are also connected to the bus 34. The communication I / F 26 is connected to a network 54. Examples of the network 54 include a WAN (Wide Area Network) and / or a LAN (Local Area Network).

[0028] The smart device 14 includes a computer 36, a reception device 38, an output device 40, a camera 42, and a communication I / F 44. The computer 36 includes a processor 46, a RAM 48, and a storage 50. The processor 46, the RAM 48, and the storage 50 are connected to a bus 52. The reception device 38, the output device 40, and the camera 42 are also connected to the bus 52.

[0029] The reception device 38 includes a touch panel 38A, a microphone 38B, and the like, and receives user input. The touch panel 38A detects contact with an indicator (for example, a pen or a finger) to receive user input by the touch of the indicator. The microphone 38B detects the user's voice to receive user input by voice. The control unit 46A transmits data indicating the user input received by the touch panel 38A and the microphone 38B to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the data indicating the user input.

[0030] 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 of expression that the user 20 can perceive (for example, audio and / or text). The display 40A displays visible information such as text and images in accordance with instructions from the processor 46. The speaker 40B outputs audio in accordance with instructions from the processor 46. The camera 42 is a compact digital camera equipped with an optical system including a lens, aperture, and shutter, and an imaging element such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor.

[0031] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 control the exchange of various information between the processor 46 and the processor 28 via the network 54.

[0032] FIG. 2 shows an example of the main functions of the data processing device 12 and the smart device 14.

[0033] 2, in the data processing device 12, a specific process is performed by the processor 28. A specific processing program 56 is stored in the storage 32. The specific processing program 56 is an example of a "program" according to the technology of the present disclosure. The processor 28 reads the specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific process is realized by the processor 28 operating as a specific processing unit 290 in accordance with the specific processing program 56 executed on the RAM 30.

[0034] The storage 32 stores a data generation model 58 and an emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290.

[0035] In the smart device 14, the processor 46 performs the reception output process. The storage 50 stores a reception output program 60. The reception output program 60 is used in conjunction with the 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 process is realized by the processor 46 operating as the control unit 46A in accordance with the reception output program 60 executed on the RAM 48.

[0036] Next, a description will be given of the specific processing performed by the specific processing unit 290 of the data processing device 12. In the following description, the data processing device 12 will be referred to as a "server" and the smart device 14 will be referred to as a "terminal."

[0037] This invention is an educational environment platform that grasps the learning status of each student, automatically generates and provides appropriate learning content and comprehension tests, and also improves the work efficiency of faculty and staff. This platform consists of a server, terminals (devices used by students and faculty and staff), and users (students and faculty and staff).

[0038] Collection and accumulation of learning data

[0039] Data entry and submission

[0040] User

[0041] Users (students) input answers to daily study questions and comprehension tests into the terminal.

[0042] Terminal

[0043] The device sends the data entered by the student to the server in real time. For example, when a student solves an arithmetic problem and enters the answer into the tablet, the answer is sent directly to the server.

[0044] server

[0045] The server stores the transmitted learning data in a database, which includes information such as answer content, answer time, and accuracy rate.

[0046] Learning content generation and delivery

[0047] Data analysis and content generation

[0048] server

[0049] The server analyzes the collected learning data using machine learning algorithms, which identifies each student's learning progress and weaknesses.

[0050] server

[0051] The server generates learning content (such as videos) based on the analysis results. For example, for students who do not fully understand fractions, it generates a video that explains the basics of fractions in detail.

[0052] Content distribution and viewing

[0053] server

[0054] The server distributes the generated learning content to each student's device, typically via streaming.

[0055] Terminal

[0056] The devices display learning content distributed from the server and allow students to view it. Students can then watch videos on their tablets or computers to deepen their understanding.

[0057] Example: If Student A has difficulty with fractions in mathematics, the server generates a supplementary video on the specific topic of fractions and distributes it to Student A's tablet. Student A watches the video and deepens his understanding of fractions.

[0058] Providing and collecting comprehension tests

[0059] Test question generation and distribution

[0060] server

[0061] The server generates test questions to assess students' understanding, again using machine learning algorithms to set questions that address students' weaknesses.

[0062] server

[0063] The server distributes the generated test questions to the target student terminals.

[0064] Testing and collecting results

[0065] Terminal

[0066] The devices are designed to allow students to take comprehension tests, which they answer on tablets or computers.

[0067] Terminal

[0068] The terminal automatically transmits the answer result to the server.

[0069] server

[0070] The server then re-analyzes the collected answer data to determine the student's most recent understanding.

[0071] Example: Student A takes a fraction comprehension test and sends the answer data to the server. The server analyzes the test results and determines whether the student's understanding of fractions has improved.

[0072] Automatic generation and distribution of timetables

[0073] Timetable data collection and generation

[0074] server

[0075] The server collects data on classroom usage, faculty schedules, and student grades and progress, while also considering special lessons to address student weaknesses.

[0076] server

[0077] The server analyzes the collected data and generates an optimal timetable that reflects the availability of each classroom, teacher availability, and student learning needs.

[0078] Distribution and use of timetables

[0079] server

[0080] The server distributes the generated timetable to the terminals of faculty and students.

[0081] Terminal

[0082] The devices will display the distributed timetable, allowing teachers, staff and students to check it and act according to the schedule.

[0083] Example: Teacher B checks the new timetable and prepares for the next lesson. Student A also checks the time of the next lesson and prepares the necessary teaching materials.

[0084] As described above, the educational environment platform of the present invention enables flexible content distribution according to the learning situation of each student, accurate understanding of their level of understanding, and efficient timetable generation. This promotes efficiency and digitalization throughout the educational field, and makes it possible to provide an optimal learning environment.

[0085] The processing flow will be explained below.

[0086] Collection and accumulation of learning data

[0087] Step 1:

[0088] User

[0089] Students use tablets or computers to enter answers to their daily study questions and homework.

[0090] Step 2:

[0091] Terminal

[0092] The device sends the answer data entered by the student to the server in real time using a secure protocol.

[0093] Step 3:

[0094] server

[0095] The server stores the transmitted learning data in a database, including detailed information such as the student's ID, answer content, answer time, and whether the answer was correct or incorrect.

[0096] Learning content generation and delivery

[0097] Step 1:

[0098] server

[0099] The server analyzes the accumulated learning data using machine learning algorithms, thereby identifying each student's learning progress and weaknesses.

[0100] Step 2:

[0101] server

[0102] The server generates learning content (such as videos) appropriate for each student based on the analysis results. Specifically, it selects educational videos and supplementary materials according to specific themes and customizes them as needed.

[0103] Step 3:

[0104] server

[0105] The server distributes the generated learning content to each student's device in a streaming format, and also supports offline viewing if necessary.

[0106] Step 4:

[0107] Terminal

[0108] The device displays learning content delivered from the server, and students can view and understand specific learning content.

[0109] Providing and collecting comprehension tests

[0110] Step 1:

[0111] server

[0112] The server generates personalized test questions to gauge students' understanding, using machine learning algorithms.

[0113] Step 2:

[0114] server

[0115] The server distributes the generated comprehension test questions to the student's terminal.

[0116] Step 3:

[0117] Terminal

[0118] The device displays questions for students to take comprehension tests, and students enter their answers on a tablet or computer.

[0119] Step 4:

[0120] Terminal

[0121] The device sends the results of the student's answers to the test questions in real time to the server, including not only the answers but also the time and process of answering.

[0122] Step 5:

[0123] server

[0124] The server then analyzes the collected answer data again, thereby gaining an understanding of the students' current learning comprehension and reflecting this in the generation of the next learning content.

[0125] Automatic generation and distribution of timetables

[0126] Step 1:

[0127] server

[0128] The server collects staffing data, classroom utilization, faculty schedules, and student grades and progress data.

[0129] Step 2:

[0130] server

[0131] The server analyzes the collected data and generates an optimal timetable, taking into account classroom availability, teacher availability, and student learning needs.

[0132] Step 3:

[0133] server

[0134] The server distributes the generated timetable to the terminals of faculty and students.

[0135] Step 4:

[0136] Terminal

[0137] The terminal displays the distributed timetable, allowing teachers to prepare for class, while students check the time and content of their next class.

[0138] Through the specific processing steps described above, the present invention achieves efficiency and digitalization in educational settings. By providing content suited to each student's learning situation, enabling appropriate comprehension assessment, and enabling the automatic generation of efficient timetables, the aim is to improve the quality of education and reduce the workload of teachers and staff.

[0139] Example 1

[0140] Next, a description will be given of Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the smart device 14 will be referred to as a "terminal."

[0141] In today's educational environment, there is a need to closely grasp each student's learning situation and provide appropriate learning content based on that understanding. However, conventional methods often provide uniform learning materials to a large number of students, making it difficult to flexibly respond to each student's level of understanding and progress. Furthermore, the workload of teachers and staff is increasing, making efficiency an urgent need. Furthermore, insufficient collection and analysis of learning data makes it difficult to provide individualized support. The present invention aims to solve these problems and improve the efficiency of the entire educational environment while providing learning content optimized for each student.

[0142] The specific processing by the specific processing unit 290 of the data processing device 12 in the first embodiment is realized by the following means.

[0143] In this invention, the server includes: means for collecting answer data from learners' devices; means for transmitting the collected answer data to the server in real time; means for storing the transmitted answer data in a database; means for analyzing the accumulated learning data using a machine learning algorithm; means for generating learning content suitable for the learner based on the analysis results; means for distributing and displaying the generated learning content to the learner's device; means for generating test questions for assessing comprehension; means for distributing the generated test questions to the learner's device; means for transmitting answer data answered by the learner on his / her device to the server; means for reanalyzing the transmitted answer data and understanding the learner's learning situation; means for collecting data on school classroom usage, teacher schedules, and learner grades and progress; means for generating an optimal class schedule based on the collected data; and means for distributing the generated class schedule to the teacher's and learner's devices. This enables the provision of optimized educational content based on individual learner data and improves the efficiency of the entire educational environment.

[0144] "Student's device" refers to an electronic device (e.g., tablet, PC, smartphone, etc.) used by a learner, which can input learning data, view learning content, and take comprehension tests.

[0145] "Answer data" refers to data that includes the answers entered by a learner to study questions and comprehension tests.

[0146] The "server" is a central computer system that receives data sent from learners' devices and stores, analyzes, and distributes the data.

[0147] A "database" is a storage device installed on a server that organizes and stores data in an organized manner and manages it so that it can be easily accessed later.

[0148] A "machine learning algorithm" is a computer program that automatically analyzes collected data and performs pattern recognition and predictions.

[0149] "Learning Content" refers to educational materials and learning materials (e.g., video, audio, written text, interactive questions, etc.) provided to support learners' learning.

[0150] A "comprehension test" is a test or question provided to measure a learner's proficiency or comprehension.

[0151] "Classroom usage status" is information indicating the time periods during which each classroom in a school is available for use or in use.

[0152] "Teacher schedule" is information including the timetable of each teacher's working hours, class schedule, meeting schedule, etc.

[0153] "Student performance" refers to data that indicates the academic achievements that a student has made to date.

[0154] "Progress data" refers to data that indicates the learner's learning situation, progress, and state of progress.

[0155] A "timetable" is a table or list that shows students and teachers the schedule of their lessons and activities.

[0156] "Distribution" refers to the act of transmitting generated data or content to a specific terminal or user.

[0157] This invention is an educational environment platform that grasps the learning status of each student, automatically generates and provides appropriate learning content and comprehension tests, and also improves the work efficiency of faculty and staff. This platform consists of a server, terminals (devices used by students and faculty and staff), and users (students and faculty and staff).

[0158] Collection and accumulation of learning data

[0159] Data entry and submission

[0160] Students, who are users, input their daily study questions and comprehension tests into their own devices. For example, a student solves an arithmetic problem and enters the answer into a tablet. This answer data is sent to the server in real time by the device. The server then stores the sent learning data in a database. This data includes the answer content, answer time, accuracy rate, etc.

[0161] Learning content generation and delivery

[0162] Data analysis and content generation

[0163] The server analyzes the accumulated learning data using machine learning algorithms. This analysis identifies each student's learning status and weaknesses. For example, the server might determine that "Student A is struggling with fraction problems."

[0164] The server then generates learning content based on the analysis, including videos and interactive exercises, such as a video explaining the basics of fractions.

[0165] Content distribution and viewing

[0166] The server distributes the generated learning content to each student's device. This distribution is in streaming format. The device plays the distributed learning content so that the student can view it. For example, a student can view "Frequency Fundamentals" on a tablet to deepen their understanding.

[0167] Providing and collecting comprehension tests

[0168] Test question generation and distribution

[0169] The server generates test questions to assess students' understanding. This also uses machine learning algorithms to create questions tailored to each student's weaknesses. For example, it generates new fraction questions in a specific format. The generated test questions are then distributed to each student's device.

[0170] Testing and collecting results

[0171] The student user takes a comprehension test on their device. For example, they answer questions on a tablet to measure their "understanding of fractions." The device sends the test results to the server in real time. The server reanalyzes these test results and keeps track of the student's latest understanding.

[0172] Automatic generation and distribution of timetables

[0173] Timetable data collection and generation

[0174] The server collects data on classroom usage, faculty schedules, and student performance and progress. This data includes classroom availability, teacher availability, and student learning needs. The server analyzes the collected data and generates an optimal timetable.

[0175] Distribution and use of timetables

[0176] The server distributes the generated timetable to the terminals of faculty and students. The terminals display the distributed timetable so that faculty and students can check it. For example, faculty and staff check the timetable to prepare for the next class, and students also check the time of the next class and prepare the necessary teaching materials.

[0177] Specific examples

[0178] If it is determined that Student A's understanding of fractions is insufficient, the server uses a machine learning algorithm to generate an explanatory video on fractions tailored to the student and distributes it to Student A's tablet. Student A watches the video to deepen his or her understanding. Student A is then given a fraction comprehension test, and the results are sent to the server, which then provides appropriate learning content based on the analysis results.

[0179] Prompt Sentence Examples

[0180] Below are some example prompts to input to a generative AI model:

[0181] "Please use this AI model to design a system that collects and analyzes student learning data and generates and delivers individualized learning content. Specifically, I would like to build an educational environment platform that generates comprehension tests, collects and analyzes the results, and automatically generates appropriate timetables."

[0182] As described above, the educational environment platform of the present invention can flexibly distribute content according to each student's learning situation, accurately grasp their level of understanding, and generate efficient timetables. This will promote efficiency and digitalization throughout the educational field, and make it possible to provide an optimal learning environment.

[0183] The flow of the identification process in the first embodiment will be described with reference to FIG.

[0184] Step 1:

[0185] Input of training data

[0186] The user (student) inputs daily study questions and comprehension tests into the terminal. For example, a student inputs answers to math problems. This input data includes the answer content and answer time entered by the student. The input data is sent to the next step.

[0187] Input: Answer data entered by the student into the device (answer content, answer time)

[0188] Output: Answer data saved on the device

[0189] Step 2:

[0190] Sending training data

[0191] The terminal transmits the answer data entered by the student to the server in real time. For example, the terminal transfers the answer data to the server via the network. This data includes the answer content and the answer time.

[0192] Input: Answer data saved on the device

[0193] Output: Answer data sent to the server

[0194] Step 3:

[0195] Accumulation of learning data

[0196] The server receives the submitted answer data and stores it in a database. This data includes the answer content, answer time, and correct answer rate. The server stores the data in the database so that it can be used for future processing.

[0197] Input: Answer data sent to the server (answer content, answer time, correct answer rate)

[0198] Output: Answer data stored in the database

[0199] Step 4:

[0200] Data analysis

[0201] The server analyzes the accumulated answer data using a machine learning algorithm. This analysis identifies the student's learning status and weaknesses. For example, the server analyzes that Student A is struggling with fraction problems.

[0202] Input: Answer data stored in the database

[0203] Output: Analysis results (student weaknesses and learning status)

[0204] Step 5:

[0205] Generating learning content

[0206] The server generates learning content based on the analysis results, including instructional videos and interactive exercises. For example, it generates a video explaining the basics of fractions.

[0207] Input: Analysis results

[0208] Output: Generated learning content

[0209] Step 6:

[0210] Delivery of learning content

[0211] The server then distributes the generated learning content to the learner's device. This distribution is done in streaming format. The server distributes the most suitable content to each learner in a timely manner.

[0212] Input: Generated learning content

[0213] Output: Learning content delivered to the learner's device

[0214] Step 7:

[0215] Viewing content

[0216] The device plays learning content distributed from the server and allows learners to view it. For example, a student can watch a video explaining fractions on a tablet.

[0217] Input: Learning content delivered to your device

[0218] Output: Learning content viewed by the learner

[0219] Step 8:

[0220] Generate comprehension tests

[0221] The server generates test questions to assess students' understanding. It uses machine learning algorithms to create questions tailored to students' weaknesses, for example, generating fraction questions in a specific format.

[0222] Input: Analysis results

[0223] Output: Generated assessment questions

[0224] Step 9:

[0225] Comprehension test distribution

[0226] The server distributes the generated test questions to the learner's terminal, which displays the test questions in an appropriate format.

[0227] Input: Generated assessment questions

[0228] Output: Comprehension test questions delivered to the learner's device

[0229] Step 10:

[0230] Comprehension test

[0231] The user (student) takes a comprehension test on the device. For example, the student answers a fraction comprehension test on a tablet.

[0232] Input: Comprehension test questions delivered to the learner's device

[0233] Output: Answered comprehension test data

[0234] Step 11:

[0235] Sending test results

[0236] The device sends test results in real time to a server, including the percentage of correct answers and response time.

[0237] Input: Answered comprehension test data

[0238] Output: Test results sent to the server

[0239] Step 12:

[0240] Analyzing test results

[0241] The server re-analyzes the test results and determines the latest learning status. For example, the server determines whether Student A's understanding of fractions has improved.

[0242] Input: Test results sent to the server

[0243] Output: Reanalysis results (latest learning status)

[0244] Step 13:

[0245] Collection of timetable data

[0246] The server collects data on the school's classroom usage, teacher schedules, and student performance and progress, including classroom availability, teacher availability, and student learning needs.

[0247] Input: Various data (classroom usage, teacher schedules, student grades and progress data)

[0248] Output: Collected timetable data

[0249] Step 14:

[0250] Generating optimal timetables

[0251] The server generates an optimal timetable based on the collected data, for example, one that reflects the available time of each classroom, the free time of teachers, and the learning needs of students.

[0252] Input: Collected timetable data

[0253] Output: Generated optimal timetable

[0254] Step 15:

[0255] Timetable distribution

[0256] The server distributes the generated timetable to the devices of faculty and students. The devices display the distributed timetable so that faculty and students can check it. For example, faculty and students check the new timetable to prepare for the next class, and students also check the time of the next class and prepare the necessary teaching materials.

[0257] Input: Generated optimal timetable

[0258] Output: Timetables distributed to faculty and student devices

[0259] The above is the specific flow of program processing for this system.

[0260] (Application example 1)

[0261] Next, a description will be given of Application Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the smart device 14 will be referred to as a "terminal."

[0262] Conventional educational platforms face the challenge of making it difficult to provide personalized learning content tailored to each student's learning situation. In particular, generating and delivering appropriate content based on the student's level of understanding, as well as providing effective feedback, is time-consuming, hindering the efficiency of classrooms. It is also not easy to optimize timetables based on each student's learning progress and weaknesses. Therefore, there is a need for a system that can provide a learning environment tailored to each student's needs and reduce the workload of teachers.

[0263] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 1 is realized by the following means.

[0264] In this invention, the server includes: means for storing learning data collected from learning institutions nationwide in a database; means for analyzing the learning data stored in the database; means for generating learning content appropriate for each user based on the analysis results; means for distributing the generated learning content to each user's device; means for generating questions to test each user's level of comprehension; means for distributing the generated comprehension test questions to the device and collecting user answer data; means for re-analyzing the user's learning status based on the collected answer data; means for generating an optimal timetable based on classroom usage status, faculty schedules, and user grades and progress data; means for distributing the generated timetable to faculty and user devices; and means for using a generative AI model to generate personalized learning content and distributing the learning content to each user's device using prompts. This enables the automatic generation and distribution of learning content tailored to each student's level of comprehension, thereby improving the efficiency of education and student comprehension.

[0265] "Learning institutions" refers to all educational institutions, and is a general term for institutions that provide education such as elementary schools, junior high schools, high schools, universities, and vocational schools.

[0266] "Learning data" refers to information about a student's learning status, including digital data such as answer content, answer time, and correct answer rate.

[0267] A "database" is a system for systematically managing collected information and performing operations such as storage, search, and analysis.

[0268] "Analysis" is the process of processing collected data using methods and algorithms to obtain information for a specific purpose.

[0269] "Learning content" is a general term for teaching materials and resources used for educational purposes, including videos, texts, quizzes, etc.

[0270] A "terminal" is a digital device or equipment used by a user, such as a smartphone, tablet, or PC.

[0271] A "comprehension test" is a test to evaluate a student's level of comprehension of the learning content, and is given in the form of questions.

[0272] "Answer data" refers to a digital record of a student's answers to tests and questions.

[0273] A "timetable" is a table that shows the schedule of an educational institution or individual student, including the times and contents of classes.

[0274] A "generative AI model" is a collection of algorithms and programs that use artificial intelligence technology to automatically generate learning content and test questions.

[0275] A "prompt sentence" is an input sentence or command that gives a generative AI model specific instructions or requests.

[0276] This invention builds a system for providing an efficient and personalized learning environment in educational settings. This system uses the following hardware and software to collect and analyze various data, and then generates and distributes appropriate learning content.

[0277] Hardware

[0278] Server: A high-performance computer that can be cloud-based or on-premise.

[0279] Device: The device used by the user, such as a smartphone, tablet, or computer.

[0280] software

[0281] Mobile Application: A cross-platform application developed using React Native or Flutter (registered trademark).

[0282] Server side: Built using Django and Node.js. PostgreSQL database is used.

[0283] Machine learning algorithms: TENSORFLOW (registered trademark) and PyTorch are used for analysis. FFmpeg and OpenCV are used for video generation.

[0284] Data collection and storage

[0285] User: When students answer questions on their smartphones or tablets, the answer data is sent to the server in real time.

[0286] Server: The transmitted learning data is stored in a database, including answer content, answer time, and accuracy rate.

[0287] Data analysis and learning content generation

[0288] Server: Analyzes accumulated learning data using machine learning algorithms to identify each student's learning situation and weaknesses.

[0289] Server: Generates personalized learning content based on the analysis results. This uses a generative AI model to generate videos and text based on specific prompts. The generated content is saved in the appropriate format (video, text, etc.).

[0290] Content distribution and viewing

[0291] Server: The server distributes the generated learning content to each student's device using streaming technology.

[0292] Devices: Students can view and understand the learning content delivered on tablets and computers.

[0293] Providing comprehension tests and analyzing results

[0294] Server: Generates test questions to assess comprehension and distributes them to each student's device.

[0295] Device: Students answer test questions on their devices. The answer data is automatically sent to the server.

[0296] Server: Re-analyzes the collected answer data and updates the student's learning status.

[0297] Automatic generation and distribution of timetables

[0298] Server: Analyzes classroom usage, faculty schedules, and student grades and progress data to generate optimal timetables.

[0299] Server: Distributes the generated timetable to the terminals of faculty and students.

[0300] Terminals: Used by faculty and students to check upcoming lesson times and content.

[0301] Examples and prompts

[0302] For example, a user (student) solves a problem on "mathematical fractions" and sends the answer data to the server. The server analyzes the data and determines that the user lacks understanding of fractions. Next, it uses a generative AI model to generate a "video explaining the basics of fractions" and distributes it to the user. An example of a prompt sentence used in this case is, "This user's understanding of fractions is lacking. Please generate video teaching materials to help them understand the basics of fractions."

[0303] This system makes it possible to automatically generate and distribute learning content tailored to each user's level of understanding, thereby improving the efficiency of the classroom and the students' level of understanding.

[0304] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[0305] Step 1:

[0306] Data collection and transmission

[0307] Input: Data on the study questions answered by the user (student) on the device (answer content, answer time, correct answer rate)

[0308] How it works: When a user answers a study question on a smartphone or tablet, the data is sent to the server in real time. The application prompts the user to enter the answer, and once the answer is completed, the information is transferred to the server in JSON format.

[0309] Output: Answer data sent to the server

[0310] Step 2:

[0311] Data accumulation

[0312] Input: Answer data submitted in Step 1

[0313] Specific operation: The server stores the received answer data in a database using PostgreSQL, and the answer data is organized and saved in a table.

[0314] Output: Answer data stored in the database

[0315] Step 3:

[0316] Data analysis

[0317] Input: Answer data stored in the database

[0318] Specific operation: The server analyzes the answer data using machine learning algorithms (TensorFlow and PyTorch). This analysis identifies each student's learning status and weaknesses. Python is used for data analysis, and the learning status is quantified and evaluated.

[0319] Output: Analysis results (each student's level of understanding and weaknesses)

[0320] Step 4:

[0321] Learning content generation

[0322] Input: Analysis results obtained in step 3

[0323] Specific operation: The server uses the generative AI model to generate learning content (videos and text) based on the prompt. For example, a prompt such as "This user's understanding of fractions is insufficient. Please generate video materials to help them understand the basics of fractions" is input into the AI ​​model, and a video with the corresponding learning content is generated.

[0324] Output: Generated learning content (videos, text)

[0325] Step 5:

[0326] Content Delivery

[0327] Input: Learning content generated in Step 4

[0328] Specific operation: The server delivers the generated learning content to each user's device. The delivery format is mainly streaming, and the server notifies the user using Firebase Cloud Messaging or similar and provides the content URL.

[0329] Output: Learning content delivered to the user's device

[0330] Step 6:

[0331] Test generation and delivery

[0332] Input: Analysis results obtained in step 3

[0333] Specific operation: The server generates test questions to evaluate the user's level of understanding and distributes them to the device. The generated test questions are converted into JSON format and sent to the device via push notification.

[0334] Output: Comprehension test questions delivered to the user's device

[0335] Step 7:

[0336] Conducting comprehension tests and collecting results

[0337] Input: Comprehension test questions delivered in Step 6

[0338] Specific operation: The user answers the test questions on the device, and the answer data is sent to the server again in real time in JSON format.

[0339] Output: Test answer data sent to the server

[0340] Step 8:

[0341] Reanalysis and feedback

[0342] Input: Test response data collected in Step 7

[0343] Specific operation: The server analyzes the collected answer data again to grasp the student's latest learning situation. Based on the analysis results, it determines whether new learning content is necessary.

[0344] Output: Analysis results based on the latest learning status

[0345] Step 9:

[0346] Timetable generation and distribution

[0347] Input: User grades, progress data, classroom usage, faculty schedules

[0348] Specific operation: The server generates an optimal timetable based on the above data. The generated timetable is distributed to each user and faculty member via their terminal.

[0349] Output: Timetable distributed to each user and faculty terminal

[0350] Furthermore, an emotion engine that estimates the user's emotion may be combined. That is, the identification processing unit 290 may estimate the user's emotion using the emotion identification model 59 and perform identification processing using the user's emotion.

[0351] This invention is a system that combines an emotion engine with an educational environment platform that grasps each student's learning situation and automatically generates and provides appropriate learning content and comprehension tests. This makes it possible to grasp students' emotional states, improve the learning experience, and increase educational efficiency. This platform consists of a server, terminals (devices used by students and faculty), and users (students and faculty).

[0352] Collection and storage of learning data and emotion data

[0353] Data entry and submission

[0354] User

[0355] Students use tablets or computers to input answers to daily study questions and homework, and emotional data is automatically collected through facial expressions and voice.

[0356] Terminal

[0357] Terminal

[0358] The device transmits the answer data and emotion data entered by the student to the server in real time using a secure protocol.

[0359] server

[0360] server

[0361] The server stores the transmitted learning data and emotional data in a database, including detailed information such as the student's ID, answer content, answer time, correct or incorrect answers, and emotional state.

[0362] Learning content generation and delivery

[0363] Data analysis and content generation

[0364] server

[0365] The server analyzes the accumulated learning and emotional data using machine learning algorithms to identify each student's learning progress, weaknesses, and emotional state.

[0366] server

[0367] The server then generates learning content (such as videos) tailored to each student based on the analysis results. For example, it selects educational videos and supplemental materials tailored to specific themes and customizes them as needed. Emotional data is also taken into account, so if a student is feeling anxious, content is generated that includes clearer explanations and encouraging messages.

[0368] Content distribution and viewing

[0369] server

[0370] The server distributes the generated learning content to each student's device in a streaming format, and also supports offline viewing if necessary.

[0371] Terminal

[0372] The device displays learning content delivered from the server, and students can view and understand specific learning content.

[0373] Example: If Student A has difficulty with fractions in mathematics and shows signs of anxiety while studying, the server generates a supplementary video on the specific topic of fractions, including an encouraging message. This video is then distributed to Student A's tablet, and Student A watches it, deepening his understanding of fractions and feeling reassured.

[0374] Providing and collecting comprehension tests

[0375] Test question generation and distribution

[0376] server

[0377] The server generates personalized test questions to gauge students' understanding, using machine learning algorithms based on learning and sentiment data.

[0378] server

[0379] The server distributes the generated comprehension test questions to the student's terminal.

[0380] Testing and collecting results

[0381] Terminal

[0382] The device displays questions for students to take comprehension tests, and students enter their answers on a tablet or computer.

[0383] Terminal

[0384] The device sends the student's answers to the test questions in real time to the server, including not only the answers but also the emotional responses they gave while answering.

[0385] server

[0386] The server then performs a second analysis based on the collected answer data and emotion data, thereby gaining an understanding of the student's current learning comprehension and emotional state, which is then reflected in the generation of the next learning content.

[0387] Example: When Student B takes a comprehension test, if he takes a long time to answer and looks confused, the server can analyze the data to identify the areas where Student B's understanding is lacking and generate questions for the next test to reinforce those areas.

[0388] Automatic generation and distribution of timetables

[0389] Timetable data collection and generation

[0390] server

[0391] The server collects staffing data, classroom utilization, faculty schedules, student grades and progress data, and sentiment data.

[0392] server

[0393] The server analyzes the collected data and generates an optimal timetable that takes into account classroom availability, teacher availability, student learning needs, and emotional state.

[0394] Distribution and use of timetables

[0395] server

[0396] The server distributes the generated timetable to the terminals of faculty and students.

[0397] Terminal

[0398] The terminal displays the distributed timetable, allowing teachers to prepare for class, while students check the time and content of their next class.

[0399] Example: Teacher C checks the new timetable and prepares for the next lesson. Student A also checks the time of the next lesson and prepares the necessary materials. Based on Student A's emotional data, relaxing lessons and activities are incorporated during times of particularly high stress.

[0400] As described above, the educational environment platform of the present invention provides flexible content and assessment of comprehension according to each student's learning situation and emotional state, and automatically generates efficient timetables. This promotes efficiency and digitalization throughout the entire educational environment, making it possible to provide an optimal learning environment.

[0401] The processing flow will be explained below.

[0402] Collection and storage of learning data and emotion data

[0403] Step 1:

[0404] User

[0405] Students use tablets or PCs to input answers to study questions and homework, and their facial expressions and voice data are automatically collected by the emotion engine while they are studying.

[0406] Step 2:

[0407] Terminal

[0408] The device transmits the answer data entered by the student and the collected emotion data to the server in real time, using a security protocol.

[0409] Step 3:

[0410] server

[0411] The server stores the submitted answer data and emotional data in a database, which contains information on the student's ID, answer content, answer time, correct / incorrect answers, and emotional state.

[0412] Learning content generation and delivery

[0413] Step 1:

[0414] server

[0415] The server analyzes the accumulated learning and emotional data using machine learning algorithms to identify students' learning progress, weaknesses, and emotional patterns.

[0416] Step 2:

[0417] server

[0418] The server generates learning content (e.g., videos) appropriate for the student based on the analysis results. For example, if a student is having trouble in a particular area, it generates a detailed explanatory video on that area. It also takes into account the student's emotional state and includes messages to ease anxiety.

[0419] Step 3:

[0420] server

[0421] The server distributes the generated learning content to students' devices. The distribution format is primarily streaming, but offline viewing is also supported if necessary.

[0422] Step 4:

[0423] Terminal

[0424] The device displays the delivered learning content to the students, who can then view and understand the content.

[0425] Example: If Student A feels uncomfortable with fraction problems in mathematics, the server generates a video with a detailed explanation of fractions and a message of encouragement, and distributes it to Student A's tablet. Student A watches this video, deepens his understanding of fractions, and reduces his anxiety about learning.

[0426] Providing and collecting comprehension tests

[0427] Step 1:

[0428] server

[0429] The server generates test questions to measure students' comprehension using machine learning algorithms based on training data and emotional data.

[0430] Step 2:

[0431] server

[0432] The server distributes the generated comprehension test questions to the student's terminal.

[0433] Step 3:

[0434] Terminal

[0435] The device displays questions for students to take comprehension tests, and students enter their answers on a tablet or computer.

[0436] Step 4:

[0437] Terminal

[0438] The terminal transmits the content of the answer and the emotion data in the answer to the server in real time.

[0439] Step 5:

[0440] server

[0441] The server analyzes the collected answer data and emotional data to grasp the latest learning comprehension and emotional state, and generates the next learning content and comprehension test based on the analysis results.

[0442] Example: If Student B shows signs of confusion or anxiety while taking a comprehension test, the server analyzes the data and identifies the areas where Student B is having difficulty. The next test will include reinforcement questions specific to those areas.

[0443] Automatic generation and distribution of timetables

[0444] Step 1:

[0445] server

[0446] The server collects classroom usage, faculty schedules, student grades and progress data, and sentiment data.

[0447] Step 2:

[0448] server

[0449] The server analyzes the collected data and generates an optimal timetable that takes into account classroom availability, faculty availability, students' learning needs, and emotional state.

[0450] Step 3:

[0451] server

[0452] The server distributes the generated timetable to the terminals of faculty and students.

[0453] Step 4:

[0454] Terminal

[0455] The terminals display the distributed timetable, which teachers and students can check. Teachers prepare for the lesson, and students check the time and content of the next lesson.

[0456] Example: Staff member C checks the new timetable and prepares for the next lesson. Based on emotional data, relaxing lessons and activities are scheduled during particularly stressful times. Student A also checks the timetable and prepares the necessary materials.

[0457] As described above, the present invention provides a system that improves students' learning efficiency and education quality by combining emotion engines. It realizes an individually optimized learning environment for each student through content distribution, test evaluation, and timetable generation based on the learning situation and emotional state.

[0458] Example 2

[0459] Next, a description will be given of Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the smart device 14 will be referred to as a "terminal."

[0460] Conventional educational systems have difficulty efficiently grasping the progress and level of understanding of individual learners and providing appropriate learning content. Furthermore, they are unable to take into account the learner's emotional state, making it difficult to provide an educational environment that maximizes the effectiveness of learning. This leads to a decline in learner motivation and delays in learning progress, resulting in the inability to fully realize the effectiveness of education.

[0461] The specific processing by the specific processing unit 290 of the data processing device 12 in the second embodiment is realized by the following means.

[0462] In this invention, the server includes a means for storing learning data and emotional data collected from educational institutions nationwide in a database, a means for analyzing the stored learning data and emotional data, and a means for generating learning content appropriate for each learner based on the analysis results. This makes it possible to provide optimal learning content and create an efficient learning environment by taking into account the progress and emotional state of each individual learner.

[0463] "Learning data" refers to data collected by educational institutions, such as a learner's learning history, grades, progress, and answer content.

[0464] "Emotion data" is data that indicates the emotional state of a learner, obtained from their facial expressions and voice.

[0465] A "database" is a system for systematically storing and managing collected learning data and emotional data.

[0466] "Analysis" refers to the use of machine learning algorithms to analyze collected data and identify learners' progress, level of understanding, and emotional state.

[0467] "Learning content" refers to educational materials, videos, and supplementary materials that are customized according to the learner's progress and level of understanding.

[0468] "Devices" are electronic devices such as tablets and computers used by learners and faculty and staff.

[0469] A "machine learning algorithm" is a computer program used to perform analysis based on collected data, and can utilize libraries such as TensorFlow and Scikit-learn.

[0470] A "comprehension test" is a test question that measures a learner's level of comprehension and is customized for each individual.

[0471] A "timetable" is a schedule that is optimally organized taking into account classroom usage, faculty and staff schedules, learners' grades and progress data, and emotional data.

[0472] "Educational institutions" refers to facilities and organizations that carry out educational activities, such as schools and cram schools.

[0473] This invention provides an educational platform that analyzes collected learning data and emotional data, and automatically generates and delivers learning content and comprehension tests appropriate for each learner. This system includes a server, terminals (devices used by learners and faculty), and users (learners and faculty). The following describes how to specifically implement this system.

[0474] Data collection and transmission

[0475] User

[0476] Learners use tablets or PCs to input answers to daily study questions and homework assignments, and emotional data is automatically collected through the learner's facial expressions and voice.

[0477] Terminal

[0478] The device transmits the answer data and emotion data entered by the student to the server in real time using a secure protocol (e.g., HTTPS).

[0479] Data accumulation

[0480] server

[0481] The server stores the learning data and emotional data sent from the device in a database. This database uses MySQL (registered trademark) or PostgreSQL. This data includes the learner's ID, answer content, answer time, correct or incorrect answers, emotional state, etc.

[0482] Data analysis and content generation

[0483] server

[0484] The server analyzes the accumulated learning data and emotional data using machine learning algorithms such as Python's TensorFlow and Scikit-learn, thereby identifying each learner's learning progress, weaknesses, and emotional state.

[0485] server

[0486] The server generates learning content appropriate for each learner based on the analysis results. For example, if a learner is weak in a particular topic, it provides supplementary learning materials or educational videos on that topic. Furthermore, it generates content that includes encouraging messages for learners who are feeling anxious.

[0487] Content distribution and viewing

[0488] server

[0489] The server distributes the generated learning content to the learner's device using streaming technology such as HLS (HTTP Live Streaming).

[0490] Terminal

[0491] The terminal displays the learning content delivered from the server, and the learner watches and listens to it to understand the learning content.

[0492] Example: If Learner A has difficulty with fractions in mathematics and shows signs of anxiety while studying, the server generates a supplementary video explaining fractions and includes an encouraging message. This video is then distributed to Learner A's tablet, and Learner A watches it, deepening his understanding of fractions and feeling reassured.

[0493] Providing comprehension tests and collecting results

[0494] server

[0495] The server generates test questions based on the learning data and emotion data to measure the learner's level of understanding.

[0496] server

[0497] The server distributes the generated comprehension test questions to the learner's terminal.

[0498] Terminal

[0499] The device displays questions so that learners can take comprehension tests, and learners enter their answers on a tablet or computer.

[0500] Terminal

[0501] The device transmits the learner's test results and emotional data during the response to the server in real time.

[0502] Comprehension test analysis

[0503] server

[0504] The server reanalyzes the collected answer data and emotion data to grasp the learner's latest learning comprehension and emotional state. This information is reflected in the generation of the next learning content. The analysis is performed using the Python Pandas library.

[0505] Example: When Learner B takes a comprehension test, if he looks confused and takes a long time to answer a particular question, the server will analyze that data and generate questions for the next test that will help Learner B to fill in the gaps in his understanding.

[0506] Automatic generation and distribution of timetables

[0507] server

[0508] The server collects staffing data, classroom usage, faculty schedules, student grades and progress data, and emotional data to generate an optimal timetable.

[0509] server

[0510] The server distributes the generated timetable to the terminals of teachers and students.

[0511] Terminal

[0512] The terminal displays the distributed timetable, allowing teachers to prepare for lessons and students to check the time and content of their next lesson.

[0513] Example: Faculty member C checks the new timetable and prepares for the next lesson. Learner A also checks the time of the next lesson and prepares the necessary materials. Based on Learner A's emotional data, lessons and activities that help him relax are incorporated during times when he is feeling particularly stressed.

[0514] Prompt Sentence Examples

[0515] How do you collect and analyze student learning and emotion data?

[0516] Explain how to generate optimal learning content taking into account learning progress and emotional state.

[0517] What is the process for automatically generating tests to effectively assess student understanding?

[0518] The flow of the identification process in the second embodiment will be described with reference to FIG.

[0519] Step 1: Enter and submit data

[0520] User

[0521] Learners use tablets or computers to input their daily homework and answers to study questions, and their facial expressions and voice data are automatically captured while they study via cameras and microphones.

[0522] Input: Learner's answer data (answer content, answer time, correct / incorrect) and emotional data (facial expression, voice)

[0523] Output: Input answer data and emotion data

[0524] Terminal

[0525] The device sends the input answer data and emotion data to the server in real time using the HTTPS protocol to ensure data security.

[0526] Input: Learner's answer data and emotion data

[0527] Output: Answer data and emotion data sent to the server

[0528] Step 2: Accumulating data

[0529] server

[0530] The server stores the learning data and emotional data sent from the device in a relational database (e.g., MySQL or PostgreSQL). The database appropriately stores metadata such as the learner's ID, answer content, answer time, correct or incorrect answers, and emotional state.

[0531] Input: Submitted training data and emotion data

[0532] Output: Learning data and emotion data stored in the database

[0533] Step 3: Analyze the data

[0534] server

[0535] The server runs machine learning algorithms using Python's TensorFlow and Scikit-learn to analyze the accumulated learning data and emotional data, identifying each learner's learning progress, weaknesses, and emotional state. The analysis process also includes data preprocessing (e.g., normalization, missing value imputation).

[0536] Input: Accumulated learning data and emotion data

[0537] Output: Analysis of progress, weaknesses, and emotional state of each learner

[0538] Step 4: Generate learning content

[0539] server

[0540] The server generates learning content appropriate for each learner based on the analysis results. This content includes educational videos, supplementary materials, encouraging messages, etc. For example, if a learner is anxious about a particular topic, content including a detailed explanatory video on that topic and encouraging messages will be generated.

[0541] Input: Analysis results (learning progress, weaknesses, emotional state)

[0542] Output: Generated learning content

[0543] Step 5: Deliver your content

[0544] server

[0545] The server distributes the generated learning content to the learner's device. Streaming technology (e.g., HLS) is used for distribution. The distributed data is sent in a format appropriate for each learner's device. At the same time, it is cached in a format that allows for offline viewing.

[0546] Input: Generated learning content

[0547] Output: Learning content delivered to the learner's device

[0548] Terminal

[0549] The device receives the learning content distributed from the server and displays it for the learner to view, allowing the learner to acquire new knowledge and resolve any concerns they may have.

[0550] Input: Delivered learning content

[0551] Output: View and play learning content

[0552] Step 6: Provide a test

[0553] server

[0554] The server generates individually customized comprehension test questions to measure the learner's level of comprehension, using machine learning algorithms and analysis results based on learning data and emotional data.

[0555] Input: Analysis results, training data, emotion data

[0556] Output: Generated assessment questions

[0557] server

[0558] The server distributes the generated comprehension test questions to the learner's terminal.

[0559] Input: Generated assessment questions

[0560] Output: Comprehension test questions delivered to the learner's device

[0561] Step 7: Collect and analyze test results

[0562] Terminal

[0563] The device displays questions so that learners can take comprehension tests, and learners enter their answers on a tablet or computer.

[0564] Input: The displayed assessment question

[0565] Output: Answer data entered by the learner

[0566] Terminal

[0567] The device transmits the learner's test results and emotional data during the response to the server in real time.

[0568] Input: Answer data and emotion data entered by the learner

[0569] Output: Answer data and emotion data sent to the server

[0570] server

[0571] The server analyzes the collected answer data and emotional data. This allows it to grasp the learner's current level of learning comprehension and emotional state. The analysis results are reflected in the generation of the next learning content.

[0572] Input: Collected answer data, emotion data

[0573] Output: Analysis of the learner's comprehension and emotional state

[0574] Step 8: Generate and distribute timetables

[0575] server

[0576] The server collects staffing data, classroom usage, faculty schedules, student performance and progress data, and sentiment data. It analyzes this data to generate an optimal timetable. This analysis utilizes the Google® Calendar API and other scheduling systems.

[0577] Inputs: Staffing data, classroom utilization, faculty schedules, learner performance, progress data, sentiment data

[0578] Output: The generated timetable

[0579] server

[0580] The server distributes the generated timetable to the terminals of teachers and students.

[0581] Input: Generated timetable

[0582] Output: Distributed timetable

[0583] Terminal

[0584] The terminal displays the distributed timetable, allowing teachers to prepare for lessons and students to check the time and content of their next lesson.

[0585] Input: Distributed timetable

[0586] Output: Displayed timetable

[0587] (Application example 2)

[0588] Next, a description will be given of Application Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the smart device 14 will be referred to as a "terminal."

[0589] Conventional educational environment platforms have difficulty providing appropriate learning content based on each student's learning ability and progress. They also lack a mechanism for understanding the emotional state of students and customers in real time and adjusting learning content accordingly. This has led to problems such as a decline in student motivation and a drop in customer satisfaction. Furthermore, it has been difficult to provide information tailored to individual needs when dealing with customers in virtual stores. To solve these issues, a system is needed that can understand the emotional state of students and provide learning content and information appropriate to that situation.

[0590] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 2 is realized by the following means.

[0591] In this invention, the server includes: means for storing learning data collected from educational institutions nationwide in a database; means for analyzing the learning data stored in the database; means for generating learning content appropriate for each learner based on the analysis results; means for distributing the generated learning content to each learner's terminal; means for generating questions to test each learner's level of comprehension; means for distributing the generated comprehension test questions to the terminal and collecting learner answer data; means for re-analyzing the learner's learning status based on the collected answer data; means for collecting learner emotional data and adjusting the learning content based on that data; means for generating and distributing learning content for customers in a virtual store; means for analyzing the customer's emotional state and providing interactive content based on the analyzed data; means for generating an optimal class schedule based on classroom usage, faculty schedules, and learner grades and progress data; and means for distributing the generated class schedule to faculty and learner terminals. This enables flexible content provision according to the emotional state of learners and customers, thereby improving learning efficiency and customer satisfaction.

[0592] "Educational institutions" is a general term for facilities and organizations that conduct learning activities, including elementary schools, junior high schools, high schools, universities, and vocational schools.

[0593] "Learning data" refers to various data generated by learners through their learning activities, and examples include answer content, correct / incorrect answers, response time, and progress status.

[0594] "Emotional data" refers to data that indicates the emotional state of a learner as analyzed from their facial expressions and voice, and includes, for example, joy, anxiety, confusion, etc.

[0595] "Database" means a system capable of storing, managing, and retrieving large amounts of data in a structured form.

[0596] A "machine learning algorithm" is an algorithm that automatically makes predictions and judgments through learning from data.

[0597] "Learning content" refers to educational materials and information provided to learners, including videos, textbooks, workbooks, interactive learning materials, etc.

[0598] "Device" is a general term for electronic devices used by learners and faculty and staff, including personal computers, tablets, smartphones, etc.

[0599] A "comprehension test" is a test used to assess a learner's level of comprehension, and includes question formats, quizzes, questionnaires, etc.

[0600] "Analysis" refers to the process of collecting, classifying, and processing data to clarify its meaning and characteristics.

[0601] "Virtual store" refers to a virtual store that offers products and services over the Internet.

[0602] "Interactive content" refers to content that requires interaction with users, and includes chatbots, interactive videos, and dialogue training.

[0603] "Timetable" means a table showing the schedule of lessons and activities at an educational institution or program of study.

[0604] "Customer" means a user who intends to purchase or use goods or services in the virtual store.

[0605] "Generated" and "produced" refer to something newly created using a specific algorithm or method.

[0606] This invention relates to an educational environment platform that collects, analyzes, and distributes learning data and emotional data. This platform provides flexible content that takes into account the emotional state of students and customers to improve the learning experience. It also includes a system for grasping the emotional state of customers in a virtual store and providing appropriate information.

[0607] System configuration

[0608] The present invention comprises the following hardware and software components:

[0609] server

[0610] The server has the following functions:

[0611] Database Management:

[0612] Training data and emotion data are stored in a relational database such as MySQL or PostgreSQL.

[0613] Running machine learning algorithms:

[0614] To analyze the collected data, machine learning libraries such as TensorFlow and PyTorch are used.

[0615] Content Generation:

[0616] Based on the analysis results, learning content such as learning videos and supplementary materials is generated, and the generated content is stored in cloud storage such as AWS (registered trademark) S3.

[0617] Streaming:

[0618] It provides a streaming service to deliver learning content to each device, using a CDN such as AWS CloudFront.

[0619] Terminal

[0620] The device has the following features:

[0621] Data collection:

[0622] Collects answer data and emotional data (facial expressions, voice) from students and customers using cameras and microphones.

[0623] Content Display:

[0624] The learning content distributed from the server is displayed on display devices such as tablets, smartphones, and smart glasses.

[0625] User

[0626] Users (students and faculty) have the following roles:

[0627] Implementing learning activities:

[0628] Students use tablets and computers to answer daily study questions.

[0629] Sentiment data provided by:

[0630] Students and customers provide emotional data via a camera and microphone.

[0631] Data analysis and content generation

[0632] The server uses machine learning algorithms to analyze the collected learning data and emotional data. This analysis identifies the learning progress and emotional state of the student or customer. Based on the analysis results, appropriate learning content is generated and delivered to each device.

[0633] Application in virtual stores

[0634] In the virtual store, if a customer expresses interest in a new product, detailed educational content about that product will be generated and delivered. The customer's emotional state will also be analyzed, and if they are feeling anxious or confused, more detailed explanations or support messages will be provided.

[0635] Examples:

[0636] For example, if a customer expresses interest in a new smartphone but appears anxious, the server analyzes the facial expression data and generates a friendly instructional video that clearly explains the product's features and how to use it, along with encouraging messages, and streams the video to the smart glasses or tablet.

[0637] Example prompt sentence:

[0638] "Analyze what emotions the person in the image is expressing"

[0639] "Generate explainer videos about product details based on specific emotional states."

[0640] In this way, the present invention makes it possible to provide content flexibly according to the emotional state of the learner or customer, thereby improving learning efficiency and customer satisfaction.

[0641] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[0642] Step 1:

[0643] Data collection

[0644] Users (students or customers) use devices (e.g., tablets, smart glasses) to carry out daily learning activities. During this time, the devices use cameras and microphones to collect facial and voice data of the users.

[0645] Input: Learner's answer data and emotional data (facial expressions, voice)

[0646] Output: A set of collected answer data and sentiment data

[0647] How it works: The device's camera and microphone are constantly active, capturing the user's face and voice, which are then processed in real time and sent to a server.

[0648] Step 2:

[0649] Data transmission

[0650] The device transmits the collected data of the learner's answers and emotions to the server in real time. The communication is carried out using a secure protocol (e.g., HTTPS).

[0651] Input: Collected answer data and sentiment data

[0652] Output: Collected data sent to the server

[0653] How it works: Data is sent asynchronously from the device to the server, and the transmission status is monitored in real time.

[0654] Step 3:

[0655] Data accumulation

[0656] The server stores the received data in a database, where the data is identified for each user and classified as learning data and emotion data.

[0657] Input: Submitted answer data and emotion data

[0658] Output: Learning data and emotion data for each student stored in a database

[0659] How it works: The server uses an appropriate database schema to structure and store data so that it can be queried efficiently.

[0660] Step 4:

[0661] Data analysis

[0662] The server analyzes the accumulated learning data and emotional data using machine learning algorithms (e.g., TensorFlow, PyTorch), which allows the user's learning progress and emotional state to be identified.

[0663] Input: Learning data and emotion data for each student stored in the database

[0664] Output: Learning progress report and emotional state report

[0665] How it works: Machine learning algorithms analyze data and update models for each user. Results are displayed on a dashboard.

[0666] Step 5:

[0667] Content Generation

[0668] Based on the data analysis results, the server generates learning content (e.g., videos, supplementary materials) appropriate for the user. The content is customized as needed, taking into account emotional data.

[0669] Input: Learning progress report and emotional state report

[0670] Output: Customized learning content

[0671] How it works: Using the analysis results, a generative AI model is used to create content and save it to storage.

[0672] Step 6:

[0673] Content Delivery

[0674] The server delivers the generated learning content to each user's device using a CDN (e.g., AWS CloudFront), and the content is delivered in streaming format.

[0675] Input: Customized learning content

[0676] Output: URL of content that can be played on the user's device

[0677] How it works: Content is streamed and monitored to ensure the connection is not dropped.

[0678] Step 7:

[0679] Comprehension test

[0680] The user takes the comprehension test on the device, which displays the questions and collects the user's answers. Once the answers are completed, they are sent back to the server.

[0681] Input: Assessment questions and user answers

[0682] Output: The test results sent to the server.

[0683] How it works: Test questions are displayed and the user's answers are collected. The answers are sent in real time to a server and stored in an answer database.

[0684] Step 8:

[0685] reanalysis

[0686] The server then analyzes the collected answer data again to determine the user's latest learning comprehension and emotional state.

[0687] Input: Comprehension test answer data

[0688] Output: Latest learning progress report and emotional state report

[0689] What it does: The analytical model is updated and new progress and emotional states are displayed on the dashboard.

[0690] Step 9:

[0691] Timetable generation

[0692] The server generates an optimal timetable based on collected classroom usage, faculty schedules, and student grades and progress data.

[0693] Inputs: classroom utilization, faculty schedules, grades and progress data

[0694] Output: Generated timetable

[0695] How it works: Generates an optimal timetable based on data and converts it into a format that can be distributed to each device.

[0696] Step 10:

[0697] Timetable distribution

[0698] The server distributes the generated timetable to the terminals of teachers and students.

[0699] Input: Generated timetable

[0700] Output: A timetable that can be displayed on the devices of faculty and students

[0701] How it works: The timetable is sent to the device via push notification or email, and each user can check it.

[0702] The specific processing unit 290 transmits the result of the specific processing to the smart device 14. In the smart device 14, the control unit 46A causes the output device 40 to output the result of the specific processing. The microphone 38B acquires audio indicating a user input regarding the result of the specific processing. The control unit 46A transmits audio data indicating the user input acquired by the microphone 38B to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the audio data.

[0703] The data generation model 58 is a so-called generative AI (Artificial Intelligence). An example of the data generation model 58 is ChatGPT (registered trademark) (Internet search engine).<URL: https: / / openai.com / blog / chatgpt> ), Gemini (registered trademark) (Internet search <url: https: gemini.google.com ?hl="ja">) and other generation AIs. The data generation model 58 is obtained by performing deep learning on a neural network. A prompt including an instruction is input to the data generation model 58, and inference data such as voice data indicating voice, text data indicating text, and image data indicating an image is also input. The data generation model 58 performs inference on the input inference data in accordance with the instruction indicated by the prompt, and outputs the inference result in a data format such as voice data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[0704] In the above embodiment, an example in which the specific process is performed by the data processing device 12 has been given, but the technology of the present disclosure is not limited to this, and the specific process may be performed by the smart device 14.

[0705] [Second embodiment]

[0706] FIG. 3 shows an example of the configuration of a data processing system 210 according to the second embodiment.

[0707] 3, the data processing system 210 includes the data processing device 12 and smart glasses 214. An example of the data processing device 12 is a server.

[0708] The data processing device 12 includes a computer 22, a database 24, and a communication I / F 26. The computer 22 is an example of a "computer" according to the technology of the present disclosure. The computer 22 includes a processor 28, a RAM 30, and a storage 32. The processor 28, the RAM 30, and the storage 32 are connected to a bus 34. The database 24 and the communication I / F 26 are also connected to the bus 34. The communication I / F 26 is connected to a network 54. Examples of the network 54 include a WAN (Wide Area Network) and / or a LAN (Local Area Network).

[0709] The smart glasses 214 include a computer 36, a microphone 238, a speaker 240, a camera 42, and a communication I / F 44. The computer 36 includes a processor 46, a RAM 48, and a storage 50. The processor 46, the RAM 48, and the storage 50 are connected to a bus 52. The microphone 238, the speaker 240, and the camera 42 are also connected to the bus 52.

[0710] The microphone 238 receives instructions and the like from the user 20 by receiving voice uttered by the user 20. The microphone 238 captures the voice uttered by the user 20, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio in accordance with instructions from the processor 46.

[0711] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an imaging element such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, and captures images of the surroundings of user 20 (for example, an imaging range defined by an angle of view equivalent to the field of vision of a typical healthy person).

[0712] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 are responsible for the exchange of various information between the processor 46 and the processor 28 via the network 54. The exchange of various information between the processor 46 and the processor 28 using the communication I / Fs 44 and 26 is carried out in a secure state.

[0713] Fig. 4 shows an example of the main functions of the data processing device 12 and the smart glasses 214. As shown in Fig. 4, in the data processing device 12, a specific process is performed by the processor 28. A specific process program 56 is stored in the storage 32.

[0714] The specific processing program 56 is an example of a "program" according to the technology of the present disclosure. The processor 28 reads the specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific 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.

[0715] The storage 32 stores a data generation model 58 and an emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290.

[0716] In the smart glasses 214, the reception output process is performed by the processor 46. A reception output program 60 is stored in the storage 50. 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 process is realized by the processor 46 operating as the control unit 46A in accordance with the reception output program 60 executed on the RAM 48.

[0717] Next, a description will be given of the identification process performed by the identification processing unit 290 of the data processing device 12. 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."

[0718] This invention is an educational environment platform that grasps the learning status of each student, automatically generates and provides appropriate learning content and comprehension tests, and also improves the work efficiency of faculty and staff. This platform consists of a server, terminals (devices used by students and faculty and staff), and users (students and faculty and staff).

[0719] Collection and accumulation of learning data

[0720] Data entry and submission

[0721] User

[0722] Users (students) input answers to daily study questions and comprehension tests into the terminal.

[0723] Terminal

[0724] The device sends the data entered by the student to the server in real time. For example, when a student solves an arithmetic problem and enters the answer into the tablet, the answer is sent directly to the server.

[0725] server

[0726] The server stores the transmitted learning data in a database, which includes information such as answer content, answer time, and accuracy rate.

[0727] Learning content generation and delivery

[0728] Data analysis and content generation

[0729] server

[0730] The server analyzes the collected learning data using machine learning algorithms, which identifies each student's learning progress and weaknesses.

[0731] server

[0732] The server generates learning content (such as videos) based on the analysis results. For example, for students who do not fully understand fractions, it generates a video that explains the basics of fractions in detail.

[0733] Content distribution and viewing

[0734] server

[0735] The server distributes the generated learning content to each student's device, typically via streaming.

[0736] Terminal

[0737] The devices display learning content distributed from the server and allow students to view it. Students can then watch videos on their tablets or computers to deepen their understanding.

[0738] Example: If Student A has difficulty with fractions in mathematics, the server generates a supplementary video on the specific topic of fractions and distributes it to Student A's tablet. Student A watches the video and deepens his understanding of fractions.

[0739] Providing and collecting comprehension tests

[0740] Test question generation and distribution

[0741] server

[0742] The server generates test questions to assess students' understanding, again using machine learning algorithms to set questions that address students' weaknesses.

[0743] server

[0744] The server distributes the generated test questions to the target student terminals.

[0745] Testing and collecting results

[0746] Terminal

[0747] The devices are designed to allow students to take comprehension tests, which they answer on tablets or computers.

[0748] Terminal

[0749] The terminal automatically transmits the answer result to the server.

[0750] server

[0751] The server then re-analyzes the collected answer data to determine the student's most recent understanding.

[0752] Example: Student A takes a fraction comprehension test and sends the answer data to the server. The server analyzes the test results and determines whether the student's understanding of fractions has improved.

[0753] Automatic generation and distribution of timetables

[0754] Timetable data collection and generation

[0755] server

[0756] The server collects data on classroom usage, faculty schedules, and student grades and progress, while also considering special lessons to address student weaknesses.

[0757] server

[0758] The server analyzes the collected data and generates an optimal timetable that reflects the availability of each classroom, teacher availability, and student learning needs.

[0759] Distribution and use of timetables

[0760] server

[0761] The server distributes the generated timetable to the terminals of faculty and students.

[0762] Terminal

[0763] The devices will display the distributed timetable, allowing teachers, staff and students to check it and act according to the schedule.

[0764] Example: Teacher B checks the new timetable and prepares for the next lesson. Student A also checks the time of the next lesson and prepares the necessary teaching materials.

[0765] As described above, the educational environment platform of the present invention enables flexible content distribution according to the learning situation of each student, accurate understanding of their level of understanding, and efficient timetable generation. This promotes efficiency and digitalization throughout the educational field, and makes it possible to provide an optimal learning environment.

[0766] The processing flow will be explained below.

[0767] Collection and accumulation of learning data

[0768] Step 1:

[0769] User

[0770] Students use tablets or computers to enter answers to their daily study questions and homework.

[0771] Step 2:

[0772] Terminal

[0773] The device sends the answer data entered by the student to the server in real time using a secure protocol.

[0774] Step 3:

[0775] server

[0776] The server stores the transmitted learning data in a database, including detailed information such as the student's ID, answer content, answer time, and whether the answer was correct or incorrect.

[0777] Learning content generation and delivery

[0778] Step 1:

[0779] server

[0780] The server analyzes the accumulated learning data using machine learning algorithms, thereby identifying each student's learning progress and weaknesses.

[0781] Step 2:

[0782] server

[0783] The server generates learning content (such as videos) appropriate for each student based on the analysis results. Specifically, it selects educational videos and supplementary materials according to specific themes and customizes them as needed.

[0784] Step 3:

[0785] server

[0786] The server distributes the generated learning content to each student's device in a streaming format, and also supports offline viewing if necessary.

[0787] Step 4:

[0788] Terminal

[0789] The device displays learning content delivered from the server, and students can view and understand specific learning content.

[0790] Providing and collecting comprehension tests

[0791] Step 1:

[0792] server

[0793] The server generates personalized test questions to gauge students' understanding, using machine learning algorithms.

[0794] Step 2:

[0795] server

[0796] The server distributes the generated comprehension test questions to the student's terminal.

[0797] Step 3:

[0798] Terminal

[0799] The device displays questions for students to take comprehension tests, and students enter their answers on a tablet or computer.

[0800] Step 4:

[0801] Terminal

[0802] The device sends the results of the student's answers to the test questions in real time to the server, including not only the answers but also the time and process of answering.

[0803] Step 5:

[0804] server

[0805] The server then analyzes the collected answer data again, thereby gaining an understanding of the students' current learning comprehension and reflecting this in the generation of the next learning content.

[0806] Automatic generation and distribution of timetables

[0807] Step 1:

[0808] server

[0809] The server collects staffing data, classroom utilization, faculty schedules, and student grades and progress data.

[0810] Step 2:

[0811] server

[0812] The server analyzes the collected data and generates an optimal timetable, taking into account classroom availability, teacher availability, and student learning needs.

[0813] Step 3:

[0814] server

[0815] The server distributes the generated timetable to the terminals of faculty and students.

[0816] Step 4:

[0817] Terminal

[0818] The terminal displays the distributed timetable, allowing teachers to prepare for class, while students check the time and content of their next class.

[0819] Through the specific processing steps described above, the present invention achieves efficiency and digitalization in educational settings. By providing content suited to each student's learning situation, enabling appropriate comprehension assessment, and enabling the automatic generation of efficient timetables, the aim is to improve the quality of education and reduce the workload of teachers and staff.

[0820] Example 1

[0821] Next, a description will be given of Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the smart glasses 214 will be referred to as a "terminal."

[0822] In today's educational environment, there is a need to closely grasp each student's learning situation and provide appropriate learning content based on that understanding. However, conventional methods often provide uniform learning materials to a large number of students, making it difficult to flexibly respond to each student's level of understanding and progress. Furthermore, the workload of teachers and staff is increasing, making efficiency an urgent need. Furthermore, insufficient collection and analysis of learning data makes it difficult to provide individualized support. The present invention aims to solve these problems and improve the efficiency of the entire educational environment while providing learning content optimized for each student.

[0823] The specific processing by the specific processing unit 290 of the data processing device 12 in the first embodiment is realized by the following means.

[0824] In this invention, the server includes: means for collecting answer data from learners' devices; means for transmitting the collected answer data to the server in real time; means for storing the transmitted answer data in a database; means for analyzing the accumulated learning data using a machine learning algorithm; means for generating learning content suitable for the learner based on the analysis results; means for distributing and displaying the generated learning content to the learner's device; means for generating test questions for assessing comprehension; means for distributing the generated test questions to the learner's device; means for transmitting answer data answered by the learner on his / her device to the server; means for reanalyzing the transmitted answer data and understanding the learner's learning situation; means for collecting data on school classroom usage, teacher schedules, and learner grades and progress; means for generating an optimal class schedule based on the collected data; and means for distributing the generated class schedule to the teacher's and learner's devices. This enables the provision of optimized educational content based on individual learner data and improves the efficiency of the entire educational environment.

[0825] "Student's device" refers to an electronic device (e.g., tablet, PC, smartphone, etc.) used by a learner, which can input learning data, view learning content, and take comprehension tests.

[0826] "Answer data" refers to data that includes the answers entered by a learner to study questions and comprehension tests.

[0827] The "server" is a central computer system that receives data sent from learners' devices and stores, analyzes, and distributes the data.

[0828] A "database" is a storage device installed on a server that organizes and stores data in an organized manner and manages it so that it can be easily accessed later.

[0829] A "machine learning algorithm" is a computer program that automatically analyzes collected data and performs pattern recognition and predictions.

[0830] "Learning Content" refers to educational materials and learning materials (e.g., video, audio, written text, interactive questions, etc.) provided to support learners' learning.

[0831] A "comprehension test" is a test or question provided to measure a learner's proficiency or comprehension.

[0832] "Classroom usage status" is information indicating the time periods during which each classroom in a school is available for use or in use.

[0833] "Teacher schedule" is information including the timetable of each teacher's working hours, class schedule, meeting schedule, etc.

[0834] "Student performance" refers to data that indicates the academic achievements that a student has made to date.

[0835] "Progress data" refers to data that indicates the learner's learning situation, progress, and state of progress.

[0836] A "timetable" is a table or list that shows students and teachers the schedule of their lessons and activities.

[0837] "Distribution" refers to the act of transmitting generated data or content to a specific terminal or user.

[0838] This invention is an educational environment platform that grasps the learning status of each student, automatically generates and provides appropriate learning content and comprehension tests, and also improves the work efficiency of faculty and staff. This platform consists of a server, terminals (devices used by students and faculty and staff), and users (students and faculty and staff).

[0839] Collection and accumulation of learning data

[0840] Data entry and submission

[0841] Students, who are users, input their daily study questions and comprehension tests into their own devices. For example, a student solves an arithmetic problem and enters the answer into a tablet. This answer data is sent to the server in real time by the device. The server then stores the sent learning data in a database. This data includes the answer content, answer time, accuracy rate, etc.

[0842] Learning content generation and delivery

[0843] Data analysis and content generation

[0844] The server analyzes the accumulated learning data using machine learning algorithms. This analysis identifies each student's learning status and weaknesses. For example, the server might determine that "Student A is struggling with fraction problems."

[0845] The server then generates learning content based on the analysis, including videos and interactive exercises, such as a video explaining the basics of fractions.

[0846] Content distribution and viewing

[0847] The server distributes the generated learning content to each student's device. This distribution is in streaming format. The device plays the distributed learning content so that the student can view it. For example, a student can view "Frequency Fundamentals" on a tablet to deepen their understanding.

[0848] Providing and collecting comprehension tests

[0849] Test question generation and distribution

[0850] The server generates test questions to assess students' understanding. This also uses machine learning algorithms to create questions tailored to each student's weaknesses. For example, it generates new fraction questions in a specific format. The generated test questions are then distributed to each student's device.

[0851] Testing and collecting results

[0852] The student user takes a comprehension test on their device. For example, they answer questions on a tablet to measure their "understanding of fractions." The device sends the test results to the server in real time. The server reanalyzes these test results and keeps track of the student's latest understanding.

[0853] Automatic generation and distribution of timetables

[0854] Timetable data collection and generation

[0855] The server collects data on classroom usage, faculty schedules, and student performance and progress. This data includes classroom availability, teacher availability, and student learning needs. The server analyzes the collected data and generates an optimal timetable.

[0856] Distribution and use of timetables

[0857] The server distributes the generated timetable to the terminals of faculty and students. The terminals display the distributed timetable so that faculty and students can check it. For example, faculty and staff check the timetable to prepare for the next class, and students also check the time of the next class and prepare the necessary teaching materials.

[0858] Specific examples

[0859] If it is determined that Student A's understanding of fractions is insufficient, the server uses a machine learning algorithm to generate an explanatory video on fractions tailored to the student and distributes it to Student A's tablet. Student A watches the video to deepen his or her understanding. Student A is then given a fraction comprehension test, and the results are sent to the server, which then provides appropriate learning content based on the analysis results.

[0860] Prompt Sentence Examples

[0861] Below are some example prompts to input to a generative AI model:

[0862] "Please use this AI model to design a system that collects and analyzes student learning data and generates and delivers individualized learning content. Specifically, I would like to build an educational environment platform that generates comprehension tests, collects and analyzes the results, and automatically generates appropriate timetables."

[0863] As described above, the educational environment platform of the present invention can flexibly distribute content according to each student's learning situation, accurately grasp their level of understanding, and generate efficient timetables. This will promote efficiency and digitalization throughout the educational field, and make it possible to provide an optimal learning environment.

[0864] The flow of the identification process in the first embodiment will be described with reference to FIG.

[0865] Step 1:

[0866] Input of training data

[0867] The user (student) inputs daily study questions and comprehension tests into the terminal. For example, a student inputs answers to math problems. This input data includes the answer content and answer time entered by the student. The input data is sent to the next step.

[0868] Input: Answer data entered by the student into the device (answer content, answer time)

[0869] Output: Answer data saved on the device

[0870] Step 2:

[0871] Sending training data

[0872] The terminal transmits the answer data entered by the student to the server in real time. For example, the terminal transfers the answer data to the server via the network. This data includes the answer content and the answer time.

[0873] Input: Answer data saved on the device

[0874] Output: Answer data sent to the server

[0875] Step 3:

[0876] Accumulation of learning data

[0877] The server receives the submitted answer data and stores it in a database. This data includes the answer content, answer time, and correct answer rate. The server stores the data in the database so that it can be used for future processing.

[0878] Input: Answer data sent to the server (answer content, answer time, correct answer rate)

[0879] Output: Answer data stored in the database

[0880] Step 4:

[0881] Data analysis

[0882] The server analyzes the accumulated answer data using a machine learning algorithm. This analysis identifies the student's learning status and weaknesses. For example, the server analyzes that Student A is struggling with fraction problems.

[0883] Input: Answer data stored in the database

[0884] Output: Analysis results (student weaknesses and learning status)

[0885] Step 5:

[0886] Generating learning content

[0887] The server generates learning content based on the analysis results, including instructional videos and interactive exercises. For example, it generates a video explaining the basics of fractions.

[0888] Input: Analysis results

[0889] Output: Generated learning content

[0890] Step 6:

[0891] Delivery of learning content

[0892] The server then distributes the generated learning content to the learner's device. This distribution is done in streaming format. The server distributes the most suitable content to each learner in a timely manner.

[0893] Input: Generated learning content

[0894] Output: Learning content delivered to the learner's device

[0895] Step 7:

[0896] Viewing content

[0897] The device plays learning content distributed from the server and allows learners to view it. For example, a student can watch a video explaining fractions on a tablet.

[0898] Input: Learning content delivered to your device

[0899] Output: Learning content viewed by the learner

[0900] Step 8:

[0901] Generate comprehension tests

[0902] The server generates test questions to assess students' understanding. It uses machine learning algorithms to create questions tailored to students' weaknesses, for example, generating fraction questions in a specific format.

[0903] Input: Analysis results

[0904] Output: Generated assessment questions

[0905] Step 9:

[0906] Comprehension test distribution

[0907] The server distributes the generated test questions to the learner's terminal, which displays the test questions in an appropriate format.

[0908] Input: Generated assessment questions

[0909] Output: Comprehension test questions delivered to the learner's device

[0910] Step 10:

[0911] Comprehension test

[0912] The user (student) takes a comprehension test on the device. For example, the student answers a fraction comprehension test on a tablet.

[0913] Input: Comprehension test questions delivered to the learner's device

[0914] Output: Answered comprehension test data

[0915] Step 11:

[0916] Sending test results

[0917] The device sends test results in real time to a server, including the percentage of correct answers and response time.

[0918] Input: Answered comprehension test data

[0919] Output: Test results sent to the server

[0920] Step 12:

[0921] Analyzing test results

[0922] The server re-analyzes the test results and determines the latest learning status. For example, the server determines whether Student A's understanding of fractions has improved.

[0923] Input: Test results sent to the server

[0924] Output: Reanalysis results (latest learning status)

[0925] Step 13:

[0926] Collection of timetable data

[0927] The server collects data on the school's classroom usage, teacher schedules, and student performance and progress, including classroom availability, teacher availability, and student learning needs.

[0928] Input: Various data (classroom usage, teacher schedules, student grades and progress data)

[0929] Output: Collected timetable data

[0930] Step 14:

[0931] Generating optimal timetables

[0932] The server generates an optimal timetable based on the collected data, for example, one that reflects the available time of each classroom, the free time of teachers, and the learning needs of students.

[0933] Input: Collected timetable data

[0934] Output: Generated optimal timetable

[0935] Step 15:

[0936] Timetable distribution

[0937] The server distributes the generated timetable to the devices of faculty and students. The devices display the distributed timetable so that faculty and students can check it. For example, faculty and students check the new timetable to prepare for the next class, and students also check the time of the next class and prepare the necessary teaching materials.

[0938] Input: Generated optimal timetable

[0939] Output: Timetables distributed to faculty and student devices

[0940] The above is the specific flow of program processing for this system.

[0941] (Application example 1)

[0942] Next, a description will be given of Application Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the smart glasses 214 will be referred to as a "terminal."

[0943] Conventional educational platforms face the challenge of making it difficult to provide personalized learning content tailored to each student's learning situation. In particular, generating and delivering appropriate content based on the student's level of understanding, as well as providing effective feedback, is time-consuming, hindering the efficiency of classrooms. It is also not easy to optimize timetables based on each student's learning progress and weaknesses. Therefore, there is a need for a system that can provide a learning environment tailored to each student's needs and reduce the workload of teachers.

[0944] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 1 is realized by the following means.

[0945] In this invention, the server includes: means for storing learning data collected from learning institutions nationwide in a database; means for analyzing the learning data stored in the database; means for generating learning content appropriate for each user based on the analysis results; means for distributing the generated learning content to each user's device; means for generating questions to test each user's level of comprehension; means for distributing the generated comprehension test questions to the device and collecting user answer data; means for re-analyzing the user's learning status based on the collected answer data; means for generating an optimal timetable based on classroom usage status, faculty schedules, and user grades and progress data; means for distributing the generated timetable to faculty and user devices; and means for using a generative AI model to generate personalized learning content and distributing the learning content to each user's device using prompts. This enables the automatic generation and distribution of learning content tailored to each student's level of comprehension, thereby improving the efficiency of education and student comprehension.

[0946] "Learning institutions" refers to all educational institutions, and is a general term for institutions that provide education such as elementary schools, junior high schools, high schools, universities, and vocational schools.

[0947] "Learning data" refers to information about a student's learning status, including digital data such as answer content, answer time, and correct answer rate.

[0948] A "database" is a system for systematically managing collected information and performing operations such as storage, search, and analysis.

[0949] "Analysis" is the process of processing collected data using methods and algorithms to obtain information for a specific purpose.

[0950] "Learning content" is a general term for teaching materials and resources used for educational purposes, including videos, texts, quizzes, etc.

[0951] A "terminal" is a digital device or equipment used by a user, such as a smartphone, tablet, or PC.

[0952] A "comprehension test" is a test to evaluate a student's level of comprehension of the learning content, and is given in the form of questions.

[0953] "Answer data" refers to a digital record of a student's answers to tests and questions.

[0954] A "timetable" is a table that shows the schedule of an educational institution or individual student, including the times and contents of classes.

[0955] A "generative AI model" is a collection of algorithms and programs that use artificial intelligence technology to automatically generate learning content and test questions.

[0956] A "prompt sentence" is an input sentence or command that gives a generative AI model specific instructions or requests.

[0957] This invention builds a system for providing an efficient and personalized learning environment in educational settings. This system uses the following hardware and software to collect and analyze various data, and then generates and distributes appropriate learning content.

[0958] Hardware

[0959] Server: A high-performance computer that can be cloud-based or on-premise.

[0960] Device: The device used by the user, such as a smartphone, tablet, or computer.

[0961] software

[0962] Mobile applications: Cross-platform applications developed using React Native or Flutter.

[0963] Server side: Built using Django and Node.js. PostgreSQL database is used.

[0964] Machine learning algorithms: TensorFlow and PyTorch are used for analysis. FFmpeg and OpenCV are used for video generation.

[0965] Data collection and storage

[0966] User: When students answer questions on their smartphones or tablets, the answer data is sent to the server in real time.

[0967] Server: The transmitted learning data is stored in a database, including answer content, answer time, and accuracy rate.

[0968] Data analysis and learning content generation

[0969] Server: Analyzes accumulated learning data using machine learning algorithms to identify each student's learning situation and weaknesses.

[0970] Server: Generates personalized learning content based on the analysis results. This uses a generative AI model to generate videos and text based on specific prompts. The generated content is saved in the appropriate format (video, text, etc.).

[0971] Content distribution and viewing

[0972] Server: The server distributes the generated learning content to each student's device using streaming technology.

[0973] Devices: Students can view and understand the learning content delivered on tablets and computers.

[0974] Providing comprehension tests and analyzing results

[0975] Server: Generates test questions to assess comprehension and distributes them to each student's device.

[0976] Device: Students answer test questions on their devices. The answer data is automatically sent to the server.

[0977] Server: Re-analyzes the collected answer data and updates the student's learning status.

[0978] Automatic generation and distribution of timetables

[0979] Server: Analyzes classroom usage, faculty schedules, and student grades and progress data to generate optimal timetables.

[0980] Server: Distributes the generated timetable to the terminals of faculty and students.

[0981] Terminals: Used by faculty and students to check upcoming lesson times and content.

[0982] Examples and prompts

[0983] For example, a user (student) solves a problem on "mathematical fractions" and sends the answer data to the server. The server analyzes the data and determines that the user lacks understanding of fractions. Next, it uses a generative AI model to generate a "video explaining the basics of fractions" and distributes it to the user. An example of a prompt sentence used in this case is, "This user's understanding of fractions is lacking. Please generate video teaching materials to help them understand the basics of fractions."

[0984] This system makes it possible to automatically generate and distribute learning content tailored to each user's level of understanding, thereby improving the efficiency of the classroom and the students' level of understanding.

[0985] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[0986] Step 1:

[0987] Data collection and transmission

[0988] Input: Data on the study questions answered by the user (student) on the device (answer content, answer time, correct answer rate)

[0989] How it works: When a user answers a study question on a smartphone or tablet, the data is sent to the server in real time. The application prompts the user to enter the answer, and once the answer is completed, the information is transferred to the server in JSON format.

[0990] Output: Answer data sent to the server

[0991] Step 2:

[0992] Data accumulation

[0993] Input: Answer data submitted in Step 1

[0994] Specific operation: The server stores the received answer data in a database using PostgreSQL, and the answer data is organized and saved in a table.

[0995] Output: Answer data stored in the database

[0996] Step 3:

[0997] Data analysis

[0998] Input: Answer data stored in the database

[0999] Specific operation: The server analyzes the answer data using machine learning algorithms (TensorFlow and PyTorch). This analysis identifies each student's learning status and weaknesses. Python is used for data analysis, and the learning status is quantified and evaluated.

[1000] Output: Analysis results (each student's level of understanding and weaknesses)

[1001] Step 4:

[1002] Learning content generation

[1003] Input: Analysis results obtained in step 3

[1004] Specific operation: The server uses the generative AI model to generate learning content (videos and text) based on the prompt. For example, a prompt such as "This user's understanding of fractions is insufficient. Please generate video materials to help them understand the basics of fractions" is input into the AI ​​model, and a video with the corresponding learning content is generated.

[1005] Output: Generated learning content (videos, text)

[1006] Step 5:

[1007] Content Delivery

[1008] Input: Learning content generated in Step 4

[1009] Specific operation: The server delivers the generated learning content to each user's device. The delivery format is mainly streaming, and the server notifies the user using Firebase Cloud Messaging or similar and provides the content URL.

[1010] Output: Learning content delivered to the user's device

[1011] Step 6:

[1012] Test generation and delivery

[1013] Input: Analysis results obtained in step 3

[1014] Specific operation: The server generates test questions to evaluate the user's level of understanding and distributes them to the device. The generated test questions are converted into JSON format and sent to the device via push notification.

[1015] Output: Comprehension test questions delivered to the user's device

[1016] Step 7:

[1017] Conducting comprehension tests and collecting results

[1018] Input: Comprehension test questions delivered in Step 6

[1019] Specific operation: The user answers the test questions on the device, and the answer data is sent to the server again in real time in JSON format.

[1020] Output: Test answer data sent to the server

[1021] Step 8:

[1022] Reanalysis and feedback

[1023] Input: Test response data collected in Step 7

[1024] Specific operation: The server analyzes the collected answer data again to grasp the student's latest learning situation. Based on the analysis results, it determines whether new learning content is necessary.

[1025] Output: Analysis results based on the latest learning status

[1026] Step 9:

[1027] Timetable generation and distribution

[1028] Input: User grades, progress data, classroom usage, faculty schedules

[1029] Specific operation: The server generates an optimal timetable based on the above data. The generated timetable is distributed to each user and faculty member via their terminal.

[1030] Output: Timetable distributed to each user and faculty terminal

[1031] Furthermore, an emotion engine that estimates the user's emotion may be further combined. That is, the identification processing unit 290 may estimate the user's emotion using the emotion identification model 59, and perform identification processing using the user's emotion.

[1032] This invention is a system that combines an emotion engine with an educational environment platform that grasps each student's learning situation and automatically generates and provides appropriate learning content and comprehension tests. This makes it possible to grasp students' emotional states, improve the learning experience, and increase educational efficiency. This platform consists of a server, terminals (devices used by students and faculty), and users (students and faculty).

[1033] Collection and storage of learning data and emotion data

[1034] Data entry and submission

[1035] User

[1036] Students use tablets or computers to input answers to daily study questions and homework, and emotional data is automatically collected through facial expressions and voice.

[1037] Terminal

[1038] Terminal

[1039] The device transmits the answer data and emotion data entered by the student to the server in real time using a secure protocol.

[1040] server

[1041] server

[1042] The server stores the transmitted learning data and emotional data in a database, including detailed information such as the student's ID, answer content, answer time, correct or incorrect answers, and emotional state.

[1043] Learning content generation and delivery

[1044] Data analysis and content generation

[1045] server

[1046] The server analyzes the accumulated learning and emotional data using machine learning algorithms to identify each student's learning progress, weaknesses, and emotional state.

[1047] server

[1048] The server then generates learning content (such as videos) tailored to each student based on the analysis results. For example, it selects educational videos and supplemental materials tailored to specific themes and customizes them as needed. Emotional data is also taken into account, so if a student is feeling anxious, content is generated that includes clearer explanations and encouraging messages.

[1049] Content distribution and viewing

[1050] server

[1051] The server distributes the generated learning content to each student's device in a streaming format, and also supports offline viewing if necessary.

[1052] Terminal

[1053] The device displays learning content delivered from the server, and students can view and understand specific learning content.

[1054] Example: If Student A has difficulty with fractions in mathematics and shows signs of anxiety while studying, the server generates a supplementary video on the specific topic of fractions, including an encouraging message. This video is then distributed to Student A's tablet, and Student A watches it, deepening his understanding of fractions and feeling reassured.

[1055] Providing and collecting comprehension tests

[1056] Test question generation and distribution

[1057] server

[1058] The server generates personalized test questions to gauge students' understanding, using machine learning algorithms based on learning and sentiment data.

[1059] server

[1060] The server distributes the generated comprehension test questions to the student's terminal.

[1061] Testing and collecting results

[1062] Terminal

[1063] The device displays questions for students to take comprehension tests, and students enter their answers on a tablet or computer.

[1064] Terminal

[1065] The device sends the student's answers to the test questions in real time to the server, including not only the answers but also the emotional responses they gave while answering.

[1066] server

[1067] The server then performs a second analysis based on the collected answer data and emotion data, thereby gaining an understanding of the student's current learning comprehension and emotional state, which is then reflected in the generation of the next learning content.

[1068] Example: When Student B takes a comprehension test, if he takes a long time to answer and looks confused, the server can analyze the data to identify the areas where Student B's understanding is lacking and generate questions for the next test to reinforce those areas.

[1069] Automatic generation and distribution of timetables

[1070] Timetable data collection and generation

[1071] server

[1072] The server collects staffing data, classroom utilization, faculty schedules, student grades and progress data, and sentiment data.

[1073] server

[1074] The server analyzes the collected data and generates an optimal timetable that takes into account classroom availability, teacher availability, student learning needs, and emotional state.

[1075] Distribution and use of timetables

[1076] server

[1077] The server distributes the generated timetable to the terminals of faculty and students.

[1078] Terminal

[1079] The terminal displays the distributed timetable, allowing teachers to prepare for class, while students check the time and content of their next class.

[1080] Example: Teacher C checks the new timetable and prepares for the next lesson. Student A also checks the time of the next lesson and prepares the necessary materials. Based on Student A's emotional data, relaxing lessons and activities are incorporated during times of particularly high stress.

[1081] As described above, the educational environment platform of the present invention provides flexible content and assessment of comprehension according to each student's learning situation and emotional state, and automatically generates efficient timetables. This promotes efficiency and digitalization throughout the entire educational environment, making it possible to provide an optimal learning environment.

[1082] The processing flow will be explained below.

[1083] Collection and storage of learning data and emotion data

[1084] Step 1:

[1085] User

[1086] Students use tablets or PCs to input answers to study questions and homework, and their facial expressions and voice data are automatically collected by the emotion engine while they are studying.

[1087] Step 2:

[1088] Terminal

[1089] The device transmits the answer data entered by the student and the collected emotion data to the server in real time, using a security protocol.

[1090] Step 3:

[1091] server

[1092] The server stores the submitted answer data and emotional data in a database, which contains information on the student's ID, answer content, answer time, correct / incorrect answers, and emotional state.

[1093] Learning content generation and delivery

[1094] Step 1:

[1095] server

[1096] The server analyzes the accumulated learning and emotional data using machine learning algorithms to identify students' learning progress, weaknesses, and emotional patterns.

[1097] Step 2:

[1098] server

[1099] The server generates learning content (e.g., videos) appropriate for the student based on the analysis results. For example, if a student is having trouble in a particular area, it generates a detailed explanatory video on that area. It also takes into account the student's emotional state and includes messages to ease anxiety.

[1100] Step 3:

[1101] server

[1102] The server distributes the generated learning content to students' devices. The distribution format is primarily streaming, but offline viewing is also supported if necessary.

[1103] Step 4:

[1104] Terminal

[1105] The device displays the delivered learning content to the students, who can then view and understand the content.

[1106] Example: If Student A feels uncomfortable with fraction problems in mathematics, the server generates a video with a detailed explanation of fractions and a message of encouragement, and distributes it to Student A's tablet. Student A watches this video, deepens his understanding of fractions, and reduces his anxiety about learning.

[1107] Providing and collecting comprehension tests

[1108] Step 1:

[1109] server

[1110] The server generates test questions to measure students' comprehension using machine learning algorithms based on training data and emotional data.

[1111] Step 2:

[1112] server

[1113] The server distributes the generated comprehension test questions to the student's terminal.

[1114] Step 3:

[1115] Terminal

[1116] The device displays questions for students to take comprehension tests, and students enter their answers on a tablet or computer.

[1117] Step 4:

[1118] Terminal

[1119] The terminal transmits the content of the answer and the emotion data in the answer to the server in real time.

[1120] Step 5:

[1121] server

[1122] The server analyzes the collected answer data and emotional data to grasp the latest learning comprehension and emotional state, and generates the next learning content and comprehension test based on the analysis results.

[1123] Example: If Student B shows signs of confusion or anxiety while taking a comprehension test, the server analyzes the data and identifies the areas where Student B is having difficulty. The next test will include reinforcement questions specific to those areas.

[1124] Automatic generation and distribution of timetables

[1125] Step 1:

[1126] server

[1127] The server collects classroom usage, faculty schedules, student grades and progress data, and sentiment data.

[1128] Step 2:

[1129] server

[1130] The server analyzes the collected data and generates an optimal timetable that takes into account classroom availability, faculty availability, students' learning needs, and emotional state.

[1131] Step 3:

[1132] server

[1133] The server distributes the generated timetable to the terminals of faculty and students.

[1134] Step 4:

[1135] Terminal

[1136] The terminals display the distributed timetable, which teachers and students can check. Teachers prepare for the lesson, and students check the time and content of the next lesson.

[1137] Example: Staff member C checks the new timetable and prepares for the next lesson. Based on emotional data, relaxing lessons and activities are scheduled during particularly stressful times. Student A also checks the timetable and prepares the necessary materials.

[1138] As described above, the present invention provides a system that improves students' learning efficiency and education quality by combining emotion engines. It realizes an individually optimized learning environment for each student through content distribution, test evaluation, and timetable generation based on the learning situation and emotional state.

[1139] Example 2

[1140] Next, a description will be given of Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the smart glasses 214 will be referred to as a "terminal."

[1141] Conventional educational systems have difficulty efficiently grasping the progress and level of understanding of individual learners and providing appropriate learning content. Furthermore, they are unable to take into account the learner's emotional state, making it difficult to provide an educational environment that maximizes the effectiveness of learning. This leads to a decline in learner motivation and delays in learning progress, resulting in the inability to fully realize the effectiveness of education.

[1142] The specific processing by the specific processing unit 290 of the data processing device 12 in the second embodiment is realized by the following means.

[1143] In this invention, the server includes a means for storing learning data and emotional data collected from educational institutions nationwide in a database, a means for analyzing the stored learning data and emotional data, and a means for generating learning content appropriate for each learner based on the analysis results. This makes it possible to provide optimal learning content and create an efficient learning environment by taking into account the progress and emotional state of each individual learner.

[1144] "Learning data" refers to data collected by educational institutions, such as a learner's learning history, grades, progress, and answer content.

[1145] "Emotion data" is data that indicates the emotional state of a learner, obtained from their facial expressions and voice.

[1146] A "database" is a system for systematically storing and managing collected learning data and emotional data.

[1147] "Analysis" refers to the use of machine learning algorithms to analyze collected data and identify learners' progress, level of understanding, and emotional state.

[1148] "Learning content" refers to educational materials, videos, and supplementary materials that are customized according to the learner's progress and level of understanding.

[1149] "Devices" are electronic devices such as tablets and computers used by learners and faculty and staff.

[1150] A "machine learning algorithm" is a computer program used to perform analysis based on collected data, and can utilize libraries such as TensorFlow and Scikit-learn.

[1151] A "comprehension test" is a test question that measures a learner's level of comprehension and is customized for each individual.

[1152] A "timetable" is a schedule that is optimally organized taking into account classroom usage, faculty and staff schedules, learners' grades and progress data, and emotional data.

[1153] "Educational institutions" refers to facilities and organizations that carry out educational activities, such as schools and cram schools.

[1154] This invention provides an educational platform that analyzes collected learning data and emotional data, and automatically generates and delivers learning content and comprehension tests appropriate for each learner. This system includes a server, terminals (devices used by learners and faculty), and users (learners and faculty). The following describes how to specifically implement this system.

[1155] Data collection and transmission

[1156] User

[1157] Learners use tablets or PCs to input answers to daily study questions and homework assignments, and emotional data is automatically collected through the learner's facial expressions and voice.

[1158] Terminal

[1159] The device transmits the answer data and emotion data entered by the student to the server in real time using a secure protocol (e.g., HTTPS).

[1160] Data accumulation

[1161] server

[1162] The server stores the learning data and emotional data sent from the device in a database. This database uses MySQL, PostgreSQL, etc. This data includes the learner's ID, answer content, answer time, correct or incorrect answers, emotional state, etc.

[1163] Data analysis and content generation

[1164] server

[1165] The server analyzes the accumulated learning data and emotional data using machine learning algorithms such as Python's TensorFlow and Scikit-learn, thereby identifying each learner's learning progress, weaknesses, and emotional state.

[1166] server

[1167] The server generates learning content appropriate for each learner based on the analysis results. For example, if a learner is weak in a particular topic, it provides supplementary learning materials or educational videos on that topic. Furthermore, it generates content that includes encouraging messages for learners who are feeling anxious.

[1168] Content distribution and viewing

[1169] server

[1170] The server distributes the generated learning content to the learner's device using streaming technology such as HLS (HTTP Live Streaming).

[1171] Terminal

[1172] The terminal displays the learning content delivered from the server, and the learner watches and listens to it to understand the learning content.

[1173] Example: If Learner A has difficulty with fractions in mathematics and shows signs of anxiety while studying, the server generates a supplementary video explaining fractions and includes an encouraging message. This video is then distributed to Learner A's tablet, and Learner A watches it, deepening his understanding of fractions and feeling reassured.

[1174] Providing comprehension tests and collecting results

[1175] server

[1176] The server generates test questions based on the learning data and emotion data to measure the learner's level of understanding.

[1177] server

[1178] The server distributes the generated comprehension test questions to the learner's terminal.

[1179] Terminal

[1180] The device displays questions so that learners can take comprehension tests, and learners enter their answers on a tablet or computer.

[1181] Terminal

[1182] The device transmits the learner's test results and emotional data during the response to the server in real time.

[1183] Comprehension test analysis

[1184] server

[1185] The server reanalyzes the collected answer data and emotion data to grasp the learner's latest learning comprehension and emotional state. This information is reflected in the generation of the next learning content. The analysis is performed using the Python Pandas library.

[1186] Example: When Learner B takes a comprehension test, if he looks confused and takes a long time to answer a particular question, the server will analyze that data and generate questions for the next test that will help Learner B to fill in the gaps in his understanding.

[1187] Automatic generation and distribution of timetables

[1188] server

[1189] The server collects staffing data, classroom usage, faculty schedules, student grades and progress data, and emotional data to generate an optimal timetable.

[1190] server

[1191] The server distributes the generated timetable to the terminals of teachers and students.

[1192] Terminal

[1193] The terminal displays the distributed timetable, allowing teachers to prepare for lessons and students to check the time and content of their next lesson.

[1194] Example: Faculty member C checks the new timetable and prepares for the next lesson. Learner A also checks the time of the next lesson and prepares the necessary materials. Based on Learner A's emotional data, lessons and activities that help him relax are incorporated during times when he is feeling particularly stressed.

[1195] Prompt Sentence Examples

[1196] How do you collect and analyze student learning and emotion data?

[1197] Explain how to generate optimal learning content taking into account learning progress and emotional state.

[1198] What is the process for automatically generating tests to effectively assess student understanding?

[1199] The flow of the identification process in the second embodiment will be described with reference to FIG.

[1200] Step 1: Enter and submit data

[1201] User

[1202] Learners use tablets or computers to input their daily homework and answers to study questions, and their facial expressions and voice data are automatically captured while they study via cameras and microphones.

[1203] Input: Learner's answer data (answer content, answer time, correct / incorrect) and emotional data (facial expression, voice)

[1204] Output: Input answer data and emotion data

[1205] Terminal

[1206] The device sends the input answer data and emotion data to the server in real time using the HTTPS protocol to ensure data security.

[1207] Input: Learner's answer data and emotion data

[1208] Output: Answer data and emotion data sent to the server

[1209] Step 2: Accumulating data

[1210] server

[1211] The server stores the learning data and emotional data sent from the device in a relational database (e.g., MySQL or PostgreSQL). The database appropriately stores metadata such as the learner's ID, answer content, answer time, correct or incorrect answers, and emotional state.

[1212] Input: Submitted training data and emotion data

[1213] Output: Learning data and emotion data stored in the database

[1214] Step 3: Analyze the data

[1215] server

[1216] The server runs machine learning algorithms using Python's TensorFlow and Scikit-learn to analyze the accumulated learning data and emotional data, identifying each learner's learning progress, weaknesses, and emotional state. The analysis process also includes data preprocessing (e.g., normalization, missing value imputation).

[1217] Input: Accumulated learning data and emotion data

[1218] Output: Analysis of progress, weaknesses, and emotional state of each learner

[1219] Step 4: Generate learning content

[1220] server

[1221] The server generates learning content appropriate for each learner based on the analysis results. This content includes educational videos, supplementary materials, encouraging messages, etc. For example, if a learner is anxious about a particular topic, content including a detailed explanatory video on that topic and encouraging messages will be generated.

[1222] Input: Analysis results (learning progress, weaknesses, emotional state)

[1223] Output: Generated learning content

[1224] Step 5: Deliver your content

[1225] server

[1226] The server distributes the generated learning content to the learner's device. Streaming technology (e.g., HLS) is used for distribution. The distributed data is sent in a format appropriate for each learner's device. At the same time, it is cached in a format that allows for offline viewing.

[1227] Input: Generated learning content

[1228] Output: Learning content delivered to the learner's device

[1229] Terminal

[1230] The device receives the learning content distributed from the server and displays it for the learner to view, allowing the learner to acquire new knowledge and resolve any concerns they may have.

[1231] Input: Delivered learning content

[1232] Output: View and play learning content

[1233] Step 6: Provide a test

[1234] server

[1235] The server generates individually customized comprehension test questions to measure the learner's level of comprehension, using machine learning algorithms and analysis results based on learning data and emotional data.

[1236] Input: Analysis results, training data, emotion data

[1237] Output: Generated assessment questions

[1238] server

[1239] The server distributes the generated comprehension test questions to the learner's terminal.

[1240] Input: Generated assessment questions

[1241] Output: Comprehension test questions delivered to the learner's device

[1242] Step 7: Collect and analyze test results

[1243] Terminal

[1244] The device displays questions so that learners can take comprehension tests, and learners enter their answers on a tablet or computer.

[1245] Input: The displayed assessment question

[1246] Output: Answer data entered by the learner

[1247] Terminal

[1248] The device transmits the learner's test results and emotional data during the response to the server in real time.

[1249] Input: Answer data and emotion data entered by the learner

[1250] Output: Answer data and emotion data sent to the server

[1251] server

[1252] The server analyzes the collected answer data and emotional data. This allows it to grasp the learner's current level of learning comprehension and emotional state. The analysis results are reflected in the generation of the next learning content.

[1253] Input: Collected answer data, emotion data

[1254] Output: Analysis of the learner's comprehension and emotional state

[1255] Step 8: Generate and distribute timetables

[1256] server

[1257] The server collects staffing data, classroom usage, faculty schedules, student performance and progress data, and sentiment data. It analyzes this data to generate an optimal timetable. This analysis utilizes the Google Calendar API and other scheduling systems.

[1258] Inputs: Staffing data, classroom utilization, faculty schedules, learner performance, progress data, sentiment data

[1259] Output: The generated timetable

[1260] server

[1261] The server distributes the generated timetable to the terminals of teachers and students.

[1262] Input: Generated timetable

[1263] Output: Distributed timetable

[1264] Terminal

[1265] The terminal displays the distributed timetable, allowing teachers to prepare for lessons and students to check the time and content of their next lesson.

[1266] Input: Distributed timetable

[1267] Output: Displayed timetable

[1268] (Application example 2)

[1269] Next, a description will be given of Application Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the smart glasses 214 will be referred to as a "terminal."

[1270] Conventional educational environment platforms have difficulty providing appropriate learning content based on each student's learning ability and progress. They also lack a mechanism for understanding the emotional state of students and customers in real time and adjusting learning content accordingly. This has led to problems such as a decline in student motivation and a drop in customer satisfaction. Furthermore, it has been difficult to provide information tailored to individual needs when dealing with customers in virtual stores. To solve these issues, a system is needed that can understand the emotional state of students and provide learning content and information appropriate to that situation.

[1271] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 2 is realized by the following means.

[1272] In this invention, the server includes: means for storing learning data collected from educational institutions nationwide in a database; means for analyzing the learning data stored in the database; means for generating learning content appropriate for each learner based on the analysis results; means for distributing the generated learning content to each learner's terminal; means for generating questions to test each learner's level of comprehension; means for distributing the generated comprehension test questions to the terminal and collecting learner answer data; means for re-analyzing the learner's learning status based on the collected answer data; means for collecting learner emotional data and adjusting the learning content based on that data; means for generating and distributing learning content for customers in a virtual store; means for analyzing the customer's emotional state and providing interactive content based on the analyzed data; means for generating an optimal class schedule based on classroom usage, faculty schedules, and learner grades and progress data; and means for distributing the generated class schedule to faculty and learner terminals. This enables flexible content provision according to the emotional state of learners and customers, thereby improving learning efficiency and customer satisfaction.

[1273] "Educational institutions" is a general term for facilities and organizations that conduct learning activities, including elementary schools, junior high schools, high schools, universities, and vocational schools.

[1274] "Learning data" refers to various data generated by learners through their learning activities, and examples include answer content, correct / incorrect answers, response time, and progress status.

[1275] "Emotional data" refers to data that indicates the emotional state of a learner as analyzed from their facial expressions and voice, and includes, for example, joy, anxiety, confusion, etc.

[1276] "Database" means a system capable of storing, managing, and retrieving large amounts of data in a structured form.

[1277] A "machine learning algorithm" is an algorithm that automatically makes predictions and judgments through learning from data.

[1278] "Learning content" refers to educational materials and information provided to learners, including videos, textbooks, workbooks, interactive learning materials, etc.

[1279] "Device" is a general term for electronic devices used by learners and faculty and staff, including personal computers, tablets, smartphones, etc.

[1280] A "comprehension test" is a test used to assess a learner's level of comprehension, and includes question formats, quizzes, questionnaires, etc.

[1281] "Analysis" refers to the process of collecting, classifying, and processing data to clarify its meaning and characteristics.

[1282] "Virtual store" refers to a virtual store that offers products and services over the Internet.

[1283] "Interactive content" refers to content that requires interaction with users, and includes chatbots, interactive videos, and dialogue training.

[1284] "Timetable" means a table showing the schedule of lessons and activities at an educational institution or program of study.

[1285] "Customer" means a user who intends to purchase or use goods or services in the virtual store.

[1286] "Generated" and "produced" refer to something newly created using a specific algorithm or method.

[1287] This invention relates to an educational environment platform that collects, analyzes, and distributes learning data and emotional data. This platform provides flexible content that takes into account the emotional state of students and customers to improve the learning experience. It also includes a system for grasping the emotional state of customers in a virtual store and providing appropriate information.

[1288] System configuration

[1289] The present invention comprises the following hardware and software components:

[1290] server

[1291] The server has the following functions:

[1292] Database Management:

[1293] Training data and emotion data are stored in a relational database such as MySQL or PostgreSQL.

[1294] Running machine learning algorithms:

[1295] To analyze the collected data, machine learning libraries such as TensorFlow and PyTorch are used.

[1296] Content Generation:

[1297] Based on the analysis results, learning content such as learning videos and supplementary materials is generated, and the generated content is stored in cloud storage such as AWS S3.

[1298] Streaming:

[1299] It provides a streaming service to deliver learning content to each device, using a CDN such as AWS CloudFront.

[1300] Terminal

[1301] The device has the following features:

[1302] Data collection:

[1303] Collects answer data and emotional data (facial expressions, voice) from students and customers using cameras and microphones.

[1304] Content Display:

[1305] The learning content distributed from the server is displayed on display devices such as tablets, smartphones, and smart glasses.

[1306] User

[1307] Users (students and faculty) have the following roles:

[1308] Implementing learning activities:

[1309] Students use tablets and computers to answer daily study questions.

[1310] Sentiment data provided by:

[1311] Students and customers provide emotional data via a camera and microphone.

[1312] Data analysis and content generation

[1313] The server uses machine learning algorithms to analyze the collected learning data and emotional data. This analysis identifies the learning progress and emotional state of the student or customer. Based on the analysis results, appropriate learning content is generated and delivered to each device.

[1314] Application in virtual stores

[1315] In the virtual store, if a customer expresses interest in a new product, detailed educational content about that product will be generated and delivered. The customer's emotional state will also be analyzed, and if they are feeling anxious or confused, more detailed explanations or support messages will be provided.

[1316] Examples:

[1317] For example, if a customer expresses interest in a new smartphone but appears anxious, the server analyzes the facial expression data and generates a friendly instructional video that clearly explains the product's features and how to use it, along with encouraging messages, and streams the video to the smart glasses or tablet.

[1318] Example prompt sentence:

[1319] "Analyze what emotions the person in the image is expressing"

[1320] "Generate explainer videos about product details based on specific emotional states."

[1321] In this way, the present invention makes it possible to provide content flexibly according to the emotional state of the learner or customer, thereby improving learning efficiency and customer satisfaction.

[1322] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[1323] Step 1:

[1324] Data collection

[1325] Users (students or customers) use devices (e.g., tablets, smart glasses) to carry out daily learning activities. During this time, the devices use cameras and microphones to collect facial and voice data of the users.

[1326] Input: Learner's answer data and emotional data (facial expressions, voice)

[1327] Output: A set of collected answer data and sentiment data

[1328] How it works: The device's camera and microphone are constantly active, capturing the user's face and voice, which are then processed in real time and sent to a server.

[1329] Step 2:

[1330] Data transmission

[1331] The device transmits the collected data of the learner's answers and emotions to the server in real time. The communication is carried out using a secure protocol (e.g., HTTPS).

[1332] Input: Collected answer data and sentiment data

[1333] Output: Collected data sent to the server

[1334] How it works: Data is sent asynchronously from the device to the server, and the transmission status is monitored in real time.

[1335] Step 3:

[1336] Data accumulation

[1337] The server stores the received data in a database, where the data is identified for each user and classified as learning data and emotion data.

[1338] Input: Submitted answer data and emotion data

[1339] Output: Learning data and emotion data for each student stored in a database

[1340] How it works: The server uses an appropriate database schema to structure and store data so that it can be queried efficiently.

[1341] Step 4:

[1342] Data analysis

[1343] The server analyzes the accumulated learning data and emotional data using machine learning algorithms (e.g., TensorFlow, PyTorch), which allows the user's learning progress and emotional state to be identified.

[1344] Input: Learning data and emotion data for each student stored in the database

[1345] Output: Learning progress report and emotional state report

[1346] How it works: Machine learning algorithms analyze data and update models for each user. Results are displayed on a dashboard.

[1347] Step 5:

[1348] Content Generation

[1349] Based on the data analysis results, the server generates learning content (e.g., videos, supplementary materials) appropriate for the user. The content is customized as needed, taking into account emotional data.

[1350] Input: Learning progress report and emotional state report

[1351] Output: Customized learning content

[1352] How it works: Using the analysis results, a generative AI model is used to create content and save it to storage.

[1353] Step 6:

[1354] Content Delivery

[1355] The server delivers the generated learning content to each user's device using a CDN (e.g., AWS CloudFront), and the content is delivered in streaming format.

[1356] Input: Customized learning content

[1357] Output: URL of content that can be played on the user's device

[1358] How it works: Content is streamed and monitored to ensure the connection is not dropped.

[1359] Step 7:

[1360] Comprehension test

[1361] The user takes the comprehension test on the device, which displays the questions and collects the user's answers. Once the answers are completed, they are sent back to the server.

[1362] Input: Assessment questions and user answers

[1363] Output: The test results sent to the server.

[1364] How it works: Test questions are displayed and the user's answers are collected. The answers are sent in real time to a server and stored in an answer database.

[1365] Step 8:

[1366] reanalysis

[1367] The server then analyzes the collected answer data again to determine the user's latest learning comprehension and emotional state.

[1368] Input: Comprehension test answer data

[1369] Output: Latest learning progress report and emotional state report

[1370] What it does: The analytical model is updated and new progress and emotional states are displayed on the dashboard.

[1371] Step 9:

[1372] Timetable generation

[1373] The server generates an optimal timetable based on collected classroom usage, faculty schedules, and student grades and progress data.

[1374] Inputs: classroom utilization, faculty schedules, grades and progress data

[1375] Output: Generated timetable

[1376] How it works: Generates an optimal timetable based on data and converts it into a format that can be distributed to each device.

[1377] Step 10:

[1378] Timetable distribution

[1379] The server distributes the generated timetable to the terminals of teachers and students.

[1380] Input: Generated timetable

[1381] Output: A timetable that can be displayed on the devices of faculty and students

[1382] How it works: The timetable is sent to the device via push notification or email, and each user can check it.

[1383] The specific processing unit 290 transmits the result of the specific processing to the smart glasses 214. In the smart glasses 214, the control unit 46A causes the speaker 240 to output the result of the specific processing. The microphone 238 acquires audio indicating a user input regarding the result of the specific processing. The control unit 46A transmits audio data indicating the user input acquired by the microphone 238 to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the audio data.

[1384] The data generation model 58 is a so-called generative AI (Artificial Intelligence). An example of the data generation model 58 is ChatGPT (Internet Search<URL: https: / / openai.com / blog / chatgpt> ), Gemini (Internet search <url: https: gemini.google.com ?hl="ja">) and other generation AIs. The data generation model 58 is obtained by performing deep learning on a neural network. A prompt including an instruction is input to the data generation model 58, and inference data such as voice data indicating voice, text data indicating text, and image data indicating an image is also input. The data generation model 58 performs inference on the input inference data in accordance with the instruction indicated by the prompt, and outputs the inference result in a data format such as voice data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[1385] In the above embodiment, an example in which the specific processing is performed by the data processing device 12 has been given, but the technology of the present disclosure is not limited to this, and the specific processing may be performed by the smart glasses 214.

[1386] [Third embodiment]

[1387] FIG. 5 shows an example of the configuration of a data processing system 310 according to the third embodiment.

[1388] 5, the data processing system 310 includes the data processing device 12 and a headset terminal 314. An example of the data processing device 12 is a server.

[1389] The data processing device 12 includes a computer 22, a database 24, and a communication I / F 26. The computer 22 is an example of a "computer" according to the technology of the present disclosure. The computer 22 includes a processor 28, a RAM 30, and a storage 32. The processor 28, the RAM 30, and the storage 32 are connected to a bus 34. The database 24 and the communication I / F 26 are also connected to the bus 34. The communication I / F 26 is connected to a network 54. Examples of the network 54 include a WAN (Wide Area Network) and / or a LAN (Local Area Network).

[1390] The headset type terminal 314 includes a computer 36, a microphone 238, a speaker 240, a camera 42, a communication I / F 44, and a display 343. The computer 36 includes a processor 46, a RAM 48, and a storage 50. The processor 46, the RAM 48, and the storage 50 are connected to a bus 52. The microphone 238, the speaker 240, the camera 42, and the display 343 are also connected to the bus 52.

[1391] The microphone 238 receives instructions and the like from the user 20 by receiving voice uttered by the user 20. The microphone 238 captures the voice uttered by the user 20, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio in accordance with instructions from the processor 46.

[1392] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an imaging element such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, and captures images of the surroundings of user 20 (for example, an imaging range defined by an angle of view equivalent to the field of vision of a typical healthy person).

[1393] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 are responsible for the exchange of various information between the processor 46 and the processor 28 via the network 54. The exchange of various information between the processor 46 and the processor 28 using the communication I / Fs 44 and 26 is carried out in a secure state.

[1394] Fig. 6 shows an example of the main functions of the data processing device 12 and the headset type terminal 314. As shown in Fig. 6, in the data processing device 12, a specific process is performed by the processor 28. A specific process program 56 is stored in the storage 32.

[1395] The specific processing program 56 is an example of a "program" according to the technology of the present disclosure. The processor 28 reads the specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific 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.

[1396] The storage 32 stores a data generation model 58 and an emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290.

[1397] In the headset type terminal 314, a reception output process is performed by the processor 46. A reception output program 60 is stored in the storage 50. 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 process is realized by the processor 46 operating as the control unit 46A in accordance with the reception output program 60 executed on the RAM 48.

[1398] Next, a description will be given of the identification process performed by the identification processing unit 290 of the data processing device 12. 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."

[1399] This invention is an educational environment platform that grasps the learning status of each student, automatically generates and provides appropriate learning content and comprehension tests, and also improves the work efficiency of faculty and staff. This platform consists of a server, terminals (devices used by students and faculty and staff), and users (students and faculty and staff).

[1400] Collection and accumulation of learning data

[1401] Data entry and submission

[1402] User

[1403] Users (students) input answers to daily study questions and comprehension tests into the terminal.

[1404] Terminal

[1405] The device sends the data entered by the student to the server in real time. For example, when a student solves an arithmetic problem and enters the answer into the tablet, the answer is sent directly to the server.

[1406] server

[1407] The server stores the transmitted learning data in a database, which includes information such as answer content, answer time, and accuracy rate.

[1408] Learning content generation and delivery

[1409] Data analysis and content generation

[1410] server

[1411] The server analyzes the collected learning data using machine learning algorithms, which identifies each student's learning progress and weaknesses.

[1412] server

[1413] The server generates learning content (such as videos) based on the analysis results. For example, for students who do not fully understand fractions, it generates a video that explains the basics of fractions in detail.

[1414] Content distribution and viewing

[1415] server

[1416] The server distributes the generated learning content to each student's device, typically via streaming.

[1417] Terminal

[1418] The devices display learning content distributed from the server and allow students to view it. Students can then watch videos on their tablets or computers to deepen their understanding.

[1419] Example: If Student A has difficulty with fractions in mathematics, the server generates a supplementary video on the specific topic of fractions and distributes it to Student A's tablet. Student A watches the video and deepens his understanding of fractions.

[1420] Providing and collecting comprehension tests

[1421] Test question generation and distribution

[1422] server

[1423] The server generates test questions to assess students' understanding, again using machine learning algorithms to set questions that address students' weaknesses.

[1424] server

[1425] The server distributes the generated test questions to the target student terminals.

[1426] Testing and collecting results

[1427] Terminal

[1428] The devices are designed to allow students to take comprehension tests, which they answer on tablets or computers.

[1429] Terminal

[1430] The terminal automatically transmits the answer result to the server.

[1431] server

[1432] The server then re-analyzes the collected answer data to determine the student's most recent understanding.

[1433] Example: Student A takes a fraction comprehension test and sends the answer data to the server. The server analyzes the test results and determines whether the student's understanding of fractions has improved.

[1434] Automatic generation and distribution of timetables

[1435] Timetable data collection and generation

[1436] server

[1437] The server collects data on classroom usage, faculty schedules, and student grades and progress, while also considering special lessons to address student weaknesses.

[1438] server

[1439] The server analyzes the collected data and generates an optimal timetable that reflects the availability of each classroom, teacher availability, and student learning needs.

[1440] Distribution and use of timetables

[1441] server

[1442] The server distributes the generated timetable to the terminals of faculty and students.

[1443] Terminal

[1444] The devices will display the distributed timetable, allowing teachers, staff and students to check it and act according to the schedule.

[1445] Example: Teacher B checks the new timetable and prepares for the next lesson. Student A also checks the time of the next lesson and prepares the necessary teaching materials.

[1446] As described above, the educational environment platform of the present invention enables flexible content distribution according to the learning situation of each student, accurate understanding of their level of understanding, and efficient timetable generation. This promotes efficiency and digitalization throughout the educational field, and makes it possible to provide an optimal learning environment.

[1447] The processing flow will be explained below.

[1448] Collection and accumulation of learning data

[1449] Step 1:

[1450] User

[1451] Students use tablets or computers to enter answers to their daily study questions and homework.

[1452] Step 2:

[1453] Terminal

[1454] The device sends the answer data entered by the student to the server in real time using a secure protocol.

[1455] Step 3:

[1456] server

[1457] The server stores the transmitted learning data in a database, including detailed information such as the student's ID, answer content, answer time, and whether the answer was correct or incorrect.

[1458] Learning content generation and delivery

[1459] Step 1:

[1460] server

[1461] The server analyzes the accumulated learning data using machine learning algorithms, thereby identifying each student's learning progress and weaknesses.

[1462] Step 2:

[1463] server

[1464] The server generates learning content (such as videos) appropriate for each student based on the analysis results. Specifically, it selects educational videos and supplementary materials according to specific themes and customizes them as needed.

[1465] Step 3:

[1466] server

[1467] The server distributes the generated learning content to each student's device in a streaming format, and also supports offline viewing if necessary.

[1468] Step 4:

[1469] Terminal

[1470] The device displays learning content delivered from the server, and students can view and understand specific learning content.

[1471] Providing and collecting comprehension tests

[1472] Step 1:

[1473] server

[1474] The server generates personalized test questions to gauge students' understanding, using machine learning algorithms.

[1475] Step 2:

[1476] server

[1477] The server distributes the generated comprehension test questions to the student's terminal.

[1478] Step 3:

[1479] Terminal

[1480] The device displays questions for students to take comprehension tests, and students enter their answers on a tablet or computer.

[1481] Step 4:

[1482] Terminal

[1483] The device sends the results of the student's answers to the test questions in real time to the server, including not only the answers but also the time and process of answering.

[1484] Step 5:

[1485] server

[1486] The server then analyzes the collected answer data again, thereby gaining an understanding of the students' current learning comprehension and reflecting this in the generation of the next learning content.

[1487] Automatic generation and distribution of timetables

[1488] Step 1:

[1489] server

[1490] The server collects staffing data, classroom utilization, faculty schedules, and student grades and progress data.

[1491] Step 2:

[1492] server

[1493] The server analyzes the collected data and generates an optimal timetable, taking into account classroom availability, teacher availability, and student learning needs.

[1494] Step 3:

[1495] server

[1496] The server distributes the generated timetable to the terminals of faculty and students.

[1497] Step 4:

[1498] Terminal

[1499] The terminal displays the distributed timetable, allowing teachers to prepare for class, while students check the time and content of their next class.

[1500] Through the specific processing steps described above, the present invention achieves efficiency and digitalization in educational settings. By providing content suited to each student's learning situation, enabling appropriate comprehension assessment, and enabling the automatic generation of efficient timetables, the aim is to improve the quality of education and reduce the workload of teachers and staff.

[1501] Example 1

[1502] Next, a description will be given of Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the headset type terminal 314 will be referred to as a "terminal."

[1503] In today's educational environment, there is a need to closely grasp each student's learning situation and provide appropriate learning content based on that understanding. However, conventional methods often provide uniform learning materials to a large number of students, making it difficult to flexibly respond to each student's level of understanding and progress. Furthermore, the workload of teachers and staff is increasing, making efficiency an urgent need. Furthermore, insufficient collection and analysis of learning data makes it difficult to provide individualized support. The present invention aims to solve these problems and improve the efficiency of the entire educational environment while providing learning content optimized for each student.

[1504] The specific processing by the specific processing unit 290 of the data processing device 12 in the first embodiment is realized by the following means.

[1505] In this invention, the server includes: means for collecting answer data from learners' devices; means for transmitting the collected answer data to the server in real time; means for storing the transmitted answer data in a database; means for analyzing the accumulated learning data using a machine learning algorithm; means for generating learning content suitable for the learner based on the analysis results; means for distributing and displaying the generated learning content to the learner's device; means for generating test questions for assessing comprehension; means for distributing the generated test questions to the learner's device; means for transmitting answer data answered by the learner on his / her device to the server; means for reanalyzing the transmitted answer data and understanding the learner's learning situation; means for collecting data on school classroom usage, teacher schedules, and learner grades and progress; means for generating an optimal class schedule based on the collected data; and means for distributing the generated class schedule to the teacher's and learner's devices. This enables the provision of optimized educational content based on individual learner data and improves the efficiency of the entire educational environment.

[1506] "Student's device" refers to an electronic device (e.g., tablet, PC, smartphone, etc.) used by a learner, which can input learning data, view learning content, and take comprehension tests.

[1507] "Answer data" refers to data that includes the answers entered by a learner to study questions and comprehension tests.

[1508] The "server" is a central computer system that receives data sent from learners' devices and stores, analyzes, and distributes the data.

[1509] A "database" is a storage device installed on a server that organizes and stores data in an organized manner and manages it so that it can be easily accessed later.

[1510] A "machine learning algorithm" is a computer program that automatically analyzes collected data and performs pattern recognition and predictions.

[1511] "Learning Content" refers to educational materials and learning materials (e.g., video, audio, written text, interactive questions, etc.) provided to support learners' learning.

[1512] A "comprehension test" is a test or question provided to measure a learner's proficiency or comprehension.

[1513] "Classroom usage status" is information indicating the time periods during which each classroom in a school is available for use or in use.

[1514] "Teacher schedule" is information including the timetable of each teacher's working hours, class schedule, meeting schedule, etc.

[1515] "Student performance" refers to data that indicates the academic achievements that a student has made to date.

[1516] "Progress data" refers to data that indicates the learner's learning situation, progress, and state of progress.

[1517] A "timetable" is a table or list that shows students and teachers the schedule of their lessons and activities.

[1518] "Distribution" refers to the act of transmitting generated data or content to a specific terminal or user.

[1519] This invention is an educational environment platform that grasps the learning status of each student, automatically generates and provides appropriate learning content and comprehension tests, and also improves the work efficiency of faculty and staff. This platform consists of a server, terminals (devices used by students and faculty and staff), and users (students and faculty and staff).

[1520] Collection and accumulation of learning data

[1521] Data entry and submission

[1522] Students, who are users, input their daily study questions and comprehension tests into their own devices. For example, a student solves an arithmetic problem and enters the answer into a tablet. This answer data is sent to the server in real time by the device. The server then stores the sent learning data in a database. This data includes the answer content, answer time, accuracy rate, etc.

[1523] Learning content generation and delivery

[1524] Data analysis and content generation

[1525] The server analyzes the accumulated learning data using machine learning algorithms. This analysis identifies each student's learning status and weaknesses. For example, the server might determine that "Student A is struggling with fraction problems."

[1526] The server then generates learning content based on the analysis, including videos and interactive exercises, such as a video explaining the basics of fractions.

[1527] Content distribution and viewing

[1528] The server distributes the generated learning content to each student's device. This distribution is in streaming format. The device plays the distributed learning content so that the student can view it. For example, a student can view "Frequency Fundamentals" on a tablet to deepen their understanding.

[1529] Providing and collecting comprehension tests

[1530] Test question generation and distribution

[1531] The server generates test questions to assess students' understanding. This also uses machine learning algorithms to create questions tailored to each student's weaknesses. For example, it generates new fraction questions in a specific format. The generated test questions are then distributed to each student's device.

[1532] Testing and collecting results

[1533] The student user takes a comprehension test on their device. For example, they answer questions on a tablet to measure their "understanding of fractions." The device sends the test results to the server in real time. The server reanalyzes these test results and keeps track of the student's latest understanding.

[1534] Automatic generation and distribution of timetables

[1535] Timetable data collection and generation

[1536] The server collects data on classroom usage, faculty schedules, and student performance and progress. This data includes classroom availability, teacher availability, and student learning needs. The server analyzes the collected data and generates an optimal timetable.

[1537] Distribution and use of timetables

[1538] The server distributes the generated timetable to the terminals of faculty and students. The terminals display the distributed timetable so that faculty and students can check it. For example, faculty and staff check the timetable to prepare for the next class, and students also check the time of the next class and prepare the necessary teaching materials.

[1539] Specific examples

[1540] If it is determined that Student A's understanding of fractions is insufficient, the server uses a machine learning algorithm to generate an explanatory video on fractions tailored to the student and distributes it to Student A's tablet. Student A watches the video to deepen his or her understanding. Student A is then given a fraction comprehension test, and the results are sent to the server, which then provides appropriate learning content based on the analysis results.

[1541] Prompt Sentence Examples

[1542] Below are some example prompts to input to a generative AI model:

[1543] "Please use this AI model to design a system that collects and analyzes student learning data and generates and delivers individualized learning content. Specifically, I would like to build an educational environment platform that generates comprehension tests, collects and analyzes the results, and automatically generates appropriate timetables."

[1544] As described above, the educational environment platform of the present invention can flexibly distribute content according to each student's learning situation, accurately grasp their level of understanding, and generate efficient timetables. This will promote efficiency and digitalization throughout the educational field, and make it possible to provide an optimal learning environment.

[1545] The flow of the identification process in the first embodiment will be described with reference to FIG.

[1546] Step 1:

[1547] Input of training data

[1548] The user (student) inputs daily study questions and comprehension tests into the terminal. For example, a student inputs answers to math problems. This input data includes the answer content and answer time entered by the student. The input data is sent to the next step.

[1549] Input: Answer data entered by the student into the device (answer content, answer time)

[1550] Output: Answer data saved on the device

[1551] Step 2:

[1552] Sending training data

[1553] The terminal transmits the answer data entered by the student to the server in real time. For example, the terminal transfers the answer data to the server via the network. This data includes the answer content and the answer time.

[1554] Input: Answer data saved on the device

[1555] Output: Answer data sent to the server

[1556] Step 3:

[1557] Accumulation of learning data

[1558] The server receives the submitted answer data and stores it in a database. This data includes the answer content, answer time, and correct answer rate. The server stores the data in the database so that it can be used for future processing.

[1559] Input: Answer data sent to the server (answer content, answer time, correct answer rate)

[1560] Output: Answer data stored in the database

[1561] Step 4:

[1562] Data analysis

[1563] The server analyzes the accumulated answer data using a machine learning algorithm. This analysis identifies the student's learning status and weaknesses. For example, the server analyzes that Student A is struggling with fraction problems.

[1564] Input: Answer data stored in the database

[1565] Output: Analysis results (student weaknesses and learning status)

[1566] Step 5:

[1567] Generating learning content

[1568] The server generates learning content based on the analysis results, including instructional videos and interactive exercises. For example, it generates a video explaining the basics of fractions.

[1569] Input: Analysis results

[1570] Output: Generated learning content

[1571] Step 6:

[1572] Delivery of learning content

[1573] The server then distributes the generated learning content to the learner's device. This distribution is done in streaming format. The server distributes the most suitable content to each learner in a timely manner.

[1574] Input: Generated learning content

[1575] Output: Learning content delivered to the learner's device

[1576] Step 7:

[1577] Viewing content

[1578] The device plays learning content distributed from the server and allows learners to view it. For example, a student can watch a video explaining fractions on a tablet.

[1579] Input: Learning content delivered to your device

[1580] Output: Learning content viewed by the learner

[1581] Step 8:

[1582] Generate comprehension tests

[1583] The server generates test questions to assess students' understanding. It uses machine learning algorithms to create questions tailored to students' weaknesses, for example, generating fraction questions in a specific format.

[1584] Input: Analysis results

[1585] Output: Generated assessment questions

[1586] Step 9:

[1587] Comprehension test distribution

[1588] The server distributes the generated test questions to the learner's terminal, which displays the test questions in an appropriate format.

[1589] Input: Generated assessment questions

[1590] Output: Comprehension test questions delivered to the learner's device

[1591] Step 10:

[1592] Comprehension test

[1593] The user (student) takes a comprehension test on the device. For example, the student answers a fraction comprehension test on a tablet.

[1594] Input: Comprehension test questions delivered to the learner's device

[1595] Output: Answered comprehension test data

[1596] Step 11:

[1597] Sending test results

[1598] The device sends test results in real time to a server, including the percentage of correct answers and response time.

[1599] Input: Answered comprehension test data

[1600] Output: Test results sent to the server

[1601] Step 12:

[1602] Analyzing test results

[1603] The server re-analyzes the test results and determines the latest learning status. For example, the server determines whether Student A's understanding of fractions has improved.

[1604] Input: Test results sent to the server

[1605] Output: Reanalysis results (latest learning status)

[1606] Step 13:

[1607] Collection of timetable data

[1608] The server collects data on the school's classroom usage, teacher schedules, and student performance and progress, including classroom availability, teacher availability, and student learning needs.

[1609] Input: Various data (classroom usage, teacher schedules, student grades and progress data)

[1610] Output: Collected timetable data

[1611] Step 14:

[1612] Generating optimal timetables

[1613] The server generates an optimal timetable based on the collected data, for example, one that reflects the available time of each classroom, the free time of teachers, and the learning needs of students.

[1614] Input: Collected timetable data

[1615] Output: Generated optimal timetable

[1616] Step 15:

[1617] Timetable distribution

[1618] The server distributes the generated timetable to the devices of faculty and students. The devices display the distributed timetable so that faculty and students can check it. For example, faculty and students check the new timetable to prepare for the next class, and students also check the time of the next class and prepare the necessary teaching materials.

[1619] Input: Generated optimal timetable

[1620] Output: Timetables distributed to faculty and student devices

[1621] The above is the specific flow of program processing for this system.

[1622] (Application example 1)

[1623] Next, a description will be given of Application Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the headset type terminal 314 will be referred to as a "terminal."

[1624] Conventional educational platforms face the challenge of making it difficult to provide personalized learning content tailored to each student's learning situation. In particular, generating and delivering appropriate content based on the student's level of understanding, as well as providing effective feedback, is time-consuming, hindering the efficiency of classrooms. It is also not easy to optimize timetables based on each student's learning progress and weaknesses. Therefore, there is a need for a system that can provide a learning environment tailored to each student's needs and reduce the workload of teachers.

[1625] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 1 is realized by the following means.

[1626] In this invention, the server includes: means for storing learning data collected from learning institutions nationwide in a database; means for analyzing the learning data stored in the database; means for generating learning content appropriate for each user based on the analysis results; means for distributing the generated learning content to each user's device; means for generating questions to test each user's level of comprehension; means for distributing the generated comprehension test questions to the device and collecting user answer data; means for re-analyzing the user's learning status based on the collected answer data; means for generating an optimal timetable based on classroom usage status, faculty schedules, and user grades and progress data; means for distributing the generated timetable to faculty and user devices; and means for using a generative AI model to generate personalized learning content and distributing the learning content to each user's device using prompts. This enables the automatic generation and distribution of learning content tailored to each student's level of comprehension, thereby improving the efficiency of education and student comprehension.

[1627] "Learning institutions" refers to all educational institutions, and is a general term for institutions that provide education such as elementary schools, junior high schools, high schools, universities, and vocational schools.

[1628] "Learning data" refers to information about a student's learning status, including digital data such as answer content, answer time, and correct answer rate.

[1629] A "database" is a system for systematically managing collected information and performing operations such as storage, search, and analysis.

[1630] "Analysis" is the process of processing collected data using methods and algorithms to obtain information for a specific purpose.

[1631] "Learning content" is a general term for teaching materials and resources used for educational purposes, including videos, texts, quizzes, etc.

[1632] A "terminal" is a digital device or equipment used by a user, such as a smartphone, tablet, or PC.

[1633] A "comprehension test" is a test to evaluate a student's level of comprehension of the learning content, and is given in the form of questions.

[1634] "Answer data" refers to a digital record of a student's answers to tests and questions.

[1635] A "timetable" is a table that shows the schedule of an educational institution or individual student, including the times and contents of classes.

[1636] A "generative AI model" is a collection of algorithms and programs that use artificial intelligence technology to automatically generate learning content and test questions.

[1637] A "prompt sentence" is an input sentence or command that gives a generative AI model specific instructions or requests.

[1638] This invention builds a system for providing an efficient and personalized learning environment in educational settings. This system uses the following hardware and software to collect and analyze various data, and then generates and distributes appropriate learning content.

[1639] Hardware

[1640] Server: A high-performance computer that can be cloud-based or on-premise.

[1641] Device: The device used by the user, such as a smartphone, tablet, or computer.

[1642] software

[1643] Mobile applications: Cross-platform applications developed using React Native or Flutter.

[1644] Server side: Built using Django and Node.js. PostgreSQL database is used.

[1645] Machine learning algorithms: TensorFlow and PyTorch are used for analysis. FFmpeg and OpenCV are used for video generation.

[1646] Data collection and storage

[1647] User: When students answer questions on their smartphones or tablets, the answer data is sent to the server in real time.

[1648] Server: The transmitted learning data is stored in a database, including answer content, answer time, and accuracy rate.

[1649] Data analysis and learning content generation

[1650] Server: Analyzes accumulated learning data using machine learning algorithms to identify each student's learning situation and weaknesses.

[1651] Server: Generates personalized learning content based on the analysis results. This uses a generative AI model to generate videos and text based on specific prompts. The generated content is saved in the appropriate format (video, text, etc.).

[1652] Content distribution and viewing

[1653] Server: The server distributes the generated learning content to each student's device using streaming technology.

[1654] Devices: Students can view and understand the learning content delivered on tablets and computers.

[1655] Providing comprehension tests and analyzing results

[1656] Server: Generates test questions to assess comprehension and distributes them to each student's device.

[1657] Device: Students answer test questions on their devices. The answer data is automatically sent to the server.

[1658] Server: Re-analyzes the collected answer data and updates the student's learning status.

[1659] Automatic generation and distribution of timetables

[1660] Server: Analyzes classroom usage, faculty schedules, and student grades and progress data to generate optimal timetables.

[1661] Server: Distributes the generated timetable to the terminals of faculty and students.

[1662] Terminals: Used by faculty and students to check upcoming lesson times and content.

[1663] Examples and prompts

[1664] For example, a user (student) solves a problem on "mathematical fractions" and sends the answer data to the server. The server analyzes the data and determines that the user lacks understanding of fractions. Next, it uses a generative AI model to generate a "video explaining the basics of fractions" and distributes it to the user. An example of a prompt sentence used in this case is, "This user's understanding of fractions is lacking. Please generate video teaching materials to help them understand the basics of fractions."

[1665] This system makes it possible to automatically generate and distribute learning content tailored to each user's level of understanding, thereby improving the efficiency of the classroom and the students' level of understanding.

[1666] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[1667] Step 1:

[1668] Data collection and transmission

[1669] Input: Data on the study questions answered by the user (student) on the device (answer content, answer time, correct answer rate)

[1670] How it works: When a user answers a study question on a smartphone or tablet, the data is sent to the server in real time. The application prompts the user to enter the answer, and once the answer is completed, the information is transferred to the server in JSON format.

[1671] Output: Answer data sent to the server

[1672] Step 2:

[1673] Data accumulation

[1674] Input: Answer data submitted in Step 1

[1675] Specific operation: The server stores the received answer data in a database using PostgreSQL, and the answer data is organized and saved in a table.

[1676] Output: Answer data stored in the database

[1677] Step 3:

[1678] Data analysis

[1679] Input: Answer data stored in the database

[1680] Specific operation: The server analyzes the answer data using machine learning algorithms (TensorFlow and PyTorch). This analysis identifies each student's learning status and weaknesses. Python is used for data analysis, and the learning status is quantified and evaluated.

[1681] Output: Analysis results (each student's level of understanding and weaknesses)

[1682] Step 4:

[1683] Learning content generation

[1684] Input: Analysis results obtained in step 3

[1685] Specific operation: The server uses the generative AI model to generate learning content (videos and text) based on the prompt. For example, a prompt such as "This user's understanding of fractions is insufficient. Please generate video materials to help them understand the basics of fractions" is input into the AI ​​model, and a video with the corresponding learning content is generated.

[1686] Output: Generated learning content (videos, text)

[1687] Step 5:

[1688] Content Delivery

[1689] Input: Learning content generated in Step 4

[1690] Specific operation: The server delivers the generated learning content to each user's device. The delivery format is mainly streaming, and the server notifies the user using Firebase Cloud Messaging or similar and provides the content URL.

[1691] Output: Learning content delivered to the user's device

[1692] Step 6:

[1693] Test generation and delivery

[1694] Input: Analysis results obtained in step 3

[1695] Specific operation: The server generates test questions to evaluate the user's level of understanding and distributes them to the device. The generated test questions are converted into JSON format and sent to the device via push notification.

[1696] Output: Comprehension test questions delivered to the user's device

[1697] Step 7:

[1698] Conducting comprehension tests and collecting results

[1699] Input: Comprehension test questions delivered in Step 6

[1700] Specific operation: The user answers the test questions on the device, and the answer data is sent to the server again in real time in JSON format.

[1701] Output: Test answer data sent to the server

[1702] Step 8:

[1703] Reanalysis and feedback

[1704] Input: Test response data collected in Step 7

[1705] Specific operation: The server analyzes the collected answer data again to grasp the student's latest learning situation. Based on the analysis results, it determines whether new learning content is necessary.

[1706] Output: Analysis results based on the latest learning status

[1707] Step 9:

[1708] Timetable generation and distribution

[1709] Input: User grades, progress data, classroom usage, faculty schedules

[1710] Specific operation: The server generates an optimal timetable based on the above data. The generated timetable is distributed to each user and faculty member via their terminal.

[1711] Output: Timetable distributed to each user and faculty terminal

[1712] Furthermore, an emotion engine that estimates the user's emotion may be further combined. That is, the identification processing unit 290 may estimate the user's emotion using the emotion identification model 59, and perform identification processing using the user's emotion.

[1713] This invention is a system that combines an emotion engine with an educational environment platform that grasps each student's learning situation and automatically generates and provides appropriate learning content and comprehension tests. This makes it possible to grasp students' emotional states, improve the learning experience, and increase educational efficiency. This platform consists of a server, terminals (devices used by students and faculty), and users (students and faculty).

[1714] Collection and storage of learning data and emotion data

[1715] Data entry and submission

[1716] User

[1717] Students use tablets or computers to input answers to daily study questions and homework, and emotional data is automatically collected through facial expressions and voice.

[1718] Terminal

[1719] Terminal

[1720] The device transmits the answer data and emotion data entered by the student to the server in real time using a secure protocol.

[1721] server

[1722] server

[1723] The server stores the transmitted learning data and emotional data in a database, including detailed information such as the student's ID, answer content, answer time, correct or incorrect answers, and emotional state.

[1724] Learning content generation and delivery

[1725] Data analysis and content generation

[1726] server

[1727] The server analyzes the accumulated learning and emotional data using machine learning algorithms to identify each student's learning progress, weaknesses, and emotional state.

[1728] server

[1729] The server then generates learning content (such as videos) tailored to each student based on the analysis results. For example, it selects educational videos and supplemental materials tailored to specific themes and customizes them as needed. Emotional data is also taken into account, so if a student is feeling anxious, content is generated that includes clearer explanations and encouraging messages.

[1730] Content distribution and viewing

[1731] server

[1732] The server distributes the generated learning content to each student's device in a streaming format, and also supports offline viewing if necessary.

[1733] Terminal

[1734] The device displays learning content delivered from the server, and students can view and understand specific learning content.

[1735] Example: If Student A has difficulty with fractions in mathematics and shows signs of anxiety while studying, the server generates a supplementary video on the specific topic of fractions, including an encouraging message. This video is then distributed to Student A's tablet, and Student A watches it, deepening his understanding of fractions and feeling reassured.

[1736] Providing and collecting comprehension tests

[1737] Test question generation and distribution

[1738] server

[1739] The server generates personalized test questions to gauge students' understanding, using machine learning algorithms based on learning and sentiment data.

[1740] server

[1741] The server distributes the generated comprehension test questions to the student's terminal.

[1742] Testing and collecting results

[1743] Terminal

[1744] The device displays questions for students to take comprehension tests, and students enter their answers on a tablet or computer.

[1745] Terminal

[1746] The device sends the student's answers to the test questions in real time to the server, including not only the answers but also the emotional responses they gave while answering.

[1747] server

[1748] The server then performs a second analysis based on the collected answer data and emotion data, thereby gaining an understanding of the student's current learning comprehension and emotional state, which is then reflected in the generation of the next learning content.

[1749] Example: When Student B takes a comprehension test, if he takes a long time to answer and looks confused, the server can analyze the data to identify the areas where Student B's understanding is lacking and generate questions for the next test to reinforce those areas.

[1750] Automatic generation and distribution of timetables

[1751] Timetable data collection and generation

[1752] server

[1753] The server collects staffing data, classroom utilization, faculty schedules, student grades and progress data, and sentiment data.

[1754] server

[1755] The server analyzes the collected data and generates an optimal timetable that takes into account classroom availability, teacher availability, student learning needs, and emotional state.

[1756] Distribution and use of timetables

[1757] server

[1758] The server distributes the generated timetable to the terminals of faculty and students.

[1759] Terminal

[1760] The terminal displays the distributed timetable, allowing teachers to prepare for class, while students check the time and content of their next class.

[1761] Example: Teacher C checks the new timetable and prepares for the next lesson. Student A also checks the time of the next lesson and prepares the necessary materials. Based on Student A's emotional data, relaxing lessons and activities are incorporated during times of particularly high stress.

[1762] As described above, the educational environment platform of the present invention provides flexible content and assessment of comprehension according to each student's learning situation and emotional state, and automatically generates efficient timetables. This promotes efficiency and digitalization throughout the entire educational environment, making it possible to provide an optimal learning environment.

[1763] The processing flow will be explained below.

[1764] Collection and storage of learning data and emotion data

[1765] Step 1:

[1766] User

[1767] Students use tablets or PCs to input answers to study questions and homework, and their facial expressions and voice data are automatically collected by the emotion engine while they are studying.

[1768] Step 2:

[1769] Terminal

[1770] The device transmits the answer data entered by the student and the collected emotion data to the server in real time, using a security protocol.

[1771] Step 3:

[1772] server

[1773] The server stores the submitted answer data and emotional data in a database, which contains information on the student's ID, answer content, answer time, correct / incorrect answers, and emotional state.

[1774] Learning content generation and delivery

[1775] Step 1:

[1776] server

[1777] The server analyzes the accumulated learning and emotional data using machine learning algorithms to identify students' learning progress, weaknesses, and emotional patterns.

[1778] Step 2:

[1779] server

[1780] The server generates learning content (e.g., videos) appropriate for the student based on the analysis results. For example, if a student is having trouble in a particular area, it generates a detailed explanatory video on that area. It also takes into account the student's emotional state and includes messages to ease anxiety.

[1781] Step 3:

[1782] server

[1783] The server distributes the generated learning content to students' devices. The distribution format is primarily streaming, but offline viewing is also supported if necessary.

[1784] Step 4:

[1785] Terminal

[1786] The device displays the delivered learning content to the students, who can then view and understand the content.

[1787] Example: If Student A feels uncomfortable with fraction problems in mathematics, the server generates a video with a detailed explanation of fractions and a message of encouragement, and distributes it to Student A's tablet. Student A watches this video, deepens his understanding of fractions, and reduces his anxiety about learning.

[1788] Providing and collecting comprehension tests

[1789] Step 1:

[1790] server

[1791] The server generates test questions to measure students' comprehension using machine learning algorithms based on training data and emotional data.

[1792] Step 2:

[1793] server

[1794] The server distributes the generated comprehension test questions to the student's terminal.

[1795] Step 3:

[1796] Terminal

[1797] The device displays questions for students to take comprehension tests, and students enter their answers on a tablet or computer.

[1798] Step 4:

[1799] Terminal

[1800] The terminal transmits the content of the answer and the emotion data in the answer to the server in real time.

[1801] Step 5:

[1802] server

[1803] The server analyzes the collected answer data and emotional data to grasp the latest learning comprehension and emotional state, and generates the next learning content and comprehension test based on the analysis results.

[1804] Example: If Student B shows signs of confusion or anxiety while taking a comprehension test, the server analyzes the data and identifies the areas where Student B is having difficulty. The next test will include reinforcement questions specific to those areas.

[1805] Automatic generation and distribution of timetables

[1806] Step 1:

[1807] server

[1808] The server collects classroom usage, faculty schedules, student grades and progress data, and sentiment data.

[1809] Step 2:

[1810] server

[1811] The server analyzes the collected data and generates an optimal timetable that takes into account classroom availability, faculty availability, students' learning needs, and emotional state.

[1812] Step 3:

[1813] server

[1814] The server distributes the generated timetable to the terminals of faculty and students.

[1815] Step 4:

[1816] Terminal

[1817] The terminals display the distributed timetable, which teachers and students can check. Teachers prepare for the lesson, and students check the time and content of the next lesson.

[1818] Example: Staff member C checks the new timetable and prepares for the next lesson. Based on emotional data, relaxing lessons and activities are scheduled during particularly stressful times. Student A also checks the timetable and prepares the necessary materials.

[1819] As described above, the present invention provides a system that improves students' learning efficiency and education quality by combining emotion engines. It realizes an individually optimized learning environment for each student through content distribution, test evaluation, and timetable generation based on the learning situation and emotional state.

[1820] Example 2

[1821] Next, a description will be given of Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the headset type terminal 314 will be referred to as a "terminal."

[1822] Conventional educational systems have difficulty efficiently grasping the progress and level of understanding of individual learners and providing appropriate learning content. Furthermore, they are unable to take into account the learner's emotional state, making it difficult to provide an educational environment that maximizes the effectiveness of learning. This leads to a decline in learner motivation and delays in learning progress, resulting in the inability to fully realize the effectiveness of education.

[1823] The specific processing by the specific processing unit 290 of the data processing device 12 in the second embodiment is realized by the following means.

[1824] In this invention, the server includes a means for storing learning data and emotional data collected from educational institutions nationwide in a database, a means for analyzing the stored learning data and emotional data, and a means for generating learning content appropriate for each learner based on the analysis results. This makes it possible to provide optimal learning content and create an efficient learning environment by taking into account the progress and emotional state of each individual learner.

[1825] "Learning data" refers to data collected by educational institutions, such as a learner's learning history, grades, progress, and answer content.

[1826] "Emotion data" is data that indicates the emotional state of a learner, obtained from their facial expressions and voice.

[1827] A "database" is a system for systematically storing and managing collected learning data and emotional data.

[1828] "Analysis" refers to the use of machine learning algorithms to analyze collected data and identify learners' progress, level of understanding, and emotional state.

[1829] "Learning content" refers to educational materials, videos, and supplementary materials that are customized according to the learner's progress and level of understanding.

[1830] "Devices" are electronic devices such as tablets and computers used by learners and faculty and staff.

[1831] A "machine learning algorithm" is a computer program used to perform analysis based on collected data, and can utilize libraries such as TensorFlow and Scikit-learn.

[1832] A "comprehension test" is a test question that measures a learner's level of comprehension and is customized for each individual.

[1833] A "timetable" is a schedule that is optimally organized taking into account classroom usage, faculty and staff schedules, learners' grades and progress data, and emotional data.

[1834] "Educational institutions" refers to facilities and organizations that carry out educational activities, such as schools and cram schools.

[1835] This invention provides an educational platform that analyzes collected learning data and emotional data, and automatically generates and delivers learning content and comprehension tests appropriate for each learner. This system includes a server, terminals (devices used by learners and faculty), and users (learners and faculty). The following describes how to specifically implement this system.

[1836] Data collection and transmission

[1837] User

[1838] Learners use tablets or PCs to input answers to daily study questions and homework assignments, and emotional data is automatically collected through the learner's facial expressions and voice.

[1839] Terminal

[1840] The device transmits the answer data and emotion data entered by the student to the server in real time using a secure protocol (e.g., HTTPS).

[1841] Data accumulation

[1842] server

[1843] The server stores the learning data and emotional data sent from the device in a database. This database uses MySQL, PostgreSQL, etc. This data includes the learner's ID, answer content, answer time, correct or incorrect answers, emotional state, etc.

[1844] Data analysis and content generation

[1845] server

[1846] The server analyzes the accumulated learning data and emotional data using machine learning algorithms such as Python's TensorFlow and Scikit-learn, thereby identifying each learner's learning progress, weaknesses, and emotional state.

[1847] server

[1848] The server generates learning content appropriate for each learner based on the analysis results. For example, if a learner is weak in a particular topic, it provides supplementary learning materials or educational videos on that topic. Furthermore, it generates content that includes encouraging messages for learners who are feeling anxious.

[1849] Content distribution and viewing

[1850] server

[1851] The server distributes the generated learning content to the learner's device using streaming technology such as HLS (HTTP Live Streaming).

[1852] Terminal

[1853] The terminal displays the learning content delivered from the server, and the learner watches and listens to it to understand the learning content.

[1854] Example: If Learner A has difficulty with fractions in mathematics and shows signs of anxiety while studying, the server generates a supplementary video explaining fractions and includes an encouraging message. This video is then distributed to Learner A's tablet, and Learner A watches it, deepening his understanding of fractions and feeling reassured.

[1855] Providing comprehension tests and collecting results

[1856] server

[1857] The server generates test questions based on the learning data and emotion data to measure the learner's level of understanding.

[1858] server

[1859] The server distributes the generated comprehension test questions to the learner's terminal.

[1860] Terminal

[1861] The device displays questions so that learners can take comprehension tests, and learners enter their answers on a tablet or computer.

[1862] Terminal

[1863] The device transmits the learner's test results and emotional data during the response to the server in real time.

[1864] Comprehension test analysis

[1865] server

[1866] The server reanalyzes the collected answer data and emotion data to grasp the learner's latest learning comprehension and emotional state. This information is reflected in the generation of the next learning content. The analysis is performed using the Python Pandas library.

[1867] Example: When Learner B takes a comprehension test, if he looks confused and takes a long time to answer a particular question, the server will analyze that data and generate questions for the next test that will help Learner B to fill in the gaps in his understanding.

[1868] Automatic generation and distribution of timetables

[1869] server

[1870] The server collects staffing data, classroom usage, faculty schedules, student grades and progress data, and emotional data to generate an optimal timetable.

[1871] server

[1872] The server distributes the generated timetable to the terminals of teachers and students.

[1873] Terminal

[1874] The terminal displays the distributed timetable, allowing teachers to prepare for lessons and students to check the time and content of their next lesson.

[1875] Example: Faculty member C checks the new timetable and prepares for the next lesson. Learner A also checks the time of the next lesson and prepares the necessary materials. Based on Learner A's emotional data, lessons and activities that help him relax are incorporated during times when he is feeling particularly stressed.

[1876] Prompt Sentence Examples

[1877] How do you collect and analyze student learning and emotion data?

[1878] Explain how to generate optimal learning content taking into account learning progress and emotional state.

[1879] What is the process for automatically generating tests to effectively assess student understanding?

[1880] The flow of the identification process in the second embodiment will be described with reference to FIG.

[1881] Step 1: Enter and submit data

[1882] User

[1883] Learners use tablets or computers to input their daily homework and answers to study questions, and their facial expressions and voice data are automatically captured while they study via cameras and microphones.

[1884] Input: Learner's answer data (answer content, answer time, correct / incorrect) and emotional data (facial expression, voice)

[1885] Output: Input answer data and emotion data

[1886] Terminal

[1887] The device sends the input answer data and emotion data to the server in real time using the HTTPS protocol to ensure data security.

[1888] Input: Learner's answer data and emotion data

[1889] Output: Answer data and emotion data sent to the server

[1890] Step 2: Accumulating data

[1891] server

[1892] The server stores the learning data and emotional data sent from the device in a relational database (e.g., MySQL or PostgreSQL). The database appropriately stores metadata such as the learner's ID, answer content, answer time, correct or incorrect answers, and emotional state.

[1893] Input: Submitted training data and emotion data

[1894] Output: Learning data and emotion data stored in the database

[1895] Step 3: Analyze the data

[1896] server

[1897] The server runs machine learning algorithms using Python's TensorFlow and Scikit-learn to analyze the accumulated learning data and emotional data, identifying each learner's learning progress, weaknesses, and emotional state. The analysis process also includes data preprocessing (e.g., normalization, missing value imputation).

[1898] Input: Accumulated learning data and emotion data

[1899] Output: Analysis of progress, weaknesses, and emotional state of each learner

[1900] Step 4: Generate learning content

[1901] server

[1902] The server generates learning content appropriate for each learner based on the analysis results. This content includes educational videos, supplementary materials, encouraging messages, etc. For example, if a learner is anxious about a particular topic, content including a detailed explanatory video on that topic and encouraging messages will be generated.

[1903] Input: Analysis results (learning progress, weaknesses, emotional state)

[1904] Output: Generated learning content

[1905] Step 5: Deliver your content

[1906] server

[1907] The server distributes the generated learning content to the learner's device. Streaming technology (e.g., HLS) is used for distribution. The distributed data is sent in a format appropriate for each learner's device. At the same time, it is cached in a format that allows for offline viewing.

[1908] Input: Generated learning content

[1909] Output: Learning content delivered to the learner's device

[1910] Terminal

[1911] The device receives the learning content distributed from the server and displays it for the learner to view, allowing the learner to acquire new knowledge and resolve any concerns they may have.

[1912] Input: Delivered learning content

[1913] Output: View and play learning content

[1914] Step 6: Provide a test

[1915] server

[1916] The server generates individually customized comprehension test questions to measure the learner's level of comprehension, using machine learning algorithms and analysis results based on learning data and emotional data.

[1917] Input: Analysis results, training data, emotion data

[1918] Output: Generated assessment questions

[1919] server

[1920] The server distributes the generated comprehension test questions to the learner's terminal.

[1921] Input: Generated assessment questions

[1922] Output: Comprehension test questions delivered to the learner's device

[1923] Step 7: Collect and analyze test results

[1924] Terminal

[1925] The device displays questions so that learners can take comprehension tests, and learners enter their answers on a tablet or computer.

[1926] Input: The displayed assessment question

[1927] Output: Answer data entered by the learner

[1928] Terminal

[1929] The device transmits the learner's test results and emotional data during the response to the server in real time.

[1930] Input: Answer data and emotion data entered by the learner

[1931] Output: Answer data and emotion data sent to the server

[1932] server

[1933] The server analyzes the collected answer data and emotional data. This allows it to grasp the learner's current level of learning comprehension and emotional state. The analysis results are reflected in the generation of the next learning content.

[1934] Input: Collected answer data, emotion data

[1935] Output: Analysis of the learner's comprehension and emotional state

[1936] Step 8: Generate and distribute timetables

[1937] server

[1938] The server collects staffing data, classroom usage, faculty schedules, student performance and progress data, and sentiment data. It analyzes this data to generate an optimal timetable. This analysis utilizes the Google Calendar API and other scheduling systems.

[1939] Inputs: Staffing data, classroom utilization, faculty schedules, learner performance, progress data, sentiment data

[1940] Output: The generated timetable

[1941] server

[1942] The server distributes the generated timetable to the terminals of teachers and students.

[1943] Input: Generated timetable

[1944] Output: Distributed timetable

[1945] Terminal

[1946] The terminal displays the distributed timetable, allowing teachers to prepare for lessons and students to check the time and content of their next lesson.

[1947] Input: Distributed timetable

[1948] Output: Displayed timetable

[1949] (Application example 2)

[1950] Next, a description will be given of Application Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the headset type terminal 314 will be referred to as a "terminal."

[1951] Conventional educational environment platforms have difficulty providing appropriate learning content based on each student's learning ability and progress. They also lack a mechanism for understanding the emotional state of students and customers in real time and adjusting learning content accordingly. This has led to problems such as a decline in student motivation and a drop in customer satisfaction. Furthermore, it has been difficult to provide information tailored to individual needs when dealing with customers in virtual stores. To solve these issues, a system is needed that can understand the emotional state of students and provide learning content and information appropriate to that situation.

[1952] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 2 is realized by the following means.

[1953] In this invention, the server includes: means for storing learning data collected from educational institutions nationwide in a database; means for analyzing the learning data stored in the database; means for generating learning content appropriate for each learner based on the analysis results; means for distributing the generated learning content to each learner's terminal; means for generating questions to test each learner's level of comprehension; means for distributing the generated comprehension test questions to the terminal and collecting learner answer data; means for re-analyzing the learner's learning status based on the collected answer data; means for collecting learner emotional data and adjusting the learning content based on that data; means for generating and distributing learning content for customers in a virtual store; means for analyzing the customer's emotional state and providing interactive content based on the analyzed data; means for generating an optimal class schedule based on classroom usage, faculty schedules, and learner grades and progress data; and means for distributing the generated class schedule to faculty and learner terminals. This enables flexible content provision according to the emotional state of learners and customers, thereby improving learning efficiency and customer satisfaction.

[1954] "Educational institutions" is a general term for facilities and organizations that conduct learning activities, including elementary schools, junior high schools, high schools, universities, and vocational schools.

[1955] "Learning data" refers to various data generated by learners through their learning activities, and examples include answer content, correct / incorrect answers, response time, and progress status.

[1956] "Emotional data" refers to data that indicates the emotional state of a learner as analyzed from their facial expressions and voice, and includes, for example, joy, anxiety, confusion, etc.

[1957] "Database" means a system capable of storing, managing, and retrieving large amounts of data in a structured form.

[1958] A "machine learning algorithm" is an algorithm that automatically makes predictions and judgments through learning from data.

[1959] "Learning content" refers to educational materials and information provided to learners, including videos, textbooks, workbooks, interactive learning materials, etc.

[1960] "Device" is a general term for electronic devices used by learners and faculty and staff, including personal computers, tablets, smartphones, etc.

[1961] A "comprehension test" is a test used to assess a learner's level of comprehension, and includes question formats, quizzes, questionnaires, etc.

[1962] "Analysis" refers to the process of collecting, classifying, and processing data to clarify its meaning and characteristics.

[1963] "Virtual store" refers to a virtual store that offers products and services over the Internet.

[1964] "Interactive content" refers to content that requires interaction with users, and includes chatbots, interactive videos, and dialogue training.

[1965] "Timetable" means a table showing the schedule of lessons and activities at an educational institution or program of study.

[1966] "Customer" means a user who intends to purchase or use goods or services in the virtual store.

[1967] "Generated" and "produced" refer to something newly created using a specific algorithm or method.

[1968] This invention relates to an educational environment platform that collects, analyzes, and distributes learning data and emotional data. This platform provides flexible content that takes into account the emotional state of students and customers to improve the learning experience. It also includes a system for grasping the emotional state of customers in a virtual store and providing appropriate information.

[1969] System configuration

[1970] The present invention comprises the following hardware and software components:

[1971] server

[1972] The server has the following functions:

[1973] Database Management:

[1974] Training data and emotion data are stored in a relational database such as MySQL or PostgreSQL.

[1975] Running machine learning algorithms:

[1976] To analyze the collected data, machine learning libraries such as TensorFlow and PyTorch are used.

[1977] Content Generation:

[1978] Based on the analysis results, learning content such as learning videos and supplementary materials is generated, and the generated content is stored in cloud storage such as AWS S3.

[1979] Streaming:

[1980] It provides a streaming service to deliver learning content to each device, using a CDN such as AWS CloudFront.

[1981] Terminal

[1982] The device has the following features:

[1983] Data collection:

[1984] Collects answer data and emotional data (facial expressions, voice) from students and customers using cameras and microphones.

[1985] Content Display:

[1986] The learning content distributed from the server is displayed on display devices such as tablets, smartphones, and smart glasses.

[1987] User

[1988] Users (students and faculty) have the following roles:

[1989] Implementing learning activities:

[1990] Students use tablets and computers to answer daily study questions.

[1991] Sentiment data provided by:

[1992] Students and customers provide emotional data via a camera and microphone.

[1993] Data analysis and content generation

[1994] The server uses machine learning algorithms to analyze the collected learning data and emotional data. This analysis identifies the learning progress and emotional state of the student or customer. Based on the analysis results, appropriate learning content is generated and delivered to each device.

[1995] Application in virtual stores

[1996] In the virtual store, if a customer expresses interest in a new product, detailed educational content about that product will be generated and delivered. The customer's emotional state will also be analyzed, and if they are feeling anxious or confused, more detailed explanations or support messages will be provided.

[1997] Examples:

[1998] For example, if a customer expresses interest in a new smartphone but appears anxious, the server analyzes the facial expression data and generates a friendly instructional video that clearly explains the product's features and how to use it, along with encouraging messages, and streams the video to the smart glasses or tablet.

[1999] Example prompt sentence:

[2000] "Analyze what emotions the person in the image is expressing"

[2001] "Generate explainer videos about product details based on specific emotional states."

[2002] In this way, the present invention makes it possible to provide content flexibly according to the emotional state of the learner or customer, thereby improving learning efficiency and customer satisfaction.

[2003] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[2004] Step 1:

[2005] Data collection

[2006] Users (students or customers) use devices (e.g., tablets, smart glasses) to carry out daily learning activities. During this time, the devices use cameras and microphones to collect facial and voice data of the users.

[2007] Input: Learner's answer data and emotional data (facial expressions, voice)

[2008] Output: A set of collected answer data and sentiment data

[2009] How it works: The device's camera and microphone are constantly active, capturing the user's face and voice, which are then processed in real time and sent to a server.

[2010] Step 2:

[2011] Data transmission

[2012] The device transmits the collected data of the learner's answers and emotions to the server in real time. The communication is carried out using a secure protocol (e.g., HTTPS).

[2013] Input: Collected answer data and sentiment data

[2014] Output: Collected data sent to the server

[2015] How it works: Data is sent asynchronously from the device to the server, and the transmission status is monitored in real time.

[2016] Step 3:

[2017] Data accumulation

[2018] The server stores the received data in a database, where the data is identified for each user and classified as learning data and emotion data.

[2019] Input: Submitted answer data and emotion data

[2020] Output: Learning data and emotion data for each student stored in a database

[2021] How it works: The server uses an appropriate database schema to structure and store data so that it can be queried efficiently.

[2022] Step 4:

[2023] Data analysis

[2024] The server analyzes the accumulated learning data and emotional data using machine learning algorithms (e.g., TensorFlow, PyTorch), which allows the user's learning progress and emotional state to be identified.

[2025] Input: Learning data and emotion data for each student stored in the database

[2026] Output: Learning progress report and emotional state report

[2027] How it works: Machine learning algorithms analyze data and update models for each user. Results are displayed on a dashboard.

[2028] Step 5:

[2029] Content Generation

[2030] Based on the data analysis results, the server generates learning content (e.g., videos, supplementary materials) appropriate for the user. The content is customized as needed, taking into account emotional data.

[2031] Input: Learning progress report and emotional state report

[2032] Output: Customized learning content

[2033] How it works: Using the analysis results, a generative AI model is used to create content and save it to storage.

[2034] Step 6:

[2035] Content Delivery

[2036] The server delivers the generated learning content to each user's device using a CDN (e.g., AWS CloudFront), and the content is delivered in streaming format.

[2037] Input: Customized learning content

[2038] Output: URL of content that can be played on the user's device

[2039] How it works: Content is streamed and monitored to ensure the connection is not dropped.

[2040] Step 7:

[2041] Comprehension test

[2042] The user takes the comprehension test on the device, which displays the questions and collects the user's answers. Once the answers are completed, they are sent back to the server.

[2043] Input: Assessment questions and user answers

[2044] Output: The test results sent to the server.

[2045] How it works: Test questions are displayed and the user's answers are collected. The answers are sent in real time to a server and stored in an answer database.

[2046] Step 8:

[2047] reanalysis

[2048] The server then analyzes the collected answer data again to determine the user's latest learning comprehension and emotional state.

[2049] Input: Comprehension test answer data

[2050] Output: Latest learning progress report and emotional state report

[2051] What it does: The analytical model is updated and new progress and emotional states are displayed on the dashboard.

[2052] Step 9:

[2053] Timetable generation

[2054] The server generates an optimal timetable based on collected classroom usage, faculty schedules, and student grades and progress data.

[2055] Inputs: classroom utilization, faculty schedules, grades and progress data

[2056] Output: Generated timetable

[2057] How it works: Generates an optimal timetable based on data and converts it into a format that can be distributed to each device.

[2058] Step 10:

[2059] Timetable distribution

[2060] The server distributes the generated timetable to the terminals of teachers and students.

[2061] Input: Generated timetable

[2062] Output: A timetable that can be displayed on the devices of faculty and students

[2063] How it works: The timetable is sent to the device via push notification or email, and each user can check it.

[2064] The specific processing unit 290 transmits the result of the specific processing to the headset type terminal 314. In the headset type terminal 314, the control unit 46A causes the speaker 240 and the display 343 to output the result of the specific processing. The microphone 238 acquires audio indicating a user input regarding the result of the specific processing. The control unit 46A transmits audio data indicating the user input acquired by the microphone 238 to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the audio data.

[2065] The data generation model 58 is a so-called generative AI (Artificial Intelligence). An example of the data generation model 58 is ChatGPT (Internet Search<URL: https: / / openai.com / blog / chatgpt> ), Gemini (Internet search <url: https: gemini.google.com ?hl="ja">) and other generation AIs. The data generation model 58 is obtained by performing deep learning on a neural network. A prompt including an instruction is input to the data generation model 58, and inference data such as voice data indicating voice, text data indicating text, and image data indicating an image is also input. The data generation model 58 performs inference on the input inference data in accordance with the instruction indicated by the prompt, and outputs the inference result in a data format such as voice data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[2066] 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 the present disclosure is not limited to this, and the specific processing may be performed by the headset type terminal 314.

[2067] [Fourth embodiment]

[2068] FIG. 7 shows an example of the configuration of a data processing system 410 according to the fourth embodiment.

[2069] 7, a data processing system 410 includes a data processing device 12 and a robot 414. An example of the data processing device 12 is a server.

[2070] The data processing device 12 includes a computer 22, a database 24, and a communication I / F 26. The computer 22 is an example of a "computer" according to the technology of the present disclosure. The computer 22 includes a processor 28, a RAM 30, and a storage 32. The processor 28, the RAM 30, and the storage 32 are connected to a bus 34. The database 24 and the communication I / F 26 are also connected to the bus 34. The communication I / F 26 is connected to a network 54. Examples of the network 54 include a WAN (Wide Area Network) and / or a LAN (Local Area Network).

[2071] The robot 414 includes a computer 36, a microphone 238, a speaker 240, a camera 42, a communication I / F 44, and a control target 443. The computer 36 includes a processor 46, a RAM 48, and a storage 50. The processor 46, the RAM 48, and the storage 50 are connected to a bus 52. The microphone 238, the speaker 240, the camera 42, and the control target 443 are also connected to the bus 52.

[2072] The microphone 238 receives instructions and the like from the user 20 by receiving voice uttered by the user 20. The microphone 238 captures the voice uttered by the user 20, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio in accordance with instructions from the processor 46.

[2073] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an imaging element such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, and captures images of the surroundings of user 20 (for example, an imaging range defined by an angle of view equivalent to the field of vision of a typical healthy person).

[2074] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 are responsible for the exchange of various information between the processor 46 and the processor 28 via the network 54. The exchange of various information between the processor 46 and the processor 28 using the communication I / Fs 44 and 26 is carried out in a secure state.

[2075] The control object 443 includes a display device, LEDs in the eyes, and motors for driving the arms, hands, and feet. The posture and gestures of the robot 414 are controlled by controlling the motors of the arms, hands, and feet. Some of the emotions of the robot 414 can be expressed by controlling these motors. In addition, the facial expressions of the robot 414 can also be expressed by controlling the light emission state of the LEDs in the eyes of the robot 414.

[2076] Fig. 8 shows an example of the main functions of the data processing device 12 and the robot 414. As shown in Fig. 8, in the data processing device 12, a specific process is performed by the processor 28. A specific process program 56 is stored in the storage 32.

[2077] The specific processing program 56 is an example of a "program" according to the technology of the present disclosure. The processor 28 reads the specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific 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.

[2078] The storage 32 stores a data generation model 58 and an emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290.

[2079] In the robot 414, the processor 46 performs the reception output process. A reception output program 60 is stored in the storage 50. 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 process is realized by the processor 46 operating as the control unit 46A in accordance with the reception output program 60 executed on the RAM 48.

[2080] Next, a description will be given of the specific processing performed by the specific processing unit 290 of the data processing device 12. In the following description, the data processing device 12 will be referred to as a "server" and the robot 414 will be referred to as a "terminal."

[2081] This invention is an educational environment platform that grasps the learning status of each student, automatically generates and provides appropriate learning content and comprehension tests, and also improves the work efficiency of faculty and staff. This platform consists of a server, terminals (devices used by students and faculty and staff), and users (students and faculty and staff).

[2082] Collection and accumulation of learning data

[2083] Data entry and submission

[2084] User

[2085] Users (students) input answers to daily study questions and comprehension tests into the terminal.

[2086] Terminal

[2087] The device sends the data entered by the student to the server in real time. For example, when a student solves an arithmetic problem and enters the answer into the tablet, the answer is sent directly to the server.

[2088] server

[2089] The server stores the transmitted learning data in a database, which includes information such as answer content, answer time, and accuracy rate.

[2090] Learning content generation and delivery

[2091] Data analysis and content generation

[2092] server

[2093] The server analyzes the collected learning data using machine learning algorithms, which identifies each student's learning progress and weaknesses.

[2094] server

[2095] The server generates learning content (such as videos) based on the analysis results. For example, for students who do not fully understand fractions, it generates a video that explains the basics of fractions in detail.

[2096] Content distribution and viewing

[2097] server

[2098] The server distributes the generated learning content to each student's device, typically via streaming.

[2099] Terminal

[2100] The devices display learning content distributed from the server and allow students to view it. Students can then watch videos on their tablets or computers to deepen their understanding.

[2101] Example: If Student A has difficulty with fractions in mathematics, the server generates a supplementary video on the specific topic of fractions and distributes it to Student A's tablet. Student A watches the video and deepens his understanding of fractions.

[2102] Providing and collecting comprehension tests

[2103] Test question generation and distribution

[2104] server

[2105] The server generates test questions to assess students' understanding, again using machine learning algorithms to set questions that address students' weaknesses.

[2106] server

[2107] The server distributes the generated test questions to the target student terminals.

[2108] Testing and collecting results

[2109] Terminal

[2110] The devices are designed to allow students to take comprehension tests, which they answer on tablets or computers.

[2111] Terminal

[2112] The terminal automatically transmits the answer result to the server.

[2113] server

[2114] The server then re-analyzes the collected answer data to determine the student's most recent understanding.

[2115] Example: Student A takes a fraction comprehension test and sends the answer data to the server. The server analyzes the test results and determines whether the student's understanding of fractions has improved.

[2116] Automatic generation and distribution of timetables

[2117] Timetable data collection and generation

[2118] server

[2119] The server collects data on classroom usage, faculty schedules, and student grades and progress, while also considering special lessons to address student weaknesses.

[2120] server

[2121] The server analyzes the collected data and generates an optimal timetable that reflects the availability of each classroom, teacher availability, and student learning needs.

[2122] Distribution and use of timetables

[2123] server

[2124] The server distributes the generated timetable to the terminals of faculty and students.

[2125] Terminal

[2126] The devices will display the distributed timetable, allowing teachers, staff and students to check it and act according to the schedule.

[2127] Example: Teacher B checks the new timetable and prepares for the next lesson. Student A also checks the time of the next lesson and prepares the necessary teaching materials.

[2128] As described above, the educational environment platform of the present invention enables flexible content distribution according to the learning situation of each student, accurate understanding of their level of understanding, and efficient timetable generation. This promotes efficiency and digitalization throughout the educational field, and makes it possible to provide an optimal learning environment.

[2129] The processing flow will be explained below.

[2130] Collection and accumulation of learning data

[2131] Step 1:

[2132] User

[2133] Students use tablets or computers to enter answers to their daily study questions and homework.

[2134] Step 2:

[2135] Terminal

[2136] The device sends the answer data entered by the student to the server in real time using a secure protocol.

[2137] Step 3:

[2138] server

[2139] The server stores the transmitted learning data in a database, including detailed information such as the student's ID, answer content, answer time, and whether the answer was correct or incorrect.

[2140] Learning content generation and delivery

[2141] Step 1:

[2142] server

[2143] The server analyzes the accumulated learning data using machine learning algorithms, thereby identifying each student's learning progress and weaknesses.

[2144] Step 2:

[2145] server

[2146] The server generates learning content (such as videos) appropriate for each student based on the analysis results. Specifically, it selects educational videos and supplementary materials according to specific themes and customizes them as needed.

[2147] Step 3:

[2148] server

[2149] The server distributes the generated learning content to each student's device in a streaming format, and also supports offline viewing if necessary.

[2150] Step 4:

[2151] Terminal

[2152] The device displays learning content delivered from the server, and students can view and understand specific learning content.

[2153] Providing and collecting comprehension tests

[2154] Step 1:

[2155] server

[2156] The server generates personalized test questions to gauge students' understanding, using machine learning algorithms.

[2157] Step 2:

[2158] server

[2159] The server distributes the generated comprehension test questions to the student's terminal.

[2160] Step 3:

[2161] Terminal

[2162] The device displays questions for students to take comprehension tests, and students enter their answers on a tablet or computer.

[2163] Step 4:

[2164] Terminal

[2165] The device sends the results of the student's answers to the test questions in real time to the server, including not only the answers but also the time and process of answering.

[2166] Step 5:

[2167] server

[2168] The server then analyzes the collected answer data again, thereby gaining an understanding of the students' current learning comprehension and reflecting this in the generation of the next learning content.

[2169] Automatic generation and distribution of timetables

[2170] Step 1:

[2171] server

[2172] The server collects staffing data, classroom utilization, faculty schedules, and student grades and progress data.

[2173] Step 2:

[2174] server

[2175] The server analyzes the collected data and generates an optimal timetable, taking into account classroom availability, teacher availability, and student learning needs.

[2176] Step 3:

[2177] server

[2178] The server distributes the generated timetable to the terminals of faculty and students.

[2179] Step 4:

[2180] Terminal

[2181] The terminal displays the distributed timetable, allowing teachers to prepare for class, while students check the time and content of their next class.

[2182] Through the specific processing steps described above, the present invention achieves efficiency and digitalization in educational settings. By providing content suited to each student's learning situation, enabling appropriate comprehension assessment, and enabling the automatic generation of efficient timetables, the aim is to improve the quality of education and reduce the workload of teachers and staff.

[2183] Example 1

[2184] Next, a description will be given of Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the robot 414 will be referred to as a "terminal."

[2185] In today's educational environment, there is a need to closely grasp each student's learning situation and provide appropriate learning content based on that understanding. However, conventional methods often provide uniform learning materials to a large number of students, making it difficult to flexibly respond to each student's level of understanding and progress. Furthermore, the workload of teachers and staff is increasing, making efficiency an urgent need. Furthermore, insufficient collection and analysis of learning data makes it difficult to provide individualized support. The present invention aims to solve these problems and improve the efficiency of the entire educational environment while providing learning content optimized for each student.

[2186] The specific processing by the specific processing unit 290 of the data processing device 12 in the first embodiment is realized by the following means.

[2187] In this invention, the server includes: means for collecting answer data from learners' devices; means for transmitting the collected answer data to the server in real time; means for storing the transmitted answer data in a database; means for analyzing the accumulated learning data using a machine learning algorithm; means for generating learning content suitable for the learner based on the analysis results; means for distributing and displaying the generated learning content to the learner's device; means for generating test questions for assessing comprehension; means for distributing the generated test questions to the learner's device; means for transmitting answer data answered by the learner on his / her device to the server; means for reanalyzing the transmitted answer data and understanding the learner's learning situation; means for collecting data on school classroom usage, teacher schedules, and learner grades and progress; means for generating an optimal class schedule based on the collected data; and means for distributing the generated class schedule to the teacher's and learner's devices. This enables the provision of optimized educational content based on individual learner data and improves the efficiency of the entire educational environment.

[2188] "Student's device" refers to an electronic device (e.g., tablet, PC, smartphone, etc.) used by a learner, which can input learning data, view learning content, and take comprehension tests.

[2189] "Answer data" refers to data that includes the answers entered by a learner to study questions and comprehension tests.

[2190] The "server" is a central computer system that receives data sent from learners' devices and stores, analyzes, and distributes the data.

[2191] A "database" is a storage device installed on a server that organizes and stores data in an organized manner and manages it so that it can be easily accessed later.

[2192] A "machine learning algorithm" is a computer program that automatically analyzes collected data and performs pattern recognition and predictions.

[2193] "Learning Content" refers to educational materials and learning materials (e.g., video, audio, written text, interactive questions, etc.) provided to support learners' learning.

[2194] A "comprehension test" is a test or question provided to measure a learner's proficiency or comprehension.

[2195] "Classroom usage status" is information indicating the time periods during which each classroom in a school is available for use or in use.

[2196] "Teacher schedule" is information including the timetable of each teacher's working hours, class schedule, meeting schedule, etc.

[2197] "Student performance" refers to data that indicates the academic achievements that a student has made to date.

[2198] "Progress data" refers to data that indicates the learner's learning situation, progress, and state of progress.

[2199] A "timetable" is a table or list that shows students and teachers the schedule of their lessons and activities.

[2200] "Distribution" refers to the act of transmitting generated data or content to a specific terminal or user.

[2201] This invention is an educational environment platform that grasps the learning status of each student, automatically generates and provides appropriate learning content and comprehension tests, and also improves the work efficiency of faculty and staff. This platform consists of a server, terminals (devices used by students and faculty and staff), and users (students and faculty and staff).

[2202] Collection and accumulation of learning data

[2203] Data entry and submission

[2204] Students, who are users, input their daily study questions and comprehension tests into their own devices. For example, a student solves an arithmetic problem and enters the answer into a tablet. This answer data is sent to the server in real time by the device. The server then stores the sent learning data in a database. This data includes the answer content, answer time, accuracy rate, etc.

[2205] Learning content generation and delivery

[2206] Data analysis and content generation

[2207] The server analyzes the accumulated learning data using machine learning algorithms. This analysis identifies each student's learning status and weaknesses. For example, the server might determine that "Student A is struggling with fraction problems."

[2208] The server then generates learning content based on the analysis, including videos and interactive exercises, such as a video explaining the basics of fractions.

[2209] Content distribution and viewing

[2210] The server distributes the generated learning content to each student's device. This distribution is in streaming format. The device plays the distributed learning content so that the student can view it. For example, a student can view "Frequency Fundamentals" on a tablet to deepen their understanding.

[2211] Providing and collecting comprehension tests

[2212] Test question generation and distribution

[2213] The server generates test questions to assess students' understanding. This also uses machine learning algorithms to create questions tailored to each student's weaknesses. For example, it generates new fraction questions in a specific format. The generated test questions are then distributed to each student's device.

[2214] Testing and collecting results

[2215] The student user takes a comprehension test on their device. For example, they answer questions on a tablet to measure their "understanding of fractions." The device sends the test results to the server in real time. The server reanalyzes these test results and keeps track of the student's latest understanding.

[2216] Automatic generation and distribution of timetables

[2217] Timetable data collection and generation

[2218] The server collects data on classroom usage, faculty schedules, and student performance and progress. This data includes classroom availability, teacher availability, and student learning needs. The server analyzes the collected data and generates an optimal timetable.

[2219] Distribution and use of timetables

[2220] The server distributes the generated timetable to the terminals of faculty and students. The terminals display the distributed timetable so that faculty and students can check it. For example, faculty and staff check the timetable to prepare for the next class, and students also check the time of the next class and prepare the necessary teaching materials.

[2221] Specific examples

[2222] If it is determined that Student A's understanding of fractions is insufficient, the server uses a machine learning algorithm to generate an explanatory video on fractions tailored to the student and distributes it to Student A's tablet. Student A watches the video to deepen his or her understanding. Student A is then given a fraction comprehension test, and the results are sent to the server, which then provides appropriate learning content based on the analysis results.

[2223] Prompt Sentence Examples

[2224] Below are some example prompts to input to a generative AI model:

[2225] "Please use this AI model to design a system that collects and analyzes student learning data and generates and delivers individualized learning content. Specifically, I would like to build an educational environment platform that generates comprehension tests, collects and analyzes the results, and automatically generates appropriate timetables."

[2226] As described above, the educational environment platform of the present invention can flexibly distribute content according to each student's learning situation, accurately grasp their level of understanding, and generate efficient timetables. This will promote efficiency and digitalization throughout the educational field, and make it possible to provide an optimal learning environment.

[2227] The flow of the identification process in the first embodiment will be described with reference to FIG.

[2228] Step 1:

[2229] Input of training data

[2230] The user (student) inputs daily study questions and comprehension tests into the terminal. For example, a student inputs answers to math problems. This input data includes the answer content and answer time entered by the student. The input data is sent to the next step.

[2231] Input: Answer data entered by the student into the device (answer content, answer time)

[2232] Output: Answer data saved on the device

[2233] Step 2:

[2234] Sending training data

[2235] The terminal transmits the answer data entered by the student to the server in real time. For example, the terminal transfers the answer data to the server via the network. This data includes the answer content and the answer time.

[2236] Input: Answer data saved on the device

[2237] Output: Answer data sent to the server

[2238] Step 3:

[2239] Accumulation of learning data

[2240] The server receives the submitted answer data and stores it in a database. This data includes the answer content, answer time, and correct answer rate. The server stores the data in the database so that it can be used for future processing.

[2241] Input: Answer data sent to the server (answer content, answer time, correct answer rate)

[2242] Output: Answer data stored in the database

[2243] Step 4:

[2244] Data analysis

[2245] The server analyzes the accumulated answer data using a machine learning algorithm. This analysis identifies the student's learning status and weaknesses. For example, the server analyzes that Student A is struggling with fraction problems.

[2246] Input: Answer data stored in the database

[2247] Output: Analysis results (student weaknesses and learning status)

[2248] Step 5:

[2249] Generating learning content

[2250] The server generates learning content based on the analysis results, including instructional videos and interactive exercises. For example, it generates a video explaining the basics of fractions.

[2251] Input: Analysis results

[2252] Output: Generated learning content

[2253] Step 6:

[2254] Delivery of learning content

[2255] The server then distributes the generated learning content to the learner's device. This distribution is done in streaming format. The server distributes the most suitable content to each learner in a timely manner.

[2256] Input: Generated learning content

[2257] Output: Learning content delivered to the learner's device

[2258] Step 7:

[2259] Viewing content

[2260] The device plays learning content distributed from the server and allows learners to view it. For example, a student can watch a video explaining fractions on a tablet.

[2261] Input: Learning content delivered to your device

[2262] Output: Learning content viewed by the learner

[2263] Step 8:

[2264] Generate comprehension tests

[2265] The server generates test questions to assess students' understanding. It uses machine learning algorithms to create questions tailored to students' weaknesses, for example, generating fraction questions in a specific format.

[2266] Input: Analysis results

[2267] Output: Generated assessment questions

[2268] Step 9:

[2269] Comprehension test distribution

[2270] The server distributes the generated test questions to the learner's terminal, which displays the test questions in an appropriate format.

[2271] Input: Generated assessment questions

[2272] Output: Comprehension test questions delivered to the learner's device

[2273] Step 10:

[2274] Comprehension test

[2275] The user (student) takes a comprehension test on the device. For example, the student answers a fraction comprehension test on a tablet.

[2276] Input: Comprehension test questions delivered to the learner's device

[2277] Output: Answered comprehension test data

[2278] Step 11:

[2279] Sending test results

[2280] The device sends test results in real time to a server, including the percentage of correct answers and response time.

[2281] Input: Answered comprehension test data

[2282] Output: Test results sent to the server

[2283] Step 12:

[2284] Analyzing test results

[2285] The server re-analyzes the test results and determines the latest learning status. For example, the server determines whether Student A's understanding of fractions has improved.

[2286] Input: Test results sent to the server

[2287] Output: Reanalysis results (latest learning status)

[2288] Step 13:

[2289] Collection of timetable data

[2290] The server collects data on the school's classroom usage, teacher schedules, and student performance and progress, including classroom availability, teacher availability, and student learning needs.

[2291] Input: Various data (classroom usage, teacher schedules, student grades and progress data)

[2292] Output: Collected timetable data

[2293] Step 14:

[2294] Generating optimal timetables

[2295] The server generates an optimal timetable based on the collected data, for example, one that reflects the available time of each classroom, the free time of teachers, and the learning needs of students.

[2296] Input: Collected timetable data

[2297] Output: Generated optimal timetable

[2298] Step 15:

[2299] Timetable distribution

[2300] The server distributes the generated timetable to the devices of faculty and students. The devices display the distributed timetable so that faculty and students can check it. For example, faculty and students check the new timetable to prepare for the next class, and students also check the time of the next class and prepare the necessary teaching materials.

[2301] Input: Generated optimal timetable

[2302] Output: Timetables distributed to faculty and student devices

[2303] The above is the specific flow of program processing for this system.

[2304] (Application example 1)

[2305] Next, a description will be given of Application Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the robot 414 will be referred to as a "terminal."

[2306] Conventional educational platforms face the challenge of making it difficult to provide personalized learning content tailored to each student's learning situation. In particular, generating and delivering appropriate content based on the student's level of understanding, as well as providing effective feedback, is time-consuming, hindering the efficiency of classrooms. It is also not easy to optimize timetables based on each student's learning progress and weaknesses. Therefore, there is a need for a system that can provide a learning environment tailored to each student's needs and reduce the workload of teachers.

[2307] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 1 is realized by the following means.

[2308] In this invention, the server includes: means for storing learning data collected from learning institutions nationwide in a database; means for analyzing the learning data stored in the database; means for generating learning content appropriate for each user based on the analysis results; means for distributing the generated learning content to each user's device; means for generating questions to test each user's level of comprehension; means for distributing the generated comprehension test questions to the device and collecting user answer data; means for re-analyzing the user's learning status based on the collected answer data; means for generating an optimal timetable based on classroom usage status, faculty schedules, and user grades and progress data; means for distributing the generated timetable to faculty and user devices; and means for using a generative AI model to generate personalized learning content and distributing the learning content to each user's device using prompts. This enables the automatic generation and distribution of learning content tailored to each student's level of comprehension, thereby improving the efficiency of education and student comprehension.

[2309] "Learning institutions" refers to all educational institutions, and is a general term for institutions that provide education such as elementary schools, junior high schools, high schools, universities, and vocational schools.

[2310] "Learning data" refers to information about a student's learning status, including digital data such as answer content, answer time, and correct answer rate.

[2311] A "database" is a system for systematically managing collected information and performing operations such as storage, search, and analysis.

[2312] "Analysis" is the process of processing collected data using methods and algorithms to obtain information for a specific purpose.

[2313] "Learning content" is a general term for teaching materials and resources used for educational purposes, including videos, texts, quizzes, etc.

[2314] A "terminal" is a digital device or equipment used by a user, such as a smartphone, tablet, or PC.

[2315] A "comprehension test" is a test to evaluate a student's level of comprehension of the learning content, and is given in the form of questions.

[2316] "Answer data" refers to a digital record of a student's answers to tests and questions.

[2317] A "timetable" is a table that shows the schedule of an educational institution or individual student, including the times and contents of classes.

[2318] A "generative AI model" is a collection of algorithms and programs that use artificial intelligence technology to automatically generate learning content and test questions.

[2319] A "prompt sentence" is an input sentence or command that gives a generative AI model specific instructions or requests.

[2320] This invention builds a system for providing an efficient and personalized learning environment in educational settings. This system uses the following hardware and software to collect and analyze various data, and then generates and distributes appropriate learning content.

[2321] Hardware

[2322] Server: A high-performance computer that can be cloud-based or on-premise.

[2323] Device: The device used by the user, such as a smartphone, tablet, or computer.

[2324] software

[2325] Mobile applications: Cross-platform applications developed using React Native or Flutter.

[2326] Server side: Built using Django and Node.js. PostgreSQL database is used.

[2327] Machine learning algorithms: TensorFlow and PyTorch are used for analysis. FFmpeg and OpenCV are used for video generation.

[2328] Data collection and storage

[2329] User: When students answer questions on their smartphones or tablets, the answer data is sent to the server in real time.

[2330] Server: The transmitted learning data is stored in a database, including answer content, answer time, and accuracy rate.

[2331] Data analysis and learning content generation

[2332] Server: Analyzes accumulated learning data using machine learning algorithms to identify each student's learning situation and weaknesses.

[2333] Server: Generates personalized learning content based on the analysis results. This uses a generative AI model to generate videos and text based on specific prompts. The generated content is saved in the appropriate format (video, text, etc.).

[2334] Content distribution and viewing

[2335] Server: The server distributes the generated learning content to each student's device using streaming technology.

[2336] Devices: Students can view and understand the learning content delivered on tablets and computers.

[2337] Providing comprehension tests and analyzing results

[2338] Server: Generates test questions to assess comprehension and distributes them to each student's device.

[2339] Device: Students answer test questions on their devices. The answer data is automatically sent to the server.

[2340] Server: Re-analyzes the collected answer data and updates the student's learning status.

[2341] Automatic generation and distribution of timetables

[2342] Server: Analyzes classroom usage, faculty schedules, and student grades and progress data to generate optimal timetables.

[2343] Server: Distributes the generated timetable to the terminals of faculty and students.

[2344] Terminals: Used by faculty and students to check upcoming lesson times and content.

[2345] Examples and prompts

[2346] For example, a user (student) solves a problem on "mathematical fractions" and sends the answer data to the server. The server analyzes the data and determines that the user lacks understanding of fractions. Next, it uses a generative AI model to generate a "video explaining the basics of fractions" and distributes it to the user. An example of a prompt sentence used in this case is, "This user's understanding of fractions is lacking. Please generate video teaching materials to help them understand the basics of fractions."

[2347] This system makes it possible to automatically generate and distribute learning content tailored to each user's level of understanding, thereby improving the efficiency of the classroom and the students' level of understanding.

[2348] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[2349] Step 1:

[2350] Data collection and transmission

[2351] Input: Data on the study questions answered by the user (student) on the device (answer content, answer time, correct answer rate)

[2352] How it works: When a user answers a study question on a smartphone or tablet, the data is sent to the server in real time. The application prompts the user to enter the answer, and once the answer is completed, the information is transferred to the server in JSON format.

[2353] Output: Answer data sent to the server

[2354] Step 2:

[2355] Data accumulation

[2356] Input: Answer data submitted in Step 1

[2357] Specific operation: The server stores the received answer data in a database using PostgreSQL, and the answer data is organized and saved in a table.

[2358] Output: Answer data stored in the database

[2359] Step 3:

[2360] Data analysis

[2361] Input: Answer data stored in the database

[2362] Specific operation: The server analyzes the answer data using machine learning algorithms (TensorFlow and PyTorch). This analysis identifies each student's learning status and weaknesses. Python is used for data analysis, and the learning status is quantified and evaluated.

[2363] Output: Analysis results (each student's level of understanding and weaknesses)

[2364] Step 4:

[2365] Learning content generation

[2366] Input: Analysis results obtained in step 3

[2367] Specific operation: The server uses the generative AI model to generate learning content (videos and text) based on the prompt. For example, a prompt such as "This user's understanding of fractions is insufficient. Please generate video materials to help them understand the basics of fractions" is input into the AI ​​model, and a video with the corresponding learning content is generated.

[2368] Output: Generated learning content (videos, text)

[2369] Step 5:

[2370] Content Delivery

[2371] Input: Learning content generated in Step 4

[2372] Specific operation: The server delivers the generated learning content to each user's device. The delivery format is mainly streaming, and the server notifies the user using Firebase Cloud Messaging or similar and provides the content URL.

[2373] Output: Learning content delivered to the user's device

[2374] Step 6:

[2375] Test generation and delivery

[2376] Input: Analysis results obtained in step 3

[2377] Specific operation: The server generates test questions to evaluate the user's level of understanding and distributes them to the device. The generated test questions are converted into JSON format and sent to the device via push notification.

[2378] Output: Comprehension test questions delivered to the user's device

[2379] Step 7:

[2380] Conducting comprehension tests and collecting results

[2381] Input: Comprehension test questions delivered in Step 6

[2382] Specific operation: The user answers the test questions on the device, and the answer data is sent to the server again in real time in JSON format.

[2383] Output: Test answer data sent to the server

[2384] Step 8:

[2385] Reanalysis and feedback

[2386] Input: Test response data collected in Step 7

[2387] Specific operation: The server analyzes the collected answer data again to grasp the student's latest learning situation. Based on the analysis results, it determines whether new learning content is necessary.

[2388] Output: Analysis results based on the latest learning status

[2389] Step 9:

[2390] Timetable generation and distribution

[2391] Input: User grades, progress data, classroom usage, faculty schedules

[2392] Specific operation: The server generates an optimal timetable based on the above data. The generated timetable is distributed to each user and faculty member via their terminal.

[2393] Output: Timetable distributed to each user and faculty terminal

[2394] Furthermore, an emotion engine that estimates the user's emotion may be further combined. That is, the identification processing unit 290 may estimate the user's emotion using the emotion identification model 59, and perform identification processing using the user's emotion.

[2395] This invention is a system that combines an emotion engine with an educational environment platform that grasps each student's learning situation and automatically generates and provides appropriate learning content and comprehension tests. This makes it possible to grasp students' emotional states, improve the learning experience, and increase educational efficiency. This platform consists of a server, terminals (devices used by students and faculty), and users (students and faculty).

[2396] Collection and storage of learning data and emotion data

[2397] Data entry and submission

[2398] User

[2399] Students use tablets or computers to input answers to daily study questions and homework, and emotional data is automatically collected through facial expressions and voice.

[2400] Terminal

[2401] Terminal

[2402] The device transmits the answer data and emotion data entered by the student to the server in real time using a secure protocol.

[2403] server

[2404] server

[2405] The server stores the transmitted learning data and emotional data in a database, including detailed information such as the student's ID, answer content, answer time, correct or incorrect answers, and emotional state.

[2406] Learning content generation and delivery

[2407] Data analysis and content generation

[2408] server

[2409] The server analyzes the accumulated learning and emotional data using machine learning algorithms to identify each student's learning progress, weaknesses, and emotional state.

[2410] server

[2411] The server then generates learning content (such as videos) tailored to each student based on the analysis results. For example, it selects educational videos and supplemental materials tailored to specific themes and customizes them as needed. Emotional data is also taken into account, so if a student is feeling anxious, content is generated that includes clearer explanations and encouraging messages.

[2412] Content distribution and viewing

[2413] server

[2414] The server distributes the generated learning content to each student's device in a streaming format, and also supports offline viewing if necessary.

[2415] Terminal

[2416] The device displays learning content delivered from the server, and students can view and understand specific learning content.

[2417] Example: If Student A has difficulty with fractions in mathematics and shows signs of anxiety while studying, the server generates a supplementary video on the specific topic of fractions, including an encouraging message. This video is then distributed to Student A's tablet, and Student A watches it, deepening his understanding of fractions and feeling reassured.

[2418] Providing and collecting comprehension tests

[2419] Test question generation and distribution

[2420] server

[2421] The server generates personalized test questions to gauge students' understanding, using machine learning algorithms based on learning and sentiment data.

[2422] server

[2423] The server distributes the generated comprehension test questions to the student's terminal.

[2424] Testing and collecting results

[2425] Terminal

[2426] The device displays questions for students to take comprehension tests, and students enter their answers on a tablet or computer.

[2427] Terminal

[2428] The device sends the student's answers to the test questions in real time to the server, including not only the answers but also the emotional responses they gave while answering.

[2429] server

[2430] The server then performs a second analysis based on the collected answer data and emotion data, thereby gaining an understanding of the student's current learning comprehension and emotional state, which is then reflected in the generation of the next learning content.

[2431] Example: When Student B takes a comprehension test, if he takes a long time to answer and looks confused, the server can analyze the data to identify the areas where Student B's understanding is lacking and generate questions for the next test to reinforce those areas.

[2432] Automatic generation and distribution of timetables

[2433] Timetable data collection and generation

[2434] server

[2435] The server collects staffing data, classroom utilization, faculty schedules, student grades and progress data, and sentiment data.

[2436] server

[2437] The server analyzes the collected data and generates an optimal timetable that takes into account classroom availability, teacher availability, student learning needs, and emotional state.

[2438] Distribution and use of timetables

[2439] server

[2440] The server distributes the generated timetable ...

Claims

1. A means of storing learning data collected from elementary schools across the country in a database, and means for analyzing the learning data stored in the database; A means for generating learning content suitable for each student based on the analysis results; means for distributing the generated learning content to each student's terminal; a means of generating questions to test each student's understanding; means for distributing the generated comprehension test questions to a terminal and collecting answer data of students; A means to re-analyze students' learning status based on the collected answer data, and A means of generating optimal timetables based on classroom usage, faculty schedules, and student performance and progress data; means for distributing the generated timetable to terminals of faculty and students; A system including:

2. 10. The system of claim 1, wherein the analysis of the training data uses a machine learning algorithm.

3. 2. The system according to claim 1, wherein learning content suitable for each student is delivered in a video format.

Images