System

Abstract

A system is provided.SOLUTION: The system includes a means for automatically generating a lecture moving image and a script, a means for storing the generated lecture moving image and script in a database, a means for automatically generating a test question based on a class content, a means for receiving test data answered by a student, a means for automatically scoring the received test data by AI, a means for recording a scoring result in the database, a means for receiving an inquiry about a unit acquisition from the student and analyzing the inquiry by natural language processing, and a means for generating and providing an appropriate answer based on an analysis result.SELECTED DRAWING: Figure 1

Description

[Technical Field]

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

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

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

[0004] The current higher education system faces problems such as enormous operating costs and a heavy burden on faculty and staff, while also placing a financial burden on students and their families. There is a lack of resources to prepare classes, create and grade tests, manage grades, and even respond to the vast number of inquiries from students. Furthermore, while efficient educational management is required, it is difficult to provide students with a high-quality education. Because it is difficult to fundamentally solve these problems using conventional methods, a new system is needed that automates classes, tests, and grade management, significantly reducing operating costs while maintaining educational quality. [Means for solving the problem]

[0005] The present invention solves the above-mentioned problems by the following means: A system is provided that includes: means for automatically generating lecture videos and scripts; means for saving the generated lecture videos and scripts in a database; means for automatically generating test questions based on the content of the lecture; means for receiving test data answered by students; means for automatically scoring the received test data using AI; means for recording the scoring results in a database; means for receiving inquiries from students regarding earning credits and analyzing them using natural language processing; and means for generating and providing appropriate answers based on the analysis results. By further including means for automatically generating lecture slides and lecture videos, and means for analyzing inquiries and generating answers in real time, this system can streamline educational operations and provide high-quality educational services at low cost.

[0006] "Lecture videos" are videos that provide visual and audio educational content automatically generated using AI technology.

[0007] A "script" is text data that includes slides and explanatory text used in the lecture video.

[0008] The "database" is a system that systematically stores generated course videos, scripts, test data, grade information, etc.

[0009] An "AI algorithm" is a calculation procedure used to analyze and automatically generate data using artificial intelligence technology.

[0010] "Test questions" are questions or assignments automatically generated by AI to assess students' understanding of the lesson content.

[0011] "Answer data" refers to answer information provided by students to test questions.

[0012] "Scoring" is the process by which AI evaluates answers to test questions and assigns scores.

[0013] "Natural language processing" is a technology that allows computers to understand, analyze, and generate human language.

[0014] An "inquiry" is a question from a student about the syllabus or credit acquisition, and is input information that allows the system to provide an answer to that question.

[0015] A "student" is a user who uses the system to receive education, take tests, and earn credits.

[0016] "System" is a general term for a series of processes and related hardware and software that use AI technology to automatically generate course videos and scripts, create, grade, and record tests, and respond to inquiries. [Brief explanation of the drawings]

[0017] [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

[0018] 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.

[0019] First, the terms used in the following description will be explained.

[0020] 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).

[0021] 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.

[0022] 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.

[0023] 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.

[0024] 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."

[0025] [First embodiment]

[0026] FIG. 1 shows an example of the configuration of a data processing system 10 according to the first embodiment.

[0027] 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.

[0028] 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).

[0029] 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.

[0030] 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.

[0031] 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.

[0032] 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.

[0033] FIG. 2 shows an example of the main functions of the data processing device 12 and the smart device 14.

[0034] 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.

[0035] 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.

[0036] 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.

[0037] 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."

[0038] This invention is a system for automating university education classes, tests, and grade management, and uses AI technology to provide high-quality education at low cost. Each function of this system is explained in detail below.

[0039] Creating course content

[0040] The server first retrieves information about the specified course topic from the database. Based on this data, an AI algorithm is used to automatically generate course slides. The AI ​​then creates a course video based on the generated slides. This video is structured in a format where a virtual instructor explains the slides, and is designed to be easy for students to understand. The generated course video and slides are saved in the database so that students can view them later.

[0041] For example, when creating a lesson on "linear algebra," the server retrieves teaching material data related to linear algebra, and the AI ​​generates slides that include matrix calculations and solutions to linear equations. Based on those slides, a lecture video is created and saved in the database.

[0042] Test creation, grading, and recording

[0043] The server uses AI to automatically generate test questions based on the content of the class. The generated test questions are distributed to students via their devices. Users (students) take the test using their devices and send their answers to the server.

[0044] The received response data is analyzed by the server's AI and automatically graded. The graded results are recorded in a database and organized for each student.

[0045] For example, when creating a "linear algebra" test, the server automatically generates questions about matrix calculations and solving linear equations. After students answer these questions and complete the test, the answer data is sent to the server. The AI ​​then scores the students and records the scores in a database.

[0046] Inquiry response

[0047] Users use their devices to submit questions about the syllabus or credit acquisition. For example, they might type, "What math courses should I take next semester?" The question is sent to the server, where the AI ​​chatbot analyzes it using natural language processing. Based on the analysis results, the AI ​​chatbot generates an appropriate answer and responds to the student via their device.

[0048] In this way, the server can respond to student inquiries in real time and provide course registration information and the conditions necessary to obtain credits. This type of response also contributes to the efficiency of educational management.

[0049] As a specific example, if a student sends a question such as "Please tell me the syllabus for mathematical statistics," the server searches the database for relevant syllabus information, and the AI ​​organizes that information and responds to the student.

[0050] As described above, the system of the present invention uses AI technology to automatically generate lecture videos and scripts, create, grade, and record tests, and respond to inquiries, making it possible to provide high-quality educational services at low cost. This system can significantly reduce the costs and labor required for traditional educational operations, and also ease the financial burden on students.

[0051] The processing flow will be explained below.

[0052] Creating course content

[0053] Step 1:

[0054] The server retrieves information about the specified course topic from the database.

[0055] Step 2:

[0056] Based on the information obtained by the server, lecture slides are automatically generated using an AI algorithm.

[0057] Step 3:

[0058] The server uses AI to automatically generate lecture videos based on the generated slides.

[0059] Step 4:

[0060] The server stores the generated lecture slides and videos in a database.

[0061] Test creation, grading, and recording

[0062] Step 1:

[0063] The server uses AI to automatically generate test questions based on the lesson content.

[0064] Step 2:

[0065] The test questions generated by the server are distributed to students via their terminals.

[0066] Step 3:

[0067] A user takes a test using a terminal and transmits answer data from the terminal to a server.

[0068] Step 4:

[0069] The server analyzes the answer data received using AI and scores the answers.

[0070] Step 5:

[0071] The server records the grading results in a database and organizes them by student.

[0072] Inquiry response

[0073] Step 1:

[0074] Users use their devices to submit questions about the syllabus and credit acquisition.

[0075] Step 2:

[0076] The questions received by the server are analyzed by an AI chatbot.

[0077] Step 3:

[0078] The server generates an appropriate answer based on the analysis results.

[0079] Step 4:

[0080] The server generates a response and sends it to the user via the terminal.

[0081] Example 1

[0082] 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."

[0083] In the traditional university education system, creating course content and preparing and grading tests requires a significant amount of time and cost, making it difficult to manage education efficiently. Furthermore, while prompt and accurate responses to a wide variety of student inquiries are required, responses are often delayed. This results in a decline in the quality of education provided and the student learning experience.

[0084] 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.

[0085] In this invention, the server includes means for automatically generating course videos and scripts, means for storing the generated course videos and scripts in a database, means for automatically generating test questions based on the content of the lessons, means for receiving test data answered by learners, means for automatically scoring the received test data using artificial intelligence, means for recording the scoring results in a database, means for receiving inquiries from learners regarding obtaining credits and analyzing them using natural language processing, means for generating and providing appropriate answers based on the analysis results, means for acquiring information on a specified course topic from the database, means for automatically generating course materials by analyzing the acquired information, means for generating course videos by a virtual instructor based on the materials, and means for providing answers to learners' inquiries in real time using AI. This enables the automatic creation and scoring of course content and tests, and rapid response to inquiries.

[0086] "Lecture videos" are video-based teaching materials created to explain the content of a lesson.

[0087] "Script" refers to the content of the course video written in text format.

[0088] A "database" is a data collection system that systematically organizes and stores information and can be retrieved as needed.

[0089] "Exam questions" are questions or assignments given to measure the level of understanding of the course content.

[0090] "Learner" means an individual receiving an education, such as a student taking a class or taking an exam.

[0091] "Exam data" refers to data that records the answers given by learners to exams.

[0092] "Artificial intelligence" refers to technologies and systems that enable computers to mimic human intelligence.

[0093] "Natural language processing" is a technology that allows computers to understand and analyze human language.

[0094] "Analysis results" refers to the results of information obtained through analytical methods such as natural language processing.

[0095] "Course Materials" refers to textbooks and slide-style teaching materials prepared to supplement the course content.

[0096] A "virtual instructor" is a computer-generated instructor character used to explain a course.

[0097] "Answer" means the answer submitted by a learner to an exam question.

[0098] This system automates university education classes, tests, and grade management, and uses AI technology to provide high-quality education at low cost. Specifically, it uses the following hardware and software to process and calculate various data.

[0099] First, the server retrieves information about the specified course topic from the database. This information includes teaching material data and the course content. Next, the server uses AI algorithms such as TensorFlow and OpenAI GPT to automatically generate course slides based on the retrieved information. Specific content includes matrix calculations and solving linear equations. The server also creates a lecture video by a virtual instructor based on the slides. The lecture video is edited using Adobe Premiere Pro. The generated lecture video and slides are saved in the database so that students can view them later.

[0100] For example, when creating a lesson on "linear algebra," the server retrieves teaching material data related to linear algebra, and the AI ​​generates slides that include matrix calculations and solutions to linear equations. Based on those slides, a lecture video is created and saved in the database.

[0101] Next, the server uses AI to automatically generate test questions based on the class content. The generated test questions are distributed via devices (student PCs or tablets) using the Google Forms API. Users (students) receive a notification, access the test via a specified link, and enter their answers. Once they have finished answering, the data is sent to the server. The server receives this data in real time and automatically grades it using AI. The grade results are recorded in a database and tallied as each student's grade.

[0102] For example, when creating exam questions for "Linear Algebra," the server exports them in Google Forms format and automatically generates questions on matrix calculations and solving linear equations. After students answer these questions and the exam is completed, the answer data is sent to the server, where the AI ​​grades the students and records the scores in a database.

[0103] Furthermore, users can use their devices to send questions about the syllabus or credit acquisition to the server. For example, they can enter a question like, "What math courses should I take next semester?" The question is sent to the server, where an AI chatbot using the OpenAI GPT-3 model analyzes it through natural language processing. Based on the analysis results, an appropriate answer is generated and sent back to the student via the device. This enables quick and accurate responses to student inquiries.

[0104] As a specific example, if a student sends a question such as "Please tell me the syllabus for mathematical statistics," the server searches the database for relevant syllabus information, and the AI ​​organizes that information and responds to the student.

[0105] An example prompt is:

[0106] "Please create slides related to your linear algebra class. Include matrix calculations and solving linear equations."

[0107] "Please create some linear algebra exam questions. Please include matrix calculations and linear equation solving questions."

[0108] "What math courses should I take next semester?"

[0109] By automatically creating and grading course content and exams, this system significantly reduces the costs and labor involved in educational administration, and also reduces the financial burden on students.

[0110] The flow of the identification process in the first embodiment will be described with reference to FIG.

[0111] Step 1: Get course data

[0112] The server retrieves information about a specified course topic from the database. The input is the specified data of the course topic, and the output is the retrieved teaching material data. Specifically, the server executes a query to retrieve teaching material data related to the course topic from the database.

[0113] Step 2: Generate course slides

[0114] The server uses an AI algorithm based on the acquired information to automatically generate course slides. The input is the acquired teaching material data, and the output is the generated course slides. Specifically, TensorFlow is used to analyze the teaching material data and create slides based on the content.

[0115] Step 3: Create a course video

[0116] The server creates a lecture video by a virtual lecturer based on the generated lecture slides. The input is the generated lecture slides, and the output is the lecture video. Specifically, OpenAI GPT and Adobe Premiere Pro are used to generate a video in which the virtual lecturer explains something that matches the content of the slides.

[0117] Step 4: Save your course data

[0118] The server saves the generated lecture slides and videos in a database. The input is the generated lecture slides and videos, and the output is the saved state in the database. Specifically, it saves them in a dedicated table in the database and generates a link so that students can access them later.

[0119] Step 5: Generate exam questions

[0120] The server uses AI to automatically generate test questions based on the content of the lessons. The input is the lesson content data, and the output is the generated test questions. Specifically, the test questions are created using the Google Forms API, and questions on matrix calculations and solving linear equations are automatically generated.

[0121] Step 6: Exam Question Distribution

[0122] The server distributes the generated exam questions to students via their devices. The input is the generated exam questions, and the output is the exam questions notified to the device. Specifically, the server exports the questions in Google Forms format and sends a link to the student's device via notification.

[0123] Step 7: Testing

[0124] Users (students) take exams using their terminals and send their answers to the server. The input is the student's answers, and the output is the answer data sent to the server. Specifically, students enter their answers to the exam questions displayed on their terminals and send them after completion.

[0125] Step 8: Receive test data

[0126] The server checks the received test data in real time and starts the automatic scoring process. The input is the answer data sent from the device, and the output is the scoring results. Specifically, it uses AI to analyze the sent answers and calculates the score for each question.

[0127] Step 9: Record your results

[0128] The server records the grading results in a database and organizes them for each student. The input is the grading result data, and the output is the state recorded in the database. Specifically, the results are saved in the database as each student's grade and organized so that they can be checked later.

[0129] Step 10: Receiving an inquiry

[0130] Users use their terminals to send questions about the syllabus or credit acquisition to the server. The input is the student's question, and the output is the question data received by the server. Specifically, the question content entered in the chat window of the terminal is sent.

[0131] Step 11: Parsing Natural Language

[0132] The server analyzes the received question using an AI chatbot. The input is the received question data, and the output is the analysis result. Specifically, the OpenAI GPT-3 model is used to analyze the question content and understand its intent.

[0133] Step 12: Generate and serve answers

[0134] The server generates an appropriate answer based on the analysis results and returns it to the student via the terminal. The input is the analysis results and the output is the generated answer. Specifically, it searches for relevant information from a database, generates an answer, and returns it to the student.

[0135] (Application example 1)

[0136] 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."

[0137] Automation of classes and grade management in university education is essential for providing students with a high-quality education at low cost. However, conventional systems require manual processes such as generating class content, grading tests, and responding to student inquiries, which requires a great deal of time and effort. Furthermore, in brick-and-mortar stores, staff manually handle customer service and explain products, hindering operational efficiency. To solve these problems, automated systems using advanced AI technology are needed.

[0138] 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.

[0139] In this invention, the server includes means for automatically generating lecture videos and scripts, means for saving the generated lecture videos and scripts in a database, means for automatically generating test questions based on the content of the lectures, means for receiving test data answered by students, means for automatically scoring the received test data using AI, means for recording the scoring results in a database, means for receiving inquiries from students regarding obtaining credits and analyzing them using natural language processing, means for generating and providing appropriate answers based on the analysis results, means for acquiring product information and automatically generating product descriptions for customers using a generative AI model, and means for analyzing customer inquiries using natural language processing and generating and providing appropriate answers.This enables the automation of university education and the efficiency of customer service in physical stores.

[0140] A "server" is a central control device that processes and stores various data and provides it to other terminals as needed.

[0141] "Course videos" are video-based teaching materials created to provide specific educational content visually and aurally.

[0142] A "script" is a document that describes the content of a video lecture as text information and is saved in text format.

[0143] A "generative AI model" is an artificial intelligence algorithm that analyzes information based on a specified task and automatically generates new content or answers.

[0144] A "database" is a system for efficiently storing, searching, and updating large amounts of data.

[0145] "Test items" are questions or problems used to assess a student's understanding.

[0146] "Test data" refers to the answers given by students to test questions.

[0147] "Natural language processing" is a technology that allows computers to understand and analyze human language and generate appropriate responses.

[0148] "Product information" refers to detailed data about a particular product, such as its characteristics, price, and usage.

[0149] "Customer-friendly product description" means text or audio information generated to describe a product in a manner that is easy for customers to understand.

[0150] "Inquiries" refer to questions or inquiries from users or customers.

[0151] "Answer generation" is the process of creating an appropriate response to a query.

[0152] DETAILED DESCRIPTION OF THE PREFERRED EMBODIMENTS The present invention will be described in detail below with reference to the accompanying drawings.

[0153] The server first retrieves information about the specified course topic from a database and then uses AI algorithms to automatically generate course slides and videos. The generated slides and videos are then stored in a database for students to view later. This process is performed using software such as Python and TensorFlow.

[0154] For example, when creating a lesson on "linear algebra," the server retrieves teaching material data related to linear algebra, and the AI ​​generates slides that include matrix calculations and solutions to linear equations. Based on those slides, a lecture video is created and saved in the database.

[0155] Furthermore, the server automatically generates test questions based on the content of the lessons. The generated test questions are distributed to students via their smartphones or PCs. The test data answered by the students is sent to the server, which then automatically scores the received test data using AI. The scoring results are recorded in a database and organized for each student. This process uses a combination of an SQLite database and Python.

[0156] For example, when creating a "linear algebra" test, the server automatically generates questions about matrix calculations and solving linear equations. After students answer these questions and complete the test, the answer data is sent to the server. The AI ​​then scores the students and records the scores in a database.

[0157] In addition, inquiries from students regarding the acquisition of credits are sent to the server via their devices and analyzed using natural language processing. An appropriate answer is generated based on the analysis results and sent back to the student via their device. This makes it possible to improve the efficiency of educational management.

[0158] This system can also be applied to improving operational efficiency in physical stores. The server acquires product information and automatically generates product descriptions for customers using a generative AI model. For example, when a store clerk scans a product barcode with a smartphone app, detailed product information is sent to the server, and the GPT-3 model generates concise and attractive product descriptions based on the product details. It is also possible to analyze customer inquiries using natural language processing and generate appropriate answers to provide to store clerks.

[0159] To illustrate, if a sales associate scans a new lipstick and asks the customer for a brief description, the prompt might be:

[0160] "Please tell your customers about your new lipstick. Below are the details of the product."

[0161] Product Name: High Quality Lipstick

[0162] Features: Long-lasting, moisturizing, contains Vitamin E, allergy tested

[0163] Color: Cherry Red

[0164] Price: 3,000 yen

[0165] How to use: Apply directly to dry lips after applying lip balm.

[0166] This system will enable more efficient university education and more efficient customer service in physical stores.

[0167] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[0168] Step 1:

[0169] The server retrieves information about the specified course topic from the database. The input is the course topic specification, and the output is the retrieved teaching material data. Based on this data, an AI algorithm is used to automatically generate slides.

[0170] Step 2:

[0171] The server creates a lecture video of the virtual lecturer based on the generated slides. The input is the generated slides, and the output is the lecture video. Specifically, the AI ​​reads the content of the slides and creates a video in the form of an explanation.

[0172] Step 3:

[0173] The server saves the generated lecture videos and slides in a database. The input is the lecture videos and slides, and the output is a notification that the videos and slides have been saved to the database, allowing students to access them later.

[0174] Step 4:

[0175] The server automatically generates test questions based on the lesson content. The input is lesson content data, and the output is the generated test questions. It uses an AI algorithm to automatically generate questions related to the lesson content.

[0176] Step 5:

[0177] Students answer test questions via their terminals. The input is the student's answer data, and the output is the transmission of the test answers. Students use their smartphones or PCs to enter their answers to the test questions and send them to the server.

[0178] Step 6:

[0179] The server automatically scores the received test answer data using AI. The input is the student's test answer data, and the output is the scoring results. The AI ​​algorithm analyzes the answers and accurately scores them.

[0180] Step 7:

[0181] The server records the grading results in a database. The input is the grading results, and the output is a notification that the results have been saved to the database. This allows each student's grades to be recorded and viewed.

[0182] Step 8:

[0183] A user's inquiry regarding the acquisition of credits is sent to the server using a terminal. The input is the user's inquiry, and the output is a notification of completion of the transmission to the server. The user enters a question in natural language and sends it to the server.

[0184] Step 9:

[0185] The server analyzes the query using natural language processing. The input is the user's query, and the output is the analysis result. The AI ​​model analyzes the query and extracts the information needed to generate the optimal answer.

[0186] Step 10:

[0187] The server generates an appropriate answer based on the analysis results and sends it back to the user via the terminal. The input is the analysis results and the output is the answer to the user. This allows questions to be answered in real time.

[0188] Step 11:

[0189] The terminal is used to scan the product and send the product information to the server. The input is barcode information, and the output is a notification that the product information has been sent. The store clerk uses a smartphone to scan the product and send the information to the server.

[0190] Step 12:

[0191] The server uses a generative AI model to automatically generate a product description for the customer. The input is the scanned product information, and the output is the generated product description. A generative AI model such as GPT-3 creates an easy-to-understand description based on the product data.

[0192] Step 13:

[0193] The product description generated for the customer is displayed through the terminal. The input is the automatically generated product description, and the output is what is presented to the customer. By having the salesperson show the generated product description to the customer, the appeal of the product can be effectively conveyed.

[0194] 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.

[0195] This invention is a system that uses AI technology to automate university education classes, tests, and grade management, providing low-cost, high-quality education. Furthermore, this invention incorporates an emotion engine that recognizes user emotions, enabling flexible education provision according to the emotional state of each individual user.

[0196] Creating course content

[0197] The server first retrieves information about the specified course topic from a database. Based on this data, an AI algorithm is used to automatically generate course slides. The AI ​​then creates a course video based on the generated slides. During this process, an emotion engine recognizes the user's emotions and can adjust the tone and level of detail of the explanations depending on their state. For example, if the user is feeling tired, the explanation can be made more concise or include words of encouragement. The generated course video and slides are stored in a database and made available for students to view.

[0198] For example, when creating a lesson on "linear algebra," the server retrieves learning material data on linear algebra, and the AI ​​generates slides including matrix calculations and solutions to linear equations. If the emotion engine recognizes that a student is confused, it generates a video with detailed explanations and additional examples, making it easier for students to understand.

[0199] Test creation, grading, and recording

[0200] The server uses AI to automatically generate test questions based on the content of lessons. The generated test questions are distributed to students via their devices. The users (students) take the test using their devices and send their answers to the server. The emotion engine monitors the user's emotions during the test and can adjust the difficulty of the questions if the user is under high stress. For example, if the user is very nervous, the difficulty of the questions can be lowered to reduce the user's burden.

[0201] The received response data is analyzed by the server's AI and automatically graded. The graded results are recorded in a database and organized for each student.

[0202] As a concrete example, when creating a "linear algebra" test, the server automatically generates questions related to matrix calculations and solving linear equations. If the user feels impatient during the test, the emotion engine will slightly lower the difficulty of the questions to maintain performance. When the user completes the test, the answer data is sent to the server, where the AI ​​scores the answer and records the score in a database.

[0203] Inquiry response

[0204] Users use their devices to submit questions about syllabuses or credit acquisition, such as, "What math courses should I take next semester?" The question is sent to a server where an AI chatbot analyzes it through natural language processing. The emotion engine can recognize the emotion of the user's inquiry and generate a response with the appropriate tone and content.

[0205] Based on the analysis, the server generates appropriate responses and sends them back to the student via their device. For example, if a student is feeling anxious, the server can provide not only syllabus information but also additional advice and words of encouragement.

[0206] For example, if a student sends a question such as "Please tell me the syllabus for mathematical statistics," the server will search the database for relevant syllabus information, organize that information, and respond to the student. If the emotion engine recognizes the student's anxiety, the response will also include advice on how to proceed with the study and the necessary preparations.

[0207] As described above, the system of the present invention uses AI technology and an emotion engine to automatically generate lecture videos and scripts, create, grade, and record tests, and respond to inquiries, thereby providing more personalized, high-quality educational services. This system can improve the efficiency of educational management and enhance students' learning experiences. It also significantly reduces the costs and labor required for traditional educational management, thereby easing the financial burden on students.

[0208] The processing flow will be explained below.

[0209] Creating course content

[0210] Step 1:

[0211] The server retrieves information about the specified course topic from the database.

[0212] Step 2:

[0213] Based on the information obtained by the server, lecture slides are automatically generated using an AI algorithm.

[0214] Step 3:

[0215] The server uses AI to automatically generate lecture videos based on the generated slides, and uses an emotion engine to recognize the user's emotional state and adjust the tone and level of detail of the explanations.

[0216] Step 4:

[0217] The server stores the generated lecture slides and videos in a database.

[0218] Test creation, grading, and recording

[0219] Step 1:

[0220] The server uses AI to automatically generate test questions based on the lesson content.

[0221] Step 2:

[0222] The test questions generated by the server are distributed to students via their terminals.

[0223] Step 3:

[0224] The user takes the test using a device and sends the answer data from the device to the server. During the test, the emotion engine monitors the user's emotions and adjusts the difficulty of the questions as needed.

[0225] Step 4:

[0226] The server analyzes the answer data received using AI and scores the answers.

[0227] Step 5:

[0228] The server records the grading results in a database and organizes them by student.

[0229] Inquiry response

[0230] Step 1:

[0231] Users use their devices to submit questions about the syllabus and credit acquisition.

[0232] Step 2:

[0233] The AI ​​chatbot analyzes the questions received by the server, and the emotion engine recognizes the user's emotional state and responds appropriately.

[0234] Step 3:

[0235] The server generates an appropriate answer based on the analysis results.

[0236] Step 4:

[0237] The server generates a response and sends it to the user via the terminal.

[0238] Example 2

[0239] 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."

[0240] Traditional university education systems require a lot of effort and cost for creating educational content, creating and grading tests, and responding to inquiries. It has also been difficult to provide flexible education tailored to students' learning progress, level of understanding, and emotional state. This has led to a standardization of educational quality and a lack of individualized attention, resulting in issues that lead to a decline in student learning efficiency and motivation.

[0241] 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.

[0242] In this invention, the server includes means for automatically generating lecture videos and scripts, means for storing the generated lecture videos and scripts in a database, means for automatically generating test questions based on the content of the lessons, means for receiving test data answered by students, means for automatically scoring the received test data using artificial intelligence, means for recording the scoring results in a database, means for receiving inquiries from students regarding the acquisition of credits, means for analyzing using natural language processing, means for generating and providing appropriate answers based on the analysis results, means for recognizing a user's emotions using an emotion recognition system and adjusting the tone and level of detail of the lecture videos and slides based on the recognized emotions, and means for monitoring the user's emotions during the test and adjusting the difficulty of the test according to the user's stress level. This enables efficient generation of educational content, individualized responses for each student, and appropriate adjustment of the difficulty level.

[0243] 1. "Server" means a computer system that has computing capabilities, manages and processes data over a network, and provides services to other computers or devices.

[0244] 2. "Lecture Video" means video content created to provide students with visual and audio education on academic subjects, technology, etc.

[0245] 3. A "script" is text data that is automatically generated based on the content of the lecture video and slides, and serves as the basis for the text and narration that explain the educational content.

[0246] 4. "Test Questions" are automatically generated questions or tasks used to assess a student's understanding of the learning content.

[0247] 5. "Database" refers to a system for systematically storing and managing information such as course videos, scripts, test data, and grading results.

[0248] 6. "Artificial intelligence" refers to technology that mimics human thought processes and automates data analysis, problem solving, and decision-making.

[0249] 7. "Natural language processing" is a technology that enables computers to understand, analyze, and generate human language, and is used to analyze inquiries and generate appropriate responses.

[0250] 8. An "emotion recognition system" is a technology that analyzes a user's facial expressions and tone of voice to identify their emotional state.

[0251] 9. "Tone" refers to the way information is conveyed or the style of speaking, which is adjusted according to emotion or situation.

[0252] 10. "Level of detail" refers to the specific level of detail provided in the information, and indicates the depth of content and the degree of specificity of the explanation.

[0253] 11. "Emotion" refers to a user's temporary emotional state or psychological response.

[0254] 12. "Stress level" indicates the degree of psychological stress or mental tension felt by the user.

[0255] This invention is a system that uses AI technology to automate university education classes, tests, and grade management, providing low-cost, high-quality education. It also incorporates an emotion engine that recognizes user emotions, enabling flexible education provision according to the emotional state of each individual user.

[0256] First, the server creates the course content. It retrieves information about the specified course topic from the database and automatically generates course slides using a generative AI model (e.g., GPT-4). Next, it creates a course video based on the generated slides using an AI voiceover model. At this time, an emotion recognition system analyzes the user's emotions in real time and can adjust the tone and level of detail of the explanation. The generated course video and slides are stored in the database and can be viewed by students via their devices.

[0257] As a concrete example, when creating a "Linear Algebra" course, the server retrieves teaching material data related to linear algebra from the database, inputs a prompt to the generative AI model saying, "Create slides related to matrix calculations in linear algebra," and creates slides including matrix definitions, calculation procedures, and example problems. It then uses a speech synthesis system (e.g., Google Text-to-Speech) to generate audio that reads the contents of the slides, and generates a video that combines this with the slides.

[0258] The server then automatically generates test questions based on the content of the class. The test questions generated using AI are distributed to students via their devices, who then take the test and send their answers to the server. The emotion recognition system monitors the user's emotions during the test and can adjust the difficulty of the questions according to their stress level. The received answer data is analyzed by the server's AI and automatically scored. The scoring results are recorded in a database and organized for each student.

[0259] As a specific example, when delivering a "Linear Algebra" test, the server inputs a prompt such as "Create test questions centered on matrix calculations" into a generative AI model, generating multiple questions. If a facial expression analysis system (e.g., Affectiva) determines that the user is feeling impatient during the test, the difficulty of the next question can be lowered. When the user completes the test, the answer data is sent to the server, where the AI ​​scores the questions and records the results in a database.

[0260] Users can also use their devices to send questions about the syllabus or credit acquisition to the server. The questions are analyzed by an AI chatbot (using natural language processing technology) and an appropriate answer is generated. The emotion recognition system can recognize the user's emotion when making an inquiry and generate an answer with a tone and content that matches it.

[0261] Example: When a user submits the question, "What math courses should I take next semester?", the server analyzes the question and generates specific advice such as, "The math courses you should take next semester are linear algebra and calculus." If the emotion recognition system recognizes the user's anxiety, it responds with encouraging words such as, "Don't worry, it's okay."

[0262] As described above, the system for implementing the present invention can automatically generate lecture videos and slides, create, grade, and record tests, and respond to inquiries using AI technology and an emotion recognition system, providing personalized, high-quality educational services. This system can improve the efficiency of educational management and enhance students' learning experiences. It can also significantly reduce the costs and labor required for traditional educational management, thereby easing the financial burden on students.

[0263] The flow of the identification process in the second embodiment will be described with reference to FIG.

[0264] Creating course content

[0265] Step 1: Get information about course topics from the database

[0266] The server is given a course topic as input. For example, if the topic is "Linear Algebra," the server accesses the database and executes an SQL query (e.g., "SELECT FROM Courseware WHERE Topic='Linear Algebra'"), which returns information about linear algebra as output.

[0267] Step 2: Automatically generate lecture slides using AI algorithms

[0268] The server uses the acquired teaching material information as input and generates a prompt for the generative AI model, such as "Create slides on matrix calculations in linear algebra." By providing this prompt, the AI ​​algorithm automatically generates the slides. The output is a set of slides that includes matrix definitions, calculation procedures, and example problems.

[0269] Step 3: Generate course videos

[0270] The server uses the generated slides as input and creates a lecture video using an AI voice-over model. For example, it uses a speech synthesis system (e.g., Google Text-to-Speech) to generate a voice that reads the contents of the slides, and combines it with the slides to create a video. The lecture video is generated as output.

[0271] Step 4: Adjust tone and detail with the emotion engine

[0272] The server uses an emotion recognition system to analyze the user's facial expressions and tone of voice. The user's emotional data is provided as input, and the tone and level of detail of the generated video are adjusted as output. For example, if the server determines that the user is feeling fatigued, it generates a video containing a brief explanation and encouraging words.

[0273] Step 5: Save the course video and slides

[0274] The server takes the generated lecture videos and slides as input and stores them in a database. This generates a URL that students can access through their devices. The output is the saved lecture videos and slides and a URL.

[0275] Test creation, grading, and recording

[0276] Step 1: Automatically generate test questions based on lesson content

[0277] The server takes the lesson content as input and generates prompts to the generative AI model, such as "Create test questions centered on matrix calculations." This automatically generates test questions, and a test question set is generated as output.

[0278] Step 2: Distribute the test questions to students

[0279] The server takes the generated test questions as input and distributes them to students via their terminals. For example, it generates a test web page and sends the URL to students via email. The test questions are distributed as output.

[0280] Step 3: Collect user responses and sentiment data

[0281] The user takes the test using a terminal and sends the answer data as input to the server. The emotion recognition system collects the user's emotional data during the test. The answer data and the user's emotional data are obtained as output.

[0282] Step 4: Analyze responses and auto-score

[0283] The server takes the answer data as input and automatically scores it using AI. For example, it analyzes the answer content using a natural language processing (NLP) algorithm and calculates the score based on the point allocation. The scoring result is obtained as output.

[0284] Step 5: Recording and feedback of results

[0285] The server takes the grading results as input, records them in a database, and organizes them for each student. It also automatically generates performance feedback and provides it to students via their devices. The server outputs the grading results and feedback.

[0286] Inquiry response

[0287] Step 1: Submitting a user question

[0288] A user uses a terminal to send a question to the server, for example, "What math courses should I take next semester?" The question data is sent to the server as output.

[0289] Step 2: Parsing the Question

[0290] The server takes the question data as input, analyzes the question using natural language processing technology, and outputs the analysis results.

[0291] Step 3: Generate appropriate answers

[0292] The server uses the analysis results as input and generates an appropriate answer using a generative AI model. For example, it generates an answer such as, "The mathematics courses you should take next semester are linear algebra and calculus." The answer data is obtained as output.

[0293] Step 4: Submit your response

[0294] The server receives the generated answer data as input and responds to the user via the device. The emotion recognition system analyzes the user's emotions and adds words of encouragement as needed. The answer is provided to the user as output.

[0295] (Application example 2)

[0296] 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."

[0297] Conventional educational systems often struggle to individualize education and are unable to respond flexibly to the emotional state of a particular student. This makes it difficult to improve students' understanding, and also results in insufficient individualized responses to increase customer satisfaction. In particular, brick-and-mortar stores require a system that can recognize customers' emotional states in real time and respond appropriately to those states.

[0298] The specific processing by the specific processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means. In this invention, the server includes means for automatically generating lecture videos and scripts, means for saving the generated lecture videos and scripts in a database, and means for automatically generating test questions based on the lesson content. This enables the automatic generation of lecture videos and scripts, making it possible to improve the efficiency and quality of education.

[0299] The system also includes a means for receiving test data answered by students using a user device, a means for automatically scoring the received test data using AI, a means for recording the scoring results in a database, a means for receiving inquiries from students regarding obtaining credits and analyzing them using natural language processing, a means for generating and providing appropriate answers based on the analysis results, a means for monitoring the user's emotional state in real time using an emotion recognition engine, and a means for providing a response method according to the user's emotional state.This enables flexible responses according to the student's emotional state, thereby achieving individualized education.In addition, in customer service, it enables appropriate responses in real time according to the customer's emotional state, thereby improving customer satisfaction.

[0300] "Means for automatically generating lecture videos and scripts" refers to technology that uses algorithms or models to automatically generate educational content on specified topics and corresponding scripts.

[0301] "Means for storing the generated lecture videos and scripts in a database" refers to a technology that stores the generated educational content in a database in a persistent format so that it can be accessed and referenced later.

[0302] "Means for automatically generating test questions based on class content" refers to technology that automatically generates assessment questions based on the topic and content of a class and presents them to test takers.

[0303] "Means for receiving test data answered by students using user devices" refers to technology for sending and receiving data on students' answers to test questions to a server via the Internet or a local network.

[0304] "Means for automatically scoring received test data using AI" refers to a technology that uses artificial intelligence technology to evaluate the test data answered by test takers and automatically calculate scores.

[0305] "Means for recording scoring results in a database" refers to a technology that stores the results scored by AI in a database so that they can be accessed and referenced later.

[0306] "Means for receiving inquiries from students regarding the acquisition of credits and analyzing them using natural language processing" refers to a technology in which students submit questions regarding the acquisition of credits or courses and the questions are analyzed using natural language processing technology.

[0307] "Means for generating and providing appropriate answers based on analysis results" refers to technology that automatically generates appropriate, contextual answers based on the results of analysis using natural language processing and provides them to users.

[0308] "Means for monitoring a user's emotional state in real time using an emotion recognition engine" is a technology that analyzes image data, audio data, etc. to identify a user's current emotional state in real time.

[0309] The "means for providing a response method according to the user's emotional state" is a technology that automatically generates appropriate response methods and advice based on the recognized emotional state and provides them to the user.

[0310] This invention is a system that combines AI technology and emotion recognition technology to respond to the needs of education and customer service by providing personalized responses according to the user's emotional state. The system operates mainly with three parties: a server, a terminal, and the user.

[0311] server

[0312] The server first retrieves information about the specified topic from the database. Based on this data, the algorithm uses a generative AI model to automatically generate lecture slides and lecture videos. An emotion recognition engine monitors the user's emotional state and, for example, if the user is feeling tired, generates a concise, encouraging video. The generated lecture videos and scripts are stored in the database and can be viewed by users.

[0313] Next, the generative AI model automatically generates test questions based on the lesson content. The generated test is delivered to the user's device, and the user takes the test. The answers are sent from the device to a server, and the server's AI automatically scores the received test data. The scoring results are recorded in a database and can be viewed by the user later.

[0314] Terminal

[0315] Users use devices such as smart glasses. These devices capture the user's facial expressions and voice in real time, and an emotion recognition engine analyzes the data. Based on the analysis results, the device provides the user with appropriate advice and methods of response in real time. For example, if a salesperson in a physical store is using smart glasses and the customer looks anxious, a message will appear on the glasses' display saying, "This customer seems anxious. Please try to explain in a way that puts them at ease."

[0316] User

[0317] In implementing the invention, users use the system on the front lines. For example, they watch video lectures and answer generated tests. If they have any questions, they input them in natural language, and the system generates and provides appropriate answers.

[0318] Specific examples

[0319] For example, in a university linear algebra class, a server retrieves linear algebra teaching data, and a generative AI model generates slides including matrix calculations and linear equation solutions. If an emotion recognition engine detects that a student is confused, it creates a video with more detailed explanations and additional examples, helping students to deepen their understanding.

[0320] An example of a prompt would be:

[0321] You are a sales staff member at a brick-and-mortar store wearing smart glasses. The camera is currently capturing the facial expression of a customer standing at the counter. If the customer's emotion is recognized as "anxiety," the advice displayed is "This customer seems anxious. Try to explain in a reassuring way."

[0322] By utilizing these technologies, it is possible to personalize education and improve customer service. This system makes it possible to flexibly respond to individual needs that would be difficult to meet using conventional methods.

[0323] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[0324] Step 1:

[0325] The server retrieves information about the specified course topic from the database, including lecture content, slides, references, etc. It processes the input data from the database and extracts the necessary information about the topic.

[0326] Step 2:

[0327] The server uses a generative AI model based on the acquired data to automatically generate lecture slides and lecture videos. The generative AI model analyzes the text data and generates appropriate visual content and explanatory text. The generated lecture slides and lecture videos are stored in a database. The input is teaching material data related to the topic, and the output is the generated slides and lecture videos.

[0328] Step 3:

[0329] The server receives requests for access to the lecture videos and slides from users' devices. Users send requests to view the lectures using devices such as smart glasses or PCs. Based on the requests, the server distributes the generated content to the users' devices.

[0330] Step 4:

[0331] While the user is watching the lecture video, the emotion recognition engine analyzes the user's facial expressions and voice in real time through the smart glasses and camera. The input is the user's real-time video and audio data, and the output is the user's emotional state.

[0332] Step 5:

[0333] The server receives the user's emotional state from the emotion recognition engine and adjusts the content of the lecture video and slides in real time. For example, if the server detects that the user is confused, it generates a video with detailed explanations and additional examples and provides it to the user. The input is the user's emotional state, and the output is the adjusted educational content.

[0334] Step 6:

[0335] The server automatically creates test questions using a generative AI model based on the content of the lecture. The generated test questions are then delivered to the user's device. The input is the lecture content data, and the output is the generated test questions.

[0336] Step 7:

[0337] Users answer test questions using their devices and send their answers to the server. The server analyzes the received test data and automatically scores it using an AI model. The input is the user's test answer data, and the output is the scoring results.

[0338] Step 8:

[0339] The server records the scoring results in a database so that users can check them later. The input is the scoring result data, and the output is the results recorded in the database.

[0340] Step 9:

[0341] The device receives inquiries from users regarding the acquisition of credits and sends the details to the server. The server analyzes the inquiries using AI models and natural language processing and generates appropriate answers. The input is the text data of the inquiries, and the output is the analysis results and the generated answers.

[0342] Step 10:

[0343] The server sends the generated answer to the user's terminal and provides it to the user. The input is the generated answer, and the output is the answer displayed on the user's terminal.

[0344] Through these steps, we can provide efficient, high-quality service that meets the individual needs of our users in both education and customer service.

[0345] 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.

[0346] 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.

[0347] 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.

[0348] [Second embodiment]

[0349] FIG. 3 shows an example of the configuration of a data processing system 210 according to the second embodiment.

[0350] 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.

[0351] 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).

[0352] 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.

[0353] 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.

[0354] 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).

[0355] 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.

[0356] 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.

[0357] 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.

[0358] 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.

[0359] 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.

[0360] 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."

[0361] This invention is a system for automating university education classes, tests, and grade management, and uses AI technology to provide high-quality education at low cost. Each function of this system is explained in detail below.

[0362] Creating course content

[0363] The server first retrieves information about the specified course topic from the database. Based on this data, an AI algorithm is used to automatically generate course slides. The AI ​​then creates a course video based on the generated slides. This video is structured in a format where a virtual instructor explains the slides, and is designed to be easy for students to understand. The generated course video and slides are saved in the database so that students can view them later.

[0364] For example, when creating a lesson on "linear algebra," the server retrieves teaching material data related to linear algebra, and the AI ​​generates slides that include matrix calculations and solutions to linear equations. Based on those slides, a lecture video is created and saved in the database.

[0365] Test creation, grading, and recording

[0366] The server uses AI to automatically generate test questions based on the content of the class. The generated test questions are distributed to students via their devices. Users (students) take the test using their devices and send their answers to the server.

[0367] The received response data is analyzed by the server's AI and automatically graded. The graded results are recorded in a database and organized for each student.

[0368] For example, when creating a "linear algebra" test, the server automatically generates questions about matrix calculations and solving linear equations. After students answer these questions and complete the test, the answer data is sent to the server. The AI ​​then scores the students and records the scores in a database.

[0369] Inquiry response

[0370] Users use their devices to submit questions about the syllabus or credit acquisition. For example, they might type, "What math courses should I take next semester?" The question is sent to the server, where the AI ​​chatbot analyzes it using natural language processing. Based on the analysis results, the AI ​​chatbot generates an appropriate answer and responds to the student via their device.

[0371] In this way, the server can respond to student inquiries in real time and provide course registration information and the conditions necessary to obtain credits. This type of response also contributes to the efficiency of educational management.

[0372] As a specific example, if a student sends a question such as "Please tell me the syllabus for mathematical statistics," the server searches the database for relevant syllabus information, and the AI ​​organizes that information and responds to the student.

[0373] As described above, the system of the present invention uses AI technology to automatically generate lecture videos and scripts, create, grade, and record tests, and respond to inquiries, making it possible to provide high-quality educational services at low cost. This system can significantly reduce the costs and labor required for traditional educational operations, and also ease the financial burden on students.

[0374] The processing flow will be explained below.

[0375] Creating course content

[0376] Step 1:

[0377] The server retrieves information about the specified course topic from the database.

[0378] Step 2:

[0379] Based on the information obtained by the server, lecture slides are automatically generated using an AI algorithm.

[0380] Step 3:

[0381] The server uses AI to automatically generate lecture videos based on the generated slides.

[0382] Step 4:

[0383] The server stores the generated lecture slides and videos in a database.

[0384] Test creation, grading, and recording

[0385] Step 1:

[0386] The server uses AI to automatically generate test questions based on the lesson content.

[0387] Step 2:

[0388] The test questions generated by the server are distributed to students via their terminals.

[0389] Step 3:

[0390] A user takes a test using a terminal and transmits answer data from the terminal to a server.

[0391] Step 4:

[0392] The server analyzes the answer data received using AI and scores the answers.

[0393] Step 5:

[0394] The server records the grading results in a database and organizes them by student.

[0395] Inquiry response

[0396] Step 1:

[0397] Users use their devices to submit questions about the syllabus and credit acquisition.

[0398] Step 2:

[0399] The questions received by the server are analyzed by an AI chatbot.

[0400] Step 3:

[0401] The server generates an appropriate answer based on the analysis results.

[0402] Step 4:

[0403] The server generates a response and sends it to the user via the terminal.

[0404] Example 1

[0405] 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."

[0406] In the traditional university education system, creating course content and preparing and grading tests requires a significant amount of time and cost, making it difficult to manage education efficiently. Furthermore, while prompt and accurate responses to a wide variety of student inquiries are required, responses are often delayed. This results in a decline in the quality of education provided and the student learning experience.

[0407] 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.

[0408] In this invention, the server includes means for automatically generating course videos and scripts, means for storing the generated course videos and scripts in a database, means for automatically generating test questions based on the content of the lessons, means for receiving test data answered by learners, means for automatically scoring the received test data using artificial intelligence, means for recording the scoring results in a database, means for receiving inquiries from learners regarding obtaining credits and analyzing them using natural language processing, means for generating and providing appropriate answers based on the analysis results, means for acquiring information on a specified course topic from the database, means for automatically generating course materials by analyzing the acquired information, means for generating course videos by a virtual instructor based on the materials, and means for providing answers to learners' inquiries in real time using AI. This enables the automatic creation and scoring of course content and tests, and rapid response to inquiries.

[0409] "Lecture videos" are video-based teaching materials created to explain the content of a lesson.

[0410] "Script" refers to the content of the course video written in text format.

[0411] A "database" is a data collection system that systematically organizes and stores information and can be retrieved as needed.

[0412] "Exam questions" are questions or assignments given to measure the level of understanding of the course content.

[0413] "Learner" means an individual receiving an education, such as a student taking a class or taking an exam.

[0414] "Exam data" refers to data that records the answers given by learners to exams.

[0415] "Artificial intelligence" refers to technologies and systems that enable computers to mimic human intelligence.

[0416] "Natural language processing" is a technology that allows computers to understand and analyze human language.

[0417] "Analysis results" refers to the results of information obtained through analytical methods such as natural language processing.

[0418] "Course Materials" refers to textbooks and slide-style teaching materials prepared to supplement the course content.

[0419] A "virtual instructor" is a computer-generated instructor character used to explain a course.

[0420] "Answer" means the answer submitted by a learner to an exam question.

[0421] This system automates university education classes, tests, and grade management, and uses AI technology to provide high-quality education at low cost. Specifically, it uses the following hardware and software to process and calculate various data.

[0422] First, the server retrieves information about the specified course topic from the database. This information includes teaching material data and the course content. Next, the server uses AI algorithms such as TensorFlow and OpenAI GPT to automatically generate course slides based on the retrieved information. Specific content includes matrix calculations and solving linear equations. The server also creates a lecture video by a virtual instructor based on the slides. The lecture video is edited using Adobe Premiere Pro. The generated lecture video and slides are saved in the database so that students can view them later.

[0423] For example, when creating a lesson on "linear algebra," the server retrieves teaching material data related to linear algebra, and the AI ​​generates slides that include matrix calculations and solutions to linear equations. Based on those slides, a lecture video is created and saved in the database.

[0424] Next, the server uses AI to automatically generate test questions based on the class content. The generated test questions are distributed via devices (student PCs or tablets) using the Google Forms API. Users (students) receive a notification, access the test via a specified link, and enter their answers. Once they have finished answering, the data is sent to the server. The server receives this data in real time and automatically grades it using AI. The grade results are recorded in a database and tallied as each student's grade.

[0425] For example, when creating exam questions for "Linear Algebra," the server exports them in Google Forms format and automatically generates questions on matrix calculations and solving linear equations. After students answer these questions and the exam is completed, the answer data is sent to the server, where the AI ​​grades the students and records the scores in a database.

[0426] Furthermore, users can use their devices to send questions about the syllabus or credit acquisition to the server. For example, they can enter a question like, "What math courses should I take next semester?" The question is sent to the server, where an AI chatbot using the OpenAI GPT-3 model analyzes it through natural language processing. Based on the analysis results, an appropriate answer is generated and sent back to the student via the device. This enables quick and accurate responses to student inquiries.

[0427] As a specific example, if a student sends a question such as "Please tell me the syllabus for mathematical statistics," the server searches the database for relevant syllabus information, and the AI ​​organizes that information and responds to the student.

[0428] An example prompt is:

[0429] "Please create slides related to your linear algebra class. Include matrix calculations and solving linear equations."

[0430] "Please create some linear algebra exam questions. Please include matrix calculations and linear equation solving questions."

[0431] "What math courses should I take next semester?"

[0432] By automatically creating and grading course content and exams, this system significantly reduces the costs and labor involved in educational administration, and also reduces the financial burden on students.

[0433] The flow of the identification process in the first embodiment will be described with reference to FIG.

[0434] Step 1: Get course data

[0435] The server retrieves information about a specified course topic from the database. The input is the specified data of the course topic, and the output is the retrieved teaching material data. Specifically, the server executes a query to retrieve teaching material data related to the course topic from the database.

[0436] Step 2: Generate course slides

[0437] The server uses an AI algorithm based on the acquired information to automatically generate course slides. The input is the acquired teaching material data, and the output is the generated course slides. Specifically, TensorFlow is used to analyze the teaching material data and create slides based on the content.

[0438] Step 3: Create a course video

[0439] The server creates a lecture video by a virtual lecturer based on the generated lecture slides. The input is the generated lecture slides, and the output is the lecture video. Specifically, OpenAI GPT and Adobe Premiere Pro are used to generate a video in which the virtual lecturer explains something that matches the content of the slides.

[0440] Step 4: Save your course data

[0441] The server saves the generated lecture slides and videos in a database. The input is the generated lecture slides and videos, and the output is the saved state in the database. Specifically, it saves them in a dedicated table in the database and generates a link so that students can access them later.

[0442] Step 5: Generate exam questions

[0443] The server uses AI to automatically generate test questions based on the content of the lessons. The input is the lesson content data, and the output is the generated test questions. Specifically, the test questions are created using the Google Forms API, and questions on matrix calculations and solving linear equations are automatically generated.

[0444] Step 6: Exam Question Distribution

[0445] The server distributes the generated exam questions to students via their devices. The input is the generated exam questions, and the output is the exam questions notified to the device. Specifically, the server exports the questions in Google Forms format and sends a link to the student's device via notification.

[0446] Step 7: Testing

[0447] Users (students) take exams using their terminals and send their answers to the server. The input is the student's answers, and the output is the answer data sent to the server. Specifically, students enter their answers to the exam questions displayed on their terminals and send them after completion.

[0448] Step 8: Receive test data

[0449] The server checks the received test data in real time and starts the automatic scoring process. The input is the answer data sent from the device, and the output is the scoring results. Specifically, it uses AI to analyze the sent answers and calculates the score for each question.

[0450] Step 9: Record your results

[0451] The server records the grading results in a database and organizes them for each student. The input is the grading result data, and the output is the state recorded in the database. Specifically, the results are saved in the database as each student's grade and organized so that they can be checked later.

[0452] Step 10: Receiving an inquiry

[0453] Users use their terminals to send questions about the syllabus or credit acquisition to the server. The input is the student's question, and the output is the question data received by the server. Specifically, the question content entered in the chat window of the terminal is sent.

[0454] Step 11: Parsing Natural Language

[0455] The server analyzes the received question using an AI chatbot. The input is the received question data, and the output is the analysis result. Specifically, the OpenAI GPT-3 model is used to analyze the question content and understand its intent.

[0456] Step 12: Generate and serve answers

[0457] The server generates an appropriate answer based on the analysis results and returns it to the student via the terminal. The input is the analysis results and the output is the generated answer. Specifically, it searches for relevant information from a database, generates an answer, and returns it to the student.

[0458] (Application example 1)

[0459] 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."

[0460] Automation of classes and grade management in university education is essential for providing students with a high-quality education at low cost. However, conventional systems require manual processes such as generating class content, grading tests, and responding to student inquiries, which requires a great deal of time and effort. Furthermore, in brick-and-mortar stores, staff manually handle customer service and explain products, hindering operational efficiency. To solve these problems, automated systems using advanced AI technology are needed.

[0461] 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.

[0462] In this invention, the server includes means for automatically generating lecture videos and scripts, means for saving the generated lecture videos and scripts in a database, means for automatically generating test questions based on the content of the lectures, means for receiving test data answered by students, means for automatically scoring the received test data using AI, means for recording the scoring results in a database, means for receiving inquiries from students regarding obtaining credits and analyzing them using natural language processing, means for generating and providing appropriate answers based on the analysis results, means for acquiring product information and automatically generating product descriptions for customers using a generative AI model, and means for analyzing customer inquiries using natural language processing and generating and providing appropriate answers.This enables the automation of university education and the efficiency of customer service in physical stores.

[0463] A "server" is a central control device that processes and stores various data and provides it to other terminals as needed.

[0464] "Course videos" are video-based teaching materials created to provide specific educational content visually and aurally.

[0465] A "script" is a document that describes the content of a video lecture as text information and is saved in text format.

[0466] A "generative AI model" is an artificial intelligence algorithm that analyzes information based on a specified task and automatically generates new content or answers.

[0467] A "database" is a system for efficiently storing, searching, and updating large amounts of data.

[0468] "Test items" are questions or problems used to assess a student's understanding.

[0469] "Test data" refers to the answers given by students to test questions.

[0470] "Natural language processing" is a technology that allows computers to understand and analyze human language and generate appropriate responses.

[0471] "Product information" refers to detailed data about a particular product, such as its characteristics, price, and usage.

[0472] "Customer-friendly product description" means text or audio information generated to describe a product in a manner that is easy for customers to understand.

[0473] "Inquiries" refer to questions or inquiries from users or customers.

[0474] "Answer generation" is the process of creating an appropriate response to a query.

[0475] DETAILED DESCRIPTION OF THE PREFERRED EMBODIMENTS The present invention will be described in detail below with reference to the accompanying drawings.

[0476] The server first retrieves information about the specified course topic from a database and then uses AI algorithms to automatically generate course slides and videos. The generated slides and videos are then stored in a database for students to view later. This process is performed using software such as Python and TensorFlow.

[0477] For example, when creating a lesson on "linear algebra," the server retrieves teaching material data related to linear algebra, and the AI ​​generates slides that include matrix calculations and solutions to linear equations. Based on those slides, a lecture video is created and saved in the database.

[0478] Furthermore, the server automatically generates test questions based on the content of the lessons. The generated test questions are distributed to students via their smartphones or PCs. The test data answered by the students is sent to the server, which then automatically scores the received test data using AI. The scoring results are recorded in a database and organized for each student. This process uses a combination of an SQLite database and Python.

[0479] For example, when creating a "linear algebra" test, the server automatically generates questions about matrix calculations and solving linear equations. After students answer these questions and complete the test, the answer data is sent to the server. The AI ​​then scores the students and records the scores in a database.

[0480] In addition, inquiries from students regarding the acquisition of credits are sent to the server via their devices and analyzed using natural language processing. An appropriate answer is generated based on the analysis results and sent back to the student via their device. This makes it possible to improve the efficiency of educational management.

[0481] This system can also be applied to improving operational efficiency in physical stores. The server acquires product information and automatically generates product descriptions for customers using a generative AI model. For example, when a store clerk scans a product barcode with a smartphone app, detailed product information is sent to the server, and the GPT-3 model generates concise and attractive product descriptions based on the product details. It is also possible to analyze customer inquiries using natural language processing and generate appropriate answers to provide to store clerks.

[0482] To illustrate, if a sales associate scans a new lipstick and asks the customer for a brief description, the prompt might be:

[0483] "Please tell your customers about your new lipstick. Below are the details of the product."

[0484] Product Name: High Quality Lipstick

[0485] Features: Long-lasting, moisturizing, contains Vitamin E, allergy tested

[0486] Color: Cherry Red

[0487] Price: 3,000 yen

[0488] How to use: Apply directly to dry lips after applying lip balm.

[0489] This system will enable more efficient university education and more efficient customer service in physical stores.

[0490] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[0491] Step 1:

[0492] The server retrieves information about the specified course topic from the database. The input is the course topic specification, and the output is the retrieved teaching material data. Based on this data, an AI algorithm is used to automatically generate slides.

[0493] Step 2:

[0494] The server creates a lecture video of the virtual lecturer based on the generated slides. The input is the generated slides, and the output is the lecture video. Specifically, the AI ​​reads the content of the slides and creates a video in the form of an explanation.

[0495] Step 3:

[0496] The server saves the generated lecture videos and slides in a database. The input is the lecture videos and slides, and the output is a notification that the videos and slides have been saved to the database, allowing students to access them later.

[0497] Step 4:

[0498] The server automatically generates test questions based on the lesson content. The input is lesson content data, and the output is the generated test questions. It uses an AI algorithm to automatically generate questions related to the lesson content.

[0499] Step 5:

[0500] Students answer test questions via their terminals. The input is the student's answer data, and the output is the transmission of the test answers. Students use their smartphones or PCs to enter their answers to the test questions and send them to the server.

[0501] Step 6:

[0502] The server automatically scores the received test answer data using AI. The input is the student's test answer data, and the output is the scoring results. The AI ​​algorithm analyzes the answers and accurately scores them.

[0503] Step 7:

[0504] The server records the grading results in a database. The input is the grading results, and the output is a notification that the results have been saved to the database. This allows each student's grades to be recorded and viewed.

[0505] Step 8:

[0506] A user's inquiry regarding the acquisition of credits is sent to the server using a terminal. The input is the user's inquiry, and the output is a notification of completion of the transmission to the server. The user enters a question in natural language and sends it to the server.

[0507] Step 9:

[0508] The server analyzes the query using natural language processing. The input is the user's query, and the output is the analysis result. The AI ​​model analyzes the query and extracts the information needed to generate the optimal answer.

[0509] Step 10:

[0510] The server generates an appropriate answer based on the analysis results and sends it back to the user via the terminal. The input is the analysis results and the output is the answer to the user. This allows questions to be answered in real time.

[0511] Step 11:

[0512] The terminal is used to scan the product and send the product information to the server. The input is barcode information, and the output is a notification that the product information has been sent. The store clerk uses a smartphone to scan the product and send the information to the server.

[0513] Step 12:

[0514] The server uses a generative AI model to automatically generate a product description for the customer. The input is the scanned product information, and the output is the generated product description. A generative AI model such as GPT-3 creates an easy-to-understand description based on the product data.

[0515] Step 13:

[0516] The product description generated for the customer is displayed through the terminal. The input is the automatically generated product description, and the output is what is presented to the customer. By having the salesperson show the generated product description to the customer, the appeal of the product can be effectively conveyed.

[0517] 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.

[0518] This invention is a system that uses AI technology to automate university education classes, tests, and grade management, providing low-cost, high-quality education. Furthermore, this invention incorporates an emotion engine that recognizes user emotions, enabling flexible education provision according to the emotional state of each individual user.

[0519] Creating course content

[0520] The server first retrieves information about the specified course topic from a database. Based on this data, an AI algorithm is used to automatically generate course slides. The AI ​​then creates a course video based on the generated slides. During this process, an emotion engine recognizes the user's emotions and can adjust the tone and level of detail of the explanations depending on their state. For example, if the user is feeling tired, the explanation can be made more concise or include words of encouragement. The generated course video and slides are stored in a database and made available for students to view.

[0521] For example, when creating a lesson on "linear algebra," the server retrieves learning material data on linear algebra, and the AI ​​generates slides including matrix calculations and solutions to linear equations. If the emotion engine recognizes that a student is confused, it generates a video with detailed explanations and additional examples, making it easier for students to understand.

[0522] Test creation, grading, and recording

[0523] The server uses AI to automatically generate test questions based on the content of lessons. The generated test questions are distributed to students via their devices. The users (students) take the test using their devices and send their answers to the server. The emotion engine monitors the user's emotions during the test and can adjust the difficulty of the questions if the user is under high stress. For example, if the user is very nervous, the difficulty of the questions can be lowered to reduce the user's burden.

[0524] The received response data is analyzed by the server's AI and automatically graded. The graded results are recorded in a database and organized for each student.

[0525] As a concrete example, when creating a "linear algebra" test, the server automatically generates questions related to matrix calculations and solving linear equations. If the user feels impatient during the test, the emotion engine will slightly lower the difficulty of the questions to maintain performance. When the user completes the test, the answer data is sent to the server, where the AI ​​scores the answer and records the score in a database.

[0526] Inquiry response

[0527] Users use their devices to submit questions about syllabuses or credit acquisition, such as, "What math courses should I take next semester?" The question is sent to a server where an AI chatbot analyzes it through natural language processing. The emotion engine can recognize the emotion of the user's inquiry and generate a response with the appropriate tone and content.

[0528] Based on the analysis, the server generates appropriate responses and sends them back to the student via their device. For example, if a student is feeling anxious, the server can provide not only syllabus information but also additional advice and words of encouragement.

[0529] For example, if a student sends a question such as "Please tell me the syllabus for mathematical statistics," the server will search the database for relevant syllabus information, organize that information, and respond to the student. If the emotion engine recognizes the student's anxiety, the response will also include advice on how to proceed with the study and the necessary preparations.

[0530] As described above, the system of the present invention uses AI technology and an emotion engine to automatically generate lecture videos and scripts, create, grade, and record tests, and respond to inquiries, thereby providing more personalized, high-quality educational services. This system can improve the efficiency of educational management and enhance students' learning experiences. It also significantly reduces the costs and labor required for traditional educational management, thereby easing the financial burden on students.

[0531] The processing flow will be explained below.

[0532] Creating course content

[0533] Step 1:

[0534] The server retrieves information about the specified course topic from the database.

[0535] Step 2:

[0536] Based on the information obtained by the server, lecture slides are automatically generated using an AI algorithm.

[0537] Step 3:

[0538] The server uses AI to automatically generate lecture videos based on the generated slides, and uses an emotion engine to recognize the user's emotional state and adjust the tone and level of detail of the explanations.

[0539] Step 4:

[0540] The server stores the generated lecture slides and videos in a database.

[0541] Test creation, grading, and recording

[0542] Step 1:

[0543] The server uses AI to automatically generate test questions based on the lesson content.

[0544] Step 2:

[0545] The test questions generated by the server are distributed to students via their terminals.

[0546] Step 3:

[0547] The user takes the test using a device and sends the answer data from the device to the server. During the test, the emotion engine monitors the user's emotions and adjusts the difficulty of the questions as needed.

[0548] Step 4:

[0549] The server analyzes the answer data received using AI and scores the answers.

[0550] Step 5:

[0551] The server records the grading results in a database and organizes them by student.

[0552] Inquiry response

[0553] Step 1:

[0554] Users use their devices to submit questions about the syllabus and credit acquisition.

[0555] Step 2:

[0556] The AI ​​chatbot analyzes the questions received by the server, and the emotion engine recognizes the user's emotional state and responds appropriately.

[0557] Step 3:

[0558] The server generates an appropriate answer based on the analysis results.

[0559] Step 4:

[0560] The server generates a response and sends it to the user via the terminal.

[0561] Example 2

[0562] 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."

[0563] Traditional university education systems require a lot of effort and cost for creating educational content, creating and grading tests, and responding to inquiries. It has also been difficult to provide flexible education tailored to students' learning progress, level of understanding, and emotional state. This has led to a standardization of educational quality and a lack of individualized attention, resulting in issues that lead to a decline in student learning efficiency and motivation.

[0564] 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.

[0565] In this invention, the server includes means for automatically generating lecture videos and scripts, means for storing the generated lecture videos and scripts in a database, means for automatically generating test questions based on the content of the lessons, means for receiving test data answered by students, means for automatically scoring the received test data using artificial intelligence, means for recording the scoring results in a database, means for receiving inquiries from students regarding the acquisition of credits, means for analyzing using natural language processing, means for generating and providing appropriate answers based on the analysis results, means for recognizing a user's emotions using an emotion recognition system and adjusting the tone and level of detail of the lecture videos and slides based on the recognized emotions, and means for monitoring the user's emotions during the test and adjusting the difficulty of the test according to the user's stress level. This enables efficient generation of educational content, individualized responses for each student, and appropriate adjustment of the difficulty level.

[0566] 1. "Server" means a computer system that has computing capabilities, manages and processes data over a network, and provides services to other computers or devices.

[0567] 2. "Lecture Video" means video content created to provide students with visual and audio education on academic subjects, technology, etc.

[0568] 3. A "script" is text data that is automatically generated based on the content of the lecture video and slides, and serves as the basis for the text and narration that explain the educational content.

[0569] 4. "Test Questions" are automatically generated questions or tasks used to assess a student's understanding of the learning content.

[0570] 5. "Database" refers to a system for systematically storing and managing information such as course videos, scripts, test data, and grading results.

[0571] 6. "Artificial intelligence" refers to technology that mimics human thought processes and automates data analysis, problem solving, and decision-making.

[0572] 7. "Natural language processing" is a technology that enables computers to understand, analyze, and generate human language, and is used to analyze inquiries and generate appropriate responses.

[0573] 8. An "emotion recognition system" is a technology that analyzes a user's facial expressions and tone of voice to identify their emotional state.

[0574] 9. "Tone" refers to the way information is conveyed or the style of speaking, which is adjusted according to emotion or situation.

[0575] 10. "Level of detail" refers to the specific level of detail provided in the information, and indicates the depth of content and the degree of specificity of the explanation.

[0576] 11. "Emotion" refers to a user's temporary emotional state or psychological response.

[0577] 12. "Stress level" indicates the degree of psychological stress or mental tension felt by the user.

[0578] This invention is a system that uses AI technology to automate university education classes, tests, and grade management, providing low-cost, high-quality education. It also incorporates an emotion engine that recognizes user emotions, enabling flexible education provision according to the emotional state of each individual user.

[0579] First, the server creates the course content. It retrieves information about the specified course topic from the database and automatically generates course slides using a generative AI model (e.g., GPT-4). Next, it creates a course video based on the generated slides using an AI voiceover model. At this time, an emotion recognition system analyzes the user's emotions in real time and can adjust the tone and level of detail of the explanation. The generated course video and slides are stored in the database and can be viewed by students via their devices.

[0580] As a concrete example, when creating a "Linear Algebra" course, the server retrieves teaching material data related to linear algebra from the database, inputs a prompt to the generative AI model saying, "Create slides related to matrix calculations in linear algebra," and creates slides including matrix definitions, calculation procedures, and example problems. It then uses a speech synthesis system (e.g., Google Text-to-Speech) to generate audio that reads the contents of the slides, and generates a video that combines this with the slides.

[0581] The server then automatically generates test questions based on the content of the class. The test questions generated using AI are distributed to students via their devices, who then take the test and send their answers to the server. The emotion recognition system monitors the user's emotions during the test and can adjust the difficulty of the questions according to their stress level. The received answer data is analyzed by the server's AI and automatically scored. The scoring results are recorded in a database and organized for each student.

[0582] As a specific example, when delivering a "Linear Algebra" test, the server inputs a prompt such as "Create test questions centered on matrix calculations" into a generative AI model, generating multiple questions. If a facial expression analysis system (e.g., Affectiva) determines that the user is feeling impatient during the test, the difficulty of the next question can be lowered. When the user completes the test, the answer data is sent to the server, where the AI ​​scores the questions and records the results in a database.

[0583] Users can also use their devices to send questions about the syllabus or credit acquisition to the server. The questions are analyzed by an AI chatbot (using natural language processing technology) and an appropriate answer is generated. The emotion recognition system can recognize the user's emotion when making an inquiry and generate an answer with a tone and content that matches it.

[0584] Example: When a user submits the question, "What math courses should I take next semester?", the server analyzes the question and generates specific advice such as, "The math courses you should take next semester are linear algebra and calculus." If the emotion recognition system recognizes the user's anxiety, it responds with encouraging words such as, "Don't worry, it's okay."

[0585] As described above, the system for implementing the present invention can automatically generate lecture videos and slides, create, grade, and record tests, and respond to inquiries using AI technology and an emotion recognition system, providing personalized, high-quality educational services. This system can improve the efficiency of educational management and enhance students' learning experiences. It can also significantly reduce the costs and labor required for traditional educational management, thereby easing the financial burden on students.

[0586] The flow of the identification process in the second embodiment will be described with reference to FIG.

[0587] Creating course content

[0588] Step 1: Get information about course topics from the database

[0589] The server is given a course topic as input. For example, if the topic is "Linear Algebra," the server accesses the database and executes an SQL query (e.g., "SELECT FROM Courseware WHERE Topic='Linear Algebra'"), which returns information about linear algebra as output.

[0590] Step 2: Automatically generate lecture slides using AI algorithms

[0591] The server uses the acquired teaching material information as input and generates a prompt for the generative AI model, such as "Create slides on matrix calculations in linear algebra." By providing this prompt, the AI ​​algorithm automatically generates the slides. The output is a set of slides that includes matrix definitions, calculation procedures, and example problems.

[0592] Step 3: Generate course videos

[0593] The server uses the generated slides as input and creates a lecture video using an AI voice-over model. For example, it uses a speech synthesis system (e.g., Google Text-to-Speech) to generate a voice that reads the contents of the slides, and combines it with the slides to create a video. The lecture video is generated as output.

[0594] Step 4: Adjust tone and detail with the emotion engine

[0595] The server uses an emotion recognition system to analyze the user's facial expressions and tone of voice. The user's emotional data is provided as input, and the tone and level of detail of the generated video are adjusted as output. For example, if the server determines that the user is feeling fatigued, it generates a video containing a brief explanation and encouraging words.

[0596] Step 5: Save the course video and slides

[0597] The server takes the generated lecture videos and slides as input and stores them in a database. This generates a URL that students can access through their devices. The output is the saved lecture videos and slides and a URL.

[0598] Test creation, grading, and recording

[0599] Step 1: Automatically generate test questions based on lesson content

[0600] The server takes the lesson content as input and generates prompts to the generative AI model, such as "Create test questions centered on matrix calculations." This automatically generates test questions, and a test question set is generated as output.

[0601] Step 2: Distribute the test questions to students

[0602] The server takes the generated test questions as input and distributes them to students via their terminals. For example, it generates a test web page and sends the URL to students via email. The test questions are distributed as output.

[0603] Step 3: Collect user responses and sentiment data

[0604] The user takes the test using a terminal and sends the answer data as input to the server. The emotion recognition system collects the user's emotional data during the test. The answer data and the user's emotional data are obtained as output.

[0605] Step 4: Analyze responses and auto-score

[0606] The server takes the answer data as input and automatically scores it using AI. For example, it analyzes the answer content using a natural language processing (NLP) algorithm and calculates the score based on the point allocation. The scoring result is obtained as output.

[0607] Step 5: Recording and feedback of results

[0608] The server takes the grading results as input, records them in a database, and organizes them for each student. It also automatically generates performance feedback and provides it to students via their devices. The server outputs the grading results and feedback.

[0609] Inquiry response

[0610] Step 1: Submitting a user question

[0611] A user uses a terminal to send a question to the server, for example, "What math courses should I take next semester?" The question data is sent to the server as output.

[0612] Step 2: Parsing the Question

[0613] The server takes the question data as input, analyzes the question using natural language processing technology, and outputs the analysis results.

[0614] Step 3: Generate appropriate answers

[0615] The server uses the analysis results as input and generates an appropriate answer using a generative AI model. For example, it generates an answer such as, "The mathematics courses you should take next semester are linear algebra and calculus." The answer data is obtained as output.

[0616] Step 4: Submit your response

[0617] The server receives the generated answer data as input and responds to the user via the device. The emotion recognition system analyzes the user's emotions and adds words of encouragement as needed. The answer is provided to the user as output.

[0618] (Application example 2)

[0619] 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."

[0620] Conventional educational systems often struggle to individualize education and are unable to respond flexibly to the emotional state of a particular student. This makes it difficult to improve students' understanding, and also results in insufficient individualized responses to increase customer satisfaction. In particular, brick-and-mortar stores require a system that can recognize customers' emotional states in real time and respond appropriately to those states.

[0621] The specific processing by the specific processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means. In this invention, the server includes means for automatically generating lecture videos and scripts, means for saving the generated lecture videos and scripts in a database, and means for automatically generating test questions based on the lesson content. This enables the automatic generation of lecture videos and scripts, making it possible to improve the efficiency and quality of education.

[0622] The system also includes a means for receiving test data answered by students using a user device, a means for automatically scoring the received test data using AI, a means for recording the scoring results in a database, a means for receiving inquiries from students regarding obtaining credits and analyzing them using natural language processing, a means for generating and providing appropriate answers based on the analysis results, a means for monitoring the user's emotional state in real time using an emotion recognition engine, and a means for providing a response method according to the user's emotional state.This enables flexible responses according to the student's emotional state, thereby achieving individualized education.In addition, in customer service, it enables appropriate responses in real time according to the customer's emotional state, thereby improving customer satisfaction.

[0623] "Means for automatically generating lecture videos and scripts" refers to technology that uses algorithms or models to automatically generate educational content on specified topics and corresponding scripts.

[0624] "Means for storing the generated lecture videos and scripts in a database" refers to a technology that stores the generated educational content in a database in a persistent format so that it can be accessed and referenced later.

[0625] "Means for automatically generating test questions based on class content" refers to technology that automatically generates assessment questions based on the topic and content of a class and presents them to test takers.

[0626] "Means for receiving test data answered by students using user devices" refers to technology for sending and receiving data on students' answers to test questions to a server via the Internet or a local network.

[0627] "Means for automatically scoring received test data using AI" refers to a technology that uses artificial intelligence technology to evaluate the test data answered by test takers and automatically calculate scores.

[0628] "Means for recording scoring results in a database" refers to a technology that stores the results scored by AI in a database so that they can be accessed and referenced later.

[0629] "Means for receiving inquiries from students regarding the acquisition of credits and analyzing them using natural language processing" refers to a technology in which students submit questions regarding the acquisition of credits or courses and the questions are analyzed using natural language processing technology.

[0630] "Means for generating and providing appropriate answers based on analysis results" refers to technology that automatically generates appropriate, contextual answers based on the results of analysis using natural language processing and provides them to users.

[0631] "Means for monitoring a user's emotional state in real time using an emotion recognition engine" is a technology that analyzes image data, audio data, etc. to identify a user's current emotional state in real time.

[0632] The "means for providing a response method according to the user's emotional state" is a technology that automatically generates appropriate response methods and advice based on the recognized emotional state and provides them to the user.

[0633] This invention is a system that combines AI technology and emotion recognition technology to respond to the needs of education and customer service by providing personalized responses according to the user's emotional state. The system operates mainly with three parties: a server, a terminal, and the user.

[0634] server

[0635] The server first retrieves information about the specified topic from the database. Based on this data, the algorithm uses a generative AI model to automatically generate lecture slides and lecture videos. An emotion recognition engine monitors the user's emotional state and, for example, if the user is feeling tired, generates a concise, encouraging video. The generated lecture videos and scripts are stored in the database and can be viewed by users.

[0636] Next, the generative AI model automatically generates test questions based on the lesson content. The generated test is delivered to the user's device, and the user takes the test. The answers are sent from the device to a server, and the server's AI automatically scores the received test data. The scoring results are recorded in a database and can be viewed by the user later.

[0637] Terminal

[0638] Users use devices such as smart glasses. These devices capture the user's facial expressions and voice in real time, and an emotion recognition engine analyzes the data. Based on the analysis results, the device provides the user with appropriate advice and methods of response in real time. For example, if a salesperson in a physical store is using smart glasses and the customer looks anxious, a message will appear on the glasses' display saying, "This customer seems anxious. Please try to explain in a way that puts them at ease."

[0639] User

[0640] In implementing the invention, users use the system on the front lines. For example, they watch video lectures and answer generated tests. If they have any questions, they input them in natural language, and the system generates and provides appropriate answers.

[0641] Specific examples

[0642] For example, in a university linear algebra class, a server retrieves linear algebra teaching data, and a generative AI model generates slides including matrix calculations and linear equation solutions. If an emotion recognition engine detects that a student is confused, it creates a video with more detailed explanations and additional examples, helping students to deepen their understanding.

[0643] An example of a prompt would be:

[0644] You are a sales staff member at a brick-and-mortar store wearing smart glasses. The camera is currently capturing the facial expression of a customer standing at the counter. If the customer's emotion is recognized as "anxiety," the advice displayed is "This customer seems anxious. Try to explain in a reassuring way."

[0645] By utilizing these technologies, it is possible to personalize education and improve customer service. This system makes it possible to flexibly respond to individual needs that would be difficult to meet using conventional methods.

[0646] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[0647] Step 1:

[0648] The server retrieves information about the specified course topic from the database, including lecture content, slides, references, etc. It processes the input data from the database and extracts the necessary information about the topic.

[0649] Step 2:

[0650] The server uses a generative AI model based on the acquired data to automatically generate lecture slides and lecture videos. The generative AI model analyzes the text data and generates appropriate visual content and explanatory text. The generated lecture slides and lecture videos are stored in a database. The input is teaching material data related to the topic, and the output is the generated slides and lecture videos.

[0651] Step 3:

[0652] The server receives requests for access to the lecture videos and slides from users' devices. Users send requests to view the lectures using devices such as smart glasses or PCs. Based on the requests, the server distributes the generated content to the users' devices.

[0653] Step 4:

[0654] While the user is watching the lecture video, the emotion recognition engine analyzes the user's facial expressions and voice in real time through the smart glasses and camera. The input is the user's real-time video and audio data, and the output is the user's emotional state.

[0655] Step 5:

[0656] The server receives the user's emotional state from the emotion recognition engine and adjusts the content of the lecture video and slides in real time. For example, if the server detects that the user is confused, it generates a video with detailed explanations and additional examples and provides it to the user. The input is the user's emotional state, and the output is the adjusted educational content.

[0657] Step 6:

[0658] The server automatically creates test questions using a generative AI model based on the content of the lecture. The generated test questions are then delivered to the user's device. The input is the lecture content data, and the output is the generated test questions.

[0659] Step 7:

[0660] Users answer test questions using their devices and send their answers to the server. The server analyzes the received test data and automatically scores it using an AI model. The input is the user's test answer data, and the output is the scoring results.

[0661] Step 8:

[0662] The server records the scoring results in a database so that users can check them later. The input is the scoring result data, and the output is the results recorded in the database.

[0663] Step 9:

[0664] The device receives inquiries from users regarding the acquisition of credits and sends the details to the server. The server analyzes the inquiries using AI models and natural language processing and generates appropriate answers. The input is the text data of the inquiries, and the output is the analysis results and the generated answers.

[0665] Step 10:

[0666] The server sends the generated answer to the user's terminal and provides it to the user. The input is the generated answer, and the output is the answer displayed on the user's terminal.

[0667] Through these steps, we can provide efficient, high-quality service that meets the individual needs of our users in both education and customer service.

[0668] 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.

[0669] 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.

[0670] 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.

[0671] [Third embodiment]

[0672] FIG. 5 shows an example of the configuration of a data processing system 310 according to the third embodiment.

[0673] 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.

[0674] 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).

[0675] 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.

[0676] 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.

[0677] 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).

[0678] 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.

[0679] 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.

[0680] 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.

[0681] 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.

[0682] 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.

[0683] 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."

[0684] This invention is a system for automating university education classes, tests, and grade management, and uses AI technology to provide high-quality education at low cost. Each function of this system is explained in detail below.

[0685] Creating course content

[0686] The server first retrieves information about the specified course topic from the database. Based on this data, an AI algorithm is used to automatically generate course slides. The AI ​​then creates a course video based on the generated slides. This video is structured in a format where a virtual instructor explains the slides, and is designed to be easy for students to understand. The generated course video and slides are saved in the database so that students can view them later.

[0687] For example, when creating a lesson on "linear algebra," the server retrieves teaching material data related to linear algebra, and the AI ​​generates slides that include matrix calculations and solutions to linear equations. Based on those slides, a lecture video is created and saved in the database.

[0688] Test creation, grading, and recording

[0689] The server uses AI to automatically generate test questions based on the content of the class. The generated test questions are distributed to students via their devices. Users (students) take the test using their devices and send their answers to the server.

[0690] The received response data is analyzed by the server's AI and automatically graded. The graded results are recorded in a database and organized for each student.

[0691] For example, when creating a "linear algebra" test, the server automatically generates questions about matrix calculations and solving linear equations. After students answer these questions and complete the test, the answer data is sent to the server. The AI ​​then scores the students and records the scores in a database.

[0692] Inquiry response

[0693] Users use their devices to submit questions about the syllabus or credit acquisition. For example, they might type, "What math courses should I take next semester?" The question is sent to the server, where the AI ​​chatbot analyzes it using natural language processing. Based on the analysis results, the AI ​​chatbot generates an appropriate answer and responds to the student via their device.

[0694] In this way, the server can respond to student inquiries in real time and provide course registration information and the conditions necessary to obtain credits. This type of response also contributes to the efficiency of educational management.

[0695] As a specific example, if a student sends a question such as "Please tell me the syllabus for mathematical statistics," the server searches the database for relevant syllabus information, and the AI ​​organizes that information and responds to the student.

[0696] As described above, the system of the present invention uses AI technology to automatically generate lecture videos and scripts, create, grade, and record tests, and respond to inquiries, making it possible to provide high-quality educational services at low cost. This system can significantly reduce the costs and labor required for traditional educational operations, and also ease the financial burden on students.

[0697] The processing flow will be explained below.

[0698] Creating course content

[0699] Step 1:

[0700] The server retrieves information about the specified course topic from the database.

[0701] Step 2:

[0702] Based on the information obtained by the server, lecture slides are automatically generated using an AI algorithm.

[0703] Step 3:

[0704] The server uses AI to automatically generate lecture videos based on the generated slides.

[0705] Step 4:

[0706] The server stores the generated lecture slides and videos in a database.

[0707] Test creation, grading, and recording

[0708] Step 1:

[0709] The server uses AI to automatically generate test questions based on the lesson content.

[0710] Step 2:

[0711] The test questions generated by the server are distributed to students via their terminals.

[0712] Step 3:

[0713] A user takes a test using a terminal and transmits answer data from the terminal to a server.

[0714] Step 4:

[0715] The server analyzes the answer data received using AI and scores the answers.

[0716] Step 5:

[0717] The server records the grading results in a database and organizes them by student.

[0718] Inquiry response

[0719] Step 1:

[0720] Users use their devices to submit questions about the syllabus and credit acquisition.

[0721] Step 2:

[0722] The questions received by the server are analyzed by an AI chatbot.

[0723] Step 3:

[0724] The server generates an appropriate answer based on the analysis results.

[0725] Step 4:

[0726] The server generates a response and sends it to the user via the terminal.

[0727] Example 1

[0728] 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."

[0729] In the traditional university education system, creating course content and preparing and grading tests requires a significant amount of time and cost, making it difficult to manage education efficiently. Furthermore, while prompt and accurate responses to a wide variety of student inquiries are required, responses are often delayed. This results in a decline in the quality of education provided and the student learning experience.

[0730] 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.

[0731] In this invention, the server includes means for automatically generating course videos and scripts, means for storing the generated course videos and scripts in a database, means for automatically generating test questions based on the content of the lessons, means for receiving test data answered by learners, means for automatically scoring the received test data using artificial intelligence, means for recording the scoring results in a database, means for receiving inquiries from learners regarding obtaining credits and analyzing them using natural language processing, means for generating and providing appropriate answers based on the analysis results, means for acquiring information on a specified course topic from the database, means for automatically generating course materials by analyzing the acquired information, means for generating course videos by a virtual instructor based on the materials, and means for providing answers to learners' inquiries in real time using AI. This enables the automatic creation and scoring of course content and tests, and rapid response to inquiries.

[0732] "Lecture videos" are video-based teaching materials created to explain the content of a lesson.

[0733] "Script" refers to the content of the course video written in text format.

[0734] A "database" is a data collection system that systematically organizes and stores information and can be retrieved as needed.

[0735] "Exam questions" are questions or assignments given to measure the level of understanding of the course content.

[0736] "Learner" means an individual receiving an education, such as a student taking a class or taking an exam.

[0737] "Exam data" refers to data that records the answers given by learners to exams.

[0738] "Artificial intelligence" refers to technologies and systems that enable computers to mimic human intelligence.

[0739] "Natural language processing" is a technology that allows computers to understand and analyze human language.

[0740] "Analysis results" refers to the results of information obtained through analytical methods such as natural language processing.

[0741] "Course Materials" refers to textbooks and slide-style teaching materials prepared to supplement the course content.

[0742] A "virtual instructor" is a computer-generated instructor character used to explain a course.

[0743] "Answer" means the answer submitted by a learner to an exam question.

[0744] This system automates university education classes, tests, and grade management, and uses AI technology to provide high-quality education at low cost. Specifically, it uses the following hardware and software to process and calculate various data.

[0745] First, the server retrieves information about the specified course topic from the database. This information includes teaching material data and the course content. Next, the server uses AI algorithms such as TensorFlow and OpenAI GPT to automatically generate course slides based on the retrieved information. Specific content includes matrix calculations and solving linear equations. The server also creates a lecture video by a virtual instructor based on the slides. The lecture video is edited using Adobe Premiere Pro. The generated lecture video and slides are saved in the database so that students can view them later.

[0746] For example, when creating a lesson on "linear algebra," the server retrieves teaching material data related to linear algebra, and the AI ​​generates slides that include matrix calculations and solutions to linear equations. Based on those slides, a lecture video is created and saved in the database.

[0747] Next, the server uses AI to automatically generate test questions based on the class content. The generated test questions are distributed via devices (student PCs or tablets) using the Google Forms API. Users (students) receive a notification, access the test via a specified link, and enter their answers. Once they have finished answering, the data is sent to the server. The server receives this data in real time and automatically grades it using AI. The grade results are recorded in a database and tallied as each student's grade.

[0748] For example, when creating exam questions for "Linear Algebra," the server exports them in Google Forms format and automatically generates questions on matrix calculations and solving linear equations. After students answer these questions and the exam is completed, the answer data is sent to the server, where the AI ​​grades the students and records the scores in a database.

[0749] Furthermore, users can use their devices to send questions about the syllabus or credit acquisition to the server. For example, they can enter a question like, "What math courses should I take next semester?" The question is sent to the server, where an AI chatbot using the OpenAI GPT-3 model analyzes it through natural language processing. Based on the analysis results, an appropriate answer is generated and sent back to the student via the device. This enables quick and accurate responses to student inquiries.

[0750] As a specific example, if a student sends a question such as "Please tell me the syllabus for mathematical statistics," the server searches the database for relevant syllabus information, and the AI ​​organizes that information and responds to the student.

[0751] An example prompt is:

[0752] "Please create slides related to your linear algebra class. Include matrix calculations and solving linear equations."

[0753] "Please create some linear algebra exam questions. Please include matrix calculations and linear equation solving questions."

[0754] "What math courses should I take next semester?"

[0755] By automatically creating and grading course content and exams, this system significantly reduces the costs and labor involved in educational administration, and also reduces the financial burden on students.

[0756] The flow of the identification process in the first embodiment will be described with reference to FIG.

[0757] Step 1: Get course data

[0758] The server retrieves information about a specified course topic from the database. The input is the specified data of the course topic, and the output is the retrieved teaching material data. Specifically, the server executes a query to retrieve teaching material data related to the course topic from the database.

[0759] Step 2: Generate course slides

[0760] The server uses an AI algorithm based on the acquired information to automatically generate course slides. The input is the acquired teaching material data, and the output is the generated course slides. Specifically, TensorFlow is used to analyze the teaching material data and create slides based on the content.

[0761] Step 3: Create a course video

[0762] The server creates a lecture video by a virtual lecturer based on the generated lecture slides. The input is the generated lecture slides, and the output is the lecture video. Specifically, OpenAI GPT and Adobe Premiere Pro are used to generate a video in which the virtual lecturer explains something that matches the content of the slides.

[0763] Step 4: Save your course data

[0764] The server saves the generated lecture slides and videos in a database. The input is the generated lecture slides and videos, and the output is the saved state in the database. Specifically, it saves them in a dedicated table in the database and generates a link so that students can access them later.

[0765] Step 5: Generate exam questions

[0766] The server uses AI to automatically generate test questions based on the content of the lessons. The input is the lesson content data, and the output is the generated test questions. Specifically, the test questions are created using the Google Forms API, and questions on matrix calculations and solving linear equations are automatically generated.

[0767] Step 6: Exam Question Distribution

[0768] The server distributes the generated exam questions to students via their devices. The input is the generated exam questions, and the output is the exam questions notified to the device. Specifically, the server exports the questions in Google Forms format and sends a link to the student's device via notification.

[0769] Step 7: Testing

[0770] Users (students) take exams using their terminals and send their answers to the server. The input is the student's answers, and the output is the answer data sent to the server. Specifically, students enter their answers to the exam questions displayed on their terminals and send them after completion.

[0771] Step 8: Receive test data

[0772] The server checks the received test data in real time and starts the automatic scoring process. The input is the answer data sent from the device, and the output is the scoring results. Specifically, it uses AI to analyze the sent answers and calculates the score for each question.

[0773] Step 9: Record your results

[0774] The server records the grading results in a database and organizes them for each student. The input is the grading result data, and the output is the state recorded in the database. Specifically, the results are saved in the database as each student's grade and organized so that they can be checked later.

[0775] Step 10: Receiving an inquiry

[0776] Users use their terminals to send questions about the syllabus or credit acquisition to the server. The input is the student's question, and the output is the question data received by the server. Specifically, the question content entered in the chat window of the terminal is sent.

[0777] Step 11: Parsing Natural Language

[0778] The server analyzes the received question using an AI chatbot. The input is the received question data, and the output is the analysis result. Specifically, the OpenAI GPT-3 model is used to analyze the question content and understand its intent.

[0779] Step 12: Generate and serve answers

[0780] The server generates an appropriate answer based on the analysis results and returns it to the student via the terminal. The input is the analysis results and the output is the generated answer. Specifically, it searches for relevant information from a database, generates an answer, and returns it to the student.

[0781] (Application example 1)

[0782] 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."

[0783] Automation of classes and grade management in university education is essential for providing students with a high-quality education at low cost. However, conventional systems require manual processes such as generating class content, grading tests, and responding to student inquiries, which requires a great deal of time and effort. Furthermore, in brick-and-mortar stores, staff manually handle customer service and explain products, hindering operational efficiency. To solve these problems, automated systems using advanced AI technology are needed.

[0784] 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.

[0785] In this invention, the server includes means for automatically generating lecture videos and scripts, means for saving the generated lecture videos and scripts in a database, means for automatically generating test questions based on the content of the lectures, means for receiving test data answered by students, means for automatically scoring the received test data using AI, means for recording the scoring results in a database, means for receiving inquiries from students regarding obtaining credits and analyzing them using natural language processing, means for generating and providing appropriate answers based on the analysis results, means for acquiring product information and automatically generating product descriptions for customers using a generative AI model, and means for analyzing customer inquiries using natural language processing and generating and providing appropriate answers.This enables the automation of university education and the efficiency of customer service in physical stores.

[0786] A "server" is a central control device that processes and stores various data and provides it to other terminals as needed.

[0787] "Course videos" are video-based teaching materials created to provide specific educational content visually and aurally.

[0788] A "script" is a document that describes the content of a video lecture as text information and is saved in text format.

[0789] A "generative AI model" is an artificial intelligence algorithm that analyzes information based on a specified task and automatically generates new content or answers.

[0790] A "database" is a system for efficiently storing, searching, and updating large amounts of data.

[0791] "Test items" are questions or problems used to assess a student's understanding.

[0792] "Test data" refers to the answers given by students to test questions.

[0793] "Natural language processing" is a technology that allows computers to understand and analyze human language and generate appropriate responses.

[0794] "Product information" refers to detailed data about a particular product, such as its characteristics, price, and usage.

[0795] "Customer-friendly product description" means text or audio information generated to describe a product in a manner that is easy for customers to understand.

[0796] "Inquiries" refer to questions or inquiries from users or customers.

[0797] "Answer generation" is the process of creating an appropriate response to a query.

[0798] DETAILED DESCRIPTION OF THE PREFERRED EMBODIMENTS The present invention will be described in detail below with reference to the accompanying drawings.

[0799] The server first retrieves information about the specified course topic from a database and then uses AI algorithms to automatically generate course slides and videos. The generated slides and videos are then stored in a database for students to view later. This process is performed using software such as Python and TensorFlow.

[0800] For example, when creating a lesson on "linear algebra," the server retrieves teaching material data related to linear algebra, and the AI ​​generates slides that include matrix calculations and solutions to linear equations. Based on those slides, a lecture video is created and saved in the database.

[0801] Furthermore, the server automatically generates test questions based on the content of the lessons. The generated test questions are distributed to students via their smartphones or PCs. The test data answered by the students is sent to the server, which then automatically scores the received test data using AI. The scoring results are recorded in a database and organized for each student. This process uses a combination of an SQLite database and Python.

[0802] For example, when creating a "linear algebra" test, the server automatically generates questions about matrix calculations and solving linear equations. After students answer these questions and complete the test, the answer data is sent to the server. The AI ​​then scores the students and records the scores in a database.

[0803] In addition, inquiries from students regarding the acquisition of credits are sent to the server via their devices and analyzed using natural language processing. An appropriate answer is generated based on the analysis results and sent back to the student via their device. This makes it possible to improve the efficiency of educational management.

[0804] This system can also be applied to improving operational efficiency in physical stores. The server acquires product information and automatically generates product descriptions for customers using a generative AI model. For example, when a store clerk scans a product barcode with a smartphone app, detailed product information is sent to the server, and the GPT-3 model generates concise and attractive product descriptions based on the product details. It is also possible to analyze customer inquiries using natural language processing and generate appropriate answers to provide to store clerks.

[0805] To illustrate, if a sales associate scans a new lipstick and asks the customer for a brief description, the prompt might be:

[0806] "Please tell your customers about your new lipstick. Below are the details of the product."

[0807] Product Name: High Quality Lipstick

[0808] Features: Long-lasting, moisturizing, contains Vitamin E, allergy tested

[0809] Color: Cherry Red

[0810] Price: 3,000 yen

[0811] How to use: Apply directly to dry lips after applying lip balm.

[0812] This system will enable more efficient university education and more efficient customer service in physical stores.

[0813] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[0814] Step 1:

[0815] The server retrieves information about the specified course topic from the database. The input is the course topic specification, and the output is the retrieved teaching material data. Based on this data, an AI algorithm is used to automatically generate slides.

[0816] Step 2:

[0817] The server creates a lecture video of the virtual lecturer based on the generated slides. The input is the generated slides, and the output is the lecture video. Specifically, the AI ​​reads the content of the slides and creates a video in the form of an explanation.

[0818] Step 3:

[0819] The server saves the generated lecture videos and slides in a database. The input is the lecture videos and slides, and the output is a notification that the videos and slides have been saved to the database, allowing students to access them later.

[0820] Step 4:

[0821] The server automatically generates test questions based on the lesson content. The input is lesson content data, and the output is the generated test questions. It uses an AI algorithm to automatically generate questions related to the lesson content.

[0822] Step 5:

[0823] Students answer test questions via their terminals. The input is the student's answer data, and the output is the transmission of the test answers. Students use their smartphones or PCs to enter their answers to the test questions and send them to the server.

[0824] Step 6:

[0825] The server automatically scores the received test answer data using AI. The input is the student's test answer data, and the output is the scoring results. The AI ​​algorithm analyzes the answers and accurately scores them.

[0826] Step 7:

[0827] The server records the grading results in a database. The input is the grading results, and the output is a notification that the results have been saved to the database. This allows each student's grades to be recorded and viewed.

[0828] Step 8:

[0829] A user's inquiry regarding the acquisition of credits is sent to the server using a terminal. The input is the user's inquiry, and the output is a notification of completion of the transmission to the server. The user enters a question in natural language and sends it to the server.

[0830] Step 9:

[0831] The server analyzes the query using natural language processing. The input is the user's query, and the output is the analysis result. The AI ​​model analyzes the query and extracts the information needed to generate the optimal answer.

[0832] Step 10:

[0833] The server generates an appropriate answer based on the analysis results and sends it back to the user via the terminal. The input is the analysis results and the output is the answer to the user. This allows questions to be answered in real time.

[0834] Step 11:

[0835] The terminal is used to scan the product and send the product information to the server. The input is barcode information, and the output is a notification that the product information has been sent. The store clerk uses a smartphone to scan the product and send the information to the server.

[0836] Step 12:

[0837] The server uses a generative AI model to automatically generate a product description for the customer. The input is the scanned product information, and the output is the generated product description. A generative AI model such as GPT-3 creates an easy-to-understand description based on the product data.

[0838] Step 13:

[0839] The product description generated for the customer is displayed through the terminal. The input is the automatically generated product description, and the output is what is presented to the customer. By having the salesperson show the generated product description to the customer, the appeal of the product can be effectively conveyed.

[0840] 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.

[0841] This invention is a system that uses AI technology to automate university education classes, tests, and grade management, providing low-cost, high-quality education. Furthermore, this invention incorporates an emotion engine that recognizes user emotions, enabling flexible education provision according to the emotional state of each individual user.

[0842] Creating course content

[0843] The server first retrieves information about the specified course topic from a database. Based on this data, an AI algorithm is used to automatically generate course slides. The AI ​​then creates a course video based on the generated slides. During this process, an emotion engine recognizes the user's emotions and can adjust the tone and level of detail of the explanations depending on their state. For example, if the user is feeling tired, the explanation can be made more concise or include words of encouragement. The generated course video and slides are stored in a database and made available for students to view.

[0844] For example, when creating a lesson on "linear algebra," the server retrieves learning material data on linear algebra, and the AI ​​generates slides including matrix calculations and solutions to linear equations. If the emotion engine recognizes that a student is confused, it generates a video with detailed explanations and additional examples, making it easier for students to understand.

[0845] Test creation, grading, and recording

[0846] The server uses AI to automatically generate test questions based on the content of lessons. The generated test questions are distributed to students via their devices. The users (students) take the test using their devices and send their answers to the server. The emotion engine monitors the user's emotions during the test and can adjust the difficulty of the questions if the user is under high stress. For example, if the user is very nervous, the difficulty of the questions can be lowered to reduce the user's burden.

[0847] The received response data is analyzed by the server's AI and automatically graded. The graded results are recorded in a database and organized for each student.

[0848] As a concrete example, when creating a "linear algebra" test, the server automatically generates questions related to matrix calculations and solving linear equations. If the user feels impatient during the test, the emotion engine will slightly lower the difficulty of the questions to maintain performance. When the user completes the test, the answer data is sent to the server, where the AI ​​scores the answer and records the score in a database.

[0849] Inquiry response

[0850] Users use their devices to submit questions about syllabuses or credit acquisition, such as, "What math courses should I take next semester?" The question is sent to a server where an AI chatbot analyzes it through natural language processing. The emotion engine can recognize the emotion of the user's inquiry and generate a response with the appropriate tone and content.

[0851] Based on the analysis, the server generates appropriate responses and sends them back to the student via their device. For example, if a student is feeling anxious, the server can provide not only syllabus information but also additional advice and words of encouragement.

[0852] For example, if a student sends a question such as "Please tell me the syllabus for mathematical statistics," the server will search the database for relevant syllabus information, organize that information, and respond to the student. If the emotion engine recognizes the student's anxiety, the response will also include advice on how to proceed with the study and the necessary preparations.

[0853] As described above, the system of the present invention uses AI technology and an emotion engine to automatically generate lecture videos and scripts, create, grade, and record tests, and respond to inquiries, thereby providing more personalized, high-quality educational services. This system can improve the efficiency of educational management and enhance students' learning experiences. It also significantly reduces the costs and labor required for traditional educational management, thereby easing the financial burden on students.

[0854] The processing flow will be explained below.

[0855] Creating course content

[0856] Step 1:

[0857] The server retrieves information about the specified course topic from the database.

[0858] Step 2:

[0859] Based on the information obtained by the server, lecture slides are automatically generated using an AI algorithm.

[0860] Step 3:

[0861] The server uses AI to automatically generate lecture videos based on the generated slides, and uses an emotion engine to recognize the user's emotional state and adjust the tone and level of detail of the explanations.

[0862] Step 4:

[0863] The server stores the generated lecture slides and videos in a database.

[0864] Test creation, grading, and recording

[0865] Step 1:

[0866] The server uses AI to automatically generate test questions based on the lesson content.

[0867] Step 2:

[0868] The test questions generated by the server are distributed to students via their terminals.

[0869] Step 3:

[0870] The user takes the test using a device and sends the answer data from the device to the server. During the test, the emotion engine monitors the user's emotions and adjusts the difficulty of the questions as needed.

[0871] Step 4:

[0872] The server analyzes the answer data received using AI and scores the answers.

[0873] Step 5:

[0874] The server records the grading results in a database and organizes them by student.

[0875] Inquiry response

[0876] Step 1:

[0877] Users use their devices to submit questions about the syllabus and credit acquisition.

[0878] Step 2:

[0879] The AI ​​chatbot analyzes the questions received by the server, and the emotion engine recognizes the user's emotional state and responds appropriately.

[0880] Step 3:

[0881] The server generates an appropriate answer based on the analysis results.

[0882] Step 4:

[0883] The server generates a response and sends it to the user via the terminal.

[0884] Example 2

[0885] 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."

[0886] Traditional university education systems require a lot of effort and cost for creating educational content, creating and grading tests, and responding to inquiries. It has also been difficult to provide flexible education tailored to students' learning progress, level of understanding, and emotional state. This has led to a standardization of educational quality and a lack of individualized attention, resulting in issues that lead to a decline in student learning efficiency and motivation.

[0887] 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.

[0888] In this invention, the server includes means for automatically generating lecture videos and scripts, means for storing the generated lecture videos and scripts in a database, means for automatically generating test questions based on the content of the lessons, means for receiving test data answered by students, means for automatically scoring the received test data using artificial intelligence, means for recording the scoring results in a database, means for receiving inquiries from students regarding the acquisition of credits, means for analyzing using natural language processing, means for generating and providing appropriate answers based on the analysis results, means for recognizing a user's emotions using an emotion recognition system and adjusting the tone and level of detail of the lecture videos and slides based on the recognized emotions, and means for monitoring the user's emotions during the test and adjusting the difficulty of the test according to the user's stress level. This enables efficient generation of educational content, individualized responses for each student, and appropriate adjustment of the difficulty level.

[0889] 1. "Server" means a computer system that has computing capabilities, manages and processes data over a network, and provides services to other computers or devices.

[0890] 2. "Lecture Video" means video content created to provide students with visual and audio education on academic subjects, technology, etc.

[0891] 3. A "script" is text data that is automatically generated based on the content of the lecture video and slides, and serves as the basis for the text and narration that explain the educational content.

[0892] 4. "Test Questions" are automatically generated questions or tasks used to assess a student's understanding of the learning content.

[0893] 5. "Database" refers to a system for systematically storing and managing information such as course videos, scripts, test data, and grading results.

[0894] 6. "Artificial intelligence" refers to technology that mimics human thought processes and automates data analysis, problem solving, and decision-making.

[0895] 7. "Natural language processing" is a technology that enables computers to understand, analyze, and generate human language, and is used to analyze inquiries and generate appropriate responses.

[0896] 8. An "emotion recognition system" is a technology that analyzes a user's facial expressions and tone of voice to identify their emotional state.

[0897] 9. "Tone" refers to the way information is conveyed or the style of speaking, which is adjusted according to emotion or situation.

[0898] 10. "Level of detail" refers to the specific level of detail provided in the information, and indicates the depth of content and the degree of specificity of the explanation.

[0899] 11. "Emotion" refers to a user's temporary emotional state or psychological response.

[0900] 12. "Stress level" indicates the degree of psychological stress or mental tension felt by the user.

[0901] This invention is a system that uses AI technology to automate university education classes, tests, and grade management, providing low-cost, high-quality education. It also incorporates an emotion engine that recognizes user emotions, enabling flexible education provision according to the emotional state of each individual user.

[0902] First, the server creates the course content. It retrieves information about the specified course topic from the database and automatically generates course slides using a generative AI model (e.g., GPT-4). Next, it creates a course video based on the generated slides using an AI voiceover model. At this time, an emotion recognition system analyzes the user's emotions in real time and can adjust the tone and level of detail of the explanation. The generated course video and slides are stored in the database and can be viewed by students via their devices.

[0903] As a concrete example, when creating a "Linear Algebra" course, the server retrieves teaching material data related to linear algebra from the database, inputs a prompt to the generative AI model saying, "Create slides related to matrix calculations in linear algebra," and creates slides including matrix definitions, calculation procedures, and example problems. It then uses a speech synthesis system (e.g., Google Text-to-Speech) to generate audio that reads the contents of the slides, and generates a video that combines this with the slides.

[0904] The server then automatically generates test questions based on the content of the class. The test questions generated using AI are distributed to students via their devices, who then take the test and send their answers to the server. The emotion recognition system monitors the user's emotions during the test and can adjust the difficulty of the questions according to their stress level. The received answer data is analyzed by the server's AI and automatically scored. The scoring results are recorded in a database and organized for each student.

[0905] As a specific example, when delivering a "Linear Algebra" test, the server inputs a prompt such as "Create test questions centered on matrix calculations" into a generative AI model, generating multiple questions. If a facial expression analysis system (e.g., Affectiva) determines that the user is feeling impatient during the test, the difficulty of the next question can be lowered. When the user completes the test, the answer data is sent to the server, where the AI ​​scores the questions and records the results in a database.

[0906] Users can also use their devices to send questions about the syllabus or credit acquisition to the server. The questions are analyzed by an AI chatbot (using natural language processing technology) and an appropriate answer is generated. The emotion recognition system can recognize the user's emotion when making an inquiry and generate an answer with a tone and content that matches it.

[0907] Example: When a user submits the question, "What math courses should I take next semester?", the server analyzes the question and generates specific advice such as, "The math courses you should take next semester are linear algebra and calculus." If the emotion recognition system recognizes the user's anxiety, it responds with encouraging words such as, "Don't worry, it's okay."

[0908] As described above, the system for implementing the present invention can automatically generate lecture videos and slides, create, grade, and record tests, and respond to inquiries using AI technology and an emotion recognition system, providing personalized, high-quality educational services. This system can improve the efficiency of educational management and enhance students' learning experiences. It can also significantly reduce the costs and labor required for traditional educational management, thereby easing the financial burden on students.

[0909] The flow of the identification process in the second embodiment will be described with reference to FIG.

[0910] Creating course content

[0911] Step 1: Get information about course topics from the database

[0912] The server is given a course topic as input. For example, if the topic is "Linear Algebra," the server accesses the database and executes an SQL query (e.g., "SELECT FROM Courseware WHERE Topic='Linear Algebra'"), which returns information about linear algebra as output.

[0913] Step 2: Automatically generate lecture slides using AI algorithms

[0914] The server uses the acquired teaching material information as input and generates a prompt for the generative AI model, such as "Create slides on matrix calculations in linear algebra." By providing this prompt, the AI ​​algorithm automatically generates the slides. The output is a set of slides that includes matrix definitions, calculation procedures, and example problems.

[0915] Step 3: Generate course videos

[0916] The server uses the generated slides as input and creates a lecture video using an AI voice-over model. For example, it uses a speech synthesis system (e.g., Google Text-to-Speech) to generate a voice that reads the contents of the slides, and combines it with the slides to create a video. The lecture video is generated as output.

[0917] Step 4: Adjust tone and detail with the emotion engine

[0918] The server uses an emotion recognition system to analyze the user's facial expressions and tone of voice. The user's emotional data is provided as input, and the tone and level of detail of the generated video are adjusted as output. For example, if the server determines that the user is feeling fatigued, it generates a video containing a brief explanation and encouraging words.

[0919] Step 5: Save the course video and slides

[0920] The server takes the generated lecture videos and slides as input and stores them in a database. This generates a URL that students can access through their devices. The output is the saved lecture videos and slides and a URL.

[0921] Test creation, grading, and recording

[0922] Step 1: Automatically generate test questions based on lesson content

[0923] The server takes the lesson content as input and generates prompts to the generative AI model, such as "Create test questions centered on matrix calculations." This automatically generates test questions, and a test question set is generated as output.

[0924] Step 2: Distribute the test questions to students

[0925] The server takes the generated test questions as input and distributes them to students via their terminals. For example, it generates a test web page and sends the URL to students via email. The test questions are distributed as output.

[0926] Step 3: Collect user responses and sentiment data

[0927] The user takes the test using a terminal and sends the answer data as input to the server. The emotion recognition system collects the user's emotional data during the test. The answer data and the user's emotional data are obtained as output.

[0928] Step 4: Analyze responses and auto-score

[0929] The server takes the answer data as input and automatically scores it using AI. For example, it analyzes the answer content using a natural language processing (NLP) algorithm and calculates the score based on the point allocation. The scoring result is obtained as output.

[0930] Step 5: Recording and feedback of results

[0931] The server takes the grading results as input, records them in a database, and organizes them for each student. It also automatically generates performance feedback and provides it to students via their devices. The server outputs the grading results and feedback.

[0932] Inquiry response

[0933] Step 1: Submitting a user question

[0934] A user uses a terminal to send a question to the server, for example, "What math courses should I take next semester?" The question data is sent to the server as output.

[0935] Step 2: Parsing the Question

[0936] The server takes the question data as input, analyzes the question using natural language processing technology, and outputs the analysis results.

[0937] Step 3: Generate appropriate answers

[0938] The server uses the analysis results as input and generates an appropriate answer using a generative AI model. For example, it generates an answer such as, "The mathematics courses you should take next semester are linear algebra and calculus." The answer data is obtained as output.

[0939] Step 4: Submit your response

[0940] The server receives the generated answer data as input and responds to the user via the device. The emotion recognition system analyzes the user's emotions and adds words of encouragement as needed. The answer is provided to the user as output.

[0941] (Application example 2)

[0942] 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."

[0943] Conventional educational systems often struggle to individualize education and are unable to respond flexibly to the emotional state of a particular student. This makes it difficult to improve students' understanding, and also results in insufficient individualized responses to increase customer satisfaction. In particular, brick-and-mortar stores require a system that can recognize customers' emotional states in real time and respond appropriately to those states.

[0944] The specific processing by the specific processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means. In this invention, the server includes means for automatically generating lecture videos and scripts, means for saving the generated lecture videos and scripts in a database, and means for automatically generating test questions based on the lesson content. This enables the automatic generation of lecture videos and scripts, making it possible to improve the efficiency and quality of education.

[0945] The system also includes a means for receiving test data answered by students using a user device, a means for automatically scoring the received test data using AI, a means for recording the scoring results in a database, a means for receiving inquiries from students regarding obtaining credits and analyzing them using natural language processing, a means for generating and providing appropriate answers based on the analysis results, a means for monitoring the user's emotional state in real time using an emotion recognition engine, and a means for providing a response method according to the user's emotional state.This enables flexible responses according to the student's emotional state, thereby achieving individualized education.In addition, in customer service, it enables appropriate responses in real time according to the customer's emotional state, thereby improving customer satisfaction.

[0946] "Means for automatically generating lecture videos and scripts" refers to technology that uses algorithms or models to automatically generate educational content on specified topics and corresponding scripts.

[0947] "Means for storing the generated lecture videos and scripts in a database" refers to a technology that stores the generated educational content in a database in a persistent format so that it can be accessed and referenced later.

[0948] "Means for automatically generating test questions based on class content" refers to technology that automatically generates assessment questions based on the topic and content of a class and presents them to test takers.

[0949] "Means for receiving test data answered by students using user devices" refers to technology for sending and receiving data on students' answers to test questions to a server via the Internet or a local network.

[0950] "Means for automatically scoring received test data using AI" refers to a technology that uses artificial intelligence technology to evaluate the test data answered by test takers and automatically calculate scores.

[0951] "Means for recording scoring results in a database" refers to a technology that stores the results scored by AI in a database so that they can be accessed and referenced later.

[0952] "Means for receiving inquiries from students regarding the acquisition of credits and analyzing them using natural language processing" refers to a technology in which students submit questions regarding the acquisition of credits or courses and the questions are analyzed using natural language processing technology.

[0953] "Means for generating and providing appropriate answers based on analysis results" refers to technology that automatically generates appropriate, contextual answers based on the results of analysis using natural language processing and provides them to users.

[0954] "Means for monitoring a user's emotional state in real time using an emotion recognition engine" is a technology that analyzes image data, audio data, etc. to identify a user's current emotional state in real time.

[0955] The "means for providing a response method according to the user's emotional state" is a technology that automatically generates appropriate response methods and advice based on the recognized emotional state and provides them to the user.

[0956] This invention is a system that combines AI technology and emotion recognition technology to respond to the needs of education and customer service by providing personalized responses according to the user's emotional state. The system operates mainly with three parties: a server, a terminal, and the user.

[0957] server

[0958] The server first retrieves information about the specified topic from the database. Based on this data, the algorithm uses a generative AI model to automatically generate lecture slides and lecture videos. An emotion recognition engine monitors the user's emotional state and, for example, if the user is feeling tired, generates a concise, encouraging video. The generated lecture videos and scripts are stored in the database and can be viewed by users.

[0959] Next, the generative AI model automatically generates test questions based on the lesson content. The generated test is delivered to the user's device, and the user takes the test. The answers are sent from the device to a server, and the server's AI automatically scores the received test data. The scoring results are recorded in a database and can be viewed by the user later.

[0960] Terminal

[0961] Users use devices such as smart glasses. These devices capture the user's facial expressions and voice in real time, and an emotion recognition engine analyzes the data. Based on the analysis results, the device provides the user with appropriate advice and methods of response in real time. For example, if a salesperson in a physical store is using smart glasses and the customer looks anxious, a message will appear on the glasses' display saying, "This customer seems anxious. Please try to explain in a way that puts them at ease."

[0962] User

[0963] In implementing the invention, users use the system on the front lines. For example, they watch video lectures and answer generated tests. If they have any questions, they input them in natural language, and the system generates and provides appropriate answers.

[0964] Specific examples

[0965] For example, in a university linear algebra class, a server retrieves linear algebra teaching data, and a generative AI model generates slides including matrix calculations and linear equation solutions. If an emotion recognition engine detects that a student is confused, it creates a video with more detailed explanations and additional examples, helping students to deepen their understanding.

[0966] An example of a prompt would be:

[0967] You are a sales staff member at a brick-and-mortar store wearing smart glasses. The camera is currently capturing the facial expression of a customer standing at the counter. If the customer's emotion is recognized as "anxiety," the advice displayed is "This customer seems anxious. Try to explain in a reassuring way."

[0968] By utilizing these technologies, it is possible to personalize education and improve customer service. This system makes it possible to flexibly respond to individual needs that would be difficult to meet using conventional methods.

[0969] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[0970] Step 1:

[0971] The server retrieves information about the specified course topic from the database, including lecture content, slides, references, etc. It processes the input data from the database and extracts the necessary information about the topic.

[0972] Step 2:

[0973] The server uses a generative AI model based on the acquired data to automatically generate lecture slides and lecture videos. The generative AI model analyzes the text data and generates appropriate visual content and explanatory text. The generated lecture slides and lecture videos are stored in a database. The input is teaching material data related to the topic, and the output is the generated slides and lecture videos.

[0974] Step 3:

[0975] The server receives requests for access to the lecture videos and slides from users' devices. Users send requests to view the lectures using devices such as smart glasses or PCs. Based on the requests, the server distributes the generated content to the users' devices.

[0976] Step 4:

[0977] While the user is watching the lecture video, the emotion recognition engine analyzes the user's facial expressions and voice in real time through the smart glasses and camera. The input is the user's real-time video and audio data, and the output is the user's emotional state.

[0978] Step 5:

[0979] The server receives the user's emotional state from the emotion recognition engine and adjusts the content of the lecture video and slides in real time. For example, if the server detects that the user is confused, it generates a video with detailed explanations and additional examples and provides it to the user. The input is the user's emotional state, and the output is the adjusted educational content.

[0980] Step 6:

[0981] The server automatically creates test questions using a generative AI model based on the content of the lecture. The generated test questions are then delivered to the user's device. The input is the lecture content data, and the output is the generated test questions.

[0982] Step 7:

[0983] Users answer test questions using their devices and send their answers to the server. The server analyzes the received test data and automatically scores it using an AI model. The input is the user's test answer data, and the output is the scoring results.

[0984] Step 8:

[0985] The server records the scoring results in a database so that users can check them later. The input is the scoring result data, and the output is the results recorded in the database.

[0986] Step 9:

[0987] The device receives inquiries from users regarding the acquisition of credits and sends the details to the server. The server analyzes the inquiries using AI models and natural language processing and generates appropriate answers. The input is the text data of the inquiries, and the output is the analysis results and the generated answers.

[0988] Step 10:

[0989] The server sends the generated answer to the user's terminal and provides it to the user. The input is the generated answer, and the output is the answer displayed on the user's terminal.

[0990] Through these steps, we can provide efficient, high-quality service that meets the individual needs of our users in both education and customer service.

[0991] 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.

[0992] 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.

[0993] 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.

[0994] [Fourth embodiment]

[0995] FIG. 7 shows an example of the configuration of a data processing system 410 according to the fourth embodiment.

[0996] 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.

[0997] 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).

[0998] 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.

[0999] 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.

[1000] 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).

[1001] 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.

[1002] 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.

[1003] 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.

[1004] 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.

[1005] 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.

[1006] 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.

[1007] 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."

[1008] This invention is a system for automating university education classes, tests, and grade management, and uses AI technology to provide high-quality education at low cost. Each function of this system is explained in detail below.

[1009] Creating course content

[1010] The server first retrieves information about the specified course topic from the database. Based on this data, an AI algorithm is used to automatically generate course slides. The AI ​​then creates a course video based on the generated slides. This video is structured in a format where a virtual instructor explains the slides, and is designed to be easy for students to understand. The generated course video and slides are saved in the database so that students can view them later.

[1011] For example, when creating a lesson on "linear algebra," the server retrieves teaching material data related to linear algebra, and the AI ​​generates slides that include matrix calculations and solutions to linear equations. Based on those slides, a lecture video is created and saved in the database.

[1012] Test creation, grading, and recording

[1013] The server uses AI to automatically generate test questions based on the content of the class. The generated test questions are distributed to students via their devices. Users (students) take the test using their devices and send their answers to the server.

[1014] The received response data is analyzed by the server's AI and automatically graded. The graded results are recorded in a database and organized for each student.

[1015] For example, when creating a "linear algebra" test, the server automatically generates questions about matrix calculations and solving linear equations. After students answer these questions and complete the test, the answer data is sent to the server. The AI ​​then scores the students and records the scores in a database.

[1016] Inquiry response

[1017] Users use their devices to submit questions about the syllabus or credit acquisition. For example, they might type, "What math courses should I take next semester?" The question is sent to the server, where the AI ​​chatbot analyzes it using natural language processing. Based on the analysis results, the AI ​​chatbot generates an appropriate answer and responds to the student via their device.

[1018] In this way, the server can respond to student inquiries in real time and provide course registration information and the conditions necessary to obtain credits. This type of response also contributes to the efficiency of educational management.

[1019] As a specific example, if a student sends a question such as "Please tell me the syllabus for mathematical statistics," the server searches the database for relevant syllabus information, and the AI ​​organizes that information and responds to the student.

[1020] As described above, the system of the present invention uses AI technology to automatically generate lecture videos and scripts, create, grade, and record tests, and respond to inquiries, making it possible to provide high-quality educational services at low cost. This system can significantly reduce the costs and labor required for traditional educational operations, and also ease the financial burden on students.

[1021] The processing flow will be explained below.

[1022] Creating course content

[1023] Step 1:

[1024] The server retrieves information about the specified course topic from the database.

[1025] Step 2:

[1026] Based on the information obtained by the server, lecture slides are automatically generated using an AI algorithm.

[1027] Step 3:

[1028] The server uses AI to automatically generate lecture videos based on the generated slides.

[1029] Step 4:

[1030] The server stores the generated lecture slides and videos in a database.

[1031] Test creation, grading, and recording

[1032] Step 1:

[1033] The server uses AI to automatically generate test questions based on the lesson content.

[1034] Step 2:

[1035] The test questions generated by the server are distributed to students via their terminals.

[1036] Step 3:

[1037] A user takes a test using a terminal and transmits answer data from the terminal to a server.

[1038] Step 4:

[1039] The server analyzes the answer data received using AI and scores the answers.

[1040] Step 5:

[1041] The server records the grading results in a database and organizes them by student.

[1042] Inquiry response

[1043] Step 1:

[1044] Users use their devices to submit questions about the syllabus and credit acquisition.

[1045] Step 2:

[1046] The questions received by the server are analyzed by an AI chatbot.

[1047] Step 3:

[1048] The server generates an appropriate answer based on the analysis results.

[1049] Step 4:

[1050] The server generates a response and sends it to the user via the terminal.

[1051] Example 1

[1052] 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."

[1053] In the traditional university education system, creating course content and preparing and grading tests requires a significant amount of time and cost, making it difficult to manage education efficiently. Furthermore, while prompt and accurate responses to a wide variety of student inquiries are required, responses are often delayed. This results in a decline in the quality of education provided and the student learning experience.

[1054] 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.

[1055] In this invention, the server includes means for automatically generating course videos and scripts, means for storing the generated course videos and scripts in a database, means for automatically generating test questions based on the content of the lessons, means for receiving test data answered by learners, means for automatically scoring the received test data using artificial intelligence, means for recording the scoring results in a database, means for receiving inquiries from learners regarding obtaining credits and analyzing them using natural language processing, means for generating and providing appropriate answers based on the analysis results, means for acquiring information on a specified course topic from the database, means for automatically generating course materials by analyzing the acquired information, means for generating course videos by a virtual instructor based on the materials, and means for providing answers to learners' inquiries in real time using AI. This enables the automatic creation and scoring of course content and tests, and rapid response to inquiries.

[1056] "Lecture videos" are video-based teaching materials created to explain the content of a lesson.

[1057] "Script" refers to the content of the course video written in text format.

[1058] A "database" is a data collection system that systematically organizes and stores information and can be retrieved as needed.

[1059] "Exam questions" are questions or assignments given to measure the level of understanding of the course content.

[1060] "Learner" means an individual receiving an education, such as a student taking a class or taking an exam.

[1061] "Exam data" refers to data that records the answers given by learners to exams.

[1062] "Artificial intelligence" refers to technologies and systems that enable computers to mimic human intelligence.

[1063] "Natural language processing" is a technology that allows computers to understand and analyze human language.

[1064] "Analysis results" refers to the results of information obtained through analytical methods such as natural language processing.

[1065] "Course Materials" refers to textbooks and slide-style teaching materials prepared to supplement the course content.

[1066] A "virtual instructor" is a computer-generated instructor character used to explain a course.

[1067] "Answer" means the answer submitted by a learner to an exam question.

[1068] This system automates university education classes, tests, and grade management, and uses AI technology to provide high-quality education at low cost. Specifically, it uses the following hardware and software to process and calculate various data.

[1069] First, the server retrieves information about the specified course topic from the database. This information includes teaching material data and the course content. Next, the server uses AI algorithms such as TensorFlow and OpenAI GPT to automatically generate course slides based on the retrieved information. Specific content includes matrix calculations and solving linear equations. The server also creates a lecture video by a virtual instructor based on the slides. The lecture video is edited using Adobe Premiere Pro. The generated lecture video and slides are saved in the database so that students can view them later.

[1070] For example, when creating a lesson on "linear algebra," the server retrieves teaching material data related to linear algebra, and the AI ​​generates slides that include matrix calculations and solutions to linear equations. Based on those slides, a lecture video is created and saved in the database.

[1071] Next, the server uses AI to automatically generate test questions based on the class content. The generated test questions are distributed via devices (student PCs or tablets) using the Google Forms API. Users (students) receive a notification, access the test via a specified link, and enter their answers. Once they have finished answering, the data is sent to the server. The server receives this data in real time and automatically grades it using AI. The grade results are recorded in a database and tallied as each student's grade.

[1072] For example, when creating exam questions for "Linear Algebra," the server exports them in Google Forms format and automatically generates questions on matrix calculations and solving linear equations. After students answer these questions and the exam is completed, the answer data is sent to the server, where the AI ​​grades the students and records the scores in a database.

[1073] Furthermore, users can use their devices to send questions about the syllabus or credit acquisition to the server. For example, they can enter a question like, "What math courses should I take next semester?" The question is sent to the server, where an AI chatbot using the OpenAI GPT-3 model analyzes it through natural language processing. Based on the analysis results, an appropriate answer is generated and sent back to the student via the device. This enables quick and accurate responses to student inquiries.

[1074] As a specific example, if a student sends a question such as "Please tell me the syllabus for mathematical statistics," the server searches the database for relevant syllabus information, and the AI ​​organizes that information and responds to the student.

[1075] An example prompt is:

[1076] "Please create slides related to your linear algebra class. Include matrix calculations and solving linear equations."

[1077] "Please create some linear algebra exam questions. Please include matrix calculations and linear equation solving questions."

[1078] "What math courses should I take next semester?"

[1079] By automatically creating and grading course content and exams, this system significantly reduces the costs and labor involved in educational administration, and also reduces the financial burden on students.

[1080] The flow of the identification process in the first embodiment will be described with reference to FIG.

[1081] Step 1: Get course data

[1082] The server retrieves information about a specified course topic from the database. The input is the specified data of the course topic, and the output is the retrieved teaching material data. Specifically, the server executes a query to retrieve teaching material data related to the course topic from the database.

[1083] Step 2: Generate course slides

[1084] The server uses an AI algorithm based on the acquired information to automatically generate course slides. The input is the acquired teaching material data, and the output is the generated course slides. Specifically, TensorFlow is used to analyze the teaching material data and create slides based on the content.

[1085] Step 3: Create a course video

[1086] The server creates a lecture video by a virtual lecturer based on the generated lecture slides. The input is the generated lecture slides, and the output is the lecture video. Specifically, OpenAI GPT and Adobe Premiere Pro are used to generate a video in which the virtual lecturer explains something that matches the content of the slides.

[1087] Step 4: Save your course data

[1088] The server saves the generated lecture slides and videos in a database. The input is the generated lecture slides and videos, and the output is the saved state in the database. Specifically, it saves them in a dedicated table in the database and generates a link so that students can access them later.

[1089] Step 5: Generate exam questions

[1090] The server uses AI to automatically generate test questions based on the content of the lessons. The input is the lesson content data, and the output is the generated test questions. Specifically, the test questions are created using the Google Forms API, and questions on matrix calculations and solving linear equations are automatically generated.

[1091] Step 6: Exam Question Distribution

[1092] The server distributes the generated exam questions to students via their devices. The input is the generated exam questions, and the output is the exam questions notified to the device. Specifically, the server exports the questions in Google Forms format and sends a link to the student's device via notification.

[1093] Step 7: Testing

[1094] Users (students) take exams using their terminals and send their answers to the server. The input is the student's answers, and the output is the answer data sent to the server. Specifically, students enter their answers to the exam questions displayed on their terminals and send them after completion.

[1095] Step 8: Receive test data

[1096] The server checks the received test data in real time and starts the automatic scoring process. The input is the answer data sent from the device, and the output is the scoring results. Specifically, it uses AI to analyze the sent answers and calculates the score for each question.

[1097] Step 9: Record your results

[1098] The server records the grading results in a database and organizes them for each student. The input is the grading result data, and the output is the state recorded in the database. Specifically, the results are saved in the database as each student's grade and organized so that they can be checked later.

[1099] Step 10: Receiving an inquiry

[1100] Users use their terminals to send questions about the syllabus or credit acquisition to the server. The input is the student's question, and the output is the question data received by the server. Specifically, the question content entered in the chat window of the terminal is sent.

[1101] Step 11: Parsing Natural Language

[1102] The server analyzes the received question using an AI chatbot. The input is the received question data, and the output is the analysis result. Specifically, the OpenAI GPT-3 model is used to analyze the question content and understand its intent.

[1103] Step 12: Generate and serve answers

[1104] The server generates an appropriate answer based on the analysis results and returns it to the student via the terminal. The input is the analysis results and the output is the generated answer. Specifically, it searches for relevant information from a database, generates an answer, and returns it to the student.

[1105] (Application example 1)

[1106] 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."

[1107] Automation of classes and grade management in university education is essential for providing students with a high-quality education at low cost. However, conventional systems require manual processes such as generating class content, grading tests, and responding to student inquiries, which requires a great deal of time and effort. Furthermore, in brick-and-mortar stores, staff manually handle customer service and explain products, hindering operational efficiency. To solve these problems, automated systems using advanced AI technology are needed.

[1108] 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.

[1109] In this invention, the server includes means for automatically generating lecture videos and scripts, means for saving the generated lecture videos and scripts in a database, means for automatically generating test questions based on the content of the lectures, means for receiving test data answered by students, means for automatically scoring the received test data using AI, means for recording the scoring results in a database, means for receiving inquiries from students regarding obtaining credits and analyzing them using natural language processing, means for generating and providing appropriate answers based on the analysis results, means for acquiring product information and automatically generating product descriptions for customers using a generative AI model, and means for analyzing customer inquiries using natural language processing and generating and providing appropriate answers.This enables the automation of university education and the efficiency of customer service in physical stores.

[1110] A "server" is a central control device that processes and stores various data and provides it to other terminals as needed.

[1111] "Course videos" are video-based teaching materials created to provide specific educational content visually and aurally.

[1112] A "script" is a document that describes the content of a video lecture as text information and is saved in text format.

[1113] A "generative AI model" is an artificial intelligence algorithm that analyzes information based on a specified task and automatically generates new content or answers.

[1114] A "database" is a system for efficiently storing, searching, and updating large amounts of data.

[1115] "Test items" are questions or problems used to assess a student's understanding.

[1116] "Test data" refers to the answers given by students to test questions.

[1117] "Natural language processing" is a technology that allows computers to understand and analyze human language and generate appropriate responses.

[1118] "Product information" refers to detailed data about a particular product, such as its characteristics, price, and usage.

[1119] "Customer-friendly product description" means text or audio information generated to describe a product in a manner that is easy for customers to understand.

[1120] "Inquiries" refer to questions or inquiries from users or customers.

[1121] "Answer generation" is the process of creating an appropriate response to a query.

[1122] DETAILED DESCRIPTION OF THE PREFERRED EMBODIMENTS The present invention will be described in detail below with reference to the accompanying drawings.

[1123] The server first retrieves information about the specified course topic from a database and then uses AI algorithms to automatically generate course slides and videos. The generated slides and videos are then stored in a database for students to view later. This process is performed using software such as Python and TensorFlow.

[1124] For example, when creating a lesson on "linear algebra," the server retrieves teaching material data related to linear algebra, and the AI ​​generates slides that include matrix calculations and solutions to linear equations. Based on those slides, a lecture video is created and saved in the database.

[1125] Furthermore, the server automatically generates test questions based on the content of the lessons. The generated test questions are distributed to students via their smartphones or PCs. The test data answered by the students is sent to the server, which then automatically scores the received test data using AI. The scoring results are recorded in a database and organized for each student. This process uses a combination of an SQLite database and Python.

[1126] For example, when creating a "linear algebra" test, the server automatically generates questions about matrix calculations and solving linear equations. After students answer these questions and complete the test, the answer data is sent to the server. The AI ​​then scores the students and records the scores in a database.

[1127] In addition, inquiries from students regarding the acquisition of credits are sent to the server via their devices and analyzed using natural language processing. An appropriate answer is generated based on the analysis results and sent back to the student via their device. This makes it possible to improve the efficiency of educational management.

[1128] This system can also be applied to improving operational efficiency in physical stores. The server acquires product information and automatically generates product descriptions for customers using a generative AI model. For example, when a store clerk scans a product barcode with a smartphone app, detailed product information is sent to the server, and the GPT-3 model generates concise and attractive product descriptions based on the product details. It is also possible to analyze customer inquiries using natural language processing and generate appropriate answers to provide to store clerks.

[1129] To illustrate, if a sales associate scans a new lipstick and asks the customer for a brief description, the prompt might be:

[1130] "Please tell your customers about your new lipstick. Below are the details of the product."

[1131] Product Name: High Quality Lipstick

[1132] Features: Long-lasting, moisturizing, contains Vitamin E, allergy tested

[1133] Color: Cherry Red

[1134] Price: 3,000 yen

[1135] How to use: Apply directly to dry lips after applying lip balm.

[1136] This system will enable more efficient university education and more efficient customer service in physical stores.

[1137] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[1138] Step 1:

[1139] The server retrieves information about the specified course topic from the database. The input is the course topic specification, and the output is the retrieved teaching material data. Based on this data, an AI algorithm is used to automatically generate slides.

[1140] Step 2:

[1141] The server creates a lecture video of the virtual lecturer based on the generated slides. The input is the generated slides, and the output is the lecture video. Specifically, the AI ​​reads the content of the slides and creates a video in the form of an explanation.

[1142] Step 3:

[1143] The server saves the generated lecture videos and slides in a database. The input is the lecture videos and slides, and the output is a notification that the videos and slides have been saved to the database, allowing students to access them later.

[1144] Step 4:

[1145] The server automatically generates test questions based on the lesson content. The input is lesson content data, and the output is the generated test questions. It uses an AI algorithm to automatically generate questions related to the lesson content.

[1146] Step 5:

[1147] Students answer test questions via their terminals. The input is the student's answer data, and the output is the transmission of the test answers. Students use their smartphones or PCs to enter their answers to the test questions and send them to the server.

[1148] Step 6:

[1149] The server automatically scores the received test answer data using AI. The input is the student's test answer data, and the output is the scoring results. The AI ​​algorithm analyzes the answers and accurately scores them.

[1150] Step 7:

[1151] The server records the grading results in a database. The input is the grading results, and the output is a notification that the results have been saved to the database. This allows each student's grades to be recorded and viewed.

[1152] Step 8:

[1153] A user's inquiry regarding the acquisition of credits is sent to the server using a terminal. The input is the user's inquiry, and the output is a notification of completion of the transmission to the server. The user enters a question in natural language and sends it to the server.

[1154] Step 9:

[1155] The server analyzes the query using natural language processing. The input is the user's query, and the output is the analysis result. The AI ​​model analyzes the query and extracts the information needed to generate the optimal answer.

[1156] Step 10:

[1157] The server generates an appropriate answer based on the analysis results and sends it back to the user via the terminal. The input is the analysis results and the output is the answer to the user. This allows questions to be answered in real time.

[1158] Step 11:

[1159] The terminal is used to scan the product and send the product information to the server. The input is barcode information, and the output is a notification that the product information has been sent. The store clerk uses a smartphone to scan the product and send the information to the server.

[1160] Step 12:

[1161] The server uses a generative AI model to automatically generate a product description for the customer. The input is the scanned product information, and the output is the generated product description. A generative AI model such as GPT-3 creates an easy-to-understand description based on the product data.

[1162] Step 13:

[1163] The product description generated for the customer is displayed through the terminal. The input is the automatically generated product description, and the output is what is presented to the customer. By having the salesperson show the generated product description to the customer, the appeal of the product can be effectively conveyed.

[1164] 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.

[1165] This invention is a system that uses AI technology to automate university education classes, tests, and grade management, providing low-cost, high-quality education. Furthermore, this invention incorporates an emotion engine that recognizes user emotions, enabling flexible education provision according to the emotional state of each individual user.

[1166] Creating course content

[1167] The server first retrieves information about the specified course topic from a database. Based on this data, an AI algorithm is used to automatically generate course slides. The AI ​​then creates a course video based on the generated slides. During this process, an emotion engine recognizes the user's emotions and can adjust the tone and level of detail of the explanations depending on their state. For example, if the user is feeling tired, the explanation can be made more concise or include words of encouragement. The generated course video and slides are stored in a database and made available for students to view.

[1168] For example, when creating a lesson on "linear algebra," the server retrieves learning material data on linear algebra, and the AI ​​generates slides including matrix calculations and solutions to linear equations. If the emotion engine recognizes that a student is confused, it generates a video with detailed explanations and additional examples, making it easier for students to understand.

[1169] Test creation, grading, and recording

[1170] The server uses AI to automatically generate test questions based on the content of lessons. The generated test questions are distributed to students via their devices. The users (students) take the test using their devices and send their answers to the server. The emotion engine monitors the user's emotions during the test and can adjust the difficulty of the questions if the user is under high stress. For example, if the user is very nervous, the difficulty of the questions can be lowered to reduce the user's burden.

[1171] The received response data is analyzed by the server's AI and automatically graded. The graded results are recorded in a database and organized for each student.

[1172] As a concrete example, when creating a "linear algebra" test, the server automatically generates questions related to matrix calculations and solving linear equations. If the user feels impatient during the test, the emotion engine will slightly lower the difficulty of the questions to maintain performance. When the user completes the test, the answer data is sent to the server, where the AI ​​scores the answer and records the score in a database.

[1173] Inquiry response

[1174] Users use their devices to submit questions about syllabuses or credit acquisition, such as, "What math courses should I take next semester?" The question is sent to a server where an AI chatbot analyzes it through natural language processing. The emotion engine can recognize the emotion of the user's inquiry and generate a response with the appropriate tone and content.

[1175] Based on the analysis, the server generates appropriate responses and sends them back to the student via their device. For example, if a student is feeling anxious, the server can provide not only syllabus information but also additional advice and words of encouragement.

[1176] For example, if a student sends a question such as "Please tell me the syllabus for mathematical statistics," the server will search the database for relevant syllabus information, organize that information, and respond to the student. If the emotion engine recognizes the student's anxiety, the response will also include advice on how to proceed with the study and the necessary preparations.

[1177] As described above, the system of the present invention uses AI technology and an emotion engine to automatically generate lecture videos and scripts, create, grade, and record tests, and respond to inquiries, thereby providing more personalized, high-quality educational services. This system can improve the efficiency of educational management and enhance students' learning experiences. It also significantly reduces the costs and labor required for traditional educational management, thereby easing the financial burden on students.

[1178] The processing flow will be explained below.

[1179] Creating course content

[1180] Step 1:

[1181] The server retrieves information about the specified course topic from the database.

[1182] Step 2:

[1183] Based on the information obtained by the server, lecture slides are automatically generated using an AI algorithm.

[1184] Step 3:

[1185] The server uses AI to automatically generate lecture videos based on the generated slides, and uses an emotion engine to recognize the user's emotional state and adjust the tone and level of detail of the explanations.

[1186] Step 4:

[1187] The server stores the generated lecture slides and videos in a database.

[1188] Test creation, grading, and recording

[1189] Step 1:

[1190] The server uses AI to automatically generate test questions based on the lesson content.

[1191] Step 2:

[1192] The test questions generated by the server are distributed to students via their terminals.

[1193] Step 3:

[1194] The user takes the test using a device and sends the answer data from the device to the server. During the test, the emotion engine monitors the user's emotions and adjusts the difficulty of the questions as needed.

[1195] Step 4:

[1196] The server analyzes the answer data received using AI and scores the answers.

[1197] Step 5:

[1198] The server records the grading results in a database and organizes them by student.

[1199] Inquiry response

[1200] Step 1:

[1201] Users use their devices to submit questions about the syllabus and credit acquisition.

[1202] Step 2:

[1203] The AI ​​chatbot analyzes the questions received by the server, and the emotion engine recognizes the user's emotional state and responds appropriately.

[1204] Step 3:

[1205] The server generates an appropriate answer based on the analysis results.

[1206] Step 4:

[1207] The server generates a response and sends it to the user via the terminal.

[1208] Example 2

[1209] 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 robot 414 will be referred to as a "terminal."

[1210] Traditional university education systems require a lot of effort and cost for creating educational content, creating and grading tests, and responding to inquiries. It has also been difficult to provide flexible education tailored to students' learning progress, level of understanding, and emotional state. This has led to a standardization of educational quality and a lack of individualized attention, resulting in issues that lead to a decline in student learning efficiency and motivation.

[1211] 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.

[1212] In this invention, the server includes means for automatically generating lecture videos and scripts, means for storing the generated lecture videos and scripts in a database, means for automatically generating test questions based on the content of the lessons, means for receiving test data answered by students, means for automatically scoring the received test data using artificial intelligence, means for recording the scoring results in a database, means for receiving inquiries from students regarding the acquisition of credits, means for analyzing using natural language processing, means for generating and providing appropriate answers based on the analysis results, means for recognizing a user's emotions using an emotion recognition system and adjusting the tone and level of detail of the lecture videos and slides based on the recognized emotions, and means for monitoring the user's emotions during the test and adjusting the difficulty of the test according to the user's stress level. This enables efficient generation of educational content, individualized responses for each student, and appropriate adjustment of the difficulty level.

[1213] 1. "Server" means a computer system that has computing capabilities, manages and processes data over a network, and provides services to other computers or devices.

[1214] 2. "Lecture Video" means video content created to provide students with visual and audio education on academic subjects, technology, etc.

[1215] 3. A "script" is text data that is automatically generated based on the content of the lecture video and slides, and serves as the basis for the text and narration that explain the educational content.

[1216] 4. "Test Questions" are automatically generated questions or tasks used to assess a student's understanding of the learning content.

[1217] 5. "Database" refers to a system for systematically storing and managing information such as course videos, scripts, test data, and grading results.

[1218] 6. "Artificial intelligence" refers to technology that mimics human thought processes and automates data analysis, problem solving, and decision-making.

[1219] 7. "Natural language processing" is a technology that enables computers to understand, analyze, and generate human language, and is used to analyze inquiries and generate appropriate responses.

[1220] 8. An "emotion recognition system" is a technology that analyzes a user's facial expressions and tone of voice to identify their emotional state.

[1221] 9. "Tone" refers to the way information is conveyed or the style of speaking, which is adjusted according to emotion or situation.

[1222] 10. "Level of detail" refers to the specific level of detail provided in the information, and indicates the depth of content and the degree of specificity of the explanation.

[1223] 11. "Emotion" refers to a user's temporary emotional state or psychological response.

[1224] 12. "Stress level" indicates the degree of psychological stress or mental tension felt by the user.

[1225] This invention is a system that uses AI technology to automate university education classes, tests, and grade management, providing low-cost, high-quality education. It also incorporates an emotion engine that recognizes user emotions, enabling flexible education provision according to the emotional state of each individual user.

[1226] First, the server creates the course content. It retrieves information about the specified course topic from the database and automatically generates course slides using a generative AI model (e.g., GPT-4). Next, it creates a course video based on the generated slides using an AI voiceover model. At this time, an emotion recognition system analyzes the user's emotions in real time and can adjust the tone and level of detail of the explanation. The generated course video and slides are stored in the database and can be viewed by students via their devices.

[1227] As a concrete example, when creating a "Linear Algebra" course, the server retrieves teaching material data related to linear algebra from the database, inputs a prompt to the generative AI model saying, "Create slides related to matrix calculations in linear algebra," and creates slides including matrix definitions, calculation procedures, and example problems. It then uses a speech synthesis system (e.g., Google Text-to-Speech) to generate audio that reads the contents of the slides, and generates a video that combines this with the slides.

[1228] The server then automatically generates test questions based on the content of the class. The test questions generated using AI are distributed to students via their devices, who then take the test and send their answers to the server. The emotion recognition system monitors the user's emotions during the test and can adjust the difficulty of the questions according to their stress level. The received answer data is analyzed by the server's AI and automatically scored. The scoring results are recorded in a database and organized for each student.

[1229] As a specific example, when delivering a "Linear Algebra" test, the server inputs a prompt such as "Create test questions centered on matrix calculations" into a generative AI model, generating multiple questions. If a facial expression analysis system (e.g., Affectiva) determines that the user is feeling impatient during the test, the difficulty of the next question can be lowered. When the user completes the test, the answer data is sent to the server, where the AI ​​scores the questions and records the results in a database.

[1230] Users can also use their devices to send questions about the syllabus or credit acquisition to the server. The questions are analyzed by an AI chatbot (using natural language processing technology) and an appropriate answer is generated. The emotion recognition system can recognize the user's emotion when making an inquiry and generate an answer with a tone and content that matches it.

[1231] Example: When a user submits the question, "What math courses should I take next semester?", the server analyzes the question and generates specific advice such as, "The math courses you should take next semester are linear algebra and calculus." If the emotion recognition system recognizes the user's anxiety, it responds with encouraging words such as, "Don't worry, it's okay."

[1232] As described above, the system for implementing the present invention can automatically generate lecture videos and slides, create, grade, and record tests, and respond to inquiries using AI technology and an emotion recognition system, providing personalized, high-quality educational services. This system can improve the efficiency of educational management and enhance students' learning experiences. It can also significantly reduce the costs and labor required for traditional educational management, thereby easing the financial burden on students.

[1233] The flow of the identification process in the second embodiment will be described with reference to FIG.

[1234] Creating course content

[1235] Step 1: Get information about course topics from the database

[1236] The server is given a course topic as input. For example, if the topic is "Linear Algebra," the server accesses the database and executes an SQL query (e.g., "SELECT FROM Courseware WHERE Topic='Linear Algebra'"), which returns information about linear algebra as output.

[1237] Step 2: Automatically generate lecture slides using AI algorithms

[1238] The server uses the acquired teaching material information as input and generates a prompt for the generative AI model, such as "Create slides on matrix calculations in linear algebra." By providing this prompt, the AI ​​algorithm automatically generates the slides. The output is a set of slides that includes matrix definitions, calculation procedures, and example problems.

[1239] Step 3: Generate course videos

[1240] The server uses the generated slides as input and creates a lecture video using an AI voice-over model. For example, it uses a speech synthesis system (e.g., Google Text-to-Speech) to generate a voice that reads the contents of the slides, and combines it with the slides to create a video. The lecture video is generated as output.

[1241] Step 4: Adjust tone and detail with the emotion engine

[1242] The server uses an emotion recognition system to analyze the user's facial expressions and tone of voice. The user's emotional data is provided as input, and the tone and level of detail of the generated video are adjusted as output. For example, if the server determines that the user is feeling fatigued, it generates a video containing a brief explanation and encouraging words.

[1243] Step 5: Save the course video and slides

[1244] The server takes the generated lecture videos and slides as input and stores them in a database. This generates a URL that students can access through their devices. The output is the saved lecture videos and slides and a URL.

[1245] Test creation, grading, and recording

[1246] Step 1: Automatically generate test questions based on lesson content

[1247] The server takes the lesson content as input and generates prompts to the generative AI model, such as "Create test questions centered on matrix calculations." This automatically generates test questions, and a test question set is generated as output.

[1248] Step 2: Distribute the test questions to students

[1249] The server takes the generated test questions as input and distributes them to students via their terminals. For example, it generates a test web page and sends the URL to students via email. The test questions are distributed as output.

[1250] Step 3: Collect user responses and sentiment data

[1251] The user takes the test using a terminal and sends the answer data as input to the server. The emotion recognition system collects the user's emotional data during the test. The answer data and the user's emotional data are obtained as output.

[1252] Step 4: Analyze responses and auto-score

[1253] The server takes the answer data as input and automatically scores it using AI. For example, it analyzes the answer content using a natural language processing (NLP) algorithm and calculates the score based on the point allocation. The scoring result is obtained as output.

[1254] Step 5: Recording and feedback of results

[1255] The server takes the grading results as input, records them in a database, and organizes them for each student. It also automatically generates performance feedback and provides it to students via their devices. The server outputs the grading results and feedback.

[1256] Inquiry response

[1257] Step 1: Submitting a user question

[1258] A user uses a terminal to send a question to the server, for example, "What math courses should I take next semester?" The question data is sent to the server as output.

[1259] Step 2: Parsing the Question

[1260] The server takes the question data as input, analyzes the question using natural language processing technology, and outputs the analysis results.

[1261] Step 3: Generate appropriate answers

[1262] The server uses the analysis results as input and generates an appropriate answer using a generative AI model. For example, it generates an answer such as, "The mathematics courses you should take next semester are linear algebra and calculus." The answer data is obtained as output.

[1263] Step 4: Submit your response

[1264] The server receives the generated answer data as input and responds to the user via the device. The emotion recognition system analyzes the user's emotions and adds words of encouragement as needed. The answer is provided to the user as output.

[1265] (Application example 2)

[1266] 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 robot 414 will be referred to as a "terminal."

[1267] Conventional educational systems often struggle to individualize education and are unable to respond flexibly to the emotional state of a particular student. This makes it difficult to improve students' understanding, and also results in insufficient individualized responses to increase customer satisfaction. In particular, brick-and-mortar stores require a system that can recognize customers' emotional states in real time and respond appropriately to those states.

[1268] The specific processing by the specific processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means. In this invention, the server includes means for automatically generating lecture videos and scripts, means for saving the generated lecture videos and scripts in a database, and means for automatically generating test questions based on the lesson content. This enables the automatic generation of lecture videos and scripts, making it possible to improve the efficiency and quality of education.

[1269] The system also includes a means for receiving test data answered by students using a user device, a means for automatically scoring the received test data using AI, a means for recording the scoring results in a database, a means for receiving inquiries from students regarding obtaining credits and analyzing them using natural language processing, a means for generating and providing appropriate answers based on the analysis results, a means for monitoring the user's emotional state in real time using an emotion recognition engine, and a means for providing a response method according to the user's emotional state.This enables flexible responses according to the student's emotional state, thereby achieving individualized education.In addition, in customer service, it enables appropriate responses in real time according to the customer's emotional state, thereby improving customer satisfaction.

[1270] "Means for automatically generating lecture videos and scripts" refers to technology that uses algorithms or models to automatically generate educational content on specified topics and corresponding scripts.

[1271] "Means for storing the generated lecture videos and scripts in a database" refers to a technology that stores the generated educational content in a database in a persistent format so that it can be accessed and referenced later.

[1272] "Means for automatically generating test questions based on class content" refers to technology that automatically generates assessment questions based on the topic and content of a class and presents them to test takers.

[1273] "Means for receiving test data answered by students using user devices" refers to technology for sending and receiving data on students' answers to test questions to a server via the Internet or a local network.

[1274] "Means for automatically scoring received test data using AI" refers to a technology that uses artificial intelligence technology to evaluate the test data answered by test takers and automatically calculate scores.

[1275] "Means for recording scoring results in a database" refers to a technology that stores the results scored by AI in a database so that they can be accessed and referenced later.

[1276] "Means for receiving inquiries from students regarding the acquisition of credits and analyzing them using natural language processing" refers to a technology in which students submit questions regarding the acquisition of credits or courses and the questions are analyzed using natural language processing technology.

[1277] "Means for generating and providing appropriate answers based on analysis results" refers to technology that automatically generates appropriate, contextual answers based on the results of analysis using natural language processing and provides them to users.

[1278] "Means for monitoring a user's emotional state in real time using an emotion recognition engine" is a technology that analyzes image data, audio data, etc. to identify a user's current emotional state in real time.

[1279] The "means for providing a response method according to the user's emotional state" is a technology that automatically generates appropriate response methods and advice based on the recognized emotional state and provides them to the user.

[1280] This invention is a system that combines AI technology and emotion recognition technology to respond to the needs of education and customer service by providing personalized responses according to the user's emotional state. The system operates mainly with three parties: a server, a terminal, and the user.

[1281] server

[1282] The server first retrieves information about the specified topic from the database. Based on this data, the algorithm uses a generative AI model to automatically generate lecture slides and lecture videos. An emotion recognition engine monitors the user's emotional state and, for example, if the user is feeling tired, generates a concise, encouraging video. The generated lecture videos and scripts are stored in the database and can be viewed by users.

[1283] Next, the generative AI model automatically generates test questions based on the lesson content. The generated test is delivered to the user's device, and the user takes the test. The answers are sent from the device to a server, and the server's AI automatically scores the received test data. The scoring results are recorded in a database and can be viewed by the user later.

[1284] Terminal

[1285] Users use devices such as smart glasses. These devices capture the user's facial expressions and voice in real time, and an emotion recognition engine analyzes the data. Based on the analysis results, the device provides the user with appropriate advice and methods of response in real time. For example, if a salesperson in a physical store is using smart glasses and the customer looks anxious, a message will appear on the glasses' display saying, "This customer seems anxious. Please try to explain in a way that puts them at ease."

[1286] User

[1287] In implementing the invention, users use the system on the front lines. For example, they watch video lectures and answer generated tests. If they have any questions, they input them in natural language, and the system generates and provides appropriate answers.

[1288] Specific examples

[1289] For example, in a university linear algebra class, a server retrieves linear algebra teaching data, and a generative AI model generates slides including matrix calculations and linear equation solutions. If an emotion recognition engine detects that a student is confused, it creates a video with more detailed explanations and additional examples, helping students to deepen their understanding.

[1290] An example of a prompt would be:

[1291] You are a sales staff member at a brick-and-mortar store wearing smart glasses. The camera is currently capturing the facial expression of a customer standing at the counter. If the customer's emotion is recognized as "anxiety," the advice displayed is "This customer seems anxious. Try to explain in a reassuring way."

[1292] By utilizing these technologies, it is possible to personalize education and improve customer service. This system makes it possible to flexibly respond to individual needs that would be difficult to meet using conventional methods.

[1293] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[1294] Step 1:

[1295] The server retrieves information about the specified course topic from the database, including lecture content, slides, references, etc. It processes the input data from the database and extracts the necessary information about the topic.

[1296] Step 2:

[1297] The server uses a generative AI model based on the acquired data to automatically generate lecture slides and lecture videos. The generative AI model analyzes the text data and generates appropriate visual content and explanatory text. The generated lecture slides and lecture videos are stored in a database. The input is teaching material data related to the topic, and the output is the generated slides and lecture videos.

[1298] Step 3:

[1299] The server receives requests for access to the lecture videos and slides from users' devices. Users send requests to view the lectures using devices such as smart glasses or PCs. Based on the requests, the server distributes the generated content to the users' devices.

[1300] Step 4:

[1301] While the user is watching the lecture video, the emotion recognition engine analyzes the user's facial expressions and voice in real time through the smart glasses and camera. The input is the user's real-time video and audio data, and the output is the user's emotional state.

[1302] Step 5:

[1303] The server receives the user's emotional state from the emotion recognition engine and adjusts the content of the lecture video and slides in real time. For example, if the server detects that the user is confused, it generates a video with detailed explanations and additional examples and provides it to the user. The input is the user's emotional state, and the output is the adjusted educational content.

[1304] Step 6:

[1305] The server automatically creates test questions using a generative AI model based on the content of the lecture. The generated test questions are then delivered to the user's device. The input is the lecture content data, and the output is the generated test questions.

[1306] Step 7:

[1307] Users answer test questions using their devices and send their answers to the server. The server analyzes the received test data and automatically scores it using an AI model. The input is the user's test answer data, and the output is the scoring results.

[1308] Step 8:

[1309] The server records the scoring results in a database so that users can check them later. The input is the scoring result data, and the output is the results recorded in the database.

[1310] Step 9:

[1311] The device receives inquiries from users regarding the acquisition of credits and sends the details to the server. The server analyzes the inquiries using AI models and natural language processing and generates appropriate answers. The input is the text data of the inquiries, and the output is the analysis results and the generated answers.

[1312] Step 10:

[1313] The server sends the generated answer to the user's terminal and provides it to the user. The input is the generated answer, and the output is the answer displayed on the user's terminal.

[1314] Through these steps, we can provide efficient, high-quality service that meets the individual needs of our users in both education and customer service.

[1315] The specific processing unit 290 transmits the result of the specific processing to the robot 414. In the robot 414, the control unit 46A causes the speaker 240 and the control target 443 to output the result of the specific processing. The microphone 238 acquires voice indicating a user input regarding the result of the specific processing. The control unit 46A transmits voice data indicating the user input acquired by the microphone 238 to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the voice data.

[1316] 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.

[1317] 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 robot 414.

[1318] The emotion identification model 59 as an emotion engine may determine the user's emotion according to a specific mapping. Specifically, the emotion identification model 59 may determine the user's emotion according to an emotion map (see FIG. 9), which is a specific mapping. Similarly, the emotion identification model 59 may determine the robot's emotion, and the identification processing unit 290 may perform identification processing using the robot's emotion.

[1319] FIG. 9 is a diagram illustrating an emotion map 400 on which multiple emotions are mapped. In the emotion map 400, emotions are arranged in concentric circles radiating from the center. Emotions closer to the center of the concentric circles are more primitive. Emotions representing states and actions arising from a state of mind are arranged on the outer edges of the concentric circles. The concept of emotion includes both affect and mental states. Emotions generally generated from reactions occurring in the brain are arranged on the left side of the concentric circles. Emotions generally induced by situational judgment are arranged on the right side of the concentric circles. Emotions generally generated from reactions occurring in the brain and induced by situational judgment are arranged on the upper and lower sides of the concentric circles. Furthermore, the emotion of "pleasure" is arranged on the upper side of the concentric circles, and the emotion of "discomfort" is arranged on the lower side. In this way, in the emotion map 400, multiple emotions are mapped based on the structure by which emotions are generated, and emotions that tend to occur simultaneously are mapped close to each other.

[1320] These emotions are distributed in the 3 o'clock direction on emotion map 400, and typically fluctuate between relief and anxiety. In the right half of emotion map 400, situational awareness dominates over internal sensations, resulting in a sense of calm.

[1321] The inside of emotion map 400 represents what is going on in the mind, and the outside of emotion map 400 represents behavior, so the further you go outside emotion map 400, the more visible the emotions become (the more they are expressed in behavior).

[1322] Human emotions are based on various balances, such as posture and blood sugar levels. When these balances deviate from the ideal, a state of discomfort is indicated, and when they approach the ideal, a state of pleasure is indicated. Emotions can also be created for robots, automobiles, and motorcycles, based on various balances, such as posture and remaining battery life. When these balances deviate from the ideal, a state of discomfort is indicated, and when they approach the ideal, a state of pleasure is indicated. An emotion map can be generated, for example, based on Dr. Mitsuyoshi's emotion map (Research on Voice Emotion Recognition and Emotional Brain Physiological Signal Analysis Systems, Tokushima University, Doctoral Dissertation: https: / / ci.nii.ac.jp / naid / 500000375379). The left half of the emotion map lists emotions belonging to the "reaction" domain, where sensation is dominant. The right half of the emotion map lists emotions belonging to the "situation" domain, where situational awareness is dominant.

[1323] The emotion map defines two emotions that promote learning. One is a negative emotion on the situation side, around the middle of "repentance" or "reflection." In other words, this occurs when the robot experiences negative emotions such as "I never want to feel this way again" or "I don't want to be scolded again." The other is a positive emotion on the response side, around "desire." In other words, this occurs when the robot experiences positive feelings such as "I want more" or "I want to know more."

[1324] The emotion identification model 59 inputs user input into a pre-trained neural network, obtains emotion values ​​indicating each emotion shown in the emotion map 400, and determines the user's emotion. This neural network is pre-trained based on multiple pieces of training data that are combinations of user input and emotion values ​​indicating each emotion shown in the emotion map 400. Furthermore, this neural network is trained so that emotions that are located close to each other have similar values, as in the emotion map 900 shown in FIG. 10. FIG. 10 shows an example in which multiple emotions, "relieved," "calm," and "reassuring," have similar emotion values.

[1325] The system according to the present disclosure has been described above mainly with respect to the functions of the data processing device 12, but the system according to the present disclosure is not necessarily implemented on a server. The system according to the present disclosure may be implemented as a general information processing system. The present disclosure may be implemented, for example, as a software program running on a personal computer or an application running on a smartphone, etc. The method according to the present disclosure may be provided to users in the form of SaaS (Software as a Service).

[1326] In the above embodiment, an example was given in which the specific processing is performed by one computer 22, but the technology of the present disclosure is not limited to this, and the specific processing may be distributed and performed by a plurality of computers including the computer 22. For example, the data generation model 58 may be provided in an external device of the data processing device 12, and data may be generated in the external device in accordance with input data.

[1327] In the above embodiment, an example in which the specific processing program 56 is stored in the storage 32 has been described, but the technology of the present disclosure is not limited to this. For example, the specific processing program 56 may be stored in a portable, computer-readable, non-transitory storage medium such as a USB (Universal Serial Bus) memory. The specific processing program 56 stored in the non-transitory storage medium is installed in the computer 22 of the data processing device 12. The processor 28 executes the specific processing in accordance with the specific processing program 56.

[1328] Alternatively, the specific processing program 56 may be stored in a storage device such as a server connected to the data processing device 12 via the network 54, and the specific processing program 56 may be downloaded and installed on the computer 22 in response to a request from the data processing device 12.

[1329] It is not necessary to store all of the specific processing program 56 in a storage device such as a server connected to the data processing device 12 via the network 54, or to store all of the specific processing program 56 in the storage 32; only a portion of the specific processing program 56 may be stored.

[1330] The hardware resource for executing a specific process can be any of the following processors: An example of a processor is a CPU, which is a general-purpose processor that functions as a hardware resource for executing a specific process by executing software, i.e., a program. Another example of a processor is a dedicated electrical circuit, such as an FPGA (Field-Programmable Gate Array), a PLD (Programmable Logic Device), or an ASIC (Application Specific Integrated Circuit), which is a processor with a circuit configuration designed specifically for executing a specific process. Each processor has built-in or connected memory, and each processor uses the memory to execute the specific process.

[1331] The hardware resource that executes the specific processing may be configured with one of these various processors, or may be configured with a combination of two or more processors of the same or different types (for example, a combination of multiple FPGAs, or a combination of a CPU and an FPGA). Also, the hardware resource that executes the specific processing may be a single processor.

[1332] As an example of a system configured with a single processor, first, one processor is configured by combining one or more CPUs and software, and this processor functions as a hardware resource that executes a specific process. Second, there is a system that uses a processor that realizes the functions of an entire system including multiple hardware resources that execute a specific process on a single IC chip, as typified by SoC (System-on-a-chip). In this way, a specific process is realized using one or more of the above-mentioned various processors as hardware resources.

[1333] Furthermore, the hardware structure of these various processors can be, more specifically, an electric circuit that combines circuit elements such as semiconductor devices. The specific processing described above is merely an example. Therefore, it goes without saying that unnecessary steps may be deleted, new steps may be added, or the processing order may be rearranged, without departing from the spirit of the invention.

[1334] The above-described description and illustrations are a detailed explanation of the parts related to the technology of the present disclosure and are merely an example of the technology of the present disclosure. For example, the above description of the configuration, functions, actions, and effects is an explanation of an example of the configuration, functions, actions, and effects of the parts related to the technology of the present disclosure. Therefore, it goes without saying that unnecessary parts may be deleted, new elements may be added, or replacements may be made to the above-described description and illustrations within the scope of the gist of the technology of the present disclosure. Furthermore, to avoid confusion and facilitate understanding of the parts related to the technology of the present disclosure, the above-described description and illustrations omit explanations of common technical knowledge that do not require particular explanation to enable the implementation of the technology of the present disclosure.

[1335] All publications, patent applications, and technical standards mentioned in this specification are herein incorporated by reference to the same extent as if each individual publication, patent application, or technical standard was specifically and individually indicated to be incorporated by reference.

[1336] The following is further disclosed regarding the above embodiment.

[1337] (Claim 1)

[1338] A means for automatically generating lecture videos and scripts;

[1339] A means for storing the generated lecture videos and scripts in a database;

[1340] A means for automatically generating test questions based on the content of lessons;

[1341] a means for receiving test data completed by students;

[1342] A means of automatically scoring received test data using AI,

[1343] a means for recording the results of the scoring in a database;

[1344] Receive inquiries from students regarding credit acquisition,

[1345] A means of analyzing using natural language processing;

[1346] A means for generating and providing an appropriate answer based on the analysis results;

[1347] A system including:

[1348] (Claim 2)

[1349] 10. The system of claim 1, further comprising means for automatically generating lesson slides and lecture videos.

[1350] (Claim 3)

[1351] 10. The system of claim 1, further comprising means for analyzing and generating answers to queries in real time.

[1352] "Example 1"

[1353] (Claim 1)

[1354] A means for automatically generating lecture videos and scripts;

[1355] A means for storing the generated lecture videos and scripts in a database;

[1356] A means for automatically generating test questions based on the content of the lesson;

[1357] means for receiving test data answered by learners;

[1358] A means for automatically scoring the received test data using artificial intelligence;

[1359] a means for recording the results of the scoring in a database;

[1360] Receive inquiries from learners regarding the acquisition of credits,

[1361] A means of analyzing using natural language processing;

[1362] A means for generating and providing an appropriate answer based on the analysis results;

[1363] means for retrieving information about a specified course topic from a database;

[1364] A means for automatically generating course materials by analyzing the acquired information;

[1365] A means for generating a lecture video by a virtual instructor based on the materials;

[1366] A means of using AI to provide answers to learners' inquiries in real time,

[1367] A system including:

[1368] (Claim 2)

[1369] 10. The system of claim 1, further comprising means for automatically generating lesson slides and lecture videos.

[1370] (Claim 3)

[1371] 10. The system of claim 1, further comprising means for analyzing and generating answers to queries in real time.

[1372] "Application Example 1"

[1373] (Claim 1)

[1374] A means for automatically generating lecture videos and scripts;

[1375] A means for storing the generated lecture videos and scripts in a database;

[1376] A means for automatically generating test questions based on the content of lessons;

[1377] a means for receiving test data completed by students;

[1378] A means of automatically scoring received test data using AI,

[1379] a means for recording the results of the scoring in a database;

[1380] Receive inquiries from students regarding credit acquisition,

[1381] A means of analyzing using natural language processing;

[1382] A means for generating and providing an appropriate answer based on the analysis results;

[1383] A means of acquiring product information and automatically generating product descriptions for customers using a generative AI model;

[1384] A means for analyzing customer inquiries using natural language processing and generating and providing appropriate answers;

[1385] A system including:

[1386] (Claim 2)

[1387] 10. The system of claim 1, further comprising means for automatically generating lesson slides and lecture videos.

[1388] (Claim 3)

[1389] 10. The system of claim 1, further comprising means for analyzing and generating answers to queries in real time.

[1390] "Example 2: Combining Emotion Engines"

[1391] (Claim 1)

[1392] A means for automatically generating lecture videos and scripts;

[1393] A means for storing the generated lecture videos and scripts in a database;

[1394] A means for automatically generating test questions based on the content of lessons;

[1395] a means for receiving test data completed by students;

[1396] A means for automatically scoring the received test data using artificial intelligence;

[1397] a means for recording the results of the scoring in a database;

[1398] a means of receiving inquiries from students regarding credit acquisition;

[1399] A means of analyzing using natural language processing;

[1400] A means for generating and providing an appropriate answer based on the analysis results;

[1401] a means for recognizing a user's emotion using an emotion recognition system and adjusting the tone and level of detail of the lecture video and slides based on the recognized emotion;

[1402] means for monitoring the user's emotions during the test and adjusting the difficulty of the test according to the user's stress level;

[1403] A system including:

[1404] (Claim 2)

[1405] 10. The system of claim 1, further comprising means for automatically generating lesson slides and lecture videos.

[1406] (Claim 3)

[1407] 10. The system of claim 1, further comprising means for analyzing and generating answers to queries in real time.

[1408] "Application example 2 when combining emotion engines"

[1409] (Claim 1)

[1410] A means for automatically generating lecture videos and scripts;

[1411] A means for storing the generated lecture videos and scripts in a database;

[1412] A means for automatically generating test questions based on the content of lessons;

[1413] means for receiving test data completed by a student using a user device;

[1414] A means of automatically scoring received test data using AI,

[1415] a means for recording the results of the scoring in a database;

[1416] Receive inquiries from students regarding credit acquisition,

[1417] A means of analyzing using natural language processing;

[1418] A means for generating and providing an appropriate answer based on the analysis results;

[1419] means for monitoring the user's emotional state in real time using an emotion recognition engine;

[1420] means for providing a response method according to the emotional state of the user;

[1421] A system including:

[1422] (Claim 2)

[1423] 10. The system of claim 1, further comprising means for automatically generating lesson slides and lecture videos.

[1424] (Claim 3)

[1425] 10. The system of claim 1, further comprising means for analyzing and generating answers to queries in real time. [Explanation of symbols]

[1426] 10, 210, 310, 410 Data Processing Systems 12 Data Processing Device 14 Smart Devices 214 Smart Glasses 314 Headset-type terminal 414 Robot< / url:> < / url:> < / url:> < / url:>

Claims

1. A means for automatically generating lecture videos and scripts; A means for storing the generated lecture videos and scripts in a database; A means for automatically generating test questions based on the content of lessons; a means for receiving test data completed by students; A means of automatically scoring received test data using AI, a means for recording the results of the scoring in a database; Receive inquiries from students regarding credit acquisition, A means of analyzing using natural language processing; A means for generating and providing an appropriate answer based on the analysis results; A system including:

2. The system of claim 1 further comprising means for automatically generating lesson slides and lecture videos.

3. 10. The system of claim 1, further comprising means for analyzing and generating answers to queries in real time.

Images