System

Abstract

A system is provided.SOLUTION: A system comprising: generating means for generating homework assignments or examination questions based on a subject and a difficulty level selected by a teacher; distributing means for distributing the generated homework assignments or examination questions to digital devices of students; inputting means for inputting answers by the students using the digital devices; scoring means for automatically scoring the input answers; result notifying means for instantaneously returning the scoring results to the devices of the students; and explanation generating means for generating an explanation of a wrong part or a repair question as necessary and displaying the explanation or the repair question on the devices of the students.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] Teachers have a wide range of daily tasks, including lesson preparation, student guidance, and club activities. Among these, creating and grading homework and exam questions is a significant burden. Overwork and stress are particularly significant issues for teachers in Japan, and systems to alleviate these problems are needed. There is also a need for grading quickly and accurately, which improves students' learning outcomes. To solve these issues, a system is needed that can automatically generate homework and exam questions, grade them, and provide feedback all at once. [Means for solving the problem]

[0005] The present invention provides a system that includes a means for generating homework and test questions based on the subject and level of difficulty selected by a teacher using a generation AI, a means for distributing the generated homework and test questions to students' digital devices, a means for students to input answers using their digital devices, a means for automatically grading the input answers, a means for instantly returning the grading results to the students' devices, and a means for generating explanations and correction questions for incorrect sections and displaying them on the students' devices as needed. Furthermore, by providing a means for teachers to check the generated homework and test questions and make corrections or additions, and a means for storing the generated homework and test questions, students' answers, and grading results in a database, the system significantly reduces teachers' workload, improves teachers' work-life balance, and enhances students' learning effectiveness.

[0006] The "generation means" is a means for automatically generating homework and test questions based on the subject and level of difficulty selected by the teacher.

[0007] "Distribution means" refers to a means for distributing the generated homework and exam questions to students' digital devices.

[0008] "Input means" refers to the means by which students use digital devices to input answers to homework and exam questions.

[0009] A "grading tool" is a tool for automatically grading answers entered by students.

[0010] A "result notification means" is a means for instantly returning graded results to students' digital devices.

[0011] The "explanation generating means" is a means for automatically generating and displaying explanations and correction questions for the student's mistakes as needed.

[0012] The "verification means" is a means by which a teacher can check the generated homework and test questions and make corrections or additions.

[0013] The "storage means" is a means for storing the generated homework and test questions, student answers, and grading results in a database. [Brief explanation of the drawings]

[0014] [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

[0015] 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.

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

[0017] 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).

[0018] 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.

[0019] 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.

[0020] 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.

[0021] 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."

[0022] [First embodiment]

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

[0024] 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.

[0025] 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).

[0026] 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.

[0027] 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.

[0028] The output device 40 includes a display 40A and a speaker 40B, and presents data to the user 20 by outputting the data in a form 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.

[0029] 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.

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

[0031] 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.

[0032] 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.

[0033] 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.

[0034] 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."

[0035] The present invention is a system that enables teachers to efficiently generate, distribute, grade, and provide feedback on homework and test questions, and has the following specific embodiments.

[0036] Overall system configuration

[0037] The system mainly consists of the following components:

[0038] 1. Server

[0039] 2. Teacher's device

[0040] 3. Student Devices

[0041] Teacher's device

[0042] 1. A user (teacher) logs in to the system using the teacher's terminal and sends a request to generate homework or exam questions. Specifically, the user selects a subject (e.g., mathematics) and difficulty level (e.g., intermediate level) and sends a request to the system.

[0043] server

[0044] 1. The server receives the teacher's request and passes the request information to the generative AI model, which then generates appropriate homework and exam questions based on the specified subject and difficulty level.

[0045] 2. The server stores the generated questions in a database, which includes the question text, correct answers, explanations, etc. The server then sends the generated questions back to the teacher's device so that the teacher can check them.

[0046] Teacher's device

[0047] 1. The user (teacher) checks the generated questions and makes corrections or additional comments as necessary, thereby maintaining the accuracy and appropriateness of the questions.

[0048] server

[0049] 1. After the teacher has finalized the questions, the server requests that the questions be distributed to the students' devices. The questions are distributed based on the student ID and class information.

[0050] Student devices

[0051] 1. The user (student) logs in to their device and accesses the distributed questions. An interface for answering the questions is displayed, and the user enters their answers.

[0052] 2. The student's device sends the entered answers to the server, which receives and stores the answers.

[0053] server

[0054] 1. The server automatically scores the questions using an AI model based on the saved answers. It compares the correct answers with the student's answers and generates a score. This score is recorded for each student and stored in a database.

[0055] 2. The server sends the scoring results back to the student's device and also generates detailed explanations and correction questions for any mistakes.

[0056] Student devices

[0057] 1. The student's device will display the graded results, explanations, and supplementary questions to the student, allowing them to quickly and effectively check their learning progress and review any necessary sections.

[0058] Specific use cases

[0059] For example, if a teacher wants to generate intermediate-level mathematics exam questions, the teacher sends a request from their device to the server, selecting the subject "Mathematics" and the difficulty level "Intermediate." The server then invokes the generative AI model, generates an appropriate set of questions, and sends them back to the teacher's device. After the teacher checks the generated questions, they distribute them to students. Students then answer the questions using their digital devices and send their answers to the server. The server automatically grades the answers, providing instant feedback and explanations or remedial questions as needed.

[0060] This system is expected to significantly reduce the workload of teachers and improve students' learning outcomes.

[0061] The processing flow will be explained below.

[0062] Step 1:

[0063] A user (teacher) logs in to the system using the teacher's terminal and sends a request to generate homework or exam questions. Specifically, the user selects a subject (e.g., mathematics) and a level of difficulty (e.g., intermediate level) and clicks the "Generate" button.

[0064] Step 2:

[0065] The teacher's terminal sends a request to the server including the subject and difficulty level information input by the user.

[0066] Step 3:

[0067] The server receives requests from the teacher's device and passes the request information to the generative AI model. The server then sends a "Mathematics" "Intermediate" problem generation request to the AI ​​model.

[0068] Step 4:

[0069] The generative AI model generates appropriate homework and exam questions based on the subject and level of difficulty, including the question statement, correct answers, and explanations.

[0070] Step 5:

[0071] The server stores the generated questions in a database, which includes information such as the question, the correct answer, and an explanation.

[0072] Step 6:

[0073] The server sends the generated questions back to the teacher's terminal, where the teacher can check the questions.

[0074] Step 7:

[0075] The user (teacher) checks the generated questions and makes corrections or additional comments as necessary. Once the teacher reviews and confirms the questions, the questions based on this are sent to the server.

[0076] Step 8:

[0077] After the teacher has finalized the questions, the server sends a request to distribute the questions to the students' devices. The server retrieves the student's ID and class information from the database and distributes the questions.

[0078] Step 9:

[0079] The user (student) logs in to the student's terminal and accesses the distributed questions. An interface for answering the questions is displayed, and the user inputs their answers.

[0080] Step 10:

[0081] The student's device sends the answers entered by the user (student) to the server, which receives the answers and stores them in a database.

[0082] Step 11:

[0083] The server automatically grades the questions using an AI model based on the stored answers. The server compares the correct answers with the student's answers and generates a score.

[0084] Step 12:

[0085] The server returns the graded results to the student's terminal and also sends a request to the explanation generation means to generate detailed explanations and correction questions for the incorrect parts.

[0086] Step 13:

[0087] The explanation generating means generates explanations and correction questions as needed and sends them back to the server.

[0088] Step 14:

[0089] The server sends explanations and supplementary questions to the students' devices and records them in a database as logs.

[0090] Step 15:

[0091] The user (student) can check the grades, explanations, and supplementary questions on their own device, allowing them to check their own understanding and review any necessary parts.

[0092] Example 1

[0093] 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."

[0094] In conventional educational systems, teachers manually create homework and exam questions, distribute them to students, and then grade and provide feedback, requiring a great deal of time and effort. This cumbersome process reduces teachers' work efficiency and hinders their ability to provide prompt feedback to students. Furthermore, the balance between question content and difficulty level is inconsistent, making it difficult to provide personalized support based on each student's learning progress. To address these issues, the present invention aims to provide a system that automates teachers' work and provides appropriate and prompt feedback to students.

[0095] 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.

[0096] In this invention, the server includes a generating means for generating homework and test questions based on the subject and difficulty level selected by the teacher, a distributing means for distributing the generated homework and test questions to the students' digital devices, an input means for the students to input answers using their digital devices, a sending and saving means for sending the input answers to the server and saving them, a scoring means for automatically scoring the saved answers, a result notifying means for returning the scoring results to the students' digital devices, and an explanation generating means for generating explanations and correction questions for incorrect parts as needed and displaying them on the students' digital devices. This reduces the workload on teachers and enables them to provide students with quick and appropriate feedback.

[0097] "Generative means" refers to a function that automatically generates homework and exam questions using an AI model based on the subject and difficulty level selected by the teacher.

[0098] "Distribution means" refers to the function of sending generated homework and exam questions to students' digital devices in an appropriate format.

[0099] "Input means" refers to the interface and functionality that allows students to input answers to homework and exam questions using digital devices.

[0100] The "transmission and storage means" is a function that sends the answers entered by the students to the server and stores them in a database.

[0101] The "scoring method" is a function that automatically scores answers stored on the server using an AI model to generate a score.

[0102] "Result notification means" is a function that quickly returns graded results to students' digital devices.

[0103] The "explanation generation means" is a function that generates explanations and correction questions for incorrect parts as needed and displays them on the student's digital device.

[0104] "Storage means" is a function that stores generated homework and test questions, students' answers, and grading results in a database, allowing the information to be retrieved later.

[0105] The present invention is a system for teachers to efficiently generate, distribute, grade, and provide feedback on homework and exam questions. The system comprises the following components:

[0106] Overall system configuration

[0107] The main components of the system are:

[0108] 1. Server

[0109] 2. Teacher's device

[0110] 3. Student Devices

[0111] Teacher's device

[0112] Users (teachers) log in to the system from their own devices via an internet browser and use a dedicated application (e.g., a UI built with React) to send a request to the server to generate homework or exam questions. The teacher selects the subject (e.g., mathematics) and difficulty level (e.g., intermediate), and presses the generate button, which sends the request to the server. An example of a prompt sentence is "Please create intermediate-level mathematics exam questions."

[0113] server

[0114] The server has a backend system written in Python that receives requests, analyzes them, and sends prompts to an AI model (e.g., OpenAI GPT-3), which then generates an appropriate problem set based on the specified subject and difficulty level.

[0115] The generated problem set is sent back to the server in JSON format, which stores it in a MySQL database. The stored data includes the problem statement, correct answers, and explanations. The generated problem set is then sent back to the teacher's computer.

[0116] Teacher's device

[0117] The user (teacher) checks the generated questions and, if necessary, edits the question text and explanations using a rich text editor (e.g., Quill.js). Once the edits are complete, the user presses the confirm button to send a request to the server to save the changes.

[0118] server

[0119] The server then obtains a list of students based on their IDs and class information to distribute the finalized questions to them. At this time, the questions are again organized in JSON format and sent to the students' devices.

[0120] Student devices

[0121] Users (students) log in to their own devices and access the distributed questions. An interface built with Angular is displayed on the student's device, allowing the user to enter answers to the questions.

[0122] server

[0123] The student's device sends the entered answers in JSON format to the server. The server receives them and stores them in a MySQL database. Then, based on the saved answers, an AI model (e.g., TensorFlow) is used again to automatically grade the answers. The correct answer is compared with the student's answer, a score is generated, and the score is recorded in the database.

[0124] The graded results are quickly returned to the student's digital device, and feedback and correction questions are generated and sent to the student's device for any errors.

[0125] Student devices

[0126] The student's device displays the feedback, explanations, and revision questions received from the server to the user (student). The student can refer to this to check their own learning progress and review the material as appropriate.

[0127] Specific examples

[0128] For example, if a teacher wants to generate intermediate-level math exam questions, they send a prompt request to the server saying, "Please create intermediate-level math exam questions." The server uses OpenAI GPT-3 to generate the questions and stores the results in a MySQL database. The questions are sent back to the teacher's device, where the teacher can review and correct them before distributing them to the students. Students then submit their answers to the server through an interface, and the server uses TensorFlow to grade them and provide instant feedback.

[0129] The present invention significantly reduces the workload of teachers, provides students with prompt and appropriate feedback, and improves learning effectiveness.

[0130] The flow of the identification process in the first embodiment will be described with reference to FIG.

[0131] Step 1:

[0132] A user (teacher) logs into the system using a dedicated application (e.g., a UI built with React). The teacher selects the subject (e.g., mathematics) and difficulty level (e.g., intermediate) from drop-down menus and presses the generate button. This action sends a generation request to the server.

[0133] Input: Selection information as subject and difficulty level.

[0134] Output: The generated request sent to the server.

[0135] Step 2:

[0136] The server receives the teacher's request and analyzes it. Based on the analyzed request information, the server sends a prompt message to the generative AI model (e.g., OpenAI GPT-3) asking it to generate questions: "Please create intermediate-level math exam questions."

[0137] Input: Subject and difficulty level as generation request.

[0138] Output: The prompt sent to the generative AI model.

[0139] Step 3:

[0140] The generative AI model generates questions appropriate for the specified subject and level of difficulty based on the prompt text, and the generated question set is sent back to the server in JSON format.

[0141] Input: The prompt statement.

[0142] Output: The generated problem set.

[0143] Step 4:

[0144] The server stores the received problem set in JSON format in a MySQL database. The stored data includes the problem statement, correct answer, and explanation. The server then sends the problem set to the teacher's device.

[0145] Input: The generated problem set.

[0146] Output: The problem set sent to the teacher's device.

[0147] Step 5:

[0148] The user (teacher) checks the questions generated on the device and, if necessary, edits the questions and explanations using a rich text editor (e.g., Quill.js). Once edits are complete, the teacher presses the confirm button to send the revised question set to the server.

[0149] Input: Problem set and correction information.

[0150] Output: The revised problem set that is sent to the server.

[0151] Step 6:

[0152] The server receives the revised questions, stores them in the MySQL database again, and then distributes the questions to students based on their IDs and class information.

[0153] Input: A revised problem set and student information.

[0154] Output: Questions distributed to student devices.

[0155] Step 7:

[0156] Users (students) log in to their own devices and access the distributed questions. Students enter their answers to the questions using an interface built with Angular.

[0157] Input: The distributed question.

[0158] Output: The answer entered by the student.

[0159] Step 8:

[0160] The student's device sends the entered answers in JSON format to the server, which receives them and stores them in a MySQL database.

[0161] Input: Student answers.

[0162] Output: The answer sent to the server and stored in the database.

[0163] Step 9:

[0164] The server automatically scores the answers using an AI model (e.g., TensorFlow) based on the saved answers, comparing the correct answers with the student's answers, generating a score and recording it in a database.

[0165] Input: Your saved answer.

[0166] Output: The resulting score.

[0167] Step 10:

[0168] The server generates feedback based on the scoring results, and also creates explanations and correction questions for incorrect answers, which are sent to the student's device.

[0169] Input: Scoring results.

[0170] Output: Feedback, explanations, and remedial questions.

[0171] Step 11:

[0172] The student's device displays the feedback, explanations, and revision questions received from the server to the user (student). The student can refer to this to check their own learning progress and review the material as appropriate.

[0173] Input: Feedback, explanations, and remedial questions.

[0174] Output: Feedback information displayed on student devices.

[0175] (Application example 1)

[0176] 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."

[0177] Traditionally, it takes a lot of time and effort for teachers to create homework and exam questions, distribute them to students, and then grade and provide feedback. Furthermore, stores selling education-related products require a lot of time and effort to provide detailed explanations and demonstrations of their products and services, and it is difficult to quickly provide services such as creating homework questions and providing instant grading. This places a heavy burden on teachers and store staff, making it difficult to provide fast and effective feedback to students and customers.

[0178] 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.

[0179] In this invention, the server includes a generation unit that generates homework and test questions based on the subject and level of difficulty selected by the teacher, a distribution unit that distributes the generated homework and test questions to the students' computers, and an input unit that allows the students to input answers using their computers. This enables the processes of generating, distributing, grading, and providing feedback on homework and test questions to be carried out automatically and efficiently. Furthermore, by using store terminals in the store to explain educational products and services and to generate and demonstrate homework questions, the burden on store staff can be reduced, enabling the provision of fast and effective services to customers.

[0180] The "generation means" refers to a device or software that has the function of generating homework and test questions based on the subject and level of difficulty selected by the teacher.

[0181] The "distribution means" refers to a device or software that has the function of transmitting and distributing the generated homework and test questions to the students' computers.

[0182] "Input means" refers to the interface or software that allows students to input answers using a computer.

[0183] The "scoring means" refers to a device or software that has the function of automatically scoring the answers entered.

[0184] The "result notification means" is a device or software that has the function of instantly returning the grading results to the student's computer.

[0185] The "explanation generating means" is a device or software that has the function of generating explanations and correction questions for incorrect parts as needed and displaying them on the student's computer.

[0186] "Store terminal" refers to a device used in a store to explain educational products and services, generate homework questions, and provide demonstrations.

[0187] This invention is a system that allows teachers to efficiently generate, distribute, grade, and provide feedback on homework and exam questions, and has been improved to effectively introduce, explain, and demonstrate educational products and services in physical stores. The detailed configuration and operation of this system are described below.

[0188] Overall system configuration

[0189] The system mainly consists of the following components:

[0190] 1. Server

[0191] 2. Teacher's device

[0192] 3. Student Devices

[0193] 4. In-store terminals

[0194] Teacher's device

[0195] 1. A teacher logs in to the system using their terminal and sends a request to generate homework or exam questions. Specifically, the teacher selects the subject (e.g., mathematics) and difficulty level (e.g., intermediate level) and sends the request to the system.

[0196] server

[0197] 1. The server receives the teacher's request and passes the request information to the generative AI model, which then generates appropriate homework and exam questions based on the specified subject and difficulty level.

[0198] 2. The server saves the generated questions in a database, including the question text, correct answers, explanations, etc. The server then sends the generated questions back to the teacher's device so that the teacher can check them.

[0199] Teacher's device

[0200] 1. The teacher reviews the generated questions and makes corrections or additional comments as necessary to ensure the accuracy and appropriateness of the questions.

[0201] server

[0202] 1. After the teacher has finalized the questions, the server requests that the questions be distributed to the students' devices. The questions are distributed based on the student ID and class information.

[0203] Student devices

[0204] 1. Students log in to their devices and access the distributed questions. An interface for answering the questions is displayed, and students enter their answers.

[0205] 2. The student's device sends the entered answers to the server, which receives and stores the answers.

[0206] server

[0207] 1. The server automatically scores the questions using an AI model based on the saved answers. It compares the correct answers with the student's answers and generates a score. This score is recorded for each student and stored in a database.

[0208] 2. The server sends the scoring results back to the student's device and also generates detailed explanations and correction questions for any mistakes.

[0209] Student devices

[0210] 1. The student's device will display the graded results, explanations, and supplementary questions to the student, allowing them to quickly and effectively check their learning progress and review any necessary sections.

[0211] Physical store terminals

[0212] 1. The in-store terminals are used to explain educational products and services, generate homework questions, and demonstrate them. Sample homework questions can be generated and checked on the spot before customers purchase the requested products in the store.

[0213] 2. Promote educational software sales by instantly demonstrating curriculum on in-store tablets.

[0214] 3. A service can be developed for educational events and workshops that provides participants with generated homework and grades it on the spot.

[0215] Usage example

[0216] For example, if a teacher wants to generate intermediate-level mathematics exam questions, the teacher sends a request to the server from their device, selecting the subject "Mathematics" and the difficulty level "Intermediate." The server then invokes the generative AI model, generates an appropriate set of questions, and sends them back to the teacher's device. The teacher reviews the generated questions, corrects them if necessary, and then distributes them to students. Students then answer the questions using their digital devices and send the answers to the server. The server automatically grades the answers, provides instant feedback, and provides explanations and remedial questions as needed. Furthermore, customers can try out the features of educational products and services when purchasing them in physical stores.

[0217] Prompt Sentence Examples

[0218] "Generate intermediate level math homework problems."

[0219] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[0220] Step 1:

[0221] The teacher terminal displays an interface for the user (teacher) to select the subject and difficulty level. The teacher terminal receives the subject and difficulty level information entered by the user and sends a request to the server.

[0222] Input: Subject (e.g., Math), Difficulty (e.g., Intermediate)

[0223] Data processing: Convert form data into JSON format

[0224] Output: Request to server

[0225] Step 2:

[0226] The server receives requests sent from the teacher device, analyzes the received data, and provides the necessary information for the generative AI model.

[0227] Input: Subject and difficulty request (JSON format)

[0228] Data processing: Analyzes request data and generates prompts

[0229] Output: A request to the generative AI model

[0230] Step 3:

[0231] The generative AI model generates homework and exam questions based on requests received from the server.

[0232] Input: Parsed prompt ("Generate intermediate level math homework problems.")

[0233] Data calculation: Generative AI model generates question, answer, and explanation

[0234] Output: Generated homework questions (question statement, answer, explanation, etc.)

[0235] Step 4:

[0236] The server stores the generated questions in a database and returns the stored questions to the teacher's terminal.

[0237] Input: Generated homework questions

[0238] Data processing: Data storage in the database and data generation for sending to the teacher's terminal

[0239] Output: Database update, response to teacher terminal

[0240] Step 5:

[0241] The teacher's terminal displays the received homework questions to the user, who then checks the questions and makes corrections or additional comments as necessary.

[0242] Input: Homework question sent from the server

[0243] Data processing: Converting data into a format suitable for display on the screen

[0244] Output: Teacher confirmation and correction data

[0245] Step 6:

[0246] The teacher's terminal sends the confirmed homework questions to the server again.

[0247] Input: Confirmed homework question

[0248] Data processing: Convert the complete problem set, including teacher correction data, into JSON format

[0249] Output: Send to server

[0250] Step 7:

[0251] The server makes a request to distribute the determined homework problems to the student's terminal.

[0252] Input: Confirmed homework question

[0253] Data processing: Adding student ID and class information to be distributed

[0254] Output: Distribution request to student devices

[0255] Step 8:

[0256] The student terminal receives the distributed homework questions and displays an interface for the user (student) to answer the questions.

[0257] Input: Homework question sent from the server

[0258] Data processing: generating an interface for answers

[0259] Output: Student answer data

[0260] Step 9:

[0261] The server receives the answer data sent from the student terminal and automatically grades it.

[0262] Input: Student answer data

[0263] Data calculation: Automatic scoring by comparing with correct data

[0264] Output: Scoring results

[0265] Step 10:

[0266] The server sends the results of the marks to the student's terminal, and also generates and displays explanations of the incorrect parts and correction questions.

[0267] Input: Marking results and answer data

[0268] Data calculation: Error analysis and repair problem generation

[0269] Output: Detailed feedback to student devices

[0270] Step 11:

[0271] The terminals in the physical stores provide an interface for explaining educational products and services, generating homework questions, and running demonstrations.

[0272] Input: Store staff or customer request

[0273] Data Computing: Generating demo homework problems using generative techniques

[0274] Output: Instant feedback and demo execution for the customer

[0275] 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.

[0276] This invention is a system that allows teachers to efficiently generate, distribute, grade, and provide feedback on homework and exam questions, and it also maximizes learning effectiveness by combining it with an emotion engine that recognizes the user's emotions and provides appropriate explanations and revision questions based on those emotions. Specific embodiments of this system are described below.

[0277] Overall system configuration

[0278] The system mainly consists of the following components:

[0279] 1. Server

[0280] 2. Teacher's device

[0281] 3. Student Devices

[0282] 4. Emotion Engine

[0283] Teacher's device

[0284] 1. A user (teacher) logs in to the system using the teacher's terminal and sends a request to generate homework or exam questions. Specifically, the user selects a subject (e.g., mathematics) and difficulty level (e.g., intermediate level) and clicks the "Generate" button.

[0285] server

[0286] 1. The server receives the teacher's request and passes the request information to the generative AI model. The server then sends a "Mathematics" "Intermediate" problem generation request to the AI ​​model.

[0287] 2. The server stores the generated questions in a database, which includes the question text, correct answers, explanations, etc. The server then sends the generated questions back to the teacher's device so that the teacher can check them.

[0288] Teacher's device

[0289] 1. The user (teacher) checks the generated questions and makes corrections or additional comments as necessary, thereby maintaining the accuracy and appropriateness of the questions.

[0290] server

[0291] 1. After the teacher has finalized the questions, the server sends a request to distribute the questions to the students' devices. The server retrieves the student's ID and class information from the database and distributes the questions.

[0292] Student devices

[0293] 1. The user (student) logs in to their device and accesses the distributed questions. An interface for answering the questions is displayed, and the user enters their answers.

[0294] 2. The student's device sends the entered answer to the server, which receives the student's answer and stores it in a database.

[0295] server

[0296] 1. The server automatically scores the students using an AI model based on their saved answers. The server compares the correct answers with the students' answers and generates a score. This score is recorded for each student and stored in a database.

[0297] 2. The server returns the results of the marks to the student's terminal and also sends a request to the explanation generation means to generate detailed explanations and correction questions for the incorrect parts.

[0298] 3. The explanation generation means generates explanations and correction questions as needed and sends them back to the server.

[0299] Emotion Engine

[0300] 1. The emotion engine recognizes the user's emotions in real time while the student is entering their answers. For example, it analyzes facial expressions and tone of voice via a camera or microphone to determine the user's emotional state.

[0301] 2. The emotion engine sends the detected emotion information to the server, and adaptively generates the next explanation or remedial question based on that information. For example, if the user is "confused," it can provide a more detailed explanation, and if the user is recognized as "understanding," it can proceed to the next question.

[0302] 3. The emotion engine also recognizes teachers' emotions and provides alerts and guidance to help teachers manage stress and reduce their workload.

[0303] Specific use cases

[0304] For example, if a teacher wants to generate intermediate-level mathematics exam questions, the user (teacher) sends a request from their own device to the server, selecting the subject "Mathematics" and difficulty level "Intermediate." The server then invokes the generative AI model, generates an appropriate set of questions, and sends them back to the teacher's device. After the teacher checks the generated questions, they distribute them to students. The user (student) answers the questions using a digital device and sends the answers to the server. The server automatically grades the answers and provides instant feedback, while the emotion engine provides detailed explanations and remedial questions based on the student's emotional information.

[0305] This system is expected to significantly reduce the workload of teachers and improve students' learning outcomes. In addition, by recognizing users' emotions, it will enable more personalized learning support, improving the efficiency of the entire learning process.

[0306] The processing flow will be explained below.

[0307] Step 1:

[0308] A user (teacher) logs in to the system using the teacher's terminal and sends a request to generate homework or exam questions. Specifically, the user selects a subject (e.g., mathematics) and a level of difficulty (e.g., intermediate level) and clicks the "Generate" button.

[0309] Step 2:

[0310] The teacher's terminal sends a request to the server including the subject and difficulty level information input by the user.

[0311] Step 3:

[0312] The server receives the request from the teacher's device and passes the request information to the generation AI model. The server then sends a problem generation request for "Subject: Mathematics" and "Difficulty: Intermediate" to the AI ​​model.

[0313] Step 4:

[0314] The generative AI model generates appropriate homework and exam questions based on the subject and difficulty level specified, including the question statement, correct answers, and explanations.

[0315] Step 5:

[0316] The server stores the generated questions in a database, which includes the question text, correct answers, explanations, etc.

[0317] Step 6:

[0318] The server sends the generated questions back to the teacher's terminal, where the teacher can check the questions.

[0319] Step 7:

[0320] The user (teacher) checks the generated questions and makes corrections or additional comments as necessary, thereby maintaining the accuracy and appropriateness of the questions.

[0321] Step 8:

[0322] After the teacher has finalized the questions, the server sends a request to distribute the questions to the students' devices. The server retrieves the student's ID and class information from the database and distributes the questions.

[0323] Step 9:

[0324] The user (student) logs in to the student's terminal and accesses the distributed questions. An interface for answering the questions is displayed, and the user inputs their answers.

[0325] Step 10:

[0326] The student's device sends the answers entered by the user (student) to the server, which receives the answers and stores them in a database.

[0327] Step 11:

[0328] The server automatically grades the questions using an AI model based on the stored answers. The server compares the correct answers with the student's answers and generates a score.

[0329] Step 12:

[0330] The server returns the results of the marks to the student's terminal and also sends a request to the explanation generating means to generate detailed explanations and correction questions for the incorrect parts.

[0331] Step 13:

[0332] The explanation generating means generates explanations and correction questions as needed and sends them back to the server.

[0333] Step 14:

[0334] The user (student) can check the grades, explanations, and supplementary questions on their own device, allowing them to check their own understanding and review any necessary parts.

[0335] Step 15:

[0336] The emotion engine recognizes the user's emotions in real time while the student is typing their answers, for example by analyzing facial expressions and tone of voice via the camera and microphone to determine the user's emotional state.

[0337] Step 16:

[0338] The emotion engine sends the detected emotion information to the server, and adaptively generates the next explanation or remedial question based on that information. For example, if the user is "confused," the engine can provide a more detailed explanation, and if the server recognizes that the user "understands," the engine can proceed to the next question.

[0339] Step 17:

[0340] The emotion engine also recognizes teachers' emotions and provides alerts and guidance to help them manage stress and reduce their workload.

[0341] In this way, the system provides an optimal learning environment for both teachers and students, maximizing educational effectiveness.

[0342] Example 2

[0343] 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."

[0344] In conventional educational support systems, teachers often manually create, distribute, and grade homework and exam questions, placing a heavy burden on teachers. Furthermore, systems that provide appropriate feedback based on each student's learning progress and level of understanding are still insufficient. Furthermore, there are no systems that can recognize the emotions of students and teachers in real time and respond individually based on that, making it difficult to provide learning support that takes emotions into account.

[0345] 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.

[0346] In this invention, the server includes a generation unit that generates homework and test questions based on the subject and difficulty level selected by the teacher, a distribution unit that distributes the generated homework and test questions to students' devices, and an input unit that allows students to input answers using their devices. This reduces the workload of teachers and improves students' learning effectiveness. Furthermore, by incorporating a scoring unit that automatically scores the input answers and an emotion recognition unit that recognizes students' emotions in real time and adaptively generates explanations and supplementary questions based on them, appropriate feedback can be provided in response to individual learning needs, enabling efficient educational support.

[0347] "Generation means" refers to a function that automatically generates homework and exam questions based on the subject and difficulty level selected by the teacher.

[0348] "Distribution means" refers to the function of distributing generated homework and exam questions to student devices.

[0349] "Input means" refers to the interface through which students use their devices to input their answers.

[0350] "Scoring means" refers to a function that automatically scores the answers entered.

[0351] "Result notification means" refers to the function of instantly returning grading results to students' devices.

[0352] "Explanation generation means" refers to the function that generates explanations and correction questions for incorrect parts as needed and displays them on the student's device.

[0353] "Emotion recognition means" refers to the function of recognizing students' emotions in real time and adaptively generating explanations and supplementary questions based on that.

[0354] "Storage means" refers to the function of storing generated homework and test questions, students' answers, and grading results in a database.

[0355] This invention is a system that allows teachers to efficiently generate, distribute, grade, and provide feedback on homework and exam questions, and it also maximizes learning effectiveness by combining it with an emotion engine that recognizes students' emotions and provides appropriate explanations and remedial questions based on those emotions.

[0356] Overall system configuration

[0357] The system mainly consists of the following components:

[0358] 1. Server

[0359] 2. Teacher's device

[0360] 3. Student Devices

[0361] 4. Emotion Engine

[0362] Teacher's device

[0363] A user (teacher) logs in to the system using the teacher's terminal and sends a request to generate homework or exam questions. Specifically, the user selects a subject (e.g., mathematics) and a level of difficulty (e.g., intermediate level) and clicks the "Generate" button.

[0364] server

[0365] The server receives the teacher's request and passes the request information to the generative AI model. The server then sends a request to the AI ​​model to generate "intermediate level" math questions. The generative AI model used uses a general-purpose generative AI framework. Specifically, it includes large-scale language models such as GPT-4. An example of a prompt sentence is "Please generate intermediate level math test questions."

[0366] The server stores the generated questions in a database, which includes the question text, correct answers, explanations, etc. The server then sends the generated questions back to the teacher's device so that the teacher can check them.

[0367] Teacher's device

[0368] The user (teacher) checks the generated questions and makes corrections or additional comments as necessary, thereby maintaining the accuracy and appropriateness of the questions.

[0369] server

[0370] After the teacher has finalized the questions, the server sends a request to distribute the questions to the students' devices. The server retrieves the student's ID and class information from the database and distributes the questions.

[0371] Student devices

[0372] The user (student) logs in to the student's terminal and accesses the distributed questions. An interface for answering the questions is displayed, and the user inputs their answers.

[0373] The student's device sends the entered answers to the server, which receives the answers and stores them in a database.

[0374] server

[0375] The server automatically grades the answers using an AI model based on the saved answers. The server compares the correct answers with the student's answers and generates a score. This score is recorded for each student and stored in a database.

[0376] The server returns the scoring results to the student's terminal and also sends a request to the explanation generation means to generate detailed explanations and correction questions for the incorrect parts. The explanation generation means generates explanations and correction questions as needed and returns them to the server. An example of a specific prompt sentence is "Please explain in detail the differences between the student's answer below and the correct answer: [differences between the student's answer and the correct answer]."

[0377] Emotion Engine

[0378] The emotion engine recognizes students' emotions in real time while they are typing their answers. For example, it analyzes facial expressions and tone of voice via a camera or microphone to determine the user's emotional state. The emotion engine performs its analysis using an AI model using Python's OpenCV and TensorFlow.

[0379] The emotion engine sends the detected emotion information to the server, and adaptively generates the next explanation or remedial question based on that information. For example, if the user is "confused," the engine can provide a more detailed explanation, and if the server recognizes that the user "understands," the engine can proceed to the next question.

[0380] The emotion engine also recognizes teachers' emotions and provides alerts and guidance to help them manage stress and reduce their workload.

[0381] This system is expected to significantly reduce the workload of teachers and improve student learning outcomes. In addition, by recognizing the emotions of students and teachers, more personalized learning support will be possible, improving the efficiency of the entire learning process.

[0382] The flow of the identification process in the second embodiment will be described with reference to FIG.

[0383] Step 1:

[0384] The user (teacher) logs in to the system using the teacher's terminal. They enter their username and password as input and send this information to the server. The server compares the entered information with the database, and if authentication is successful, the teacher's home screen is displayed.

[0385] Step 2:

[0386] The user (teacher) requests the generation of homework or exam questions on the home screen. Specifically, the user selects the subject (e.g., mathematics) and difficulty level (e.g., intermediate level) and clicks the "Generate" button. This selection information is sent as input to the server.

[0387] Step 3:

[0388] The server receives a generation request from the teacher. As input, it obtains the requested information on subject and difficulty level and passes it to the generative AI model. It then sends a "Mathematics" "Intermediate" problem generation prompt to the generative AI model. An example of this prompt is "Please generate intermediate level math test questions."

[0389] Step 4:

[0390] The generative AI model receives prompts from the server and generates questions. It receives the prompt as input, processes data, and performs data calculations to generate a problem set that includes the question, correct answer, explanation, etc. The generated problem set is output to the server.

[0391] Step 5:

[0392] The server receives the problem set from the generative AI model and stores it in a database. The problem set is received as input and stored in a table containing the problem ID, problem statement, correct answer, and explanation.

[0393] Step 6:

[0394] The server returns the generated problem set to the teacher's terminal. The server takes the saved problem set as input and sends it to the teacher's terminal. The generated problem is displayed on the teacher's terminal.

[0395] Step 7:

[0396] The user (teacher) checks the generated questions, makes corrections or adds comments as necessary, edits the questions displayed as input, and sends the corrections from the terminal to the server. The server then saves the corrected question set back into the database.

[0397] Step 8:

[0398] The server requests the distribution of questions determined by the teacher to the student's device. It obtains the student's ID and class information from the database as input and distributes the questions. It then sends this distribution information to the student's device.

[0399] Step 9:

[0400] The user (student) logs in to their device and accesses the distributed questions. The login information is sent from the device to the server as input, and if authentication is successful, the question display screen is output.

[0401] Step 10:

[0402] The user (student) inputs the answer to the displayed question. The answer information is entered into the terminal as input, and the answer content is sent to the server. The terminal also sends this answer information to the emotion engine in real time.

[0403] Step 11:

[0404] The server receives the student's answers and stores them in a database. The server takes the answer information as input and stores it in a database.

[0405] Step 12:

[0406] The server automatically scores the students' answers using a generative AI model based on the saved answers. It compares the correct answer data with the students' answers as input, performs data calculations, and generates a score. This score is then output to a database.

[0407] Step 13:

[0408] The server returns the marking results to the student's device and sends a request to the explanation generation means to generate detailed explanations and correction questions for the incorrect parts.The server takes the marking results as input and sends an explanation generation prompt to the generative AI model.

[0409] Step 14:

[0410] The explanation generation means uses a prompt sentence to make the generative AI model generate detailed explanations and remedial questions. It sends the prompt "Please explain in detail the difference between the student's answer below and the correct answer" as input, and outputs the generated explanation to the server.

[0411] Step 15:

[0412] The server returns the generated explanations and supplementary questions to the student's device. The server receives explanation data as input and sends it to the student's device. The specific explanations and supplementary questions are displayed on the student's device.

[0413] Step 16:

[0414] The emotion engine recognizes students' emotions in real time while they are typing their answers. It analyzes facial expressions and tone of voice collected via a camera and microphone as input, and outputs the analysis results to a server.

[0415] Step 17:

[0416] The emotion engine sends the detected emotion information to the server and adaptively generates explanations and remedial questions based on that information. For example, if a student is "confused," it generates a prompt to provide a detailed explanation. It takes the emotion information as input and sends the prompt to the generative AI model to generate an adaptive explanation. As a result, a detailed explanation or instructions to proceed to the next question are output to the student's device.

[0417] (Application example 2)

[0418] 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."

[0419] In today's world, the burden on teachers in the educational field is increasing. Furthermore, in brick-and-mortar stores, the demand for customer service that meets customer needs is increasing the workload on store clerks. It is becoming increasingly difficult for teachers to efficiently generate, distribute, grade, and provide feedback on homework and exam questions, and for store clerks to respond quickly and appropriately to customer emotions. Furthermore, conventional systems have difficulty accurately reading and responding to the emotions of users (teachers and store clerks), resulting in a lack of systems that maximize learning outcomes and customer service efficiency. There is a need to solve these issues, reduce the workload on teachers and store clerks, and provide personalized support to users (students and customers).

[0420] 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: a generation unit that generates homework and test questions based on the subject and difficulty level selected by the teacher; a distribution unit that distributes the generated homework and test questions to students' digital devices; an input unit that allows students to input answers using their digital devices; a scoring unit that automatically grades the entered answers; a result notification unit that instantly returns the graded results to the students' devices; an explanation generation unit that generates explanations and correction questions for incorrect sections as needed and displays them on the students' devices; an emotion recognition unit that recognizes emotions based on customer questions, images, and voices and generates responses based on the emotions; a response generation unit that generates and displays appropriate product explanations and suggestions based on the customer's emotions; and a notification unit that displays the generated questions and responses on the digital devices of store clerks. This reduces the burden on teachers in educational settings and improves students' learning outcomes. Furthermore, in physical stores, appropriate responses based on customer emotions can be quickly provided, thereby improving customer satisfaction.

[0421] "Generation means" refers to a device or program for generating homework and test questions based on the subject and level of difficulty selected by the teacher.

[0422] "Distribution means" refers to a device or program for distributing generated homework and exam questions to students' digital devices.

[0423] "Input means" refers to the device or interface that allows students to input answers using a digital device.

[0424] "Scoring means" refers to a device or program for automatically scoring the answers entered.

[0425] "Result notification means" refers to a device or program that instantly returns the grading results to the student's device.

[0426] "Explanation generation means" refers to a device or program that generates explanations and correction questions for incorrect parts as needed and displays them on the student's device.

[0427] "Emotion recognition means" refers to devices or programs that recognize emotions based on customer questions, images, and voices.

[0428] The "response generation means" refers to a device or program for generating and displaying appropriate product descriptions and suggestions based on the customer's emotions.

[0429] "Notification means" refers to a device or program for displaying the generated questions and responses on the store clerk's digital device.

[0430] To implement this invention, a server, a teacher's terminal, a student's terminal, an emotion engine, and a database are required. The following describes specific embodiments of the invention.

[0431] Overall system configuration

[0432] server

[0433] The server includes the following means:

[0434] Generator: Generate homework and exam questions based on teacher-selected subjects and difficulty levels. This process is driven by a generative AI model.

[0435] Distribution: Distributing generated homework and exam questions to students' digital devices.

[0436] Scoring: Automatically score student-entered answers.

[0437] Results notification: Grading results are instantly sent back to student devices.

[0438] Explanation generation means: Explanations and correction questions for incorrect parts are generated and displayed on the student's device.

[0439] Emotion recognition: Recognizes emotions based on customer questions, images, and voice. For this, we use an emotion engine.

[0440] Response generation means: Generate and display appropriate product descriptions and suggestions based on customer sentiment.

[0441] Teacher's device

[0442] Teacher devices have the following features:

[0443] Ability for teachers to submit requests to generate homework and exam questions.

[0444] Ability to review generated issues and make corrections or additions.

[0445] Student devices

[0446] Student devices have the following features:

[0447] Ability to access distributed questions and enter answers.

[0448] A function to receive scoring results and explanations.

[0449] Emotion Engine

[0450] The emotion engine has the following features:

[0451] Ability to recognize user emotions in real time.

[0452] A function that generates appropriate explanations and supplementary questions based on emotional information.

[0453] Specific use cases

[0454] If a teacher wants to generate intermediate-level math exam questions, they send a request to the server from their own device, selecting the subject "Mathematics" and the difficulty level "Intermediate." The server then invokes the generative AI model, generates an appropriate set of questions, and sends them back to the teacher's device. After the teacher checks the generated questions, they distribute them to students. Students answer the questions using their digital devices and send their answers to the server. The server automatically grades the answers and provides instant feedback, while the emotion engine provides detailed explanations and remedial questions based on the students' emotional information.

[0455] A similar system can also be used in physical stores. In response to customer questions, store clerks can provide appropriate responses while recognizing the customer's emotions. For example, if a customer asks, "Tell me about this product," the emotion engine reads the customer's emotions from their image and voice. Based on this, the generative AI model generates the optimal response, which is displayed on the clerk's device.

[0456] Prompt Sentence Examples

[0457] "A customer asks, 'Tell me about this product.' The customer's emotion is 'Confused.' Generate an appropriate response."

[0458] In this way, this invention is a system that can generate appropriate questions and provide individualized responses based on emotions in educational settings and brick-and-mortar stores.

[0459] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[0460] Step 1:

[0461] A request is sent from the teacher's terminal to the server to generate homework or exam questions based on the subject and difficulty level selected by the teacher. Here, the input is the subject and difficulty level selected by the teacher, and the server side calls the generative AI model based on this. In this process, the server passes the selection information to the generative AI model and uses it as a prompt for question generation.

[0462] Step 2:

[0463] The server uses a generative AI model to generate homework and exam questions. Based on the input data (selected subjects and difficulty level), the generative AI model generates a problem set. Here, the generative AI model generates questions using prompts such as "math" or "intermediate" and sends the results back to the server. The server receives the generated results: the problem statement, correct answers, and explanations.

[0464] Step 3:

[0465] The generated homework and exam questions are sent back from the server to the teacher's terminal, where the teacher can review them and add corrections or comments. The input is the generated question set, and the output is the question set edited by the teacher.

[0466] Step 4:

[0467] Once the teacher has finalized the problem set, the information is sent to the server again. The server saves the finalized problem set in the database and prepares it for distribution to the students' devices. The input is the finalized problem set, and the output is a notification that it is ready to be saved in the database and distributed.

[0468] Step 5:

[0469] The student's device accesses the distributed questions and inputs the answers. At this stage, an interface is displayed for the student to answer the questions. The input is the student's answer, and the output is the answer data.

[0470] Step 6:

[0471] The answers are sent from the student's terminal to the server. The server stores the received answers in a database and then automatically grades them using a grading tool. The input is the student's answer data, and the output is the graded results.

[0472] Step 7:

[0473] The server stores the grading results in a database and sends the results back to the student's device using a result notification means. The input is the grading results and the output is a notification to the student's device.

[0474] Step 8:

[0475] Next, the explanation generation means generates explanations and correction questions for the incorrect parts. The server sends the generated explanations and correction questions to the student's terminal. The input is the grade data and incorrect answers, and the output is the generated explanations and correction questions.

[0476] Step 9:

[0477] In parallel, an emotion recognition means is used to recognize emotions based on the customer's question, image, and voice, where the input is the customer's question, facial expression image, and voice data, and the output is the recognized emotional state.

[0478] Step 10:

[0479] Based on the emotion recognition results, the response generation means generates appropriate product descriptions and suggestions. The server then sends the generated responses to the salesperson's terminal. The input is the customer's question and emotional state, and the output is the generated responses.

[0480] Step 11:

[0481] The generated questions and responses are displayed on the salesperson's terminal, and the salesperson responds to the customer based on them. Here, the input is the generated response sentence, and the output is the information that the salesperson provides to the customer.

[0482] In this way, the system generates appropriate questions and provides personalized, emotion-based responses in educational settings and brick-and-mortar stores.

[0483] 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.

[0484] 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.

[0485] 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.

[0486] [Second embodiment]

[0487] FIG. 3 shows an example of the configuration of a data processing system 210 according to the second embodiment.

[0488] 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.

[0489] 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).

[0490] 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.

[0491] 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.

[0492] 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).

[0493] 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.

[0494] 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.

[0495] 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.

[0496] 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.

[0497] 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.

[0498] 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."

[0499] The present invention is a system that enables teachers to efficiently generate, distribute, grade, and provide feedback on homework and test questions, and has the following specific embodiments.

[0500] Overall system configuration

[0501] The system mainly consists of the following components:

[0502] 1. Server

[0503] 2. Teacher's device

[0504] 3. Student Devices

[0505] Teacher's device

[0506] 1. A user (teacher) logs in to the system using the teacher's terminal and sends a request to generate homework or exam questions. Specifically, the user selects a subject (e.g., mathematics) and difficulty level (e.g., intermediate level) and sends a request to the system.

[0507] server

[0508] 1. The server receives the teacher's request and passes the request information to the generative AI model, which then generates appropriate homework and exam questions based on the specified subject and difficulty level.

[0509] 2. The server stores the generated questions in a database, which includes the question text, correct answers, explanations, etc. The server then sends the generated questions back to the teacher's device so that the teacher can check them.

[0510] Teacher's device

[0511] 1. The user (teacher) checks the generated questions and makes corrections or additional comments as necessary, thereby maintaining the accuracy and appropriateness of the questions.

[0512] server

[0513] 1. After the teacher has finalized the questions, the server requests that the questions be distributed to the students' devices. The questions are distributed based on the student ID and class information.

[0514] Student devices

[0515] 1. The user (student) logs in to their device and accesses the distributed questions. An interface for answering the questions is displayed, and the user enters their answers.

[0516] 2. The student's device sends the entered answers to the server, which receives and stores the answers.

[0517] server

[0518] 1. The server automatically scores the questions using an AI model based on the saved answers. It compares the correct answers with the student's answers and generates a score. This score is recorded for each student and stored in a database.

[0519] 2. The server sends the scoring results back to the student's device and also generates detailed explanations and correction questions for any mistakes.

[0520] Student devices

[0521] 1. The student's device will display the graded results, explanations, and supplementary questions to the student, allowing them to quickly and effectively check their learning progress and review any necessary sections.

[0522] Specific use cases

[0523] For example, if a teacher wants to generate intermediate-level mathematics exam questions, the teacher sends a request from their device to the server, selecting the subject "Mathematics" and the difficulty level "Intermediate." The server then invokes the generative AI model, generates an appropriate set of questions, and sends them back to the teacher's device. After the teacher checks the generated questions, they distribute them to students. Students then answer the questions using their digital devices and send their answers to the server. The server automatically grades the answers, providing instant feedback and explanations or remedial questions as needed.

[0524] This system is expected to significantly reduce the workload of teachers and improve students' learning outcomes.

[0525] The processing flow will be explained below.

[0526] Step 1:

[0527] A user (teacher) logs in to the system using the teacher's terminal and sends a request to generate homework or exam questions. Specifically, the user selects a subject (e.g., mathematics) and a level of difficulty (e.g., intermediate level) and clicks the "Generate" button.

[0528] Step 2:

[0529] The teacher's terminal sends a request to the server including the subject and difficulty level information input by the user.

[0530] Step 3:

[0531] The server receives requests from the teacher's device and passes the request information to the generative AI model. The server then sends a "Mathematics" "Intermediate" problem generation request to the AI ​​model.

[0532] Step 4:

[0533] The generative AI model generates appropriate homework and exam questions based on the subject and level of difficulty, including the question statement, correct answers, and explanations.

[0534] Step 5:

[0535] The server stores the generated questions in a database, which includes information such as the question, the correct answer, and an explanation.

[0536] Step 6:

[0537] The server sends the generated questions back to the teacher's terminal, where the teacher can check the questions.

[0538] Step 7:

[0539] The user (teacher) checks the generated questions and makes corrections or additional comments as necessary. Once the teacher reviews and confirms the questions, the questions based on this are sent to the server.

[0540] Step 8:

[0541] After the teacher has finalized the questions, the server sends a request to distribute the questions to the students' devices. The server retrieves the student's ID and class information from the database and distributes the questions.

[0542] Step 9:

[0543] The user (student) logs in to the student's terminal and accesses the distributed questions. An interface for answering the questions is displayed, and the user inputs their answers.

[0544] Step 10:

[0545] The student's device sends the answers entered by the user (student) to the server, which receives the answers and stores them in a database.

[0546] Step 11:

[0547] The server automatically grades the questions using an AI model based on the stored answers. The server compares the correct answers with the student's answers and generates a score.

[0548] Step 12:

[0549] The server returns the graded results to the student's terminal and also sends a request to the explanation generation means to generate detailed explanations and correction questions for the incorrect parts.

[0550] Step 13:

[0551] The explanation generating means generates explanations and correction questions as needed and sends them back to the server.

[0552] Step 14:

[0553] The server sends explanations and supplementary questions to the students' devices and records them in a database as logs.

[0554] Step 15:

[0555] The user (student) can check the grades, explanations, and supplementary questions on their own device, allowing them to check their own understanding and review any necessary parts.

[0556] Example 1

[0557] 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."

[0558] In conventional educational systems, teachers manually create homework and exam questions, distribute them to students, and then grade and provide feedback, requiring a great deal of time and effort. This cumbersome process reduces teachers' work efficiency and hinders their ability to provide prompt feedback to students. Furthermore, the balance between question content and difficulty level is inconsistent, making it difficult to provide personalized support based on each student's learning progress. To address these issues, the present invention aims to provide a system that automates teachers' work and provides appropriate and prompt feedback to students.

[0559] 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.

[0560] In this invention, the server includes a generating means for generating homework and test questions based on the subject and difficulty level selected by the teacher, a distributing means for distributing the generated homework and test questions to the students' digital devices, an input means for the students to input answers using their digital devices, a sending and saving means for sending the input answers to the server and saving them, a scoring means for automatically scoring the saved answers, a result notifying means for returning the scoring results to the students' digital devices, and an explanation generating means for generating explanations and correction questions for incorrect parts as needed and displaying them on the students' digital devices. This reduces the workload on teachers and enables them to provide students with quick and appropriate feedback.

[0561] "Generative means" refers to a function that automatically generates homework and exam questions using an AI model based on the subject and difficulty level selected by the teacher.

[0562] "Distribution means" refers to the function of sending generated homework and exam questions to students' digital devices in an appropriate format.

[0563] "Input means" refers to the interface and functionality that allows students to input answers to homework and exam questions using digital devices.

[0564] The "transmission and storage means" is a function that sends the answers entered by the students to the server and stores them in a database.

[0565] The "scoring method" is a function that automatically scores answers stored on the server using an AI model to generate a score.

[0566] "Result notification means" is a function that quickly returns graded results to students' digital devices.

[0567] The "explanation generation means" is a function that generates explanations and correction questions for incorrect parts as needed and displays them on the student's digital device.

[0568] "Storage means" is a function that stores generated homework and test questions, students' answers, and grading results in a database, allowing the information to be retrieved later.

[0569] The present invention is a system for teachers to efficiently generate, distribute, grade, and provide feedback on homework and exam questions. The system comprises the following components:

[0570] Overall system configuration

[0571] The main components of the system are:

[0572] 1. Server

[0573] 2. Teacher's device

[0574] 3. Student Devices

[0575] Teacher's device

[0576] Users (teachers) log in to the system from their own devices via an internet browser and use a dedicated application (e.g., a UI built with React) to send a request to the server to generate homework or exam questions. The teacher selects the subject (e.g., mathematics) and difficulty level (e.g., intermediate), and presses the generate button, which sends the request to the server. An example of a prompt sentence is "Please create intermediate-level mathematics exam questions."

[0577] server

[0578] The server has a backend system written in Python that receives requests, analyzes them, and sends prompts to an AI model (e.g., OpenAI GPT-3), which then generates an appropriate problem set based on the specified subject and difficulty level.

[0579] The generated problem set is sent back to the server in JSON format, which stores it in a MySQL database. The stored data includes the problem statement, correct answers, and explanations. The generated problem set is then sent back to the teacher's computer.

[0580] Teacher's device

[0581] The user (teacher) checks the generated questions and, if necessary, edits the question text and explanations using a rich text editor (e.g., Quill.js). Once the edits are complete, the user presses the confirm button to send a request to the server to save the changes.

[0582] server

[0583] The server then obtains a list of students based on their IDs and class information to distribute the finalized questions to them. At this time, the questions are again organized in JSON format and sent to the students' devices.

[0584] Student devices

[0585] Users (students) log in to their own devices and access the distributed questions. An interface built with Angular is displayed on the student's device, allowing the user to enter answers to the questions.

[0586] server

[0587] The student's device sends the entered answers in JSON format to the server. The server receives them and stores them in a MySQL database. Then, based on the saved answers, an AI model (e.g., TensorFlow) is used again to automatically grade the answers. The correct answer is compared with the student's answer, a score is generated, and the score is recorded in the database.

[0588] The graded results are quickly returned to the student's digital device, and feedback and correction questions are generated and sent to the student's device for any errors.

[0589] Student devices

[0590] The student's device displays the feedback, explanations, and revision questions received from the server to the user (student). The student can refer to this to check their own learning progress and review the material as appropriate.

[0591] Specific examples

[0592] For example, if a teacher wants to generate intermediate-level math exam questions, they send a prompt request to the server saying, "Please create intermediate-level math exam questions." The server uses OpenAI GPT-3 to generate the questions and stores the results in a MySQL database. The questions are sent back to the teacher's device, where the teacher can review and correct them before distributing them to the students. Students then submit their answers to the server through an interface, and the server uses TensorFlow to grade them and provide instant feedback.

[0593] The present invention significantly reduces the workload of teachers, provides students with prompt and appropriate feedback, and improves learning effectiveness.

[0594] The flow of the identification process in the first embodiment will be described with reference to FIG.

[0595] Step 1:

[0596] A user (teacher) logs into the system using a dedicated application (e.g., a UI built with React). The teacher selects the subject (e.g., mathematics) and difficulty level (e.g., intermediate) from drop-down menus and presses the generate button. This action sends a generation request to the server.

[0597] Input: Selection information as subject and difficulty level.

[0598] Output: The generated request sent to the server.

[0599] Step 2:

[0600] The server receives the teacher's request and analyzes it. Based on the analyzed request information, the server sends a prompt message to the generative AI model (e.g., OpenAI GPT-3) asking it to generate questions: "Please create intermediate-level math exam questions."

[0601] Input: Subject and difficulty level as generation request.

[0602] Output: The prompt sent to the generative AI model.

[0603] Step 3:

[0604] The generative AI model generates questions appropriate for the specified subject and level of difficulty based on the prompt text, and the generated question set is sent back to the server in JSON format.

[0605] Input: The prompt statement.

[0606] Output: The generated problem set.

[0607] Step 4:

[0608] The server stores the received problem set in JSON format in a MySQL database. The stored data includes the problem statement, correct answer, and explanation. The server then sends the problem set to the teacher's device.

[0609] Input: The generated problem set.

[0610] Output: The problem set sent to the teacher's device.

[0611] Step 5:

[0612] The user (teacher) checks the questions generated on the device and, if necessary, edits the questions and explanations using a rich text editor (e.g., Quill.js). Once edits are complete, the teacher presses the confirm button to send the revised question set to the server.

[0613] Input: Problem set and correction information.

[0614] Output: The revised problem set that is sent to the server.

[0615] Step 6:

[0616] The server receives the revised questions, stores them in the MySQL database again, and then distributes the questions to students based on their IDs and class information.

[0617] Input: A revised problem set and student information.

[0618] Output: Questions distributed to student devices.

[0619] Step 7:

[0620] Users (students) log in to their own devices and access the distributed questions. Students enter their answers to the questions using an interface built with Angular.

[0621] Input: The distributed question.

[0622] Output: The answer entered by the student.

[0623] Step 8:

[0624] The student's device sends the entered answers in JSON format to the server, which receives them and stores them in a MySQL database.

[0625] Input: Student answers.

[0626] Output: The answer sent to the server and stored in the database.

[0627] Step 9:

[0628] The server automatically scores the answers using an AI model (e.g., TensorFlow) based on the saved answers, comparing the correct answers with the student's answers, generating a score and recording it in a database.

[0629] Input: Your saved answer.

[0630] Output: The resulting score.

[0631] Step 10:

[0632] The server generates feedback based on the scoring results, and also creates explanations and correction questions for incorrect answers, which are sent to the student's device.

[0633] Input: Scoring results.

[0634] Output: Feedback, explanations, and remedial questions.

[0635] Step 11:

[0636] The student's device displays the feedback, explanations, and revision questions received from the server to the user (student). The student can refer to this to check their own learning progress and review the material as appropriate.

[0637] Input: Feedback, explanations, and remedial questions.

[0638] Output: Feedback information displayed on student devices.

[0639] (Application example 1)

[0640] 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."

[0641] Traditionally, it takes a lot of time and effort for teachers to create homework and exam questions, distribute them to students, and then grade and provide feedback. Furthermore, stores selling education-related products require a lot of time and effort to provide detailed explanations and demonstrations of their products and services, and it is difficult to quickly provide services such as creating homework questions and providing instant grading. This places a heavy burden on teachers and store staff, making it difficult to provide fast and effective feedback to students and customers.

[0642] 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.

[0643] In this invention, the server includes a generation unit that generates homework and test questions based on the subject and level of difficulty selected by the teacher, a distribution unit that distributes the generated homework and test questions to the students' computers, and an input unit that allows the students to input answers using their computers. This enables the processes of generating, distributing, grading, and providing feedback on homework and test questions to be carried out automatically and efficiently. Furthermore, by using store terminals in the store to explain educational products and services and to generate and demonstrate homework questions, the burden on store staff can be reduced, enabling the provision of fast and effective services to customers.

[0644] The "generation means" refers to a device or software that has the function of generating homework and test questions based on the subject and level of difficulty selected by the teacher.

[0645] The "distribution means" refers to a device or software that has the function of transmitting and distributing the generated homework and test questions to the students' computers.

[0646] "Input means" refers to the interface or software that allows students to input answers using a computer.

[0647] The "scoring means" refers to a device or software that has the function of automatically scoring the answers entered.

[0648] The "result notification means" is a device or software that has the function of instantly returning the grading results to the student's computer.

[0649] The "explanation generating means" is a device or software that has the function of generating explanations and correction questions for incorrect parts as needed and displaying them on the student's computer.

[0650] "Store terminal" refers to a device used in a store to explain educational products and services, generate homework questions, and provide demonstrations.

[0651] This invention is a system that allows teachers to efficiently generate, distribute, grade, and provide feedback on homework and exam questions, and has been improved to effectively introduce, explain, and demonstrate educational products and services in physical stores. The detailed configuration and operation of this system are described below.

[0652] Overall system configuration

[0653] The system mainly consists of the following components:

[0654] 1. Server

[0655] 2. Teacher's device

[0656] 3. Student Devices

[0657] 4. In-store terminals

[0658] Teacher's device

[0659] 1. A teacher logs in to the system using their terminal and sends a request to generate homework or exam questions. Specifically, the teacher selects the subject (e.g., mathematics) and difficulty level (e.g., intermediate level) and sends the request to the system.

[0660] server

[0661] 1. The server receives the teacher's request and passes the request information to the generative AI model, which then generates appropriate homework and exam questions based on the specified subject and difficulty level.

[0662] 2. The server saves the generated questions in a database, including the question text, correct answers, explanations, etc. The server then sends the generated questions back to the teacher's device so that the teacher can check them.

[0663] Teacher's device

[0664] 1. The teacher reviews the generated questions and makes corrections or additional comments as necessary to ensure the accuracy and appropriateness of the questions.

[0665] server

[0666] 1. After the teacher has finalized the questions, the server requests that the questions be distributed to the students' devices. The questions are distributed based on the student ID and class information.

[0667] Student devices

[0668] 1. Students log in to their devices and access the distributed questions. An interface for answering the questions is displayed, and students enter their answers.

[0669] 2. The student's device sends the entered answers to the server, which receives and stores the answers.

[0670] server

[0671] 1. The server automatically scores the questions using an AI model based on the saved answers. It compares the correct answers with the student's answers and generates a score. This score is recorded for each student and stored in a database.

[0672] 2. The server sends the scoring results back to the student's device and also generates detailed explanations and correction questions for any mistakes.

[0673] Student devices

[0674] 1. The student's device will display the graded results, explanations, and supplementary questions to the student, allowing them to quickly and effectively check their learning progress and review any necessary sections.

[0675] Physical store terminals

[0676] 1. The in-store terminals are used to explain educational products and services, generate homework questions, and demonstrate them. Sample homework questions can be generated and checked on the spot before customers purchase the requested products in the store.

[0677] 2. Promote educational software sales by instantly demonstrating curriculum on in-store tablets.

[0678] 3. A service can be developed for educational events and workshops that provides participants with generated homework and grades it on the spot.

[0679] Usage example

[0680] For example, if a teacher wants to generate intermediate-level mathematics exam questions, the teacher sends a request to the server from their device, selecting the subject "Mathematics" and the difficulty level "Intermediate." The server then invokes the generative AI model, generates an appropriate set of questions, and sends them back to the teacher's device. The teacher reviews the generated questions, corrects them if necessary, and then distributes them to students. Students then answer the questions using their digital devices and send the answers to the server. The server automatically grades the answers, provides instant feedback, and provides explanations and remedial questions as needed. Furthermore, customers can try out the features of educational products and services when purchasing them in physical stores.

[0681] Prompt Sentence Examples

[0682] "Generate intermediate level math homework problems."

[0683] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[0684] Step 1:

[0685] The teacher terminal displays an interface for the user (teacher) to select the subject and difficulty level. The teacher terminal receives the subject and difficulty level information entered by the user and sends a request to the server.

[0686] Input: Subject (e.g., Math), Difficulty (e.g., Intermediate)

[0687] Data processing: Convert form data into JSON format

[0688] Output: Request to server

[0689] Step 2:

[0690] The server receives requests sent from the teacher device, analyzes the received data, and provides the necessary information for the generative AI model.

[0691] Input: Subject and difficulty request (JSON format)

[0692] Data processing: Analyzes request data and generates prompts

[0693] Output: A request to the generative AI model

[0694] Step 3:

[0695] The generative AI model generates homework and exam questions based on requests received from the server.

[0696] Input: Parsed prompt ("Generate intermediate level math homework problems.")

[0697] Data calculation: Generative AI model generates question, answer, and explanation

[0698] Output: Generated homework questions (question statement, answer, explanation, etc.)

[0699] Step 4:

[0700] The server stores the generated questions in a database and returns the stored questions to the teacher's terminal.

[0701] Input: Generated homework questions

[0702] Data processing: Data storage in the database and data generation for sending to the teacher's terminal

[0703] Output: Database update, response to teacher terminal

[0704] Step 5:

[0705] The teacher's terminal displays the received homework questions to the user, who then checks the questions and makes corrections or additional comments as necessary.

[0706] Input: Homework question sent from the server

[0707] Data processing: Converting data into a format suitable for display on the screen

[0708] Output: Teacher confirmation and correction data

[0709] Step 6:

[0710] The teacher's terminal sends the confirmed homework questions to the server again.

[0711] Input: Confirmed homework question

[0712] Data processing: Convert the complete problem set, including teacher correction data, into JSON format

[0713] Output: Send to server

[0714] Step 7:

[0715] The server makes a request to distribute the determined homework problems to the student's terminal.

[0716] Input: Confirmed homework question

[0717] Data processing: Adding student ID and class information to be distributed

[0718] Output: Distribution request to student devices

[0719] Step 8:

[0720] The student terminal receives the distributed homework questions and displays an interface for the user (student) to answer the questions.

[0721] Input: Homework question sent from the server

[0722] Data processing: generating an interface for answers

[0723] Output: Student answer data

[0724] Step 9:

[0725] The server receives the answer data sent from the student terminal and automatically grades it.

[0726] Input: Student answer data

[0727] Data calculation: Automatic scoring by comparing with correct data

[0728] Output: Scoring results

[0729] Step 10:

[0730] The server sends the results of the marks to the student's terminal, and also generates and displays explanations of the incorrect parts and correction questions.

[0731] Input: Marking results and answer data

[0732] Data calculation: Error analysis and repair problem generation

[0733] Output: Detailed feedback to student devices

[0734] Step 11:

[0735] The terminals in the physical stores provide an interface for explaining educational products and services, generating homework questions, and running demonstrations.

[0736] Input: Store staff or customer request

[0737] Data Computing: Generating demo homework problems using generative techniques

[0738] Output: Instant feedback and demo execution for the customer

[0739] 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.

[0740] This invention is a system that allows teachers to efficiently generate, distribute, grade, and provide feedback on homework and exam questions, and it also maximizes learning effectiveness by combining it with an emotion engine that recognizes the user's emotions and provides appropriate explanations and revision questions based on those emotions. Specific embodiments of this system are described below.

[0741] Overall system configuration

[0742] The system mainly consists of the following components:

[0743] 1. Server

[0744] 2. Teacher's device

[0745] 3. Student Devices

[0746] 4. Emotion Engine

[0747] Teacher's device

[0748] 1. A user (teacher) logs in to the system using the teacher's terminal and sends a request to generate homework or exam questions. Specifically, the user selects a subject (e.g., mathematics) and difficulty level (e.g., intermediate level) and clicks the "Generate" button.

[0749] server

[0750] 1. The server receives the teacher's request and passes the request information to the generative AI model. The server then sends a "Mathematics" "Intermediate" problem generation request to the AI ​​model.

[0751] 2. The server stores the generated questions in a database, which includes the question text, correct answers, explanations, etc. The server then sends the generated questions back to the teacher's device so that the teacher can check them.

[0752] Teacher's device

[0753] 1. The user (teacher) checks the generated questions and makes corrections or additional comments as necessary, thereby maintaining the accuracy and appropriateness of the questions.

[0754] server

[0755] 1. After the teacher has finalized the questions, the server sends a request to distribute the questions to the students' devices. The server retrieves the student's ID and class information from the database and distributes the questions.

[0756] Student devices

[0757] 1. The user (student) logs in to their device and accesses the distributed questions. An interface for answering the questions is displayed, and the user enters their answers.

[0758] 2. The student's device sends the entered answer to the server, which receives the student's answer and stores it in a database.

[0759] server

[0760] 1. The server automatically scores the students using an AI model based on their saved answers. The server compares the correct answers with the students' answers and generates a score. This score is recorded for each student and stored in a database.

[0761] 2. The server returns the results of the marks to the student's terminal and also sends a request to the explanation generation means to generate detailed explanations and correction questions for the incorrect parts.

[0762] 3. The explanation generation means generates explanations and correction questions as needed and sends them back to the server.

[0763] Emotion Engine

[0764] 1. The emotion engine recognizes the user's emotions in real time while the student is entering their answers. For example, it analyzes facial expressions and tone of voice via a camera or microphone to determine the user's emotional state.

[0765] 2. The emotion engine sends the detected emotion information to the server, and adaptively generates the next explanation or remedial question based on that information. For example, if the user is "confused," it can provide a more detailed explanation, and if the user is recognized as "understanding," it can proceed to the next question.

[0766] 3. The emotion engine also recognizes teachers' emotions and provides alerts and guidance to help teachers manage stress and reduce their workload.

[0767] Specific use cases

[0768] For example, if a teacher wants to generate intermediate-level mathematics exam questions, the user (teacher) sends a request from their own device to the server, selecting the subject "Mathematics" and difficulty level "Intermediate." The server then invokes the generative AI model, generates an appropriate set of questions, and sends them back to the teacher's device. After the teacher checks the generated questions, they distribute them to students. The user (student) answers the questions using a digital device and sends the answers to the server. The server automatically grades the answers and provides instant feedback, while the emotion engine provides detailed explanations and remedial questions based on the student's emotional information.

[0769] This system is expected to significantly reduce the workload of teachers and improve students' learning outcomes. In addition, by recognizing users' emotions, it will enable more personalized learning support, improving the efficiency of the entire learning process.

[0770] The processing flow will be explained below.

[0771] Step 1:

[0772] A user (teacher) logs in to the system using the teacher's terminal and sends a request to generate homework or exam questions. Specifically, the user selects a subject (e.g., mathematics) and a level of difficulty (e.g., intermediate level) and clicks the "Generate" button.

[0773] Step 2:

[0774] The teacher's terminal sends a request to the server including the subject and difficulty level information input by the user.

[0775] Step 3:

[0776] The server receives the request from the teacher's device and passes the request information to the generation AI model. The server then sends a problem generation request for "Subject: Mathematics" and "Difficulty: Intermediate" to the AI ​​model.

[0777] Step 4:

[0778] The generative AI model generates appropriate homework and exam questions based on the subject and difficulty level specified, including the question statement, correct answers, and explanations.

[0779] Step 5:

[0780] The server stores the generated questions in a database, which includes the question text, correct answers, explanations, etc.

[0781] Step 6:

[0782] The server sends the generated questions back to the teacher's terminal, where the teacher can check the questions.

[0783] Step 7:

[0784] The user (teacher) checks the generated questions and makes corrections or additional comments as necessary, thereby maintaining the accuracy and appropriateness of the questions.

[0785] Step 8:

[0786] After the teacher has finalized the questions, the server sends a request to distribute the questions to the students' devices. The server retrieves the student's ID and class information from the database and distributes the questions.

[0787] Step 9:

[0788] The user (student) logs in to the student's terminal and accesses the distributed questions. An interface for answering the questions is displayed, and the user inputs their answers.

[0789] Step 10:

[0790] The student's device sends the answers entered by the user (student) to the server, which receives the answers and stores them in a database.

[0791] Step 11:

[0792] The server automatically grades the questions using an AI model based on the stored answers. The server compares the correct answers with the student's answers and generates a score.

[0793] Step 12:

[0794] The server returns the results of the marks to the student's terminal and also sends a request to the explanation generating means to generate detailed explanations and correction questions for the incorrect parts.

[0795] Step 13:

[0796] The explanation generating means generates explanations and correction questions as needed and sends them back to the server.

[0797] Step 14:

[0798] The user (student) can check the grades, explanations, and supplementary questions on their own device, allowing them to check their own understanding and review any necessary parts.

[0799] Step 15:

[0800] The emotion engine recognizes the user's emotions in real time while the student is typing their answers, for example by analyzing facial expressions and tone of voice via the camera and microphone to determine the user's emotional state.

[0801] Step 16:

[0802] The emotion engine sends the detected emotion information to the server, and adaptively generates the next explanation or remedial question based on that information. For example, if the user is "confused," the engine can provide a more detailed explanation, and if the server recognizes that the user "understands," the engine can proceed to the next question.

[0803] Step 17:

[0804] The emotion engine also recognizes teachers' emotions and provides alerts and guidance to help them manage stress and reduce their workload.

[0805] In this way, the system provides an optimal learning environment for both teachers and students, maximizing educational effectiveness.

[0806] Example 2

[0807] 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."

[0808] In conventional educational support systems, teachers often manually create, distribute, and grade homework and exam questions, placing a heavy burden on teachers. Furthermore, systems that provide appropriate feedback based on each student's learning progress and level of understanding are still insufficient. Furthermore, there are no systems that can recognize the emotions of students and teachers in real time and respond individually based on that, making it difficult to provide learning support that takes emotions into account.

[0809] 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.

[0810] In this invention, the server includes a generation unit that generates homework and test questions based on the subject and difficulty level selected by the teacher, a distribution unit that distributes the generated homework and test questions to students' devices, and an input unit that allows students to input answers using their devices. This reduces the workload of teachers and improves students' learning effectiveness. Furthermore, by incorporating a scoring unit that automatically scores the input answers and an emotion recognition unit that recognizes students' emotions in real time and adaptively generates explanations and supplementary questions based on them, appropriate feedback can be provided in response to individual learning needs, enabling efficient educational support.

[0811] "Generation means" refers to a function that automatically generates homework and exam questions based on the subject and difficulty level selected by the teacher.

[0812] "Distribution means" refers to the function of distributing generated homework and exam questions to student devices.

[0813] "Input means" refers to the interface through which students use their devices to input their answers.

[0814] "Scoring means" refers to a function that automatically scores the answers entered.

[0815] "Result notification means" refers to the function of instantly returning grading results to students' devices.

[0816] "Explanation generation means" refers to the function that generates explanations and correction questions for incorrect parts as needed and displays them on the student's device.

[0817] "Emotion recognition means" refers to the function of recognizing students' emotions in real time and adaptively generating explanations and supplementary questions based on that.

[0818] "Storage means" refers to the function of storing generated homework and test questions, students' answers, and grading results in a database.

[0819] This invention is a system that allows teachers to efficiently generate, distribute, grade, and provide feedback on homework and exam questions, and it also maximizes learning effectiveness by combining it with an emotion engine that recognizes students' emotions and provides appropriate explanations and remedial questions based on those emotions.

[0820] Overall system configuration

[0821] The system mainly consists of the following components:

[0822] 1. Server

[0823] 2. Teacher's device

[0824] 3. Student Devices

[0825] 4. Emotion Engine

[0826] Teacher's device

[0827] A user (teacher) logs in to the system using the teacher's terminal and sends a request to generate homework or exam questions. Specifically, the user selects a subject (e.g., mathematics) and a level of difficulty (e.g., intermediate level) and clicks the "Generate" button.

[0828] server

[0829] The server receives the teacher's request and passes the request information to the generative AI model. The server then sends a request to the AI ​​model to generate "intermediate level" math questions. The generative AI model used uses a general-purpose generative AI framework. Specifically, it includes large-scale language models such as GPT-4. An example of a prompt sentence is "Please generate intermediate level math test questions."

[0830] The server stores the generated questions in a database, which includes the question text, correct answers, explanations, etc. The server then sends the generated questions back to the teacher's device so that the teacher can check them.

[0831] Teacher's device

[0832] The user (teacher) checks the generated questions and makes corrections or additional comments as necessary, thereby maintaining the accuracy and appropriateness of the questions.

[0833] server

[0834] After the teacher has finalized the questions, the server sends a request to distribute the questions to the students' devices. The server retrieves the student's ID and class information from the database and distributes the questions.

[0835] Student devices

[0836] The user (student) logs in to the student's terminal and accesses the distributed questions. An interface for answering the questions is displayed, and the user inputs their answers.

[0837] The student's device sends the entered answers to the server, which receives the answers and stores them in a database.

[0838] server

[0839] The server automatically grades the answers using an AI model based on the saved answers. The server compares the correct answers with the student's answers and generates a score. This score is recorded for each student and stored in a database.

[0840] The server returns the scoring results to the student's terminal and also sends a request to the explanation generation means to generate detailed explanations and correction questions for the incorrect parts. The explanation generation means generates explanations and correction questions as needed and returns them to the server. An example of a specific prompt sentence is "Please explain in detail the differences between the student's answer below and the correct answer: [differences between the student's answer and the correct answer]."

[0841] Emotion Engine

[0842] The emotion engine recognizes students' emotions in real time while they are typing their answers. For example, it analyzes facial expressions and tone of voice via a camera or microphone to determine the user's emotional state. The emotion engine performs its analysis using an AI model using Python's OpenCV and TensorFlow.

[0843] The emotion engine sends the detected emotion information to the server, and adaptively generates the next explanation or remedial question based on that information. For example, if the user is "confused," the engine can provide a more detailed explanation, and if the server recognizes that the user "understands," the engine can proceed to the next question.

[0844] The emotion engine also recognizes teachers' emotions and provides alerts and guidance to help them manage stress and reduce their workload.

[0845] This system is expected to significantly reduce the workload of teachers and improve student learning outcomes. In addition, by recognizing the emotions of students and teachers, more personalized learning support will be possible, improving the efficiency of the entire learning process.

[0846] The flow of the identification process in the second embodiment will be described with reference to FIG.

[0847] Step 1:

[0848] The user (teacher) logs in to the system using the teacher's terminal. They enter their username and password as input and send this information to the server. The server compares the entered information with the database, and if authentication is successful, the teacher's home screen is displayed.

[0849] Step 2:

[0850] The user (teacher) requests the generation of homework or exam questions on the home screen. Specifically, the user selects the subject (e.g., mathematics) and difficulty level (e.g., intermediate level) and clicks the "Generate" button. This selection information is sent as input to the server.

[0851] Step 3:

[0852] The server receives a generation request from the teacher. As input, it obtains the requested information on subject and difficulty level and passes it to the generative AI model. It then sends a "Mathematics" "Intermediate" problem generation prompt to the generative AI model. An example of this prompt is "Please generate intermediate level math test questions."

[0853] Step 4:

[0854] The generative AI model receives prompts from the server and generates questions. It receives the prompt as input, processes data, and performs data calculations to generate a problem set that includes the question, correct answer, explanation, etc. The generated problem set is output to the server.

[0855] Step 5:

[0856] The server receives the problem set from the generative AI model and stores it in a database. The problem set is received as input and stored in a table containing the problem ID, problem statement, correct answer, and explanation.

[0857] Step 6:

[0858] The server returns the generated problem set to the teacher's terminal. The server takes the saved problem set as input and sends it to the teacher's terminal. The generated problem is displayed on the teacher's terminal.

[0859] Step 7:

[0860] The user (teacher) checks the generated questions, makes corrections or adds comments as necessary, edits the questions displayed as input, and sends the corrections from the terminal to the server. The server then saves the corrected question set back into the database.

[0861] Step 8:

[0862] The server requests the distribution of questions determined by the teacher to the student's device. It obtains the student's ID and class information from the database as input and distributes the questions. It then sends this distribution information to the student's device.

[0863] Step 9:

[0864] The user (student) logs in to their device and accesses the distributed questions. The login information is sent from the device to the server as input, and if authentication is successful, the question display screen is output.

[0865] Step 10:

[0866] The user (student) inputs the answer to the displayed question. The answer information is entered into the terminal as input, and the answer content is sent to the server. The terminal also sends this answer information to the emotion engine in real time.

[0867] Step 11:

[0868] The server receives the student's answers and stores them in a database. The server takes the answer information as input and stores it in a database.

[0869] Step 12:

[0870] The server automatically scores the students' answers using a generative AI model based on the saved answers. It compares the correct answer data with the students' answers as input, performs data calculations, and generates a score. This score is then output to a database.

[0871] Step 13:

[0872] The server returns the marking results to the student's device and sends a request to the explanation generation means to generate detailed explanations and correction questions for the incorrect parts.The server takes the marking results as input and sends an explanation generation prompt to the generative AI model.

[0873] Step 14:

[0874] The explanation generation means uses a prompt sentence to make the generative AI model generate detailed explanations and remedial questions. It sends the prompt "Please explain in detail the difference between the student's answer below and the correct answer" as input, and outputs the generated explanation to the server.

[0875] Step 15:

[0876] The server returns the generated explanations and supplementary questions to the student's device. The server receives explanation data as input and sends it to the student's device. The specific explanations and supplementary questions are displayed on the student's device.

[0877] Step 16:

[0878] The emotion engine recognizes students' emotions in real time while they are typing their answers. It analyzes facial expressions and tone of voice collected via a camera and microphone as input, and outputs the analysis results to a server.

[0879] Step 17:

[0880] The emotion engine sends the detected emotion information to the server and adaptively generates explanations and remedial questions based on that information. For example, if a student is "confused," it generates a prompt to provide a detailed explanation. It takes the emotion information as input and sends the prompt to the generative AI model to generate an adaptive explanation. As a result, a detailed explanation or instructions to proceed to the next question are output to the student's device.

[0881] (Application example 2)

[0882] 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."

[0883] In today's world, the burden on teachers in the educational field is increasing. Furthermore, in brick-and-mortar stores, the demand for customer service that meets customer needs is increasing the workload on store clerks. It is becoming increasingly difficult for teachers to efficiently generate, distribute, grade, and provide feedback on homework and exam questions, and for store clerks to respond quickly and appropriately to customer emotions. Furthermore, conventional systems have difficulty accurately reading and responding to the emotions of users (teachers and store clerks), resulting in a lack of systems that maximize learning outcomes and customer service efficiency. There is a need to solve these issues, reduce the workload on teachers and store clerks, and provide personalized support to users (students and customers).

[0884] 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: a generation unit that generates homework and test questions based on the subject and difficulty level selected by the teacher; a distribution unit that distributes the generated homework and test questions to students' digital devices; an input unit that allows students to input answers using their digital devices; a scoring unit that automatically grades the entered answers; a result notification unit that instantly returns the graded results to the students' devices; an explanation generation unit that generates explanations and correction questions for incorrect sections as needed and displays them on the students' devices; an emotion recognition unit that recognizes emotions based on customer questions, images, and voices and generates responses based on the emotions; a response generation unit that generates and displays appropriate product explanations and suggestions based on the customer's emotions; and a notification unit that displays the generated questions and responses on the digital devices of store clerks. This reduces the burden on teachers in educational settings and improves students' learning outcomes. Furthermore, in physical stores, appropriate responses based on customer emotions can be quickly provided, thereby improving customer satisfaction.

[0885] "Generation means" refers to a device or program for generating homework and test questions based on the subject and level of difficulty selected by the teacher.

[0886] "Distribution means" refers to a device or program for distributing generated homework and exam questions to students' digital devices.

[0887] "Input means" refers to the device or interface that allows students to input answers using a digital device.

[0888] "Scoring means" refers to a device or program for automatically scoring the answers entered.

[0889] "Result notification means" refers to a device or program that instantly returns the grading results to the student's device.

[0890] "Explanation generation means" refers to a device or program that generates explanations and correction questions for incorrect parts as needed and displays them on the student's device.

[0891] "Emotion recognition means" refers to devices or programs that recognize emotions based on customer questions, images, and voices.

[0892] The "response generation means" refers to a device or program for generating and displaying appropriate product descriptions and suggestions based on the customer's emotions.

[0893] "Notification means" refers to a device or program for displaying the generated questions and responses on the store clerk's digital device.

[0894] To implement this invention, a server, a teacher's terminal, a student's terminal, an emotion engine, and a database are required. The following describes specific embodiments of the invention.

[0895] Overall system configuration

[0896] server

[0897] The server includes the following means:

[0898] Generator: Generate homework and exam questions based on teacher-selected subjects and difficulty levels. This process is driven by a generative AI model.

[0899] Distribution: Distributing generated homework and exam questions to students' digital devices.

[0900] Scoring: Automatically score student-entered answers.

[0901] Results notification: Grading results are instantly sent back to student devices.

[0902] Explanation generation means: Explanations and correction questions for incorrect parts are generated and displayed on the student's device.

[0903] Emotion recognition: Recognizes emotions based on customer questions, images, and voice. For this, we use an emotion engine.

[0904] Response generation means: Generate and display appropriate product descriptions and suggestions based on customer sentiment.

[0905] Teacher's device

[0906] Teacher devices have the following features:

[0907] Ability for teachers to submit requests to generate homework and exam questions.

[0908] Ability to review generated issues and make corrections or additions.

[0909] Student devices

[0910] Student devices have the following features:

[0911] Ability to access distributed questions and enter answers.

[0912] A function to receive scoring results and explanations.

[0913] Emotion Engine

[0914] The emotion engine has the following features:

[0915] Ability to recognize user emotions in real time.

[0916] A function that generates appropriate explanations and supplementary questions based on emotional information.

[0917] Specific use cases

[0918] If a teacher wants to generate intermediate-level math exam questions, they send a request to the server from their own device, selecting the subject "Mathematics" and the difficulty level "Intermediate." The server then invokes the generative AI model, generates an appropriate set of questions, and sends them back to the teacher's device. After the teacher checks the generated questions, they distribute them to students. Students answer the questions using their digital devices and send their answers to the server. The server automatically grades the answers and provides instant feedback, while the emotion engine provides detailed explanations and remedial questions based on the students' emotional information.

[0919] A similar system can also be used in physical stores. In response to customer questions, store clerks can provide appropriate responses while recognizing the customer's emotions. For example, if a customer asks, "Tell me about this product," the emotion engine reads the customer's emotions from their image and voice. Based on this, the generative AI model generates the optimal response, which is displayed on the clerk's device.

[0920] Prompt Sentence Examples

[0921] "A customer asks, 'Tell me about this product.' The customer's emotion is 'Confused.' Generate an appropriate response."

[0922] In this way, this invention is a system that can generate appropriate questions and provide individualized responses based on emotions in educational settings and brick-and-mortar stores.

[0923] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[0924] Step 1:

[0925] A request is sent from the teacher's terminal to the server to generate homework or exam questions based on the subject and difficulty level selected by the teacher. Here, the input is the subject and difficulty level selected by the teacher, and the server side calls the generative AI model based on this. In this process, the server passes the selection information to the generative AI model and uses it as a prompt for question generation.

[0926] Step 2:

[0927] The server uses a generative AI model to generate homework and exam questions. Based on the input data (selected subjects and difficulty level), the generative AI model generates a problem set. Here, the generative AI model generates questions using prompts such as "math" or "intermediate" and sends the results back to the server. The server receives the generated results: the problem statement, correct answers, and explanations.

[0928] Step 3:

[0929] The generated homework and exam questions are sent back from the server to the teacher's terminal, where the teacher can review them and add corrections or comments. The input is the generated question set, and the output is the question set edited by the teacher.

[0930] Step 4:

[0931] Once the teacher has finalized the problem set, the information is sent to the server again. The server saves the finalized problem set in the database and prepares it for distribution to the students' devices. The input is the finalized problem set, and the output is a notification that it is ready to be saved in the database and distributed.

[0932] Step 5:

[0933] The student's device accesses the distributed questions and inputs the answers. At this stage, an interface is displayed for the student to answer the questions. The input is the student's answer, and the output is the answer data.

[0934] Step 6:

[0935] The answers are sent from the student's terminal to the server. The server stores the received answers in a database and then automatically grades them using a grading tool. The input is the student's answer data, and the output is the graded results.

[0936] Step 7:

[0937] The server stores the grading results in a database and sends the results back to the student's device using a result notification means. The input is the grading results and the output is a notification to the student's device.

[0938] Step 8:

[0939] Next, the explanation generation means generates explanations and correction questions for the incorrect parts. The server sends the generated explanations and correction questions to the student's terminal. The input is the grade data and incorrect answers, and the output is the generated explanations and correction questions.

[0940] Step 9:

[0941] In parallel, an emotion recognition means is used to recognize emotions based on the customer's question, image, and voice, where the input is the customer's question, facial expression image, and voice data, and the output is the recognized emotional state.

[0942] Step 10:

[0943] Based on the emotion recognition results, the response generation means generates appropriate product descriptions and suggestions. The server then sends the generated responses to the salesperson's terminal. The input is the customer's question and emotional state, and the output is the generated responses.

[0944] Step 11:

[0945] The generated questions and responses are displayed on the salesperson's terminal, and the salesperson responds to the customer based on them. Here, the input is the generated response sentence, and the output is the information that the salesperson provides to the customer.

[0946] In this way, the system generates appropriate questions and provides personalized, emotion-based responses in educational settings and brick-and-mortar stores.

[0947] 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.

[0948] 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.

[0949] 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.

[0950] [Third embodiment]

[0951] FIG. 5 shows an example of the configuration of a data processing system 310 according to the third embodiment.

[0952] 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.

[0953] 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).

[0954] 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.

[0955] 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.

[0956] 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).

[0957] 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.

[0958] 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.

[0959] 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.

[0960] 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.

[0961] 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.

[0962] 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."

[0963] The present invention is a system that enables teachers to efficiently generate, distribute, grade, and provide feedback on homework and test questions, and has the following specific embodiments.

[0964] Overall system configuration

[0965] The system mainly consists of the following components:

[0966] 1. Server

[0967] 2. Teacher's device

[0968] 3. Student Devices

[0969] Teacher's device

[0970] 1. A user (teacher) logs in to the system using the teacher's terminal and sends a request to generate homework or exam questions. Specifically, the user selects a subject (e.g., mathematics) and difficulty level (e.g., intermediate level) and sends a request to the system.

[0971] server

[0972] 1. The server receives the teacher's request and passes the request information to the generative AI model, which then generates appropriate homework and exam questions based on the specified subject and difficulty level.

[0973] 2. The server stores the generated questions in a database, which includes the question text, correct answers, explanations, etc. The server then sends the generated questions back to the teacher's device so that the teacher can check them.

[0974] Teacher's device

[0975] 1. The user (teacher) checks the generated questions and makes corrections or additional comments as necessary, thereby maintaining the accuracy and appropriateness of the questions.

[0976] server

[0977] 1. After the teacher has finalized the questions, the server requests that the questions be distributed to the students' devices. The questions are distributed based on the student ID and class information.

[0978] Student devices

[0979] 1. The user (student) logs in to their device and accesses the distributed questions. An interface for answering the questions is displayed, and the user enters their answers.

[0980] 2. The student's device sends the entered answers to the server, which receives and stores the answers.

[0981] server

[0982] 1. The server automatically scores the questions using an AI model based on the saved answers. It compares the correct answers with the student's answers and generates a score. This score is recorded for each student and stored in a database.

[0983] 2. The server sends the scoring results back to the student's device and also generates detailed explanations and correction questions for any mistakes.

[0984] Student devices

[0985] 1. The student's device will display the graded results, explanations, and supplementary questions to the student, allowing them to quickly and effectively check their learning progress and review any necessary sections.

[0986] Specific use cases

[0987] For example, if a teacher wants to generate intermediate-level mathematics exam questions, the teacher sends a request from their device to the server, selecting the subject "Mathematics" and the difficulty level "Intermediate." The server then invokes the generative AI model, generates an appropriate set of questions, and sends them back to the teacher's device. After the teacher checks the generated questions, they distribute them to students. Students then answer the questions using their digital devices and send their answers to the server. The server automatically grades the answers, providing instant feedback and explanations or remedial questions as needed.

[0988] This system is expected to significantly reduce the workload of teachers and improve students' learning outcomes.

[0989] The processing flow will be explained below.

[0990] Step 1:

[0991] A user (teacher) logs in to the system using the teacher's terminal and sends a request to generate homework or exam questions. Specifically, the user selects a subject (e.g., mathematics) and a level of difficulty (e.g., intermediate level) and clicks the "Generate" button.

[0992] Step 2:

[0993] The teacher's terminal sends a request to the server including the subject and difficulty level information input by the user.

[0994] Step 3:

[0995] The server receives requests from the teacher's device and passes the request information to the generative AI model. The server then sends a "Mathematics" "Intermediate" problem generation request to the AI ​​model.

[0996] Step 4:

[0997] The generative AI model generates appropriate homework and exam questions based on the subject and level of difficulty, including the question statement, correct answers, and explanations.

[0998] Step 5:

[0999] The server stores the generated questions in a database, which includes information such as the question, the correct answer, and an explanation.

[1000] Step 6:

[1001] The server sends the generated questions back to the teacher's terminal, where the teacher can check the questions.

[1002] Step 7:

[1003] The user (teacher) checks the generated questions and makes corrections or additional comments as necessary. Once the teacher reviews and confirms the questions, the questions based on this are sent to the server.

[1004] Step 8:

[1005] After the teacher has finalized the questions, the server sends a request to distribute the questions to the students' devices. The server retrieves the student's ID and class information from the database and distributes the questions.

[1006] Step 9:

[1007] The user (student) logs in to the student's terminal and accesses the distributed questions. An interface for answering the questions is displayed, and the user inputs their answers.

[1008] Step 10:

[1009] The student's device sends the answers entered by the user (student) to the server, which receives the answers and stores them in a database.

[1010] Step 11:

[1011] The server automatically grades the questions using an AI model based on the stored answers. The server compares the correct answers with the student's answers and generates a score.

[1012] Step 12:

[1013] The server returns the graded results to the student's terminal and also sends a request to the explanation generation means to generate detailed explanations and correction questions for the incorrect parts.

[1014] Step 13:

[1015] The explanation generating means generates explanations and correction questions as needed and sends them back to the server.

[1016] Step 14:

[1017] The server sends explanations and supplementary questions to the students' devices and records them in a database as logs.

[1018] Step 15:

[1019] The user (student) can check the grades, explanations, and supplementary questions on their own device, allowing them to check their own understanding and review any necessary parts.

[1020] Example 1

[1021] 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."

[1022] In conventional educational systems, teachers manually create homework and exam questions, distribute them to students, and then grade and provide feedback, requiring a great deal of time and effort. This cumbersome process reduces teachers' work efficiency and hinders their ability to provide prompt feedback to students. Furthermore, the balance between question content and difficulty level is inconsistent, making it difficult to provide personalized support based on each student's learning progress. To address these issues, the present invention aims to provide a system that automates teachers' work and provides appropriate and prompt feedback to students.

[1023] 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.

[1024] In this invention, the server includes a generating means for generating homework and test questions based on the subject and difficulty level selected by the teacher, a distributing means for distributing the generated homework and test questions to the students' digital devices, an input means for the students to input answers using their digital devices, a sending and saving means for sending the input answers to the server and saving them, a scoring means for automatically scoring the saved answers, a result notifying means for returning the scoring results to the students' digital devices, and an explanation generating means for generating explanations and correction questions for incorrect parts as needed and displaying them on the students' digital devices. This reduces the workload on teachers and enables them to provide students with quick and appropriate feedback.

[1025] "Generative means" refers to a function that automatically generates homework and exam questions using an AI model based on the subject and difficulty level selected by the teacher.

[1026] "Distribution means" refers to the function of sending generated homework and exam questions to students' digital devices in an appropriate format.

[1027] "Input means" refers to the interface and functionality that allows students to input answers to homework and exam questions using digital devices.

[1028] The "transmission and storage means" is a function that sends the answers entered by the students to the server and stores them in a database.

[1029] The "scoring method" is a function that automatically scores answers stored on the server using an AI model to generate a score.

[1030] "Result notification means" is a function that quickly returns graded results to students' digital devices.

[1031] The "explanation generation means" is a function that generates explanations and correction questions for incorrect parts as needed and displays them on the student's digital device.

[1032] "Storage means" is a function that stores generated homework and test questions, students' answers, and grading results in a database, allowing the information to be retrieved later.

[1033] The present invention is a system for teachers to efficiently generate, distribute, grade, and provide feedback on homework and exam questions. The system comprises the following components:

[1034] Overall system configuration

[1035] The main components of the system are:

[1036] 1. Server

[1037] 2. Teacher's device

[1038] 3. Student Devices

[1039] Teacher's device

[1040] Users (teachers) log in to the system from their own devices via an internet browser and use a dedicated application (e.g., a UI built with React) to send a request to the server to generate homework or exam questions. The teacher selects the subject (e.g., mathematics) and difficulty level (e.g., intermediate), and presses the generate button, which sends the request to the server. An example of a prompt sentence is "Please create intermediate-level mathematics exam questions."

[1041] server

[1042] The server has a backend system written in Python that receives requests, analyzes them, and sends prompts to an AI model (e.g., OpenAI GPT-3), which then generates an appropriate problem set based on the specified subject and difficulty level.

[1043] The generated problem set is sent back to the server in JSON format, which stores it in a MySQL database. The stored data includes the problem statement, correct answers, and explanations. The generated problem set is then sent back to the teacher's computer.

[1044] Teacher's device

[1045] The user (teacher) checks the generated questions and, if necessary, edits the question text and explanations using a rich text editor (e.g., Quill.js). Once the edits are complete, the user presses the confirm button to send a request to the server to save the changes.

[1046] server

[1047] The server then obtains a list of students based on their IDs and class information to distribute the finalized questions to them. At this time, the questions are again organized in JSON format and sent to the students' devices.

[1048] Student devices

[1049] Users (students) log in to their own devices and access the distributed questions. An interface built with Angular is displayed on the student's device, allowing the user to enter answers to the questions.

[1050] server

[1051] The student's device sends the entered answers in JSON format to the server. The server receives them and stores them in a MySQL database. Then, based on the saved answers, an AI model (e.g., TensorFlow) is used again to automatically grade the answers. The correct answer is compared with the student's answer, a score is generated, and the score is recorded in the database.

[1052] The graded results are quickly returned to the student's digital device, and feedback and correction questions are generated and sent to the student's device for any errors.

[1053] Student devices

[1054] The student's device displays the feedback, explanations, and revision questions received from the server to the user (student). The student can refer to this to check their own learning progress and review the material as appropriate.

[1055] Specific examples

[1056] For example, if a teacher wants to generate intermediate-level math exam questions, they send a prompt request to the server saying, "Please create intermediate-level math exam questions." The server uses OpenAI GPT-3 to generate the questions and stores the results in a MySQL database. The questions are sent back to the teacher's device, where the teacher can review and correct them before distributing them to the students. Students then submit their answers to the server through an interface, and the server uses TensorFlow to grade them and provide instant feedback.

[1057] The present invention significantly reduces the workload of teachers, provides students with prompt and appropriate feedback, and improves learning effectiveness.

[1058] The flow of the identification process in the first embodiment will be described with reference to FIG.

[1059] Step 1:

[1060] A user (teacher) logs into the system using a dedicated application (e.g., a UI built with React). The teacher selects the subject (e.g., mathematics) and difficulty level (e.g., intermediate) from drop-down menus and presses the generate button. This action sends a generation request to the server.

[1061] Input: Selection information as subject and difficulty level.

[1062] Output: The generated request sent to the server.

[1063] Step 2:

[1064] The server receives the teacher's request and analyzes it. Based on the analyzed request information, the server sends a prompt message to the generative AI model (e.g., OpenAI GPT-3) asking it to generate questions: "Please create intermediate-level math exam questions."

[1065] Input: Subject and difficulty level as generation request.

[1066] Output: The prompt sent to the generative AI model.

[1067] Step 3:

[1068] The generative AI model generates questions appropriate for the specified subject and level of difficulty based on the prompt text, and the generated question set is sent back to the server in JSON format.

[1069] Input: The prompt statement.

[1070] Output: The generated problem set.

[1071] Step 4:

[1072] The server stores the received problem set in JSON format in a MySQL database. The stored data includes the problem statement, correct answer, and explanation. The server then sends the problem set to the teacher's device.

[1073] Input: The generated problem set.

[1074] Output: The problem set sent to the teacher's device.

[1075] Step 5:

[1076] The user (teacher) checks the questions generated on the device and, if necessary, edits the questions and explanations using a rich text editor (e.g., Quill.js). Once edits are complete, the teacher presses the confirm button to send the revised question set to the server.

[1077] Input: Problem set and correction information.

[1078] Output: The revised problem set that is sent to the server.

[1079] Step 6:

[1080] The server receives the revised questions, stores them in the MySQL database again, and then distributes the questions to students based on their IDs and class information.

[1081] Input: A revised problem set and student information.

[1082] Output: Questions distributed to student devices.

[1083] Step 7:

[1084] Users (students) log in to their own devices and access the distributed questions. Students enter their answers to the questions using an interface built with Angular.

[1085] Input: The distributed question.

[1086] Output: The answer entered by the student.

[1087] Step 8:

[1088] The student's device sends the entered answers in JSON format to the server, which receives them and stores them in a MySQL database.

[1089] Input: Student answers.

[1090] Output: The answer sent to the server and stored in the database.

[1091] Step 9:

[1092] The server automatically scores the answers using an AI model (e.g., TensorFlow) based on the saved answers, comparing the correct answers with the student's answers, generating a score and recording it in a database.

[1093] Input: Your saved answer.

[1094] Output: The resulting score.

[1095] Step 10:

[1096] The server generates feedback based on the scoring results, and also creates explanations and correction questions for incorrect answers, which are sent to the student's device.

[1097] Input: Scoring results.

[1098] Output: Feedback, explanations, and remedial questions.

[1099] Step 11:

[1100] The student's device displays the feedback, explanations, and revision questions received from the server to the user (student). The student can refer to this to check their own learning progress and review the material as appropriate.

[1101] Input: Feedback, explanations, and remedial questions.

[1102] Output: Feedback information displayed on student devices.

[1103] (Application example 1)

[1104] 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."

[1105] Traditionally, it takes a lot of time and effort for teachers to create homework and exam questions, distribute them to students, and then grade and provide feedback. Furthermore, stores selling education-related products require a lot of time and effort to provide detailed explanations and demonstrations of their products and services, and it is difficult to quickly provide services such as creating homework questions and providing instant grading. This places a heavy burden on teachers and store staff, making it difficult to provide fast and effective feedback to students and customers.

[1106] 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.

[1107] In this invention, the server includes a generation unit that generates homework and test questions based on the subject and level of difficulty selected by the teacher, a distribution unit that distributes the generated homework and test questions to the students' computers, and an input unit that allows the students to input answers using their computers. This enables the processes of generating, distributing, grading, and providing feedback on homework and test questions to be carried out automatically and efficiently. Furthermore, by using store terminals in the store to explain educational products and services and to generate and demonstrate homework questions, the burden on store staff can be reduced, enabling the provision of fast and effective services to customers.

[1108] The "generation means" refers to a device or software that has the function of generating homework and test questions based on the subject and level of difficulty selected by the teacher.

[1109] The "distribution means" refers to a device or software that has the function of transmitting and distributing the generated homework and test questions to the students' computers.

[1110] "Input means" refers to the interface or software that allows students to input answers using a computer.

[1111] The "scoring means" refers to a device or software that has the function of automatically scoring the answers entered.

[1112] The "result notification means" is a device or software that has the function of instantly returning the grading results to the student's computer.

[1113] The "explanation generating means" is a device or software that has the function of generating explanations and correction questions for incorrect parts as needed and displaying them on the student's computer.

[1114] "Store terminal" refers to a device used in a store to explain educational products and services, generate homework questions, and provide demonstrations.

[1115] This invention is a system that allows teachers to efficiently generate, distribute, grade, and provide feedback on homework and exam questions, and has been improved to effectively introduce, explain, and demonstrate educational products and services in physical stores. The detailed configuration and operation of this system are described below.

[1116] Overall system configuration

[1117] The system mainly consists of the following components:

[1118] 1. Server

[1119] 2. Teacher's device

[1120] 3. Student Devices

[1121] 4. In-store terminals

[1122] Teacher's device

[1123] 1. A teacher logs in to the system using their terminal and sends a request to generate homework or exam questions. Specifically, the teacher selects the subject (e.g., mathematics) and difficulty level (e.g., intermediate level) and sends the request to the system.

[1124] server

[1125] 1. The server receives the teacher's request and passes the request information to the generative AI model, which then generates appropriate homework and exam questions based on the specified subject and difficulty level.

[1126] 2. The server saves the generated questions in a database, including the question text, correct answers, explanations, etc. The server then sends the generated questions back to the teacher's device so that the teacher can check them.

[1127] Teacher's device

[1128] 1. The teacher reviews the generated questions and makes corrections or additional comments as necessary to ensure the accuracy and appropriateness of the questions.

[1129] server

[1130] 1. After the teacher has finalized the questions, the server requests that the questions be distributed to the students' devices. The questions are distributed based on the student ID and class information.

[1131] Student devices

[1132] 1. Students log in to their devices and access the distributed questions. An interface for answering the questions is displayed, and students enter their answers.

[1133] 2. The student's device sends the entered answers to the server, which receives and stores the answers.

[1134] server

[1135] 1. The server automatically scores the questions using an AI model based on the saved answers. It compares the correct answers with the student's answers and generates a score. This score is recorded for each student and stored in a database.

[1136] 2. The server sends the scoring results back to the student's device and also generates detailed explanations and correction questions for any mistakes.

[1137] Student devices

[1138] 1. The student's device will display the graded results, explanations, and supplementary questions to the student, allowing them to quickly and effectively check their learning progress and review any necessary sections.

[1139] Physical store terminals

[1140] 1. The in-store terminals are used to explain educational products and services, generate homework questions, and demonstrate them. Sample homework questions can be generated and checked on the spot before customers purchase the requested products in the store.

[1141] 2. Promote educational software sales by instantly demonstrating curriculum on in-store tablets.

[1142] 3. A service can be developed for educational events and workshops that provides participants with generated homework and grades it on the spot.

[1143] Usage example

[1144] For example, if a teacher wants to generate intermediate-level mathematics exam questions, the teacher sends a request to the server from their device, selecting the subject "Mathematics" and the difficulty level "Intermediate." The server then invokes the generative AI model, generates an appropriate set of questions, and sends them back to the teacher's device. The teacher reviews the generated questions, corrects them if necessary, and then distributes them to students. Students then answer the questions using their digital devices and send the answers to the server. The server automatically grades the answers, provides instant feedback, and provides explanations and remedial questions as needed. Furthermore, customers can try out the features of educational products and services when purchasing them in physical stores.

[1145] Prompt Sentence Examples

[1146] "Generate intermediate level math homework problems."

[1147] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[1148] Step 1:

[1149] The teacher terminal displays an interface for the user (teacher) to select the subject and difficulty level. The teacher terminal receives the subject and difficulty level information entered by the user and sends a request to the server.

[1150] Input: Subject (e.g., Math), Difficulty (e.g., Intermediate)

[1151] Data processing: Convert form data into JSON format

[1152] Output: Request to server

[1153] Step 2:

[1154] The server receives requests sent from the teacher device, analyzes the received data, and provides the necessary information for the generative AI model.

[1155] Input: Subject and difficulty request (JSON format)

[1156] Data processing: Analyzes request data and generates prompts

[1157] Output: A request to the generative AI model

[1158] Step 3:

[1159] The generative AI model generates homework and exam questions based on requests received from the server.

[1160] Input: Parsed prompt ("Generate intermediate level math homework problems.")

[1161] Data calculation: Generative AI model generates question, answer, and explanation

[1162] Output: Generated homework questions (question statement, answer, explanation, etc.)

[1163] Step 4:

[1164] The server stores the generated questions in a database and returns the stored questions to the teacher's terminal.

[1165] Input: Generated homework questions

[1166] Data processing: Data storage in the database and data generation for sending to the teacher's terminal

[1167] Output: Database update, response to teacher terminal

[1168] Step 5:

[1169] The teacher's terminal displays the received homework questions to the user, who then checks the questions and makes corrections or additional comments as necessary.

[1170] Input: Homework question sent from the server

[1171] Data processing: Converting data into a format suitable for display on the screen

[1172] Output: Teacher confirmation and correction data

[1173] Step 6:

[1174] The teacher's terminal sends the confirmed homework questions to the server again.

[1175] Input: Confirmed homework question

[1176] Data processing: Convert the complete problem set, including teacher correction data, into JSON format

[1177] Output: Send to server

[1178] Step 7:

[1179] The server makes a request to distribute the determined homework problems to the student's terminal.

[1180] Input: Confirmed homework question

[1181] Data processing: Adding student ID and class information to be distributed

[1182] Output: Distribution request to student devices

[1183] Step 8:

[1184] The student terminal receives the distributed homework questions and displays an interface for the user (student) to answer the questions.

[1185] Input: Homework question sent from the server

[1186] Data processing: generating an interface for answers

[1187] Output: Student answer data

[1188] Step 9:

[1189] The server receives the answer data sent from the student terminal and automatically grades it.

[1190] Input: Student answer data

[1191] Data calculation: Automatic scoring by comparing with correct data

[1192] Output: Scoring results

[1193] Step 10:

[1194] The server sends the results of the marks to the student's terminal, and also generates and displays explanations of the incorrect parts and correction questions.

[1195] Input: Marking results and answer data

[1196] Data calculation: Error analysis and repair problem generation

[1197] Output: Detailed feedback to student devices

[1198] Step 11:

[1199] The terminals in the physical stores provide an interface for explaining educational products and services, generating homework questions, and running demonstrations.

[1200] Input: Store staff or customer request

[1201] Data Computing: Generating demo homework problems using generative techniques

[1202] Output: Instant feedback and demo execution for the customer

[1203] 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.

[1204] This invention is a system that allows teachers to efficiently generate, distribute, grade, and provide feedback on homework and exam questions, and it also maximizes learning effectiveness by combining it with an emotion engine that recognizes the user's emotions and provides appropriate explanations and revision questions based on those emotions. Specific embodiments of this system are described below.

[1205] Overall system configuration

[1206] The system mainly consists of the following components:

[1207] 1. Server

[1208] 2. Teacher's device

[1209] 3. Student Devices

[1210] 4. Emotion Engine

[1211] Teacher's device

[1212] 1. A user (teacher) logs in to the system using the teacher's terminal and sends a request to generate homework or exam questions. Specifically, the user selects a subject (e.g., mathematics) and difficulty level (e.g., intermediate level) and clicks the "Generate" button.

[1213] server

[1214] 1. The server receives the teacher's request and passes the request information to the generative AI model. The server then sends a "Mathematics" "Intermediate" problem generation request to the AI ​​model.

[1215] 2. The server stores the generated questions in a database, which includes the question text, correct answers, explanations, etc. The server then sends the generated questions back to the teacher's device so that the teacher can check them.

[1216] Teacher's device

[1217] 1. The user (teacher) checks the generated questions and makes corrections or additional comments as necessary, thereby maintaining the accuracy and appropriateness of the questions.

[1218] server

[1219] 1. After the teacher has finalized the questions, the server sends a request to distribute the questions to the students' devices. The server retrieves the student's ID and class information from the database and distributes the questions.

[1220] Student devices

[1221] 1. The user (student) logs in to their device and accesses the distributed questions. An interface for answering the questions is displayed, and the user enters their answers.

[1222] 2. The student's device sends the entered answer to the server, which receives the student's answer and stores it in a database.

[1223] server

[1224] 1. The server automatically scores the students using an AI model based on their saved answers. The server compares the correct answers with the students' answers and generates a score. This score is recorded for each student and stored in a database.

[1225] 2. The server returns the results of the marks to the student's terminal and also sends a request to the explanation generation means to generate detailed explanations and correction questions for the incorrect parts.

[1226] 3. The explanation generation means generates explanations and correction questions as needed and sends them back to the server.

[1227] Emotion Engine

[1228] 1. The emotion engine recognizes the user's emotions in real time while the student is entering their answers. For example, it analyzes facial expressions and tone of voice via a camera or microphone to determine the user's emotional state.

[1229] 2. The emotion engine sends the detected emotion information to the server, and adaptively generates the next explanation or remedial question based on that information. For example, if the user is "confused," it can provide a more detailed explanation, and if the user is recognized as "understanding," it can proceed to the next question.

[1230] 3. The emotion engine also recognizes teachers' emotions and provides alerts and guidance to help teachers manage stress and reduce their workload.

[1231] Specific use cases

[1232] For example, if a teacher wants to generate intermediate-level mathematics exam questions, the user (teacher) sends a request from their own device to the server, selecting the subject "Mathematics" and difficulty level "Intermediate." The server then invokes the generative AI model, generates an appropriate set of questions, and sends them back to the teacher's device. After the teacher checks the generated questions, they distribute them to students. The user (student) answers the questions using a digital device and sends the answers to the server. The server automatically grades the answers and provides instant feedback, while the emotion engine provides detailed explanations and remedial questions based on the student's emotional information.

[1233] This system is expected to significantly reduce the workload of teachers and improve students' learning outcomes. In addition, by recognizing users' emotions, it will enable more personalized learning support, improving the efficiency of the entire learning process.

[1234] The processing flow will be explained below.

[1235] Step 1:

[1236] A user (teacher) logs in to the system using the teacher's terminal and sends a request to generate homework or exam questions. Specifically, the user selects a subject (e.g., mathematics) and a level of difficulty (e.g., intermediate level) and clicks the "Generate" button.

[1237] Step 2:

[1238] The teacher's terminal sends a request to the server including the subject and difficulty level information input by the user.

[1239] Step 3:

[1240] The server receives the request from the teacher's device and passes the request information to the generation AI model. The server then sends a problem generation request for "Subject: Mathematics" and "Difficulty: Intermediate" to the AI ​​model.

[1241] Step 4:

[1242] The generative AI model generates appropriate homework and exam questions based on the subject and difficulty level specified, including the question statement, correct answers, and explanations.

[1243] Step 5:

[1244] The server stores the generated questions in a database, which includes the question text, correct answers, explanations, etc.

[1245] Step 6:

[1246] The server sends the generated questions back to the teacher's terminal, where the teacher can check the questions.

[1247] Step 7:

[1248] The user (teacher) checks the generated questions and makes corrections or additional comments as necessary, thereby maintaining the accuracy and appropriateness of the questions.

[1249] Step 8:

[1250] After the teacher has finalized the questions, the server sends a request to distribute the questions to the students' devices. The server retrieves the student's ID and class information from the database and distributes the questions.

[1251] Step 9:

[1252] The user (student) logs in to the student's terminal and accesses the distributed questions. An interface for answering the questions is displayed, and the user inputs their answers.

[1253] Step 10:

[1254] The student's device sends the answers entered by the user (student) to the server, which receives the answers and stores them in a database.

[1255] Step 11:

[1256] The server automatically grades the questions using an AI model based on the stored answers. The server compares the correct answers with the student's answers and generates a score.

[1257] Step 12:

[1258] The server returns the results of the marks to the student's terminal and also sends a request to the explanation generating means to generate detailed explanations and correction questions for the incorrect parts.

[1259] Step 13:

[1260] The explanation generating means generates explanations and correction questions as needed and sends them back to the server.

[1261] Step 14:

[1262] The user (student) can check the grades, explanations, and supplementary questions on their own device, allowing them to check their own understanding and review any necessary parts.

[1263] Step 15:

[1264] The emotion engine recognizes the user's emotions in real time while the student is typing their answers, for example by analyzing facial expressions and tone of voice via the camera and microphone to determine the user's emotional state.

[1265] Step 16:

[1266] The emotion engine sends the detected emotion information to the server, and adaptively generates the next explanation or remedial question based on that information. For example, if the user is "confused," the engine can provide a more detailed explanation, and if the server recognizes that the user "understands," the engine can proceed to the next question.

[1267] Step 17:

[1268] The emotion engine also recognizes teachers' emotions and provides alerts and guidance to help them manage stress and reduce their workload.

[1269] In this way, the system provides an optimal learning environment for both teachers and students, maximizing educational effectiveness.

[1270] Example 2

[1271] 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."

[1272] In conventional educational support systems, teachers often manually create, distribute, and grade homework and exam questions, placing a heavy burden on teachers. Furthermore, systems that provide appropriate feedback based on each student's learning progress and level of understanding are still insufficient. Furthermore, there are no systems that can recognize the emotions of students and teachers in real time and respond individually based on that, making it difficult to provide learning support that takes emotions into account.

[1273] 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.

[1274] In this invention, the server includes a generation unit that generates homework and test questions based on the subject and difficulty level selected by the teacher, a distribution unit that distributes the generated homework and test questions to students' devices, and an input unit that allows students to input answers using their devices. This reduces the workload of teachers and improves students' learning effectiveness. Furthermore, by incorporating a scoring unit that automatically scores the input answers and an emotion recognition unit that recognizes students' emotions in real time and adaptively generates explanations and supplementary questions based on them, appropriate feedback can be provided in response to individual learning needs, enabling efficient educational support.

[1275] "Generation means" refers to a function that automatically generates homework and exam questions based on the subject and difficulty level selected by the teacher.

[1276] "Distribution means" refers to the function of distributing generated homework and exam questions to student devices.

[1277] "Input means" refers to the interface through which students use their devices to input their answers.

[1278] "Scoring means" refers to a function that automatically scores the answers entered.

[1279] "Result notification means" refers to the function of instantly returning grading results to students' devices.

[1280] "Explanation generation means" refers to the function that generates explanations and correction questions for incorrect parts as needed and displays them on the student's device.

[1281] "Emotion recognition means" refers to the function of recognizing students' emotions in real time and adaptively generating explanations and supplementary questions based on that.

[1282] "Storage means" refers to the function of storing generated homework and test questions, students' answers, and grading results in a database.

[1283] This invention is a system that allows teachers to efficiently generate, distribute, grade, and provide feedback on homework and exam questions, and it also maximizes learning effectiveness by combining it with an emotion engine that recognizes students' emotions and provides appropriate explanations and remedial questions based on those emotions.

[1284] Overall system configuration

[1285] The system mainly consists of the following components:

[1286] 1. Server

[1287] 2. Teacher's device

[1288] 3. Student Devices

[1289] 4. Emotion Engine

[1290] Teacher's device

[1291] A user (teacher) logs in to the system using the teacher's terminal and sends a request to generate homework or exam questions. Specifically, the user selects a subject (e.g., mathematics) and a level of difficulty (e.g., intermediate level) and clicks the "Generate" button.

[1292] server

[1293] The server receives the teacher's request and passes the request information to the generative AI model. The server then sends a request to the AI ​​model to generate "intermediate level" math questions. The generative AI model used uses a general-purpose generative AI framework. Specifically, it includes large-scale language models such as GPT-4. An example of a prompt sentence is "Please generate intermediate level math test questions."

[1294] The server stores the generated questions in a database, which includes the question text, correct answers, explanations, etc. The server then sends the generated questions back to the teacher's device so that the teacher can check them.

[1295] Teacher's device

[1296] The user (teacher) checks the generated questions and makes corrections or additional comments as necessary, thereby maintaining the accuracy and appropriateness of the questions.

[1297] server

[1298] After the teacher has finalized the questions, the server sends a request to distribute the questions to the students' devices. The server retrieves the student's ID and class information from the database and distributes the questions.

[1299] Student devices

[1300] The user (student) logs in to the student's terminal and accesses the distributed questions. An interface for answering the questions is displayed, and the user inputs their answers.

[1301] The student's device sends the entered answers to the server, which receives the answers and stores them in a database.

[1302] server

[1303] The server automatically grades the answers using an AI model based on the saved answers. The server compares the correct answers with the student's answers and generates a score. This score is recorded for each student and stored in a database.

[1304] The server returns the scoring results to the student's terminal and also sends a request to the explanation generation means to generate detailed explanations and correction questions for the incorrect parts. The explanation generation means generates explanations and correction questions as needed and returns them to the server. An example of a specific prompt sentence is "Please explain in detail the differences between the student's answer below and the correct answer: [differences between the student's answer and the correct answer]."

[1305] Emotion Engine

[1306] The emotion engine recognizes students' emotions in real time while they are typing their answers. For example, it analyzes facial expressions and tone of voice via a camera or microphone to determine the user's emotional state. The emotion engine performs its analysis using an AI model using Python's OpenCV and TensorFlow.

[1307] The emotion engine sends the detected emotion information to the server, and adaptively generates the next explanation or remedial question based on that information. For example, if the user is "confused," the engine can provide a more detailed explanation, and if the server recognizes that the user "understands," the engine can proceed to the next question.

[1308] The emotion engine also recognizes teachers' emotions and provides alerts and guidance to help them manage stress and reduce their workload.

[1309] This system is expected to significantly reduce the workload of teachers and improve student learning outcomes. In addition, by recognizing the emotions of students and teachers, more personalized learning support will be possible, improving the efficiency of the entire learning process.

[1310] The flow of the identification process in the second embodiment will be described with reference to FIG.

[1311] Step 1:

[1312] The user (teacher) logs in to the system using the teacher's terminal. They enter their username and password as input and send this information to the server. The server compares the entered information with the database, and if authentication is successful, the teacher's home screen is displayed.

[1313] Step 2:

[1314] The user (teacher) requests the generation of homework or exam questions on the home screen. Specifically, the user selects the subject (e.g., mathematics) and difficulty level (e.g., intermediate level) and clicks the "Generate" button. This selection information is sent as input to the server.

[1315] Step 3:

[1316] The server receives a generation request from the teacher. As input, it obtains the requested information on subject and difficulty level and passes it to the generative AI model. It then sends a "Mathematics" "Intermediate" problem generation prompt to the generative AI model. An example of this prompt is "Please generate intermediate level math test questions."

[1317] Step 4:

[1318] The generative AI model receives prompts from the server and generates questions. It receives the prompt as input, processes data, and performs data calculations to generate a problem set that includes the question, correct answer, explanation, etc. The generated problem set is output to the server.

[1319] Step 5:

[1320] The server receives the problem set from the generative AI model and stores it in a database. The problem set is received as input and stored in a table containing the problem ID, problem statement, correct answer, and explanation.

[1321] Step 6:

[1322] The server returns the generated problem set to the teacher's terminal. The server takes the saved problem set as input and sends it to the teacher's terminal. The generated problem is displayed on the teacher's terminal.

[1323] Step 7:

[1324] The user (teacher) checks the generated questions, makes corrections or adds comments as necessary, edits the questions displayed as input, and sends the corrections from the terminal to the server. The server then saves the corrected question set back into the database.

[1325] Step 8:

[1326] The server requests the distribution of questions determined by the teacher to the student's device. It obtains the student's ID and class information from the database as input and distributes the questions. It then sends this distribution information to the student's device.

[1327] Step 9:

[1328] The user (student) logs in to their device and accesses the distributed questions. The login information is sent from the device to the server as input, and if authentication is successful, the question display screen is output.

[1329] Step 10:

[1330] The user (student) inputs the answer to the displayed question. The answer information is entered into the terminal as input, and the answer content is sent to the server. The terminal also sends this answer information to the emotion engine in real time.

[1331] Step 11:

[1332] The server receives the student's answers and stores them in a database. The server takes the answer information as input and stores it in a database.

[1333] Step 12:

[1334] The server automatically scores the students' answers using a generative AI model based on the saved answers. It compares the correct answer data with the students' answers as input, performs data calculations, and generates a score. This score is then output to a database.

[1335] Step 13:

[1336] The server returns the marking results to the student's device and sends a request to the explanation generation means to generate detailed explanations and correction questions for the incorrect parts.The server takes the marking results as input and sends an explanation generation prompt to the generative AI model.

[1337] Step 14:

[1338] The explanation generation means uses a prompt sentence to make the generative AI model generate detailed explanations and remedial questions. It sends the prompt "Please explain in detail the difference between the student's answer below and the correct answer" as input, and outputs the generated explanation to the server.

[1339] Step 15:

[1340] The server returns the generated explanations and supplementary questions to the student's device. The server receives explanation data as input and sends it to the student's device. The specific explanations and supplementary questions are displayed on the student's device.

[1341] Step 16:

[1342] The emotion engine recognizes students' emotions in real time while they are typing their answers. It analyzes facial expressions and tone of voice collected via a camera and microphone as input, and outputs the analysis results to a server.

[1343] Step 17:

[1344] The emotion engine sends the detected emotion information to the server and adaptively generates explanations and remedial questions based on that information. For example, if a student is "confused," it generates a prompt to provide a detailed explanation. It takes the emotion information as input and sends the prompt to the generative AI model to generate an adaptive explanation. As a result, a detailed explanation or instructions to proceed to the next question are output to the student's device.

[1345] (Application example 2)

[1346] 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."

[1347] In today's world, the burden on teachers in the educational field is increasing. Furthermore, in brick-and-mortar stores, the demand for customer service that meets customer needs is increasing the workload on store clerks. It is becoming increasingly difficult for teachers to efficiently generate, distribute, grade, and provide feedback on homework and exam questions, and for store clerks to respond quickly and appropriately to customer emotions. Furthermore, conventional systems have difficulty accurately reading and responding to the emotions of users (teachers and store clerks), resulting in a lack of systems that maximize learning outcomes and customer service efficiency. There is a need to solve these issues, reduce the workload on teachers and store clerks, and provide personalized support to users (students and customers).

[1348] 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: a generation unit that generates homework and test questions based on the subject and difficulty level selected by the teacher; a distribution unit that distributes the generated homework and test questions to students' digital devices; an input unit that allows students to input answers using their digital devices; a scoring unit that automatically grades the entered answers; a result notification unit that instantly returns the graded results to the students' devices; an explanation generation unit that generates explanations and correction questions for incorrect sections as needed and displays them on the students' devices; an emotion recognition unit that recognizes emotions based on customer questions, images, and voices and generates responses based on the emotions; a response generation unit that generates and displays appropriate product explanations and suggestions based on the customer's emotions; and a notification unit that displays the generated questions and responses on the digital devices of store clerks. This reduces the burden on teachers in educational settings and improves students' learning outcomes. Furthermore, in physical stores, appropriate responses based on customer emotions can be quickly provided, thereby improving customer satisfaction.

[1349] "Generation means" refers to a device or program for generating homework and test questions based on the subject and level of difficulty selected by the teacher.

[1350] "Distribution means" refers to a device or program for distributing generated homework and exam questions to students' digital devices.

[1351] "Input means" refers to the device or interface that allows students to input answers using a digital device.

[1352] "Scoring means" refers to a device or program for automatically scoring the answers entered.

[1353] "Result notification means" refers to a device or program that instantly returns the grading results to the student's device.

[1354] "Explanation generation means" refers to a device or program that generates explanations and correction questions for incorrect parts as needed and displays them on the student's device.

[1355] "Emotion recognition means" refers to devices or programs that recognize emotions based on customer questions, images, and voices.

[1356] The "response generation means" refers to a device or program for generating and displaying appropriate product descriptions and suggestions based on the customer's emotions.

[1357] "Notification means" refers to a device or program for displaying the generated questions and responses on the store clerk's digital device.

[1358] To implement this invention, a server, a teacher's terminal, a student's terminal, an emotion engine, and a database are required. The following describes specific embodiments of the invention.

[1359] Overall system configuration

[1360] server

[1361] The server includes the following means:

[1362] Generator: Generate homework and exam questions based on teacher-selected subjects and difficulty levels. This process is driven by a generative AI model.

[1363] Distribution: Distributing generated homework and exam questions to students' digital devices.

[1364] Scoring: Automatically score student-entered answers.

[1365] Results notification: Grading results are instantly sent back to student devices.

[1366] Explanation generation means: Explanations and correction questions for incorrect parts are generated and displayed on the student's device.

[1367] Emotion recognition: Recognizes emotions based on customer questions, images, and voice. For this, we use an emotion engine.

[1368] Response generation means: Generate and display appropriate product descriptions and suggestions based on customer sentiment.

[1369] Teacher's device

[1370] Teacher devices have the following features:

[1371] Ability for teachers to submit requests to generate homework and exam questions.

[1372] Ability to review generated issues and make corrections or additions.

[1373] Student devices

[1374] Student devices have the following features:

[1375] Ability to access distributed questions and enter answers.

[1376] A function to receive scoring results and explanations.

[1377] Emotion Engine

[1378] The emotion engine has the following features:

[1379] Ability to recognize user emotions in real time.

[1380] A function that generates appropriate explanations and supplementary questions based on emotional information.

[1381] Specific use cases

[1382] If a teacher wants to generate intermediate-level math exam questions, they send a request to the server from their own device, selecting the subject "Mathematics" and the difficulty level "Intermediate." The server then invokes the generative AI model, generates an appropriate set of questions, and sends them back to the teacher's device. After the teacher checks the generated questions, they distribute them to students. Students answer the questions using their digital devices and send their answers to the server. The server automatically grades the answers and provides instant feedback, while the emotion engine provides detailed explanations and remedial questions based on the students' emotional information.

[1383] A similar system can also be used in physical stores. In response to customer questions, store clerks can provide appropriate responses while recognizing the customer's emotions. For example, if a customer asks, "Tell me about this product," the emotion engine reads the customer's emotions from their image and voice. Based on this, the generative AI model generates the optimal response, which is displayed on the clerk's device.

[1384] Prompt Sentence Examples

[1385] "A customer asks, 'Tell me about this product.' The customer's emotion is 'Confused.' Generate an appropriate response."

[1386] In this way, this invention is a system that can generate appropriate questions and provide individualized responses based on emotions in educational settings and brick-and-mortar stores.

[1387] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[1388] Step 1:

[1389] A request is sent from the teacher's terminal to the server to generate homework or exam questions based on the subject and difficulty level selected by the teacher. Here, the input is the subject and difficulty level selected by the teacher, and the server side calls the generative AI model based on this. In this process, the server passes the selection information to the generative AI model and uses it as a prompt for question generation.

[1390] Step 2:

[1391] The server uses a generative AI model to generate homework and exam questions. Based on the input data (selected subjects and difficulty level), the generative AI model generates a problem set. Here, the generative AI model generates questions using prompts such as "math" or "intermediate" and sends the results back to the server. The server receives the generated results: the problem statement, correct answers, and explanations.

[1392] Step 3:

[1393] The generated homework and exam questions are sent back from the server to the teacher's terminal, where the teacher can review them and add corrections or comments. The input is the generated question set, and the output is the question set edited by the teacher.

[1394] Step 4:

[1395] Once the teacher has finalized the problem set, the information is sent to the server again. The server saves the finalized problem set in the database and prepares it for distribution to the students' devices. The input is the finalized problem set, and the output is a notification that it is ready to be saved in the database and distributed.

[1396] Step 5:

[1397] The student's device accesses the distributed questions and inputs the answers. At this stage, an interface is displayed for the student to answer the questions. The input is the student's answer, and the output is the answer data.

[1398] Step 6:

[1399] The answers are sent from the student's terminal to the server. The server stores the received answers in a database and then automatically grades them using a grading tool. The input is the student's answer data, and the output is the graded results.

[1400] Step 7:

[1401] The server stores the grading results in a database and sends the results back to the student's device using a result notification means. The input is the grading results and the output is a notification to the student's device.

[1402] Step 8:

[1403] Next, the explanation generation means generates explanations and correction questions for the incorrect parts. The server sends the generated explanations and correction questions to the student's terminal. The input is the grade data and incorrect answers, and the output is the generated explanations and correction questions.

[1404] Step 9:

[1405] In parallel, an emotion recognition means is used to recognize emotions based on the customer's question, image, and voice, where the input is the customer's question, facial expression image, and voice data, and the output is the recognized emotional state.

[1406] Step 10:

[1407] Based on the emotion recognition results, the response generation means generates appropriate product descriptions and suggestions. The server then sends the generated responses to the salesperson's terminal. The input is the customer's question and emotional state, and the output is the generated responses.

[1408] Step 11:

[1409] The generated questions and responses are displayed on the salesperson's terminal, and the salesperson responds to the customer based on them. Here, the input is the generated response sentence, and the output is the information that the salesperson provides to the customer.

[1410] In this way, the system generates appropriate questions and provides personalized, emotion-based responses in educational settings and brick-and-mortar stores.

[1411] 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.

[1412] 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.

[1413] 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.

[1414] [Fourth embodiment]

[1415] FIG. 7 shows an example of the configuration of a data processing system 410 according to the fourth embodiment.

[1416] 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.

[1417] 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).

[1418] 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.

[1419] 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.

[1420] 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).

[1421] 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.

[1422] 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.

[1423] 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.

[1424] 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.

[1425] 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.

[1426] 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.

[1427] 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."

[1428] The present invention is a system that enables teachers to efficiently generate, distribute, grade, and provide feedback on homework and test questions, and has the following specific embodiments.

[1429] Overall system configuration

[1430] The system mainly consists of the following components:

[1431] 1. Server

[1432] 2. Teacher's device

[1433] 3. Student Devices

[1434] Teacher's device

[1435] 1. A user (teacher) logs in to the system using the teacher's terminal and sends a request to generate homework or exam questions. Specifically, the user selects a subject (e.g., mathematics) and difficulty level (e.g., intermediate level) and sends a request to the system.

[1436] server

[1437] 1. The server receives the teacher's request and passes the request information to the generative AI model, which then generates appropriate homework and exam questions based on the specified subject and difficulty level.

[1438] 2. The server stores the generated questions in a database, which includes the question text, correct answers, explanations, etc. The server then sends the generated questions back to the teacher's device so that the teacher can check them.

[1439] Teacher's device

[1440] 1. The user (teacher) checks the generated questions and makes corrections or additional comments as necessary, thereby maintaining the accuracy and appropriateness of the questions.

[1441] server

[1442] 1. After the teacher has finalized the questions, the server requests that the questions be distributed to the students' devices. The questions are distributed based on the student ID and class information.

[1443] Student devices

[1444] 1. The user (student) logs in to their device and accesses the distributed questions. An interface for answering the questions is displayed, and the user enters their answers.

[1445] 2. The student's device sends the entered answers to the server, which receives and stores the answers.

[1446] server

[1447] 1. The server automatically scores the questions using an AI model based on the saved answers. It compares the correct answers with the student's answers and generates a score. This score is recorded for each student and stored in a database.

[1448] 2. The server sends the scoring results back to the student's device and also generates detailed explanations and correction questions for any mistakes.

[1449] Student devices

[1450] 1. The student's device will display the graded results, explanations, and supplementary questions to the student, allowing them to quickly and effectively check their learning progress and review any necessary sections.

[1451] Specific use cases

[1452] For example, if a teacher wants to generate intermediate-level mathematics exam questions, the teacher sends a request from their device to the server, selecting the subject "Mathematics" and the difficulty level "Intermediate." The server then invokes the generative AI model, generates an appropriate set of questions, and sends them back to the teacher's device. After the teacher checks the generated questions, they distribute them to students. Students then answer the questions using their digital devices and send their answers to the server. The server automatically grades the answers, providing instant feedback and explanations or remedial questions as needed.

[1453] This system is expected to significantly reduce the workload of teachers and improve students' learning outcomes.

[1454] The processing flow will be explained below.

[1455] Step 1:

[1456] A user (teacher) logs in to the system using the teacher's terminal and sends a request to generate homework or exam questions. Specifically, the user selects a subject (e.g., mathematics) and a level of difficulty (e.g., intermediate level) and clicks the "Generate" button.

[1457] Step 2:

[1458] The teacher's terminal sends a request to the server including the subject and difficulty level information input by the user.

[1459] Step 3:

[1460] The server receives requests from the teacher's device and passes the request information to the generative AI model. The server then sends a "Mathematics" "Intermediate" problem generation request to the AI ​​model.

[1461] Step 4:

[1462] The generative AI model generates appropriate homework and exam questions based on the subject and level of difficulty, including the question statement, correct answers, and explanations.

[1463] Step 5:

[1464] The server stores the generated questions in a database, which includes information such as the question, the correct answer, and an explanation.

[1465] Step 6:

[1466] The server sends the generated questions back to the teacher's terminal, where the teacher can check the questions.

[1467] Step 7:

[1468] The user (teacher) checks the generated questions and makes corrections or additional comments as necessary. Once the teacher reviews and confirms the questions, the questions based on this are sent to the server.

[1469] Step 8:

[1470] After the teacher has finalized the questions, the server sends a request to distribute the questions to the students' devices. The server retrieves the student's ID and class information from the database and distributes the questions.

[1471] Step 9:

[1472] The user (student) logs in to the student's terminal and accesses the distributed questions. An interface for answering the questions is displayed, and the user inputs their answers.

[1473] Step 10:

[1474] The student's device sends the answers entered by the user (student) to the server, which receives the answers and stores them in a database.

[1475] Step 11:

[1476] The server automatically grades the questions using an AI model based on the stored answers. The server compares the correct answers with the student's answers and generates a score.

[1477] Step 12:

[1478] The server returns the graded results to the student's terminal and also sends a request to the explanation generation means to generate detailed explanations and correction questions for the incorrect parts.

[1479] Step 13:

[1480] The explanation generating means generates explanations and correction questions as needed and sends them back to the server.

[1481] Step 14:

[1482] The server sends explanations and supplementary questions to the students' devices and records them in a database as logs.

[1483] Step 15:

[1484] The user (student) can check the grades, explanations, and supplementary questions on their own device, allowing them to check their own understanding and review any necessary parts.

[1485] Example 1

[1486] 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."

[1487] In conventional educational systems, teachers manually create homework and exam questions, distribute them to students, and then grade and provide feedback, requiring a great deal of time and effort. This cumbersome process reduces teachers' work efficiency and hinders their ability to provide prompt feedback to students. Furthermore, the balance between question content and difficulty level is inconsistent, making it difficult to provide personalized support based on each student's learning progress. To address these issues, the present invention aims to provide a system that automates teachers' work and provides appropriate and prompt feedback to students.

[1488] 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.

[1489] In this invention, the server includes a generating means for generating homework and test questions based on the subject and difficulty level selected by the teacher, a distributing means for distributing the generated homework and test questions to the students' digital devices, an input means for the students to input answers using their digital devices, a sending and saving means for sending the input answers to the server and saving them, a scoring means for automatically scoring the saved answers, a result notifying means for returning the scoring results to the students' digital devices, and an explanation generating means for generating explanations and correction questions for incorrect parts as needed and displaying them on the students' digital devices. This reduces the workload on teachers and enables them to provide students with quick and appropriate feedback.

[1490] "Generative means" refers to a function that automatically generates homework and exam questions using an AI model based on the subject and difficulty level selected by the teacher.

[1491] "Distribution means" refers to the function of sending generated homework and exam questions to students' digital devices in an appropriate format.

[1492] "Input means" refers to the interface and functionality that allows students to input answers to homework and exam questions using digital devices.

[1493] The "transmission and storage means" is a function that sends the answers entered by the students to the server and stores them in a database.

[1494] The "scoring method" is a function that automatically scores answers stored on the server using an AI model to generate a score.

[1495] "Result notification means" is a function that quickly returns graded results to students' digital devices.

[1496] The "explanation generation means" is a function that generates explanations and correction questions for incorrect parts as needed and displays them on the student's digital device.

[1497] "Storage means" is a function that stores generated homework and test questions, students' answers, and grading results in a database, allowing the information to be retrieved later.

[1498] The present invention is a system for teachers to efficiently generate, distribute, grade, and provide feedback on homework and exam questions. The system comprises the following components:

[1499] Overall system configuration

[1500] The main components of the system are:

[1501] 1. Server

[1502] 2. Teacher's device

[1503] 3. Student Devices

[1504] Teacher's device

[1505] Users (teachers) log in to the system from their own devices via an internet browser and use a dedicated application (e.g., a UI built with React) to send a request to the server to generate homework or exam questions. The teacher selects the subject (e.g., mathematics) and difficulty level (e.g., intermediate), and presses the generate button, which sends the request to the server. An example of a prompt sentence is "Please create intermediate-level mathematics exam questions."

[1506] server

[1507] The server has a backend system written in Python that receives requests, analyzes them, and sends prompts to an AI model (e.g., OpenAI GPT-3), which then generates an appropriate problem set based on the specified subject and difficulty level.

[1508] The generated problem set is sent back to the server in JSON format, which stores it in a MySQL database. The stored data includes the problem statement, correct answers, and explanations. The generated problem set is then sent back to the teacher's computer.

[1509] Teacher's device

[1510] The user (teacher) checks the generated questions and, if necessary, edits the question text and explanations using a rich text editor (e.g., Quill.js). Once the edits are complete, the user presses the confirm button to send a request to the server to save the changes.

[1511] server

[1512] The server then obtains a list of students based on their IDs and class information to distribute the finalized questions to them. At this time, the questions are again organized in JSON format and sent to the students' devices.

[1513] Student devices

[1514] Users (students) log in to their own devices and access the distributed questions. An interface built with Angular is displayed on the student's device, allowing the user to enter answers to the questions.

[1515] server

[1516] The student's device sends the entered answers in JSON format to the server. The server receives them and stores them in a MySQL database. Then, based on the saved answers, an AI model (e.g., TensorFlow) is used again to automatically grade the answers. The correct answer is compared with the student's answer, a score is generated, and the score is recorded in the database.

[1517] The graded results are quickly returned to the student's digital device, and feedback and correction questions are generated and sent to the student's device for any errors.

[1518] Student devices

[1519] The student's device displays the feedback, explanations, and revision questions received from the server to the user (student). The student can refer to this to check their own learning progress and review the material as appropriate.

[1520] Specific examples

[1521] For example, if a teacher wants to generate intermediate-level math exam questions, they send a prompt request to the server saying, "Please create intermediate-level math exam questions." The server uses OpenAI GPT-3 to generate the questions and stores the results in a MySQL database. The questions are sent back to the teacher's device, where the teacher can review and correct them before distributing them to the students. Students then submit their answers to the server through an interface, and the server uses TensorFlow to grade them and provide instant feedback.

[1522] The present invention significantly reduces the workload of teachers, provides students with prompt and appropriate feedback, and improves learning effectiveness.

[1523] The flow of the identification process in the first embodiment will be described with reference to FIG.

[1524] Step 1:

[1525] A user (teacher) logs into the system using a dedicated application (e.g., a UI built with React). The teacher selects the subject (e.g., mathematics) and difficulty level (e.g., intermediate) from drop-down menus and presses the generate button. This action sends a generation request to the server.

[1526] Input: Selection information as subject and difficulty level.

[1527] Output: The generated request sent to the server.

[1528] Step 2:

[1529] The server receives the teacher's request and analyzes it. Based on the analyzed request information, the server sends a prompt message to the generative AI model (e.g., OpenAI GPT-3) asking it to generate questions: "Please create intermediate-level math exam questions."

[1530] Input: Subject and difficulty level as generation request.

[1531] Output: The prompt sent to the generative AI model.

[1532] Step 3:

[1533] The generative AI model generates questions appropriate for the specified subject and level of difficulty based on the prompt text, and the generated question set is sent back to the server in JSON format.

[1534] Input: The prompt statement.

[1535] Output: The generated problem set.

[1536] Step 4:

[1537] The server stores the received problem set in JSON format in a MySQL database. The stored data includes the problem statement, correct answer, and explanation. The server then sends the problem set to the teacher's device.

[1538] Input: The generated problem set.

[1539] Output: The problem set sent to the teacher's device.

[1540] Step 5:

[1541] The user (teacher) checks the questions generated on the device and, if necessary, edits the questions and explanations using a rich text editor (e.g., Quill.js). Once edits are complete, the teacher presses the confirm button to send the revised question set to the server.

[1542] Input: Problem set and correction information.

[1543] Output: The revised problem set that is sent to the server.

[1544] Step 6:

[1545] The server receives the revised questions, stores them in the MySQL database again, and then distributes the questions to students based on their IDs and class information.

[1546] Input: A revised problem set and student information.

[1547] Output: Questions distributed to student devices.

[1548] Step 7:

[1549] Users (students) log in to their own devices and access the distributed questions. Students enter their answers to the questions using an interface built with Angular.

[1550] Input: The distributed question.

[1551] Output: The answer entered by the student.

[1552] Step 8:

[1553] The student's device sends the entered answers in JSON format to the server, which receives them and stores them in a MySQL database.

[1554] Input: Student answers.

[1555] Output: The answer sent to the server and stored in the database.

[1556] Step 9:

[1557] The server automatically scores the answers using an AI model (e.g., TensorFlow) based on the saved answers, comparing the correct answers with the student's answers, generating a score and recording it in a database.

[1558] Input: Your saved answer.

[1559] Output: The resulting score.

[1560] Step 10:

[1561] The server generates feedback based on the scoring results, and also creates explanations and correction questions for incorrect answers, which are sent to the student's device.

[1562] Input: Scoring results.

[1563] Output: Feedback, explanations, and remedial questions.

[1564] Step 11:

[1565] The student's device displays the feedback, explanations, and revision questions received from the server to the user (student). The student can refer to this to check their own learning progress and review the material as appropriate.

[1566] Input: Feedback, explanations, and remedial questions.

[1567] Output: Feedback information displayed on student devices.

[1568] (Application example 1)

[1569] 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."

[1570] Traditionally, it takes a lot of time and effort for teachers to create homework and exam questions, distribute them to students, and then grade and provide feedback. Furthermore, stores selling education-related products require a lot of time and effort to provide detailed explanations and demonstrations of their products and services, and it is difficult to quickly provide services such as creating homework questions and providing instant grading. This places a heavy burden on teachers and store staff, making it difficult to provide fast and effective feedback to students and customers.

[1571] 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.

[1572] In this invention, the server includes a generation unit that generates homework and test questions based on the subject and level of difficulty selected by the teacher, a distribution unit that distributes the generated homework and test questions to the students' computers, and an input unit that allows the students to input answers using their computers. This enables the processes of generating, distributing, grading, and providing feedback on homework and test questions to be carried out automatically and efficiently. Furthermore, by using store terminals in the store to explain educational products and services and to generate and demonstrate homework questions, the burden on store staff can be reduced, enabling the provision of fast and effective services to customers.

[1573] The "generation means" refers to a device or software that has the function of generating homework and test questions based on the subject and level of difficulty selected by the teacher.

[1574] The "distribution means" refers to a device or software that has the function of transmitting and distributing the generated homework and test questions to the students' computers.

[1575] "Input means" refers to the interface or software that allows students to input answers using a computer.

[1576] The "scoring means" refers to a device or software that has the function of automatically scoring the answers entered.

[1577] The "result notification means" is a device or software that has the function of instantly returning the grading results to the student's computer.

[1578] The "explanation generating means" is a device or software that has the function of generating explanations and correction questions for incorrect parts as needed and displaying them on the student's computer.

[1579] "Store terminal" refers to a device used in a store to explain educational products and services, generate homework questions, and provide demonstrations.

[1580] This invention is a system that allows teachers to efficiently generate, distribute, grade, and provide feedback on homework and exam questions, and has been improved to effectively introduce, explain, and demonstrate educational products and services in physical stores. The detailed configuration and operation of this system are described below.

[1581] Overall system configuration

[1582] The system mainly consists of the following components:

[1583] 1. Server

[1584] 2. Teacher's device

[1585] 3. Student Devices

[1586] 4. In-store terminals

[1587] Teacher's device

[1588] 1. A teacher logs in to the system using their terminal and sends a request to generate homework or exam questions. Specifically, the teacher selects the subject (e.g., mathematics) and difficulty level (e.g., intermediate level) and sends the request to the system.

[1589] server

[1590] 1. The server receives the teacher's request and passes the request information to the generative AI model, which then generates appropriate homework and exam questions based on the specified subject and difficulty level.

[1591] 2. The server saves the generated questions in a database, including the question text, correct answers, explanations, etc. The server then sends the generated questions back to the teacher's device so that the teacher can check them.

[1592] Teacher's device

[1593] 1. The teacher reviews the generated questions and makes corrections or additional comments as necessary to ensure the accuracy and appropriateness of the questions.

[1594] server

[1595] 1. After the teacher has finalized the questions, the server requests that the questions be distributed to the students' devices. The questions are distributed based on the student ID and class information.

[1596] Student devices

[1597] 1. Students log in to their devices and access the distributed questions. An interface for answering the questions is displayed, and students enter their answers.

[1598] 2. The student's device sends the entered answers to the server, which receives and stores the answers.

[1599] server

[1600] 1. The server automatically scores the questions using an AI model based on the saved answers. It compares the correct answers with the student's answers and generates a score. This score is recorded for each student and stored in a database.

[1601] 2. The server sends the scoring results back to the student's device and also generates detailed explanations and correction questions for any mistakes.

[1602] Student devices

[1603] 1. The student's device will display the graded results, explanations, and supplementary questions to the student, allowing them to quickly and effectively check their learning progress and review any necessary sections.

[1604] Physical store terminals

[1605] 1. The in-store terminals are used to explain educational products and services, generate homework questions, and demonstrate them. Sample homework questions can be generated and checked on the spot before customers purchase the requested products in the store.

[1606] 2. Promote educational software sales by instantly demonstrating curriculum on in-store tablets.

[1607] 3. A service can be developed for educational events and workshops that provides participants with generated homework and grades it on the spot.

[1608] Usage example

[1609] For example, if a teacher wants to generate intermediate-level mathematics exam questions, the teacher sends a request to the server from their device, selecting the subject "Mathematics" and the difficulty level "Intermediate." The server then invokes the generative AI model, generates an appropriate set of questions, and sends them back to the teacher's device. The teacher reviews the generated questions, corrects them if necessary, and then distributes them to students. Students then answer the questions using their digital devices and send the answers to the server. The server automatically grades the answers, provides instant feedback, and provides explanations and remedial questions as needed. Furthermore, customers can try out the features of educational products and services when purchasing them in physical stores.

[1610] Prompt Sentence Examples

[1611] "Generate intermediate level math homework problems."

[1612] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[1613] Step 1:

[1614] The teacher terminal displays an interface for the user (teacher) to select the subject and difficulty level. The teacher terminal receives the subject and difficulty level information entered by the user and sends a request to the server.

[1615] Input: Subject (e.g., Math), Difficulty (e.g., Intermediate)

[1616] Data processing: Convert form data into JSON format

[1617] Output: Request to server

[1618] Step 2:

[1619] The server receives requests sent from the teacher device, analyzes the received data, and provides the necessary information for the generative AI model.

[1620] Input: Subject and difficulty request (JSON format)

[1621] Data processing: Analyzes request data and generates prompts

[1622] Output: A request to the generative AI model

[1623] Step 3:

[1624] The generative AI model generates homework and exam questions based on requests received from the server.

[1625] Input: Parsed prompt ("Generate intermediate level math homework problems.")

[1626] Data calculation: Generative AI model generates question, answer, and explanation

[1627] Output: Generated homework questions (question statement, answer, explanation, etc.)

[1628] Step 4:

[1629] The server stores the generated questions in a database and returns the stored questions to the teacher's terminal.

[1630] Input: Generated homework questions

[1631] Data processing: Data storage in the database and data generation for sending to the teacher's terminal

[1632] Output: Database update, response to teacher terminal

[1633] Step 5:

[1634] The teacher's terminal displays the received homework questions to the user, who then checks the questions and makes corrections or additional comments as necessary.

[1635] Input: Homework question sent from the server

[1636] Data processing: Converting data into a format suitable for display on the screen

[1637] Output: Teacher confirmation and correction data

[1638] Step 6:

[1639] The teacher's terminal sends the confirmed homework questions to the server again.

[1640] Input: Confirmed homework question

[1641] Data processing: Convert the complete problem set, including teacher correction data, into JSON format

[1642] Output: Send to server

[1643] Step 7:

[1644] The server makes a request to distribute the determined homework problems to the student's terminal.

[1645] Input: Confirmed homework question

[1646] Data processing: Adding student ID and class information to be distributed

[1647] Output: Distribution request to student devices

[1648] Step 8:

[1649] The student terminal receives the distributed homework questions and displays an interface for the user (student) to answer the questions.

[1650] Input: Homework question sent from the server

[1651] Data processing: generating an interface for answers

[1652] Output: Student answer data

[1653] Step 9:

[1654] The server receives the answer data sent from the student terminal and automatically grades it.

[1655] Input: Student answer data

[1656] Data calculation: Automatic scoring by comparing with correct data

[1657] Output: Scoring results

[1658] Step 10:

[1659] The server sends the results of the marks to the student's terminal, and also generates and displays explanations of the incorrect parts and correction questions.

[1660] Input: Marking results and answer data

[1661] Data calculation: Error analysis and repair problem generation

[1662] Output: Detailed feedback to student devices

[1663] Step 11:

[1664] The terminals in the physical stores provide an interface for explaining educational products and services, generating homework questions, and running demonstrations.

[1665] Input: Store staff or customer request

[1666] Data Computing: Generating demo homework problems using generative techniques

[1667] Output: Instant feedback and demo execution for the customer

[1668] 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.

[1669] This invention is a system that allows teachers to efficiently generate, distribute, grade, and provide feedback on homework and exam questions, and it also maximizes learning effectiveness by combining it with an emotion engine that recognizes the user's emotions and provides appropriate explanations and revision questions based on those emotions. Specific embodiments of this system are described below.

[1670] Overall system configuration

[1671] The system mainly consists of the following components:

[1672] 1. Server

[1673] 2. Teacher's device

[1674] 3. Student Devices

[1675] 4. Emotion Engine

[1676] Teacher's device

[1677] 1. A user (teacher) logs in to the system using the teacher's terminal and sends a request to generate homework or exam questions. Specifically, the user selects a subject (e.g., mathematics) and difficulty level (e.g., intermediate level) and clicks the "Generate" button.

[1678] server

[1679] 1. The server receives the teacher's request and passes the request information to the generative AI model. The server then sends a "Mathematics" "Intermediate" problem generation request to the AI ​​model.

[1680] 2. The server stores the generated questions in a database, which includes the question text, correct answers, explanations, etc. The server then sends the generated questions back to the teacher's device so that the teacher can check them.

[1681] Teacher's device

[1682] 1. The user (teacher) checks the generated questions and makes corrections or additional comments as necessary, thereby maintaining the accuracy and appropriateness of the questions.

[1683] server

[1684] 1. After the teacher has finalized the questions, the server sends a request to distribute the questions to the students' devices. The server retrieves the student's ID and class information from the database and distributes the questions.

[1685] Student devices

[1686] 1. The user (student) logs in to their device and accesses the distributed questions. An interface for answering the questions is displayed, and the user enters their answers.

[1687] 2. The student's device sends the entered answer to the server, which receives the student's answer and stores it in a database.

[1688] server

[1689] 1. The server automatically scores the students using an AI model based on their saved answers. The server compares the correct answers with the students' answers and generates a score. This score is recorded for each student and stored in a database.

[1690] 2. The server returns the results of the marks to the student's terminal and also sends a request to the explanation generation means to generate detailed explanations and correction questions for the incorrect parts.

[1691] 3. The explanation generation means generates explanations and correction questions as needed and sends them back to the server.

[1692] Emotion Engine

[1693] 1. The emotion engine recognizes the user's emotions in real time while the student is entering their answers. For example, it analyzes facial expressions and tone of voice via a camera or microphone to determine the user's emotional state.

[1694] 2. The emotion engine sends the detected emotion information to the server, and adaptively generates the next explanation or remedial question based on that information. For example, if the user is "confused," it can provide a more detailed explanation, and if the user is recognized as "understanding," it can proceed to the next question.

[1695] 3. The emotion engine also recognizes teachers' emotions and provides alerts and guidance to help teachers manage stress and reduce their workload.

[1696] Specific use cases

[1697] For example, if a teacher wants to generate intermediate-level mathematics exam questions, the user (teacher) sends a request from their own device to the server, selecting the subject "Mathematics" and difficulty level "Intermediate." The server then invokes the generative AI model, generates an appropriate set of questions, and sends them back to the teacher's device. After the teacher checks the generated questions, they distribute them to students. The user (student) answers the questions using a digital device and sends the answers to the server. The server automatically grades the answers and provides instant feedback, while the emotion engine provides detailed explanations and remedial questions based on the student's emotional information.

[1698] This system is expected to significantly reduce the workload of teachers and improve students' learning outcomes. In addition, by recognizing users' emotions, it will enable more personalized learning support, improving the efficiency of the entire learning process.

[1699] The processing flow will be explained below.

[1700] Step 1:

[1701] A user (teacher) logs in to the system using the teacher's terminal and sends a request to generate homework or exam questions. Specifically, the user selects a subject (e.g., mathematics) and a level of difficulty (e.g., intermediate level) and clicks the "Generate" button.

[1702] Step 2:

[1703] The teacher's terminal sends a request to the server including the subject and difficulty level information input by the user.

[1704] Step 3:

[1705] The server receives the request from the teacher's device and passes the request information to the generation AI model. The server then sends a problem generation request for "Subject: Mathematics" and "Difficulty: Intermediate" to the AI ​​model.

[1706] Step 4:

[1707] The generative AI model generates appropriate homework and exam questions based on the subject and difficulty level specified, including the question statement, correct answers, and explanations.

[1708] Step 5:

[1709] The server stores the generated questions in a database, which includes the question text, correct answers, explanations, etc.

[1710] Step 6:

[1711] The server sends the generated questions back to the teacher's terminal, where the teacher can check the questions.

[1712] Step 7:

[1713] The user (teacher) checks the generated questions and makes corrections or additional comments as necessary, thereby maintaining the accuracy and appropriateness of the questions.

[1714] Step 8:

[1715] After the teacher has finalized the questions, the server sends a request to distribute the questions to the students' devices. The server retrieves the student's ID and class information from the database and distributes the questions.

[1716] Step 9:

[1717] The user (student) logs in to the student's terminal and accesses the distributed questions. An interface for answering the questions is displayed, and the user inputs their answers.

[1718] Step 10:

[1719] The student's device sends the answers entered by the user (student) to the server, which receives the answers and stores them in a database.

[1720] Step 11:

[1721] The server automatically grades the questions using an AI model based on the stored answers. The server compares the correct answers with the student's answers and generates a score.

[1722] Step 12:

[1723] The server returns the results of the marks to the student's terminal and also sends a request to the explanation generating means to generate detailed explanations and correction questions for the incorrect parts.

[1724] Step 13:

[1725] The explanation generating means generates explanations and correction questions as needed and sends them back to the server.

[1726] Step 14:

[1727] The user (student) can check the grades, explanations, and supplementary questions on their own device, allowing them to check their own understanding and review any necessary parts.

[1728] Step 15:

[1729] The emotion engine recognizes the user's emotions in real time while the student is typing their answers, for example by analyzing facial expressions and tone of voice via the camera and microphone to determine the user's emotional state.

[1730] Step 16:

[1731] The emotion engine sends the detected emotion information to the server, and adaptively generates the next explanation or remedial question based on that information. For example, if the user is "confused," the engine can provide a more detailed explanation, and if the server recognizes that the user "understands," the engine can proceed to the next question.

[1732] Step 17:

[1733] The emotion engine also recognizes teachers' emotions and provides alerts and guidance to help them manage stress and reduce their workload.

[1734] In this way, the system provides an optimal learning environment for both teachers and students, maximizing educational effectiveness.

[1735] Example 2

[1736] 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."

[1737] In conventional educational support systems, teachers often manually create, distribute, and grade homework and exam questions, placing a heavy burden on teachers. Furthermore, systems that provide appropriate feedback based on each student's learning progress and level of understanding are still insufficient. Furthermore, there are no systems that can recognize the emotions of students and teachers in real time and respond individually based on that, making it difficult to provide learning support that takes emotions into account.

[1738] 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.

[1739] In this invention, the server includes a generation unit that generates homework and test questions based on the subject and difficulty level selected by the teacher, a distribution unit that distributes the generated homework and test questions to students' devices, and an input unit that allows students to input answers using their devices. This reduces the workload of teachers and improves students' learning effectiveness. Furthermore, by incorporating a scoring unit that automatically scores the input answers and an emotion recognition unit that recognizes students' emotions in real time and adaptively generates explanations and supplementary questions based on them, appropriate feedback can be provided in response to individual learning needs, enabling efficient educational support.

[1740] "Generation means" refers to a function that automatically generates homework and exam questions based on the subject and difficulty level selected by the teacher.

[1741] "Distribution means" refers to the function of distributing generated homework and exam questions to student devices.

[1742] "Input means" refers to the interface through which students use their devices to input their answers.

[1743] "Scoring means" refers to a function that automatically scores the answers entered.

[1744] "Result notification means" refers to the function of instantly returning grading results to students' devices.

[1745] "Explanation generation means" refers to the function that generates explanations and correction questions for incorrect parts as needed and displays them on the student's device.

[1746] "Emotion recognition means" refers to the function of recognizing students' emotions in real time and adaptively generating explanations and supplementary questions based on that.

[1747] "Storage means" refers to the function of storing generated homework and test questions, students' answers, and grading results in a database.

[1748] This invention is a system that allows teachers to efficiently generate, distribute, grade, and provide feedback on homework and exam questions, and it also maximizes learning effectiveness by combining it with an emotion engine that recognizes students' emotions and provides appropriate explanations and remedial questions based on those emotions.

[1749] Overall system configuration

[1750] The system mainly consists of the following components:

[1751] 1. Server

[1752] 2. Teacher's device

[1753] 3. Student Devices

[1754] 4. Emotion Engine

[1755] Teacher's device

[1756] A user (teacher) logs in to the system using the teacher's terminal and sends a request to generate homework or exam questions. Specifically, the user selects a subject (e.g., mathematics) and a level of difficulty (e.g., intermediate level) and clicks the "Generate" button.

[1757] server

[1758] The server receives the teacher's request and passes the request information to the generative AI model. The server then sends a request to the AI ​​model to generate "intermediate level" math questions. The generative AI model used uses a general-purpose generative AI framework. Specifically, it includes large-scale language models such as GPT-4. An example of a prompt sentence is "Please generate intermediate level math test questions."

[1759] The server stores the generated questions in a database, which includes the question text, correct answers, explanations, etc. The server then sends the generated questions back to the teacher's device so that the teacher can check them.

[1760] Teacher's device

[1761] The user (teacher) checks the generated questions and makes corrections or additional comments as necessary, thereby maintaining the accuracy and appropriateness of the questions.

[1762] server

[1763] After the teacher has finalized the questions, the server sends a request to distribute the questions to the students' devices. The server retrieves the student's ID and class information from the database and distributes the questions.

[1764] Student devices

[1765] The user (student) logs in to the student's terminal and accesses the distributed questions. An interface for answering the questions is displayed, and the user inputs their answers.

[1766] The student's device sends the entered answers to the server, which receives the answers and stores them in a database.

[1767] server

[1768] The server automatically grades the answers using an AI model based on the saved answers. The server compares the correct answers with the student's answers and generates a score. This score is recorded for each student and stored in a database.

[1769] The server returns the scoring results to the student's terminal and also sends a request to the explanation generation means to generate detailed explanations and correction questions for the incorrect parts. The explanation generation means generates explanations and correction questions as needed and returns them to the server. An example of a specific prompt sentence is "Please explain in detail the differences between the student's answer below and the correct answer: [differences between the student's answer and the correct answer]."

[1770] Emotion Engine

[1771] The emotion engine recognizes students' emotions in real time while they are typing their answers. For example, it analyzes facial expressions and tone of voice via a camera or microphone to determine the user's emotional state. The emotion engine performs its analysis using an AI model using Python's OpenCV and TensorFlow.

[1772] The emotion engine sends the detected emotion information to the server, and adaptively generates the next explanation or remedial question based on that information. For example, if the user is "confused," the engine can provide a more detailed explanation, and if the server recognizes that the user "understands," the engine can proceed to the next question.

[1773] The emotion engine also recognizes teachers' emotions and provides alerts and guidance to help them manage stress and reduce their workload.

[1774] This system is expected to significantly reduce the workload of teachers and improve student learning outcomes. In addition, by recognizing the emotions of students and teachers, more personalized learning support will be possible, improving the efficiency of the entire learning process.

[1775] The flow of the identification process in the second embodiment will be described with reference to FIG.

[1776] Step 1:

[1777] The user (teacher) logs in to the system using the teacher's terminal. They enter their username and password as input and send this information to the server. The server compares the entered information with the database, and if authentication is successful, the teacher's home screen is displayed.

[1778] Step 2:

[1779] The user (teacher) requests the generation of homework or exam questions on the home screen. Specifically, the user selects the subject (e.g., mathematics) and difficulty level (e.g., intermediate level) and clicks the "Generate" button. This selection information is sent as input to the server.

[1780] Step 3:

[1781] The server receives a generation request from the teacher. As input, it obtains the requested information on subject and difficulty level and passes it to the generative AI model. It then sends a "Mathematics" "Intermediate" problem generation prompt to the generative AI model. An example of this prompt is "Please generate intermediate level math test questions."

[1782] Step 4:

[1783] The generative AI model receives prompts from the server and generates questions. It receives the prompt as input, processes data, and performs data calculations to generate a problem set that includes the question, correct answer, explanation, etc. The generated problem set is output to the server.

[1784] Step 5:

[1785] The server receives the problem set from the generative AI model and stores it in a database. The problem set is received as input and stored in a table containing the problem ID, problem statement, correct answer, and explanation.

[1786] Step 6:

[1787] The server returns the generated problem set to the teacher's terminal. The server takes the saved problem set as input and sends it to the teacher's terminal. The generated problem is displayed on the teacher's terminal.

[1788] Step 7:

[1789] The user (teacher) checks the generated questions, makes corrections or adds comments as necessary, edits the questions displayed as input, and sends the corrections from the terminal to the server. The server then saves the corrected question set back into the database.

[1790] Step 8:

[1791] The server requests the distribution of questions determined by the teacher to the student's device. It obtains the student's ID and class information from the database as input and distributes the questions. It then sends this distribution information to the student's device.

[1792] Step 9:

[1793] The user (student) logs in to their device and accesses the distributed questions. The login information is sent from the device to the server as input, and if authentication is successful, the question display screen is output.

[1794] Step 10:

[1795] The user (student) inputs the answer to the displayed question. The answer information is entered into the terminal as input, and the answer content is sent to the server. The terminal also sends this answer information to the emotion engine in real time.

[1796] Step 11:

[1797] The server receives the student's answers and stores them in a database. The server takes the answer information as input and stores it in a database.

[1798] Step 12:

[1799] The server automatically scores the students' answers using a generative AI model based on the saved answers. It compares the correct answer data with the students' answers as input, performs data calculations, and generates a score. This score is then output to a database.

[1800] Step 13:

[1801] The server returns the marking results to the student's device and sends a request to the explanation generation means to generate detailed explanations and correction questions for the incorrect parts.The server takes the marking results as input and sends an explanation generation prompt to the generative AI model.

[1802] Step 14:

[1803] The explanation generation means uses a prompt sentence to make the generative AI model generate detailed explanations and remedial questions. It sends the prompt "Please explain in detail the difference between the student's answer below and the correct answer" as input, and outputs the generated explanation to the server.

[1804] Step 15:

[1805] The server returns the generated explanations and supplementary questions to the student's device. The server receives explanation data as input and sends it to the student's device. The specific explanations and supplementary questions are displayed on the student's device.

[1806] Step 16:

[1807] The emotion engine recognizes students' emotions in real time while they are typing their answers. It analyzes facial expressions and tone of voice collected via a camera and microphone as input, and outputs the analysis results to a server.

[1808] Step 17:

[1809] The emotion engine sends the detected emotion information to the server and adaptively generates explanations and remedial questions based on that information. For example, if a student is "confused," it generates a prompt to provide a detailed explanation. It takes the emotion information as input and sends the prompt to the generative AI model to generate an adaptive explanation. As a result, a detailed explanation or instructions to proceed to the next question are output to the student's device.

[1810] (Application example 2)

[1811] 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."

[1812] In today's world, the burden on teachers in the educational field is increasing. Furthermore, in brick-and-mortar stores, the demand for customer service that meets customer needs is increasing the workload on store clerks. It is becoming increasingly difficult for teachers to efficiently generate, distribute, grade, and provide feedback on homework and exam questions, and for store clerks to respond quickly and appropriately to customer emotions. Furthermore, conventional systems have difficulty accurately reading and responding to the emotions of users (teachers and store clerks), resulting in a lack of systems that maximize learning outcomes and customer service efficiency. There is a need to solve these issues, reduce the workload on teachers and store clerks, and provide personalized support to users (students and customers).

[1813] 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: a generation unit that generates homework and test questions based on the subject and difficulty level selected by the teacher; a distribution unit that distributes the generated homework and test questions to students' digital devices; an input unit that allows students to input answers using their digital devices; a scoring unit that automatically grades the entered answers; a result notification unit that instantly returns the graded results to the students' devices; an explanation generation unit that generates explanations and correction questions for incorrect sections as needed and displays them on the students' devices; an emotion recognition unit that recognizes emotions based on customer questions, images, and voices and generates responses based on the emotions; a response generation unit that generates and displays appropriate product explanations and suggestions based on the customer's emotions; and a notification unit that displays the generated questions and responses on the digital devices of store clerks. This reduces the burden on teachers in educational settings and improves students' learning outcomes. Furthermore, in physical stores, appropriate responses based on customer emotions can be quickly provided, thereby improving customer satisfaction.

[1814] "Generation means" refers to a device or program for generating homework and test questions based on the subject and level of difficulty selected by the teacher.

[1815] "Distribution means" refers to a device or program for distributing generated homework and exam questions to students' digital devices.

[1816] "Input means" refers to the device or interface that allows students to input answers using a digital device.

[1817] "Scoring means" refers to a device or program for automatically scoring the answers entered.

[1818] "Result notification means" refers to a device or program that instantly returns the grading results to the student's device.

[1819] "Explanation generation means" refers to a device or program that generates explanations and correction questions for incorrect parts as needed and displays them on the student's device.

[1820] "Emotion recognition means" refers to devices or programs that recognize emotions based on customer questions, images, and voices.

[1821] The "response generation means" refers to a device or program for generating and displaying appropriate product descriptions and suggestions based on the customer's emotions.

[1822] "Notification means" refers to a device or program for displaying the generated questions and responses on the store clerk's digital device.

[1823] To implement this invention, a server, a teacher's terminal, a student's terminal, an emotion engine, and a database are required. The following describes specific embodiments of the invention.

[1824] Overall system configuration

[1825] server

[1826] The server includes the following means:

[1827] Generator: Generate homework and exam questions based on teacher-selected subjects and difficulty levels. This process is driven by a generative AI model.

[1828] Distribution: Distributing generated homework and exam questions to students' digital devices.

[1829] Scoring: Automatically score student-entered answers.

[1830] Results notification: Grading results are instantly sent back to student devices.

[1831] Explanation generation means: Explanations and correction questions for incorrect parts are generated and displayed on the student's device.

[1832] Emotion recognition: Recognizes emotions based on customer questions, images, and voice. For this, we use an emotion engine.

[1833] Response generation means: Generate and display appropriate product descriptions and suggestions based on customer sentiment.

[1834] Teacher's device

[1835] Teacher devices have the following features:

[1836] Ability for teachers to submit requests to generate homework and exam questions.

[1837] Ability to review generated issues and make corrections or additions.

[1838] Student devices

[1839] Student devices have the following features:

[1840] Ability to access distributed questions and enter answers.

[1841] A function to receive scoring results and explanations.

[1842] Emotion Engine

[1843] The emotion engine has the following features:

[1844] Ability to recognize user emotions in real time.

[1845] A function that generates appropriate explanations and supplementary questions based on emotional information.

[1846] Specific use cases

[1847] If a teacher wants to generate intermediate-level math exam questions, they send a request to the server from their own device, selecting the subject "Mathematics" and the difficulty level "Intermediate." The server then invokes the generative AI model, generates an appropriate set of questions, and sends them back to the teacher's device. After the teacher checks the generated questions, they distribute them to students. Students answer the questions using their digital devices and send their answers to the server. The server automatically grades the answers and provides instant feedback, while the emotion engine provides detailed explanations and remedial questions based on the students' emotional information.

[1848] A similar system can also be used in physical stores. In response to customer questions, store clerks can provide appropriate responses while recognizing the customer's emotions. For example, if a customer asks, "Tell me about this product," the emotion engine reads the customer's emotions from their image and voice. Based on this, the generative AI model generates the optimal response, which is displayed on the clerk's device.

[1849] Prompt Sentence Examples

[1850] "A customer asks, 'Tell me about this product.' The customer's emotion is 'Confused.' Generate an appropriate response."

[1851] In this way, this invention is a system that can generate appropriate questions and provide individualized responses based on emotions in educational settings and brick-and-mortar stores.

[1852] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[1853] Step 1:

[1854] A request is sent from the teacher's terminal to the server to generate homework or exam questions based on the subject and difficulty level selected by the teacher. Here, the input is the subject and difficulty level selected by the teacher, and the server side calls the generative AI model based on this. In this process, the server passes the selection information to the generative AI model and uses it as a prompt for question generation.

[1855] Step 2:

[1856] The server uses a generative AI model to generate homework and exam questions. Based on the input data (selected subjects and difficulty level), the generative AI model generates a problem set. Here, the generative AI model generates questions using prompts such as "math" or "intermediate" and sends the results back to the server. The server receives the generated results: the problem statement, correct answers, and explanations.

[1857] Step 3:

[1858] The generated homework and exam questions are sent back from the server to the teacher's terminal, where the teacher can review them and add corrections or comments. The input is the generated question set, and the output is the question set edited by the teacher.

[1859] Step 4:

[1860] Once the teacher has finalized the problem set, the information is sent to the server again. The server saves the finalized problem set in the database and prepares it for distribution to the students' devices. The input is the finalized problem set, and the output is a notification that it is ready to be saved in the database and distributed.

[1861] Step 5:

[1862] The student's device accesses the distributed questions and inputs the answers. At this stage, an interface is displayed for the student to answer the questions. The input is the student's answer, and the output is the answer data.

[1863] Step 6:

[1864] The answers are sent from the student's terminal to the server. The server stores the received answers in a database and then automatically grades them using a grading tool. The input is the student's answer data, and the output is the graded results.

[1865] Step 7:

[1866] The server stores the grading results in a database and sends the results back to the student's device using a result notification means. The input is the grading results and the output is a notification to the student's device.

[1867] Step 8:

[1868] Next, the explanation generation means generates explanations and correction questions for the incorrect parts. The server sends the generated explanations and correction questions to the student's terminal. The input is the grade data and incorrect answers, and the output is the generated explanations and correction questions.

[1869] Step 9:

[1870] In parallel, an emotion recognition means is used to recognize emotions based on the customer's question, image, and voice, where the input is the customer's question, facial expression image, and voice data, and the output is the recognized emotional state.

[1871] Step 10:

[1872] Based on the emotion recognition results, the response generation means generates appropriate product descriptions and suggestions. The server then sends the generated responses to the salesperson's terminal. The input is the customer's question and emotional state, and the output is the generated responses.

[1873] Step 11:

[1874] The generated questions and responses are displayed on the salesperson's terminal, and the salesperson responds to the customer based on them. Here, the input is the generated response sentence, and the output is the information that the salesperson provides to the customer.

[1875] In this way, the system generates appropriate questions and provides personalized, emotion-based responses in educational settings and brick-and-mortar stores.

[1876] 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.

[1877] 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.

[1878] 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.

[1879] 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.

[1880] 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.

[1881] 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.

[1882] 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).

[1883] 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.

[1884] 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."

[1885] 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.

[1886] 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).

[1887] 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.

[1888] 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.

[1889] 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.

[1890] 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.

[1891] 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.

[1892] 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.

[1893] 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.

[1894] 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.

[1895] 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 t...

Claims

1. a generating means for generating homework and exam questions based on the subject and difficulty level selected by the teacher; a distribution means for distributing the generated homework and exam questions to students' digital devices; an input means for students to input their responses using a digital device; A scoring means for automatically scoring the input answers; A result notification method that instantly returns the grading results to the student's device; An explanation generation means for generating explanations and correction questions for incorrect parts as needed and displaying them on the student's device; A system including:

2. 10. The system of claim 1, further comprising means for a teacher to review the generated homework and test questions and make corrections or additions.

3. 2. The system according to claim 1, further comprising a storage means for storing the generated homework and test questions, the students' answers, and the grading results in a database.

Images