system

Abstract

Provide a system. The method includes: a means for utilizing a generative artificial intelligence model to evaluate received test answers and identify correct, incorrect, and difficult answers; a means for recording the results of the assessment and calculating the graded marks for each student; a means for generating qualitative advice for each student based on the assessment results; A means to analyze the assessment results and create an optimized learning plan for each student in conjunction with learning support software; A system including:

Description

[Technical Field]

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

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

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

[0004] In the educational field, teacher shortages, increased overtime, grading errors, and the excessive consumption of work time are becoming serious problems. Furthermore, it is difficult to provide optimal learning support for each student. Conventional systems struggle to automate grading while providing qualitative advice and individually optimized learning plans, resulting in ineffective learning support. Given this background, a system is needed that can efficiently and accurately grade exams and provide individualized learning support for each student. [Means for solving the problem]

[0005] The present invention provides a means for evaluating received test answers using a generative artificial intelligence model to distinguish between correct, incorrect, and difficult answers. It also includes a means for recording the evaluation results and calculating a grade for each student. It also incorporates a means for generating qualitative advice for each student based on the evaluation results, and a means for analyzing the evaluation results and creating an optimized learning plan for each student in cooperation with learning support software, thereby achieving efficient and accurate learning support. It also includes a means for providing a teacher's terminal with sample comments pre-generated by the generative artificial intelligence model, allowing the teacher to make additional comments. These means enable advanced learning support to be provided to students while reducing the burden on teachers.

[0006] A "generative AI model" is an artificial intelligence technology designed to automatically perform specific tasks, such as evaluating test answers or generating feedback.

[0007] "Received test answers" refers to data received by the system by means of obtaining the results of a test answered by a student.

[0008] "Evaluation" is the process of using a generative AI model to determine whether a test answer is correct or incorrect.

[0009] A "correct answer" is a result indicating that the received test answer matches a predetermined correct answer.

[0010] An "error" is a result that indicates that the received test answer does not match the predetermined correct answer.

[0011] "Difficult answers to judge" are results that show test answers that the generative AI model cannot determine whether they are correct or incorrect.

[0012] "Recording" refers to the act of storing the evaluation results of a generative AI model in a database or other recording medium.

[0013] "Graded score" is the student's test score calculated based on the evaluation results.

[0014] "Qualitative advice" refers to specific feedback and suggestions provided by the generative AI model based on the evaluation results.

[0015] "Assessment analysis" is the process of conducting detailed analysis of data related to student test responses.

[0016] "Learning support software" is application software that supports students' learning.

[0017] An "optimized learning plan" is an optimal learning strategy or plan proposed by a generative AI model based on each student's individual assessment results.

[0018] "Sample comments" are sample comments that are generated in advance by the generative AI model and are subject to supplementation by a teacher.

[0019] "Teacher Terminal" means an electronic device used by a teacher to review and edit students' assessment results, comments, and advice.

[0020] "Adding comments" refers to the act of a teacher adding supplements or corrections to sample comments created by a generative AI model.

[0021] A "system" is a technical overall configuration in which multiple means work together to automate test scoring and provide learning support. [Brief explanation of the drawings]

[0022] [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

[0023] 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.

[0024] First, the terms used in the following description will be explained.

[0025] 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).

[0026] 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.

[0027] 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.

[0028] 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.

[0029] 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."

[0030] [First embodiment]

[0031] FIG. 1 shows an example of the configuration of a data processing system 10 according to the first embodiment.

[0032] 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.

[0033] 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).

[0034] 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.

[0035] 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.

[0036] 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.

[0037] 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.

[0038] FIG. 2 shows an example of the main functions of the data processing device 12 and the smart device 14.

[0039] 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.

[0040] 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.

[0041] 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.

[0042] 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."

[0043] This invention is a system that utilizes a generative artificial intelligence model to improve the efficiency of test scoring and provide learning support optimized for each student. Below, we will explain in detail each element of the system and its operation.

[0044] 1. Collecting test answers

[0045] The server receives the test data answered by students. This data is sent to the server by teachers or educational institutions and parsed into a data format such as JSON. The server stores the received data in a database.

[0046] Example: Student A takes an online math test and sends the answer data to a server, which analyzes the data and stores it in a database.

[0047] 2. Generative AI scoring

[0048] The server inputs the answer data stored in the database into the generative AI model and evaluates each answer as "〇" (correct), "×" (incorrect), or "△" (determined). The evaluation results are recorded in the database.

[0049] Example: Student A's answer "5 x 3 = 15" is judged to be correct and recorded as "Yes." On the other hand, Student A's answer "4 x 3 = 11" is judged to be incorrect and recorded as "No."

[0050] 3. Calculation of the scores

[0051] The server calculates the score for each student based on the evaluation results. For example, a "good" score is 1 point, an "bad" score is 0 point, and a "bad" score is also 0 point. The calculated scores are saved in a database.

[0052] Example: If Student A answers 10 questions correctly and 2 questions incorrectly, his total score will be recorded as 10 points.

[0053] 4. Generating personalized advice

[0054] The server uses a generative AI model to analyze each student's answer patterns and generate qualitative advice, providing feedback tailored to each student's strengths and weaknesses.

[0055] Example: In the case of Student A, the advice generated is "You got high marks in the calculation questions, but you need to improve in the application questions."

[0056] 5. Create a study plan

[0057] The server analyzes the assessment results and works with learning support software to create an optimized learning plan for each student, providing specific guidelines for effective learning.

[0058] Example: Student A is proposed a learning plan that "strengthens review of calculation problems and practice of applied problems."

[0059] 6. Teacher's Comments

[0060] Pre-generated sample comments are displayed on the device, and teachers can add or correct them. The final comments are sent to the server and stored in a database.

[0061] Example: In response to the comment made by the generating AI, "You are strong at calculation problems," the teacher adds, "You are particularly good at problems with equations."

[0062] 7. Viewing Results and Receiving Feedback

[0063] The user's device displays the grades, advice, and study plans obtained from the server, allowing students to advance their studies based on this information.

[0064] Example: Student A checks the grades and feedback on their own device to understand what they should study next.

[0065] As described above, the present invention is a system that improves the efficiency of test grading and provides optimal learning support for each student. This is expected to improve the efficiency of educational settings and the learning effectiveness of students.

[0066] The processing flow will be explained below.

[0067] Step 1:

[0068] The server receives the test answers sent from each device. The answer data is sent in JSON format, and when the server receives the HTTP request, it parses the data and saves it in a database.

[0069] Step 2:

[0070] The server reads the test answers stored in the database, inputs them into the generative AI model, and evaluates them. The generative AI model labels correct answers as "O," incorrect answers as "X," and answers that are difficult to judge as "△." The evaluation results are then saved back into the database.

[0071] Step 3:

[0072] The server calculates each student's score based on the evaluation results. Each "O" is counted as 1 point, while "X" and "△" are counted as 0 points, and the total score is recorded in the database.

[0073] Step 4:

[0074] The server uses the generative AI model to generate qualitative advice based on each student's answer patterns, including specific suggestions for improving their learning, which are also stored in a database.

[0075] Step 5:

[0076] The server analyzes the assessment results and works with the learning support software to create an optimized learning plan for each student. The learning plan takes into account the student's strengths and weaknesses and recommends specific learning activities and materials. The generated learning plan is also stored in a database.

[0077] Step 6:

[0078] A pre-generated sample comment is displayed on the device. The teacher uses this as a reference to make any necessary corrections or additions, and then creates the final comment. The created comment is sent to the server and stored in a database.

[0079] Step 7:

[0080] The user's device retrieves and displays their own assessment results, qualitative advice, and an optimized learning plan from the server. Based on this information, students can confirm their learning guidelines and understand what they should study next.

[0081] Example 1

[0082] Next, a description will be given of Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the smart device 14 will be referred to as a "terminal."

[0083] In today's educational environment, grading tests requires a great deal of effort and time. Furthermore, providing individualized feedback and learning plans for each student places an even greater burden on teachers. Therefore, there is a need for a system that can efficiently grade tests and provide optimized learning support for each student.

[0084] The specific processing by the specific processing unit 290 of the data processing device 12 in the first embodiment is realized by the following means.

[0085] In this invention, the server includes means for evaluating received educational data using a generative AI model and identifying correct answers, incorrect answers, and difficult answers, means for recording the evaluation results and calculating a score for each user, means for generating qualitative feedback for each user based on the evaluation results, and means for analyzing the evaluation results and creating an optimized learning plan for each user in cooperation with educational support software. This makes it possible to streamline test scoring and provide personalized learning support for each student.

[0086] A "generative artificial intelligence model" is an artificial intelligence model that uses machine learning algorithms to analyze data and make predictions.

[0087] "Educational data" refers to education-related information such as answer data, test results, and learning history provided by users (students).

[0088] "Evaluation" is the process of using a generative artificial intelligence model to identify correct, incorrect, and difficult-to-judge answers based on received educational data.

[0089] "Feedback" refers to personalized learning improvement suggestions and advice provided based on students' test results and answer patterns.

[0090] A "study plan" is a plan for providing optimized learning content and schedules based on each student's strengths and weaknesses.

[0091] "Educational support software" is software that supports educational activities, such as creating learning plans, managing progress, and providing teaching materials.

[0092] "Server" means a computer system for collecting, analyzing, evaluating, and recording educational data.

[0093] "User" means a student or person receiving education who uses the system to learn.

[0094] "Score" refers to the score for each student calculated based on the test evaluation results.

[0095] The present invention is a system that utilizes a generative artificial intelligence model to improve the efficiency of test scoring and provide optimized learning support for each student. A specific implementation method of the system is described below.

[0096] First, the server receives the educational data sent from the device. The educational data includes test data answered by students and is sent in a format such as JSON. The server parses this data and stores it in a database. The hardware used here is a standard server computer, and software such as Apache (registered trademark) or MySQL (registered trademark) can be used.

[0097] The server then reads the educational data stored in the database and evaluates each answer using a generative AI model. The generative AI model uses machine learning algorithms to distinguish between correct answers, incorrect answers, and difficult answers from the input data. Possible software used is Tensorflow (registered trademark) or PyTorch. The evaluation results are recorded in the database.

[0098] Based on the evaluation results, the server calculates a score for each student. Correct answers are assigned 1 point, incorrect answers 0 points, and difficult-to-judge answers are also assigned 0 points. The total score is then stored in a database. In addition, the server uses a generative AI model to analyze each student's answer patterns and generate qualitative feedback. This feedback is also stored in the database.

[0099] The server then connects to educational support software to create an optimal learning plan for each student based on the assessment results and feedback. Software such as a learning management system (LMS) can be used. The learning plan is customized based on each student's strengths and weaknesses and stored in a database.

[0100] The teacher's role is also important. Pre-generated sample comments are displayed on the device, and the teacher can add or correct them. The final comments sent from the device are saved on the server.

[0101] Finally, users can use their own devices to check the grades, feedback, and study plans retrieved from the server, allowing students to understand their own learning progress and clarify what they should work on next.

[0102] As a specific example, consider a scenario in which Student A takes an online test on a device and sends the answers to a server. The server receives the answer data and evaluates it based on the generative AI model, recording the correct answer "5 x 3 = 15" as "Yes" and the incorrect answer "4 x 3 = 11" as "No." The server then aggregates the evaluation results and saves them in a database as a total score of 10 points for Student A. It then generates feedback such as "You scored well on the calculation problems, but you show weaknesses in the application problems," and creates a learning plan through learning support software to "review the calculation problems and strengthen your practice of the application problems."

[0103] An example of a prompt is "Please solve the following equation: 5 x 3 =?"

[0104] As described above, this system makes it possible to improve the efficiency of test grading and also to provide individualized learning support for each student.

[0105] The flow of the identification process in the first embodiment will be described with reference to FIG.

[0106] Step 1: Collecting educational data

[0107] The server receives the educational data sent from the device. The input data is the test data answered by the student, and is received in a format such as JSON. The server parses this data and saves it in a database. Specifically, when Student A finishes the online test on his / her device and clicks the "Submit" button, the answer data is sent to the server. The server analyzes this data and stores it in a database. The output is the analyzed educational data.

[0108] Step 2: Evaluation using generative AI models

[0109] The server reads the educational data stored in the database and inputs it into the generative AI model. The input data are the students' answers. The generative AI model distinguishes between correct answers, incorrect answers, and answers that are difficult to judge, and generates an evaluation result. Specifically, the server evaluates the answer "5 x 3 = 15" as correct "Yes" and the answer "4 x 3 = 11" as incorrect "No". This evaluation result is recorded in the database. The output is the evaluated educational data.

[0110] Step 3: Calculating the scores

[0111] The server reads the evaluation results stored in the database and calculates the score for each student. The input data is the evaluation results. For example, a correct answer "〇" is worth 1 point, an incorrect answer "×" is worth 0 points, and a difficult answer "△" is also worth 0 points, and the total score is calculated. In concrete terms, the server tallies the number of correct answers and the number of errors for Student A and calculates the total score. The output is the score for each student.

[0112] Step 4: Generate qualitative feedback

[0113] The server uses a generative AI model to analyze each student's answer patterns and generate qualitative feedback. The input data is the evaluation results. The generative AI model classifies strengths and weaknesses and generates specific advice. Specifically, the server generates feedback to Student A that "You are good at calculation problems, but have weaknesses in applied problems." The output is feedback.

[0114] Step 5: Create an optimized study plan

[0115] The server analyzes the generated feedback and evaluation results and works with the learning support software to create an optimal learning plan for each student. The input data are the feedback and evaluation results. Specifically, the server uses the learning support software to create a learning plan for Student A that "reviews calculation problems and strengthens practice of applied problems." The output is the learning plan.

[0116] Step 6: Teacher comments

[0117] The device provides the teacher with pre-generated sample comments, which the teacher can then add or correct. The input data are the sample comments. Specifically, the teacher checks Student A's feedback and learning plan on the device, and adds "He is particularly good at equation problems" to "He is strong at calculation problems." The server saves the added comments in a database. The output is the final comment.

[0118] Step 7: View results and receive feedback

[0119] The user's device displays the grading results, feedback, and learning plan obtained from the server. The input data is the learning-related data sent from the server. Specifically, Student A checks the latest grading results and feedback on his or her own device and understands the learning content he or she should tackle next. The output is the displayed learning-related data.

[0120] (Application example 1)

[0121] 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."

[0122] Traditionally, evaluating the performance of factory robot operators has been time-consuming and labor-intensive, and it has been difficult to maintain accuracy and consistency in the evaluations. Traditional evaluation methods have been largely subjective, making it difficult to provide individually optimized training plans. This has led to delays in improving operator skills and the risk of reduced production efficiency.

[0123] 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.

[0124] In this invention, the server includes means for evaluating received information using a generative artificial intelligence model and identifying correct answers, incorrect answers, and answers that are difficult to evaluate, means for recording the evaluation results and calculating an evaluation score for each subject, means for generating qualitative advice for each subject based on the evaluation results, and means for analyzing the evaluation results and creating a training plan optimized for each subject in cooperation with the assistance software. This makes it possible to objectively and efficiently evaluate an operator's performance and provide individually optimized feedback and training plans.

[0125] A "generative artificial intelligence model" is an algorithm that uses artificial intelligence technology to analyze data and generate responses or decisions based on the results.

[0126] "Information" is a concept that encompasses facts, data, or knowledge about a particular subject.

[0127] "Evaluation" is the act of analyzing received information and making a judgment based on specific criteria.

[0128] A "correct answer" is the only correct expected response to a problem or question.

[0129] An "error" is an answer or action that is incorrect compared to the correct answer.

[0130] "Answers that are difficult to evaluate" are ambiguous answers that the generative AI model cannot clearly determine as correct or incorrect.

[0131] "Evaluation results" are the results of evaluation obtained by the generative artificial intelligence model, including identification of correct answers, incorrect answers, and answers that are difficult to evaluate.

[0132] "Individual subject" means the individual being evaluated.

[0133] The "evaluation score" is a numerical representation of the performance of each subject.

[0134] "Qualitative advice" refers to specific, verbalized instructions or suggestions based on the results of the assessment.

[0135] A "training plan" is a plan designed to help an individual subject acquire specific skills or knowledge.

[0136] "Support Software" means a software program for performing the calculations and analyses necessary for the evaluation and development of a training plan.

[0137] "Individually optimized feedback" refers to advice that is customized to each individual subject's specific needs and circumstances.

[0138] The present invention is a system that utilizes generative artificial intelligence models to efficiently evaluate the performance of factory robot operators and provide individually optimized feedback and training plans. Below, we will explain in detail each element of the system and its operation.

[0139] 1. Collecting Operational Data

[0140] The server collects data from the factory robot's operations through sensors and a logging system, and sends it to the server. This data is parsed into a data format such as JSON, and the server stores the received data in a database.

[0141] Example: When operator A controls the robot and commands it to "move," the coordinate data and timestamp of that movement are sent to the server.

[0142] 2. Evaluation by generative AI

[0143] The server inputs the operation data stored in the database into the generative AI model and evaluates the accuracy, efficiency, error rate, etc. of each operation. The evaluation results are recorded in the database.

[0144] Example: If Operator A's operation "Pick item A" is performed accurately and quickly, it will be recorded as a "High Score." On the other hand, if "Pick item B" is performed incorrectly, it will be recorded as a "Low Score."

[0145] 3. Calculation of evaluation results

[0146] The server calculates the performance score for each operator based on the evaluation results. For example, a "high rating" is 2 points, a "low rating" is 0 points, and the total score is calculated. The calculated scores are saved in a database.

[0147] Example: If Operator A has 10 likes and 2 dislikes, their total score will be recorded as 20 points.

[0148] 4. Generating personalized advice

[0149] The server uses a generative AI model to analyze each operator's operating patterns and generate qualitative advice, providing feedback tailored to each operator's individual strengths and weaknesses.

[0150] Example: For Operator A, the advice generated is "Your moving operations are highly rated, but your picking operations need improvement."

[0151] 5. Create a training plan

[0152] The server analyzes the evaluation results and works with the assistance software to create an optimized training plan for each operator, providing specific guidelines for operators to effectively improve their skills.

[0153] Example: Operator A is proposed a training plan to "strengthen training in picking operations."

[0154] 6. Additional Supervisor Comments

[0155] Pre-generated sample comments are displayed on the terminal, and the supervisor can add or correct them. The final comments are sent to the server and stored in a database.

[0156] Example: In response to the generated AI's comment "Picking accuracy is low," the supervisor adds, "Please note that the picking accuracy of item B is particularly low."

[0157] 7. Viewing Results and Receiving Feedback

[0158] The user's device displays the evaluation results, advice, and training plans obtained from the server, allowing the operator to improve their own operating skills based on this information.

[0159] Example: Operator A checks the evaluation results and feedback on his own device and understands the next training content he should work on.

[0160] The system uses generative AI models using AI frameworks such as TensorFlow and PyTorch, databases such as PostgreSQL, and API servers such as Flask and Django as its main software components.

[0161] Example prompt sentence:

[0162] It collects operation data from the robot operator and evaluates their performance using a generative AI model. Based on the evaluation results, it generates individualized feedback and training plans and provides feedback to the operator.

[0163] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[0164] Step 1:

[0165] Operational Data Collection

[0166] The server collects data on the operations of factory robot operators. This data is acquired through sensors and logging systems and sent to the server in formats such as JSON. The server stores the received data in a database, thereby recording the operator's operation history.

[0167] Input: Operator operation data (e.g. movement coordinates, item pick data)

[0168] Output: Operational data stored in a database

[0169] Step 2:

[0170] Generative AI evaluation

[0171] The server inputs the operation data stored in the database into the generative AI model and evaluates the accuracy, efficiency, error rate, etc. of each operation. The generative AI model analyzes the operation data and identifies correct, incorrect, and difficult-to-evaluate operations. The evaluation results are recorded in the database.

[0172] Input: Operational data stored in the database

[0173] Output: Evaluation result (e.g., correct answer, incorrect answer, difficult operation to evaluate)

[0174] Step 3:

[0175] Aggregation of evaluation results

[0176] The server calculates the performance score for each operator based on the evaluation results. For example, a "high rating" is given 2 points, and a "low rating" is given 0 points, and the total score is calculated. The calculated scores are saved in a database.

[0177] Input: Evaluation result

[0178] Output: Performance score

[0179] Step 4:

[0180] Generating personalized advice

[0181] The server uses a generative AI model to analyze each operator's operating patterns and generate qualitative advice, providing feedback tailored to each operator's strengths and weaknesses. The advice is then recorded in a database.

[0182] Input: Evaluation results and operation patterns

[0183] Output: Qualitative advice

[0184] Step 5:

[0185] Creating a training plan

[0186] The server analyzes the evaluation results and works with the assistance software to create an optimized training plan for each operator, providing specific guidelines for the operator to effectively improve their skills. The training plan is then saved in a database.

[0187] Input: Evaluation results and qualitative advice

[0188] Output: Training plan

[0189] Step 6:

[0190] Additional supervisor comments

[0191] The terminal provides the supervisor with pre-generated sample comments, which the supervisor can add or correct, and the final comments are sent to the server and stored in a database.

[0192] Input: Generated comment sample

[0193] Output: Annotated comments

[0194] Step 7:

[0195] Viewing results and receiving feedback

[0196] The user's device displays the evaluation results, advice, and training plans obtained from the server, allowing the operator to improve their own operating skills based on this information.

[0197] Input: Assessment results, advice, training plan

[0198] Output: Information displayed on the user's terminal

[0199] 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.

[0200] This invention is a system that utilizes a generative artificial intelligence model to improve the efficiency of test scoring and provide learning support optimized for each student. Furthermore, by recognizing the user's emotional state and incorporating this into the learning support, more effective learning support is realized.

[0201] Configuration and Operation

[0202] 1. Collecting test answers

[0203] The server receives the test answers from each device. This answer data is sent in JSON format, and the server parses it and stores it in a database. This allows all answer data to be managed centrally.

[0204] Example: Student A takes an online math test and sends the answer data to a server, which analyzes the data and stores it in a database.

[0205] 2. Generative AI scoring

[0206] The server inputs the answer data stored in the database into the generative AI model and evaluates each answer as "〇" (correct), "×" (incorrect), or "△" (determined). The evaluation results are then saved back into the database.

[0207] Example: Student A's answer "5 x 3 = 15" is judged to be correct and recorded as "Yes." On the other hand, Student A's answer "4 x 3 = 11" is judged to be incorrect and recorded as "No."

[0208] 3. Calculation of the scores

[0209] The server calculates each student's score based on the evaluation results. Each "O" is worth 1 point, and each "X" and "△" is worth 0 point. The server calculates the total score and records the total score in the database.

[0210] Example: If Student A answers 10 questions correctly and 2 questions incorrectly, his total score will be recorded as 10 points.

[0211] 4. User Emotion Recognition

[0212] The server uses an emotion engine to analyze the user's emotional state. The emotion engine analyzes the user's facial expressions and tone of voice via a camera or microphone to obtain emotional data. Based on this, the student's emotional state is determined and recorded.

[0213] Example: If Student A looks anxious during a test, the emotion engine will recognize this and record the emotion data as "anxious."

[0214] 5. Generating personalized advice

[0215] The server uses a generative AI model to generate qualitative advice based on each student's answer patterns and emotional data, providing more personalized feedback.

[0216] Example: Advice generated for Student A is, "You are good at calculation problems, but tend to feel uneasy with applied problems. You should practice applied problems more and also practice to gain confidence."

[0217] 6. Create a study plan

[0218] The server analyzes the assessment results and emotional data and works with learning support software to create an optimized learning plan, which includes specific learning activities and materials that take emotional state into account.

[0219] Example: Student A's study plan might include relaxation exercises before tackling applied problems, helping him focus on his studies while reducing anxiety.

[0220] 7. Teacher's Comments

[0221] Pre-generated sample comments are displayed on the device, and teachers can add or correct them. The final comments are sent to the server and stored in a database.

[0222] Example: In response to the comment made by the generating AI, "You are strong at calculation problems," the teacher adds the comment, "You are particularly good at problems with equations."

[0223] 8. Viewing Results and Receiving Feedback

[0224] The user's device retrieves and displays their own assessment results, qualitative advice, and an optimized learning plan from the server. Based on this information, students can confirm their future learning strategy and understand what they should tackle next.

[0225] Example: Student A checks the assessment results and feedback on his / her own device and understands what learning he / she should do next through a learning plan based on emotional data.

[0226] In this way, by combining a generative AI model and an emotion engine, the present invention provides a system that efficiently grades students, provides personalized feedback, and provides learning plans, which is expected to improve the efficiency of classrooms and student learning outcomes.

[0227] The processing flow will be explained below.

[0228] Step 1:

[0229] The server receives the test answers sent from each device. The test answers are sent in JSON format, and upon receiving the HTTP request, the server parses the answer data in JSON format and stores it in a database.

[0230] Step 2:

[0231] The server inputs the test answers stored in the database into the generative AI model and evaluates each answer as "〇" (correct), "×" (incorrect), or "△" (delayed judgment). The evaluation results are then saved in the database again.

[0232] Step 3:

[0233] The server calculates each student's score based on the evaluation results. Specifically, each "OK" is counted as 1 point, while "X" and "△" are counted as 0 points, and the total score is recorded in the database.

[0234] Step 4:

[0235] The server uses an emotion engine to recognize the user's emotional state. The emotion engine analyzes the user's facial expressions and voice through a camera and microphone to obtain emotional data such as "happiness," "sadness," and "surprise." This data is sent to the server at the same time as the test is received and stored in a database.

[0236] Step 5:

[0237] The server uses the generative AI model to generate qualitative advice based on the evaluation results and emotional data. The advice is also personalized, taking into account feedback based on the emotional data. This advice is also stored in a database.

[0238] Step 6:

[0239] The server analyzes the assessment results and emotional data, and works with learning support software to create an optimized learning plan for each student. The learning plan includes content that takes into account the student's emotional state, such as relaxation exercises or short breaks to refresh the mind. The generated learning plan is also stored in a database.

[0240] Step 7:

[0241] Pre-generated sample comments are displayed on the device, and the teacher can add any necessary corrections or additions. The comments are then sent to the server and stored in a database.

[0242] Step 8:

[0243] The user's device retrieves and displays their own assessment results, qualitative advice, and an optimized learning plan from the server. Based on this information, students can confirm their future learning strategy and understand what they should tackle next.

[0244] Step 9:

[0245] The user studies based on the study plan provided along with test feedback. Students use this study plan as a reference and periodically report their progress to the server, which then records this in a database. This allows the server to track the student's learning progress and emotional state and adjust the study plan as needed.

[0246] Example 2

[0247] 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."

[0248] In traditional educational systems, test scoring is often done manually, which not only requires a lot of time and effort, but also can lead to inconsistent and inaccurate scoring. It is also difficult to properly understand each student's emotional state and learning situation and provide individual feedback and learning plans based on that. This results in a lack of personalized instruction to maximize students' learning outcomes.

[0249] The identification process by the identification processing unit 290 of the data processing device 12 in Example 2 is realized by the following means. In this invention, the server includes: means for evaluating received answer data using a generative AI model and identifying correct answers, incorrect answers, and answers that are difficult to judge; means for recording the evaluation results and calculating scores for each individual; means for inputting the answer data into the generative AI model and performing the evaluation; means for analyzing the evaluation results and using an emotion engine that recognizes the emotional state of the individual; means for generating individual feedback based on the analyzed emotion data; and means for analyzing the evaluation results and the emotion data and creating an optimized study plan. This improves the efficiency and consistency of test grading and makes it possible to provide personalized feedback and study plans based on the emotional state of each student.

[0250] A "generative artificial intelligence model" is an artificial intelligence algorithm that can analyze data and determine answers and patterns based on certain rules.

[0251] "Answer data" is digital data that indicates the results of a test that a user answers using a terminal.

[0252] "Evaluation results" are data that are analyzed by a generative artificial intelligence model and include the results of identifying correct answers, incorrect answers, and answers that are difficult to judge.

[0253] The "emotion engine" is an emotional state recognition algorithm that analyzes a user's facial expressions and tone of voice using data collected through devices such as cameras and microphones.

[0254] "Feedback" refers to individual advice and guidance provided to users based on the analyzed evaluation results and emotional data.

[0255] A "learning plan" is a plan that includes an optimized learning schedule and selection of teaching materials for each student based on evaluation results and emotional data.

[0256] "Database" means the data structure and storage location where the information managed within a system is collected.

[0257] A "terminal" is an electronic device, such as a computer or mobile device, through which a user completes a test or interacts with the system.

[0258] "Educator" refers to the person in charge of education who supplements and corrects the learning plan and feedback, and provides the final instruction.

[0259] The term "system" refers to a collection of various hardware and software components that constitute the present invention as a whole, and is a computer configuration for achieving a specific purpose.

[0260] MODE FOR CARRYING OUT THE INVENTION

[0261] This invention is a system that utilizes a generative artificial intelligence model and an emotion engine to improve the efficiency of test scoring in educational settings and provide learning support optimized for each student. This system is composed of the following elements: a server, a terminal, and a user.

[0262] composition

[0263] 1. Server:

[0264] The server is equipped with a generative artificial intelligence model and an emotion engine, analyzes answer data received from multiple devices, and stores evaluation results and emotion data in a database.

[0265] The server generates personalized feedback and an optimized learning plan and provides it to the user terminal.

[0266] 2. Terminal:

[0267] The device provides an interface for users to answer questions, and transmits the user's facial expressions and voice to the emotion engine via a camera and microphone.

[0268] The terminal displays the generated feedback and learning plan to the user.

[0269] 3. User:

[0270] Users answer the test using their device and send the results to the server. Emotion data is collected by the emotion engine, allowing them to receive more effective learning support.

[0271] Specific implementation details

[0272] The server first parses the answer data received from the device in JSON format and stores it in a database. It then uses a generative AI model to evaluate the answer data and identify correct, incorrect, and difficult answers. The evaluation results are also stored in the database.

[0273] The server then uses an emotion engine to analyze the user's facial expressions and tone of voice to obtain emotional data, which is then stored in a database for future use in learning support.

[0274] The server uses a generative AI model to generate personalized feedback based on the evaluation results and emotional data. This feedback is sent to the device and displayed to the user. An optimized learning plan is also generated and provided to the user based on the user's evaluation results and emotional state.

[0275] Specific examples

[0276] In this example, the server receives Student A's math test answer data, analyzes it, and saves it in a database. The generative AI model evaluates "5 x 3 = 15" as the correct answer and records it as "Yes." On the other hand, the answer "4 x 3 = 11" is evaluated as an incorrect answer and recorded as "No." The server also uses its emotion engine to recognize Student A's anxious facial expression via the camera and record the data.

[0277] The server then generates feedback for Student A, such as: "You're strong at calculation problems, but tend to feel uneasy with applied problems. Practice more applied problems and do some practice to build your confidence." This advice can be supplemented by a human teacher and provided as a final comment.

[0278] The lesson plan includes relaxation exercises before tackling applied problems, designed to help Student A focus on learning while reducing anxiety.

[0279] Prompt Sentence Examples

[0280] "Provide personalized study advice based on students' math test answers and their current emotional state."

[0281] "Generate a lesson plan that takes into account the student's insurmountable challenges and the resulting emotional changes."

[0282] In this way, the present invention is a system that combines a generative AI model and an emotion engine to provide efficient grading and personalized learning support, which is expected to improve the efficiency of classrooms and student learning outcomes.

[0283] The flow of the identification process in the second embodiment will be described with reference to FIG.

[0284] Step 1: Collect test answers

[0285] Specific operation: The user answers the test on the device. The device generates the user's answer data in JSON format and sends it to the server.

[0286] Input: User's answer data (JSON format)

[0287] Data processing: Parse the answer data received by the server and extract the answer content

[0288] Output: Parsed answer data stored in a database

[0289] Step 2: Generative AI scoring

[0290] How it works: The server retrieves answer data from the database and inputs it into the generative AI model, which then evaluates the answer and returns the result.

[0291] Input: Answer data

[0292] Data processing: The generative AI model evaluates the answer as "〇" (correct), "×" (incorrect), or "△" (withhold judgment).

[0293] Output: The evaluation result (yes, no, or triangle) is saved in the database.

[0294] Step 3: Calculating the scores

[0295] Specific operation: The server calculates the score for each student based on the evaluation results, calculates the score, and records the total score in the database.

[0296] Input: Evaluation result

[0297] Data calculation: Each "〇" is calculated as 1 point, and "×" and "△" are calculated as 0 points.

[0298] Output: The total score is saved in the database.

[0299] Step 4: Recognizing user emotions

[0300] How it works: When a user takes a test on their device, the camera and microphone are activated to collect data. The server then uses the emotion engine to analyze the data and determine the user's emotion.

[0301] Input: User's facial expression and voice data

[0302] Data processing: The emotion engine analyzes facial expressions and tone of voice to obtain emotional data.

[0303] Output: The determined emotion data is saved in the database.

[0304] Step 5: Generate personalized advice

[0305] Specific operation: The server uses a generative AI model to generate individual advice based on the evaluation results and emotion data.

[0306] Input: Evaluation results and emotion data

[0307] Data computation: Generative AI models generate advice based on answer patterns and emotional state

[0308] Output: Individual advice stored in a database

[0309] Step 6: Create a study plan

[0310] Specific operation: The server analyzes the evaluation results and emotional data, and works with the learning support software to create an optimized learning plan.

[0311] Input: Evaluation results and emotion data

[0312] Data calculations: Select learning activities and materials based on assessment results and emotional state

[0313] Output: The learning plan is saved in the database.

[0314] Step 7: Teacher comments

[0315] Specific operation: The generated comment sample is displayed on the device, and the educator adds or corrects it. The final comment is sent to the server and stored in the database.

[0316] Input: Generated comment sample

[0317] Data processing: Educators supplement and correct comments

[0318] Output: Supplementary and corrected comments are saved in the database

[0319] Step 8: View results and receive feedback

[0320] Specific operation: The user's device retrieves and displays the evaluation results, advice, and learning plan from the server.

[0321] Input: Assessment results, feedback, learning plans

[0322] Data calculation: The server retrieves the necessary information from the database and sends it to the terminal in the appropriate format.

[0323] Output: Assessment results, feedback, and learning plans displayed on the user's device

[0324] (Application example 2)

[0325] 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."

[0326] Conventional learning support systems do not adequately consider the emotional state of each student, and the feedback itself is uniform. This can lead to significant differences in learning outcomes for each student, delays in individual optimization, and a decline in student motivation. Furthermore, the time it takes for teachers to provide feedback reduces the efficiency of education.

[0327] The identification processing by the identification processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means. In this invention, the server includes: means for evaluating received test answers using a generative AI model and identifying correct answers, incorrect answers, and difficult answers; means for recording the evaluation results and calculating individual scores; means for generating individual qualitative advice based on the evaluation results; means for analyzing the evaluation results and creating an individually optimized study plan in cooperation with learning support software; and means for recognizing the user's emotional state using an image capture device and reflecting this emotional data in the individual qualitative advice and optimized study plan. This provides individually optimized feedback that takes into account the student's emotional state, enabling improved learning effectiveness and more efficient education.

[0328] A "generative AI model" is a type of artificial intelligence that learns patterns from data and makes predictions and generates data based on new data.

[0329] "Test Answers" refers to answer data submitted by a user as part of an examination or assessment.

[0330] "Evaluation" is the process of using a generative AI model to determine whether a test answer is correct or incorrect.

[0331] A "correct answer" is the appropriate response to a test question.

[0332] An "error" is an inappropriate response to a test question.

[0333] A "difficult answer to judge" is an answer that is difficult for the generative AI model to determine whether it is correct or incorrect.

[0334] "Evaluation result" is the result of judging whether the answer generated by the generative AI model is correct or incorrect.

[0335] "Score" refers to the score of each user calculated based on the evaluation results.

[0336] "Qualitative advice" is specific, qualitative feedback provided based on the results of the assessment.

[0337] A "study plan" is a study plan optimized for each individual user, created based on the assessment results and qualitative advice.

[0338] "Image capture device" refers to a camera or other image capture device that captures image data for recognizing a user's emotional state.

[0339] "Emotional state" refers to the psychological state detected from the user's facial expression, tone of voice, etc.

[0340] This invention is a system that uses generative AI models and emotion recognition technology to improve test scoring and learning support. Specifically, it involves the collaboration of a server, a user terminal, and an image capture device.

[0341] First, the user's device collects test answers and sends them to the server. This answer data is sent in JSON format or similar, and the server parses it and stores it in a database. For example, when a student takes an online test, the answer data is sent to the server, which analyzes the data and stores it in a database.

[0342] The server then inputs the answer data stored in the database into the generative AI model, which evaluates each answer as "correct," "incorrect," or "difficult to judge." The evaluation results are then stored back in the database. For example, a student's answer "5 x 3 = 15" is determined to be correct and recorded as "correct," while the answer "4 x 3 = 11" is determined to be incorrect and recorded as "incorrect."

[0343] The server then calculates each student's score based on the evaluation results. Each "correct" answer is worth 1 point, while "incorrect" and "difficult to judge" answers are worth 0 points. The total score is then recorded in the database. For example, if a student answers 10 questions correctly and 2 questions incorrectly, the total score will be recorded as 10 points.

[0344] The server further analyzes the user's emotional state using an emotion engine. The emotion engine analyzes the user's facial expression through an image capture device (such as a camera) and acquires emotion data. For example, if a student shows an anxious expression, the emotion engine recognizes this and records the emotion data as "anxiety."

[0345] Based on the acquired evaluation results and emotion data, the server generates qualitative advice optimized for each student. This advice is personalized using a generative AI model. For example, by inputting a prompt such as "Advice for a student who is strong in calculation problems but is anxious about applied problems," the generative AI model generates specific feedback such as "Practice applied problems more to gain confidence."

[0346] This system can recognize the user's emotional state and provide advice and study plans based on that, thereby improving learning effectiveness and streamlining education.

[0347] Examples of prompts for generative AI models include:

[0348] "Advice for students who are good at calculation problems but feel uneasy about applied problems."

[0349] Finally, teachers can supplement the qualitative advice generated by the server with additional comments, resulting in more personalized feedback for students.

[0350] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[0351] Step 1:

[0352] The user's device collects test answers and sends them to the server. Specifically, the user enters the answers on the online platform, and the data is sent to the server in JSON format. The input is the user's test answer data, and the output is the data sent to the server.

[0353] Step 2:

[0354] The server receives the submitted test answer data and stores it in a database. During this process, the server parses the JSON data and stores each item in the appropriate field in the database. The input is the user's test answer data, and the output is the answer data stored in the database.

[0355] Step 3:

[0356] The server inputs the answer data stored in the database into the generative AI model, and evaluates each answer as "correct," "incorrect," or "difficult to judge." Here, the server passes the answer data to the generative AI model, which analyzes it and returns the evaluation result. The input is the answer data stored in the database, and the output is the evaluation result.

[0357] Step 4:

[0358] The server stores the evaluation results in a database. Specifically, the evaluation results from the generative AI model are recorded in association with the corresponding answer data in the database. The input is the evaluation result of the generative AI model, and the output is the evaluation result recorded in the database.

[0359] Step 5:

[0360] The server calculates the score based on the evaluation results. Each "correct" answer is given 1 point, while "incorrect" and "difficult to judge" answers are given 0 points, and the total score is calculated. In this process, the server aggregates the evaluation results, calculates the individual scores, and stores them in a database. The input is the evaluation results, and the output is the calculated total score.

[0361] Step 6:

[0362] The server uses an emotion engine to analyze the user's emotional state. An image capture device is used to collect the user's facial expression data, which is then analyzed by the emotion engine. The input is the user's facial expression data, and the output is emotion data.

[0363] Step 7:

[0364] The server generates individual qualitative advice based on the evaluation results and emotional data. The emotional data and evaluation results are input into the generative AI model as prompts to generate specific feedback. The input is the evaluation results and emotional data, and the output is the generated qualitative advice.

[0365] Step 8:

[0366] The server provides the generated qualitative advice to the teacher's device, where the teacher can add supplementary comments. Sample comments generated in advance by the generative AI model are displayed, and the teacher can add supplementary comments or make corrections to them. The input is the generated qualitative advice, and the output is feedback added by the teacher.

[0367] Step 9:

[0368] The user device retrieves and displays their own evaluation results, qualitative advice, and optimized learning plans from the server. The server sends the evaluation results and feedback to the user device, and the user confirms this information. The input is the feedback data sent from the server, and the output is the learning information displayed on the user device.

[0369] The above is an explanation of each processing step and specific operation of this system.

[0370] 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.

[0371] The data generation model 58 is a so-called generative AI (Artificial Intelligence). An example of the data generation model 58 is ChatGPT (registered trademark) (Internet search engine).<URL: https: / / openai.com / blog / chatgpt> ), Gemini (registered trademark) (Internet search <url: https: gemini.google.com ?hl="ja">) and other generation AIs. The data generation model 58 is obtained by performing deep learning on a neural network. A prompt including an instruction is input to the data generation model 58, and inference data such as voice data indicating voice, text data indicating text, and image data indicating an image is also input. The data generation model 58 performs inference on the input inference data in accordance with the instruction indicated by the prompt, and outputs the inference result in a data format such as voice data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[0372] 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.

[0373] [Second embodiment]

[0374] FIG. 3 shows an example of the configuration of a data processing system 210 according to the second embodiment.

[0375] 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.

[0376] 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).

[0377] 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.

[0378] 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.

[0379] 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).

[0380] 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.

[0381] 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.

[0382] 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.

[0383] 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.

[0384] 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.

[0385] 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."

[0386] This invention is a system that utilizes a generative artificial intelligence model to improve the efficiency of test scoring and provide learning support optimized for each student. Below, we will explain in detail each element of the system and its operation.

[0387] 1. Collecting test answers

[0388] The server receives the test data answered by students. This data is sent to the server by teachers or educational institutions and parsed into a data format such as JSON. The server stores the received data in a database.

[0389] Example: Student A takes an online math test and sends the answer data to a server, which analyzes the data and stores it in a database.

[0390] 2. Generative AI scoring

[0391] The server inputs the answer data stored in the database into the generative AI model and evaluates each answer as "〇" (correct), "×" (incorrect), or "△" (determined). The evaluation results are recorded in the database.

[0392] Example: Student A's answer "5 x 3 = 15" is judged to be correct and recorded as "Yes." On the other hand, Student A's answer "4 x 3 = 11" is judged to be incorrect and recorded as "No."

[0393] 3. Calculation of the scores

[0394] The server calculates the score for each student based on the evaluation results. For example, a "good" score is 1 point, an "bad" score is 0 point, and a "bad" score is also 0 point. The calculated scores are saved in a database.

[0395] Example: If Student A answers 10 questions correctly and 2 questions incorrectly, his total score will be recorded as 10 points.

[0396] 4. Generating personalized advice

[0397] The server uses a generative AI model to analyze each student's answer patterns and generate qualitative advice, providing feedback tailored to each student's strengths and weaknesses.

[0398] Example: In the case of Student A, the advice generated is "You got high marks in the calculation questions, but you need to improve in the application questions."

[0399] 5. Create a study plan

[0400] The server analyzes the assessment results and works with learning support software to create an optimized learning plan for each student, providing specific guidelines for effective learning.

[0401] Example: Student A is proposed a learning plan that "strengthens review of calculation problems and practice of applied problems."

[0402] 6. Teacher's Comments

[0403] Pre-generated sample comments are displayed on the device, and teachers can add or correct them. The final comments are sent to the server and stored in a database.

[0404] Example: In response to the comment made by the generating AI, "You are strong at calculation problems," the teacher adds, "You are particularly good at problems with equations."

[0405] 7. Viewing Results and Receiving Feedback

[0406] The user's device displays the grades, advice, and study plans obtained from the server, allowing students to advance their studies based on this information.

[0407] Example: Student A checks the grades and feedback on their own device to understand what they should study next.

[0408] As described above, the present invention is a system that improves the efficiency of test grading and provides optimal learning support for each student. This is expected to improve the efficiency of educational settings and the learning effectiveness of students.

[0409] The processing flow will be explained below.

[0410] Step 1:

[0411] The server receives the test answers sent from each device. The answer data is sent in JSON format, and when the server receives the HTTP request, it parses the data and saves it in a database.

[0412] Step 2:

[0413] The server reads the test answers stored in the database, inputs them into the generative AI model, and evaluates them. The generative AI model labels correct answers as "O," incorrect answers as "X," and answers that are difficult to judge as "△." The evaluation results are then saved back into the database.

[0414] Step 3:

[0415] The server calculates each student's score based on the evaluation results. Each "O" is counted as 1 point, while "X" and "△" are counted as 0 points, and the total score is recorded in the database.

[0416] Step 4:

[0417] The server uses the generative AI model to generate qualitative advice based on each student's answer patterns, including specific suggestions for improving their learning, which are also stored in a database.

[0418] Step 5:

[0419] The server analyzes the assessment results and works with the learning support software to create an optimized learning plan for each student. The learning plan takes into account the student's strengths and weaknesses and recommends specific learning activities and materials. The generated learning plan is also stored in a database.

[0420] Step 6:

[0421] A pre-generated sample comment is displayed on the device. The teacher uses this as a reference to make any necessary corrections or additions, and then creates the final comment. The created comment is sent to the server and stored in a database.

[0422] Step 7:

[0423] The user's device retrieves and displays their own assessment results, qualitative advice, and an optimized learning plan from the server. Based on this information, students can confirm their learning guidelines and understand what they should study next.

[0424] Example 1

[0425] 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."

[0426] In today's educational environment, grading tests requires a great deal of effort and time. Furthermore, providing individualized feedback and learning plans for each student places an even greater burden on teachers. Therefore, there is a need for a system that can efficiently grade tests and provide optimized learning support for each student.

[0427] 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.

[0428] In this invention, the server includes means for evaluating received educational data using a generative AI model and identifying correct answers, incorrect answers, and difficult answers, means for recording the evaluation results and calculating a score for each user, means for generating qualitative feedback for each user based on the evaluation results, and means for analyzing the evaluation results and creating an optimized learning plan for each user in cooperation with educational support software. This makes it possible to streamline test scoring and provide personalized learning support for each student.

[0429] A "generative artificial intelligence model" is an artificial intelligence model that uses machine learning algorithms to analyze data and make predictions.

[0430] "Educational data" refers to education-related information such as answer data, test results, and learning history provided by users (students).

[0431] "Evaluation" is the process of using a generative artificial intelligence model to identify correct, incorrect, and difficult-to-judge answers based on received educational data.

[0432] "Feedback" refers to personalized learning improvement suggestions and advice provided based on students' test results and answer patterns.

[0433] A "study plan" is a plan for providing optimized learning content and schedules based on each student's strengths and weaknesses.

[0434] "Educational support software" is software that supports educational activities, such as creating learning plans, managing progress, and providing teaching materials.

[0435] "Server" means a computer system for collecting, analyzing, evaluating, and recording educational data.

[0436] "User" means a student or person receiving education who uses the system to learn.

[0437] "Score" refers to the score for each student calculated based on the test evaluation results.

[0438] The present invention is a system that utilizes a generative artificial intelligence model to improve the efficiency of test scoring and provide optimized learning support for each student. A specific implementation method of the system is described below.

[0439] First, the server receives the educational data sent from the device. This educational data includes test data answered by students and is sent in a format such as JSON. The server parses this data and stores it in a database. The hardware used here is a standard server computer, and software such as Apache or MySQL can be used.

[0440] The server then reads the educational data stored in the database and evaluates each answer using a generative AI model. The generative AI model uses machine learning algorithms to distinguish between correct, incorrect, and difficult answers from the input data. Potential software used is TensorFlow or PyTorch. The evaluation results are recorded in the database.

[0441] Based on the evaluation results, the server calculates a score for each student. Correct answers are assigned 1 point, incorrect answers 0 points, and difficult-to-judge answers are also assigned 0 points. The total score is then stored in a database. In addition, the server uses a generative AI model to analyze each student's answer patterns and generate qualitative feedback. This feedback is also stored in the database.

[0442] The server then connects to educational support software to create an optimal learning plan for each student based on the assessment results and feedback. Software such as a learning management system (LMS) can be used. The learning plan is customized based on each student's strengths and weaknesses and stored in a database.

[0443] The teacher's role is also important. Pre-generated sample comments are displayed on the device, and the teacher can add or correct them. The final comments sent from the device are saved on the server.

[0444] Finally, users can use their own devices to check the grades, feedback, and study plans retrieved from the server, allowing students to understand their own learning progress and clarify what they should work on next.

[0445] As a specific example, consider a scenario in which Student A takes an online test on a device and sends the answers to a server. The server receives the answer data and evaluates it based on the generative AI model, recording the correct answer "5 x 3 = 15" as "Yes" and the incorrect answer "4 x 3 = 11" as "No." The server then aggregates the evaluation results and saves them in a database as a total score of 10 points for Student A. It then generates feedback such as "You scored well on the calculation problems, but you show weaknesses in the application problems," and creates a learning plan through learning support software to "review the calculation problems and strengthen your practice of the application problems."

[0446] An example of a prompt is "Please solve the following equation: 5 x 3 =?"

[0447] As described above, this system makes it possible to improve the efficiency of test grading and also to provide individualized learning support for each student.

[0448] The flow of the identification process in the first embodiment will be described with reference to FIG.

[0449] Step 1: Collecting educational data

[0450] The server receives the educational data sent from the device. The input data is the test data answered by the student, and is received in a format such as JSON. The server parses this data and saves it in a database. Specifically, when Student A finishes the online test on his / her device and clicks the "Submit" button, the answer data is sent to the server. The server analyzes this data and stores it in a database. The output is the analyzed educational data.

[0451] Step 2: Evaluation using generative AI models

[0452] The server reads the educational data stored in the database and inputs it into the generative AI model. The input data are the students' answers. The generative AI model distinguishes between correct answers, incorrect answers, and answers that are difficult to judge, and generates an evaluation result. Specifically, the server evaluates the answer "5 x 3 = 15" as correct "Yes" and the answer "4 x 3 = 11" as incorrect "No". This evaluation result is recorded in the database. The output is the evaluated educational data.

[0453] Step 3: Calculating the scores

[0454] The server reads the evaluation results stored in the database and calculates the score for each student. The input data is the evaluation results. For example, a correct answer "〇" is worth 1 point, an incorrect answer "×" is worth 0 points, and a difficult answer "△" is also worth 0 points, and the total score is calculated. In concrete terms, the server tallies the number of correct answers and the number of errors for Student A and calculates the total score. The output is the score for each student.

[0455] Step 4: Generate qualitative feedback

[0456] The server uses a generative AI model to analyze each student's answer patterns and generate qualitative feedback. The input data is the evaluation results. The generative AI model classifies strengths and weaknesses and generates specific advice. Specifically, the server generates feedback to Student A that "You are good at calculation problems, but have weaknesses in applied problems." The output is feedback.

[0457] Step 5: Create an optimized study plan

[0458] The server analyzes the generated feedback and evaluation results and works with the learning support software to create an optimal learning plan for each student. The input data are the feedback and evaluation results. Specifically, the server uses the learning support software to create a learning plan for Student A that "reviews calculation problems and strengthens practice of applied problems." The output is the learning plan.

[0459] Step 6: Teacher comments

[0460] The device provides the teacher with pre-generated sample comments, which the teacher can then add or correct. The input data are the sample comments. Specifically, the teacher checks Student A's feedback and learning plan on the device, and adds "He is particularly good at equation problems" to "He is strong at calculation problems." The server saves the added comments in a database. The output is the final comment.

[0461] Step 7: View results and receive feedback

[0462] The user's device displays the grading results, feedback, and learning plan obtained from the server. The input data is the learning-related data sent from the server. Specifically, Student A checks the latest grading results and feedback on his or her own device and understands the learning content he or she should tackle next. The output is the displayed learning-related data.

[0463] (Application example 1)

[0464] 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."

[0465] Traditionally, evaluating the performance of factory robot operators has been time-consuming and labor-intensive, and it has been difficult to maintain accuracy and consistency in the evaluations. Traditional evaluation methods have been largely subjective, making it difficult to provide individually optimized training plans. This has led to delays in improving operator skills and the risk of reduced production efficiency.

[0466] 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.

[0467] In this invention, the server includes means for evaluating received information using a generative artificial intelligence model and identifying correct answers, incorrect answers, and answers that are difficult to evaluate, means for recording the evaluation results and calculating an evaluation score for each subject, means for generating qualitative advice for each subject based on the evaluation results, and means for analyzing the evaluation results and creating a training plan optimized for each subject in cooperation with the assistance software. This makes it possible to objectively and efficiently evaluate an operator's performance and provide individually optimized feedback and training plans.

[0468] A "generative artificial intelligence model" is an algorithm that uses artificial intelligence technology to analyze data and generate responses or decisions based on the results.

[0469] "Information" is a concept that encompasses facts, data, or knowledge about a particular subject.

[0470] "Evaluation" is the act of analyzing received information and making a judgment based on specific criteria.

[0471] A "correct answer" is the only correct expected response to a problem or question.

[0472] An "error" is an answer or action that is incorrect compared to the correct answer.

[0473] "Answers that are difficult to evaluate" are ambiguous answers that the generative AI model cannot clearly determine as correct or incorrect.

[0474] "Evaluation results" are the results of evaluation obtained by the generative artificial intelligence model, including identification of correct answers, incorrect answers, and answers that are difficult to evaluate.

[0475] "Individual subject" means the individual being evaluated.

[0476] The "evaluation score" is a numerical representation of the performance of each subject.

[0477] "Qualitative advice" refers to specific, verbalized instructions or suggestions based on the results of the assessment.

[0478] A "training plan" is a plan designed to help an individual subject acquire specific skills or knowledge.

[0479] "Support Software" means a software program for performing the calculations and analyses necessary for the evaluation and development of a training plan.

[0480] "Individually optimized feedback" refers to advice that is customized to each individual subject's specific needs and circumstances.

[0481] The present invention is a system that utilizes generative artificial intelligence models to efficiently evaluate the performance of factory robot operators and provide individually optimized feedback and training plans. Below, we will explain in detail each element of the system and its operation.

[0482] 1. Collecting Operational Data

[0483] The server collects data from the factory robot's operations through sensors and a logging system, and sends it to the server. This data is parsed into a data format such as JSON, and the server stores the received data in a database.

[0484] Example: When operator A controls the robot and commands it to "move," the coordinate data and timestamp of that movement are sent to the server.

[0485] 2. Evaluation by generative AI

[0486] The server inputs the operation data stored in the database into the generative AI model and evaluates the accuracy, efficiency, error rate, etc. of each operation. The evaluation results are recorded in the database.

[0487] Example: If Operator A's operation "Pick item A" is performed accurately and quickly, it will be recorded as a "High Score." On the other hand, if "Pick item B" is performed incorrectly, it will be recorded as a "Low Score."

[0488] 3. Calculation of evaluation results

[0489] The server calculates the performance score for each operator based on the evaluation results. For example, a "high rating" is 2 points, a "low rating" is 0 points, and the total score is calculated. The calculated scores are saved in a database.

[0490] Example: If Operator A has 10 likes and 2 dislikes, their total score will be recorded as 20 points.

[0491] 4. Generating personalized advice

[0492] The server uses a generative AI model to analyze each operator's operating patterns and generate qualitative advice, providing feedback tailored to each operator's individual strengths and weaknesses.

[0493] Example: For Operator A, the advice generated is "Your moving operations are highly rated, but your picking operations need improvement."

[0494] 5. Create a training plan

[0495] The server analyzes the evaluation results and works with the assistance software to create an optimized training plan for each operator, providing specific guidelines for operators to effectively improve their skills.

[0496] Example: Operator A is proposed a training plan to "strengthen training in picking operations."

[0497] 6. Additional Supervisor Comments

[0498] Pre-generated sample comments are displayed on the terminal, and the supervisor can add or correct them. The final comments are sent to the server and stored in a database.

[0499] Example: In response to the generated AI's comment "Picking accuracy is low," the supervisor adds, "Please note that the picking accuracy of item B is particularly low."

[0500] 7. Viewing Results and Receiving Feedback

[0501] The user's device displays the evaluation results, advice, and training plans obtained from the server, allowing the operator to improve their own operating skills based on this information.

[0502] Example: Operator A checks the evaluation results and feedback on his own device and understands the next training content he should work on.

[0503] The system uses generative AI models using AI frameworks such as TensorFlow and PyTorch, databases such as PostgreSQL, and API servers such as Flask and Django as its main software components.

[0504] Example prompt sentence:

[0505] It collects operation data from the robot operator and evaluates their performance using a generative AI model. Based on the evaluation results, it generates individualized feedback and training plans and provides feedback to the operator.

[0506] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[0507] Step 1:

[0508] Operational Data Collection

[0509] The server collects data on the operations of factory robot operators. This data is acquired through sensors and logging systems and sent to the server in formats such as JSON. The server stores the received data in a database, thereby recording the operator's operation history.

[0510] Input: Operator operation data (e.g. movement coordinates, item pick data)

[0511] Output: Operational data stored in a database

[0512] Step 2:

[0513] Generative AI evaluation

[0514] The server inputs the operation data stored in the database into the generative AI model and evaluates the accuracy, efficiency, error rate, etc. of each operation. The generative AI model analyzes the operation data and identifies correct, incorrect, and difficult-to-evaluate operations. The evaluation results are recorded in the database.

[0515] Input: Operational data stored in the database

[0516] Output: Evaluation result (e.g., correct answer, incorrect answer, difficult operation to evaluate)

[0517] Step 3:

[0518] Aggregation of evaluation results

[0519] The server calculates the performance score for each operator based on the evaluation results. For example, a "high rating" is given 2 points, and a "low rating" is given 0 points, and the total score is calculated. The calculated scores are saved in a database.

[0520] Input: Evaluation result

[0521] Output: Performance score

[0522] Step 4:

[0523] Generating personalized advice

[0524] The server uses a generative AI model to analyze each operator's operating patterns and generate qualitative advice, providing feedback tailored to each operator's strengths and weaknesses. The advice is then recorded in a database.

[0525] Input: Evaluation results and operation patterns

[0526] Output: Qualitative advice

[0527] Step 5:

[0528] Creating a training plan

[0529] The server analyzes the evaluation results and works with the assistance software to create an optimized training plan for each operator, providing specific guidelines for the operator to effectively improve their skills. The training plan is then saved in a database.

[0530] Input: Evaluation results and qualitative advice

[0531] Output: Training plan

[0532] Step 6:

[0533] Additional supervisor comments

[0534] The terminal provides the supervisor with pre-generated sample comments, which the supervisor can add or correct, and the final comments are sent to the server and stored in a database.

[0535] Input: Generated comment sample

[0536] Output: Annotated comments

[0537] Step 7:

[0538] Viewing results and receiving feedback

[0539] The user's device displays the evaluation results, advice, and training plans obtained from the server, allowing the operator to improve their own operating skills based on this information.

[0540] Input: Assessment results, advice, training plan

[0541] Output: Information displayed on the user's terminal

[0542] 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.

[0543] This invention is a system that utilizes a generative artificial intelligence model to improve the efficiency of test scoring and provide learning support optimized for each student. Furthermore, by recognizing the user's emotional state and incorporating this into the learning support, more effective learning support is realized.

[0544] Configuration and Operation

[0545] 1. Collecting test answers

[0546] The server receives the test answers from each device. This answer data is sent in JSON format, and the server parses it and stores it in a database. This allows all answer data to be managed centrally.

[0547] Example: Student A takes an online math test and sends the answer data to a server, which analyzes the data and stores it in a database.

[0548] 2. Generative AI scoring

[0549] The server inputs the answer data stored in the database into the generative AI model and evaluates each answer as "〇" (correct), "×" (incorrect), or "△" (determined). The evaluation results are then saved back into the database.

[0550] Example: Student A's answer "5 x 3 = 15" is judged to be correct and recorded as "Yes." On the other hand, Student A's answer "4 x 3 = 11" is judged to be incorrect and recorded as "No."

[0551] 3. Calculation of the scores

[0552] The server calculates each student's score based on the evaluation results. Each "O" is worth 1 point, and each "X" and "△" is worth 0 point. The server calculates the total score and records the total score in the database.

[0553] Example: If Student A answers 10 questions correctly and 2 questions incorrectly, his total score will be recorded as 10 points.

[0554] 4. User Emotion Recognition

[0555] The server uses an emotion engine to analyze the user's emotional state. The emotion engine analyzes the user's facial expressions and tone of voice via a camera or microphone to obtain emotional data. Based on this, the student's emotional state is determined and recorded.

[0556] Example: If Student A looks anxious during a test, the emotion engine will recognize this and record the emotion data as "anxious."

[0557] 5. Generating personalized advice

[0558] The server uses a generative AI model to generate qualitative advice based on each student's answer patterns and emotional data, providing more personalized feedback.

[0559] Example: Advice generated for Student A is, "You are good at calculation problems, but tend to feel uneasy with applied problems. You should practice applied problems more and also practice to gain confidence."

[0560] 6. Create a study plan

[0561] The server analyzes the assessment results and emotional data and works with learning support software to create an optimized learning plan, which includes specific learning activities and materials that take emotional state into account.

[0562] Example: Student A's study plan might include relaxation exercises before tackling applied problems, helping him focus on his studies while reducing anxiety.

[0563] 7. Teacher's Comments

[0564] Pre-generated sample comments are displayed on the device, and teachers can add or correct them. The final comments are sent to the server and stored in a database.

[0565] Example: In response to the comment made by the generating AI, "You are strong at calculation problems," the teacher adds the comment, "You are particularly good at problems with equations."

[0566] 8. Viewing Results and Receiving Feedback

[0567] The user's device retrieves and displays their own assessment results, qualitative advice, and an optimized learning plan from the server. Based on this information, students can confirm their future learning strategy and understand what they should tackle next.

[0568] Example: Student A checks the assessment results and feedback on his / her own device and understands what learning he / she should do next through a learning plan based on emotional data.

[0569] In this way, by combining a generative AI model and an emotion engine, the present invention provides a system that efficiently grades students, provides personalized feedback, and provides learning plans, which is expected to improve the efficiency of classrooms and student learning outcomes.

[0570] The processing flow will be explained below.

[0571] Step 1:

[0572] The server receives the test answers sent from each device. The test answers are sent in JSON format, and upon receiving the HTTP request, the server parses the answer data in JSON format and stores it in a database.

[0573] Step 2:

[0574] The server inputs the test answers stored in the database into the generative AI model and evaluates each answer as "〇" (correct), "×" (incorrect), or "△" (delayed judgment). The evaluation results are then saved in the database again.

[0575] Step 3:

[0576] The server calculates each student's score based on the evaluation results. Specifically, each "OK" is counted as 1 point, while "X" and "△" are counted as 0 points, and the total score is recorded in the database.

[0577] Step 4:

[0578] The server uses an emotion engine to recognize the user's emotional state. The emotion engine analyzes the user's facial expressions and voice through a camera and microphone to obtain emotional data such as "happiness," "sadness," and "surprise." This data is sent to the server at the same time as the test is received and stored in a database.

[0579] Step 5:

[0580] The server uses the generative AI model to generate qualitative advice based on the evaluation results and emotional data. The advice is also personalized, taking into account feedback based on the emotional data. This advice is also stored in a database.

[0581] Step 6:

[0582] The server analyzes the assessment results and emotional data, and works with learning support software to create an optimized learning plan for each student. The learning plan includes content that takes into account the student's emotional state, such as relaxation exercises or short breaks to refresh the mind. The generated learning plan is also stored in a database.

[0583] Step 7:

[0584] Pre-generated sample comments are displayed on the device, and the teacher can add any necessary corrections or additions. The comments are then sent to the server and stored in a database.

[0585] Step 8:

[0586] The user's device retrieves and displays their own assessment results, qualitative advice, and an optimized learning plan from the server. Based on this information, students can confirm their future learning strategy and understand what they should tackle next.

[0587] Step 9:

[0588] The user studies based on the study plan provided along with test feedback. Students use this study plan as a reference and periodically report their progress to the server, which then records this in a database. This allows the server to track the student's learning progress and emotional state and adjust the study plan as needed.

[0589] Example 2

[0590] 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."

[0591] In traditional educational systems, test scoring is often done manually, which not only requires a lot of time and effort, but also can lead to inconsistent and inaccurate scoring. It is also difficult to properly understand each student's emotional state and learning situation and provide individual feedback and learning plans based on that. This results in a lack of personalized instruction to maximize students' learning outcomes.

[0592] The identification process by the identification processing unit 290 of the data processing device 12 in Example 2 is realized by the following means. In this invention, the server includes: means for evaluating received answer data using a generative AI model and identifying correct answers, incorrect answers, and answers that are difficult to judge; means for recording the evaluation results and calculating scores for each individual; means for inputting the answer data into the generative AI model and performing the evaluation; means for analyzing the evaluation results and using an emotion engine that recognizes the emotional state of the individual; means for generating individual feedback based on the analyzed emotion data; and means for analyzing the evaluation results and the emotion data and creating an optimized study plan. This improves the efficiency and consistency of test grading and makes it possible to provide personalized feedback and study plans based on the emotional state of each student.

[0593] A "generative artificial intelligence model" is an artificial intelligence algorithm that can analyze data and determine answers and patterns based on certain rules.

[0594] "Answer data" is digital data that indicates the results of a test that a user answers using a terminal.

[0595] "Evaluation results" are data that are analyzed by a generative artificial intelligence model and include the results of identifying correct answers, incorrect answers, and answers that are difficult to judge.

[0596] The "emotion engine" is an emotional state recognition algorithm that analyzes a user's facial expressions and tone of voice using data collected through devices such as cameras and microphones.

[0597] "Feedback" refers to individual advice and guidance provided to users based on the analyzed evaluation results and emotional data.

[0598] A "learning plan" is a plan that includes an optimized learning schedule and selection of teaching materials for each student based on evaluation results and emotional data.

[0599] "Database" means the data structure and storage location where the information managed within a system is collected.

[0600] A "terminal" is an electronic device, such as a computer or mobile device, through which a user completes a test or interacts with the system.

[0601] "Educator" refers to the person in charge of education who supplements and corrects the learning plan and feedback, and provides the final instruction.

[0602] The term "system" refers to a collection of various hardware and software components that constitute the present invention as a whole, and is a computer configuration for achieving a specific purpose.

[0603] MODE FOR CARRYING OUT THE INVENTION

[0604] This invention is a system that utilizes a generative artificial intelligence model and an emotion engine to improve the efficiency of test scoring in educational settings and provide learning support optimized for each student. This system is composed of the following elements: a server, a terminal, and a user.

[0605] composition

[0606] 1. Server:

[0607] The server is equipped with a generative artificial intelligence model and an emotion engine, analyzes answer data received from multiple devices, and stores evaluation results and emotion data in a database.

[0608] The server generates personalized feedback and an optimized learning plan and provides it to the user terminal.

[0609] 2. Terminal:

[0610] The device provides an interface for users to answer questions, and transmits the user's facial expressions and voice to the emotion engine via a camera and microphone.

[0611] The terminal displays the generated feedback and learning plan to the user.

[0612] 3. User:

[0613] Users answer the test using their device and send the results to the server. Emotion data is collected by the emotion engine, allowing them to receive more effective learning support.

[0614] Specific implementation details

[0615] The server first parses the answer data received from the device in JSON format and stores it in a database. It then uses a generative AI model to evaluate the answer data and identify correct, incorrect, and difficult answers. The evaluation results are also stored in the database.

[0616] The server then uses an emotion engine to analyze the user's facial expressions and tone of voice to obtain emotional data, which is then stored in a database for future use in learning support.

[0617] The server uses a generative AI model to generate personalized feedback based on the evaluation results and emotional data. This feedback is sent to the device and displayed to the user. An optimized learning plan is also generated and provided to the user based on the user's evaluation results and emotional state.

[0618] Specific examples

[0619] In this example, the server receives Student A's math test answer data, analyzes it, and saves it in a database. The generative AI model evaluates "5 x 3 = 15" as the correct answer and records it as "Yes." On the other hand, the answer "4 x 3 = 11" is evaluated as an incorrect answer and recorded as "No." The server also uses its emotion engine to recognize Student A's anxious facial expression via the camera and record the data.

[0620] The server then generates feedback for Student A, such as: "You're strong at calculation problems, but tend to feel uneasy with applied problems. Practice more applied problems and do some practice to build your confidence." This advice can be supplemented by a human teacher and provided as a final comment.

[0621] The lesson plan includes relaxation exercises before tackling applied problems, designed to help Student A focus on learning while reducing anxiety.

[0622] Prompt Sentence Examples

[0623] "Provide personalized study advice based on students' math test answers and their current emotional state."

[0624] "Generate a lesson plan that takes into account the student's insurmountable challenges and the resulting emotional changes."

[0625] In this way, the present invention is a system that combines a generative AI model and an emotion engine to provide efficient grading and personalized learning support, which is expected to improve the efficiency of classrooms and student learning outcomes.

[0626] The flow of the identification process in the second embodiment will be described with reference to FIG.

[0627] Step 1: Collect test answers

[0628] Specific operation: The user answers the test on the device. The device generates the user's answer data in JSON format and sends it to the server.

[0629] Input: User's answer data (JSON format)

[0630] Data processing: Parse the answer data received by the server and extract the answer content

[0631] Output: Parsed answer data stored in a database

[0632] Step 2: Generative AI scoring

[0633] How it works: The server retrieves answer data from the database and inputs it into the generative AI model, which then evaluates the answer and returns the result.

[0634] Input: Answer data

[0635] Data processing: The generative AI model evaluates the answer as "〇" (correct), "×" (incorrect), or "△" (withhold judgment).

[0636] Output: The evaluation result (yes, no, or triangle) is saved in the database.

[0637] Step 3: Calculating the scores

[0638] Specific operation: The server calculates the score for each student based on the evaluation results, calculates the score, and records the total score in the database.

[0639] Input: Evaluation result

[0640] Data calculation: Each "〇" is calculated as 1 point, and "×" and "△" are calculated as 0 points.

[0641] Output: The total score is saved in the database.

[0642] Step 4: Recognizing user emotions

[0643] How it works: When a user takes a test on their device, the camera and microphone are activated to collect data. The server then uses the emotion engine to analyze the data and determine the user's emotion.

[0644] Input: User's facial expression and voice data

[0645] Data processing: The emotion engine analyzes facial expressions and tone of voice to obtain emotional data.

[0646] Output: The determined emotion data is saved in the database.

[0647] Step 5: Generate personalized advice

[0648] Specific operation: The server uses a generative AI model to generate individual advice based on the evaluation results and emotion data.

[0649] Input: Evaluation results and emotion data

[0650] Data computation: Generative AI models generate advice based on answer patterns and emotional state

[0651] Output: Individual advice stored in a database

[0652] Step 6: Create a study plan

[0653] Specific operation: The server analyzes the evaluation results and emotional data, and works with the learning support software to create an optimized learning plan.

[0654] Input: Evaluation results and emotion data

[0655] Data calculations: Select learning activities and materials based on assessment results and emotional state

[0656] Output: The learning plan is saved in the database.

[0657] Step 7: Teacher comments

[0658] Specific operation: The generated comment sample is displayed on the device, and the educator adds or corrects it. The final comment is sent to the server and stored in the database.

[0659] Input: Generated comment sample

[0660] Data processing: Educators supplement and correct comments

[0661] Output: Supplementary and corrected comments are saved in the database

[0662] Step 8: View results and receive feedback

[0663] Specific operation: The user's device retrieves and displays the evaluation results, advice, and learning plan from the server.

[0664] Input: Assessment results, feedback, learning plans

[0665] Data calculation: The server retrieves the necessary information from the database and sends it to the terminal in the appropriate format.

[0666] Output: Assessment results, feedback, and learning plans displayed on the user's device

[0667] (Application example 2)

[0668] 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."

[0669] Conventional learning support systems do not adequately consider the emotional state of each student, and the feedback itself is uniform. This can lead to significant differences in learning outcomes for each student, delays in individual optimization, and a decline in student motivation. Furthermore, the time it takes for teachers to provide feedback reduces the efficiency of education.

[0670] The identification processing by the identification processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means. In this invention, the server includes: means for evaluating received test answers using a generative AI model and identifying correct answers, incorrect answers, and difficult answers; means for recording the evaluation results and calculating individual scores; means for generating individual qualitative advice based on the evaluation results; means for analyzing the evaluation results and creating an individually optimized study plan in cooperation with learning support software; and means for recognizing the user's emotional state using an image capture device and reflecting this emotional data in the individual qualitative advice and optimized study plan. This provides individually optimized feedback that takes into account the student's emotional state, enabling improved learning effectiveness and more efficient education.

[0671] A "generative AI model" is a type of artificial intelligence that learns patterns from data and makes predictions and generates data based on new data.

[0672] "Test Answers" refers to answer data submitted by a user as part of an examination or assessment.

[0673] "Evaluation" is the process of using a generative AI model to determine whether a test answer is correct or incorrect.

[0674] A "correct answer" is the appropriate response to a test question.

[0675] An "error" is an inappropriate response to a test question.

[0676] A "difficult answer to judge" is an answer that is difficult for the generative AI model to determine whether it is correct or incorrect.

[0677] "Evaluation result" is the result of judging whether the answer generated by the generative AI model is correct or incorrect.

[0678] "Score" refers to the score of each user calculated based on the evaluation results.

[0679] "Qualitative advice" is specific, qualitative feedback provided based on the results of the assessment.

[0680] A "study plan" is a study plan optimized for each individual user, created based on the assessment results and qualitative advice.

[0681] "Image capture device" refers to a camera or other image capture device that captures image data for recognizing a user's emotional state.

[0682] "Emotional state" refers to the psychological state detected from the user's facial expression, tone of voice, etc.

[0683] This invention is a system that uses generative AI models and emotion recognition technology to improve test scoring and learning support. Specifically, it involves the collaboration of a server, a user terminal, and an image capture device.

[0684] First, the user's device collects test answers and sends them to the server. This answer data is sent in JSON format or similar, and the server parses it and stores it in a database. For example, when a student takes an online test, the answer data is sent to the server, which analyzes the data and stores it in a database.

[0685] The server then inputs the answer data stored in the database into the generative AI model, which evaluates each answer as "correct," "incorrect," or "difficult to judge." The evaluation results are then stored back in the database. For example, a student's answer "5 x 3 = 15" is determined to be correct and recorded as "correct," while the answer "4 x 3 = 11" is determined to be incorrect and recorded as "incorrect."

[0686] The server then calculates each student's score based on the evaluation results. Each "correct" answer is worth 1 point, while "incorrect" and "difficult to judge" answers are worth 0 points. The total score is then recorded in the database. For example, if a student answers 10 questions correctly and 2 questions incorrectly, the total score will be recorded as 10 points.

[0687] The server further analyzes the user's emotional state using an emotion engine. The emotion engine analyzes the user's facial expression through an image capture device (such as a camera) and acquires emotion data. For example, if a student shows an anxious expression, the emotion engine recognizes this and records the emotion data as "anxiety."

[0688] Based on the acquired evaluation results and emotion data, the server generates qualitative advice optimized for each student. This advice is personalized using a generative AI model. For example, by inputting a prompt such as "Advice for a student who is strong in calculation problems but is anxious about applied problems," the generative AI model generates specific feedback such as "Practice applied problems more to gain confidence."

[0689] This system can recognize the user's emotional state and provide advice and study plans based on that, thereby improving learning effectiveness and streamlining education.

[0690] Examples of prompts for generative AI models include:

[0691] "Advice for students who are good at calculation problems but feel uneasy about applied problems."

[0692] Finally, teachers can supplement the qualitative advice generated by the server with additional comments, resulting in more personalized feedback for students.

[0693] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[0694] Step 1:

[0695] The user's device collects test answers and sends them to the server. Specifically, the user enters the answers on the online platform, and the data is sent to the server in JSON format. The input is the user's test answer data, and the output is the data sent to the server.

[0696] Step 2:

[0697] The server receives the submitted test answer data and stores it in a database. During this process, the server parses the JSON data and stores each item in the appropriate field in the database. The input is the user's test answer data, and the output is the answer data stored in the database.

[0698] Step 3:

[0699] The server inputs the answer data stored in the database into the generative AI model, and evaluates each answer as "correct," "incorrect," or "difficult to judge." Here, the server passes the answer data to the generative AI model, which analyzes it and returns the evaluation result. The input is the answer data stored in the database, and the output is the evaluation result.

[0700] Step 4:

[0701] The server stores the evaluation results in a database. Specifically, the evaluation results from the generative AI model are recorded in association with the corresponding answer data in the database. The input is the evaluation result of the generative AI model, and the output is the evaluation result recorded in the database.

[0702] Step 5:

[0703] The server calculates the score based on the evaluation results. Each "correct" answer is given 1 point, while "incorrect" and "difficult to judge" answers are given 0 points, and the total score is calculated. In this process, the server aggregates the evaluation results, calculates the individual scores, and stores them in a database. The input is the evaluation results, and the output is the calculated total score.

[0704] Step 6:

[0705] The server uses an emotion engine to analyze the user's emotional state. An image capture device is used to collect the user's facial expression data, which is then analyzed by the emotion engine. The input is the user's facial expression data, and the output is emotion data.

[0706] Step 7:

[0707] The server generates individual qualitative advice based on the evaluation results and emotional data. The emotional data and evaluation results are input into the generative AI model as prompts to generate specific feedback. The input is the evaluation results and emotional data, and the output is the generated qualitative advice.

[0708] Step 8:

[0709] The server provides the generated qualitative advice to the teacher's device, where the teacher can add supplementary comments. Sample comments generated in advance by the generative AI model are displayed, and the teacher can add supplementary comments or make corrections to them. The input is the generated qualitative advice, and the output is feedback added by the teacher.

[0710] Step 9:

[0711] The user device retrieves and displays their own evaluation results, qualitative advice, and optimized learning plans from the server. The server sends the evaluation results and feedback to the user device, and the user confirms this information. The input is the feedback data sent from the server, and the output is the learning information displayed on the user device.

[0712] The above is an explanation of each processing step and specific operation of this system.

[0713] 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.

[0714] 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.

[0715] 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.

[0716] [Third embodiment]

[0717] FIG. 5 shows an example of the configuration of a data processing system 310 according to the third embodiment.

[0718] 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.

[0719] 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).

[0720] 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.

[0721] 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.

[0722] 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).

[0723] 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.

[0724] 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.

[0725] 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.

[0726] 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.

[0727] 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.

[0728] 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."

[0729] This invention is a system that utilizes a generative artificial intelligence model to improve the efficiency of test scoring and provide learning support optimized for each student. Below, we will explain in detail each element of the system and its operation.

[0730] 1. Collecting test answers

[0731] The server receives the test data answered by students. This data is sent to the server by teachers or educational institutions and parsed into a data format such as JSON. The server stores the received data in a database.

[0732] Example: Student A takes an online math test and sends the answer data to a server, which analyzes the data and stores it in a database.

[0733] 2. Generative AI scoring

[0734] The server inputs the answer data stored in the database into the generative AI model and evaluates each answer as "〇" (correct), "×" (incorrect), or "△" (determined). The evaluation results are recorded in the database.

[0735] Example: Student A's answer "5 x 3 = 15" is judged to be correct and recorded as "Yes." On the other hand, Student A's answer "4 x 3 = 11" is judged to be incorrect and recorded as "No."

[0736] 3. Calculation of the scores

[0737] The server calculates the score for each student based on the evaluation results. For example, a "good" score is 1 point, an "bad" score is 0 point, and a "bad" score is also 0 point. The calculated scores are saved in a database.

[0738] Example: If Student A answers 10 questions correctly and 2 questions incorrectly, his total score will be recorded as 10 points.

[0739] 4. Generating personalized advice

[0740] The server uses a generative AI model to analyze each student's answer patterns and generate qualitative advice, providing feedback tailored to each student's strengths and weaknesses.

[0741] Example: In the case of Student A, the advice generated is "You got high marks in the calculation questions, but you need to improve in the application questions."

[0742] 5. Create a study plan

[0743] The server analyzes the assessment results and works with learning support software to create an optimized learning plan for each student, providing specific guidelines for effective learning.

[0744] Example: Student A is proposed a learning plan that "strengthens review of calculation problems and practice of applied problems."

[0745] 6. Teacher's Comments

[0746] Pre-generated sample comments are displayed on the device, and teachers can add or correct them. The final comments are sent to the server and stored in a database.

[0747] Example: In response to the comment made by the generating AI, "You are strong at calculation problems," the teacher adds, "You are particularly good at problems with equations."

[0748] 7. Viewing Results and Receiving Feedback

[0749] The user's device displays the grades, advice, and study plans obtained from the server, allowing students to advance their studies based on this information.

[0750] Example: Student A checks the grades and feedback on their own device to understand what they should study next.

[0751] As described above, the present invention is a system that improves the efficiency of test grading and provides optimal learning support for each student. This is expected to improve the efficiency of educational settings and the learning effectiveness of students.

[0752] The processing flow will be explained below.

[0753] Step 1:

[0754] The server receives the test answers sent from each device. The answer data is sent in JSON format, and when the server receives the HTTP request, it parses the data and saves it in a database.

[0755] Step 2:

[0756] The server reads the test answers stored in the database, inputs them into the generative AI model, and evaluates them. The generative AI model labels correct answers as "O," incorrect answers as "X," and answers that are difficult to judge as "△." The evaluation results are then saved back into the database.

[0757] Step 3:

[0758] The server calculates each student's score based on the evaluation results. Each "O" is counted as 1 point, while "X" and "△" are counted as 0 points, and the total score is recorded in the database.

[0759] Step 4:

[0760] The server uses the generative AI model to generate qualitative advice based on each student's answer patterns, including specific suggestions for improving their learning, which are also stored in a database.

[0761] Step 5:

[0762] The server analyzes the assessment results and works with the learning support software to create an optimized learning plan for each student. The learning plan takes into account the student's strengths and weaknesses and recommends specific learning activities and materials. The generated learning plan is also stored in a database.

[0763] Step 6:

[0764] A pre-generated sample comment is displayed on the device. The teacher uses this as a reference to make any necessary corrections or additions, and then creates the final comment. The created comment is sent to the server and stored in a database.

[0765] Step 7:

[0766] The user's device retrieves and displays their own assessment results, qualitative advice, and an optimized learning plan from the server. Based on this information, students can confirm their learning guidelines and understand what they should study next.

[0767] Example 1

[0768] 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."

[0769] In today's educational environment, grading tests requires a great deal of effort and time. Furthermore, providing individualized feedback and learning plans for each student places an even greater burden on teachers. Therefore, there is a need for a system that can efficiently grade tests and provide optimized learning support for each student.

[0770] 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.

[0771] In this invention, the server includes means for evaluating received educational data using a generative AI model and identifying correct answers, incorrect answers, and difficult answers, means for recording the evaluation results and calculating a score for each user, means for generating qualitative feedback for each user based on the evaluation results, and means for analyzing the evaluation results and creating an optimized learning plan for each user in cooperation with educational support software. This makes it possible to streamline test scoring and provide personalized learning support for each student.

[0772] A "generative artificial intelligence model" is an artificial intelligence model that uses machine learning algorithms to analyze data and make predictions.

[0773] "Educational data" refers to education-related information such as answer data, test results, and learning history provided by users (students).

[0774] "Evaluation" is the process of using a generative artificial intelligence model to identify correct, incorrect, and difficult-to-judge answers based on received educational data.

[0775] "Feedback" refers to personalized learning improvement suggestions and advice provided based on students' test results and answer patterns.

[0776] A "study plan" is a plan for providing optimized learning content and schedules based on each student's strengths and weaknesses.

[0777] "Educational support software" is software that supports educational activities, such as creating learning plans, managing progress, and providing teaching materials.

[0778] "Server" means a computer system for collecting, analyzing, evaluating, and recording educational data.

[0779] "User" means a student or person receiving education who uses the system to learn.

[0780] "Score" refers to the score for each student calculated based on the test evaluation results.

[0781] The present invention is a system that utilizes a generative artificial intelligence model to improve the efficiency of test scoring and provide optimized learning support for each student. A specific implementation method of the system is described below.

[0782] First, the server receives the educational data sent from the device. This educational data includes test data answered by students and is sent in a format such as JSON. The server parses this data and stores it in a database. The hardware used here is a standard server computer, and software such as Apache or MySQL can be used.

[0783] The server then reads the educational data stored in the database and evaluates each answer using a generative AI model. The generative AI model uses machine learning algorithms to distinguish between correct, incorrect, and difficult answers from the input data. Potential software used is TensorFlow or PyTorch. The evaluation results are recorded in the database.

[0784] Based on the evaluation results, the server calculates a score for each student. Correct answers are assigned 1 point, incorrect answers 0 points, and difficult-to-judge answers are also assigned 0 points. The total score is then stored in a database. In addition, the server uses a generative AI model to analyze each student's answer patterns and generate qualitative feedback. This feedback is also stored in the database.

[0785] The server then connects to educational support software to create an optimal learning plan for each student based on the assessment results and feedback. Software such as a learning management system (LMS) can be used. The learning plan is customized based on each student's strengths and weaknesses and stored in a database.

[0786] The teacher's role is also important. Pre-generated sample comments are displayed on the device, and the teacher can add or correct them. The final comments sent from the device are saved on the server.

[0787] Finally, users can use their own devices to check the grades, feedback, and study plans retrieved from the server, allowing students to understand their own learning progress and clarify what they should work on next.

[0788] As a specific example, consider a scenario in which Student A takes an online test on a device and sends the answers to a server. The server receives the answer data and evaluates it based on the generative AI model, recording the correct answer "5 x 3 = 15" as "Yes" and the incorrect answer "4 x 3 = 11" as "No." The server then aggregates the evaluation results and saves them in a database as a total score of 10 points for Student A. It then generates feedback such as "You scored well on the calculation problems, but you show weaknesses in the application problems," and creates a learning plan through learning support software to "review the calculation problems and strengthen your practice of the application problems."

[0789] An example of a prompt is "Please solve the following equation: 5 x 3 =?"

[0790] As described above, this system makes it possible to improve the efficiency of test grading and also to provide individualized learning support for each student.

[0791] The flow of the identification process in the first embodiment will be described with reference to FIG.

[0792] Step 1: Collecting educational data

[0793] The server receives the educational data sent from the device. The input data is the test data answered by the student, and is received in a format such as JSON. The server parses this data and saves it in a database. Specifically, when Student A finishes the online test on his / her device and clicks the "Submit" button, the answer data is sent to the server. The server analyzes this data and stores it in a database. The output is the analyzed educational data.

[0794] Step 2: Evaluation using generative AI models

[0795] The server reads the educational data stored in the database and inputs it into the generative AI model. The input data are the students' answers. The generative AI model distinguishes between correct answers, incorrect answers, and answers that are difficult to judge, and generates an evaluation result. Specifically, the server evaluates the answer "5 x 3 = 15" as correct "Yes" and the answer "4 x 3 = 11" as incorrect "No". This evaluation result is recorded in the database. The output is the evaluated educational data.

[0796] Step 3: Calculating the scores

[0797] The server reads the evaluation results stored in the database and calculates the score for each student. The input data is the evaluation results. For example, a correct answer "〇" is worth 1 point, an incorrect answer "×" is worth 0 points, and a difficult answer "△" is also worth 0 points, and the total score is calculated. In concrete terms, the server tallies the number of correct answers and the number of errors for Student A and calculates the total score. The output is the score for each student.

[0798] Step 4: Generate qualitative feedback

[0799] The server uses a generative AI model to analyze each student's answer patterns and generate qualitative feedback. The input data is the evaluation results. The generative AI model classifies strengths and weaknesses and generates specific advice. Specifically, the server generates feedback to Student A that "You are good at calculation problems, but have weaknesses in applied problems." The output is feedback.

[0800] Step 5: Create an optimized study plan

[0801] The server analyzes the generated feedback and evaluation results and works with the learning support software to create an optimal learning plan for each student. The input data are the feedback and evaluation results. Specifically, the server uses the learning support software to create a learning plan for Student A that "reviews calculation problems and strengthens practice of applied problems." The output is the learning plan.

[0802] Step 6: Teacher comments

[0803] The device provides the teacher with pre-generated sample comments, which the teacher can then add or correct. The input data are the sample comments. Specifically, the teacher checks Student A's feedback and learning plan on the device, and adds "He is particularly good at equation problems" to "He is strong at calculation problems." The server saves the added comments in a database. The output is the final comment.

[0804] Step 7: View results and receive feedback

[0805] The user's device displays the grading results, feedback, and learning plan obtained from the server. The input data is the learning-related data sent from the server. Specifically, Student A checks the latest grading results and feedback on his or her own device and understands the learning content he or she should tackle next. The output is the displayed learning-related data.

[0806] (Application example 1)

[0807] 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."

[0808] Traditionally, evaluating the performance of factory robot operators has been time-consuming and labor-intensive, and it has been difficult to maintain accuracy and consistency in the evaluations. Traditional evaluation methods have been largely subjective, making it difficult to provide individually optimized training plans. This has led to delays in improving operator skills and the risk of reduced production efficiency.

[0809] 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.

[0810] In this invention, the server includes means for evaluating received information using a generative artificial intelligence model and identifying correct answers, incorrect answers, and answers that are difficult to evaluate, means for recording the evaluation results and calculating an evaluation score for each subject, means for generating qualitative advice for each subject based on the evaluation results, and means for analyzing the evaluation results and creating a training plan optimized for each subject in cooperation with the assistance software. This makes it possible to objectively and efficiently evaluate an operator's performance and provide individually optimized feedback and training plans.

[0811] A "generative artificial intelligence model" is an algorithm that uses artificial intelligence technology to analyze data and generate responses or decisions based on the results.

[0812] "Information" is a concept that encompasses facts, data, or knowledge about a particular subject.

[0813] "Evaluation" is the act of analyzing received information and making a judgment based on specific criteria.

[0814] A "correct answer" is the only correct expected response to a problem or question.

[0815] An "error" is an answer or action that is incorrect compared to the correct answer.

[0816] "Answers that are difficult to evaluate" are ambiguous answers that the generative AI model cannot clearly determine as correct or incorrect.

[0817] "Evaluation results" are the results of evaluation obtained by the generative artificial intelligence model, including identification of correct answers, incorrect answers, and answers that are difficult to evaluate.

[0818] "Individual subject" means the individual being evaluated.

[0819] The "evaluation score" is a numerical representation of the performance of each subject.

[0820] "Qualitative advice" refers to specific, verbalized instructions or suggestions based on the results of the assessment.

[0821] A "training plan" is a plan designed to help an individual subject acquire specific skills or knowledge.

[0822] "Support Software" means a software program for performing the calculations and analyses necessary for the evaluation and development of a training plan.

[0823] "Individually optimized feedback" refers to advice that is customized to each individual subject's specific needs and circumstances.

[0824] The present invention is a system that utilizes generative artificial intelligence models to efficiently evaluate the performance of factory robot operators and provide individually optimized feedback and training plans. Below, we will explain in detail each element of the system and its operation.

[0825] 1. Collecting Operational Data

[0826] The server collects data from the factory robot's operations through sensors and a logging system, and sends it to the server. This data is parsed into a data format such as JSON, and the server stores the received data in a database.

[0827] Example: When operator A controls the robot and commands it to "move," the coordinate data and timestamp of that movement are sent to the server.

[0828] 2. Evaluation by generative AI

[0829] The server inputs the operation data stored in the database into the generative AI model and evaluates the accuracy, efficiency, error rate, etc. of each operation. The evaluation results are recorded in the database.

[0830] Example: If Operator A's operation "Pick item A" is performed accurately and quickly, it will be recorded as a "High Score." On the other hand, if "Pick item B" is performed incorrectly, it will be recorded as a "Low Score."

[0831] 3. Calculation of evaluation results

[0832] The server calculates the performance score for each operator based on the evaluation results. For example, a "high rating" is 2 points, a "low rating" is 0 points, and the total score is calculated. The calculated scores are saved in a database.

[0833] Example: If Operator A has 10 likes and 2 dislikes, their total score will be recorded as 20 points.

[0834] 4. Generating personalized advice

[0835] The server uses a generative AI model to analyze each operator's operating patterns and generate qualitative advice, providing feedback tailored to each operator's individual strengths and weaknesses.

[0836] Example: For Operator A, the advice generated is "Your moving operations are highly rated, but your picking operations need improvement."

[0837] 5. Create a training plan

[0838] The server analyzes the evaluation results and works with the assistance software to create an optimized training plan for each operator, providing specific guidelines for operators to effectively improve their skills.

[0839] Example: Operator A is proposed a training plan to "strengthen training in picking operations."

[0840] 6. Additional Supervisor Comments

[0841] Pre-generated sample comments are displayed on the terminal, and the supervisor can add or correct them. The final comments are sent to the server and stored in a database.

[0842] Example: In response to the generated AI's comment "Picking accuracy is low," the supervisor adds, "Please note that the picking accuracy of item B is particularly low."

[0843] 7. Viewing Results and Receiving Feedback

[0844] The user's device displays the evaluation results, advice, and training plans obtained from the server, allowing the operator to improve their own operating skills based on this information.

[0845] Example: Operator A checks the evaluation results and feedback on his own device and understands the next training content he should work on.

[0846] The system uses generative AI models using AI frameworks such as TensorFlow and PyTorch, databases such as PostgreSQL, and API servers such as Flask and Django as its main software components.

[0847] Example prompt sentence:

[0848] It collects operation data from the robot operator and evaluates their performance using a generative AI model. Based on the evaluation results, it generates individualized feedback and training plans and provides feedback to the operator.

[0849] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[0850] Step 1:

[0851] Operational Data Collection

[0852] The server collects data on the operations of factory robot operators. This data is acquired through sensors and logging systems and sent to the server in formats such as JSON. The server stores the received data in a database, thereby recording the operator's operation history.

[0853] Input: Operator operation data (e.g. movement coordinates, item pick data)

[0854] Output: Operational data stored in a database

[0855] Step 2:

[0856] Generative AI evaluation

[0857] The server inputs the operation data stored in the database into the generative AI model and evaluates the accuracy, efficiency, error rate, etc. of each operation. The generative AI model analyzes the operation data and identifies correct, incorrect, and difficult-to-evaluate operations. The evaluation results are recorded in the database.

[0858] Input: Operational data stored in the database

[0859] Output: Evaluation result (e.g., correct answer, incorrect answer, difficult operation to evaluate)

[0860] Step 3:

[0861] Aggregation of evaluation results

[0862] The server calculates the performance score for each operator based on the evaluation results. For example, a "high rating" is given 2 points, and a "low rating" is given 0 points, and the total score is calculated. The calculated scores are saved in a database.

[0863] Input: Evaluation result

[0864] Output: Performance score

[0865] Step 4:

[0866] Generating personalized advice

[0867] The server uses a generative AI model to analyze each operator's operating patterns and generate qualitative advice, providing feedback tailored to each operator's strengths and weaknesses. The advice is then recorded in a database.

[0868] Input: Evaluation results and operation patterns

[0869] Output: Qualitative advice

[0870] Step 5:

[0871] Creating a training plan

[0872] The server analyzes the evaluation results and works with the assistance software to create an optimized training plan for each operator, providing specific guidelines for the operator to effectively improve their skills. The training plan is then saved in a database.

[0873] Input: Evaluation results and qualitative advice

[0874] Output: Training plan

[0875] Step 6:

[0876] Additional supervisor comments

[0877] The terminal provides the supervisor with pre-generated sample comments, which the supervisor can add or correct, and the final comments are sent to the server and stored in a database.

[0878] Input: Generated comment sample

[0879] Output: Annotated comments

[0880] Step 7:

[0881] Viewing results and receiving feedback

[0882] The user's device displays the evaluation results, advice, and training plans obtained from the server, allowing the operator to improve their own operating skills based on this information.

[0883] Input: Assessment results, advice, training plan

[0884] Output: Information displayed on the user's terminal

[0885] 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.

[0886] This invention is a system that utilizes a generative artificial intelligence model to improve the efficiency of test scoring and provide learning support optimized for each student. Furthermore, by recognizing the user's emotional state and incorporating this into the learning support, more effective learning support is realized.

[0887] Configuration and Operation

[0888] 1. Collecting test answers

[0889] The server receives the test answers from each device. This answer data is sent in JSON format, and the server parses it and stores it in a database. This allows all answer data to be managed centrally.

[0890] Example: Student A takes an online math test and sends the answer data to a server, which analyzes the data and stores it in a database.

[0891] 2. Generative AI scoring

[0892] The server inputs the answer data stored in the database into the generative AI model and evaluates each answer as "〇" (correct), "×" (incorrect), or "△" (determined). The evaluation results are then saved back into the database.

[0893] Example: Student A's answer "5 x 3 = 15" is judged to be correct and recorded as "Yes." On the other hand, Student A's answer "4 x 3 = 11" is judged to be incorrect and recorded as "No."

[0894] 3. Calculation of the scores

[0895] The server calculates each student's score based on the evaluation results. Each "O" is worth 1 point, and each "X" and "△" is worth 0 point. The server calculates the total score and records the total score in the database.

[0896] Example: If Student A answers 10 questions correctly and 2 questions incorrectly, his total score will be recorded as 10 points.

[0897] 4. User Emotion Recognition

[0898] The server uses an emotion engine to analyze the user's emotional state. The emotion engine analyzes the user's facial expressions and tone of voice via a camera or microphone to obtain emotional data. Based on this, the student's emotional state is determined and recorded.

[0899] Example: If Student A looks anxious during a test, the emotion engine will recognize this and record the emotion data as "anxious."

[0900] 5. Generating personalized advice

[0901] The server uses a generative AI model to generate qualitative advice based on each student's answer patterns and emotional data, providing more personalized feedback.

[0902] Example: Advice generated for Student A is, "You are good at calculation problems, but tend to feel uneasy with applied problems. You should practice applied problems more and also practice to gain confidence."

[0903] 6. Create a study plan

[0904] The server analyzes the assessment results and emotional data and works with learning support software to create an optimized learning plan, which includes specific learning activities and materials that take emotional state into account.

[0905] Example: Student A's study plan might include relaxation exercises before tackling applied problems, helping him focus on his studies while reducing anxiety.

[0906] 7. Teacher's Comments

[0907] Pre-generated sample comments are displayed on the device, and teachers can add or correct them. The final comments are sent to the server and stored in a database.

[0908] Example: In response to the comment made by the generating AI, "You are strong at calculation problems," the teacher adds the comment, "You are particularly good at problems with equations."

[0909] 8. Viewing Results and Receiving Feedback

[0910] The user's device retrieves and displays their own assessment results, qualitative advice, and an optimized learning plan from the server. Based on this information, students can confirm their future learning strategy and understand what they should tackle next.

[0911] Example: Student A checks the assessment results and feedback on his / her own device and understands what learning he / she should do next through a learning plan based on emotional data.

[0912] In this way, by combining a generative AI model and an emotion engine, the present invention provides a system that efficiently grades students, provides personalized feedback, and provides learning plans, which is expected to improve the efficiency of classrooms and student learning outcomes.

[0913] The processing flow will be explained below.

[0914] Step 1:

[0915] The server receives the test answers sent from each device. The test answers are sent in JSON format, and upon receiving the HTTP request, the server parses the answer data in JSON format and stores it in a database.

[0916] Step 2:

[0917] The server inputs the test answers stored in the database into the generative AI model and evaluates each answer as "〇" (correct), "×" (incorrect), or "△" (delayed judgment). The evaluation results are then saved in the database again.

[0918] Step 3:

[0919] The server calculates each student's score based on the evaluation results. Specifically, each "OK" is counted as 1 point, while "X" and "△" are counted as 0 points, and the total score is recorded in the database.

[0920] Step 4:

[0921] The server uses an emotion engine to recognize the user's emotional state. The emotion engine analyzes the user's facial expressions and voice through a camera and microphone to obtain emotional data such as "happiness," "sadness," and "surprise." This data is sent to the server at the same time as the test is received and stored in a database.

[0922] Step 5:

[0923] The server uses the generative AI model to generate qualitative advice based on the evaluation results and emotional data. The advice is also personalized, taking into account feedback based on the emotional data. This advice is also stored in a database.

[0924] Step 6:

[0925] The server analyzes the assessment results and emotional data, and works with learning support software to create an optimized learning plan for each student. The learning plan includes content that takes into account the student's emotional state, such as relaxation exercises or short breaks to refresh the mind. The generated learning plan is also stored in a database.

[0926] Step 7:

[0927] Pre-generated sample comments are displayed on the device, and the teacher can add any necessary corrections or additions. The comments are then sent to the server and stored in a database.

[0928] Step 8:

[0929] The user's device retrieves and displays their own assessment results, qualitative advice, and an optimized learning plan from the server. Based on this information, students can confirm their future learning strategy and understand what they should tackle next.

[0930] Step 9:

[0931] The user studies based on the study plan provided along with test feedback. Students use this study plan as a reference and periodically report their progress to the server, which then records this in a database. This allows the server to track the student's learning progress and emotional state and adjust the study plan as needed.

[0932] Example 2

[0933] 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."

[0934] In traditional educational systems, test scoring is often done manually, which not only requires a lot of time and effort, but also can lead to inconsistent and inaccurate scoring. It is also difficult to properly understand each student's emotional state and learning situation and provide individual feedback and learning plans based on that. This results in a lack of personalized instruction to maximize students' learning outcomes.

[0935] The identification process by the identification processing unit 290 of the data processing device 12 in Example 2 is realized by the following means. In this invention, the server includes: means for evaluating received answer data using a generative AI model and identifying correct answers, incorrect answers, and answers that are difficult to judge; means for recording the evaluation results and calculating scores for each individual; means for inputting the answer data into the generative AI model and performing the evaluation; means for analyzing the evaluation results and using an emotion engine that recognizes the emotional state of the individual; means for generating individual feedback based on the analyzed emotion data; and means for analyzing the evaluation results and the emotion data and creating an optimized study plan. This improves the efficiency and consistency of test grading and makes it possible to provide personalized feedback and study plans based on the emotional state of each student.

[0936] A "generative artificial intelligence model" is an artificial intelligence algorithm that can analyze data and determine answers and patterns based on certain rules.

[0937] "Answer data" is digital data that indicates the results of a test that a user answers using a terminal.

[0938] "Evaluation results" are data that are analyzed by a generative artificial intelligence model and include the results of identifying correct answers, incorrect answers, and answers that are difficult to judge.

[0939] The "emotion engine" is an emotional state recognition algorithm that analyzes a user's facial expressions and tone of voice using data collected through devices such as cameras and microphones.

[0940] "Feedback" refers to individual advice and guidance provided to users based on the analyzed evaluation results and emotional data.

[0941] A "learning plan" is a plan that includes an optimized learning schedule and selection of teaching materials for each student based on evaluation results and emotional data.

[0942] "Database" means the data structure and storage location where the information managed within a system is collected.

[0943] A "terminal" is an electronic device, such as a computer or mobile device, through which a user completes a test or interacts with the system.

[0944] "Educator" refers to the person in charge of education who supplements and corrects the learning plan and feedback, and provides the final instruction.

[0945] The term "system" refers to a collection of various hardware and software components that constitute the present invention as a whole, and is a computer configuration for achieving a specific purpose.

[0946] MODE FOR CARRYING OUT THE INVENTION

[0947] This invention is a system that utilizes a generative artificial intelligence model and an emotion engine to improve the efficiency of test scoring in educational settings and provide learning support optimized for each student. This system is composed of the following elements: a server, a terminal, and a user.

[0948] composition

[0949] 1. Server:

[0950] The server is equipped with a generative artificial intelligence model and an emotion engine, analyzes answer data received from multiple devices, and stores evaluation results and emotion data in a database.

[0951] The server generates personalized feedback and an optimized learning plan and provides it to the user terminal.

[0952] 2. Terminal:

[0953] The device provides an interface for users to answer questions, and transmits the user's facial expressions and voice to the emotion engine via a camera and microphone.

[0954] The terminal displays the generated feedback and learning plan to the user.

[0955] 3. User:

[0956] Users answer the test using their device and send the results to the server. Emotion data is collected by the emotion engine, allowing them to receive more effective learning support.

[0957] Specific implementation details

[0958] The server first parses the answer data received from the device in JSON format and stores it in a database. It then uses a generative AI model to evaluate the answer data and identify correct, incorrect, and difficult answers. The evaluation results are also stored in the database.

[0959] The server then uses an emotion engine to analyze the user's facial expressions and tone of voice to obtain emotional data, which is then stored in a database for future use in learning support.

[0960] The server uses a generative AI model to generate personalized feedback based on the evaluation results and emotional data. This feedback is sent to the device and displayed to the user. An optimized learning plan is also generated and provided to the user based on the user's evaluation results and emotional state.

[0961] Specific examples

[0962] In this example, the server receives Student A's math test answer data, analyzes it, and saves it in a database. The generative AI model evaluates "5 x 3 = 15" as the correct answer and records it as "Yes." On the other hand, the answer "4 x 3 = 11" is evaluated as an incorrect answer and recorded as "No." The server also uses its emotion engine to recognize Student A's anxious facial expression via the camera and record the data.

[0963] The server then generates feedback for Student A, such as: "You're strong at calculation problems, but tend to feel uneasy with applied problems. Practice more applied problems and do some practice to build your confidence." This advice can be supplemented by a human teacher and provided as a final comment.

[0964] The lesson plan includes relaxation exercises before tackling applied problems, designed to help Student A focus on learning while reducing anxiety.

[0965] Prompt Sentence Examples

[0966] "Provide personalized study advice based on students' math test answers and their current emotional state."

[0967] "Generate a lesson plan that takes into account the student's insurmountable challenges and the resulting emotional changes."

[0968] In this way, the present invention is a system that combines a generative AI model and an emotion engine to provide efficient grading and personalized learning support, which is expected to improve the efficiency of classrooms and student learning outcomes.

[0969] The flow of the identification process in the second embodiment will be described with reference to FIG.

[0970] Step 1: Collect test answers

[0971] Specific operation: The user answers the test on the device. The device generates the user's answer data in JSON format and sends it to the server.

[0972] Input: User's answer data (JSON format)

[0973] Data processing: Parse the answer data received by the server and extract the answer content

[0974] Output: Parsed answer data stored in a database

[0975] Step 2: Generative AI scoring

[0976] How it works: The server retrieves answer data from the database and inputs it into the generative AI model, which then evaluates the answer and returns the result.

[0977] Input: Answer data

[0978] Data processing: The generative AI model evaluates the answer as "〇" (correct), "×" (incorrect), or "△" (withhold judgment).

[0979] Output: The evaluation result (yes, no, or triangle) is saved in the database.

[0980] Step 3: Calculating the scores

[0981] Specific operation: The server calculates the score for each student based on the evaluation results, calculates the score, and records the total score in the database.

[0982] Input: Evaluation result

[0983] Data calculation: Each "〇" is calculated as 1 point, and "×" and "△" are calculated as 0 points.

[0984] Output: The total score is saved in the database.

[0985] Step 4: Recognizing user emotions

[0986] How it works: When a user takes a test on their device, the camera and microphone are activated to collect data. The server then uses the emotion engine to analyze the data and determine the user's emotion.

[0987] Input: User's facial expression and voice data

[0988] Data processing: The emotion engine analyzes facial expressions and tone of voice to obtain emotional data.

[0989] Output: The determined emotion data is saved in the database.

[0990] Step 5: Generate personalized advice

[0991] Specific operation: The server uses a generative AI model to generate individual advice based on the evaluation results and emotion data.

[0992] Input: Evaluation results and emotion data

[0993] Data computation: Generative AI models generate advice based on answer patterns and emotional state

[0994] Output: Individual advice stored in a database

[0995] Step 6: Create a study plan

[0996] Specific operation: The server analyzes the evaluation results and emotional data, and works with the learning support software to create an optimized learning plan.

[0997] Input: Evaluation results and emotion data

[0998] Data calculations: Select learning activities and materials based on assessment results and emotional state

[0999] Output: The learning plan is saved in the database.

[1000] Step 7: Teacher comments

[1001] Specific operation: The generated comment sample is displayed on the device, and the educator adds or corrects it. The final comment is sent to the server and stored in the database.

[1002] Input: Generated comment sample

[1003] Data processing: Educators supplement and correct comments

[1004] Output: Supplementary and corrected comments are saved in the database

[1005] Step 8: View results and receive feedback

[1006] Specific operation: The user's device retrieves and displays the evaluation results, advice, and learning plan from the server.

[1007] Input: Assessment results, feedback, learning plans

[1008] Data calculation: The server retrieves the necessary information from the database and sends it to the terminal in the appropriate format.

[1009] Output: Assessment results, feedback, and learning plans displayed on the user's device

[1010] (Application example 2)

[1011] 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."

[1012] Conventional learning support systems do not adequately consider the emotional state of each student, and the feedback itself is uniform. This can lead to significant differences in learning outcomes for each student, delays in individual optimization, and a decline in student motivation. Furthermore, the time it takes for teachers to provide feedback reduces the efficiency of education.

[1013] The identification processing by the identification processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means. In this invention, the server includes: means for evaluating received test answers using a generative AI model and identifying correct answers, incorrect answers, and difficult answers; means for recording the evaluation results and calculating individual scores; means for generating individual qualitative advice based on the evaluation results; means for analyzing the evaluation results and creating an individually optimized study plan in cooperation with learning support software; and means for recognizing the user's emotional state using an image capture device and reflecting this emotional data in the individual qualitative advice and optimized study plan. This provides individually optimized feedback that takes into account the student's emotional state, enabling improved learning effectiveness and more efficient education.

[1014] A "generative AI model" is a type of artificial intelligence that learns patterns from data and makes predictions and generates data based on new data.

[1015] "Test Answers" refers to answer data submitted by a user as part of an examination or assessment.

[1016] "Evaluation" is the process of using a generative AI model to determine whether a test answer is correct or incorrect.

[1017] A "correct answer" is the appropriate response to a test question.

[1018] An "error" is an inappropriate response to a test question.

[1019] A "difficult answer to judge" is an answer that is difficult for the generative AI model to determine whether it is correct or incorrect.

[1020] "Evaluation result" is the result of judging whether the answer generated by the generative AI model is correct or incorrect.

[1021] "Score" refers to the score of each user calculated based on the evaluation results.

[1022] "Qualitative advice" is specific, qualitative feedback provided based on the results of the assessment.

[1023] A "study plan" is a study plan optimized for each individual user, created based on the assessment results and qualitative advice.

[1024] "Image capture device" refers to a camera or other image capture device that captures image data for recognizing a user's emotional state.

[1025] "Emotional state" refers to the psychological state detected from the user's facial expression, tone of voice, etc.

[1026] This invention is a system that uses generative AI models and emotion recognition technology to improve test scoring and learning support. Specifically, it involves the collaboration of a server, a user terminal, and an image capture device.

[1027] First, the user's device collects test answers and sends them to the server. This answer data is sent in JSON format or similar, and the server parses it and stores it in a database. For example, when a student takes an online test, the answer data is sent to the server, which analyzes the data and stores it in a database.

[1028] The server then inputs the answer data stored in the database into the generative AI model, which evaluates each answer as "correct," "incorrect," or "difficult to judge." The evaluation results are then stored back in the database. For example, a student's answer "5 x 3 = 15" is determined to be correct and recorded as "correct," while the answer "4 x 3 = 11" is determined to be incorrect and recorded as "incorrect."

[1029] The server then calculates each student's score based on the evaluation results. Each "correct" answer is worth 1 point, while "incorrect" and "difficult to judge" answers are worth 0 points. The total score is then recorded in the database. For example, if a student answers 10 questions correctly and 2 questions incorrectly, the total score will be recorded as 10 points.

[1030] The server further analyzes the user's emotional state using an emotion engine. The emotion engine analyzes the user's facial expression through an image capture device (such as a camera) and acquires emotion data. For example, if a student shows an anxious expression, the emotion engine recognizes this and records the emotion data as "anxiety."

[1031] Based on the acquired evaluation results and emotion data, the server generates qualitative advice optimized for each student. This advice is personalized using a generative AI model. For example, by inputting a prompt such as "Advice for a student who is strong in calculation problems but is anxious about applied problems," the generative AI model generates specific feedback such as "Practice applied problems more to gain confidence."

[1032] This system can recognize the user's emotional state and provide advice and study plans based on that, thereby improving learning effectiveness and streamlining education.

[1033] Examples of prompts for generative AI models include:

[1034] "Advice for students who are good at calculation problems but feel uneasy about applied problems."

[1035] Finally, teachers can supplement the qualitative advice generated by the server with additional comments, resulting in more personalized feedback for students.

[1036] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[1037] Step 1:

[1038] The user's device collects test answers and sends them to the server. Specifically, the user enters the answers on the online platform, and the data is sent to the server in JSON format. The input is the user's test answer data, and the output is the data sent to the server.

[1039] Step 2:

[1040] The server receives the submitted test answer data and stores it in a database. During this process, the server parses the JSON data and stores each item in the appropriate field in the database. The input is the user's test answer data, and the output is the answer data stored in the database.

[1041] Step 3:

[1042] The server inputs the answer data stored in the database into the generative AI model, and evaluates each answer as "correct," "incorrect," or "difficult to judge." Here, the server passes the answer data to the generative AI model, which analyzes it and returns the evaluation result. The input is the answer data stored in the database, and the output is the evaluation result.

[1043] Step 4:

[1044] The server stores the evaluation results in a database. Specifically, the evaluation results from the generative AI model are recorded in association with the corresponding answer data in the database. The input is the evaluation result of the generative AI model, and the output is the evaluation result recorded in the database.

[1045] Step 5:

[1046] The server calculates the score based on the evaluation results. Each "correct" answer is given 1 point, while "incorrect" and "difficult to judge" answers are given 0 points, and the total score is calculated. In this process, the server aggregates the evaluation results, calculates the individual scores, and stores them in a database. The input is the evaluation results, and the output is the calculated total score.

[1047] Step 6:

[1048] The server uses an emotion engine to analyze the user's emotional state. An image capture device is used to collect the user's facial expression data, which is then analyzed by the emotion engine. The input is the user's facial expression data, and the output is emotion data.

[1049] Step 7:

[1050] The server generates individual qualitative advice based on the evaluation results and emotional data. The emotional data and evaluation results are input into the generative AI model as prompts to generate specific feedback. The input is the evaluation results and emotional data, and the output is the generated qualitative advice.

[1051] Step 8:

[1052] The server provides the generated qualitative advice to the teacher's device, where the teacher can add supplementary comments. Sample comments generated in advance by the generative AI model are displayed, and the teacher can add supplementary comments or make corrections to them. The input is the generated qualitative advice, and the output is feedback added by the teacher.

[1053] Step 9:

[1054] The user device retrieves and displays their own evaluation results, qualitative advice, and optimized learning plans from the server. The server sends the evaluation results and feedback to the user device, and the user confirms this information. The input is the feedback data sent from the server, and the output is the learning information displayed on the user device.

[1055] The above is an explanation of each processing step and specific operation of this system.

[1056] 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.

[1057] 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.

[1058] 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.

[1059] [Fourth embodiment]

[1060] FIG. 7 shows an example of the configuration of a data processing system 410 according to the fourth embodiment.

[1061] 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.

[1062] 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).

[1063] 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.

[1064] 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.

[1065] 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).

[1066] 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.

[1067] 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.

[1068] 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.

[1069] 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.

[1070] 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.

[1071] 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.

[1072] 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."

[1073] This invention is a system that utilizes a generative artificial intelligence model to improve the efficiency of test scoring and provide learning support optimized for each student. Below, we will explain in detail each element of the system and its operation.

[1074] 1. Collecting test answers

[1075] The server receives the test data answered by students. This data is sent to the server by teachers or educational institutions and parsed into a data format such as JSON. The server stores the received data in a database.

[1076] Example: Student A takes an online math test and sends the answer data to a server, which analyzes the data and stores it in a database.

[1077] 2. Generative AI scoring

[1078] The server inputs the answer data stored in the database into the generative AI model and evaluates each answer as "〇" (correct), "×" (incorrect), or "△" (determined). The evaluation results are recorded in the database.

[1079] Example: Student A's answer "5 x 3 = 15" is judged to be correct and recorded as "Yes." On the other hand, Student A's answer "4 x 3 = 11" is judged to be incorrect and recorded as "No."

[1080] 3. Calculation of the scores

[1081] The server calculates the score for each student based on the evaluation results. For example, a "good" score is 1 point, an "bad" score is 0 point, and a "bad" score is also 0 point. The calculated scores are saved in a database.

[1082] Example: If Student A answers 10 questions correctly and 2 questions incorrectly, his total score will be recorded as 10 points.

[1083] 4. Generating personalized advice

[1084] The server uses a generative AI model to analyze each student's answer patterns and generate qualitative advice, providing feedback tailored to each student's strengths and weaknesses.

[1085] Example: In the case of Student A, the advice generated is "You got high marks in the calculation questions, but you need to improve in the application questions."

[1086] 5. Create a study plan

[1087] The server analyzes the assessment results and works with learning support software to create an optimized learning plan for each student, providing specific guidelines for effective learning.

[1088] Example: Student A is proposed a learning plan that "strengthens review of calculation problems and practice of applied problems."

[1089] 6. Teacher's Comments

[1090] Pre-generated sample comments are displayed on the device, and teachers can add or correct them. The final comments are sent to the server and stored in a database.

[1091] Example: In response to the comment made by the generating AI, "You are strong at calculation problems," the teacher adds, "You are particularly good at problems with equations."

[1092] 7. Viewing Results and Receiving Feedback

[1093] The user's device displays the grades, advice, and study plans obtained from the server, allowing students to advance their studies based on this information.

[1094] Example: Student A checks the grades and feedback on their own device to understand what they should study next.

[1095] As described above, the present invention is a system that improves the efficiency of test grading and provides optimal learning support for each student. This is expected to improve the efficiency of educational settings and the learning effectiveness of students.

[1096] The processing flow will be explained below.

[1097] Step 1:

[1098] The server receives the test answers sent from each device. The answer data is sent in JSON format, and when the server receives the HTTP request, it parses the data and saves it in a database.

[1099] Step 2:

[1100] The server reads the test answers stored in the database, inputs them into the generative AI model, and evaluates them. The generative AI model labels correct answers as "O," incorrect answers as "X," and answers that are difficult to judge as "△." The evaluation results are then saved back into the database.

[1101] Step 3:

[1102] The server calculates each student's score based on the evaluation results. Each "O" is counted as 1 point, while "X" and "△" are counted as 0 points, and the total score is recorded in the database.

[1103] Step 4:

[1104] The server uses the generative AI model to generate qualitative advice based on each student's answer patterns, including specific suggestions for improving their learning, which are also stored in a database.

[1105] Step 5:

[1106] The server analyzes the assessment results and works with the learning support software to create an optimized learning plan for each student. The learning plan takes into account the student's strengths and weaknesses and recommends specific learning activities and materials. The generated learning plan is also stored in a database.

[1107] Step 6:

[1108] A pre-generated sample comment is displayed on the device. The teacher uses this as a reference to make any necessary corrections or additions, and then creates the final comment. The created comment is sent to the server and stored in a database.

[1109] Step 7:

[1110] The user's device retrieves and displays their own assessment results, qualitative advice, and an optimized learning plan from the server. Based on this information, students can confirm their learning guidelines and understand what they should study next.

[1111] Example 1

[1112] 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."

[1113] In today's educational environment, grading tests requires a great deal of effort and time. Furthermore, providing individualized feedback and learning plans for each student places an even greater burden on teachers. Therefore, there is a need for a system that can efficiently grade tests and provide optimized learning support for each student.

[1114] 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.

[1115] In this invention, the server includes means for evaluating received educational data using a generative AI model and identifying correct answers, incorrect answers, and difficult answers, means for recording the evaluation results and calculating a score for each user, means for generating qualitative feedback for each user based on the evaluation results, and means for analyzing the evaluation results and creating an optimized learning plan for each user in cooperation with educational support software. This makes it possible to streamline test scoring and provide personalized learning support for each student.

[1116] A "generative artificial intelligence model" is an artificial intelligence model that uses machine learning algorithms to analyze data and make predictions.

[1117] "Educational data" refers to education-related information such as answer data, test results, and learning history provided by users (students).

[1118] "Evaluation" is the process of using a generative artificial intelligence model to identify correct, incorrect, and difficult-to-judge answers based on received educational data.

[1119] "Feedback" refers to personalized learning improvement suggestions and advice provided based on students' test results and answer patterns.

[1120] A "study plan" is a plan for providing optimized learning content and schedules based on each student's strengths and weaknesses.

[1121] "Educational support software" is software that supports educational activities, such as creating learning plans, managing progress, and providing teaching materials.

[1122] "Server" means a computer system for collecting, analyzing, evaluating, and recording educational data.

[1123] "User" means a student or person receiving education who uses the system to learn.

[1124] "Score" refers to the score for each student calculated based on the test evaluation results.

[1125] The present invention is a system that utilizes a generative artificial intelligence model to improve the efficiency of test scoring and provide optimized learning support for each student. A specific implementation method of the system is described below.

[1126] First, the server receives the educational data sent from the device. This educational data includes test data answered by students and is sent in a format such as JSON. The server parses this data and stores it in a database. The hardware used here is a standard server computer, and software such as Apache or MySQL can be used.

[1127] The server then reads the educational data stored in the database and evaluates each answer using a generative AI model. The generative AI model uses machine learning algorithms to distinguish between correct, incorrect, and difficult answers from the input data. Potential software used is TensorFlow or PyTorch. The evaluation results are recorded in the database.

[1128] Based on the evaluation results, the server calculates a score for each student. Correct answers are assigned 1 point, incorrect answers 0 points, and difficult-to-judge answers are also assigned 0 points. The total score is then stored in a database. In addition, the server uses a generative AI model to analyze each student's answer patterns and generate qualitative feedback. This feedback is also stored in the database.

[1129] The server then connects to educational support software to create an optimal learning plan for each student based on the assessment results and feedback. Software such as a learning management system (LMS) can be used. The learning plan is customized based on each student's strengths and weaknesses and stored in a database.

[1130] The teacher's role is also important. Pre-generated sample comments are displayed on the device, and the teacher can add or correct them. The final comments sent from the device are saved on the server.

[1131] Finally, users can use their own devices to check the grades, feedback, and study plans retrieved from the server, allowing students to understand their own learning progress and clarify what they should work on next.

[1132] As a specific example, consider a scenario in which Student A takes an online test on a device and sends the answers to a server. The server receives the answer data and evaluates it based on the generative AI model, recording the correct answer "5 x 3 = 15" as "Yes" and the incorrect answer "4 x 3 = 11" as "No." The server then aggregates the evaluation results and saves them in a database as a total score of 10 points for Student A. It then generates feedback such as "You scored well on the calculation problems, but you show weaknesses in the application problems," and creates a learning plan through learning support software to "review the calculation problems and strengthen your practice of the application problems."

[1133] An example of a prompt is "Please solve the following equation: 5 x 3 =?"

[1134] As described above, this system makes it possible to improve the efficiency of test grading and also to provide individualized learning support for each student.

[1135] The flow of the identification process in the first embodiment will be described with reference to FIG.

[1136] Step 1: Collecting educational data

[1137] The server receives the educational data sent from the device. The input data is the test data answered by the student, and is received in a format such as JSON. The server parses this data and saves it in a database. Specifically, when Student A finishes the online test on his / her device and clicks the "Submit" button, the answer data is sent to the server. The server analyzes this data and stores it in a database. The output is the analyzed educational data.

[1138] Step 2: Evaluation using generative AI models

[1139] The server reads the educational data stored in the database and inputs it into the generative AI model. The input data are the students' answers. The generative AI model distinguishes between correct answers, incorrect answers, and answers that are difficult to judge, and generates an evaluation result. Specifically, the server evaluates the answer "5 x 3 = 15" as correct "Yes" and the answer "4 x 3 = 11" as incorrect "No". This evaluation result is recorded in the database. The output is the evaluated educational data.

[1140] Step 3: Calculating the scores

[1141] The server reads the evaluation results stored in the database and calculates the score for each student. The input data is the evaluation results. For example, a correct answer "〇" is worth 1 point, an incorrect answer "×" is worth 0 points, and a difficult answer "△" is also worth 0 points, and the total score is calculated. In concrete terms, the server tallies the number of correct answers and the number of errors for Student A and calculates the total score. The output is the score for each student.

[1142] Step 4: Generate qualitative feedback

[1143] The server uses a generative AI model to analyze each student's answer patterns and generate qualitative feedback. The input data is the evaluation results. The generative AI model classifies strengths and weaknesses and generates specific advice. Specifically, the server generates feedback to Student A that "You are good at calculation problems, but have weaknesses in applied problems." The output is feedback.

[1144] Step 5: Create an optimized study plan

[1145] The server analyzes the generated feedback and evaluation results and works with the learning support software to create an optimal learning plan for each student. The input data are the feedback and evaluation results. Specifically, the server uses the learning support software to create a learning plan for Student A that "reviews calculation problems and strengthens practice of applied problems." The output is the learning plan.

[1146] Step 6: Teacher comments

[1147] The device provides the teacher with pre-generated sample comments, which the teacher can then add or correct. The input data are the sample comments. Specifically, the teacher checks Student A's feedback and learning plan on the device, and adds "He is particularly good at equation problems" to "He is strong at calculation problems." The server saves the added comments in a database. The output is the final comment.

[1148] Step 7: View results and receive feedback

[1149] The user's device displays the grading results, feedback, and learning plan obtained from the server. The input data is the learning-related data sent from the server. Specifically, Student A checks the latest grading results and feedback on his or her own device and understands the learning content he or she should tackle next. The output is the displayed learning-related data.

[1150] (Application example 1)

[1151] 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."

[1152] Traditionally, evaluating the performance of factory robot operators has been time-consuming and labor-intensive, and it has been difficult to maintain accuracy and consistency in the evaluations. Traditional evaluation methods have been largely subjective, making it difficult to provide individually optimized training plans. This has led to delays in improving operator skills and the risk of reduced production efficiency.

[1153] 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.

[1154] In this invention, the server includes means for evaluating received information using a generative artificial intelligence model and identifying correct answers, incorrect answers, and answers that are difficult to evaluate, means for recording the evaluation results and calculating an evaluation score for each subject, means for generating qualitative advice for each subject based on the evaluation results, and means for analyzing the evaluation results and creating a training plan optimized for each subject in cooperation with the assistance software. This makes it possible to objectively and efficiently evaluate an operator's performance and provide individually optimized feedback and training plans.

[1155] A "generative artificial intelligence model" is an algorithm that uses artificial intelligence technology to analyze data and generate responses or decisions based on the results.

[1156] "Information" is a concept that encompasses facts, data, or knowledge about a particular subject.

[1157] "Evaluation" is the act of analyzing received information and making a judgment based on specific criteria.

[1158] A "correct answer" is the only correct expected response to a problem or question.

[1159] An "error" is an answer or action that is incorrect compared to the correct answer.

[1160] "Answers that are difficult to evaluate" are ambiguous answers that the generative AI model cannot clearly determine as correct or incorrect.

[1161] "Evaluation results" are the results of evaluation obtained by the generative artificial intelligence model, including identification of correct answers, incorrect answers, and answers that are difficult to evaluate.

[1162] "Individual subject" means the individual being evaluated.

[1163] The "evaluation score" is a numerical representation of the performance of each subject.

[1164] "Qualitative advice" refers to specific, verbalized instructions or suggestions based on the results of the assessment.

[1165] A "training plan" is a plan designed to help an individual subject acquire specific skills or knowledge.

[1166] "Support Software" means a software program for performing the calculations and analyses necessary for the evaluation and development of a training plan.

[1167] "Individually optimized feedback" refers to advice that is customized to each individual subject's specific needs and circumstances.

[1168] The present invention is a system that utilizes generative artificial intelligence models to efficiently evaluate the performance of factory robot operators and provide individually optimized feedback and training plans. Below, we will explain in detail each element of the system and its operation.

[1169] 1. Collecting Operational Data

[1170] The server collects data from the factory robot's operations through sensors and a logging system, and sends it to the server. This data is parsed into a data format such as JSON, and the server stores the received data in a database.

[1171] Example: When operator A controls the robot and commands it to "move," the coordinate data and timestamp of that movement are sent to the server.

[1172] 2. Evaluation by generative AI

[1173] The server inputs the operation data stored in the database into the generative AI model and evaluates the accuracy, efficiency, error rate, etc. of each operation. The evaluation results are recorded in the database.

[1174] Example: If Operator A's operation "Pick item A" is performed accurately and quickly, it will be recorded as a "High Score." On the other hand, if "Pick item B" is performed incorrectly, it will be recorded as a "Low Score."

[1175] 3. Calculation of evaluation results

[1176] The server calculates the performance score for each operator based on the evaluation results. For example, a "high rating" is 2 points, a "low rating" is 0 points, and the total score is calculated. The calculated scores are saved in a database.

[1177] Example: If Operator A has 10 likes and 2 dislikes, their total score will be recorded as 20 points.

[1178] 4. Generating personalized advice

[1179] The server uses a generative AI model to analyze each operator's operating patterns and generate qualitative advice, providing feedback tailored to each operator's individual strengths and weaknesses.

[1180] Example: For Operator A, the advice generated is "Your moving operations are highly rated, but your picking operations need improvement."

[1181] 5. Create a training plan

[1182] The server analyzes the evaluation results and works with the assistance software to create an optimized training plan for each operator, providing specific guidelines for operators to effectively improve their skills.

[1183] Example: Operator A is proposed a training plan to "strengthen training in picking operations."

[1184] 6. Additional Supervisor Comments

[1185] Pre-generated sample comments are displayed on the terminal, and the supervisor can add or correct them. The final comments are sent to the server and stored in a database.

[1186] Example: In response to the generated AI's comment "Picking accuracy is low," the supervisor adds, "Please note that the picking accuracy of item B is particularly low."

[1187] 7. Viewing Results and Receiving Feedback

[1188] The user's device displays the evaluation results, advice, and training plans obtained from the server, allowing the operator to improve their own operating skills based on this information.

[1189] Example: Operator A checks the evaluation results and feedback on his own device and understands the next training content he should work on.

[1190] The system uses generative AI models using AI frameworks such as TensorFlow and PyTorch, databases such as PostgreSQL, and API servers such as Flask and Django as its main software components.

[1191] Example prompt sentence:

[1192] It collects operation data from the robot operator and evaluates their performance using a generative AI model. Based on the evaluation results, it generates individualized feedback and training plans and provides feedback to the operator.

[1193] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[1194] Step 1:

[1195] Operational Data Collection

[1196] The server collects data on the operations of factory robot operators. This data is acquired through sensors and logging systems and sent to the server in formats such as JSON. The server stores the received data in a database, thereby recording the operator's operation history.

[1197] Input: Operator operation data (e.g. movement coordinates, item pick data)

[1198] Output: Operational data stored in a database

[1199] Step 2:

[1200] Generative AI evaluation

[1201] The server inputs the operation data stored in the database into the generative AI model and evaluates the accuracy, efficiency, error rate, etc. of each operation. The generative AI model analyzes the operation data and identifies correct, incorrect, and difficult-to-evaluate operations. The evaluation results are recorded in the database.

[1202] Input: Operational data stored in the database

[1203] Output: Evaluation result (e.g., correct answer, incorrect answer, difficult operation to evaluate)

[1204] Step 3:

[1205] Aggregation of evaluation results

[1206] The server calculates the performance score for each operator based on the evaluation results. For example, a "high rating" is given 2 points, and a "low rating" is given 0 points, and the total score is calculated. The calculated scores are saved in a database.

[1207] Input: Evaluation result

[1208] Output: Performance score

[1209] Step 4:

[1210] Generating personalized advice

[1211] The server uses a generative AI model to analyze each operator's operating patterns and generate qualitative advice, providing feedback tailored to each operator's strengths and weaknesses. The advice is then recorded in a database.

[1212] Input: Evaluation results and operation patterns

[1213] Output: Qualitative advice

[1214] Step 5:

[1215] Creating a training plan

[1216] The server analyzes the evaluation results and works with the assistance software to create an optimized training plan for each operator, providing specific guidelines for the operator to effectively improve their skills. The training plan is then saved in a database.

[1217] Input: Evaluation results and qualitative advice

[1218] Output: Training plan

[1219] Step 6:

[1220] Additional supervisor comments

[1221] The terminal provides the supervisor with pre-generated sample comments, which the supervisor can add or correct, and the final comments are sent to the server and stored in a database.

[1222] Input: Generated comment sample

[1223] Output: Annotated comments

[1224] Step 7:

[1225] Viewing results and receiving feedback

[1226] The user's device displays the evaluation results, advice, and training plans obtained from the server, allowing the operator to improve their own operating skills based on this information.

[1227] Input: Assessment results, advice, training plan

[1228] Output: Information displayed on the user's terminal

[1229] 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.

[1230] This invention is a system that utilizes a generative artificial intelligence model to improve the efficiency of test scoring and provide learning support optimized for each student. Furthermore, by recognizing the user's emotional state and incorporating this into the learning support, more effective learning support is realized.

[1231] Configuration and Operation

[1232] 1. Collecting test answers

[1233] The server receives the test answers from each device. This answer data is sent in JSON format, and the server parses it and stores it in a database. This allows all answer data to be managed centrally.

[1234] Example: Student A takes an online math test and sends the answer data to a server, which analyzes the data and stores it in a database.

[1235] 2. Generative AI scoring

[1236] The server inputs the answer data stored in the database into the generative AI model and evaluates each answer as "〇" (correct), "×" (incorrect), or "△" (determined). The evaluation results are then saved back into the database.

[1237] Example: Student A's answer "5 x 3 = 15" is judged to be correct and recorded as "Yes." On the other hand, Student A's answer "4 x 3 = 11" is judged to be incorrect and recorded as "No."

[1238] 3. Calculation of the scores

[1239] The server calculates each student's score based on the evaluation results. Each "O" is worth 1 point, and each "X" and "△" is worth 0 point. The server calculates the total score and records the total score in the database.

[1240] Example: If Student A answers 10 questions correctly and 2 questions incorrectly, his total score will be recorded as 10 points.

[1241] 4. User Emotion Recognition

[1242] The server uses an emotion engine to analyze the user's emotional state. The emotion engine analyzes the user's facial expressions and tone of voice via a camera or microphone to obtain emotional data. Based on this, the student's emotional state is determined and recorded.

[1243] Example: If Student A looks anxious during a test, the emotion engine will recognize this and record the emotion data as "anxious."

[1244] 5. Generating personalized advice

[1245] The server uses a generative AI model to generate qualitative advice based on each student's answer patterns and emotional data, providing more personalized feedback.

[1246] Example: Advice generated for Student A is, "You are good at calculation problems, but tend to feel uneasy with applied problems. You should practice applied problems more and also practice to gain confidence."

[1247] 6. Create a study plan

[1248] The server analyzes the assessment results and emotional data and works with learning support software to create an optimized learning plan, which includes specific learning activities and materials that take emotional state into account.

[1249] Example: Student A's study plan might include relaxation exercises before tackling applied problems, helping him focus on his studies while reducing anxiety.

[1250] 7. Teacher's Comments

[1251] Pre-generated sample comments are displayed on the device, and teachers can add or correct them. The final comments are sent to the server and stored in a database.

[1252] Example: In response to the comment made by the generating AI, "You are strong at calculation problems," the teacher adds the comment, "You are particularly good at problems with equations."

[1253] 8. Viewing Results and Receiving Feedback

[1254] The user's device retrieves and displays their own assessment results, qualitative advice, and an optimized learning plan from the server. Based on this information, students can confirm their future learning strategy and understand what they should tackle next.

[1255] Example: Student A checks the assessment results and feedback on his / her own device and understands what learning he / she should do next through a learning plan based on emotional data.

[1256] In this way, by combining a generative AI model and an emotion engine, the present invention provides a system that efficiently grades students, provides personalized feedback, and provides learning plans, which is expected to improve the efficiency of classrooms and student learning outcomes.

[1257] The processing flow will be explained below.

[1258] Step 1:

[1259] The server receives the test answers sent from each device. The test answers are sent in JSON format, and upon receiving the HTTP request, the server parses the answer data in JSON format and stores it in a database.

[1260] Step 2:

[1261] The server inputs the test answers stored in the database into the generative AI model and evaluates each answer as "〇" (correct), "×" (incorrect), or "△" (delayed judgment). The evaluation results are then saved in the database again.

[1262] Step 3:

[1263] The server calculates each student's score based on the evaluation results. Specifically, each "OK" is counted as 1 point, while "X" and "△" are counted as 0 points, and the total score is recorded in the database.

[1264] Step 4:

[1265] The server uses an emotion engine to recognize the user's emotional state. The emotion engine analyzes the user's facial expressions and voice through a camera and microphone to obtain emotional data such as "happiness," "sadness," and "surprise." This data is sent to the server at the same time as the test is received and stored in a database.

[1266] Step 5:

[1267] The server uses the generative AI model to generate qualitative advice based on the evaluation results and emotional data. The advice is also personalized, taking into account feedback based on the emotional data. This advice is also stored in a database.

[1268] Step 6:

[1269] The server analyzes the assessment results and emotional data, and works with learning support software to create an optimized learning plan for each student. The learning plan includes content that takes into account the student's emotional state, such as relaxation exercises or short breaks to refresh the mind. The generated learning plan is also stored in a database.

[1270] Step 7:

[1271] Pre-generated sample comments are displayed on the device, and the teacher can add any necessary corrections or additions. The comments are then sent to the server and stored in a database.

[1272] Step 8:

[1273] The user's device retrieves and displays their own assessment results, qualitative advice, and an optimized learning plan from the server. Based on this information, students can confirm their future learning strategy and understand what they should tackle next.

[1274] Step 9:

[1275] The user studies based on the study plan provided along with test feedback. Students use this study plan as a reference and periodically report their progress to the server, which then records this in a database. This allows the server to track the student's learning progress and emotional state and adjust the study plan as needed.

[1276] Example 2

[1277] 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."

[1278] In traditional educational systems, test scoring is often done manually, which not only requires a lot of time and effort, but also can lead to inconsistent and inaccurate scoring. It is also difficult to properly understand each student's emotional state and learning situation and provide individual feedback and learning plans based on that. This results in a lack of personalized instruction to maximize students' learning outcomes.

[1279] The identification process by the identification processing unit 290 of the data processing device 12 in Example 2 is realized by the following means. In this invention, the server includes: means for evaluating received answer data using a generative AI model and identifying correct answers, incorrect answers, and answers that are difficult to judge; means for recording the evaluation results and calculating scores for each individual; means for inputting the answer data into the generative AI model and performing the evaluation; means for analyzing the evaluation results and using an emotion engine that recognizes the emotional state of the individual; means for generating individual feedback based on the analyzed emotion data; and means for analyzing the evaluation results and the emotion data and creating an optimized study plan. This improves the efficiency and consistency of test grading and makes it possible to provide personalized feedback and study plans based on the emotional state of each student.

[1280] A "generative artificial intelligence model" is an artificial intelligence algorithm that can analyze data and determine answers and patterns based on certain rules.

[1281] "Answer data" is digital data that indicates the results of a test that a user answers using a terminal.

[1282] "Evaluation results" are data that are analyzed by a generative artificial intelligence model and include the results of identifying correct answers, incorrect answers, and answers that are difficult to judge.

[1283] The "emotion engine" is an emotional state recognition algorithm that analyzes a user's facial expressions and tone of voice using data collected through devices such as cameras and microphones.

[1284] "Feedback" refers to individual advice and guidance provided to users based on the analyzed evaluation results and emotional data.

[1285] A "learning plan" is a plan that includes an optimized learning schedule and selection of teaching materials for each student based on evaluation results and emotional data.

[1286] "Database" means the data structure and storage location where the information managed within a system is collected.

[1287] A "terminal" is an electronic device, such as a computer or mobile device, through which a user completes a test or interacts with the system.

[1288] "Educator" refers to the person in charge of education who supplements and corrects the learning plan and feedback, and provides the final instruction.

[1289] The term "system" refers to a collection of various hardware and software components that constitute the present invention as a whole, and is a computer configuration for achieving a specific purpose.

[1290] MODE FOR CARRYING OUT THE INVENTION

[1291] This invention is a system that utilizes a generative artificial intelligence model and an emotion engine to improve the efficiency of test scoring in educational settings and provide learning support optimized for each student. This system is composed of the following elements: a server, a terminal, and a user.

[1292] composition

[1293] 1. Server:

[1294] The server is equipped with a generative artificial intelligence model and an emotion engine, analyzes answer data received from multiple devices, and stores evaluation results and emotion data in a database.

[1295] The server generates personalized feedback and an optimized learning plan and provides it to the user terminal.

[1296] 2. Terminal:

[1297] The device provides an interface for users to answer questions, and transmits the user's facial expressions and voice to the emotion engine via a camera and microphone.

[1298] The terminal displays the generated feedback and learning plan to the user.

[1299] 3. User:

[1300] Users answer the test using their device and send the results to the server. Emotion data is collected by the emotion engine, allowing them to receive more effective learning support.

[1301] Specific implementation details

[1302] The server first parses the answer data received from the device in JSON format and stores it in a database. It then uses a generative AI model to evaluate the answer data and identify correct, incorrect, and difficult answers. The evaluation results are also stored in the database.

[1303] The server then uses an emotion engine to analyze the user's facial expressions and tone of voice to obtain emotional data, which is then stored in a database for future use in learning support.

[1304] The server uses a generative AI model to generate personalized feedback based on the evaluation results and emotional data. This feedback is sent to the device and displayed to the user. An optimized learning plan is also generated and provided to the user based on the user's evaluation results and emotional state.

[1305] Specific examples

[1306] In this example, the server receives Student A's math test answer data, analyzes it, and saves it in a database. The generative AI model evaluates "5 x 3 = 15" as the correct answer and records it as "Yes." On the other hand, the answer "4 x 3 = 11" is evaluated as an incorrect answer and recorded as "No." The server also uses its emotion engine to recognize Student A's anxious facial expression via the camera and record the data.

[1307] The server then generates feedback for Student A, such as: "You're strong at calculation problems, but tend to feel uneasy with applied problems. Practice more applied problems and do some practice to build your confidence." This advice can be supplemented by a human teacher and provided as a final comment.

[1308] The lesson plan includes relaxation exercises before tackling applied problems, designed to help Student A focus on learning while reducing anxiety.

[1309] Prompt Sentence Examples

[1310] "Provide personalized study advice based on students' math test answers and their current emotional state."

[1311] "Generate a lesson plan that takes into account the student's insurmountable challenges and the resulting emotional changes."

[1312] In this way, the present invention is a system that combines a generative AI model and an emotion engine to provide efficient grading and personalized learning support, which is expected to improve the efficiency of classrooms and student learning outcomes.

[1313] The flow of the identification process in the second embodiment will be described with reference to FIG.

[1314] Step 1: Collect test answers

[1315] Specific operation: The user answers the test on the device. The device generates the user's answer data in JSON format and sends it to the server.

[1316] Input: User's answer data (JSON format)

[1317] Data processing: Parse the answer data received by the server and extract the answer content

[1318] Output: Parsed answer data stored in a database

[1319] Step 2: Generative AI scoring

[1320] How it works: The server retrieves answer data from the database and inputs it into the generative AI model, which then evaluates the answer and returns the result.

[1321] Input: Answer data

[1322] Data processing: The generative AI model evaluates the answer as "〇" (correct), "×" (incorrect), or "△" (withhold judgment).

[1323] Output: The evaluation result (yes, no, or triangle) is saved in the database.

[1324] Step 3: Calculating the scores

[1325] Specific operation: The server calculates the score for each student based on the evaluation results, calculates the score, and records the total score in the database.

[1326] Input: Evaluation result

[1327] Data calculation: Each "〇" is calculated as 1 point, and "×" and "△" are calculated as 0 points.

[1328] Output: The total score is saved in the database.

[1329] Step 4: Recognizing user emotions

[1330] How it works: When a user takes a test on their device, the camera and microphone are activated to collect data. The server then uses the emotion engine to analyze the data and determine the user's emotion.

[1331] Input: User's facial expression and voice data

[1332] Data processing: The emotion engine analyzes facial expressions and tone of voice to obtain emotional data.

[1333] Output: The determined emotion data is saved in the database.

[1334] Step 5: Generate personalized advice

[1335] Specific operation: The server uses a generative AI model to generate individual advice based on the evaluation results and emotion data.

[1336] Input: Evaluation results and emotion data

[1337] Data computation: Generative AI models generate advice based on answer patterns and emotional state

[1338] Output: Individual advice stored in a database

[1339] Step 6: Create a study plan

[1340] Specific operation: The server analyzes the evaluation results and emotional data, and works with the learning support software to create an optimized learning plan.

[1341] Input: Evaluation results and emotion data

[1342] Data calculations: Select learning activities and materials based on assessment results and emotional state

[1343] Output: The learning plan is saved in the database.

[1344] Step 7: Teacher comments

[1345] Specific operation: The generated comment sample is displayed on the device, and the educator adds or corrects it. The final comment is sent to the server and stored in the database.

[1346] Input: Generated comment sample

[1347] Data processing: Educators supplement and correct comments

[1348] Output: Supplementary and corrected comments are saved in the database

[1349] Step 8: View results and receive feedback

[1350] Specific operation: The user's device retrieves and displays the evaluation results, advice, and learning plan from the server.

[1351] Input: Assessment results, feedback, learning plans

[1352] Data calculation: The server retrieves the necessary information from the database and sends it to the terminal in the appropriate format.

[1353] Output: Assessment results, feedback, and learning plans displayed on the user's device

[1354] (Application example 2)

[1355] 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."

[1356] Conventional learning support systems do not adequately consider the emotional state of each student, and the feedback itself is uniform. This can lead to significant differences in learning outcomes for each student, delays in individual optimization, and a decline in student motivation. Furthermore, the time it takes for teachers to provide feedback reduces the efficiency of education.

[1357] The identification processing by the identification processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means. In this invention, the server includes: means for evaluating received test answers using a generative AI model and identifying correct answers, incorrect answers, and difficult answers; means for recording the evaluation results and calculating individual scores; means for generating individual qualitative advice based on the evaluation results; means for analyzing the evaluation results and creating an individually optimized study plan in cooperation with learning support software; and means for recognizing the user's emotional state using an image capture device and reflecting this emotional data in the individual qualitative advice and optimized study plan. This provides individually optimized feedback that takes into account the student's emotional state, enabling improved learning effectiveness and more efficient education.

[1358] A "generative AI model" is a type of artificial intelligence that learns patterns from data and makes predictions and generates data based on new data.

[1359] "Test Answers" refers to answer data submitted by a user as part of an examination or assessment.

[1360] "Evaluation" is the process of using a generative AI model to determine whether a test answer is correct or incorrect.

[1361] A "correct answer" is the appropriate response to a test question.

[1362] An "error" is an inappropriate response to a test question.

[1363] A "difficult answer to judge" is an answer that is difficult for the generative AI model to determine whether it is correct or incorrect.

[1364] "Evaluation result" is the result of judging whether the answer generated by the generative AI model is correct or incorrect.

[1365] "Score" refers to the score of each user calculated based on the evaluation results.

[1366] "Qualitative advice" is specific, qualitative feedback provided based on the results of the assessment.

[1367] A "study plan" is a study plan optimized for each individual user, created based on the assessment results and qualitative advice.

[1368] "Image capture device" refers to a camera or other image capture device that captures image data for recognizing a user's emotional state.

[1369] "Emotional state" refers to the psychological state detected from the user's facial expression, tone of voice, etc.

[1370] This invention is a system that uses generative AI models and emotion recognition technology to improve test scoring and learning support. Specifically, it involves the collaboration of a server, a user terminal, and an image capture device.

[1371] First, the user's device collects test answers and sends them to the server. This answer data is sent in JSON format or similar, and the server parses it and stores it in a database. For example, when a student takes an online test, the answer data is sent to the server, which analyzes the data and stores it in a database.

[1372] The server then inputs the answer data stored in the database into the generative AI model, which evaluates each answer as "correct," "incorrect," or "difficult to judge." The evaluation results are then stored back in the database. For example, a student's answer "5 x 3 = 15" is determined to be correct and recorded as "correct," while the answer "4 x 3 = 11" is determined to be incorrect and recorded as "incorrect."

[1373] The server then calculates each student's score based on the evaluation results. Each "correct" answer is worth 1 point, while "incorrect" and "difficult to judge" answers are worth 0 points. The total score is then recorded in the database. For example, if a student answers 10 questions correctly and 2 questions incorrectly, the total score will be recorded as 10 points.

[1374] The server further analyzes the user's emotional state using an emotion engine. The emotion engine analyzes the user's facial expression through an image capture device (such as a camera) and acquires emotion data. For example, if a student shows an anxious expression, the emotion engine recognizes this and records the emotion data as "anxiety."

[1375] Based on the acquired evaluation results and emotion data, the server generates qualitative advice optimized for each student. This advice is personalized using a generative AI model. For example, by inputting a prompt such as "Advice for a student who is strong in calculation problems but is anxious about applied problems," the generative AI model generates specific feedback such as "Practice applied problems more to gain confidence."

[1376] This system can recognize the user's emotional state and provide advice and study plans based on that, thereby improving learning effectiveness and streamlining education.

[1377] Examples of prompts for generative AI models include:

[1378] "Advice for students who are good at calculation problems but feel uneasy about applied problems."

[1379] Finally, teachers can supplement the qualitative advice generated by the server with additional comments, resulting in more personalized feedback for students.

[1380] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[1381] Step 1:

[1382] The user's device collects test answers and sends them to the server. Specifically, the user enters the answers on the online platform, and the data is sent to the server in JSON format. The input is the user's test answer data, and the output is the data sent to the server.

[1383] Step 2:

[1384] The server receives the submitted test answer data and stores it in a database. During this process, the server parses the JSON data and stores each item in the appropriate field in the database. The input is the user's test answer data, and the output is the answer data stored in the database.

[1385] Step 3:

[1386] The server inputs the answer data stored in the database into the generative AI model, and evaluates each answer as "correct," "incorrect," or "difficult to judge." Here, the server passes the answer data to the generative AI model, which analyzes it and returns the evaluation result. The input is the answer data stored in the database, and the output is the evaluation result.

[1387] Step 4:

[1388] The server stores the evaluation results in a database. Specifically, the evaluation results from the generative AI model are recorded in association with the corresponding answer data in the database. The input is the evaluation result of the generative AI model, and the output is the evaluation result recorded in the database.

[1389] Step 5:

[1390] The server calculates the score based on the evaluation results. Each "correct" answer is given 1 point, while "incorrect" and "difficult to judge" answers are given 0 points, and the total score is calculated. In this process, the server aggregates the evaluation results, calculates the individual scores, and stores them in a database. The input is the evaluation results, and the output is the calculated total score.

[1391] Step 6:

[1392] The server uses an emotion engine to analyze the user's emotional state. An image capture device is used to collect the user's facial expression data, which is then analyzed by the emotion engine. The input is the user's facial expression data, and the output is emotion data.

[1393] Step 7:

[1394] The server generates individual qualitative advice based on the evaluation results and emotional data. The emotional data and evaluation results are input into the generative AI model as prompts to generate specific feedback. The input is the evaluation results and emotional data, and the output is the generated qualitative advice.

[1395] Step 8:

[1396] The server provides the generated qualitative advice to the teacher's device, where the teacher can add supplementary comments. Sample comments generated in advance by the generative AI model are displayed, and the teacher can add supplementary comments or make corrections to them. The input is the generated qualitative advice, and the output is feedback added by the teacher.

[1397] Step 9:

[1398] The user device retrieves and displays their own evaluation results, qualitative advice, and optimized learning plans from the server. The server sends the evaluation results and feedback to the user device, and the user confirms this information. The input is the feedback data sent from the server, and the output is the learning information displayed on the user device.

[1399] The above is an explanation of each processing step and specific operation of this system.

[1400] 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.

[1401] 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.

[1402] 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.

[1403] 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.

[1404] 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.

[1405] 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.

[1406] 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).

[1407] 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.

[1408] 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."

[1409] 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.

[1410] 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).

[1411] 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.

[1412] 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.

[1413] 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.

[1414] 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.

[1415] 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.

[1416] 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.

[1417] 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.

[1418] 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.

[1419] The above-described description and illustrations are a detailed explanation of the parts related to the technology of the present disclosure and are merely an example of the technology of the present disclosure. For example, the above description of the configuration, functions, actions, and effects is an explanation of an example of the configuration, functions, actions, and effects of the parts related to the technology of the present disclosure. Therefore, it goes without saying that unnecessary parts may be deleted, new elements may be added, or replacements may be made to the above-described description and illustrations within the scope of the gist of the technology of the present disclosure. Furthermore, to avoid confusion and facilitate understanding of the parts related to the technology of the present disclosure, the above-described description and illustrations omit explanations of common technical knowledge that do not require particular explanation to enable the implementation of the technology of the present disclosure.

[1420] All publications, patent applications, and technical standards mentioned in this specification are herein incorporated by reference to the same extent as if each individual publication, patent application, or technical standard was specifically and individually indicated to be incorporated by reference.

[1421] The following is further disclosed regarding the above embodiment.

[1422] (Claim 1)

[1423] means for utilizing a generative artificial intelligence model to evaluate received test answers and identify correct, incorrect, and difficult answers;

[1424] a means for recording the results of the assessment and calculating the graded marks for each student;

[1425] a means for generating qualitative advice for each student based on the assessment results;

[1426] A means to analyze the assessment results and create an optimized learning plan for each student in conjunction with learning support software;

[1427] A system including:

[1428] (Claim 2)

[1429] The system according to claim 1, further comprising means for providing a teacher terminal with sample comments previously generated by the generative artificial intelligence model, and for the teacher to add comments.

[1430] (Claim 3)

[1431] 10. The system of claim 1, further comprising means for analyzing the student's learning status and tracking the student's learning progress based on the assessment results and the student's answer patterns.

[1432] "Example 1"

[1433] (Claim 1)

[1434] means for utilizing a generative artificial intelligence model to evaluate the received educational data and identify correct, incorrect, and difficult answers;

[1435] a means for recording the evaluation results and calculating a score for each user;

[1436] a means for generating qualitative feedback for each user based on the evaluation results;

[1437] A means for analyzing the evaluation results and creating an optimized learning plan for each user in conjunction with educational support software;

[1438] A system including:

[1439] (Claim 2)

[1440] The system according to claim 1, further comprising means for providing a teacher terminal with sample comments previously generated by the generative artificial intelligence model, and for the teacher to add comments.

[1441] (Claim 3)

[1442] 2. The system according to claim 1, further comprising means for analyzing the user's learning status and tracking the user's learning progress based on the evaluation results and the user's answer patterns.

[1443] "Application Example 1"

[1444] (Claim 1)

[1445] means for utilizing a generative artificial intelligence model to evaluate the received information and identify correct, incorrect, and difficult to evaluate answers;

[1446] a means for recording the evaluation results and calculating the evaluation score for each subject;

[1447] means for generating qualitative advice for each subject based on the assessment results;

[1448] A means for analyzing the evaluation results and creating a training plan optimized for each subject in cooperation with the assistance software;

[1449] A system including:

[1450] (Claim 2)

[1451] The system of claim 1, further comprising means for providing sample comments pre-generated by the generative artificial intelligence model to a supervisor terminal for the supervisor to add.

[1452] (Claim 3)

[1453] The system of claim 1, further comprising means for analyzing the operation status of the subject and tracking the progress based on the evaluation results and the subject's operation patterns.

[1454] "Example 2: Combining Emotion Engines"

[1455] (Claim 1)

[1456] means for utilizing a generative artificial intelligence model to evaluate the received answer data and identify correct, incorrect, and difficult answers;

[1457] a means for recording the assessment results and calculating individual scores;

[1458] A means for inputting answer data into a generative AI model and performing evaluation;

[1459] a means for analyzing the evaluation results and utilizing an emotion engine that recognizes the individual's emotional state;

[1460] A means for generating individual feedback based on the analyzed emotion data;

[1461] A means of analyzing assessment results and sentiment data to create an optimized learning plan;

[1462] A system including:

[1463] (Claim 2)

[1464] 10. The system of claim 1, further comprising means for providing a terminal with sample comments pre-generated by the generative artificial intelligence model for an educator to add to.

[1465] (Claim 3)

[1466] 10. The system according to claim 1, further comprising means for analyzing a learning situation and tracking a learning progress based on the evaluation results and an individual's answer pattern.

[1467] "Application example 2 when combining emotion engines"

[1468] (Claim 1)

[1469] means for utilizing a generative artificial intelligence model to evaluate received test answers and identify correct, incorrect, and difficult answers;

[1470] a means for recording the results of the assessment and calculating individual marks;

[1471] a means for generating individualized qualitative advice based on the assessment results;

[1472] A means of analyzing the assessment results and creating individually optimized learning plans in conjunction with learning support software;

[1473] means for recognizing the user's emotional state using an image capture device and incorporating this emotional data into personalized qualitative advice and optimized learning plans;

[1474] A system including:

[1475] (Claim 2)

[1476] 10. The system of claim 1, further comprising means for providing sample comments pre-generated by the generative artificial intelligence model to a display device for teacher annotation.

[1477] (Claim 3)

[1478] 2. The system according to claim 1, further comprising means for analyzing the user's learning status and tracking the user's learning progress based on the evaluation results and the user's answer patterns. [Explanation of symbols]

[1479] 10, 210, 310, 410 Data Processing Systems 12 Data Processing Device 14 Smart Devices 214 Smart Glasses 314 Headset-type terminal 414 Robot< / url:> < / url:> < / url:> < / url:>

Claims

1. means for utilizing a generative artificial intelligence model to evaluate received test answers and identify correct, incorrect, and difficult answers; a means for recording the results of the assessment and calculating the graded marks for each student; a means for generating qualitative advice for each student based on the assessment results; A means to analyze the assessment results and create an optimized learning plan for each student in conjunction with learning support software; A system including:

2. The system according to claim 1 , further comprising means for providing a teacher terminal with sample comments previously generated by the generative artificial intelligence model, and for the teacher to add comments.

3. The system of claim 1 , further comprising means for analyzing the student's learning status and tracking the student's learning progress based on the assessment results and the student's answer patterns.

Images