system

Abstract

We provide the system. [Solution] A means of presenting past examination questions from academic institutions based on the applicant's selection, A means of receiving test-takers' answer data, analyzing it, and identifying the test-takers' weak areas, A means to automatically generate similar problems that address areas of weakness, A means of presenting similar problems to test takers and accepting their answers, An educational support system that includes a feedback mechanism that analyzes answer results and provides detailed explanations.

Description

Technical Field

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

Background Art

[0002] Patent Document 1 discloses a method for controlling a persona chatbot, which is performed by at least one processor, the method including steps of receiving a user utterance, adding the user utterance to a prompt including an instruction sentence related to an explanation of a character of the chatbot, 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

Summary of the Invention

Problems to be Solved by the Invention

[0004] In current entrance examination preparation, examinees may have difficulty obtaining past exam questions related to specific academic institutions. In addition, the red-covered books and question collections only cover a limited number of years, and it is inefficient to repeatedly solve the same questions. In particular, exam questions from local academic institutions or in special fields are often not available on the market, making it difficult to study accordingly. Furthermore, existing teaching materials lack a mechanism to identify examinees' weak areas and effectively provide questions specialized for those areas, so examinees have to bear a huge learning cost and time.

Means for Solving the Problems

[0005] This invention provides an educational support system that centrally manages past examination questions from academic institutions nationwide as digital data and presents questions corresponding to the academic institution selected by the examinee. The system analyzes the answer data to identify the examinee's weak areas and uses generation AI to automatically generate similar questions for each individual examinee. Similar questions are categorized by difficulty level and presented in stages according to the examinee's understanding and progress. Furthermore, the system provides individual feedback based on the answer results and updates the learning history, accumulating information useful for future learning. In this way, examinees can learn efficiently and improve the skills necessary to pass the entrance examination for their desired academic institution.

[0006] "Applicant" refers to a person who takes an examination in order to gain admission to an academic institution.

[0007] An "academic institution" refers to an organization that provides academic or specialized education, such as a university or vocational school.

[0008] "Past exam questions" refer to questions from exams administered in a specific year, and are a resource that can be useful for test-takers' studies.

[0009] "Digital data" refers to a form of information stored using electronic technology, and data expressed in a format that can be processed by computers and other devices.

[0010] An "educational support system" refers to a computer program designed to support the learning of test takers, and includes systems that provide learning materials and manage learning progress.

[0011] "Answer data" refers to the information about the solutions provided by test takers to the presented questions.

[0012] "Analysis" refers to the act of breaking down data into smaller parts and trying to understand its meaning or structure.

[0013] "Areas of weakness" refers to subjects or topics where the test-taker lacks sufficient knowledge or skills, and which require particular attention and strengthening.

[0014] "Generative AI" refers to a program that uses artificial intelligence technology to automatically generate new problems and information.

[0015] A "similar problem" refers to a problem that is similar in form and content to an existing problem and is worth tackling again to achieve a specific learning objective.

[0016] "Feedback" refers to the process of conveying information, including evaluations and areas for improvement, based on the answers provided by the test-taker.

[0017] "Learning history" refers to a record of the examinee's past learning activities and is used to develop effective learning plans for the future. [Brief explanation of the drawing]

[0018] [Figure 1] This is a conceptual diagram showing an example of the configuration of a data processing system according to the first embodiment. [Figure 2] This is a conceptual diagram showing an example of the essential functions of the data processing device and smart device according to the first embodiment. [Figure 3] This is a conceptual diagram showing an example of the configuration of a data processing system according to the second embodiment. [Figure 4] This is a conceptual diagram showing an example of the main functions of a data processing device and smart glasses according to the second embodiment. [Figure 5] This is a conceptual diagram showing an example of the configuration of a data processing system according to the third embodiment. [Figure 6] This is a conceptual diagram showing an example of the main functions of a data processing device and a headset-type terminal according to the third embodiment. [Figure 7] This is a conceptual diagram showing an example of the configuration of a data processing system according to the fourth embodiment. [Figure 8] This is a conceptual diagram showing an example of the main functions of a data processing device and a robot according to the fourth embodiment. [Figure 9] This shows an emotion map where multiple emotions are mapped. [Figure 10] It shows an emotion map to which a plurality of emotions are mapped. [Figure 11] It is a sequence diagram showing the processing flow of the data processing system in Embodiment 1. [Figure 12] It is a sequence diagram showing the processing flow of the data processing system in Application Example 1. [Figure 13] It is a sequence diagram showing the processing flow of the data processing system in Embodiment 2 when an emotion engine is combined. [Figure 14] It is a sequence diagram showing the processing flow of the data processing system in Application Example 2 when an emotion engine is combined.

Embodiments for Carrying Out the Invention

[0019] Hereinafter, an example of an embodiment of a system according to the technology of the present disclosure will be described with reference to the accompanying drawings.

[0020] First, the terms used in the following description will be explained.

[0021] In the following embodiments, a numbered processor (hereinafter simply referred to as "processor") may be a single arithmetic unit or a combination of multiple arithmetic units. Also, the processor may be a single type of arithmetic unit or a combination of multiple types of arithmetic units. Examples of arithmetic units include a CPU (Central Processing Unit), a GPU (Graphics Processing Unit), a GPGPU (General-Purpose computing on Graphics Processing Units), an APU (Accelerated Processing Unit), and the like.

[0022] In the following embodiments, a numbered RAM (Random Access Memory) is a memory in which information is temporarily stored and is used as a work memory by the processor.

[0023] In the following embodiments, the signed storage is one or more non-volatile storage devices that store various programs and various parameters. Examples of non-volatile storage devices include flash memory (SSD (Solid State Drive)), magnetic disks (e.g., hard disks), or magnetic tapes.

[0024] In the following embodiments, the signed communication interface (I / F) is an interface that includes a communication processor and an antenna, etc. The communication interface manages communication between multiple computers. Examples of communication standards applicable to the communication interface include wireless communication standards such as 5G (5th Generation Mobile Communication System), Wi-Fi (registered trademark), or Bluetooth (registered trademark).

[0025] In the following embodiments, "A and / or B" is synonymous with "at least one of A and B." That is, "A and / or B" means that it may be A alone, or B alone, or a combination of A and B. Furthermore, in this specification, the same concept as "A and / or B" applies when expressing three or more things linked by "and / or."

[0026] [First Embodiment]

[0027] Figure 1 shows an example of the configuration of the data processing system 10 according to the first embodiment.

[0028] As shown in Figure 1, the data processing system 10 includes a data processing device 12 and a smart device 14. An example of the data processing device 12 is a server.

[0029] The data processing device 12 comprises a computer 22, a database 24, and a communication interface 26. The computer 22 is an example of a "computer" related to the technology of this disclosure. The computer 22 comprises a processor 28, RAM 30, and storage 32. The processor 28, RAM 30, and storage 32 are connected to a bus 34. The database 24 and the communication interface 26 are also connected to the bus 34. The communication interface 26 is connected to a network 54. An example of the network 54 is a WAN (Wide Area Network) and / or a LAN (Local Area Network).

[0030] The smart device 14 comprises a computer 36, a reception device 38, an output device 40, a camera 42, and a communication interface 44. The computer 36 comprises a processor 46, RAM 48, and storage 50. The processor 46, RAM 48, and storage 50 are connected to a bus 52. The reception device 38, output device 40, and camera 42 are also connected to the bus 52.

[0031] The reception device 38 is equipped with a touch panel 38A and a microphone 38B, etc., and receives user input. The touch panel 38A receives user input by detecting contact with an object (e.g., a pen or finger). The microphone 38B receives user input by detecting the user's voice. The control unit 46A transmits data indicating the user input received by the touch panel 38A and microphone 38B to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the data indicating the user input.

[0032] The output device 40 includes a display 40A and a speaker 40B, and presents data to the user 20 by outputting the data in a form perceptible to the user 20 (e.g., audio and / or text). The display 40A displays visible information such as text and images according to instructions from the processor 46. The speaker 40B outputs audio according to instructions from the processor 46. The camera 42 is a small digital camera equipped with an optical system such as a lens, aperture, and shutter, and an image sensor such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor.

[0033] Communication interface 44 is connected to network 54. Communication interfaces 44 and 26 are responsible for the exchange of various types of information between processor 46 and processor 28 via network 54.

[0034] Figure 2 shows an example of the main functions of the data processing device 12 and the smart device 14.

[0035] As shown in Figure 2, in the data processing device 12, a specific processing is performed by the processor 28. A specific processing program 56 is stored in the storage 32. The specific processing program 56 is an example of a "program" related to the technology of this disclosure. The processor 28 reads the specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific processing is realized by the processor 28 operating as a specific processing unit 290 according to the specific processing program 56 executed on the RAM 30.

[0036] The storage 32 stores the data generation model 58 and the emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290.

[0037] In the smart device 14, the processor 46 performs the reception output processing. The storage 50 stores the reception output program 60. The reception output program 60 is used in conjunction with a specific processing program 56 by the data processing system 10. The processor 46 reads the reception output program 60 from the storage 50 and executes the read reception output program 60 on the RAM 48. The reception output processing is realized by the processor 46 operating as a control unit 46A according to the reception output program 60 executed on the RAM 48.

[0038] Next, the specific processing performed by the specific processing unit 290 of the data processing device 12 will be described. In the following description, the data processing device 12 will be referred to as the "server" and the smart device 14 as the "terminal".

[0039] This invention is implemented as an educational support system to help examinees effectively study past examination questions from their desired academic institutions and overcome their weak areas. This system is realized through the exchange of digital data between a server, a terminal, and a user.

[0040] composition

[0041] Server: This server is the core of the system, storing past exam questions from various academic institutions as digital data. Each question is assigned metadata including the university name, faculty, subject, and year. Equipped with an analysis engine and generation AI, it identifies areas of weakness and generates similar questions based on the user's answer data.

[0042] Terminal: A device operated by the user, such as a smartphone or personal computer. Users can receive past exam questions from the server via their terminal and input their answers.

[0043] User: This role is taken on by the applicant, who is a user of the system. They utilize the system to solve problems related to the academic institution they wish to attend.

[0044] Implementation method

[0045] When a user logs into the system using their device, they can select their desired academic institution and subject and solve past exam questions. The server analyzes the answer data received from the user and identifies the examinee's weak areas. Based on the identified weak areas, the generating AI creates similar problems and sends the data to the device in order of difficulty. By working on these similar problems, the user can intensively strengthen specific areas.

[0046] As a concrete example, consider a user who aspires to work at a medical institution in a certain region and scores particularly low in biology. The server analyzes the answer data for life science-related errors, and a generative AI designs similar biology problems. These problems vary from basic to advanced levels, helping to improve accuracy and answer speed. The user is also provided with feedback on the analysis results, including explanations to help them understand their errors.

[0047] In this way, test-takers can efficiently tackle problems tailored to their weak areas and make progress in their studies toward passing the entrance exam for their desired academic institution.

[0048] The following describes the processing flow.

[0049] Step 1:

[0050] The user logs into their device and selects their desired academic institution and examination subjects on the device. This information is then sent from the device to the server.

[0051] Step 2:

[0052] Based on the information received by the server, past exam questions corresponding to the selected academic institution and subject are retrieved from the database. The retrieved questions are then sent to the terminal.

[0053] Step 3:

[0054] The terminal displays past exam questions received from the server to the user. The user answers the questions and enters the answers into the terminal. The terminal then sends the entered answer data to the server.

[0055] Step 4:

[0056] The server analyzes the received answer data and evaluates the user's accuracy rate and success / failure rate for each question. This helps identify which topics the user struggles with.

[0057] Step 5:

[0058] The server uses AI to generate similar problems targeting areas of weakness based on the analysis results. These similar problems are adjusted in difficulty from easy to complex.

[0059] Step 6:

[0060] The server generates similar problems and sends them to the terminal, which then presents them to the user. The user works on the presented similar problems and enters their answers into the terminal.

[0061] Step 7:

[0062] The user sends the results of similar problems they have answered to the server. The server analyzes the results again, generates explanations for incorrect answers, and updates the learning history.

[0063] Step 8:

[0064] The server sends the generated explanations and analysis results to the terminal as feedback. The terminal then presents this to the user, who continues learning while reviewing the feedback.

[0065] (Example 1)

[0066] Next, we will describe Example 1. In the following description, the data processing device 12 will be referred to as the "server," and the smart device 14 will be referred to as the "terminal."

[0067] In educational support, it is crucial for test-takers to accurately understand their learning progress and areas of weakness, and to practice problems accordingly. However, many systems struggle to identify individual test-takers' areas of weakness and provide appropriate problems, and their optimization considering multidimensional answer history is insufficient. This issue is important for test-takers to efficiently achieve their learning goals and needs to be resolved.

[0068] The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 1 is realized by the following means.

[0069] In this invention, the server includes means for retrieving past questions from educational institutions based on the examinee's selection, means for analyzing the examinee's answer information and identifying the examinee's weak areas, and means for generating questions related to the identified weak areas using a generative AI model. This allows examinees to work on individually customized questions to overcome their weak areas.

[0070] "Examinee" refers to an individual who studies for an examination administered by an academic institution.

[0071] An "educational institution" refers to an organization or group that teaches academic subjects or skills and administers examinations necessary for obtaining degrees or qualifications.

[0072] "Past questions" refers to questions and assignments used in exams previously administered by educational institutions.

[0073] "Answer information" refers to data that includes the responses and solutions that test-takers provided to the questions.

[0074] "Areas of weakness" refers to academic fields or subjects that the test-taker does not fully understand or in which they perform poorly.

[0075] A "generative AI model" refers to artificial intelligence technology that enables the automatic generation of new questions based on specific prompts.

[0076] "Generating a problem" refers to the act of creating new questions based on specific conditions or requirements.

[0077] "Learning history" refers to data that records the learning activities and answer patterns that test-takers have engaged in in the past.

[0078] "Adjusting the presentation of questions" refers to providing users with new questions at appropriate times and in appropriate order, based on their answer history and learning history.

[0079] "Feedback" refers to information provided regarding a test-taker's answers, including evaluations, suggestions for improvement, and explanations.

[0080] This educational support system effectively facilitates learning through the exchange of digital data between servers, terminals, and users. The specific roles of the hardware and software in each component are described below.

[0081] Server Role

[0082] The server is the heart of the system, storing past exam questions from educational institutions in digital format. Specifically, it uses a database management system to manage questions and associated metadata (such as institution name, subject, and year). The server is equipped with an analysis engine and a generative AI model, which receives user answer information in real time and analyzes it to identify areas where test-takers struggle. Based on this information, the generative AI model generates similar related questions. For example, the generative AI model can be given prompts such as "Generate questions on basic biology knowledge and adjust the difficulty level."

[0083] Terminal role

[0084] A terminal is a device that the user directly operates, such as a smartphone or a personal computer. Users can use their terminal to log in to the server, receive questions, and enter answers. The application on the terminal facilitates the selection of past questions and the input of answers through its user interface, and is responsible for sending the answer data to the server.

[0085] User roles

[0086] Users are the direct users of the system, and their primary role is to solve the provided problems and enter their answers. Users access the system from their terminals, select their desired educational institution and subject, and then work on past problems. They can utilize feedback sent from the server and new similar problems to focus on areas where they struggle.

[0087] This system allows test-takers to efficiently focus their studies on areas where they are weak, thereby improving the quality of their learning.

[0088] The flow of the specific processing in Example 1 will be explained using Figure 11.

[0089] Step 1:

[0090] The user logs into the system using their device. On the login screen, they enter their username and password, and the authentication information is sent to the server. The server compares the authentication information with the database, and if authentication is successful, it returns a customized dashboard to the user.

[0091] Step 2:

[0092] The user selects their desired educational institution and subject on their device. The user's selection information is sent to the server, which searches its database for past exam questions that match the selected criteria. The server returns the relevant questions to the device along with their metadata.

[0093] Step 3:

[0094] The user enters their answers to past questions obtained on their device. The answer data is sent to the server in real time. The server uses an analysis engine to analyze the answer data and identify the user's weak areas. The analysis results are stored in a database as the user's answer history.

[0095] Step 4:

[0096] The server uses a generative AI model to generate problems related to identified areas of weakness. The prompts used are in the format of "Generate a question on basic biology knowledge and adjust the difficulty level," and the generated problems are organized by difficulty level. These results are then sent to the terminal.

[0097] Step 5:

[0098] Users work on similar problems generated on their devices. After entering their answers, this information is sent back to the server for analysis. Based on this analysis, new areas of weakness are identified, and the server optimizes the learning process for the next session. Users receive feedback on their accuracy rate and areas for improvement.

[0099] Step 6:

[0100] The server updates individual learning histories based on this information and reflects it in the next set of questions. On the user's device, their progress is displayed, allowing them to create an appropriate learning plan. This enables overall reinforcement of the course material.

[0101] (Application Example 1)

[0102] Next, we will explain Application Example 1. In the following explanation, the data processing device 12 will be referred to as the "server," and the smart device 14 will be referred to as the "terminal."

[0103] A challenge exists in that learners struggle to efficiently study past exam questions and overcome individual weaknesses when preparing for exams at their desired educational institutions. Furthermore, there is a lack of systems that present questions in stages according to each learner's level of understanding and provide appropriate learning methods. Therefore, there is a need to provide individually customized learning plans and present optimal questions according to the learner's progress.

[0104] The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 1 is realized by the following means.

[0105] In this invention, the server includes means for presenting past exam questions from educational institutions based on the examinee's selection, means for receiving and analyzing the examinee's answer information to identify the examinee's weak areas, and means for presenting generated similar questions to the examinee and accepting their answers. This enables learners to efficiently prepare for exams using individually customized learning methods.

[0106] "Examinee" refers to an individual who is studying in preparation for an examination administered by an educational institution.

[0107] "Educational institutions" refer to organizations that provide education, such as public or private schools and universities.

[0108] "Past exam questions" refers to exam questions that educational institutions have used in past years.

[0109] "Answer information" refers to the answer data submitted by test takers to the questions.

[0110] A "weakness area" refers to a learning area that has been identified as being particularly poorly understood by the test-taker.

[0111] A "similar problem" refers to a problem that is similar in format and content to the original problem, but is created to help test-takers overcome their weaknesses.

[0112] "Explanation" refers to a description of the questions and answers intended to help test-takers gain a deeper understanding.

[0113] "Optimizing learning methods" refers to the process of adjusting the most effective learning approach to match the current progress and level of understanding.

[0114] "Presenting gradually" refers to gradually adjusting the complexity and difficulty of the questions according to the test-taker's level of understanding.

[0115] One embodiment of the present invention is a system that provides an individualized learning experience through the cooperation of a terminal held by the examinee and a server. The terminal serves to provide an interface for the examinee to operate, select past questions, and input answers. This interface can operate on smartphones, personal computers, and other devices.

[0116] The server receives answer information submitted by test-takers and uses an analysis engine to identify the test-takers' weak areas. Based on the analysis results, the server utilizes a generative AI model to generate similar problems based on the test-takers' weaknesses. These generated similar problems are sent to the terminal, allowing the test-taker to try again. The analysis engine and generative AI mentioned above are implemented using Python or other machine learning frameworks.

[0117] As a concrete example, if a test-taker answers a question about cell division incorrectly while taking a biology exam, the server uses this information to generate a question explaining each stage of cell division and presents it to the test-taker again. This allows the test-taker to pinpoint and strengthen their weak areas.

[0118] An example of a prompt might be, "Create questions on the area the test-taker most frequently got wrong in past biology exams." This allows the generative AI to generate appropriate new questions and provide a learning experience optimized for each individual test-taker.

[0119] The flow of a specific process in Application Example 1 will be explained using Figure 12.

[0120] Step 1:

[0121] The user logs into the system using their device. This requires a user ID and password. At this stage, the device sends the user's authentication information to the server. If authentication is successful, the server receives learning history and progress information. Based on this information, a personalized main menu is displayed to the user.

[0122] Step 2:

[0123] The user selects the subject and educational institution they wish to study. The options are based on a past exam dataset provided by the server. Once the selection is complete, the selection information is sent to the server, and the relevant past exam questions are sent from the server to the terminal. The terminal then displays the questions to the user.

[0124] Step 3:

[0125] The user answers the provided test questions. The answers are sent to the server via the terminal. The input here is the user's answer data, which the server analyzes to calculate the areas where mistakes were made and the accuracy rate. As a result, the user's weak areas are identified.

[0126] Step 4:

[0127] Based on the analysis results, the server uses a generative AI model to generate similar problems that address the user's weak areas. The input is information about the weak areas, and the output is a set of generated problems. Specifically, prompt sentences are input to the generative AI model, and the generated problems are sent to the terminal.

[0128] Step 5:

[0129] The terminal presents the user with a newly generated similar problem. The user answers the problem, and the answer data is sent back to the server. This process is often repeated to deepen the user's understanding.

[0130] Step 6:

[0131] The server aggregates multiple answer data and provides the user with detailed explanations and suggested learning plans as feedback. This allows the user to obtain information that they can use in their next learning session. Based on the feedback, the server considers starting a new learning session and generates more targeted problems as needed.

[0132] Furthermore, an emotion engine that estimates the user's emotions may be incorporated. That is, the identification processing unit 290 may use the emotion identification model 59 to estimate the user's emotions and perform identification processing using the user's emotions.

[0133] This invention is an educational support system that integrates emotion recognition technology to enable examinees to effectively study past examination questions from their desired academic institutions. The system consists of a server, a terminal, and a user, and optimizes the learning content while taking into account the examinee's emotional state.

[0134] composition

[0135] Server: Manages the core functions of the system, centrally managing past exam questions as digital data. Analyzes answers and sentiment data received from users to optimize learning and feedback. Equipped with generative AI and a sentiment engine to personalize the user's learning experience.

[0136] Terminal: This refers to the device used by the user, including smartphones and personal computers. It collects user input data and analyzes their emotional state through voice and facial expressions using an emotion engine.

[0137] User: An examinee who uses the educational support system and utilizes this system when working on problems from the target academic institution.

[0138] Implementation method

[0139] The user accesses the system through a terminal and selects their desired academic institution and subject. Appropriate past exam questions are provided to the terminal from the server, and the user answers them. While answering, the terminal records the user's voice and facial expressions, and the user's emotional state is evaluated by analyzing this data with an emotion engine.

[0140] The server uses received answer data and sentiment data to identify the user's weak areas and generates similar problems using a generation AI. These similar problems can reflect the user's emotional state and have their difficulty and content adjusted to reduce stress or improve motivation. For example, if the user is showing anxiety, the generated problems will be adjusted to be more basic. In addition, feedback based on sentiment analysis is provided to the device, offering advice and useful content to help the user calm down.

[0141] This system allows test-takers to efficiently overcome their weak areas with appropriate support, even under high stress levels, and to engage in learning that leads to success in gaining admission to their desired academic institution.

[0142] The following describes the processing flow.

[0143] Step 1:

[0144] The user logs into their device and selects their desired academic institution and subject on the device. The selection is then sent from the device to the server.

[0145] Step 2:

[0146] Based on the information received by the server, past exam questions for the selected academic institution and subject are retrieved from the database. The retrieved questions are then sent to the terminal.

[0147] Step 3:

[0148] The terminal displays past exam questions received from the server to the user. The user answers the questions and enters their answers into the terminal.

[0149] Step 4:

[0150] While the user is answering, the device records the user's voice and facial expressions through sensors, and analyzes the user's real-time emotional data using an emotion engine.

[0151] Step 5:

[0152] Answer data and sentiment data are sent from the terminal to the server. The server analyzes the answer data to identify the user's areas of weakness.

[0153] Step 6:

[0154] Based on the server's identified weaknesses and real-time emotional data, a generative AI is used to create similar problems. These problems are optimized and adjusted to the user's emotional state.

[0155] Step 7:

[0156] Similar problems are generated and sent from the server to the terminal, which then presents them to the user. The user works on the similar problems and enters their answers.

[0157] Step 8:

[0158] The results of similar problems and user sentiment data are sent from the device to the server, where the server performs further analysis. Based on the analysis results, feedback and advice are generated, and the learning history is updated.

[0159] Step 9:

[0160] The server sends generated feedback and advice to the terminal, which then provides it to the user. The user reviews their learning progress and plans their next learning steps.

[0161] (Example 2)

[0162] Next, we will describe Example 2. In the following description, the data processing device 12 will be referred to as the "server" and the smart device 14 as the "terminal".

[0163] Providing an optimized educational experience that fully considers each learner's emotional state and areas of difficulty during the learning process has been challenging. Traditional systems lacked feedback and problem-solving tailored to learners' emotions, making it difficult to maintain their motivation. Furthermore, there is a need for more effective and personalized learning support that utilizes not only answer data but also emotional data.

[0164] The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 2 is realized by the following means.

[0165] In this invention, the server includes means for analyzing the examinee's answer data and emotional data to identify the examinee's problem area, means for automatically generating similar problems corresponding to the examinee's emotional state using a generative AI model and prompt sentences, and means for analyzing the answer results and emotional data to provide emotion-based feedback. This makes it possible to adjust the difficulty level of the problems according to each examinee's emotional state and learning progress, thereby realizing appropriate and individualized learning support.

[0166] "Examinee" refers to an individual who studies in preparation for evaluation by an educational institution and takes a specific test.

[0167] "Past exam data from educational institutions" refers to a collection of information that digitally stores exam questions from past examinations conducted by educational institutions.

[0168] "Answer data" refers to the information that examinees have written down in response to the exam questions presented to them.

[0169] "Emotional data" refers to information that represents the emotional state of the test taker, analyzed based on their voice, facial expressions, and other factors.

[0170] A "problem area" refers to the area of ​​knowledge or skills in which the test taker shows particular weakness or deficiency during their studies.

[0171] A "generative AI model" refers to a program that uses artificial intelligence technology to automatically generate problems.

[0172] A "prompt" refers to a text-based instruction entered into a generative AI model to tell it to perform a specific action.

[0173] A "similar question" refers to a new question that is based on an existing exam question and has similar characteristics in terms of format and content.

[0174] "Feedback" refers to evaluations and advice provided based on the test taker's answers and emotional data.

[0175] This invention is an educational support system that enables examinees to effectively learn based on past exam data from educational institutions. The system consists of a server, terminals, and users, each playing a specific role.

[0176] About the server

[0177] The server is the core of the system, centrally managing past exam data. It receives answer data and sentiment data sent from the test-taker's terminal and analyzes this data to identify areas where the test-taker needs improvement in their learning. Furthermore, it uses a generative AI model to automatically generate similar questions based on the test-taker's emotional state. In this process, prompts are used to set specific conditions for the questions in the generative AI model. For example, instructions such as "If the user is showing anxiety, generate a basic-level question" can be given.

[0178] About the device

[0179] A terminal is a device used by the user, and includes smartphones and personal computers. The terminal presents problems provided by the server, accepts answers from the user, and acquires emotional data such as voice and facial expressions. The terminal is equipped with an emotion engine, which enables real-time analysis of the user's emotions.

[0180] About the user

[0181] The user is a test-taker who uses this system as a learner. The user accesses the system from a terminal and selects educational institutions and subjects of interest. Emotional data collected during the problem-solving process is used to create questions that reflect the user's emotional state, such as stress and anxiety.

[0182] As a concrete example, when a user works on past exam questions for a specific subject, the device monitors their voice and facial expressions after each problem solved to determine whether they are focused, anxious, or frustrated. This information is sent to a server, and the difficulty and content of the next questions presented are adjusted through a generative AI model. In this way, the user's learning experience becomes more individualized and optimized.

[0183] The flow of the specific processing in Example 2 will be explained using Figure 13.

[0184] Step 1:

[0185] The user accesses the educational support system by operating a terminal and selects their target educational institution and subjects. This selection information is then sent from the terminal to the server, conveying the user's intended learning content to the server. Specifically, user selection data entered on the terminal is sent to the server, which then searches for appropriate past exam questions based on this data.

[0186] Step 2:

[0187] The server searches past problem data based on the user's selection information and selects an appropriate set of problems. The server then sends the selected problems to the terminal in digital format. For data processing, relevant data is extracted from the problem database of the educational institution the user wishes to attend and converted into a format that can be presented to the user.

[0188] Step 3:

[0189] The terminal displays a set of questions sent from the server to the user. The user answers the presented questions, and the answer data is entered into the terminal. The entered answers are sent to the server in real time, and at the same time, emotion data is collected using voice input and facial recognition functions via the camera.

[0190] Step 4:

[0191] The device analyzes collected emotional data using its built-in emotion engine to evaluate the user's emotional state. The evaluation results are sent to the server and used to comprehensively understand the user's learning progress along with their answers. Specifically, emotional indicators such as stress and anxiety are calculated from voice and facial expression data and output as analysis data to the server.

[0192] Step 5:

[0193] The server combines answer data and sentiment data to identify the user's challenges and generates similar problems using a generative AI model. Detailed question conditions are set using prompts. As a data calculation, the AI ​​executes a problem generation algorithm tailored to the user's weaknesses and emotional state, outputting adjusted problems.

[0194] Step 6:

[0195] The server sends feedback based on the analysis, along with the generated similar problems, to the terminal. The terminal provides this information to the user to support the next learning step. Specifically, the feedback includes advice tailored to the test-taker's emotional state and suggestions to maintain motivation.

[0196] (Application Example 2)

[0197] Next, we will explain application example 2. In the following explanation, the data processing device 12 will be referred to as a "server" and the smart device 14 as a "terminal".

[0198] Traditional educational support systems provide uniform learning content and feedback without considering the emotional state of test-takers, resulting in a standardized experience and making it difficult to provide detailed support tailored to the individual characteristics of each test-taker. Furthermore, there was a lack of means to effectively promote learning while reducing the emotional distress and stress experienced by users. This could potentially lead to decreased motivation and limitations in test-takers' performance.

[0199] The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means.

[0200] In this invention, the server includes means for presenting past academic institution questions based on the examinee's selection, means for receiving and analyzing the examinee's answer information to identify the examinee's weak areas, means for automatically generating similar questions corresponding to the weak areas, means for detecting the user's emotional state and making recommendations based on that emotional state in real time, and means for providing recommendation information to the user. This makes it possible to provide an optimal learning experience tailored to the individual emotional state of each examinee, enabling them to learn effectively while reducing stress.

[0201] An "examinee" is someone who is studying in order to take an examination at an academic institution.

[0202] "Academic institutions" refer to organizations and groups that conduct education and research, including universities and vocational schools.

[0203] "Past exam questions" refer to questions from exams previously administered by academic institutions.

[0204] "Answer information" refers to data on the answers that test-takers have submitted to past exam questions.

[0205] "Areas of weakness" refers to the areas or topics that a test-taker found particularly difficult to answer among the questions they answered.

[0206] "Similar problems" are related problems created to facilitate understanding for test-takers based on their identified areas of weakness.

[0207] "Emotional state" refers to the psychological state or emotions that a test-taker exhibits when working on the problems.

[0208] "Recommendation information" refers to information such as learning content and recommended products that are optimized based on the emotional state of the test taker.

[0209] The system implementing this invention is centered around a server, terminals, and users, and aims to highly personalize the learning experience of test takers. The server plays a central role in data processing, managing past exam questions from academic institutions and analyzing test takers' answer information and emotional states to generate feedback. Specifically, a data analysis system built in Python and generative AI technologies (e.g., OpenAI® GPT-3®) are used to generate similar questions and provide recommendation information based on the test taker's weak areas and emotional state.

[0210] The device functions as a smartphone or personal computer, responsible for inputting test-takers' answer information and collecting voice and facial expression data. The collected data is analyzed by an emotion analysis engine (e.g., Affectiva SDK) within the device and transmitted to the server in real time.

[0211] Users, or test takers, use this system to work on past exam questions from academic institutions and input their answers. The server then analyzes the answers and provides personalized questions and feedback in a way that enhances the test taker's understanding. Furthermore, based on the test taker's emotional state, they can receive recommendations to maintain and improve their motivation.

[0212] For example, if a user is experiencing stress while working on a problem, the device's emotion analysis engine detects this state, and the server uses a generative AI model to provide the user with simple, basic problems designed to promote relaxation, as well as music recommendations to reduce stress. An example of a prompt to the generative AI model might be, "If a test-taker is showing signs of anxiety, what types of problems would help them calm down?" In this way, it is possible to provide detailed and personalized learning support.

[0213] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[0214] Step 1:

[0215] The user selects the academic institution and problem to study on their device. The user's selection data is used as input, and the selected problem information is sent to the server as output. The server then prepares a dataset of the corresponding past problems.

[0216] Step 2:

[0217] The device receives the user's response and inputs the voice and facial expression data into the emotion analysis engine. The input consists of the user's response data and real-time voice and facial expression data. The output is the analysis of this data, resulting in numerical information of the emotional state.

[0218] Step 3:

[0219] The server analyzes the received answer information and emotional state to identify areas of weakness. The input consists of the user's answer data and analyzed emotional information. The output generates evaluation data corresponding to the identified areas of weakness and the emotional state.

[0220] Step 4:

[0221] The server uses a generation AI model to automatically generate similar problems and determine the recommended difficulty level based on the user's emotional state. Input includes identified areas of difficulty and emotional data. The output is a personalized similar problem along with its explanation.

[0222] Step 5:

[0223] The server sends generated problems and recommendation feedback to the terminal. The input is the generated personalized problems and feedback data. The output is that actual learning is facilitated by providing the user with an optimized learning experience.

[0224] Step 6:

[0225] Users answer provided questions and receive feedback messages. The input consists of the user's answers and explanations. The output is personalized feedback that helps with future learning, thereby enhancing the learning experience.

[0226] Through these steps, the system provides flexible educational support tailored to the emotional state and learning progress of the test-taker.

[0227] The specific processing unit 290 transmits the result of the specific processing to the smart device 14. In the smart device 14, the control unit 46A causes the output device 40 to output the result of the specific processing. The microphone 38B acquires audio indicating user input for the result of the specific processing. The control unit 46A transmits the audio data indicating user input acquired by the microphone 38B to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the audio data.

[0228] Data generation model 58 is a so-called generative AI (Artificial Intelligence). An example of data generation model 58 is ChatGPT (registered trademark) (Internet search).<URL: https: / / openai.com / blog / chatgpt> ), Gemini (registered trademark) (Internet search) <url: https: gemini.google.com ?hl="ja">Examples of generative AI include the following. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 is input with prompts containing instructions, and with inference data such as audio data representing speech, text data representing text, and image data representing images. The data generation model 58 infers from the input inference data according to the instructions indicated by the prompts, and outputs the inference results in data formats such as audio data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[0229] In the above embodiment, an example was given in which specific processing is performed by the data processing device 12, but the technology of this disclosure is not limited thereto, and the specific processing may also be performed by the smart device 14.

[0230] [Second Embodiment]

[0231] Figure 3 shows an example of the configuration of the data processing system 210 according to the second embodiment.

[0232] As shown in Figure 3, the data processing system 210 includes a data processing device 12 and smart glasses 214. An example of the data processing device 12 is a server.

[0233] The data processing device 12 comprises a computer 22, a database 24, and a communication interface 26. The computer 22 is an example of a "computer" related to the technology of this disclosure. The computer 22 comprises a processor 28, RAM 30, and storage 32. The processor 28, RAM 30, and storage 32 are connected to a bus 34. The database 24 and the communication interface 26 are also connected to the bus 34. The communication interface 26 is connected to a network 54. An example of the network 54 is a WAN (Wide Area Network) and / or a LAN (Local Area Network).

[0234] The smart glasses 214 include a computer 36, a microphone 238, a speaker 240, a camera 42, and a communication interface 44. The computer 36 includes a processor 46, RAM 48, and storage 50. The processor 46, RAM 48, and storage 50 are connected to a bus 52. The microphone 238, speaker 240, and camera 42 are also connected to the bus 52.

[0235] The microphone 238 receives voice signals from the user 20 and receives instructions from the user 20. The microphone 238 captures the voice signals from the user 20, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio according to the instructions from the processor 46.

[0236] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an image sensor such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, and captures images of the area around the user 20 (for example, an imaging range defined by a field of view equivalent to the width of a typical healthy person's field of vision).

[0237] Communication interface 44 is connected to network 54. Communication interfaces 44 and 26 are responsible for the exchange of various information between processor 46 and processor 28 via network 54. The exchange of various information between processor 46 and processor 28 using communication interfaces 44 and 26 is performed in a secure manner.

[0238] Figure 4 shows an example of the main functions of the data processing device 12 and the smart glasses 214. As shown in Figure 4, the data processing device 12 performs specific processing using the processor 28. The storage 32 stores the specific processing program 56.

[0239] The specific processing program 56 is an example of a "program" relating to the technology of this disclosure. The processor 28 reads the specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific processing is realized by the processor 28 operating as a specific processing unit 290 in accordance with the specific processing program 56 executed on the RAM 30.

[0240] The storage 32 stores the data generation model 58 and the emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290.

[0241] In the smart glasses 214, the processor 46 performs the reception output processing. The storage 50 stores the reception output program 60. The processor 46 reads the reception output program 60 from the storage 50 and executes the read reception output program 60 on the RAM 48. The reception output processing is realized by the processor 46 operating as a control unit 46A according to the reception output program 60 executed on the RAM 48.

[0242] Next, the identification processing performed by the identification processing unit 290 of the data processing device 12 will be described. In the following description, the data processing device 12 will be referred to as the "server" and the smart glasses 214 will be referred to as the "terminal".

[0243] This invention is implemented as an educational support system to help examinees effectively study past examination questions from their desired academic institutions and overcome their weak areas. This system is realized through the exchange of digital data between a server, a terminal, and a user.

[0244] composition

[0245] Server: This server is the core of the system, storing past exam questions from various academic institutions as digital data. Each question is assigned metadata including the university name, faculty, subject, and year. Equipped with an analysis engine and generation AI, it identifies areas of weakness and generates similar questions based on the user's answer data.

[0246] Terminal: A device operated by the user, such as a smartphone or personal computer. Users can receive past exam questions from the server via their terminal and input their answers.

[0247] User: This role is taken on by the applicant, who is a user of the system. They utilize the system to solve problems related to the academic institution they wish to attend.

[0248] Implementation method

[0249] When a user logs into the system using their device, they can select their desired academic institution and subject and solve past exam questions. The server analyzes the answer data received from the user and identifies the examinee's weak areas. Based on the identified weak areas, the generating AI creates similar problems and sends the data to the device in order of difficulty. By working on these similar problems, the user can intensively strengthen specific areas.

[0250] As a concrete example, consider a user who aspires to work at a medical institution in a certain region and scores particularly low in biology. The server analyzes the answer data for life science-related errors, and a generative AI designs similar biology problems. These problems vary from basic to advanced levels, helping to improve accuracy and answer speed. The user is also provided with feedback on the analysis results, including explanations to help them understand their errors.

[0251] In this way, test-takers can efficiently tackle problems tailored to their weak areas and make progress in their studies toward passing the entrance exam for their desired academic institution.

[0252] The following describes the processing flow.

[0253] Step 1:

[0254] The user logs into their device and selects their desired academic institution and examination subjects on the device. This information is then sent from the device to the server.

[0255] Step 2:

[0256] Based on the information received by the server, past exam questions corresponding to the selected academic institution and subject are retrieved from the database. The retrieved questions are then sent to the terminal.

[0257] Step 3:

[0258] The terminal displays past exam questions received from the server to the user. The user answers the questions and enters the answers into the terminal. The terminal then sends the entered answer data to the server.

[0259] Step 4:

[0260] The server analyzes the received answer data and evaluates the user's accuracy rate and success / failure rate for each question. This helps identify which topics the user struggles with.

[0261] Step 5:

[0262] The server uses AI to generate similar problems targeting areas of weakness based on the analysis results. These similar problems are adjusted in difficulty from easy to complex.

[0263] Step 6:

[0264] The server generates similar problems and sends them to the terminal, which then presents them to the user. The user works on the presented similar problems and enters their answers into the terminal.

[0265] Step 7:

[0266] The user sends the results of similar problems they have answered to the server. The server analyzes the results again, generates explanations for incorrect answers, and updates the learning history.

[0267] Step 8:

[0268] The server sends the generated explanations and analysis results to the terminal as feedback. The terminal then presents this to the user, who continues learning while reviewing the feedback.

[0269] (Example 1)

[0270] Next, we will describe Example 1. In the following description, the data processing device 12 will be referred to as the "server," and the smart glasses 214 will be referred to as the "terminal."

[0271] In educational support, it is crucial for test-takers to accurately understand their learning progress and areas of weakness, and to practice problems accordingly. However, many systems struggle to identify individual test-takers' areas of weakness and provide appropriate problems, and their optimization considering multidimensional answer history is insufficient. This issue is important for test-takers to efficiently achieve their learning goals and needs to be resolved.

[0272] The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 1 is realized by the following means.

[0273] In this invention, the server includes means for retrieving past questions from educational institutions based on the examinee's selection, means for analyzing the examinee's answer information and identifying the examinee's weak areas, and means for generating questions related to the identified weak areas using a generative AI model. This allows examinees to work on individually customized questions to overcome their weak areas.

[0274] "Examinee" refers to an individual who studies for an examination administered by an academic institution.

[0275] "Educational institution" refers to an organization or group that teaches knowledge and skills and conducts examinations required for obtaining degrees or qualifications.

[0276] "Previous questions" refer to the questions and problems used in the examinations previously conducted by educational institutions.

[0277] "Answer information" refers to data that includes the responses and solutions provided by test takers to questions.

[0278] "Difficult areas" refer to academic fields or subjects that test takers do not fully understand or perform poorly in.

[0279] "Generative AI model" refers to artificial intelligence technology that enables the automatic generation of new questions based on specific prompts.

[0280] "Generate questions" refers to the act of creating new questions based on specific conditions and requirements.

[0281] "Learning history" refers to data that records the learning activities and answer patterns of test takers in the past.

[0282] "Adjust question presentation" refers to providing new questions to users at appropriate times and in appropriate sequences based on the answer history and learning history of test takers.

[0283] "Feedback" refers to information that includes evaluations, improvement points, and explanations provided for the answers of test takers.

[0284] This educational support system effectively supports learning through the exchange of digital data among servers, terminals, and users. The specific roles of the hardware and software of each component will be described.

[0285] Role of the server

[0286] The server is the center of the system and accumulates past problems of educational institutions in digital form. Specifically, it uses a database management system to manage metadata related to problems (such as institution name, subject, year, etc.). The server is equipped with an analysis engine and a generative AI model, which receives the user's answer information in real-time, analyzes it, and identifies the areas where the examinee is weak. Based on this information, the generative AI model generates related similar questions. For example, prompts like "Generate questions related to the basic knowledge of biology and adjust the difficulty level" can be used for the generative AI model.

[0287] Role of the terminal

[0288] The terminal is a device directly operated by the user, such as a smartphone or a personal computer. The user can use the terminal to log in to the server, receive questions, and input answers. The application on the terminal facilitates the selection of past questions and the input of answers through the user interface, and is responsible for sending the answer data to the server.

[0289] Role of the user

[0290] The user is the direct user of the system, and its main role is to solve the provided questions and input answers. The user accesses the system from the terminal, selects the educational institution and subject of interest, and then works on past questions. By utilizing the feedback and new similar questions sent from the server, the user can intensively study the areas where they are weak.

[0291] With this system, examinees can efficiently proceed with learning specialized in their weak areas and improve the quality of learning.

[0292] The flow of the specific process in Example 1 will be described using FIG. 11.

[0293] Step 1:

[0294] The user logs into the system using their device. On the login screen, they enter their username and password, and the authentication information is sent to the server. The server compares the authentication information with the database, and if authentication is successful, it returns a customized dashboard to the user.

[0295] Step 2:

[0296] The user selects their desired educational institution and subject on their device. The user's selection information is sent to the server, which searches its database for past exam questions that match the selected criteria. The server returns the relevant questions to the device along with their metadata.

[0297] Step 3:

[0298] The user enters their answers to past questions obtained on their device. The answer data is sent to the server in real time. The server uses an analysis engine to analyze the answer data and identify the user's weak areas. The analysis results are stored in a database as the user's answer history.

[0299] Step 4:

[0300] The server uses a generative AI model to generate problems related to identified areas of weakness. The prompts used are in the format of "Generate a question on basic biology knowledge and adjust the difficulty level," and the generated problems are organized by difficulty level. These results are then sent to the terminal.

[0301] Step 5:

[0302] Users work on similar problems generated on their devices. After entering their answers, this information is sent back to the server for analysis. Based on this analysis, new areas of weakness are identified, and the server optimizes the learning process for the next session. Users receive feedback on their accuracy rate and areas for improvement.

[0303] Step 6:

[0304] Based on this information, the server updates the individual learning history and reflects it in the next problem presentation. On the terminal, the progress of the user is displayed, and an appropriate learning plan can be formulated. As a result, the overall reinforcement of the course scope can be achieved.

[0305] (Application Example 1)

[0306] Next, Application Example 1 will be described. In the following description, the data processing device 12 is referred to as the "server", and the smart glasses 214 are referred to as the "terminal".

[0307] In the test preparation of the educational institution desired by the learner, there is a problem that it is difficult to efficiently learn past problems and overcome individual weaknesses. In addition, there is a lack of a system that presents problems step by step according to the understanding level of each learner and provides an appropriate learning method. Therefore, there is a need to provide an individually customized learning plan and present the optimal problems according to the progress of the learner.

[0308] The specific processing by the specific processing unit 290 of the data processing device 12 in Application Example 1 is realized by the following means.

[0309] In this invention, the server includes means for presenting past problems of an educational institution based on the selection of the examinee, means for receiving the answer information of the examinee, analyzing it, and identifying the weak areas of the examinee, and means for presenting the generated similar problems to the examinee and receiving the answers. As a result, the learner can efficiently prepare for the test with an individually customized learning method.

[0310] The "examinee" refers to an individual who advances learning in preparation for an exam of an educational institution.

[0311] The "educational institution" refers to an organization that provides education such as public or private schools and universities.

[0312] The "past problems" refer to the test questions issued by an educational institution in previous years.

[0313] "Answer information" refers to the answer data submitted by test takers to the questions.

[0314] A "weakness area" refers to a learning area that has been identified as being particularly poorly understood by the test-taker.

[0315] A "similar problem" refers to a problem that is similar in format and content to the original problem, but is created to help test-takers overcome their weaknesses.

[0316] "Explanation" refers to a description of the questions and answers intended to help test-takers gain a deeper understanding.

[0317] "Optimizing learning methods" refers to the process of adjusting the most effective learning approach to match the current progress and level of understanding.

[0318] "Presenting gradually" refers to gradually adjusting the complexity and difficulty of the questions according to the test-taker's level of understanding.

[0319] One embodiment of the present invention is a system that provides an individualized learning experience through the cooperation of a terminal held by the examinee and a server. The terminal serves to provide an interface for the examinee to operate, select past questions, and input answers. This interface can operate on smartphones, personal computers, and other devices.

[0320] The server receives answer information submitted by test-takers and uses an analysis engine to identify the test-takers' weak areas. Based on the analysis results, the server utilizes a generative AI model to generate similar problems based on the test-takers' weaknesses. These generated similar problems are sent to the terminal, allowing the test-taker to try again. The analysis engine and generative AI mentioned above are implemented using Python or other machine learning frameworks.

[0321] As a concrete example, if a test-taker answers a question about cell division incorrectly while taking a biology exam, the server uses this information to generate a question explaining each stage of cell division and presents it to the test-taker again. This allows the test-taker to pinpoint and strengthen their weak areas.

[0322] An example of a prompt might be, "Create questions on the area the test-taker most frequently got wrong in past biology exams." This allows the generative AI to generate appropriate new questions and provide a learning experience optimized for each individual test-taker.

[0323] The flow of a specific process in Application Example 1 will be explained using Figure 12.

[0324] Step 1:

[0325] The user logs into the system using their device. This requires a user ID and password. At this stage, the device sends the user's authentication information to the server. If authentication is successful, the server receives learning history and progress information. Based on this information, a personalized main menu is displayed to the user.

[0326] Step 2:

[0327] The user selects the subject and educational institution they wish to study. The options are based on a past exam dataset provided by the server. Once the selection is complete, the selection information is sent to the server, and the relevant past exam questions are sent from the server to the terminal. The terminal then displays the questions to the user.

[0328] Step 3:

[0329] The user answers the provided test questions. The answers are sent to the server via the terminal. The input here is the user's answer data, which the server analyzes to calculate the areas where mistakes were made and the accuracy rate. As a result, the user's weak areas are identified.

[0330] Step 4:

[0331] Based on the analysis results, the server uses a generative AI model to generate similar problems that address the user's weak areas. The input is information about the weak areas, and the output is a set of generated problems. Specifically, prompt sentences are input to the generative AI model, and the generated problems are sent to the terminal.

[0332] Step 5:

[0333] The terminal presents the user with a newly generated similar problem. The user answers the problem, and the answer data is sent back to the server. This process is often repeated to deepen the user's understanding.

[0334] Step 6:

[0335] The server aggregates multiple answer data and provides the user with detailed explanations and suggested learning plans as feedback. This allows the user to obtain information that they can use in their next learning session. Based on the feedback, the server considers starting a new learning session and generates more targeted problems as needed.

[0336] Furthermore, an emotion engine that estimates the user's emotions may be incorporated. That is, the identification processing unit 290 may use the emotion identification model 59 to estimate the user's emotions and perform identification processing using the user's emotions.

[0337] This invention is an educational support system that integrates emotion recognition technology to enable examinees to effectively study past examination questions from their desired academic institutions. The system consists of a server, a terminal, and a user, and optimizes the learning content while taking into account the examinee's emotional state.

[0338] composition

[0339] Server: Manages the core functions of the system, centrally managing past exam questions as digital data. Analyzes answers and sentiment data received from users to optimize learning and feedback. Equipped with generative AI and a sentiment engine to personalize the user's learning experience.

[0340] Terminal: This refers to the device used by the user, including smartphones and personal computers. It collects user input data and analyzes their emotional state through voice and facial expressions using an emotion engine.

[0341] User: An examinee who uses the educational support system and utilizes this system when working on problems from the target academic institution.

[0342] Implementation method

[0343] The user accesses the system through a terminal and selects their desired academic institution and subject. Appropriate past exam questions are provided to the terminal from the server, and the user answers them. While answering, the terminal records the user's voice and facial expressions, and the user's emotional state is evaluated by analyzing this data with an emotion engine.

[0344] The server uses received answer data and sentiment data to identify the user's weak areas and generates similar problems using a generation AI. These similar problems can reflect the user's emotional state and have their difficulty and content adjusted to reduce stress or improve motivation. For example, if the user is showing anxiety, the generated problems will be adjusted to be more basic. In addition, feedback based on sentiment analysis is provided to the device, offering advice and useful content to help the user calm down.

[0345] This system allows test-takers to efficiently overcome their weak areas with appropriate support, even under high stress levels, and to engage in learning that leads to success in gaining admission to their desired academic institution.

[0346] The following describes the processing flow.

[0347] Step 1:

[0348] The user logs into their device and selects their desired academic institution and subject on the device. The selection is then sent from the device to the server.

[0349] Step 2:

[0350] Based on the information received by the server, past exam questions for the selected academic institution and subject are retrieved from the database. The retrieved questions are then sent to the terminal.

[0351] Step 3:

[0352] The terminal displays past exam questions received from the server to the user. The user answers the questions and enters their answers into the terminal.

[0353] Step 4:

[0354] While the user is answering, the device records the user's voice and facial expressions through sensors, and analyzes the user's real-time emotional data using an emotion engine.

[0355] Step 5:

[0356] Answer data and sentiment data are sent from the terminal to the server. The server analyzes the answer data to identify the user's areas of weakness.

[0357] Step 6:

[0358] Based on the server's identified weaknesses and real-time emotional data, a generative AI is used to create similar problems. These problems are optimized and adjusted to the user's emotional state.

[0359] Step 7:

[0360] Similar problems are generated and sent from the server to the terminal, which then presents them to the user. The user works on the similar problems and enters their answers.

[0361] Step 8:

[0362] The results of similar problems and user sentiment data are sent from the device to the server, where the server performs further analysis. Based on the analysis results, feedback and advice are generated, and the learning history is updated.

[0363] Step 9:

[0364] The server sends generated feedback and advice to the terminal, which then provides it to the user. The user reviews their learning progress and plans their next learning steps.

[0365] (Example 2)

[0366] Next, we will describe Example 2. In the following description, the data processing device 12 will be referred to as the "server" and the smart glasses 214 will be referred to as the "terminal".

[0367] Providing an optimized educational experience that fully considers each learner's emotional state and areas of difficulty during the learning process has been challenging. Traditional systems lacked feedback and problem-solving tailored to learners' emotions, making it difficult to maintain their motivation. Furthermore, there is a need for more effective and personalized learning support that utilizes not only answer data but also emotional data.

[0368] The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 2 is realized by the following means.

[0369] In this invention, the server includes means for analyzing the examinee's answer data and emotional data to identify the examinee's problem area, means for automatically generating similar problems corresponding to the examinee's emotional state using a generative AI model and prompt sentences, and means for analyzing the answer results and emotional data to provide emotion-based feedback. This makes it possible to adjust the difficulty level of the problems according to each examinee's emotional state and learning progress, thereby realizing appropriate and individualized learning support.

[0370] "Examinee" refers to an individual who studies in preparation for evaluation by an educational institution and takes a specific test.

[0371] "Past exam data from educational institutions" refers to a collection of information that digitally stores exam questions from past examinations conducted by educational institutions.

[0372] "Answer data" refers to the information that examinees have written down in response to the exam questions presented to them.

[0373] "Emotional data" refers to information that represents the emotional state of the test taker, analyzed based on their voice, facial expressions, and other factors.

[0374] A "problem area" refers to the area of ​​knowledge or skills in which the test taker shows particular weakness or deficiency during their studies.

[0375] A "generative AI model" refers to a program that uses artificial intelligence technology to automatically generate problems.

[0376] A "prompt" refers to a text-based instruction entered into a generative AI model to tell it to perform a specific action.

[0377] A "similar question" refers to a new question that is based on an existing exam question and has similar characteristics in terms of format and content.

[0378] "Feedback" refers to evaluations and advice provided based on the test taker's answers and emotional data.

[0379] This invention is an educational support system that enables examinees to effectively learn based on past exam data from educational institutions. The system consists of a server, terminals, and users, each playing a specific role.

[0380] About the server

[0381] The server is the core of the system, centrally managing past exam data. It receives answer data and sentiment data sent from the test-taker's terminal and analyzes this data to identify areas where the test-taker needs improvement in their learning. Furthermore, it uses a generative AI model to automatically generate similar questions based on the test-taker's emotional state. In this process, prompts are used to set specific conditions for the questions in the generative AI model. For example, instructions such as "If the user is showing anxiety, generate a basic-level question" can be given.

[0382] About the device

[0383] A terminal is a device used by the user, and includes smartphones and personal computers. The terminal presents problems provided by the server, accepts answers from the user, and acquires emotional data such as voice and facial expressions. The terminal is equipped with an emotion engine, which enables real-time analysis of the user's emotions.

[0384] About the user

[0385] The user is a test-taker who uses this system as a learner. The user accesses the system from a terminal and selects educational institutions and subjects of interest. Emotional data collected during the problem-solving process is used to create questions that reflect the user's emotional state, such as stress and anxiety.

[0386] As a concrete example, when a user works on past exam questions for a specific subject, the device monitors their voice and facial expressions after each problem solved to determine whether they are focused, anxious, or frustrated. This information is sent to a server, and the difficulty and content of the next questions presented are adjusted through a generative AI model. In this way, the user's learning experience becomes more individualized and optimized.

[0387] The flow of the specific processing in Example 2 will be explained using Figure 13.

[0388] Step 1:

[0389] The user accesses the educational support system by operating a terminal and selects their target educational institution and subjects. This selection information is then sent from the terminal to the server, conveying the user's intended learning content to the server. Specifically, user selection data entered on the terminal is sent to the server, which then searches for appropriate past exam questions based on this data.

[0390] Step 2:

[0391] The server searches past problem data based on the user's selection information and selects an appropriate set of problems. The server then sends the selected problems to the terminal in digital format. For data processing, relevant data is extracted from the problem database of the educational institution the user wishes to attend and converted into a format that can be presented to the user.

[0392] Step 3:

[0393] The terminal displays a set of questions sent from the server to the user. The user answers the presented questions, and the answer data is entered into the terminal. The entered answers are sent to the server in real time, and at the same time, emotion data is collected using voice input and facial recognition functions via the camera.

[0394] Step 4:

[0395] The device analyzes collected emotional data using its built-in emotion engine to evaluate the user's emotional state. The evaluation results are sent to the server and used to comprehensively understand the user's learning progress along with their answers. Specifically, emotional indicators such as stress and anxiety are calculated from voice and facial expression data and output as analysis data to the server.

[0396] Step 5:

[0397] The server combines answer data and sentiment data to identify the user's challenges and generates similar problems using a generative AI model. Detailed question conditions are set using prompts. As a data calculation, the AI ​​executes a problem generation algorithm tailored to the user's weaknesses and emotional state, outputting adjusted problems.

[0398] Step 6:

[0399] The server sends feedback based on the analysis, along with the generated similar problems, to the terminal. The terminal provides this information to the user to support the next learning step. Specifically, the feedback includes advice tailored to the test-taker's emotional state and suggestions to maintain motivation.

[0400] (Application Example 2)

[0401] Next, we will explain application example 2. In the following explanation, the data processing device 12 will be referred to as the "server," and the smart glasses 214 will be referred to as the "terminal."

[0402] Traditional educational support systems provide uniform learning content and feedback without considering the emotional state of test-takers, resulting in a standardized experience and making it difficult to provide detailed support tailored to the individual characteristics of each test-taker. Furthermore, there was a lack of means to effectively promote learning while reducing the emotional distress and stress experienced by users. This could potentially lead to decreased motivation and limitations in test-takers' performance.

[0403] The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means.

[0404] In this invention, the server includes means for presenting past academic institution questions based on the examinee's selection, means for receiving and analyzing the examinee's answer information to identify the examinee's weak areas, means for automatically generating similar questions corresponding to the weak areas, means for detecting the user's emotional state and making recommendations based on that emotional state in real time, and means for providing recommendation information to the user. This makes it possible to provide an optimal learning experience tailored to the individual emotional state of each examinee, enabling them to learn effectively while reducing stress.

[0405] An "examinee" is someone who is studying in order to take an examination at an academic institution.

[0406] "Academic institutions" refer to organizations and groups that conduct education and research, including universities and vocational schools.

[0407] "Past exam questions" refer to questions from exams previously administered by academic institutions.

[0408] "Answer information" refers to data on the answers that test-takers have submitted to past exam questions.

[0409] "Areas of weakness" refers to the areas or topics that a test-taker found particularly difficult to answer among the questions they answered.

[0410] "Similar problems" are related problems created to facilitate understanding for test-takers based on their identified areas of weakness.

[0411] "Emotional state" refers to the psychological state or emotions that a test-taker exhibits when working on the problems.

[0412] "Recommendation information" refers to information such as learning content and recommended products that are optimized based on the emotional state of the test taker.

[0413] The system implementing this invention is centered around a server, terminals, and users, and aims to highly personalize the learning experience of test takers. The server plays a central role in data processing, managing past exam questions from academic institutions and analyzing test takers' answer information and emotional states to generate feedback. Specifically, a data analysis system built in Python and generative AI technology (e.g., OpenAI GPT-3) are used to generate similar questions and provide recommendation information based on the test taker's weak areas and emotional state.

[0414] The device functions as a smartphone or personal computer, responsible for inputting test-takers' answer information and collecting voice and facial expression data. The collected data is analyzed by an emotion analysis engine (e.g., Affectiva SDK) within the device and transmitted to the server in real time.

[0415] Users, or test takers, use this system to work on past exam questions from academic institutions and input their answers. The server then analyzes the answers and provides personalized questions and feedback in a way that enhances the test taker's understanding. Furthermore, based on the test taker's emotional state, they can receive recommendations to maintain and improve their motivation.

[0416] For example, if a user is experiencing stress while working on a problem, the device's emotion analysis engine detects this state, and the server uses a generative AI model to provide the user with simple, basic problems designed to promote relaxation, as well as music recommendations to reduce stress. An example of a prompt to the generative AI model might be, "If a test-taker is showing signs of anxiety, what types of problems would help them calm down?" In this way, it is possible to provide detailed and personalized learning support.

[0417] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[0418] Step 1:

[0419] The user selects the academic institution and problem to study on their device. The user's selection data is used as input, and the selected problem information is sent to the server as output. The server then prepares a dataset of the corresponding past problems.

[0420] Step 2:

[0421] The device receives the user's response and inputs the voice and facial expression data into the emotion analysis engine. The input consists of the user's response data and real-time voice and facial expression data. The output is the analysis of this data, resulting in numerical information of the emotional state.

[0422] Step 3:

[0423] The server analyzes the received answer information and emotional state to identify areas of weakness. The input consists of the user's answer data and analyzed emotional information. The output generates evaluation data corresponding to the identified areas of weakness and the emotional state.

[0424] Step 4:

[0425] The server uses a generation AI model to automatically generate similar problems and determine the recommended difficulty level based on the user's emotional state. Input includes identified areas of difficulty and emotional data. The output is a personalized similar problem along with its explanation.

[0426] Step 5:

[0427] The server sends generated problems and recommendation feedback to the terminal. The input is the generated personalized problems and feedback data. The output is that actual learning is facilitated by providing the user with an optimized learning experience.

[0428] Step 6:

[0429] Users answer provided questions and receive feedback messages. The input consists of the user's answers and explanations. The output is personalized feedback that helps with future learning, thereby enhancing the learning experience.

[0430] Through these steps, the system provides flexible educational support tailored to the emotional state and learning progress of the test-taker.

[0431] The specific processing unit 290 transmits the result of the specific processing to the smart glasses 214. In the smart glasses 214, the control unit 46A causes the speaker 240 to output the result of the specific processing. The microphone 238 acquires audio indicating user input for the result of the specific processing. The control unit 46A transmits the audio data indicating user input acquired by the microphone 238 to the data processing unit 12. In the data processing unit 12, the specific processing unit 290 acquires the audio data.

[0432] Data generation model 58 is a type of so-called generative AI (Artificial Intelligence). One example of data generation model 58 is ChatGPT (Internet search<URL: https: / / openai.com / blog / chatgpt> ), Gemini (Internet search) <url: https: gemini.google.com ?hl="ja">Examples of generative AI include the following. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 is input with prompts containing instructions, and with inference data such as audio data representing speech, text data representing text, and image data representing images. The data generation model 58 infers from the input inference data according to the instructions indicated by the prompts, and outputs the inference results in data formats such as audio data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[0433] In the above embodiment, an example was given in which specific processing is performed by the data processing device 12, but the technology of this disclosure is not limited thereto, and the specific processing may also be performed by the smart glasses 214.

[0434] [Third Embodiment]

[0435] Figure 5 shows an example of the configuration of the data processing system 310 according to the third embodiment.

[0436] As shown in Figure 5, the data processing system 310 includes a data processing device 12 and a headset terminal 314. An example of the data processing device 12 is a server.

[0437] The data processing device 12 comprises a computer 22, a database 24, and a communication interface 26. The computer 22 is an example of a "computer" related to the technology of this disclosure. The computer 22 comprises a processor 28, RAM 30, and storage 32. The processor 28, RAM 30, and storage 32 are connected to a bus 34. The database 24 and the communication interface 26 are also connected to the bus 34. The communication interface 26 is connected to a network 54. An example of the network 54 is a WAN (Wide Area Network) and / or a LAN (Local Area Network).

[0438] The headset terminal 314 includes a computer 36, a microphone 238, a speaker 240, a camera 42, a communication interface 44, and a display 343. The computer 36 includes a processor 46, RAM 48, and storage 50. The processor 46, RAM 48, and storage 50 are connected to a bus 52. The microphone 238, speaker 240, camera 42, and display 343 are also connected to the bus 52.

[0439] The microphone 238 receives voice signals from the user 20 and receives instructions from the user 20. The microphone 238 captures the voice signals from the user 20, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio according to the instructions from the processor 46.

[0440] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an image sensor such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, and captures images of the area around the user 20 (for example, an imaging range defined by a field of view equivalent to the width of a typical healthy person's field of vision).

[0441] Communication interface 44 is connected to network 54. Communication interfaces 44 and 26 are responsible for the exchange of various information between processor 46 and processor 28 via network 54. The exchange of various information between processor 46 and processor 28 using communication interfaces 44 and 26 is performed in a secure manner.

[0442] Figure 6 shows an example of the main functions of the data processing device 12 and the headset terminal 314. As shown in Figure 6, the data processing device 12 performs specific processing using the processor 28. The storage 32 stores the specific processing program 56.

[0443] The specific processing program 56 is an example of a "program" relating to the technology of this disclosure. The processor 28 reads the specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific processing is realized by the processor 28 operating as a specific processing unit 290 in accordance with the specific processing program 56 executed on the RAM 30.

[0444] The storage 32 stores the data generation model 58 and the emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290.

[0445] In the headset terminal 314, the processor 46 performs the reception output processing. The storage 50 stores the reception output program 60. The processor 46 reads the reception output program 60 from the storage 50 and executes the read reception output program 60 on the RAM 48. The reception output processing is realized by the processor 46 operating as a control unit 46A according to the reception output program 60 executed on the RAM 48.

[0446] Next, the specific processing performed by the specific processing unit 290 of the data processing device 12 will be described. In the following description, the data processing device 12 will be referred to as the "server" and the headset terminal 314 will be referred to as the "terminal".

[0447] This invention is implemented as an educational support system to help examinees effectively study past examination questions from their desired academic institutions and overcome their weak areas. This system is realized through the exchange of digital data between a server, a terminal, and a user.

[0448] composition

[0449] Server: This server is the core of the system, storing past exam questions from various academic institutions as digital data. Each question is assigned metadata including the university name, faculty, subject, and year. Equipped with an analysis engine and generation AI, it identifies areas of weakness and generates similar questions based on the user's answer data.

[0450] Terminal: A device operated by the user, such as a smartphone or personal computer. Users can receive past exam questions from the server via their terminal and input their answers.

[0451] User: This role is taken on by the applicant, who is a user of the system. They utilize the system to solve problems related to the academic institution they wish to attend.

[0452] Implementation method

[0453] When a user logs into the system using their device, they can select their desired academic institution and subject and solve past exam questions. The server analyzes the answer data received from the user and identifies the examinee's weak areas. Based on the identified weak areas, the generating AI creates similar problems and sends the data to the device in order of difficulty. By working on these similar problems, the user can intensively strengthen specific areas.

[0454] As a concrete example, consider a user who aspires to work at a medical institution in a certain region and scores particularly low in biology. The server analyzes the answer data for life science-related errors, and a generative AI designs similar biology problems. These problems vary from basic to advanced levels, helping to improve accuracy and answer speed. The user is also provided with feedback on the analysis results, including explanations to help them understand their errors.

[0455] In this way, test-takers can efficiently tackle problems tailored to their weak areas and make progress in their studies toward passing the entrance exam for their desired academic institution.

[0456] The following describes the processing flow.

[0457] Step 1:

[0458] The user logs into their device and selects their desired academic institution and examination subjects on the device. This information is then sent from the device to the server.

[0459] Step 2:

[0460] Based on the information received by the server, past exam questions corresponding to the selected academic institution and subject are retrieved from the database. The retrieved questions are then sent to the terminal.

[0461] Step 3:

[0462] The terminal displays past exam questions received from the server to the user. The user answers the questions and enters the answers into the terminal. The terminal then sends the entered answer data to the server.

[0463] Step 4:

[0464] The server analyzes the received answer data and evaluates the user's accuracy rate and success / failure rate for each question. This helps identify which topics the user struggles with.

[0465] Step 5:

[0466] The server uses AI to generate similar problems targeting areas of weakness based on the analysis results. These similar problems are adjusted in difficulty from easy to complex.

[0467] Step 6:

[0468] The server generates similar problems and sends them to the terminal, which then presents them to the user. The user works on the presented similar problems and enters their answers into the terminal.

[0469] Step 7:

[0470] The user sends the results of similar problems they have answered to the server. The server analyzes the results again, generates explanations for incorrect answers, and updates the learning history.

[0471] Step 8:

[0472] The server sends the generated explanations and analysis results to the terminal as feedback. The terminal then presents this to the user, who continues learning while reviewing the feedback.

[0473] (Example 1)

[0474] Next, we will describe Example 1. In the following description, the data processing device 12 will be referred to as the "server," and the headset-type terminal 314 will be referred to as the "terminal."

[0475] In educational support, it is crucial for test-takers to accurately understand their learning progress and areas of weakness, and to practice problems accordingly. However, many systems struggle to identify individual test-takers' areas of weakness and provide appropriate problems, and their optimization considering multidimensional answer history is insufficient. This issue is important for test-takers to efficiently achieve their learning goals and needs to be resolved.

[0476] The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 1 is realized by the following means.

[0477] In this invention, the server includes means for retrieving past questions from educational institutions based on the examinee's selection, means for analyzing the examinee's answer information and identifying the examinee's weak areas, and means for generating questions related to the identified weak areas using a generative AI model. This allows examinees to work on individually customized questions to overcome their weak areas.

[0478] "Examinee" refers to an individual who studies for an examination administered by an academic institution.

[0479] An "educational institution" refers to an organization or group that teaches academic subjects or skills and administers examinations necessary for obtaining degrees or qualifications.

[0480] "Past questions" refers to questions and assignments used in exams previously administered by educational institutions.

[0481] "Answer information" refers to data that includes the responses and solutions that test-takers provided to the questions.

[0482] "Areas of weakness" refers to academic fields or subjects that the test-taker does not fully understand or in which they perform poorly.

[0483] A "generative AI model" refers to artificial intelligence technology that enables the automatic generation of new questions based on specific prompts.

[0484] "Generating a problem" refers to the act of creating new questions based on specific conditions or requirements.

[0485] "Learning history" refers to data that records the learning activities and answer patterns that test-takers have engaged in in the past.

[0486] "Adjusting the presentation of questions" refers to providing users with new questions at appropriate times and in appropriate order, based on their answer history and learning history.

[0487] "Feedback" refers to information provided regarding a test-taker's answers, including evaluations, suggestions for improvement, and explanations.

[0488] This educational support system effectively facilitates learning through the exchange of digital data between servers, terminals, and users. The specific roles of the hardware and software in each component are described below.

[0489] Server Role

[0490] The server is the heart of the system, storing past exam questions from educational institutions in digital format. Specifically, it uses a database management system to manage questions and associated metadata (such as institution name, subject, and year). The server is equipped with an analysis engine and a generative AI model, which receives user answer information in real time and analyzes it to identify areas where test-takers struggle. Based on this information, the generative AI model generates similar related questions. For example, the generative AI model can be given prompts such as "Generate questions on basic biology knowledge and adjust the difficulty level."

[0491] Terminal role

[0492] A terminal is a device that the user directly operates, such as a smartphone or a personal computer. Users can use their terminal to log in to the server, receive questions, and enter answers. The application on the terminal facilitates the selection of past questions and the input of answers through its user interface, and is responsible for sending the answer data to the server.

[0493] User roles

[0494] Users are the direct users of the system, and their primary role is to solve the provided problems and enter their answers. Users access the system from their terminals, select their desired educational institution and subject, and then work on past problems. They can utilize feedback sent from the server and new similar problems to focus on areas where they struggle.

[0495] This system allows test-takers to efficiently focus their studies on areas where they are weak, thereby improving the quality of their learning.

[0496] The flow of the specific processing in Example 1 will be explained using Figure 11.

[0497] Step 1:

[0498] The user logs into the system using their device. On the login screen, they enter their username and password, and the authentication information is sent to the server. The server compares the authentication information with the database, and if authentication is successful, it returns a customized dashboard to the user.

[0499] Step 2:

[0500] The user selects their desired educational institution and subject on their device. The user's selection information is sent to the server, which searches its database for past exam questions that match the selected criteria. The server returns the relevant questions to the device along with their metadata.

[0501] Step 3:

[0502] The user enters their answers to past questions obtained on their device. The answer data is sent to the server in real time. The server uses an analysis engine to analyze the answer data and identify the user's weak areas. The analysis results are stored in a database as the user's answer history.

[0503] Step 4:

[0504] The server uses a generative AI model to generate problems related to identified areas of weakness. The prompts used are in the format of "Generate a question on basic biology knowledge and adjust the difficulty level," and the generated problems are organized by difficulty level. These results are then sent to the terminal.

[0505] Step 5:

[0506] Users work on similar problems generated on their devices. After entering their answers, this information is sent back to the server for analysis. Based on this analysis, new areas of weakness are identified, and the server optimizes the learning process for the next session. Users receive feedback on their accuracy rate and areas for improvement.

[0507] Step 6:

[0508] The server updates individual learning histories based on this information and reflects it in the next set of questions. On the user's device, their progress is displayed, allowing them to create an appropriate learning plan. This enables overall reinforcement of the course material.

[0509] (Application Example 1)

[0510] Next, we will explain Application Example 1. In the following explanation, the data processing device 12 will be referred to as the "server," and the headset-type terminal 314 will be referred to as the "terminal."

[0511] A challenge exists in that learners struggle to efficiently study past exam questions and overcome individual weaknesses when preparing for exams at their desired educational institutions. Furthermore, there is a lack of systems that present questions in stages according to each learner's level of understanding and provide appropriate learning methods. Therefore, there is a need to provide individually customized learning plans and present optimal questions according to the learner's progress.

[0512] The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 1 is realized by the following means.

[0513] In this invention, the server includes means for presenting past exam questions from educational institutions based on the examinee's selection, means for receiving and analyzing the examinee's answer information to identify the examinee's weak areas, and means for presenting generated similar questions to the examinee and accepting their answers. This enables learners to efficiently prepare for exams using individually customized learning methods.

[0514] "Examinee" refers to an individual who is studying in preparation for an examination administered by an educational institution.

[0515] "Educational institutions" refer to organizations that provide education, such as public or private schools and universities.

[0516] "Past exam questions" refers to exam questions that educational institutions have used in past years.

[0517] "Answer information" refers to the answer data submitted by test takers to the questions.

[0518] A "weakness area" refers to a learning area that has been identified as being particularly poorly understood by the test-taker.

[0519] A "similar problem" refers to a problem that is similar in format and content to the original problem, but is created to help test-takers overcome their weaknesses.

[0520] "Explanation" refers to a description of the questions and answers intended to help test-takers gain a deeper understanding.

[0521] "Optimizing learning methods" refers to the process of adjusting the most effective learning approach to match the current progress and level of understanding.

[0522] "Presenting gradually" refers to gradually adjusting the complexity and difficulty of the questions according to the test-taker's level of understanding.

[0523] One embodiment of the present invention is a system that provides an individualized learning experience through the cooperation of a terminal held by the examinee and a server. The terminal serves to provide an interface for the examinee to operate, select past questions, and input answers. This interface can operate on smartphones, personal computers, and other devices.

[0524] The server receives answer information submitted by test-takers and uses an analysis engine to identify the test-takers' weak areas. Based on the analysis results, the server utilizes a generative AI model to generate similar problems based on the test-takers' weaknesses. These generated similar problems are sent to the terminal, allowing the test-taker to try again. The analysis engine and generative AI mentioned above are implemented using Python or other machine learning frameworks.

[0525] As a concrete example, if a test-taker answers a question about cell division incorrectly while taking a biology exam, the server uses this information to generate a question explaining each stage of cell division and presents it to the test-taker again. This allows the test-taker to pinpoint and strengthen their weak areas.

[0526] An example of a prompt might be, "Create questions on the area the test-taker most frequently got wrong in past biology exams." This allows the generative AI to generate appropriate new questions and provide a learning experience optimized for each individual test-taker.

[0527] The flow of a specific process in Application Example 1 will be explained using Figure 12.

[0528] Step 1:

[0529] The user logs into the system using their device. This requires a user ID and password. At this stage, the device sends the user's authentication information to the server. If authentication is successful, the server receives learning history and progress information. Based on this information, a personalized main menu is displayed to the user.

[0530] Step 2:

[0531] The user selects the subject and educational institution they wish to study. The options are based on a past exam dataset provided by the server. Once the selection is complete, the selection information is sent to the server, and the relevant past exam questions are sent from the server to the terminal. The terminal then displays the questions to the user.

[0532] Step 3:

[0533] The user answers the provided test questions. The answers are sent to the server via the terminal. The input here is the user's answer data, which the server analyzes to calculate the areas where mistakes were made and the accuracy rate. As a result, the user's weak areas are identified.

[0534] Step 4:

[0535] Based on the analysis results, the server uses a generative AI model to generate similar problems that address the user's weak areas. The input is information about the weak areas, and the output is a set of generated problems. Specifically, prompt sentences are input to the generative AI model, and the generated problems are sent to the terminal.

[0536] Step 5:

[0537] The terminal presents the user with a newly generated similar problem. The user answers the problem, and the answer data is sent back to the server. This process is often repeated to deepen the user's understanding.

[0538] Step 6:

[0539] The server aggregates multiple answer data and provides the user with detailed explanations and suggested learning plans as feedback. This allows the user to obtain information that they can use in their next learning session. Based on the feedback, the server considers starting a new learning session and generates more targeted problems as needed.

[0540] Furthermore, an emotion engine that estimates the user's emotions may be incorporated. That is, the identification processing unit 290 may use the emotion identification model 59 to estimate the user's emotions and perform identification processing using the user's emotions.

[0541] This invention is an educational support system that integrates emotion recognition technology to enable examinees to effectively study past examination questions from their desired academic institutions. The system consists of a server, a terminal, and a user, and optimizes the learning content while taking into account the examinee's emotional state.

[0542] composition

[0543] Server: Manages the core functions of the system, centrally managing past exam questions as digital data. Analyzes answers and sentiment data received from users to optimize learning and feedback. Equipped with generative AI and a sentiment engine to personalize the user's learning experience.

[0544] Terminal: This refers to the device used by the user, including smartphones and personal computers. It collects user input data and analyzes their emotional state through voice and facial expressions using an emotion engine.

[0545] User: An examinee who uses the educational support system and utilizes this system when working on problems from the target academic institution.

[0546] Implementation method

[0547] The user accesses the system through a terminal and selects their desired academic institution and subject. Appropriate past exam questions are provided to the terminal from the server, and the user answers them. While answering, the terminal records the user's voice and facial expressions, and the user's emotional state is evaluated by analyzing this data with an emotion engine.

[0548] The server uses received answer data and sentiment data to identify the user's weak areas and generates similar problems using a generation AI. These similar problems can reflect the user's emotional state and have their difficulty and content adjusted to reduce stress or improve motivation. For example, if the user is showing anxiety, the generated problems will be adjusted to be more basic. In addition, feedback based on sentiment analysis is provided to the device, offering advice and useful content to help the user calm down.

[0549] This system allows test-takers to efficiently overcome their weak areas with appropriate support, even under high stress levels, and to engage in learning that leads to success in gaining admission to their desired academic institution.

[0550] The following describes the processing flow.

[0551] Step 1:

[0552] The user logs into their device and selects their desired academic institution and subject on the device. The selection is then sent from the device to the server.

[0553] Step 2:

[0554] Based on the information received by the server, past exam questions for the selected academic institution and subject are retrieved from the database. The retrieved questions are then sent to the terminal.

[0555] Step 3:

[0556] The terminal displays past exam questions received from the server to the user. The user answers the questions and enters their answers into the terminal.

[0557] Step 4:

[0558] While the user is answering, the device records the user's voice and facial expressions through sensors, and analyzes the user's real-time emotional data using an emotion engine.

[0559] Step 5:

[0560] Answer data and sentiment data are sent from the terminal to the server. The server analyzes the answer data to identify the user's areas of weakness.

[0561] Step 6:

[0562] Based on the server's identified weaknesses and real-time emotional data, a generative AI is used to create similar problems. These problems are optimized and adjusted to the user's emotional state.

[0563] Step 7:

[0564] Similar problems are generated and sent from the server to the terminal, which then presents them to the user. The user works on the similar problems and enters their answers.

[0565] Step 8:

[0566] The results of similar problems and user sentiment data are sent from the device to the server, where the server performs further analysis. Based on the analysis results, feedback and advice are generated, and the learning history is updated.

[0567] Step 9:

[0568] The server sends generated feedback and advice to the terminal, which then provides it to the user. The user reviews their learning progress and plans their next learning steps.

[0569] (Example 2)

[0570] Next, we will describe Example 2. In the following description, the data processing device 12 will be referred to as the "server," and the headset-type terminal 314 will be referred to as the "terminal."

[0571] Providing an optimized educational experience that fully considers each learner's emotional state and areas of difficulty during the learning process has been challenging. Traditional systems lacked feedback and problem-solving tailored to learners' emotions, making it difficult to maintain their motivation. Furthermore, there is a need for more effective and personalized learning support that utilizes not only answer data but also emotional data.

[0572] The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 2 is realized by the following means.

[0573] In this invention, the server includes means for analyzing the examinee's answer data and emotional data to identify the examinee's problem area, means for automatically generating similar problems corresponding to the examinee's emotional state using a generative AI model and prompt sentences, and means for analyzing the answer results and emotional data to provide emotion-based feedback. This makes it possible to adjust the difficulty level of the problems according to each examinee's emotional state and learning progress, thereby realizing appropriate and individualized learning support.

[0574] "Examinee" refers to an individual who studies in preparation for evaluation by an educational institution and takes a specific test.

[0575] "Past exam data from educational institutions" refers to a collection of information that digitally stores exam questions from past examinations conducted by educational institutions.

[0576] "Answer data" refers to the information that examinees have written down in response to the exam questions presented to them.

[0577] "Emotional data" refers to information that represents the emotional state of the test taker, analyzed based on their voice, facial expressions, and other factors.

[0578] A "problem area" refers to the area of ​​knowledge or skills in which the test taker shows particular weakness or deficiency during their studies.

[0579] A "generative AI model" refers to a program that uses artificial intelligence technology to automatically generate problems.

[0580] A "prompt" refers to a text-based instruction entered into a generative AI model to tell it to perform a specific action.

[0581] A "similar question" refers to a new question that is based on an existing exam question and has similar characteristics in terms of format and content.

[0582] "Feedback" refers to evaluations and advice provided based on the test taker's answers and emotional data.

[0583] This invention is an educational support system that enables examinees to effectively learn based on past exam data from educational institutions. The system consists of a server, terminals, and users, each playing a specific role.

[0584] About the server

[0585] The server is the core of the system, centrally managing past exam data. It receives answer data and sentiment data sent from the test-taker's terminal and analyzes this data to identify areas where the test-taker needs improvement in their learning. Furthermore, it uses a generative AI model to automatically generate similar questions based on the test-taker's emotional state. In this process, prompts are used to set specific conditions for the questions in the generative AI model. For example, instructions such as "If the user is showing anxiety, generate a basic-level question" can be given.

[0586] About the device

[0587] A terminal is a device used by the user, and includes smartphones and personal computers. The terminal presents problems provided by the server, accepts answers from the user, and acquires emotional data such as voice and facial expressions. The terminal is equipped with an emotion engine, which enables real-time analysis of the user's emotions.

[0588] About the user

[0589] The user is a test-taker who uses this system as a learner. The user accesses the system from a terminal and selects educational institutions and subjects of interest. Emotional data collected during the problem-solving process is used to create questions that reflect the user's emotional state, such as stress and anxiety.

[0590] As a concrete example, when a user works on past exam questions for a specific subject, the device monitors their voice and facial expressions after each problem solved to determine whether they are focused, anxious, or frustrated. This information is sent to a server, and the difficulty and content of the next questions presented are adjusted through a generative AI model. In this way, the user's learning experience becomes more individualized and optimized.

[0591] The flow of the specific processing in Example 2 will be explained using Figure 13.

[0592] Step 1:

[0593] The user accesses the educational support system by operating a terminal and selects their target educational institution and subjects. This selection information is then sent from the terminal to the server, conveying the user's intended learning content to the server. Specifically, user selection data entered on the terminal is sent to the server, which then searches for appropriate past exam questions based on this data.

[0594] Step 2:

[0595] The server searches past problem data based on the user's selection information and selects an appropriate set of problems. The server then sends the selected problems to the terminal in digital format. For data processing, relevant data is extracted from the problem database of the educational institution the user wishes to attend and converted into a format that can be presented to the user.

[0596] Step 3:

[0597] The terminal displays a set of questions sent from the server to the user. The user answers the presented questions, and the answer data is entered into the terminal. The entered answers are sent to the server in real time, and at the same time, emotion data is collected using voice input and facial recognition functions via the camera.

[0598] Step 4:

[0599] The device analyzes collected emotional data using its built-in emotion engine to evaluate the user's emotional state. The evaluation results are sent to the server and used to comprehensively understand the user's learning progress along with their answers. Specifically, emotional indicators such as stress and anxiety are calculated from voice and facial expression data and output as analysis data to the server.

[0600] Step 5:

[0601] The server combines answer data and sentiment data to identify the user's challenges and generates similar problems using a generative AI model. Detailed question conditions are set using prompts. As a data calculation, the AI ​​executes a problem generation algorithm tailored to the user's weaknesses and emotional state, outputting adjusted problems.

[0602] Step 6:

[0603] The server sends feedback based on the analysis, along with the generated similar problems, to the terminal. The terminal provides this information to the user to support the next learning step. Specifically, the feedback includes advice tailored to the test-taker's emotional state and suggestions to maintain motivation.

[0604] (Application Example 2)

[0605] Next, we will explain application example 2. In the following explanation, the data processing device 12 will be referred to as the "server," and the headset-type terminal 314 will be referred to as the "terminal."

[0606] Traditional educational support systems provide uniform learning content and feedback without considering the emotional state of test-takers, resulting in a standardized experience and making it difficult to provide detailed support tailored to the individual characteristics of each test-taker. Furthermore, there was a lack of means to effectively promote learning while reducing the emotional distress and stress experienced by users. This could potentially lead to decreased motivation and limitations in test-takers' performance.

[0607] The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means.

[0608] In this invention, the server includes means for presenting past academic institution questions based on the examinee's selection, means for receiving and analyzing the examinee's answer information to identify the examinee's weak areas, means for automatically generating similar questions corresponding to the weak areas, means for detecting the user's emotional state and making recommendations based on that emotional state in real time, and means for providing recommendation information to the user. This makes it possible to provide an optimal learning experience tailored to the individual emotional state of each examinee, enabling them to learn effectively while reducing stress.

[0609] An "examinee" is someone who is studying in order to take an examination at an academic institution.

[0610] "Academic institutions" refer to organizations and groups that conduct education and research, including universities and vocational schools.

[0611] "Past exam questions" refer to questions from exams previously administered by academic institutions.

[0612] "Answer information" refers to data on the answers that test-takers have submitted to past exam questions.

[0613] "Areas of weakness" refers to the areas or topics that a test-taker found particularly difficult to answer among the questions they answered.

[0614] "Similar problems" are related problems created to facilitate understanding for test-takers based on their identified areas of weakness.

[0615] "Emotional state" refers to the psychological state or emotions that a test-taker exhibits when working on the problems.

[0616] "Recommendation information" refers to information such as learning content and recommended products that are optimized based on the emotional state of the test taker.

[0617] The system implementing this invention is centered around a server, terminals, and users, and aims to highly personalize the learning experience of test takers. The server plays a central role in data processing, managing past exam questions from academic institutions and analyzing test takers' answer information and emotional states to generate feedback. Specifically, a data analysis system built in Python and generative AI technology (e.g., OpenAI GPT-3) are used to generate similar questions and provide recommendation information based on the test taker's weak areas and emotional state.

[0618] The device functions as a smartphone or personal computer, responsible for inputting test-takers' answer information and collecting voice and facial expression data. The collected data is analyzed by an emotion analysis engine (e.g., Affectiva SDK) within the device and transmitted to the server in real time.

[0619] Users, or test takers, use this system to work on past exam questions from academic institutions and input their answers. The server then analyzes the answers and provides personalized questions and feedback in a way that enhances the test taker's understanding. Furthermore, based on the test taker's emotional state, they can receive recommendations to maintain and improve their motivation.

[0620] For example, if a user is experiencing stress while working on a problem, the device's emotion analysis engine detects this state, and the server uses a generative AI model to provide the user with simple, basic problems designed to promote relaxation, as well as music recommendations to reduce stress. An example of a prompt to the generative AI model might be, "If a test-taker is showing signs of anxiety, what types of problems would help them calm down?" In this way, it is possible to provide detailed and personalized learning support.

[0621] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[0622] Step 1:

[0623] The user selects the academic institution and problem to study on their device. The user's selection data is used as input, and the selected problem information is sent to the server as output. The server then prepares a dataset of the corresponding past problems.

[0624] Step 2:

[0625] The device receives the user's response and inputs the voice and facial expression data into the emotion analysis engine. The input consists of the user's response data and real-time voice and facial expression data. The output is the analysis of this data, resulting in numerical information of the emotional state.

[0626] Step 3:

[0627] The server analyzes the received answer information and emotional state to identify areas of weakness. The input consists of the user's answer data and analyzed emotional information. The output generates evaluation data corresponding to the identified areas of weakness and the emotional state.

[0628] Step 4:

[0629] The server uses a generation AI model to automatically generate similar problems and determine the recommended difficulty level based on the user's emotional state. Input includes identified areas of difficulty and emotional data. The output is a personalized similar problem along with its explanation.

[0630] Step 5:

[0631] The server sends generated problems and recommendation feedback to the terminal. The input is the generated personalized problems and feedback data. The output is that actual learning is facilitated by providing the user with an optimized learning experience.

[0632] Step 6:

[0633] Users answer provided questions and receive feedback messages. The input consists of the user's answers and explanations. The output is personalized feedback that helps with future learning, thereby enhancing the learning experience.

[0634] Through these steps, the system provides flexible educational support tailored to the emotional state and learning progress of the test-taker.

[0635] The specific processing unit 290 transmits the result of the specific processing to the headset terminal 314. In the headset terminal 314, the control unit 46A causes the speaker 240 and display 343 to output the result of the specific processing. The microphone 238 acquires audio indicating user input for the result of the specific processing. The control unit 46A transmits the audio data indicating user input acquired by the microphone 238 to the data processing unit 12. In the data processing unit 12, the specific processing unit 290 acquires the audio data.

[0636] Data generation model 58 is a type of so-called generative AI (Artificial Intelligence). One example of data generation model 58 is ChatGPT (Internet search<URL: https: / / openai.com / blog / chatgpt> ), Gemini (Internet search) <url: https: gemini.google.com ?hl="ja">Examples of generative AI include the following. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 is input with prompts containing instructions, and with inference data such as audio data representing speech, text data representing text, and image data representing images. The data generation model 58 infers from the input inference data according to the instructions indicated by the prompts, and outputs the inference results in data formats such as audio data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[0637] In the above embodiment, an example was given in which specific processing is performed by the data processing device 12, but the technology of this disclosure is not limited thereto, and specific processing may also be performed by the headset terminal 314.

[0638] [Fourth Embodiment]

[0639] Figure 7 shows an example of the configuration of the data processing system 410 according to the fourth embodiment.

[0640] As shown in Figure 7, the data processing system 410 includes a data processing device 12 and a robot 414. An example of the data processing device 12 is a server.

[0641] The data processing device 12 comprises a computer 22, a database 24, and a communication interface 26. The computer 22 is an example of a "computer" related to the technology of this disclosure. The computer 22 comprises a processor 28, RAM 30, and storage 32. The processor 28, RAM 30, and storage 32 are connected to a bus 34. The database 24 and the communication interface 26 are also connected to the bus 34. The communication interface 26 is connected to a network 54. An example of the network 54 is a WAN (Wide Area Network) and / or a LAN (Local Area Network).

[0642] The robot 414 includes a computer 36, a microphone 238, a speaker 240, a camera 42, a communication interface 44, and a controlled object 443. The computer 36 includes a processor 46, RAM 48, and storage 50. The processor 46, RAM 48, and storage 50 are connected to a bus 52. The microphone 238, speaker 240, camera 42, and controlled object 443 are also connected to the bus 52.

[0643] The microphone 238 receives voice signals from the user 20 and receives instructions from the user 20. The microphone 238 captures the voice signals from the user 20, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio according to the instructions from the processor 46.

[0644] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an image sensor such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, and captures images of the area around the user 20 (for example, an imaging range defined by a field of view equivalent to the width of a typical healthy person's field of vision).

[0645] Communication interface 44 is connected to network 54. Communication interfaces 44 and 26 are responsible for the exchange of various information between processor 46 and processor 28 via network 54. The exchange of various information between processor 46 and processor 28 using communication interfaces 44 and 26 is performed in a secure manner.

[0646] The controlled object 443 includes a display device, LEDs in the eyes, and motors that drive the arms, hands, and feet. The posture and gestures of the robot 414 are controlled by controlling the motors of the arms, hands, and feet. Some of the robot 414's emotions can be expressed by controlling these motors. Furthermore, the robot 414's facial expressions can also be expressed by controlling the illumination state of the LEDs in its eyes.

[0647] Figure 8 shows an example of the main functions of the data processing device 12 and the robot 414. As shown in Figure 8, the data processing device 12 performs specific processing using the processor 28. The storage 32 stores the specific processing program 56.

[0648] The specific processing program 56 is an example of a "program" relating to the technology of this disclosure. The processor 28 reads the specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific processing is realized by the processor 28 operating as a specific processing unit 290 in accordance with the specific processing program 56 executed on the RAM 30.

[0649] The storage 32 stores the data generation model 58 and the emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290.

[0650] In robot 414, the processor 46 performs the reception output processing. The storage 50 stores the reception output program 60. The processor 46 reads the reception output program 60 from the storage 50 and executes the read reception output program 60 on the RAM 48. The reception output processing is realized by the processor 46 operating as a control unit 46A according to the reception output program 60 executed on the RAM 48.

[0651] Next, the specific processing performed by the specific processing unit 290 of the data processing device 12 will be described. In the following description, the data processing device 12 will be referred to as the "server" and the robot 414 as the "terminal".

[0652] This invention is implemented as an educational support system to help examinees effectively study past examination questions from their desired academic institutions and overcome their weak areas. This system is realized through the exchange of digital data between a server, a terminal, and a user.

[0653] composition

[0654] Server: This server is the core of the system, storing past exam questions from various academic institutions as digital data. Each question is assigned metadata including the university name, faculty, subject, and year. Equipped with an analysis engine and generation AI, it identifies areas of weakness and generates similar questions based on the user's answer data.

[0655] Terminal: A device operated by the user, such as a smartphone or personal computer. Users can receive past exam questions from the server via their terminal and input their answers.

[0656] User: This role is taken on by the applicant, who is a user of the system. They utilize the system to solve problems related to the academic institution they wish to attend.

[0657] Implementation method

[0658] When a user logs into the system using their device, they can select their desired academic institution and subject and solve past exam questions. The server analyzes the answer data received from the user and identifies the examinee's weak areas. Based on the identified weak areas, the generating AI creates similar problems and sends the data to the device in order of difficulty. By working on these similar problems, the user can intensively strengthen specific areas.

[0659] As a concrete example, consider a user who aspires to work at a medical institution in a certain region and scores particularly low in biology. The server analyzes the answer data for life science-related errors, and a generative AI designs similar biology problems. These problems vary from basic to advanced levels, helping to improve accuracy and answer speed. The user is also provided with feedback on the analysis results, including explanations to help them understand their errors.

[0660] In this way, test-takers can efficiently tackle problems tailored to their weak areas and make progress in their studies toward passing the entrance exam for their desired academic institution.

[0661] The following describes the processing flow.

[0662] Step 1:

[0663] The user logs into their device and selects their desired academic institution and examination subjects on the device. This information is then sent from the device to the server.

[0664] Step 2:

[0665] Based on the information received by the server, past exam questions corresponding to the selected academic institution and subject are retrieved from the database. The retrieved questions are then sent to the terminal.

[0666] Step 3:

[0667] The terminal displays past exam questions received from the server to the user. The user answers the questions and enters the answers into the terminal. The terminal then sends the entered answer data to the server.

[0668] Step 4:

[0669] The server analyzes the received answer data and evaluates the user's accuracy rate and success / failure rate for each question. This helps identify which topics the user struggles with.

[0670] Step 5:

[0671] The server uses AI to generate similar problems targeting areas of weakness based on the analysis results. These similar problems are adjusted in difficulty from easy to complex.

[0672] Step 6:

[0673] The server generates similar problems and sends them to the terminal, which then presents them to the user. The user works on the presented similar problems and enters their answers into the terminal.

[0674] Step 7:

[0675] The user sends the results of similar problems they have answered to the server. The server analyzes the results again, generates explanations for incorrect answers, and updates the learning history.

[0676] Step 8:

[0677] The server sends the generated explanations and analysis results to the terminal as feedback. The terminal then presents this to the user, who continues learning while reviewing the feedback.

[0678] (Example 1)

[0679] Next, we will describe Example 1. In the following description, the data processing device 12 will be referred to as the "server" and the robot 414 as the "terminal".

[0680] In educational support, it is crucial for test-takers to accurately understand their learning progress and areas of weakness, and to practice problems accordingly. However, many systems struggle to identify individual test-takers' areas of weakness and provide appropriate problems, and their optimization considering multidimensional answer history is insufficient. This issue is important for test-takers to efficiently achieve their learning goals and needs to be resolved.

[0681] The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 1 is realized by the following means.

[0682] In this invention, the server includes means for retrieving past questions from educational institutions based on the examinee's selection, means for analyzing the examinee's answer information and identifying the examinee's weak areas, and means for generating questions related to the identified weak areas using a generative AI model. This allows examinees to work on individually customized questions to overcome their weak areas.

[0683] "Examinee" refers to an individual who studies for an examination administered by an academic institution.

[0684] An "educational institution" refers to an organization or group that teaches academic subjects or skills and administers examinations necessary for obtaining degrees or qualifications.

[0685] "Past questions" refers to questions and assignments used in exams previously administered by educational institutions.

[0686] "Answer information" refers to data that includes the responses and solutions that test-takers provided to the questions.

[0687] "Areas of weakness" refers to academic fields or subjects that the test-taker does not fully understand or in which they perform poorly.

[0688] A "generative AI model" refers to artificial intelligence technology that enables the automatic generation of new questions based on specific prompts.

[0689] "Generating a problem" refers to the act of creating new questions based on specific conditions or requirements.

[0690] "Learning history" refers to data that records the learning activities and answer patterns that test-takers have engaged in in the past.

[0691] "Adjusting the presentation of questions" refers to providing users with new questions at appropriate times and in appropriate order, based on their answer history and learning history.

[0692] "Feedback" refers to information provided regarding a test-taker's answers, including evaluations, suggestions for improvement, and explanations.

[0693] This educational support system effectively facilitates learning through the exchange of digital data between servers, terminals, and users. The specific roles of the hardware and software in each component are described below.

[0694] Server Role

[0695] The server is the heart of the system, storing past exam questions from educational institutions in digital format. Specifically, it uses a database management system to manage questions and associated metadata (such as institution name, subject, and year). The server is equipped with an analysis engine and a generative AI model, which receives user answer information in real time and analyzes it to identify areas where test-takers struggle. Based on this information, the generative AI model generates similar related questions. For example, the generative AI model can be given prompts such as "Generate questions on basic biology knowledge and adjust the difficulty level."

[0696] Terminal role

[0697] A terminal is a device that the user directly operates, such as a smartphone or a personal computer. Users can use their terminal to log in to the server, receive questions, and enter answers. The application on the terminal facilitates the selection of past questions and the input of answers through its user interface, and is responsible for sending the answer data to the server.

[0698] User roles

[0699] Users are the direct users of the system, and their primary role is to solve the provided problems and enter their answers. Users access the system from their terminals, select their desired educational institution and subject, and then work on past problems. They can utilize feedback sent from the server and new similar problems to focus on areas where they struggle.

[0700] This system allows test-takers to efficiently focus their studies on areas where they are weak, thereby improving the quality of their learning.

[0701] The flow of the specific processing in Example 1 will be explained using Figure 11.

[0702] Step 1:

[0703] The user logs into the system using their device. On the login screen, they enter their username and password, and the authentication information is sent to the server. The server compares the authentication information with the database, and if authentication is successful, it returns a customized dashboard to the user.

[0704] Step 2:

[0705] The user selects their desired educational institution and subject on their device. The user's selection information is sent to the server, which searches its database for past exam questions that match the selected criteria. The server returns the relevant questions to the device along with their metadata.

[0706] Step 3:

[0707] The user enters their answers to past questions obtained on their device. The answer data is sent to the server in real time. The server uses an analysis engine to analyze the answer data and identify the user's weak areas. The analysis results are stored in a database as the user's answer history.

[0708] Step 4:

[0709] The server uses a generative AI model to generate problems related to identified areas of weakness. The prompts used are in the format of "Generate a question on basic biology knowledge and adjust the difficulty level," and the generated problems are organized by difficulty level. These results are then sent to the terminal.

[0710] Step 5:

[0711] Users work on similar problems generated on their devices. After entering their answers, this information is sent back to the server for analysis. Based on this analysis, new areas of weakness are identified, and the server optimizes the learning process for the next session. Users receive feedback on their accuracy rate and areas for improvement.

[0712] Step 6:

[0713] The server updates individual learning histories based on this information and reflects it in the next set of questions. On the user's device, their progress is displayed, allowing them to create an appropriate learning plan. This enables overall reinforcement of the course material.

[0714] (Application Example 1)

[0715] Next, we will explain Application Example 1. In the following explanation, the data processing device 12 will be referred to as the "server" and the robot 414 as the "terminal".

[0716] A challenge exists in that learners struggle to efficiently study past exam questions and overcome individual weaknesses when preparing for exams at their desired educational institutions. Furthermore, there is a lack of systems that present questions in stages according to each learner's level of understanding and provide appropriate learning methods. Therefore, there is a need to provide individually customized learning plans and present optimal questions according to the learner's progress.

[0717] The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 1 is realized by the following means.

[0718] In this invention, the server includes means for presenting past exam questions from educational institutions based on the examinee's selection, means for receiving and analyzing the examinee's answer information to identify the examinee's weak areas, and means for presenting generated similar questions to the examinee and accepting their answers. This enables learners to efficiently prepare for exams using individually customized learning methods.

[0719] "Examinee" refers to an individual who is studying in preparation for an examination administered by an educational institution.

[0720] "Educational institutions" refer to organizations that provide education, such as public or private schools and universities.

[0721] "Past exam questions" refers to exam questions that educational institutions have used in past years.

[0722] "Answer information" refers to the answer data submitted by test takers to the questions.

[0723] A "weakness area" refers to a learning area that has been identified as being particularly poorly understood by the test-taker.

[0724] A "similar problem" refers to a problem that is similar in format and content to the original problem, but is created to help test-takers overcome their weaknesses.

[0725] "Explanation" refers to a description of the questions and answers intended to help test-takers gain a deeper understanding.

[0726] "Optimizing learning methods" refers to the process of adjusting the most effective learning approach to match the current progress and level of understanding.

[0727] "Presenting gradually" refers to gradually adjusting the complexity and difficulty of the questions according to the test-taker's level of understanding.

[0728] One embodiment of the present invention is a system that provides an individualized learning experience through the cooperation of a terminal held by the examinee and a server. The terminal serves to provide an interface for the examinee to operate, select past questions, and input answers. This interface can operate on smartphones, personal computers, and other devices.

[0729] The server receives answer information submitted by test-takers and uses an analysis engine to identify the test-takers' weak areas. Based on the analysis results, the server utilizes a generative AI model to generate similar problems based on the test-takers' weaknesses. These generated similar problems are sent to the terminal, allowing the test-taker to try again. The analysis engine and generative AI mentioned above are implemented using Python or other machine learning frameworks.

[0730] As a concrete example, if a test-taker answers a question about cell division incorrectly while taking a biology exam, the server uses this information to generate a question explaining each stage of cell division and presents it to the test-taker again. This allows the test-taker to pinpoint and strengthen their weak areas.

[0731] An example of a prompt might be, "Create questions on the area the test-taker most frequently got wrong in past biology exams." This allows the generative AI to generate appropriate new questions and provide a learning experience optimized for each individual test-taker.

[0732] The flow of a specific process in Application Example 1 will be explained using Figure 12.

[0733] Step 1:

[0734] The user logs into the system using their device. This requires a user ID and password. At this stage, the device sends the user's authentication information to the server. If authentication is successful, the server receives learning history and progress information. Based on this information, a personalized main menu is displayed to the user.

[0735] Step 2:

[0736] The user selects the subject and educational institution they wish to study. The options are based on a past exam dataset provided by the server. Once the selection is complete, the selection information is sent to the server, and the relevant past exam questions are sent from the server to the terminal. The terminal then displays the questions to the user.

[0737] Step 3:

[0738] The user answers the provided test questions. The answers are sent to the server via the terminal. The input here is the user's answer data, which the server analyzes to calculate the areas where mistakes were made and the accuracy rate. As a result, the user's weak areas are identified.

[0739] Step 4:

[0740] Based on the analysis results, the server uses a generative AI model to generate similar problems that address the user's weak areas. The input is information about the weak areas, and the output is a set of generated problems. Specifically, prompt sentences are input to the generative AI model, and the generated problems are sent to the terminal.

[0741] Step 5:

[0742] The terminal presents the user with a newly generated similar problem. The user answers the problem, and the answer data is sent back to the server. This process is often repeated to deepen the user's understanding.

[0743] Step 6:

[0744] The server aggregates multiple answer data and provides the user with detailed explanations and suggested learning plans as feedback. This allows the user to obtain information that they can use in their next learning session. Based on the feedback, the server considers starting a new learning session and generates more targeted problems as needed.

[0745] Furthermore, an emotion engine that estimates the user's emotions may be incorporated. That is, the identification processing unit 290 may use the emotion identification model 59 to estimate the user's emotions and perform identification processing using the user's emotions.

[0746] This invention is an educational support system that integrates emotion recognition technology to enable examinees to effectively study past examination questions from their desired academic institutions. The system consists of a server, a terminal, and a user, and optimizes the learning content while taking into account the examinee's emotional state.

[0747] composition

[0748] Server: Manages the core functions of the system, centrally managing past exam questions as digital data. Analyzes answers and sentiment data received from users to optimize learning and feedback. Equipped with generative AI and a sentiment engine to personalize the user's learning experience.

[0749] Terminal: This refers to the device used by the user, including smartphones and personal computers. It collects user input data and analyzes their emotional state through voice and facial expressions using an emotion engine.

[0750] User: An examinee who uses the educational support system and utilizes this system when working on problems from the target academic institution.

[0751] Implementation method

[0752] The user accesses the system through a terminal and selects their desired academic institution and subject. Appropriate past exam questions are provided to the terminal from the server, and the user answers them. While answering, the terminal records the user's voice and facial expressions, and the user's emotional state is evaluated by analyzing this data with an emotion engine.

[0753] The server uses received answer data and sentiment data to identify the user's weak areas and generates similar problems using a generation AI. These similar problems can reflect the user's emotional state and have their difficulty and content adjusted to reduce stress or improve motivation. For example, if the user is showing anxiety, the generated problems will be adjusted to be more basic. In addition, feedback based on sentiment analysis is provided to the device, offering advice and useful content to help the user calm down.

[0754] This system allows test-takers to efficiently overcome their weak areas with appropriate support, even under high stress levels, and to engage in learning that leads to success in gaining admission to their desired academic institution.

[0755] The following describes the processing flow.

[0756] Step 1:

[0757] The user logs into their device and selects their desired academic institution and subject on the device. The selection is then sent from the device to the server.

[0758] Step 2:

[0759] Based on the information received by the server, past exam questions for the selected academic institution and subject are retrieved from the database. The retrieved questions are then sent to the terminal.

[0760] Step 3:

[0761] The terminal displays past exam questions received from the server to the user. The user answers the questions and enters their answers into the terminal.

[0762] Step 4:

[0763] While the user is answering, the device records the user's voice and facial expressions through sensors, and analyzes the user's real-time emotional data using an emotion engine.

[0764] Step 5:

[0765] Answer data and sentiment data are sent from the terminal to the server. The server analyzes the answer data to identify the user's areas of weakness.

[0766] Step 6:

[0767] Based on the server's identified weaknesses and real-time emotional data, a generative AI is used to create similar problems. These problems are optimized and adjusted to the user's emotional state.

[0768] Step 7:

[0769] Similar problems are generated and sent from the server to the terminal, which then presents them to the user. The user works on the similar problems and enters their answers.

[0770] Step 8:

[0771] The results of similar problems and user sentiment data are sent from the device to the server, where the server performs further analysis. Based on the analysis results, feedback and advice are generated, and the learning history is updated.

[0772] Step 9:

[0773] The server sends generated feedback and advice to the terminal, which then provides it to the user. The user reviews their learning progress and plans their next learning steps.

[0774] (Example 2)

[0775] Next, we will describe Example 2. In the following description, the data processing device 12 will be referred to as the "server" and the robot 414 as the "terminal".

[0776] Providing an optimized educational experience that fully considers each learner's emotional state and areas of difficulty during the learning process has been challenging. Traditional systems lacked feedback and problem-solving tailored to learners' emotions, making it difficult to maintain their motivation. Furthermore, there is a need for more effective and personalized learning support that utilizes not only answer data but also emotional data.

[0777] The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 2 is realized by the following means.

[0778] In this invention, the server includes means for analyzing the examinee's answer data and emotional data to identify the examinee's problem area, means for automatically generating similar problems corresponding to the examinee's emotional state using a generative AI model and prompt sentences, and means for analyzing the answer results and emotional data to provide emotion-based feedback. This makes it possible to adjust the difficulty level of the problems according to each examinee's emotional state and learning progress, thereby realizing appropriate and individualized learning support.

[0779] "Examinee" refers to an individual who studies in preparation for evaluation by an educational institution and takes a specific test.

[0780] "Past exam data from educational institutions" refers to a collection of information that digitally stores exam questions from past examinations conducted by educational institutions.

[0781] "Answer data" refers to the information that examinees have written down in response to the exam questions presented to them.

[0782] "Emotional data" refers to information that represents the emotional state of the test taker, analyzed based on their voice, facial expressions, and other factors.

[0783] A "problem area" refers to the area of ​​knowledge or skills in which the test taker shows particular weakness or deficiency during their studies.

[0784] A "generative AI model" refers to a program that uses artificial intelligence technology to automatically generate problems.

[0785] A "prompt" refers to a text-based instruction entered into a generative AI model to tell it to perform a specific action.

[0786] A "similar question" refers to a new question that is based on an existing exam question and has similar characteristics in terms of format and content.

[0787] "Feedback" refers to evaluations and advice provided based on the test taker's answers and emotional data.

[0788] This invention is an educational support system that enables examinees to effectively learn based on past exam data from educational institutions. The system consists of a server, terminals, and users, each playing a specific role.

[0789] About the server

[0790] The server is the core of the system, centrally managing past exam data. It receives answer data and sentiment data sent from the test-taker's terminal and analyzes this data to identify areas where the test-taker needs improvement in their learning. Furthermore, it uses a generative AI model to automatically generate similar questions based on the test-taker's emotional state. In this process, prompts are used to set specific conditions for the questions in the generative AI model. For example, instructions such as "If the user is showing anxiety, generate a basic-level question" can be given.

[0791] About the device

[0792] A terminal is a device used by the user, and includes smartphones and personal computers. The terminal presents problems provided by the server, accepts answers from the user, and acquires emotional data such as voice and facial expressions. The terminal is equipped with an emotion engine, which enables real-time analysis of the user's emotions.

[0793] About the user

[0794] The user is a test-taker who uses this system as a learner. The user accesses the system from a terminal and selects educational institutions and subjects of interest. Emotional data collected during the problem-solving process is used to create questions that reflect the user's emotional state, such as stress and anxiety.

[0795] As a concrete example, when a user works on past exam questions for a specific subject, the device monitors their voice and facial expressions after each problem solved to determine whether they are focused, anxious, or frustrated. This information is sent to a server, and the difficulty and content of the next questions presented are adjusted through a generative AI model. In this way, the user's learning experience becomes more individualized and optimized.

[0796] The flow of the specific processing in Example 2 will be explained using Figure 13.

[0797] Step 1:

[0798] The user accesses the educational support system by operating a terminal and selects their target educational institution and subjects. This selection information is then sent from the terminal to the server, conveying the user's intended learning content to the server. Specifically, user selection data entered on the terminal is sent to the server, which then searches for appropriate past exam questions based on this data.

[0799] Step 2:

[0800] The server searches past problem data based on the user's selection information and selects an appropriate set of problems. The server then sends the selected problems to the terminal in digital format. For data processing, relevant data is extracted from the problem database of the educational institution the user wishes to attend and converted into a format that can be presented to the user.

[0801] Step 3:

[0802] The terminal displays a set of questions sent from the server to the user. The user answers the presented questions, and the answer data is entered into the terminal. The entered answers are sent to the server in real time, and at the same time, emotion data is collected using voice input and facial recognition functions via the camera.

[0803] Step 4:

[0804] The device analyzes collected emotional data using its built-in emotion engine to evaluate the user's emotional state. The evaluation results are sent to the server and used to comprehensively understand the user's learning progress along with their answers. Specifically, emotional indicators such as stress and anxiety are calculated from voice and facial expression data and output as analysis data to the server.

[0805] Step 5:

[0806] The server combines answer data and sentiment data to identify the user's challenges and generates similar problems using a generative AI model. Detailed question conditions are set using prompts. As a data calculation, the AI ​​executes a problem generation algorithm tailored to the user's weaknesses and emotional state, outputting adjusted problems.

[0807] Step 6:

[0808] The server sends feedback based on the analysis, along with the generated similar problems, to the terminal. The terminal provides this information to the user to support the next learning step. Specifically, the feedback includes advice tailored to the test-taker's emotional state and suggestions to maintain motivation.

[0809] (Application Example 2)

[0810] Next, we will explain application example 2. In the following explanation, the data processing device 12 will be referred to as the "server" and the robot 414 as the "terminal".

[0811] Traditional educational support systems provide uniform learning content and feedback without considering the emotional state of test-takers, resulting in a standardized experience and making it difficult to provide detailed support tailored to the individual characteristics of each test-taker. Furthermore, there was a lack of means to effectively promote learning while reducing the emotional distress and stress experienced by users. This could potentially lead to decreased motivation and limitations in test-takers' performance.

[0812] The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means.

[0813] In this invention, the server includes means for presenting past academic institution questions based on the examinee's selection, means for receiving and analyzing the examinee's answer information to identify the examinee's weak areas, means for automatically generating similar questions corresponding to the weak areas, means for detecting the user's emotional state and making recommendations based on that emotional state in real time, and means for providing recommendation information to the user. This makes it possible to provide an optimal learning experience tailored to the individual emotional state of each examinee, enabling them to learn effectively while reducing stress.

[0814] An "examinee" is someone who is studying in order to take an examination at an academic institution.

[0815] "Academic institutions" refer to organizations and groups that conduct education and research, including universities and vocational schools.

[0816] "Past exam questions" refer to questions from exams previously administered by academic institutions.

[0817] "Answer information" refers to data on the answers that test-takers have submitted to past exam questions.

[0818] "Areas of weakness" refers to the areas or topics that a test-taker found particularly difficult to answer among the questions they answered.

[0819] "Similar problems" are related problems created to facilitate understanding for test-takers based on their identified areas of weakness.

[0820] "Emotional state" refers to the psychological state or emotions that a test-taker exhibits when working on the problems.

[0821] "Recommendation information" refers to information such as learning content and recommended products that are optimized based on the emotional state of the test taker.

[0822] The system implementing this invention is centered around a server, terminals, and users, and aims to highly personalize the learning experience of test takers. The server plays a central role in data processing, managing past exam questions from academic institutions and analyzing test takers' answer information and emotional states to generate feedback. Specifically, a data analysis system built in Python and generative AI technology (e.g., OpenAI GPT-3) are used to generate similar questions and provide recommendation information based on the test taker's weak areas and emotional state.

[0823] The device functions as a smartphone or personal computer, responsible for inputting test-takers' answer information and collecting voice and facial expression data. The collected data is analyzed by an emotion analysis engine (e.g., Affectiva SDK) within the device and transmitted to the server in real time.

[0824] Users, or test takers, use this system to work on past exam questions from academic institutions and input their answers. The server then analyzes the answers and provides personalized questions and feedback in a way that enhances the test taker's understanding. Furthermore, based on the test taker's emotional state, they can receive recommendations to maintain and improve their motivation.

[0825] For example, if a user is experiencing stress while working on a problem, the device's emotion analysis engine detects this state, and the server uses a generative AI model to provide the user with simple, basic problems designed to promote relaxation, as well as music recommendations to reduce stress. An example of a prompt to the generative AI model might be, "If a test-taker is showing signs of anxiety, what types of problems would help them calm down?" In this way, it is possible to provide detailed and personalized learning support.

[0826] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[0827] Step 1:

[0828] The user selects the academic institution and problem to study on their device. The user's selection data is used as input, and the selected problem information is sent to the server as output. The server then prepares a dataset of the corresponding past problems.

[0829] Step 2:

[0830] The device receives the user's response and inputs the voice and facial expression data into the emotion analysis engine. The input consists of the user's response data and real-time voice and facial expression data. The output is the analysis of this data, resulting in numerical information of the emotional state.

[0831] Step 3:

[0832] The server analyzes the received answer information and emotional state to identify areas of weakness. The input consists of the user's answer data and analyzed emotional information. The output generates evaluation data corresponding to the identified areas of weakness and the emotional state.

[0833] Step 4:

[0834] The server uses a generation AI model to automatically generate similar problems and determine the recommended difficulty level based on the user's emotional state. Input includes identified areas of difficulty and emotional data. The output is a personalized similar problem along with its explanation.

[0835] Step 5:

[0836] The server sends generated problems and recommendation feedback to the terminal. The input is the generated personalized problems and feedback data. The output is that actual learning is facilitated by providing the user with an optimized learning experience.

[0837] Step 6:

[0838] Users answer provided questions and receive feedback messages. The input consists of the user's answers and explanations. The output is personalized feedback that helps with future learning, thereby enhancing the learning experience.

[0839] Through these steps, the system provides flexible educational support tailored to the emotional state and learning progress of the test-taker.

[0840] The specific processing unit 290 transmits the result of the specific processing to the robot 414. In the robot 414, the control unit 46A causes the speaker 240 and the controlled object 443 to output the result of the specific processing. The microphone 238 acquires audio indicating user input for the result of the specific processing. The control unit 46A transmits the audio data indicating user input acquired by the microphone 238 to the data processing unit 12. In the data processing unit 12, the specific processing unit 290 acquires the audio data.

[0841] Data generation model 58 is a type of so-called generative AI (Artificial Intelligence). One example of data generation model 58 is ChatGPT (Internet search<URL: https: / / openai.com / blog / chatgpt> ), Gemini (Internet search) <url: https: gemini.google.com ?hl="ja">Examples of generative AI include the following. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 is input with prompts containing instructions, and with inference data such as audio data representing speech, text data representing text, and image data representing images. The data generation model 58 infers from the input inference data according to the instructions indicated by the prompts, and outputs the inference results in data formats such as audio data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[0842] In the above embodiment, an example was given in which the specific processing is performed by the data processing device 12, but the technology of this disclosure is not limited thereto, and the specific processing may also be performed by the robot 414.

[0843] Furthermore, the emotion identification model 59, acting as an emotion engine, may determine the user's emotion according to a specific mapping. Specifically, the emotion identification model 59 may determine the user's emotion according to a specific mapping, which is an emotion map (see Figure 9). Similarly, the emotion identification model 59 may also determine the robot's emotion, and the identification processing unit 290 may perform identification processing using the robot's emotion.

[0844] Figure 9 shows an emotion map 400 in which multiple emotions are mapped. In the emotion map 400, emotions are arranged in concentric circles radiating from the center. The closer to the center of the concentric circles, the more primitive the emotions are located. Further out of the concentric circles, emotions representing states and actions arising from mental states are located. Emotion is a concept that includes feelings and mental states. On the left side of the concentric circles, emotions that are generally generated from reactions occurring in the brain are located. On the right side of the concentric circles, emotions that are generally induced by situational judgment are located. Above and below the concentric circles, emotions that are generally generated from reactions occurring in the brain and induced by situational judgment are located. In addition, the emotion of "pleasure" is located on the upper side of the concentric circles, and the emotion of "displeasure" is located on the lower side. Thus, in the emotion map 400, multiple emotions are mapped based on the structure in which emotions arise, and emotions that are likely to occur simultaneously are mapped close together.

[0845] These emotions are distributed at the 3 o'clock position on the Emotion Map 400, and usually fluctuate between feelings of security and anxiety. In the right half of the Emotion Map 400, situational awareness takes precedence over internal feelings, resulting in a calm impression.

[0846] The inside of the Emotion Map 400 represents inner thoughts, while the outside represents actions. Therefore, the further you go from the outside of the Emotion Map 400, the more visible (expressed in actions) your emotions become.

[0847] Here, human emotions are based on various balances, such as posture and blood sugar levels. When these balances deviate from the ideal, it results in discomfort, and when they approach the ideal, it results in pleasure. Similarly, in robots, cars, motorcycles, etc., emotions can be created based on various balances, such as posture and battery level. When these balances deviate from the ideal, it results in discomfort, and when they approach the ideal, it results in pleasure. The emotion map can be generated, for example, based on Dr. Mitsuyoshi's emotion map (Research on a system for analyzing brain physiological signals of speech emotion recognition and emotion, Tokushima University, doctoral dissertation: https: / / ci.nii.ac.jp / naid / 500000375379). The left half of the emotion map contains emotions belonging to a region called "response," where sensation is dominant. The right half of the emotion map contains emotions belonging to a region called "situation," where situational awareness is dominant.

[0848] The emotion map defines two emotions that promote learning. One is the emotion around the middle of the negative "repentance" and "reflection" on the situation side. In other words, it is when the robot experiences negative emotions such as "I never want to feel this way again" or "I don't want to be scolded again." The other is the emotion around the positive "desire" on the reaction side. In other words, it is when the robot has positive feelings such as "I want more" or "I want to know more."

[0849] The emotion identification model 59 inputs user input into a pre-trained neural network, obtains emotion values ​​representing each emotion shown in the emotion map 400, and determines the user's emotion. This neural network is pre-trained based on multiple training data sets, which are combinations of user input and emotion values ​​representing each emotion shown in the emotion map 400. Furthermore, this neural network is trained so that emotions located close together have similar values, as shown in the emotion map 900 in Figure 10. Figure 10 shows an example where multiple emotions such as "reassured," "calm," and "confident" have similar emotion values.

[0850] The above description primarily focuses on the functions of the data processing device 12 in relation to this disclosure. However, the system related to this disclosure is not necessarily implemented on a server. The system related to this disclosure may be implemented as a general information processing system. This disclosure may be implemented, for example, as a software program that runs on a personal computer or as an application that runs on a smartphone. The method related to this disclosure may be provided to users in SaaS (Software as a Service) format.

[0851] In the above embodiment, an example was given in which a specific process is performed by a single computer 22. However, the technology of this disclosure is not limited thereto, and a distributed processing of the specific process may be performed by multiple computers, including computer 22. For example, a data generation model 58 may be provided in an external device of the data processing device 12, and the external device may generate data according to the input data.

[0852] In the above embodiment, an example was given in which the specific processing program 56 is stored in the storage 32, but the technology of this disclosure is not limited thereto. For example, the specific processing program 56 may be stored in a portable, computer-readable, non-temporary storage medium such as a USB (Universal Serial Bus) memory. The specific processing program 56 stored in the non-temporary storage medium is installed in the computer 22 of the data processing device 12. The processor 28 executes specific processing according to the specific processing program 56.

[0853] 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.

[0854] Furthermore, it is not necessary to store the entirety of the specific processing program 56 in a storage device such as a server connected to the data processing device 12 via the network 54, or to store the entirety of the specific processing program 56 in the storage 32; it is acceptable to store only a portion of the specific processing program 56.

[0855] The following types of processors can be used as hardware resources to perform specific processing. Examples of processors include a CPU, a general-purpose processor that functions as a hardware resource to perform specific processing by executing software, i.e., a program. Other examples of processors include dedicated electrical circuits, such as FPGAs (Field-Programmable Gate Arrays), PLDs (Programmable Logic Devices), or ASICs (Application Specific Integrated Circuits), which have circuit configurations specifically designed to perform specific processing. All of these processors have built-in or connected memory, and all of them perform specific processing by using memory.

[0856] The hardware resource that performs a specific process may consist of one of these various processors, or it may consist of a combination of two or more processors of the same or different types (for example, a combination of multiple FPGAs, or a combination of a CPU and an FPGA). Alternatively, the hardware resource that performs a specific process may consist of a single processor.

[0857] Examples of configurations using a single processor include, firstly, a configuration in which one or more CPUs and software are combined to form a single processor, and this processor functions as a hardware resource that performs a specific process. Secondly, there is a configuration using a processor that realizes the functions of the entire system, including multiple hardware resources that perform a specific process, on a single IC chip, as exemplified by SoCs (System-on-a-chip). In this way, a specific process is realized using one or more of the above types of processors as hardware resources.

[0858] Furthermore, the hardware structure of these various processors can more specifically utilize electrical circuits that combine circuit elements such as semiconductor devices. Also, the specific processing described above is merely an example. Therefore, it goes without saying that unnecessary steps can be deleted, new steps added, or the processing order rearranged, as long as it does not deviate from the main purpose.

[0859] The descriptions and illustrations presented above are detailed explanations of the technical aspects of this disclosure and are merely examples of the technical aspects. For example, the above descriptions of the structure, function, operation, and effect are examples of the structure, function, operation, and effect of the technical aspects of this disclosure. Therefore, it goes without saying that you may delete unnecessary parts, add new elements, or replace elements in the descriptions and illustrations presented above, as long as you do not deviate from the essence of the technical aspects of this disclosure. Furthermore, in order to avoid confusion and facilitate understanding of the technical aspects of this disclosure, explanations of common technical knowledge and the like that do not require special explanation to enable the implementation of the technical aspects of this disclosure have been omitted from the descriptions and illustrations presented above.

[0860] All documents, patent applications, and technical standards described herein are incorporated by reference to the same extent as if each individual document, patent application, and technical standard were specifically and individually noted to be incorporated by reference.

[0861] The following is further disclosed regarding the embodiments described above.

[0862] (Claim 1)

[0863] A means of presenting past examination questions from academic institutions based on the applicant's selection,

[0864] A means of receiving test-takers' answer data, analyzing it, and identifying the test-takers' weak areas,

[0865] A means to automatically generate similar problems that address areas of weakness,

[0866] A means of presenting similar problems to test takers and accepting their answers,

[0867] An educational support system that includes a feedback mechanism that analyzes answer results and provides detailed explanations.

[0868] (Claim 2)

[0869] The educational support system according to claim 1, which updates individual learning histories based on examinee answer data and progress, and optimizes the questions presented next time based on that.

[0870] (Claim 3)

[0871] The educational support system according to claim 1, further comprising means for recognizing the difficulty level of automatically generated similar problems and presenting them in stages according to the examinee's level of understanding.

[0872] "Example 1"

[0873] (Claim 1)

[0874] A means of obtaining past exam questions from educational institutions based on the applicant's choice,

[0875] A means of analyzing test-takers' answer information to identify areas where test-takers are weak,

[0876] A means for generating problems related to areas of weakness identified using a generative AI model,

[0877] A means of providing the generated questions to test takers and receiving their answers,

[0878] A feedback mechanism that analyzes answer information and provides detailed explanations,

[0879] A method to optimize the next set of questions based on individual answer history,

[0880] A system that recognizes the difficulty level of generated questions and includes means for presenting them in stages according to the test-taker's level of understanding.

[0881] (Claim 2)

[0882] The system according to claim 1, which updates the learning history based on the progress of the test taker and adjusts the presentation of questions accordingly.

[0883] (Claim 3)

[0884] The system according to claim 1, which dynamically adjusts the difficulty level of the generated problems and provides an individually adapted learning experience.

[0885] "Application Example 1"

[0886] (Claim 1)

[0887] A means of presenting past exam questions from educational institutions based on the applicant's selection,

[0888] A means of receiving the examinee's answer information, analyzing it, and identifying the examinee's weak areas,

[0889] A means for automatically generating similar problems corresponding to areas of weakness,

[0890] A means of presenting similar problems to test takers and accepting their answers,

[0891] A means of analyzing answer results to optimize learning methods and formulate individual learning plans,

[0892] An application method that presents problems step by step based on the analysis of the answers,

[0893] A system that includes this.

[0894] (Claim 2)

[0895] The system according to claim 1, which updates individual history based on the examinee's answer information and progress, and optimizes the questions presented next time based on that.

[0896] (Claim 3)

[0897] The system according to claim 1, further comprising means for recognizing the complexity of automatically generated similar problems and presenting them in stages according to the examinee's level of understanding.

[0898] "Example 2 of combining an emotion engine"

[0899] (Claim 1)

[0900] A means of presenting past exam data from educational institutions based on the applicant's selection,

[0901] A means of analyzing examinee answer data and emotional data to identify the examinee's areas of difficulty,

[0902] A means for automatically generating similar questions corresponding to the emotional state of test takers using a generative AI model and prompt sentences,

[0903] A means of providing similar problems to test takers and recording their answers,

[0904] A system including means for analyzing answer results and emotional data to provide emotion-based feedback.

[0905] (Claim 2)

[0906] The system according to claim 1, which updates individual learning histories based on examinee answer data and sentiment data, and uses that information to appropriately adjust the questions presented next time.

[0907] (Claim 3)

[0908] The system according to claim 1, further comprising means for analyzing the difficulty level of automatically generated similar problems and presenting them in stages according to the examinee's emotions and level of understanding.

[0909] "Application example 2 when combining with an emotional engine"

[0910] (Claim 1)

[0911] A means of presenting past exam questions from academic institutions based on the applicant's selection,

[0912] A means of receiving test-takers' answer information, analyzing it, and identifying the test-takers' weak areas,

[0913] A means to automatically generate similar problems that address areas of weakness,

[0914] A means of presenting similar problems to test takers and accepting their answers,

[0915] A feedback mechanism that analyzes the answer results and provides a detailed explanation,

[0916] A means to detect the emotional state of users and provide recommendations based on that emotional state in real time,

[0917] Means of providing recommendation information to users,

[0918] A system that includes this.

[0919] (Claim 2)

[0920] The system according to claim 1, which updates individual learning histories based on the examinee's answer information and progress, optimizes the questions presented next time based on that, and optimizes learning according to the examinee's emotional state.

[0921] (Claim 3)

[0922] The system according to claim 1, further comprising means for recognizing the difficulty level of automatically generated similar problems, presenting them in stages according to the test-taker's level of understanding, and adjusting the difficulty level based on the test-taker's emotional state. [Explanation of symbols]

[0923] 10, 210, 310, 410 Data Processing Systems 12 Data Processing Devices 14 Smart Devices 214 Smart Glasses 314 Headset-type terminal 414 Robots< / url:> < / url:> < / url:> < / url:>

Claims

1. A means of presenting past examination questions from academic institutions based on the applicant's selection, A means of receiving test-takers' answer data, analyzing it, and identifying the test-takers' weak areas, A means to automatically generate similar problems that address areas of weakness, A means of presenting similar problems to test takers and accepting their answers, An educational support system that includes a feedback mechanism that analyzes answer results and provides detailed explanations.

2. The educational support system according to claim 1, which updates individual learning histories based on examinee answer data and progress, and optimizes the questions presented next time based on that.

3. The educational support system according to claim 1, further comprising means for recognizing the difficulty level of automatically generated similar problems and presenting them in stages according to the examinee's level of understanding.

Images