System

Abstract

To provide a system for supporting an examinee to study an examination by using generative artificial intelligence.SOLUTION: The system includes a user interface means for inputting a school of choice and basic information of an examinee, an examination question generation means for automatically generating examination questions based on the school of choice information of the examinee, an analysis means for analyzing a trial result answered by the examinee and visualizing an unskillful field and a weak point, an answer explanation means for generating and displaying an explanation based on an analysis result, a teaching material recommendation means for recommending an online teaching material suitable for a learning situation of the examinee, and a similar question generation means for automatically generating similar questions based on the unskillful field of the examinee.SELECTED DRAWING: Figure 1

Description

[Technical Field]

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

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

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

[0004] Students spend a lot of time and effort trying to get into their desired school, but conventional learning methods are inefficient and difficult to address individual weaknesses. Furthermore, there is a lack of tools to accurately understand students' learning progress and areas of weakness, and to implement specific measures based on that information. It is also difficult for educational institutions and companies to effectively utilize student data. To solve these issues, a new system is needed. [Means for solving the problem]

[0005] In order to solve this problem, the present invention provides a system for supporting test takers' exam preparation using generative artificial intelligence, which includes the following means:

[0006] 1. A user interface means for entering the applicant's desired school and basic information.

[0007] 2. A test question generation means that automatically generates test questions based on the examinee's desired school information.

[0008] 3. An analytical method that analyzes mock test results given by test takers and visualizes their weak areas and weaknesses.

[0009] 4. An answer explanation means that generates and displays explanations based on the analysis results.

[0010] 5. A teaching material recommendation tool that recommends online teaching materials suitable for the student's learning situation.

[0011] 6. A method for generating similar questions that automatically generates similar questions based on the weak areas of test takers.

[0012] Furthermore, the present invention includes a statistical analysis means for statistically analyzing test-taker data and providing reports to educational institutions or companies, and a comparison means for comparing test-taker data with past test-taker data based on the test-taker's mock test results, allowing educators to effectively utilize test-taker data. This allows for learning support optimized for each test-taker, resulting in efficient test-study.

[0013] "Generative AI" is a technology that automatically generates information, answers, questions, etc. based on input data.

[0014] "Exam taker" refers to a person who engages in learning activities with the aim of passing a specific exam.

[0015] "Exam preparation" refers to a series of learning activities that students undertake in order to pass an exam.

[0016] A "system" refers to an integrated mechanism in which multiple components work together to achieve a specific function or purpose.

[0017] "User interface means" refers to an interface through which a user inputs information into a system and receives output from the system.

[0018] "Test question generation means" refers to a device or process that has the function of automatically generating specific test questions based on various data such as the school of choice.

[0019] "Analysis means" refers to a device or process that has the function of analyzing input data or answers and deriving a specific conclusion or result.

[0020] "Answer explanation means" refers to a device or process that has the function of generating and displaying detailed explanations and guidance for the answers based on the analysis results.

[0021] "Materials recommendation means" refers to a device or process that has the function of recommending the most suitable online materials or resources based on the candidate's learning situation and progress.

[0022] "Similar question generation means" refers to a device or process that has the function of automatically generating similar practice questions based on the weak areas of the test-taker.

[0023] "Statistical analysis means" refers to a device or process that has the function of aggregating and analyzing a large amount of data and expressing the results statistically.

[0024] "Comparison means" refers to a device or process that has the function of comparing a test taker's data with similar data from the past and finding differences and similarities.

[0025] "Educational institutions" refer to organizations that carry out educational activities, such as schools and cram schools.

[0026] "Enterprise" refers to a corporation or sole proprietorship that conducts business activities for profit. [Brief explanation of the drawings]

[0027] [Figure 1]1 is a conceptual diagram showing an example of the configuration of a data processing system according to a first embodiment. [Figure 2] 1 is a conceptual diagram showing an example of main functions of a data processing device and a smart device according to a first embodiment. [Figure 3] FIG. 10 is a conceptual diagram showing an example of the configuration of a data processing system according to a second embodiment. [Figure 4] FIG. 10 is a conceptual diagram showing an example of main functions of a data processing device and smart glasses according to a second embodiment. [Figure 5] FIG. 10 is a conceptual diagram showing an example of the configuration of a data processing system according to a third embodiment. [Figure 6] FIG. 11 is a conceptual diagram showing an example of main functions of a data processing device and a headset-type terminal according to a third embodiment. [Figure 7] FIG. 10 is a conceptual diagram showing an example of the configuration of a data processing system according to a fourth embodiment. [Figure 8] FIG. 10 is a conceptual diagram showing an example of main functions of a data processing device and a robot according to a fourth embodiment. [Figure 9] 1 shows an emotion map onto which multiple emotions are mapped. [Figure 10] 1 shows an emotion map onto which multiple emotions are mapped. [Figure 11] FIG. 3 is a sequence diagram showing a processing flow of the data processing system according to the first embodiment. [Figure 12] FIG. 10 is a sequence diagram showing the flow of processing in the data processing system in Application Example 1. [Figure 13] FIG. 10 is a sequence diagram showing the flow of processing in the data processing system according to the second embodiment when an emotion engine is combined. [Figure 14] FIG. 10 is a sequence diagram showing the flow of processing in the data processing system in Application Example 2 when an emotion engine is combined. DETAILED DESCRIPTION OF THE INVENTION

[0028] An example of an embodiment of a system according to the technology of the present disclosure will be described below with reference to the accompanying drawings.

[0029] First, the terms used in the following description will be explained.

[0030] In the following embodiments, a coded processor (hereinafter simply referred to as a "processor") may be a single arithmetic device or a combination of multiple arithmetic devices. Furthermore, a processor may be a single type of arithmetic device or a combination of multiple types of arithmetic devices. Examples of arithmetic devices include a CPU (Central Processing Unit), a GPU (Graphics Processing Unit), a GPGPU (General-Purpose computing on Graphics Processing Units), and an APU (Accelerated Processing Unit).

[0031] In the following embodiments, a coded RAM (Random Access Memory) is a memory in which information is temporarily stored and is used as a working memory by a processor.

[0032] In the following embodiments, the coded storage is one or more non-volatile storage devices that store various programs, various parameters, etc. Examples of non-volatile storage devices include flash memory (SSD (Solid State Drive)), magnetic disks (e.g., hard disks), and magnetic tapes.

[0033] In the following embodiments, a communication I / F (Interface) with a symbol is an interface including a communication processor, an antenna, etc. The communication I / F controls communication between multiple computers. Examples of communication standards applied to the communication I / F include wireless communication standards including 5G (5th Generation Mobile Communication System), Wi-Fi (registered trademark), Bluetooth (registered trademark), etc.

[0034] In the following embodiments, "A and / or B" is synonymous with "at least one of A and B." In other words, "A and / or B" means that it may be only A, only B, or a combination of A and B. Furthermore, in this specification, the same concept as "A and / or B" is also applied when three or more things are expressed connected by "and / or."

[0035] [First embodiment]

[0036] FIG. 1 shows an example of the configuration of a data processing system 10 according to the first embodiment.

[0037] 1, a data processing system 10 includes a data processing device 12 and a smart device 14. An example of the data processing device 12 is a server.

[0038] The data processing device 12 includes a computer 22, a database 24, and a communication I / F 26. The computer 22 is an example of a "computer" according to the technology of the present disclosure. The computer 22 includes a processor 28, a RAM 30, and a storage 32. The processor 28, the RAM 30, and the storage 32 are connected to a bus 34. The database 24 and the communication I / F 26 are also connected to the bus 34. The communication I / F 26 is connected to a network 54. Examples of the network 54 include a WAN (Wide Area Network) and / or a LAN (Local Area Network).

[0039] The smart device 14 includes a computer 36, a reception device 38, an output device 40, a camera 42, and a communication I / F 44. The computer 36 includes a processor 46, a RAM 48, and a storage 50. The processor 46, the RAM 48, and the storage 50 are connected to a bus 52. The reception device 38, the output device 40, and the camera 42 are also connected to the bus 52.

[0040] The reception device 38 includes a touch panel 38A, a microphone 38B, and the like, and receives user input. The touch panel 38A detects contact with an indicator (for example, a pen or a finger) to receive user input by the touch of the indicator. The microphone 38B detects the user's voice to receive user input by voice. The control unit 46A transmits data indicating the user input received by the touch panel 38A and the microphone 38B to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the data indicating the user input.

[0041] The output device 40 includes a display 40A and a speaker 40B, and presents data to the user 20 by outputting the data in a form of expression that the user 20 can perceive (for example, audio and / or text). The display 40A displays visible information such as text and images in accordance with instructions from the processor 46. The speaker 40B outputs audio in accordance with instructions from the processor 46. The camera 42 is a compact digital camera equipped with an optical system including a lens, aperture, and shutter, and an imaging element such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor.

[0042] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 control the exchange of various information between the processor 46 and the processor 28 via the network 54.

[0043] FIG. 2 shows an example of the main functions of the data processing device 12 and the smart device 14.

[0044] 2, in the data processing device 12, a specific process is performed by the processor 28. A specific processing program 56 is stored in the storage 32. The specific processing program 56 is an example of a "program" according to the technology of the present disclosure. The processor 28 reads the specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific process is realized by the processor 28 operating as a specific processing unit 290 in accordance with the specific processing program 56 executed on the RAM 30.

[0045] The storage 32 stores a data generation model 58 and an emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290.

[0046] In the smart device 14, the processor 46 performs the reception output process. The storage 50 stores a reception output program 60. The reception output program 60 is used in conjunction with the specific processing program 56 by the data processing system 10. The processor 46 reads the reception output program 60 from the storage 50 and executes the read reception output program 60 on the RAM 48. The reception output process is realized by the processor 46 operating as the control unit 46A in accordance with the reception output program 60 executed on the RAM 48.

[0047] Next, a description will be given of the specific processing performed by the specific processing unit 290 of the data processing device 12. In the following description, the data processing device 12 will be referred to as a "server" and the smart device 14 will be referred to as a "terminal."

[0048] The present invention is a system that efficiently supports test takers in studying for exams using generative artificial intelligence. This system includes a user interface means for inputting the user's desired school information and basic information, a test question generation means for automatically generating test questions, an analysis means for analyzing mock test results, an answer explanation means for providing explanations based on the analysis results, a learning material recommendation means for recommending appropriate learning materials, and a similar question generation means for generating similar questions based on weak areas.

[0049] User Interface Means

[0050] Users access this system and enter their desired school, exam subjects, and basic information (name, email address, etc.), which completes the initial registration.

[0051] Test question generation means

[0052] The server uses AI to automatically generate appropriate exam questions based on the user's desired school information and exam subjects. The generated questions are sent to the user's device, where they can be viewed and answered.

[0053] Analysis means

[0054] When a user completes a mock test and submits their answers, the server receives the answer data and automatically scores and analyzes it using generative AI, which clarifies the score for each subject, the percentage of correct answers, and weak areas and weaknesses.

[0055] Answer explanation method

[0056] Based on the analysis results, the server generates detailed explanations for the questions that the user got wrong, providing step-by-step instructions on how to solve the problem. This explanation data is then sent to the user's device for viewing.

[0057] Teaching material recommendation method

[0058] The server recommends optimal online learning materials and resources based on the analysis results and the user's learning progress, allowing the user to study efficiently.

[0059] Similar problem generation means

[0060] If a user has difficulty with a particular problem, the server automatically generates similar problems related to that problem using a generation AI. These similar problems are sent to the device, and the user can answer them as training.

[0061] Statistical analysis and comparison tools

[0062] This system has the ability to statistically analyze accumulated test-taker data. This data is provided to educational institutions and companies, supporting strategic data utilization in the field of education. Furthermore, by performing comparative analysis with past test-taker data, it is possible to provide more specific feedback to users.

[0063] Specific examples

[0064] A user logs into the system and enters "XYZ University" as their preferred school and "Mathematics, English, and Physics" as their exam subjects. The server then uses generative AI to automatically generate mock exams for mathematics, English, and physics based on past exam information and data on successful candidates, and sends them to the device. When the user completes the mock exam and submits their answers, the server immediately analyzes the answers and provides detailed feedback and explanations. Based on the analysis results, the server determines that the user has particular weaknesses in English grammar and recommends specialized grammar questions and explanatory videos. Furthermore, the server generates similar questions related to English grammar that the user can use for review.

[0065] In this way, the system efficiently provides learning support that is optimized for each examinee's individual situation.

[0066] The processing flow will be explained below.

[0067] User Registration Process

[0068] Step 1:

[0069] A user accesses the system and opens a login or registration form.

[0070] Step 2:

[0071] The user enters basic information such as the school of choice, exam subjects, name, and email address.

[0072] Step 3:

[0073] The terminal transmits the input information to the server.

[0074] Step 4:

[0075] The server stores the received information in a database.

[0076] Step 5:

[0077] The server generates a registration success message and sends it to the terminal.

[0078] Step 6:

[0079] The terminal displays a registration success message to the user.

[0080] Automatic generation process for mock exams

[0081] Step 1:

[0082] The user selects "Take a Practice Exam" from the dashboard.

[0083] Step 2:

[0084] The terminal sends a request to generate a mock test to the server.

[0085] Step 3:

[0086] The server references data based on the user's desired school and exam subjects, and uses a generation AI to generate mock exam questions.

[0087] Step 4:

[0088] The server stores the generated mock test questions in a database and sends them to the terminal.

[0089] Step 5:

[0090] The terminal displays the practice questions to the user and provides an answer input form.

[0091] Test result analysis process

[0092] Step 1:

[0093] The user completes the practice test and clicks the "Submit" button.

[0094] Step 2:

[0095] The terminal sends the answer data to the server.

[0096] Step 3:

[0097] The server receives the answer data and automatically scores and analyzes it using the generating AI.

[0098] Step 4:

[0099] The server calculates the score, accuracy rate, and weak areas for each subject and generates detailed feedback.

[0100] Step 5:

[0101] The server sends the analysis results and feedback to the device.

[0102] Step 6:

[0103] The device displays the feedback to the user.

[0104] Answer explanation process

[0105] Step 1:

[0106] If the user reviews the feedback and needs a detailed explanation of the incorrect question, they can click the "Show Explanation" button.

[0107] Step 2:

[0108] The device sends a description request to the server.

[0109] Step 3:

[0110] The server uses a generative AI to generate the answer process for the incorrect question and creates an explanatory text.

[0111] Step 4:

[0112] The server transmits the generated commentary data to the terminal.

[0113] Step 5:

[0114] The terminal displays the explanation to the user.

[0115] Online Material Recommendation Process

[0116] Step 1:

[0117] After the user checks the feedback, they select "View online learning materials."

[0118] Step 2:

[0119] The terminal sends a learning material request to the server.

[0120] Step 3:

[0121] The server uses AI to recommend optimal learning materials based on the user's learning progress data.

[0122] Step 4:

[0123] The server transmits the recommended teaching material information to the terminal.

[0124] Step 5:

[0125] The device displays the recommended learning materials to the user.

[0126] Similar problem generation process

[0127] Step 1:

[0128] The user selects "Generate similar questions."

[0129] Step 2:

[0130] The device sends a request to the server.

[0131] Step 3:

[0132] The server automatically generates similar questions using AI based on the user's weak areas.

[0133] Step 4:

[0134] The server sends the generated similar questions to the terminal.

[0135] Step 5:

[0136] The terminal displays similar questions to the user and provides an answer form.

[0137] Statistical Information Provision Process

[0138] Step 1:

[0139] The server periodically collects data on all test takers and performs statistical analysis.

[0140] Step 2:

[0141] The server generates statistical reports and publishes them to educational institutions and businesses.

[0142] Step 3:

[0143] Educational institutions or companies can access statistical reports on their devices to help improve and strategize their teaching.

[0144] Example 1

[0145] Next, a description will be given of Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the smart device 14 will be referred to as a "terminal."

[0146] Today's test-takers need to access a wealth of information and learning resources, making it difficult to determine which resources are most appropriate. It is also difficult to objectively analyze their own academic abilities and weaknesses and create a study plan based on that. Furthermore, they need to find the questions and study materials that are best suited to them and study efficiently.

[0147] The specific processing by the specific processing unit 290 of the data processing device 12 in the first embodiment is realized by the following means.

[0148] In this invention, the server includes a user interface means for inputting the examinee's desired school and basic information, a test question generation means for automatically generating test questions based on the examinee's desired school information and exam subjects, an analysis means for receiving the mock test results answered by the examinee and automatically scoring and analyzing them to clarify the score and correct answer rate, an answer explanation means for generating and displaying detailed explanations for questions answered incorrectly based on the analysis results, a learning material recommendation means for recommending online learning materials and resources suitable for the examinee's learning progress, and a similar question generation means for automatically generating similar questions based on the examinee's awareness of difficulty with specific questions. This allows the examinee to accurately grasp their own academic ability and efficiently progress in their studies.

[0149] "Generative AI" is an AI technology that uses natural language processing and machine learning techniques to automatically generate text and data.

[0150] A "candidate" is an individual who is taking a particular examination or entrance exam.

[0151] "User interface means" refers to input and output devices and software that allow a user to interact with the system.

[0152] "Test question generation means" refers to a function or device that automatically generates test questions based on input information.

[0153] A "generative AI model" is a mathematical model that uses machine learning algorithms to generate text and data.

[0154] "Analysis means" refers to a function or device that analyzes the test taker's answer data and identifies the test taker's score, correct answer rate, and weak points.

[0155] The "answer explanation means" is a function or device that generates detailed explanations based on the analysis results and provides them to the user.

[0156] The "teaching material recommendation means" is a function or device that recommends optimal teaching materials and resources based on the test-taker's learning progress and analysis results.

[0157] The "similar question generating means" is a function or device that automatically generates similar questions related to the subject area in which the examinee is weak.

[0158] "Statistical analysis means" refers to a function or device that statistically analyzes accumulated data and extracts specific patterns or trends.

[0159] A "comparison tool" is a function or device that compares past data with current data and analyzes specific patterns or differences.

[0160] The present invention provides a system for efficiently supporting test takers in their exam preparation using generative artificial intelligence, which includes a user interface, test question generation, analysis, answer explanation, teaching material recommendation, similar question generation, statistical analysis, and comparison.

[0161] First, a user accesses the system and uses an interface to input their desired school, exam subjects, and basic information (such as name and email address). This information is stored in a database by the server. For example, a user inputs "ABC University as their desired school" and "Mathematics, English, and Physics as their exam subjects."

[0162] Next, the server automatically generates appropriate exam questions using a generative AI model (e.g., GPT-4) based on the user's desired school information and exam subjects. The generated exam questions are sent to the user's device, where they can be viewed and answered. For example, it generates "mathematics mock exam questions based on past questions from ABC University."

[0163] When a user enters answers to practice test questions and sends them to a server, the server receives the data and automatically scores and analyzes it using a generative AI model (e.g., BERT). This analysis clarifies the score and correct answer rate for each subject, as well as weak areas and areas of weakness. For example, the result may be, "Mathematics score: 80 points, English correct answer rate: 70%."

[0164] Based on the analysis results, the server generates detailed explanations for the incorrect questions, providing step-by-step instructions on the solution process. This explanation data is sent to the user's device and can be viewed by the user. For example, it provides a "detailed explanation for English grammar questions."

[0165] Furthermore, the server recommends the most suitable online learning materials and resources based on the analysis results and the user's learning progress, allowing the user to study efficiently. For example, it might recommend an online video course specializing in English grammar.

[0166] If a user has difficulty with a particular problem, the server uses a generative AI model to automatically generate similar problems related to that problem. These similar problems are sent to the user's device, and the user can answer them as training. For example, it generates "similar practice problems related to English grammar questions."

[0167] Furthermore, the server uses statistical analysis tools to statistically analyze the accumulated data on test takers and provide reports to educational institutions and companies, enabling strategic use of data in educational settings.

[0168] Finally, through a comparison means, the server compares the past test-taker data with the current test-taker data and provides specific feedback, such as "Your English grades are in the top 20% compared to other test-takers."

[0169] Prompt Sentence Examples

[0170] "Enter ABC University as your preferred school and select Mathematics, English, and Physics as your exam subjects."

[0171] This allows test takers to accurately understand their own academic ability and study efficiently.The system utilizes generative AI models to provide optimal learning support tailored to the diverse needs of test takers.

[0172] The flow of the identification process in the first embodiment will be described with reference to FIG.

[0173] Step 1:

[0174] Users access this system and use the interface to create an account. Specifically, they enter basic information such as their name, email address, and password. The entered data is sent to the server and stored in a database. The entered basic information is used for future individual learning support.

[0175] Step 2:

[0176] Users log in with their account and enter detailed information such as their preferred school and exam subjects. This information includes, for example, "ABC University as the preferred school" and "Mathematics, English, and Physics as the exam subjects." This information is sent to the server and stored in a database. The entered details are used to automatically generate exam questions.

[0177] Step 3:

[0178] The server automatically generates appropriate test questions using a generative AI model (e.g., GPT-4) based on the desired school information and exam subjects. The server references past test data and a question database based on the information entered by the user, and generates an optimal combination of question sets. The generated test questions are then sent to the user's device.

[0179] Step 4:

[0180] The user inputs answers to the test questions received on the device. Once the answer is complete, the device sends the answer data to the server. The sent data includes the user's answer and related metadata (such as the time it took to answer).

[0181] Step 5:

[0182] The server automatically scores and analyzes the received answer data using a generative AI model (e.g., BERT). This analysis clarifies the score and correct answer rate for each subject, as well as weak areas and areas of weakness. For example, the result may be "Mathematics score: 80 points, English correct answer rate: 70%." The analysis results are stored in a database.

[0183] Step 6:

[0184] Based on the analysis results, the server generates detailed explanations for the questions where the user got the answer wrong. The generated explanation data is sent to the user's device and can be viewed by the user. For example, it can provide a "detailed explanation for an English grammar question." The explanation data is important information for the user to restudy.

[0185] Step 7:

[0186] The server recommends optimal online learning materials and resources based on the analysis results and the user's learning progress, allowing the user to study efficiently. For example, it might recommend an "online video course specializing in English grammar." The recommended learning material information is sent to the user's device.

[0187] Step 8:

[0188] If a user has difficulty with a particular problem, the server uses a generative AI model to automatically generate similar problems related to that problem. These similar problems are sent to the user's device, and the user can answer them as training. For example, it generates "similar practice problems related to English grammar questions." The server also references the user's past answer data when generating similar problems.

[0189] Step 9:

[0190] The server statistically analyzes the accumulated test-taker data and provides reports to educational institutions and companies. For example, it provides educational institutions with "statistical data on test-taker weaknesses." The server also compares past test-taker data with current test-taker data and provides specific feedback. For example, it may provide feedback such as, "Your English performance is in the top 20% compared to other test-takers."

[0191] Through these steps, this system provides multifaceted support for test takers' learning, enabling them to study efficiently.

[0192] (Application example 1)

[0193] Next, a description will be given of Application Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the smart device 14 will be referred to as a "terminal."

[0194] Conventional exam study support systems have had issues with providing optimal study plans tailored to each student's learning situation and areas of weakness, and with variations in the quality of automatically generated exam questions and answer explanations. It is also difficult to recommend optimal online learning materials based on students' learning progress, and there was a need for a system that could quickly score and analyze students' mock exam results and provide appropriate feedback based on that.

[0195] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 1 is realized by the following means.

[0196] In this invention, the server includes a user interface means for inputting the examinee's desired school and basic information, a test question generation means for automatically generating test questions based on the examinee's desired school information, an analysis means for analyzing the mock test results answered by the examinee and visualizing weak areas and areas of weakness, an answer explanation means for generating and displaying explanations based on the analysis results, a learning material recommendation means for recommending online learning materials suitable for the examinee's learning situation, a similar question generation means for automatically generating similar questions based on the examinee's weak areas, a scoring analysis means for using a generative AI model to score and analyze the examinee's answers, and a recommendation means for recommending optimal online learning materials based on the examinee's learning progress. This enables efficient learning support tailored to the learning progress of each examinee, as well as rapid feedback and improvement.

[0197] "User interface means" refers to a device, software, or a combination thereof that allows examinees to input their preferred schools and basic information.

[0198] The "exam question generation means" is a system that has the function of automatically generating appropriate exam questions based on the examinee's desired school information.

[0199] The "analysis method" is a system that has the function of analyzing the mock test results given by test takers and visualizing their weak areas and weaknesses.

[0200] The "answer explanation means" is a system that has the function of generating and displaying detailed explanations based on the analysis results.

[0201] The "material recommendation means" is a system that has the function of recommending online materials and resources that are appropriate for the student's learning situation.

[0202] The "similar question generation means" is a system that has the function of automatically generating similar questions based on the examinee's weak areas.

[0203] A "generative AI model" is a technology that uses generative artificial intelligence to generate content and feedback.

[0204] The "scoring and analysis means" is a system that has the functionality to use a generative AI model to score and analyze test takers' answers.

[0205] The "recommendation method" is a system that has the function of recommending the most suitable online learning materials based on the student's learning progress.

[0206] This invention is a system that efficiently supports test takers in studying for exams by using generative artificial intelligence (generative AI model). The system includes the following means.

[0207] User Interface Means

[0208] The user accesses the system from a terminal and enters the school of choice, exam subjects, and basic information (name, email address, etc.), which completes the initial registration.

[0209] Test question generation means

[0210] The server automatically generates appropriate test questions using a generative AI model based on the user's desired school information and exam subjects. The generated questions are sent to the user's device, where they can be viewed and answered.

[0211] Analysis means

[0212] When a user completes a mock test and submits their answers, the server receives the answer data and automatically scores and analyzes it using a generative AI model, revealing the score for each subject, the percentage of correct answers, and areas of weakness.

[0213] Answer explanation method

[0214] Based on the analysis results, the server generates detailed explanations for the questions that the user got wrong, providing step-by-step instructions on how to solve the problem. This explanation data is then sent to the user's device for viewing.

[0215] Teaching material recommendation method

[0216] The server recommends optimal online learning materials and resources based on the analysis results and the user's learning progress, allowing the user to study efficiently.

[0217] Similar problem generation means

[0218] If a user has difficulty with a particular problem, the server automatically generates similar problems related to that problem using a generative AI model. These similar problems are sent to the device, and the user can answer them as training.

[0219] Scoring and analysis methods

[0220] It uses a generative AI model to grade and analyze test-taker answer data, and provides detailed feedback on users' scores, accuracy rates, and weak areas based on the analysis results.

[0221] Recommendation method

[0222] Based on the analysis results and the user's learning progress, the system recommends the most suitable online learning materials, allowing users to study efficiently.

[0223] Specific examples

[0224] For example, a user logs into the system and enters "ABC University" as their preferred school and "Mathematics, English, and Physics" as their exam subjects. The server then uses a generative AI model to automatically generate mock exams for mathematics, English, and physics based on past exam information and data on successful candidates, and sends them to the device. When the user completes the mock exam and submits their answers, the server immediately analyzes the answers and provides detailed feedback and explanations. Based on the analysis results, the server determines that the user has particular weaknesses in English grammar and recommends specialized grammar questions and explanatory videos. Furthermore, it generates similar questions related to English grammar that the user can use for review.

[0225] Prompt Sentence Examples

[0226] "Generate practice math exam questions to help me get into ABC University."

[0227] "Generate an explanation for the English grammar question based on this answer."

[0228] To implement this system, we need to build a generative AI model using the OpenAI API, manage communication between the server and the device using a web application framework such as Flask, and build a comprehensive system, including designing the database and user interface.

[0229] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[0230] Step 1:

[0231] Initial registration

[0232] Input: The user inputs the school of choice, exam subjects, and basic information (name, email address, etc.) on the terminal.

[0233] Processing: The terminal sends the input data to the server.

[0234] Data processing: The server stores the received data in a database and performs any necessary preprocessing.

[0235] Output: The server sends a confirmation message to the terminal indicating that registration is complete.

[0236] Action: The user reconfirms the registration details on the terminal and receives a completion message.

[0237] Step 2:

[0238] Automatic generation of exam questions

[0239] Input: The server references the desired school information and exam subject data entered by the user.

[0240] Processing: The generative AI model is instructed to generate exam questions based on the student's desired school and exam subjects.

[0241] Data processing: A generative AI model generates test questions and structures the data.

[0242] Output: Send the created test questions to the terminal.

[0243] Operation: The user receives and views the generated test questions on the terminal.

[0244] Step 3:

[0245] Mock test answers and submission

[0246] Input: The user answers the practice questions on the terminal and sends the answer data after completion.

[0247] Processing: The terminal sends the answer data to the server.

[0248] Data processing: The server preprocesses the received answer data and formats it for analysis.

[0249] Output: A transmission confirmation message is displayed on the user's terminal.

[0250] Action: The user sees the delivery confirmation message.

[0251] Step 4:

[0252] Answer scoring and analysis

[0253] Input: The server uses the answer data received from the user.

[0254] Processing: Answers are graded and analyzed using a generative AI model.

[0255] Data processing: Extract scores for each subject, correct answer rate, weak areas and weaknesses, and generate analysis results.

[0256] Output: Sends the analysis results to the user's terminal and displays detailed explanations.

[0257] How it works: The user views the analysis results and explanations on their device.

[0258] Step 5:

[0259] Recommendation of teaching materials

[0260] Input: The server uses the analysis results and the user's learning progress data.

[0261] Processing: Using generative AI models to select the best online learning materials and resources.

[0262] Data processing: Format appropriate teaching material information and display it to the user as appropriate.

[0263] Output: Send recommended teaching material information to the terminal.

[0264] How it works: The user checks the recommended learning materials on their device and proceeds with their studies.

[0265] Step 6:

[0266] Generating and providing similar questions

[0267] Input: The server uses the user's weakness data.

[0268] Processing: Use a generative AI model to generate similar questions related to weak areas.

[0269] Data processing: The generated similar problem data is formatted and provided to the user.

[0270] Output: Similar problems are sent to the user's terminal.

[0271] How it works: Users view similar questions on their device and use them for training.

[0272] As a concrete example, if a user inputs "ABC University" as the school of choice and "Mathematics, English, and Physics" as the subjects to be tested, the server will use this information to generate test questions using a generative AI model. The generated test questions are sent to the user's device, and the user answers and submits them. The server analyzes the received answers and provides detailed feedback. Based on the analysis results, suitable study materials and similar questions are also recommended to the user.

[0273] Prompt Sentence Examples

[0274] "Generate practice math exam questions to help me get into ABC University."

[0275] "Generate an explanation for the English grammar question based on this answer."

[0276] Furthermore, an emotion engine that estimates the user's emotion may be combined. That is, the identification processing unit 290 may estimate the user's emotion using the emotion identification model 59 and perform identification processing using the user's emotion.

[0277] The present invention is a system that efficiently supports test takers in studying for exams by utilizing generative artificial intelligence and an emotion engine. This system includes a user interface means for inputting the user's desired school information and basic information, an exam question generation means for automatically generating exam questions, an analysis means for analyzing mock exam results, an answer explanation means for providing explanations based on the analysis results, a study material recommendation means for recommending appropriate study materials, a similar question generation means for generating similar questions based on weak areas, and an emotion engine for recognizing the user's emotions.

[0278] User Interface Means

[0279] Users access this system and enter their desired school, exam subjects, and basic information (name, email address, etc.), which completes the initial registration.

[0280] Test question generation means

[0281] The server uses AI to automatically generate appropriate exam questions based on the user's desired school information and exam subjects. The generated questions are sent to the user's device, where they can be viewed and answered.

[0282] Analysis means

[0283] When a user completes a mock test and submits their answers, the server receives the answer data and automatically scores and analyzes it using generative AI, which clarifies the score for each subject, the percentage of correct answers, and weak areas and weaknesses.

[0284] Answer explanation method

[0285] Based on the analysis results, the server generates detailed explanations for the questions that the user got wrong, providing step-by-step instructions on how to solve the problem. This explanation data is then sent to the user's device for viewing.

[0286] Teaching material recommendation method

[0287] The server recommends optimal online learning materials and resources based on the analysis results and the user's learning progress, allowing the user to study efficiently.

[0288] Similar problem generation means

[0289] If a user has difficulty with a particular problem, the server automatically generates similar problems related to that problem using a generation AI. These similar problems are sent to the device, and the user can answer them as training.

[0290] Emotion Engine

[0291] The emotion engine collects the user's facial expression recognition data and analyzes the user's emotional state during learning. For example, when the user sends their facial expression to the system through the camera, the server uses the emotion engine to analyze the facial expression and identify the emotional state that will affect the learning progress.

[0292] Emotion-based feedback

[0293] The server generates feedback based on the user's emotional state based on the results of analysis using the emotion engine. For example, if the user is feeling stressed, it will provide appropriate study advice or relaxation techniques. It also dynamically adjusts learning materials and learning approaches based on the user's emotional state to maximize learning efficiency.

[0294] Specific examples

[0295] A user logs into the system and enters "XYZ University" as their preferred school and "Mathematics, English, and Physics" as their exam subjects. The server then uses generative AI to automatically generate mock exams for mathematics, English, and physics based on past exam information and data on successful candidates, and sends them to the device. When the user completes the mock exam and submits their answers, the server immediately analyzes the answers and provides detailed feedback and explanations.

[0296] Based on the analysis results, the server determines that the user has particular weaknesses in English grammar and recommends grammar questions and explanatory videos specific to that area. It also generates similar questions related to English grammar for the user to use for review.

[0297] At the same time, the user's facial expression data is sent to the system and analyzed by the server's emotion engine. For example, if the user shows a confused expression while answering a question, the server will detect that emotional state and provide an encouraging message or advice on how to relax.

[0298] In this way, this system combines generative artificial intelligence and an emotion engine to efficiently provide learning support optimized for each test-taker's individual situation and emotions.

[0299] The processing flow will be explained below.

[0300] Processing steps of the invention combined with emotion engine

[0301] User Registration Process

[0302] Step 1:

[0303] A user accesses the system and opens a login or registration form.

[0304] Step 2:

[0305] The user enters basic information such as the school of choice, exam subjects, name, and email address.

[0306] Step 3:

[0307] The terminal transmits the input information to the server.

[0308] Step 4:

[0309] The server stores the received information in a database.

[0310] Step 5:

[0311] The server generates a registration success message and sends it to the terminal.

[0312] Step 6:

[0313] The terminal displays a registration success message to the user.

[0314] Automatic generation process for mock exams

[0315] Step 1:

[0316] The user selects "Take a Practice Exam" from the dashboard.

[0317] Step 2:

[0318] The terminal sends a request to generate a mock test to the server.

[0319] Step 3:

[0320] The server references data based on the user's desired school and exam subjects, and uses a generation AI to generate mock exam questions.

[0321] Step 4:

[0322] The server stores the generated mock test questions in a database and sends them to the terminal.

[0323] Step 5:

[0324] The terminal displays the practice questions to the user and provides an answer input form.

[0325] Test result analysis process

[0326] Step 1:

[0327] The user completes the practice test and clicks the "Submit" button.

[0328] Step 2:

[0329] The terminal sends the answer data to the server.

[0330] Step 3:

[0331] The server receives the answer data and automatically scores and analyzes it using the generating AI.

[0332] Step 4:

[0333] The server calculates the score for each subject, the percentage of correct answers, and weak areas, and generates detailed feedback.

[0334] Step 5:

[0335] The server sends the analysis results and feedback to the device.

[0336] Step 6:

[0337] The device displays the feedback to the user.

[0338] Answer explanation process

[0339] Step 1:

[0340] If the user reviews the feedback and needs a detailed explanation of the incorrect question, they can click the "Show Explanation" button.

[0341] Step 2:

[0342] The device sends a description request to the server.

[0343] Step 3:

[0344] The server uses a generative AI to generate the answer process for the incorrect question and creates an explanatory text.

[0345] Step 4:

[0346] The server transmits the generated commentary data to the terminal.

[0347] Step 5:

[0348] The terminal displays the explanation to the user.

[0349] Online Material Recommendation Process

[0350] Step 1:

[0351] After the user checks the feedback, they select "View online learning materials."

[0352] Step 2:

[0353] The terminal sends a learning material request to the server.

[0354] Step 3:

[0355] The server uses AI to recommend optimal learning materials based on the user's learning progress data.

[0356] Step 4:

[0357] The server transmits the recommended teaching material information to the terminal.

[0358] Step 5:

[0359] The device displays the recommended learning materials to the user.

[0360] Similar problem generation process

[0361] Step 1:

[0362] The user selects "Generate similar questions."

[0363] Step 2:

[0364] The device sends a request to the server.

[0365] Step 3:

[0366] The server automatically generates similar questions using AI based on the user's weak areas.

[0367] Step 4:

[0368] The server sends the generated similar questions to the terminal.

[0369] Step 5:

[0370] The terminal displays similar questions to the user and provides an answer form.

[0371] Emotion Engine Process

[0372] Step 1:

[0373] During training, the user sends emotional data (e.g., facial expressions and tone of voice) to the system via a camera or microphone.

[0374] Step 2:

[0375] The device transmits the collected emotion data to a server.

[0376] Step 3:

[0377] The server uses an emotion engine to analyze the emotion data and identify the current emotional state (e.g., stress, confusion, concentration).

[0378] Step 4:

[0379] The server generates optimal feedback and learning advice based on the emotional state.

[0380] Step 5:

[0381] The server transmits the generated feedback to the terminal.

[0382] Step 6:

[0383] The device displays emotion-based feedback and advice to the user.

[0384] Specific examples

[0385] A user logs into the system and enters "XYZ University" as their preferred school and "Mathematics, English, and Physics" as their exam subjects. The server then uses generative AI to automatically generate mock exams for mathematics, English, and physics based on past exam information and data on successful candidates, and sends them to the device. When the user completes the mock exam and submits their answers, the server immediately analyzes the answers and provides detailed feedback and explanations.

[0386] Based on the analysis results, the server determines that the user has particular weaknesses in English grammar and recommends grammar questions and explanatory videos specific to that area. It also generates similar questions related to English grammar for the user to use for review.

[0387] While the user is learning, the server monitors the user's facial expressions via a camera, and if it detects a confused expression, the emotion engine analyzes that state. As a result of the analysis, the server determines that the user is feeling stressed and provides an encouraging message or advice on how to relax. For example, a message such as "Take a deep breath and relax. Next, I'll introduce some ways to relax" is displayed.

[0388] In this way, this system combines generative artificial intelligence and an emotion engine to efficiently provide learning support optimized for each test-taker's individual situation and emotions.

[0389] Example 2

[0390] Next, a description will be given of Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the smart device 14 will be referred to as a "terminal."

[0391] Conventional exam study support systems lack personalized learning support tailored to each student's learning progress and areas of weakness, making it difficult for them to study efficiently. Furthermore, they do not provide appropriate feedback that takes into account the student's emotional state, making it difficult for them to maintain their motivation to study and often causing stress.

[0392] The specific processing by the specific processing unit 290 of the data processing device 12 in the second embodiment is realized by the following means.

[0393] In this invention, the server includes user interface means for inputting the examinee's desired school and basic information, test question generation means for automatically generating test questions based on the examinee's desired school information, analysis means for analyzing the mock test results answered by the examinee and visualizing weak areas and areas of weakness, answer explanation means for generating and displaying explanations based on the analysis results, learning material recommendation means for recommending online learning materials suited to the examinee's learning situation, similar question generation means for automatically generating similar questions based on the examinee's weak areas, emotion recognition means for recognizing and analyzing the examinee's emotional state, and emotion feedback means for providing feedback based on the emotion recognition results. This enables efficient and personalized learning support according to the learning situation and emotional state of each examinee.

[0394] "Generative artificial intelligence" refers to sophisticated algorithms that automatically generate information and data based on user input and prompts.

[0395] "Exam taker" refers to an individual studying for a particular exam or entrance examination.

[0396] "User interface means" refers to the interactive input means by which examinees input their preferred schools and basic information into the system.

[0397] "Exam question generation means" refers to a system function that automatically generates appropriate exam questions based on the desired school information and exam subjects entered by the examinee.

[0398] "Analysis means" refers to the system function that analyzes the mock test results given by test takers and clarifies their weak areas and weaknesses.

[0399] The "answer explanation means" refers to a function that generates and displays detailed explanations, especially for incorrect questions, based on the analysis results.

[0400] "Materials recommendation means" refers to the system function that recommends the most appropriate online materials and resources based on the candidate's learning progress and analysis results.

[0401] "Similar question generation means" refers to a function that automatically generates similar questions related to the examinee's weak areas.

[0402] "Emotion recognition means" refers to a function that analyzes the examinee's facial expressions and behavior to identify their current emotional state.

[0403] "Emotion feedback means" refers to a system function that provides appropriate feedback to test takers based on emotion recognition results.

[0404] The present invention is a system that efficiently supports test takers in studying for exams by utilizing generative artificial intelligence and an emotion engine. The system includes a user interface, test question generation, analysis, answer explanation, learning material recommendation, similar question generation, emotion recognition, and emotion feedback.

[0405] Users access the system and perform initial registration by entering their desired school, exam subjects, and basic information (name, email address, etc.). At this time, the information entered by the user is sent to the server and stored in a database.

[0406] The server automatically generates appropriate exam questions using a generative AI model based on the user's desired school information and exam subjects. The generated exam questions are sent to the device so that the user can view and answer them. Specifically, the server uses a generative AI model (e.g., GPT-4) to process data using Python scripts and MongoDB.

[0407] When a user completes a mock test and submits their answers, the server receives the answer data and automatically scores and analyzes it using a generative AI model. This results in clear scores for each subject, the percentage of correct answers, and areas of weakness. Scikit-learn and PostgreSQL are used for this analysis.

[0408] Based on the analysis results, the server generates detailed explanations for questions where the student got the answer wrong. The explanation data is sent to the device and can be viewed by the user. This explanation generation also uses a generative AI model and API communication (REST).

[0409] The server recommends the most suitable online learning materials and resources based on the analysis results and the user's learning progress. This is done using a recommendation engine (e.g., TensorFlow) and Elasticsearch. The recommended learning materials help the user progress efficiently.

[0410] If a user has difficulty with a particular problem, the server automatically generates similar problems related to that problem using a generative AI model. These similar problems are sent to the device and the user can use them for review. At this stage, a NoSQL database such as Firebase is used.

[0411] Furthermore, the user's facial expression data is analyzed using an emotion recognition means. When the user transmits their facial expressions through the camera while studying, the server analyzes the expressions using an emotion engine (e.g., Azure Face API) and generates useful feedback for the user's progress. This feedback may include encouraging messages or suggestions for relaxation techniques depending on the user's emotional state.

[0412] As a specific example, a user logs into the system, sets "ABC University" as their preferred school, and enters "Mathematics, English, and Physics" as their exam subjects. Based on this, the server uses past exam data and data on the trends of successful candidates to automatically generate mock exams for mathematics, English, and physics using generative AI. This mock exam data is sent to the device, and the user takes the mock exam and submits their answers after completing it. The server immediately analyzes the answers and provides detailed feedback and explanations. For example, it might recommend "videos explaining English grammar questions" or "similar questions specialized in grammar." Additionally, if the user's facial expressions during study indicate difficulty or stress, the server will provide advice and messages based on that.

[0413] Examples of prompts include:

[0414] "Please generate mock exams for Mathematics, English, and Physics for ABC University."

[0415] "Analyze users' practice test results and provide feedback with special emphasis on the area of ​​English grammar."

[0416] "Analyze facial expression data sent by the user using a camera and suggest relaxation methods when the user is feeling stressed."

[0417] In this way, the present invention combines generative artificial intelligence and an emotion engine to efficiently provide optimal learning support tailored to the individual circumstances and emotions of each test-taker.

[0418] The flow of the identification process in the second embodiment will be described with reference to FIG.

[0419] Step 1:

[0420] Initial registration

[0421] Users access the system and enter their desired school, exam subjects, and basic information (name, email address, etc.).

[0422] Input: desired school information, exam subject information, basic information (name, email address)

[0423] Output: Save to user profile database

[0424] Specific operation: A form is displayed on the user interface, and the user enters the school of choice and exam subjects and presses the submit button. The submitted data is transferred to the server and stored in a database. This process uses HTML forms, JavaScript, Python, and Django.

[0425] Step 2:

[0426] Automatic generation of exam questions

[0427] The server automatically generates appropriate exam questions using a generative AI model based on the desired school information and exam subjects entered by the user.

[0428] Input: desired school information, exam subject information

[0429] Output: Generated test question data

[0430] Specific operation: The server retrieves information about the school of choice and exam subjects from the user database and sends them as prompts to the generative AI model. The generative AI generates exam questions and returns them to the server. The server then sends the generated exam questions to the device. This process uses a generative AI model (e.g., GPT-4), Python scripts, and a database (MongoDB).

[0431] Step 3:

[0432] Mock exams and answer submission

[0433] The generated test questions are sent to the terminal, and the user takes the test. After completing the test, the answers are sent to the server.

[0434] Input: Generated test questions, user answer data

[0435] Output: Send answer data to the server

[0436] Specific operation: The test questions are displayed on the device, and when the user enters the answers and presses the submit button, the answer data is sent to the server. This process is done using React.js and Node.js.

[0437] Step 4:

[0438] Scoring and Analysis

[0439] The server receives the submitted answer data and automatically scores and analyzes it using a generative AI model.

[0440] Input: User's answer data

[0441] Output: Analysis results for each subject, score, correct answer rate, weak areas and weaknesses

[0442] How it works: The server passes the answer data to the analysis engine, which determines whether each question is correct or not. It also scores the answers and identifies areas where the user is weak. Scikit-learn and PostgreSQL are used for this analysis.

[0443] Step 5:

[0444] Providing answer explanations

[0445] Based on the analysis results, the server generates detailed explanations for the incorrect questions, and the explanation data is sent to the terminal for the user to view.

[0446] Input: Analysis results

[0447] Output: Detailed explanatory data

[0448] Specific operation: Based on the analysis results, the server sends prompts to the generative AI model to generate detailed explanations, which are then sent to the device. This process uses the generative AI model and API communication (REST).

[0449] Step 6:

[0450] Recommendation of teaching materials

[0451] The server recommends the most appropriate online learning materials and resources based on the analysis results and the user's learning progress.

[0452] Input: Analysis results, learning history

[0453] Output: Recommended online learning materials and resources

[0454] Specific operation: The server refers to the analysis results database, checks the user's past learning history and progress, selects appropriate learning materials, and notifies the user. This process uses a recommendation engine (TensorFlow) and Elasticsearch.

[0455] Step 7:

[0456] Generating similar problems

[0457] If a user feels uncomfortable with a particular problem, the server automatically generates similar problems related to that problem using a generative AI model.

[0458] Input: Weakness data

[0459] Output: Generated similar problem data

[0460] Specific operation: The server sends data on weak areas to the generative AI model as prompts, which generate similar questions. These are then sent to the device. This process uses the generative AI model and a NoSQL database such as Firebase.

[0461] Step 8:

[0462] Emotional Recognition and Feedback

[0463] The emotion engine collects the user's facial expression data and analyzes the user's emotional state during training. The server generates feedback based on the results and sends it to the device.

[0464] Input: User's facial expression data

[0465] Output: Sentiment analysis results, feedback data

[0466] Specific operation: Facial expression data collected through the camera is passed to the emotion engine, and the analysis results are obtained. The server generates appropriate feedback based on these results and sends it to the device. This process uses an emotion recognition API (e.g., Azure Face API) and a real-time database (Firebase).

[0467] (Application example 2)

[0468] Next, a description will be given of Application Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the smart device 14 will be referred to as a "terminal."

[0469] Conventional test-taking support systems have limited functionality for analyzing test-takers' learning progress and weak areas, making them unable to adequately address individual learning needs. Furthermore, they provide uniform feedback without taking test-takers' emotional state into consideration, making it difficult to provide effective learning support. Furthermore, they are unable to recommend optimal products and services in real time, limiting their ability to improve customer experience in physical stores. The present invention aims to solve these problems.

[0470] The specific processing by the specific processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means. In this invention, the server includes a user interface means for inputting the examinee's desired school and basic information, a test question generation means for automatically generating test questions based on the examinee's desired school information, an analysis means for analyzing the mock test results answered by the examinee and visualizing the examinee's weak areas and areas of weakness, an answer explanation means for generating and displaying explanations based on the analysis results, a learning material recommendation means for recommending online learning materials suited to the examinee's learning situation, a similar question generation means for automatically generating similar questions based on the examinee's weak areas, an emotion analysis means for collecting customer facial expression recognition data and analyzing the emotional state, and a feedback means for providing feedback according to the emotional state. This enables efficient learning support tailored to individual learning needs and further improves customer experience by recommending optimal products and services in real time.

[0471] "Candidate" refers to any student studying or individual taking an examination.

[0472] "User interface means" refers to the interface through which prospective students and customers input basic information and information about their preferred schools.

[0473] "Exam question generation means" refers to a function that automatically creates exam questions based on information input by examinees.

[0474] "Analysis means" refers to the function that analyzes the mock test results submitted by test takers and analyzes weak areas and correct answer rates.

[0475] "Answer explanation means" refers to a function that provides explanations based on an analysis of mock test results to encourage understanding among test takers.

[0476] "Material recommendation means" refers to a function that recommends optimal learning resources and materials based on the test-taker's learning situation and areas of weakness.

[0477] "Similar problem generation means" refers to a function that automatically generates similar problems related to problems that are difficult to solve.

[0478] "Emotion analysis means" refers to the function of analyzing facial expressions and behavioral data of test takers and customers to analyze their emotional state.

[0479] "Feedback means" refers to the function of providing appropriate feedback or encouraging messages based on the results of sentiment analysis.

[0480] The present invention is a system that efficiently supports test takers and customers of brick-and-mortar stores by utilizing generative artificial intelligence and an emotion engine. Each means of the system will be specifically described below.

[0481] User Interface Means

[0482] Users access the system and input their desired school, exam subjects, basic information (name, email address, etc.) or customer information (name, preferred product category, etc.). This information is stored by the server and becomes the basic data for responding to the individual needs of the user.

[0483] Test question generation means

[0484] Based on the student's desired school information and exam subjects, the server uses AI to automatically generate appropriate exam questions. The generated questions are sent to the device, where the user can view and answer them.

[0485] Analysis means

[0486] When a user completes a mock test and submits their answers, the server receives the answer data and automatically scores and analyzes it using generative AI, which clarifies the score for each subject, the percentage of correct answers, and weak areas and weaknesses.

[0487] Answer explanation method

[0488] Based on the analysis results, the server generates detailed explanations for the questions that the user got wrong, providing step-by-step instructions on how to solve the problem. This explanation data is then sent to the user's device for viewing.

[0489] Teaching material recommendation method

[0490] The server recommends optimal online learning materials and resources based on the analysis results and the user's learning progress, allowing the user to study efficiently.

[0491] Similar problem generation means

[0492] If a user has difficulty with a particular problem, the server automatically generates similar problems related to that problem using a generation AI. These similar problems are sent to the device, and the user can answer them as training.

[0493] Emotion analysis means

[0494] The server collects facial expression data from the user through the camera and uses the emotion engine to analyze the user's emotional state during learning. For example, when the user looks at the camera, the server uses the emotion engine to analyze the user's facial expression and identify the emotional state that will affect the user's learning progress.

[0495] Feedback Methods

[0496] Based on the results of emotion analysis, the server generates feedback according to the user's emotional state. For example, if the user is confused, it will display relaxation advice or encouraging messages. It also improves the customer experience by recommending optimal products and services based on the results of analyzing customers' facial expressions in the store.

[0497] Specific examples

[0498] 1. A user logs into the system and enters "ABC University" as their preferred school and "Mathematics, English, and Physics" as their exam subjects. The server then uses AI to automatically generate mock exams for mathematics, English, and physics based on past exam information and data on successful candidates, and sends them to the device.

[0499] 2. Once a user completes a mock test and submits their answers, the server instantly analyzes the answers and provides detailed feedback and explanations. Based on the analysis results, the server determines that the user has particular weaknesses in English grammar and recommends grammar questions and explanatory videos specific to that area. Furthermore, the server generates similar questions related to English grammar for the user to review.

[0500] 3. The user's facial expression data is sent to the system via the camera and analyzed by the server's emotion engine. For example, if the user shows a confused expression while answering a question, the server will detect that emotional state and provide an encouraging message or advice on how to relax.

[0501] 4. Even in physical stores, when customers send facial expression data via camera, it is analyzed by the emotion engine and the most suitable products and promotions are recommended in real time.

[0502] Prompt Sentence Examples

[0503] "Use your emotion engine to provide optimal product recommendations when customers are confused."

[0504] "Implement a product recommendation algorithm based on historical purchase data and real-time sentiment analysis."

[0505] In this way, the system combines generative artificial intelligence and an emotion engine to efficiently provide support optimized for the individual situations and emotions of test takers and customers in brick-and-mortar stores.

[0506] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[0507] Step 1:

[0508] The user accesses the system and inputs the school of choice, exam subjects, basic information (name, email address, etc.), or customer information (name, preferred product category, etc.) through the user interface. The input information is sent to the server and saved in the database. This completes the initial setup based on the user's individual needs. The input data is processed by checking the format of each item and saving it as the appropriate data type.

[0509] Step 2:

[0510] Based on the examinee's desired school information and exam subjects, the server uses a generative AI model to automatically generate appropriate exam questions. The generated questions are sent to the terminal so that the user can view and answer them. In this step, prompts are generated based on the user's input data, and the AI ​​model generates questions accordingly.

[0511] Step 3:

[0512] Users answer mock exam questions and send the answer data to the server. The server uses a generative AI model to automatically score the test-taker's answers and analyzes the score for each subject, the percentage of correct answers, and weak areas and weaknesses. The input data is the user's answer data, and the output data is a report of the analysis results.

[0513] Step 4:

[0514] Based on the analysis results, the server generates detailed explanations for the incorrect answers, which are then sent to the device for viewing by the user. Based on the analysis data, prompts are generated, and the AI ​​model then creates explanations accordingly.

[0515] Step 5:

[0516] The server recommends the most suitable online learning materials and resources based on the user's analysis results and learning progress. The recommended learning materials are notified to the user's device, where they can be viewed and used. Based on the analysis results, the server searches for and recommends the most suitable learning materials from a database of related learning materials.

[0517] Step 6:

[0518] If a user has difficulty with a particular problem, the server automatically generates similar problems related to that problem using a generative AI model. The generated similar problems are sent to the device, where the user can solve them for training. Using the user's answer data and analysis results as input, a prompt to generate similar problems is created and the problems are generated by the AI ​​model.

[0519] Step 7:

[0520] The user's facial expression data is collected through the camera and sent to the server. The server uses an emotion analysis engine to analyze the user's emotional state during training. This data is the user's facial expression data, and the emotional state is output as the analysis result. Analysis is performed in real time based on the emotional data.

[0521] Step 8:

[0522] Based on the results of the emotion analysis, the server generates feedback according to the user's emotional state. For example, if the user is confused, the server sends an encouraging message or advice to relax to the device, thereby supporting the user's mental state. The server uses the emotional state data as input and generates an appropriate feedback message.

[0523] Step 9:

[0524] In physical stores, customer facial expression data is collected and sent to a server. The server uses an emotion analysis engine to analyze the customer's emotions in real time. Based on the analyzed emotion data, the system recommends the most appropriate products and services. For example, if a customer is confused, corresponding products will be displayed on the smart device. Emotional state data is used to generate prompts and recommend products using an AI model.

[0525] In this way, the system effectively utilizes generative AI models and emotion engines at each step to provide advanced assistance to test takers and brick-and-mortar customers.

[0526] The specific processing unit 290 transmits the result of the specific processing to the smart device 14. In the smart device 14, the control unit 46A causes the output device 40 to output the result of the specific processing. The microphone 38B acquires audio indicating a user input regarding the result of the specific processing. The control unit 46A transmits audio data indicating the user input acquired by the microphone 38B to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the audio data.

[0527] The data generation model 58 is a so-called generative AI (Artificial Intelligence). An example of the data generation model 58 is ChatGPT (Internet Search<URL: https: / / openai.com / blog / chatgpt> ), Gemini (Internet search <url: https: gemini.google.com ?hl="ja">) and other generation AIs. The data generation model 58 is obtained by performing deep learning on a neural network. A prompt including an instruction is input to the data generation model 58, and inference data such as voice data indicating voice, text data indicating text, and image data indicating an image is also input. The data generation model 58 performs inference on the input inference data in accordance with the instruction indicated by the prompt, and outputs the inference result in a data format such as voice data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[0528] In the above embodiment, an example in which the specific process is performed by the data processing device 12 has been given, but the technology of the present disclosure is not limited to this, and the specific process may be performed by the smart device 14.

[0529] [Second embodiment]

[0530] FIG. 3 shows an example of the configuration of a data processing system 210 according to the second embodiment.

[0531] 3, the data processing system 210 includes the data processing device 12 and smart glasses 214. An example of the data processing device 12 is a server.

[0532] The data processing device 12 includes a computer 22, a database 24, and a communication I / F 26. The computer 22 is an example of a "computer" according to the technology of the present disclosure. The computer 22 includes a processor 28, a RAM 30, and a storage 32. The processor 28, the RAM 30, and the storage 32 are connected to a bus 34. The database 24 and the communication I / F 26 are also connected to the bus 34. The communication I / F 26 is connected to a network 54. Examples of the network 54 include a WAN (Wide Area Network) and / or a LAN (Local Area Network).

[0533] The smart glasses 214 include a computer 36, a microphone 238, a speaker 240, a camera 42, and a communication I / F 44. The computer 36 includes a processor 46, a RAM 48, and a storage 50. The processor 46, the RAM 48, and the storage 50 are connected to a bus 52. The microphone 238, the speaker 240, and the camera 42 are also connected to the bus 52.

[0534] The microphone 238 receives instructions and the like from the user 20 by receiving voice uttered by the user 20. The microphone 238 captures the voice uttered by the user 20, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio in accordance with instructions from the processor 46.

[0535] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an imaging element such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, and captures images of the surroundings of user 20 (for example, an imaging range defined by an angle of view equivalent to the field of vision of a typical healthy person).

[0536] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 are responsible for the exchange of various information between the processor 46 and the processor 28 via the network 54. The exchange of various information between the processor 46 and the processor 28 using the communication I / Fs 44 and 26 is carried out in a secure state.

[0537] Fig. 4 shows an example of the main functions of the data processing device 12 and the smart glasses 214. As shown in Fig. 4, in the data processing device 12, a specific process is performed by the processor 28. A specific process program 56 is stored in the storage 32.

[0538] The specific processing program 56 is an example of a "program" according to the technology of the present disclosure. The processor 28 reads the specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific processing is realized by the processor 28 operating as a specific processing unit 290 in accordance with the specific processing program 56 executed on the RAM 30.

[0539] The storage 32 stores a data generation model 58 and an emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290.

[0540] In the smart glasses 214, the reception output process is performed by the processor 46. A reception output program 60 is stored in the storage 50. The processor 46 reads the reception output program 60 from the storage 50 and executes the read reception output program 60 on the RAM 48. The reception output process is realized by the processor 46 operating as the control unit 46A in accordance with the reception output program 60 executed on the RAM 48.

[0541] Next, a description will be given of the identification process performed by the identification processing unit 290 of the data processing device 12. In the following description, the data processing device 12 will be referred to as the "server" and the smart glasses 214 will be referred to as the "terminal."

[0542] The present invention is a system that efficiently supports test takers in studying for exams using generative artificial intelligence. This system includes a user interface means for inputting the user's desired school information and basic information, a test question generation means for automatically generating test questions, an analysis means for analyzing mock test results, an answer explanation means for providing explanations based on the analysis results, a learning material recommendation means for recommending appropriate learning materials, and a similar question generation means for generating similar questions based on weak areas.

[0543] User Interface Means

[0544] Users access this system and enter their desired school, exam subjects, and basic information (name, email address, etc.), which completes the initial registration.

[0545] Test question generation means

[0546] The server uses AI to automatically generate appropriate exam questions based on the user's desired school information and exam subjects. The generated questions are sent to the user's device, where they can be viewed and answered.

[0547] Analysis means

[0548] When a user completes a mock test and submits their answers, the server receives the answer data and automatically scores and analyzes it using generative AI, which clarifies the score for each subject, the percentage of correct answers, and weak areas and weaknesses.

[0549] Answer explanation method

[0550] Based on the analysis results, the server generates detailed explanations for the questions that the user got wrong, providing step-by-step instructions on how to solve the problem. This explanation data is then sent to the user's device for viewing.

[0551] Teaching material recommendation method

[0552] The server recommends optimal online learning materials and resources based on the analysis results and the user's learning progress, allowing the user to study efficiently.

[0553] Similar problem generation means

[0554] If a user has difficulty with a particular problem, the server automatically generates similar problems related to that problem using a generation AI. These similar problems are sent to the device, and the user can answer them as training.

[0555] Statistical analysis and comparison tools

[0556] This system has the ability to statistically analyze accumulated test-taker data. This data is provided to educational institutions and companies, supporting strategic data utilization in the field of education. Furthermore, by performing comparative analysis with past test-taker data, it is possible to provide more specific feedback to users.

[0557] Specific examples

[0558] A user logs into the system and enters "XYZ University" as their preferred school and "Mathematics, English, and Physics" as their exam subjects. The server then uses generative AI to automatically generate mock exams for mathematics, English, and physics based on past exam information and data on successful candidates, and sends them to the device. When the user completes the mock exam and submits their answers, the server immediately analyzes the answers and provides detailed feedback and explanations. Based on the analysis results, the server determines that the user has particular weaknesses in English grammar and recommends specialized grammar questions and explanatory videos. Furthermore, the server generates similar questions related to English grammar that the user can use for review.

[0559] In this way, the system efficiently provides learning support that is optimized for each examinee's individual situation.

[0560] The processing flow will be explained below.

[0561] User Registration Process

[0562] Step 1:

[0563] A user accesses the system and opens a login or registration form.

[0564] Step 2:

[0565] The user enters basic information such as the school of choice, exam subjects, name, and email address.

[0566] Step 3:

[0567] The terminal transmits the input information to the server.

[0568] Step 4:

[0569] The server stores the received information in a database.

[0570] Step 5:

[0571] The server generates a registration success message and sends it to the terminal.

[0572] Step 6:

[0573] The terminal displays a registration success message to the user.

[0574] Automatic generation process for mock exams

[0575] Step 1:

[0576] The user selects "Take a Practice Exam" from the dashboard.

[0577] Step 2:

[0578] The terminal sends a request to generate a mock test to the server.

[0579] Step 3:

[0580] The server references data based on the user's desired school and exam subjects, and uses a generation AI to generate mock exam questions.

[0581] Step 4:

[0582] The server stores the generated mock test questions in a database and sends them to the terminal.

[0583] Step 5:

[0584] The terminal displays the practice questions to the user and provides an answer input form.

[0585] Test result analysis process

[0586] Step 1:

[0587] The user completes the practice test and clicks the "Submit" button.

[0588] Step 2:

[0589] The terminal sends the answer data to the server.

[0590] Step 3:

[0591] The server receives the answer data and automatically scores and analyzes it using the generating AI.

[0592] Step 4:

[0593] The server calculates the score, accuracy rate, and weak areas for each subject and generates detailed feedback.

[0594] Step 5:

[0595] The server sends the analysis results and feedback to the device.

[0596] Step 6:

[0597] The device displays the feedback to the user.

[0598] Answer explanation process

[0599] Step 1:

[0600] If the user reviews the feedback and needs a detailed explanation of the incorrect question, they can click the "Show Explanation" button.

[0601] Step 2:

[0602] The device sends a description request to the server.

[0603] Step 3:

[0604] The server uses a generative AI to generate the answer process for the incorrect question and creates an explanatory text.

[0605] Step 4:

[0606] The server transmits the generated commentary data to the terminal.

[0607] Step 5:

[0608] The terminal displays the explanation to the user.

[0609] Online Material Recommendation Process

[0610] Step 1:

[0611] After the user checks the feedback, they select "View online learning materials."

[0612] Step 2:

[0613] The terminal sends a learning material request to the server.

[0614] Step 3:

[0615] The server uses AI to recommend optimal learning materials based on the user's learning progress data.

[0616] Step 4:

[0617] The server transmits the recommended teaching material information to the terminal.

[0618] Step 5:

[0619] The device displays the recommended learning materials to the user.

[0620] Similar problem generation process

[0621] Step 1:

[0622] The user selects "Generate similar questions."

[0623] Step 2:

[0624] The device sends a request to the server.

[0625] Step 3:

[0626] The server automatically generates similar questions using AI based on the user's weak areas.

[0627] Step 4:

[0628] The server sends the generated similar questions to the terminal.

[0629] Step 5:

[0630] The terminal displays similar questions to the user and provides an answer form.

[0631] Statistical Information Provision Process

[0632] Step 1:

[0633] The server periodically collects data on all test takers and performs statistical analysis.

[0634] Step 2:

[0635] The server generates statistical reports and publishes them to educational institutions and businesses.

[0636] Step 3:

[0637] Educational institutions or companies can access statistical reports on their devices to help improve and strategize their teaching.

[0638] Example 1

[0639] Next, a description will be given of Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the smart glasses 214 will be referred to as a "terminal."

[0640] Today's test-takers need to access a wealth of information and learning resources, making it difficult to determine which resources are most appropriate. It is also difficult to objectively analyze their own academic abilities and weaknesses and create a study plan based on that. Furthermore, they need to find the questions and study materials that are best suited to them and study efficiently.

[0641] The specific processing by the specific processing unit 290 of the data processing device 12 in the first embodiment is realized by the following means.

[0642] In this invention, the server includes a user interface means for inputting the examinee's desired school and basic information, a test question generation means for automatically generating test questions based on the examinee's desired school information and exam subjects, an analysis means for receiving the mock test results answered by the examinee and automatically scoring and analyzing them to clarify the score and correct answer rate, an answer explanation means for generating and displaying detailed explanations for questions answered incorrectly based on the analysis results, a learning material recommendation means for recommending online learning materials and resources suitable for the examinee's learning progress, and a similar question generation means for automatically generating similar questions based on the examinee's awareness of difficulty with specific questions. This allows the examinee to accurately grasp their own academic ability and efficiently progress in their studies.

[0643] "Generative AI" is an AI technology that uses natural language processing and machine learning techniques to automatically generate text and data.

[0644] A "candidate" is an individual who is taking a particular examination or entrance exam.

[0645] "User interface means" refers to input and output devices and software that allow a user to interact with the system.

[0646] "Test question generation means" refers to a function or device that automatically generates test questions based on input information.

[0647] A "generative AI model" is a mathematical model that uses machine learning algorithms to generate text and data.

[0648] "Analysis means" refers to a function or device that analyzes the test taker's answer data and identifies the test taker's score, correct answer rate, and weak points.

[0649] The "answer explanation means" is a function or device that generates detailed explanations based on the analysis results and provides them to the user.

[0650] The "teaching material recommendation means" is a function or device that recommends optimal teaching materials and resources based on the test-taker's learning progress and analysis results.

[0651] The "similar question generating means" is a function or device that automatically generates similar questions related to the subject area in which the examinee is weak.

[0652] "Statistical analysis means" refers to a function or device that statistically analyzes accumulated data and extracts specific patterns or trends.

[0653] A "comparison tool" is a function or device that compares past data with current data and analyzes specific patterns or differences.

[0654] The present invention provides a system for efficiently supporting test takers in their exam preparation using generative artificial intelligence, which includes a user interface, test question generation, analysis, answer explanation, teaching material recommendation, similar question generation, statistical analysis, and comparison.

[0655] First, a user accesses the system and uses an interface to input their desired school, exam subjects, and basic information (such as name and email address). This information is stored in a database by the server. For example, a user inputs "ABC University as their desired school" and "Mathematics, English, and Physics as their exam subjects."

[0656] Next, the server automatically generates appropriate exam questions using a generative AI model (e.g., GPT-4) based on the user's desired school information and exam subjects. The generated exam questions are sent to the user's device, where they can be viewed and answered. For example, it generates "mathematics mock exam questions based on past questions from ABC University."

[0657] When a user enters answers to practice test questions and sends them to a server, the server receives the data and automatically scores and analyzes it using a generative AI model (e.g., BERT). This analysis clarifies the score and correct answer rate for each subject, as well as weak areas and areas of weakness. For example, the result may be, "Mathematics score: 80 points, English correct answer rate: 70%."

[0658] Based on the analysis results, the server generates detailed explanations for the incorrect questions, providing step-by-step instructions on the solution process. This explanation data is sent to the user's device and can be viewed by the user. For example, it provides a "detailed explanation for English grammar questions."

[0659] Furthermore, the server recommends the most suitable online learning materials and resources based on the analysis results and the user's learning progress, allowing the user to study efficiently. For example, it might recommend an online video course specializing in English grammar.

[0660] If a user has difficulty with a particular problem, the server uses a generative AI model to automatically generate similar problems related to that problem. These similar problems are sent to the user's device, and the user can answer them as training. For example, it generates "similar practice problems related to English grammar questions."

[0661] Furthermore, the server uses statistical analysis tools to statistically analyze the accumulated data on test takers and provide reports to educational institutions and companies, enabling strategic use of data in educational settings.

[0662] Finally, through a comparison means, the server compares the past test-taker data with the current test-taker data and provides specific feedback, such as "Your English grades are in the top 20% compared to other test-takers."

[0663] Prompt Sentence Examples

[0664] "Enter ABC University as your preferred school and select Mathematics, English, and Physics as your exam subjects."

[0665] This allows test takers to accurately understand their own academic ability and study efficiently.The system utilizes generative AI models to provide optimal learning support tailored to the diverse needs of test takers.

[0666] The flow of the identification process in the first embodiment will be described with reference to FIG.

[0667] Step 1:

[0668] Users access this system and use the interface to create an account. Specifically, they enter basic information such as their name, email address, and password. The entered data is sent to the server and stored in a database. The entered basic information is used for future individual learning support.

[0669] Step 2:

[0670] Users log in with their account and enter detailed information such as their preferred school and exam subjects. This information includes, for example, "ABC University as the preferred school" and "Mathematics, English, and Physics as the exam subjects." This information is sent to the server and stored in a database. The entered details are used to automatically generate exam questions.

[0671] Step 3:

[0672] The server automatically generates appropriate test questions using a generative AI model (e.g., GPT-4) based on the desired school information and exam subjects. The server references past test data and a question database based on the information entered by the user, and generates an optimal combination of question sets. The generated test questions are then sent to the user's device.

[0673] Step 4:

[0674] The user inputs answers to the test questions received on the device. Once the answer is complete, the device sends the answer data to the server. The sent data includes the user's answer and related metadata (such as the time it took to answer).

[0675] Step 5:

[0676] The server automatically scores and analyzes the received answer data using a generative AI model (e.g., BERT). This analysis clarifies the score and correct answer rate for each subject, as well as weak areas and areas of weakness. For example, the result may be "Mathematics score: 80 points, English correct answer rate: 70%." The analysis results are stored in a database.

[0677] Step 6:

[0678] Based on the analysis results, the server generates detailed explanations for the questions where the user got the answer wrong. The generated explanation data is sent to the user's device and can be viewed by the user. For example, it can provide a "detailed explanation for an English grammar question." The explanation data is important information for the user to restudy.

[0679] Step 7:

[0680] The server recommends optimal online learning materials and resources based on the analysis results and the user's learning progress, allowing the user to study efficiently. For example, it might recommend an "online video course specializing in English grammar." The recommended learning material information is sent to the user's device.

[0681] Step 8:

[0682] If a user has difficulty with a particular problem, the server uses a generative AI model to automatically generate similar problems related to that problem. These similar problems are sent to the user's device, and the user can answer them as training. For example, it generates "similar practice problems related to English grammar questions." The server also references the user's past answer data when generating similar problems.

[0683] Step 9:

[0684] The server statistically analyzes the accumulated test-taker data and provides reports to educational institutions and companies. For example, it provides educational institutions with "statistical data on test-taker weaknesses." The server also compares past test-taker data with current test-taker data and provides specific feedback. For example, it may provide feedback such as, "Your English performance is in the top 20% compared to other test-takers."

[0685] Through these steps, this system provides multifaceted support for test takers' learning, enabling them to study efficiently.

[0686] (Application example 1)

[0687] Next, a description will be given of Application Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the smart glasses 214 will be referred to as a "terminal."

[0688] Conventional exam study support systems have had issues with providing optimal study plans tailored to each student's learning situation and areas of weakness, and with variations in the quality of automatically generated exam questions and answer explanations. It is also difficult to recommend optimal online learning materials based on students' learning progress, and there was a need for a system that could quickly score and analyze students' mock exam results and provide appropriate feedback based on that.

[0689] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 1 is realized by the following means.

[0690] In this invention, the server includes a user interface means for inputting the examinee's desired school and basic information, a test question generation means for automatically generating test questions based on the examinee's desired school information, an analysis means for analyzing the mock test results answered by the examinee and visualizing weak areas and areas of weakness, an answer explanation means for generating and displaying explanations based on the analysis results, a learning material recommendation means for recommending online learning materials suitable for the examinee's learning situation, a similar question generation means for automatically generating similar questions based on the examinee's weak areas, a scoring analysis means for using a generative AI model to score and analyze the examinee's answers, and a recommendation means for recommending optimal online learning materials based on the examinee's learning progress. This enables efficient learning support tailored to the learning progress of each examinee, as well as rapid feedback and improvement.

[0691] "User interface means" refers to a device, software, or a combination thereof that allows examinees to input their preferred schools and basic information.

[0692] The "exam question generation means" is a system that has the function of automatically generating appropriate exam questions based on the examinee's desired school information.

[0693] The "analysis method" is a system that has the function of analyzing the mock test results given by test takers and visualizing their weak areas and weaknesses.

[0694] The "answer explanation means" is a system that has the function of generating and displaying detailed explanations based on the analysis results.

[0695] The "material recommendation means" is a system that has the function of recommending online materials and resources that are appropriate for the student's learning situation.

[0696] The "similar question generation means" is a system that has the function of automatically generating similar questions based on the examinee's weak areas.

[0697] A "generative AI model" is a technology that uses generative artificial intelligence to generate content and feedback.

[0698] The "scoring and analysis means" is a system that has the functionality to use a generative AI model to score and analyze test takers' answers.

[0699] The "recommendation method" is a system that has the function of recommending the most suitable online learning materials based on the student's learning progress.

[0700] This invention is a system that efficiently supports test takers in studying for exams by using generative artificial intelligence (generative AI model). The system includes the following means.

[0701] User Interface Means

[0702] The user accesses the system from a terminal and enters the school of choice, exam subjects, and basic information (name, email address, etc.), which completes the initial registration.

[0703] Test question generation means

[0704] The server automatically generates appropriate test questions using a generative AI model based on the user's desired school information and exam subjects. The generated questions are sent to the user's device, where they can be viewed and answered.

[0705] Analysis means

[0706] When a user completes a mock test and submits their answers, the server receives the answer data and automatically scores and analyzes it using a generative AI model, revealing the score for each subject, the percentage of correct answers, and areas of weakness.

[0707] Answer explanation method

[0708] Based on the analysis results, the server generates detailed explanations for the questions that the user got wrong, providing step-by-step instructions on how to solve the problem. This explanation data is then sent to the user's device for viewing.

[0709] Teaching material recommendation method

[0710] The server recommends optimal online learning materials and resources based on the analysis results and the user's learning progress, allowing the user to study efficiently.

[0711] Similar problem generation means

[0712] If a user has difficulty with a particular problem, the server automatically generates similar problems related to that problem using a generative AI model. These similar problems are sent to the device, and the user can answer them as training.

[0713] Scoring and analysis methods

[0714] It uses a generative AI model to grade and analyze test-taker answer data, and provides detailed feedback on users' scores, accuracy rates, and weak areas based on the analysis results.

[0715] Recommendation method

[0716] Based on the analysis results and the user's learning progress, the system recommends the most suitable online learning materials, allowing users to study efficiently.

[0717] Specific examples

[0718] For example, a user logs into the system and enters "ABC University" as their preferred school and "Mathematics, English, and Physics" as their exam subjects. The server then uses a generative AI model to automatically generate mock exams for mathematics, English, and physics based on past exam information and data on successful candidates, and sends them to the device. When the user completes the mock exam and submits their answers, the server immediately analyzes the answers and provides detailed feedback and explanations. Based on the analysis results, the server determines that the user has particular weaknesses in English grammar and recommends specialized grammar questions and explanatory videos. Furthermore, it generates similar questions related to English grammar that the user can use for review.

[0719] Prompt Sentence Examples

[0720] "Generate practice math exam questions to help me get into ABC University."

[0721] "Generate an explanation for the English grammar question based on this answer."

[0722] To implement this system, we need to build a generative AI model using the OpenAI API, manage communication between the server and the device using a web application framework such as Flask, and build a comprehensive system, including designing the database and user interface.

[0723] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[0724] Step 1:

[0725] Initial registration

[0726] Input: The user inputs the school of choice, exam subjects, and basic information (name, email address, etc.) on the terminal.

[0727] Processing: The terminal sends the input data to the server.

[0728] Data processing: The server stores the received data in a database and performs any necessary preprocessing.

[0729] Output: The server sends a confirmation message to the terminal indicating that registration is complete.

[0730] Action: The user reconfirms the registration details on the terminal and receives a completion message.

[0731] Step 2:

[0732] Automatic generation of exam questions

[0733] Input: The server references the desired school information and exam subject data entered by the user.

[0734] Processing: The generative AI model is instructed to generate exam questions based on the student's desired school and exam subjects.

[0735] Data processing: A generative AI model generates test questions and structures the data.

[0736] Output: Send the created test questions to the terminal.

[0737] Operation: The user receives and views the generated test questions on the terminal.

[0738] Step 3:

[0739] Mock test answers and submission

[0740] Input: The user answers the practice questions on the terminal and sends the answer data after completion.

[0741] Processing: The terminal sends the answer data to the server.

[0742] Data processing: The server preprocesses the received answer data and formats it for analysis.

[0743] Output: A transmission confirmation message is displayed on the user's terminal.

[0744] Action: The user sees the delivery confirmation message.

[0745] Step 4:

[0746] Answer scoring and analysis

[0747] Input: The server uses the answer data received from the user.

[0748] Processing: Answers are graded and analyzed using a generative AI model.

[0749] Data processing: Extract scores for each subject, correct answer rate, weak areas and weaknesses, and generate analysis results.

[0750] Output: Sends the analysis results to the user's terminal and displays detailed explanations.

[0751] How it works: The user views the analysis results and explanations on their device.

[0752] Step 5:

[0753] Recommendation of teaching materials

[0754] Input: The server uses the analysis results and the user's learning progress data.

[0755] Processing: Using generative AI models to select the best online learning materials and resources.

[0756] Data processing: Format appropriate teaching material information and display it to the user as appropriate.

[0757] Output: Send recommended teaching material information to the terminal.

[0758] How it works: The user checks the recommended learning materials on their device and proceeds with their studies.

[0759] Step 6:

[0760] Generating and providing similar questions

[0761] Input: The server uses the user's weakness data.

[0762] Processing: Use a generative AI model to generate similar questions related to weak areas.

[0763] Data processing: The generated similar problem data is formatted and provided to the user.

[0764] Output: Similar problems are sent to the user's terminal.

[0765] How it works: Users view similar questions on their device and use them for training.

[0766] As a concrete example, if a user inputs "ABC University" as the school of choice and "Mathematics, English, and Physics" as the subjects to be tested, the server will use this information to generate test questions using a generative AI model. The generated test questions are sent to the user's device, and the user answers and submits them. The server analyzes the received answers and provides detailed feedback. Based on the analysis results, suitable study materials and similar questions are also recommended to the user.

[0767] Prompt Sentence Examples

[0768] "Generate practice math exam questions to help me get into ABC University."

[0769] "Generate an explanation for the English grammar question based on this answer."

[0770] Furthermore, an emotion engine that estimates the user's emotion may be further combined. That is, the identification processing unit 290 may estimate the user's emotion using the emotion identification model 59, and perform identification processing using the user's emotion.

[0771] The present invention is a system that efficiently supports test takers in studying for exams by utilizing generative artificial intelligence and an emotion engine. This system includes a user interface means for inputting the user's desired school information and basic information, an exam question generation means for automatically generating exam questions, an analysis means for analyzing mock exam results, an answer explanation means for providing explanations based on the analysis results, a study material recommendation means for recommending appropriate study materials, a similar question generation means for generating similar questions based on weak areas, and an emotion engine for recognizing the user's emotions.

[0772] User Interface Means

[0773] Users access this system and enter their desired school, exam subjects, and basic information (name, email address, etc.), which completes the initial registration.

[0774] Test question generation means

[0775] The server uses AI to automatically generate appropriate exam questions based on the user's desired school information and exam subjects. The generated questions are sent to the user's device, where they can be viewed and answered.

[0776] Analysis means

[0777] When a user completes a mock test and submits their answers, the server receives the answer data and automatically scores and analyzes it using generative AI, which clarifies the score for each subject, the percentage of correct answers, and weak areas and weaknesses.

[0778] Answer explanation method

[0779] Based on the analysis results, the server generates detailed explanations for the questions that the user got wrong, providing step-by-step instructions on how to solve the problem. This explanation data is then sent to the user's device for viewing.

[0780] Teaching material recommendation method

[0781] The server recommends optimal online learning materials and resources based on the analysis results and the user's learning progress, allowing the user to study efficiently.

[0782] Similar problem generation means

[0783] If a user has difficulty with a particular problem, the server automatically generates similar problems related to that problem using a generation AI. These similar problems are sent to the device, and the user can answer them as training.

[0784] Emotion Engine

[0785] The emotion engine collects the user's facial expression recognition data and analyzes the user's emotional state during learning. For example, when the user sends their facial expression to the system through the camera, the server uses the emotion engine to analyze the facial expression and identify the emotional state that will affect the learning progress.

[0786] Emotion-based feedback

[0787] The server generates feedback based on the user's emotional state based on the results of analysis using the emotion engine. For example, if the user is feeling stressed, it will provide appropriate study advice or relaxation techniques. It also dynamically adjusts learning materials and learning approaches based on the user's emotional state to maximize learning efficiency.

[0788] Specific examples

[0789] A user logs into the system and enters "XYZ University" as their preferred school and "Mathematics, English, and Physics" as their exam subjects. The server then uses generative AI to automatically generate mock exams for mathematics, English, and physics based on past exam information and data on successful candidates, and sends them to the device. When the user completes the mock exam and submits their answers, the server immediately analyzes the answers and provides detailed feedback and explanations.

[0790] Based on the analysis results, the server determines that the user has particular weaknesses in English grammar and recommends grammar questions and explanatory videos specific to that area. It also generates similar questions related to English grammar for the user to use for review.

[0791] At the same time, the user's facial expression data is sent to the system and analyzed by the server's emotion engine. For example, if the user shows a confused expression while answering a question, the server will detect that emotional state and provide an encouraging message or advice on how to relax.

[0792] In this way, this system combines generative artificial intelligence and an emotion engine to efficiently provide learning support optimized for each test-taker's individual situation and emotions.

[0793] The processing flow will be explained below.

[0794] Processing steps of the invention combined with emotion engine

[0795] User Registration Process

[0796] Step 1:

[0797] A user accesses the system and opens a login or registration form.

[0798] Step 2:

[0799] The user enters basic information such as the school of choice, exam subjects, name, and email address.

[0800] Step 3:

[0801] The terminal transmits the input information to the server.

[0802] Step 4:

[0803] The server stores the received information in a database.

[0804] Step 5:

[0805] The server generates a registration success message and sends it to the terminal.

[0806] Step 6:

[0807] The terminal displays a registration success message to the user.

[0808] Automatic generation process for mock exams

[0809] Step 1:

[0810] The user selects "Take a Practice Exam" from the dashboard.

[0811] Step 2:

[0812] The terminal sends a request to generate a mock test to the server.

[0813] Step 3:

[0814] The server references data based on the user's desired school and exam subjects, and uses a generation AI to generate mock exam questions.

[0815] Step 4:

[0816] The server stores the generated mock test questions in a database and sends them to the terminal.

[0817] Step 5:

[0818] The terminal displays the practice questions to the user and provides an answer input form.

[0819] Test result analysis process

[0820] Step 1:

[0821] The user completes the practice test and clicks the "Submit" button.

[0822] Step 2:

[0823] The terminal sends the answer data to the server.

[0824] Step 3:

[0825] The server receives the answer data and automatically scores and analyzes it using the generating AI.

[0826] Step 4:

[0827] The server calculates the score for each subject, the percentage of correct answers, and weak areas, and generates detailed feedback.

[0828] Step 5:

[0829] The server sends the analysis results and feedback to the device.

[0830] Step 6:

[0831] The device displays the feedback to the user.

[0832] Answer explanation process

[0833] Step 1:

[0834] If the user reviews the feedback and needs a detailed explanation of the incorrect question, they can click the "Show Explanation" button.

[0835] Step 2:

[0836] The device sends a description request to the server.

[0837] Step 3:

[0838] The server uses a generative AI to generate the answer process for the incorrect question and creates an explanatory text.

[0839] Step 4:

[0840] The server transmits the generated commentary data to the terminal.

[0841] Step 5:

[0842] The terminal displays the explanation to the user.

[0843] Online Material Recommendation Process

[0844] Step 1:

[0845] After the user checks the feedback, they select "View online learning materials."

[0846] Step 2:

[0847] The terminal sends a learning material request to the server.

[0848] Step 3:

[0849] The server uses AI to recommend optimal learning materials based on the user's learning progress data.

[0850] Step 4:

[0851] The server transmits the recommended teaching material information to the terminal.

[0852] Step 5:

[0853] The device displays the recommended learning materials to the user.

[0854] Similar problem generation process

[0855] Step 1:

[0856] The user selects "Generate similar questions."

[0857] Step 2:

[0858] The device sends a request to the server.

[0859] Step 3:

[0860] The server automatically generates similar questions using AI based on the user's weak areas.

[0861] Step 4:

[0862] The server sends the generated similar questions to the terminal.

[0863] Step 5:

[0864] The terminal displays similar questions to the user and provides an answer form.

[0865] Emotion Engine Process

[0866] Step 1:

[0867] During training, the user sends emotional data (e.g., facial expressions and tone of voice) to the system via a camera or microphone.

[0868] Step 2:

[0869] The device transmits the collected emotion data to a server.

[0870] Step 3:

[0871] The server uses an emotion engine to analyze the emotion data and identify the current emotional state (e.g., stress, confusion, concentration).

[0872] Step 4:

[0873] The server generates optimal feedback and learning advice based on the emotional state.

[0874] Step 5:

[0875] The server transmits the generated feedback to the terminal.

[0876] Step 6:

[0877] The device displays emotion-based feedback and advice to the user.

[0878] Specific examples

[0879] A user logs into the system and enters "XYZ University" as their preferred school and "Mathematics, English, and Physics" as their exam subjects. The server then uses generative AI to automatically generate mock exams for mathematics, English, and physics based on past exam information and data on successful candidates, and sends them to the device. When the user completes the mock exam and submits their answers, the server immediately analyzes the answers and provides detailed feedback and explanations.

[0880] Based on the analysis results, the server determines that the user has particular weaknesses in English grammar and recommends grammar questions and explanatory videos specific to that area. It also generates similar questions related to English grammar for the user to use for review.

[0881] While the user is learning, the server monitors the user's facial expressions via a camera, and if it detects a confused expression, the emotion engine analyzes that state. As a result of the analysis, the server determines that the user is feeling stressed and provides an encouraging message or advice on how to relax. For example, a message such as "Take a deep breath and relax. Next, I'll introduce some ways to relax" is displayed.

[0882] In this way, this system combines generative artificial intelligence and an emotion engine to efficiently provide learning support optimized for each test-taker's individual situation and emotions.

[0883] Example 2

[0884] Next, a description will be given of Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the smart glasses 214 will be referred to as a "terminal."

[0885] Conventional exam study support systems lack personalized learning support tailored to each student's learning progress and areas of weakness, making it difficult for them to study efficiently. Furthermore, they do not provide appropriate feedback that takes into account the student's emotional state, making it difficult for them to maintain their motivation to study and often causing stress.

[0886] The specific processing by the specific processing unit 290 of the data processing device 12 in the second embodiment is realized by the following means.

[0887] In this invention, the server includes user interface means for inputting the examinee's desired school and basic information, test question generation means for automatically generating test questions based on the examinee's desired school information, analysis means for analyzing the mock test results answered by the examinee and visualizing weak areas and areas of weakness, answer explanation means for generating and displaying explanations based on the analysis results, learning material recommendation means for recommending online learning materials suited to the examinee's learning situation, similar question generation means for automatically generating similar questions based on the examinee's weak areas, emotion recognition means for recognizing and analyzing the examinee's emotional state, and emotion feedback means for providing feedback based on the emotion recognition results. This enables efficient and personalized learning support according to the learning situation and emotional state of each examinee.

[0888] "Generative artificial intelligence" refers to sophisticated algorithms that automatically generate information and data based on user input and prompts.

[0889] "Exam taker" refers to an individual studying for a particular exam or entrance examination.

[0890] "User interface means" refers to the interactive input means by which examinees input their preferred schools and basic information into the system.

[0891] "Exam question generation means" refers to a system function that automatically generates appropriate exam questions based on the desired school information and exam subjects entered by the examinee.

[0892] "Analysis means" refers to the system function that analyzes the mock test results given by test takers and clarifies their weak areas and weaknesses.

[0893] The "answer explanation means" refers to a function that generates and displays detailed explanations, especially for incorrect questions, based on the analysis results.

[0894] "Materials recommendation means" refers to the system function that recommends the most appropriate online materials and resources based on the candidate's learning progress and analysis results.

[0895] "Similar question generation means" refers to a function that automatically generates similar questions related to the examinee's weak areas.

[0896] "Emotion recognition means" refers to a function that analyzes the examinee's facial expressions and behavior to identify their current emotional state.

[0897] "Emotion feedback means" refers to a system function that provides appropriate feedback to test takers based on emotion recognition results.

[0898] The present invention is a system that efficiently supports test takers in studying for exams by utilizing generative artificial intelligence and an emotion engine. The system includes a user interface, test question generation, analysis, answer explanation, learning material recommendation, similar question generation, emotion recognition, and emotion feedback.

[0899] Users access the system and perform initial registration by entering their desired school, exam subjects, and basic information (name, email address, etc.). At this time, the information entered by the user is sent to the server and stored in a database.

[0900] The server automatically generates appropriate exam questions using a generative AI model based on the user's desired school information and exam subjects. The generated exam questions are sent to the device so that the user can view and answer them. Specifically, the server uses a generative AI model (e.g., GPT-4) to process data using Python scripts and MongoDB.

[0901] When a user completes a mock test and submits their answers, the server receives the answer data and automatically scores and analyzes it using a generative AI model. This results in clear scores for each subject, the percentage of correct answers, and areas of weakness. Scikit-learn and PostgreSQL are used for this analysis.

[0902] Based on the analysis results, the server generates detailed explanations for questions where the student got the answer wrong. The explanation data is sent to the device and can be viewed by the user. This explanation generation also uses a generative AI model and API communication (REST).

[0903] The server recommends the most suitable online learning materials and resources based on the analysis results and the user's learning progress. This is done using a recommendation engine (e.g., TensorFlow) and Elasticsearch. The recommended learning materials help the user progress efficiently.

[0904] If a user has difficulty with a particular problem, the server automatically generates similar problems related to that problem using a generative AI model. These similar problems are sent to the device and the user can use them for review. At this stage, a NoSQL database such as Firebase is used.

[0905] Furthermore, the user's facial expression data is analyzed using an emotion recognition means. When the user transmits their facial expressions through the camera while studying, the server analyzes the expressions using an emotion engine (e.g., Azure Face API) and generates useful feedback for the user's progress. This feedback may include encouraging messages or suggestions for relaxation techniques depending on the user's emotional state.

[0906] As a specific example, a user logs into the system, sets "ABC University" as their preferred school, and enters "Mathematics, English, and Physics" as their exam subjects. Based on this, the server uses past exam data and data on the trends of successful candidates to automatically generate mock exams for mathematics, English, and physics using generative AI. This mock exam data is sent to the device, and the user takes the mock exam and submits their answers after completing it. The server immediately analyzes the answers and provides detailed feedback and explanations. For example, it might recommend "videos explaining English grammar questions" or "similar questions specialized in grammar." Additionally, if the user's facial expressions during study indicate difficulty or stress, the server will provide advice and messages based on that.

[0907] Examples of prompts include:

[0908] "Please generate mock exams for Mathematics, English, and Physics for ABC University."

[0909] "Analyze users' practice test results and provide feedback with special emphasis on the area of ​​English grammar."

[0910] "Analyze facial expression data sent by the user using a camera and suggest relaxation methods when the user is feeling stressed."

[0911] In this way, the present invention combines generative artificial intelligence and an emotion engine to efficiently provide optimal learning support tailored to the individual circumstances and emotions of each test-taker.

[0912] The flow of the identification process in the second embodiment will be described with reference to FIG.

[0913] Step 1:

[0914] Initial registration

[0915] Users access the system and enter their desired school, exam subjects, and basic information (name, email address, etc.).

[0916] Input: desired school information, exam subject information, basic information (name, email address)

[0917] Output: Save to user profile database

[0918] Specific operation: A form is displayed on the user interface, and the user enters the school of choice and exam subjects and presses the submit button. The submitted data is transferred to the server and stored in a database. This process uses HTML forms, JavaScript, Python, and Django.

[0919] Step 2:

[0920] Automatic generation of exam questions

[0921] The server automatically generates appropriate exam questions using a generative AI model based on the desired school information and exam subjects entered by the user.

[0922] Input: desired school information, exam subject information

[0923] Output: Generated test question data

[0924] Specific operation: The server retrieves information about the school of choice and exam subjects from the user database and sends them as prompts to the generative AI model. The generative AI generates exam questions and returns them to the server. The server then sends the generated exam questions to the device. This process uses a generative AI model (e.g., GPT-4), Python scripts, and a database (MongoDB).

[0925] Step 3:

[0926] Mock exams and answer submission

[0927] The generated test questions are sent to the terminal, and the user takes the test. After completing the test, the answers are sent to the server.

[0928] Input: Generated test questions, user answer data

[0929] Output: Send answer data to the server

[0930] Specific operation: The test questions are displayed on the device, and when the user enters the answers and presses the submit button, the answer data is sent to the server. This process is done using React.js and Node.js.

[0931] Step 4:

[0932] Scoring and Analysis

[0933] The server receives the submitted answer data and automatically scores and analyzes it using a generative AI model.

[0934] Input: User's answer data

[0935] Output: Analysis results for each subject, score, correct answer rate, weak areas and weaknesses

[0936] How it works: The server passes the answer data to the analysis engine, which determines whether each question is correct or not. It also scores the answers and identifies areas where the user is weak. Scikit-learn and PostgreSQL are used for this analysis.

[0937] Step 5:

[0938] Providing answer explanations

[0939] Based on the analysis results, the server generates detailed explanations for the incorrect questions, and the explanation data is sent to the terminal for the user to view.

[0940] Input: Analysis results

[0941] Output: Detailed explanatory data

[0942] Specific operation: Based on the analysis results, the server sends prompts to the generative AI model to generate detailed explanations, which are then sent to the device. This process uses the generative AI model and API communication (REST).

[0943] Step 6:

[0944] Recommendation of teaching materials

[0945] The server recommends the most appropriate online learning materials and resources based on the analysis results and the user's learning progress.

[0946] Input: Analysis results, learning history

[0947] Output: Recommended online learning materials and resources

[0948] Specific operation: The server refers to the analysis results database, checks the user's past learning history and progress, selects appropriate learning materials, and notifies the user. This process uses a recommendation engine (TensorFlow) and Elasticsearch.

[0949] Step 7:

[0950] Generating similar problems

[0951] If a user feels uncomfortable with a particular problem, the server automatically generates similar problems related to that problem using a generative AI model.

[0952] Input: Weakness data

[0953] Output: Generated similar problem data

[0954] Specific operation: The server sends data on weak areas to the generative AI model as prompts, which generate similar questions. These are then sent to the device. This process uses the generative AI model and a NoSQL database such as Firebase.

[0955] Step 8:

[0956] Emotional Recognition and Feedback

[0957] The emotion engine collects the user's facial expression data and analyzes the user's emotional state during training. The server generates feedback based on the results and sends it to the device.

[0958] Input: User's facial expression data

[0959] Output: Sentiment analysis results, feedback data

[0960] Specific operation: Facial expression data collected through the camera is passed to the emotion engine, and the analysis results are obtained. The server generates appropriate feedback based on these results and sends it to the device. This process uses an emotion recognition API (e.g., Azure Face API) and a real-time database (Firebase).

[0961] (Application example 2)

[0962] Next, a description will be given of Application Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the smart glasses 214 will be referred to as a "terminal."

[0963] Conventional test-taking support systems have limited functionality for analyzing test-takers' learning progress and weak areas, making them unable to adequately address individual learning needs. Furthermore, they provide uniform feedback without taking test-takers' emotional state into consideration, making it difficult to provide effective learning support. Furthermore, they are unable to recommend optimal products and services in real time, limiting their ability to improve customer experience in physical stores. The present invention aims to solve these problems.

[0964] The specific processing by the specific processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means. In this invention, the server includes a user interface means for inputting the examinee's desired school and basic information, a test question generation means for automatically generating test questions based on the examinee's desired school information, an analysis means for analyzing the mock test results answered by the examinee and visualizing the examinee's weak areas and areas of weakness, an answer explanation means for generating and displaying explanations based on the analysis results, a learning material recommendation means for recommending online learning materials suited to the examinee's learning situation, a similar question generation means for automatically generating similar questions based on the examinee's weak areas, an emotion analysis means for collecting customer facial expression recognition data and analyzing the emotional state, and a feedback means for providing feedback according to the emotional state. This enables efficient learning support tailored to individual learning needs and further improves customer experience by recommending optimal products and services in real time.

[0965] "Candidate" refers to any student studying or individual taking an examination.

[0966] "User interface means" refers to the interface through which prospective students and customers input basic information and information about their preferred schools.

[0967] "Exam question generation means" refers to a function that automatically creates exam questions based on information input by examinees.

[0968] "Analysis means" refers to the function that analyzes the mock test results submitted by test takers and analyzes weak areas and correct answer rates.

[0969] "Answer explanation means" refers to a function that provides explanations based on an analysis of mock test results to encourage understanding among test takers.

[0970] "Material recommendation means" refers to a function that recommends optimal learning resources and materials based on the test-taker's learning situation and areas of weakness.

[0971] "Similar problem generation means" refers to a function that automatically generates similar problems related to problems that are difficult to solve.

[0972] "Emotion analysis means" refers to the function of analyzing facial expressions and behavioral data of test takers and customers to analyze their emotional state.

[0973] "Feedback means" refers to the function of providing appropriate feedback or encouraging messages based on the results of sentiment analysis.

[0974] The present invention is a system that efficiently supports test takers and customers of brick-and-mortar stores by utilizing generative artificial intelligence and an emotion engine. Each means of the system will be specifically described below.

[0975] User Interface Means

[0976] Users access the system and input their desired school, exam subjects, basic information (name, email address, etc.) or customer information (name, preferred product category, etc.). This information is stored by the server and becomes the basic data for responding to the individual needs of the user.

[0977] Test question generation means

[0978] Based on the student's desired school information and exam subjects, the server uses AI to automatically generate appropriate exam questions. The generated questions are sent to the device, where the user can view and answer them.

[0979] Analysis means

[0980] When a user completes a mock test and submits their answers, the server receives the answer data and automatically scores and analyzes it using generative AI, which clarifies the score for each subject, the percentage of correct answers, and weak areas and weaknesses.

[0981] Answer explanation method

[0982] Based on the analysis results, the server generates detailed explanations for the questions that the user got wrong, providing step-by-step instructions on how to solve the problem. This explanation data is then sent to the user's device for viewing.

[0983] Teaching material recommendation method

[0984] The server recommends optimal online learning materials and resources based on the analysis results and the user's learning progress, allowing the user to study efficiently.

[0985] Similar problem generation means

[0986] If a user has difficulty with a particular problem, the server automatically generates similar problems related to that problem using a generation AI. These similar problems are sent to the device, and the user can answer them as training.

[0987] Emotion analysis means

[0988] The server collects facial expression data from the user through the camera and uses the emotion engine to analyze the user's emotional state during learning. For example, when the user looks at the camera, the server uses the emotion engine to analyze the user's facial expression and identify the emotional state that will affect the user's learning progress.

[0989] Feedback Methods

[0990] Based on the results of emotion analysis, the server generates feedback according to the user's emotional state. For example, if the user is confused, it will display relaxation advice or encouraging messages. It also improves the customer experience by recommending optimal products and services based on the results of analyzing customers' facial expressions in the store.

[0991] Specific examples

[0992] 1. A user logs into the system and enters "ABC University" as their preferred school and "Mathematics, English, and Physics" as their exam subjects. The server then uses AI to automatically generate mock exams for mathematics, English, and physics based on past exam information and data on successful candidates, and sends them to the device.

[0993] 2. Once a user completes a mock test and submits their answers, the server instantly analyzes the answers and provides detailed feedback and explanations. Based on the analysis results, the server determines that the user has particular weaknesses in English grammar and recommends grammar questions and explanatory videos specific to that area. Furthermore, the server generates similar questions related to English grammar for the user to review.

[0994] 3. The user's facial expression data is sent to the system via the camera and analyzed by the server's emotion engine. For example, if the user shows a confused expression while answering a question, the server will detect that emotional state and provide an encouraging message or advice on how to relax.

[0995] 4. Even in physical stores, when customers send facial expression data via camera, it is analyzed by the emotion engine and the most suitable products and promotions are recommended in real time.

[0996] Prompt Sentence Examples

[0997] "Use your emotion engine to provide optimal product recommendations when customers are confused."

[0998] "Implement a product recommendation algorithm based on historical purchase data and real-time sentiment analysis."

[0999] In this way, the system combines generative artificial intelligence and an emotion engine to efficiently provide support optimized for the individual situations and emotions of test takers and customers in brick-and-mortar stores.

[1000] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[1001] Step 1:

[1002] The user accesses the system and inputs the school of choice, exam subjects, basic information (name, email address, etc.), or customer information (name, preferred product category, etc.) through the user interface. The input information is sent to the server and saved in the database. This completes the initial setup based on the user's individual needs. The input data is processed by checking the format of each item and saving it as the appropriate data type.

[1003] Step 2:

[1004] Based on the examinee's desired school information and exam subjects, the server uses a generative AI model to automatically generate appropriate exam questions. The generated questions are sent to the terminal so that the user can view and answer them. In this step, prompts are generated based on the user's input data, and the AI ​​model generates questions accordingly.

[1005] Step 3:

[1006] Users answer mock exam questions and send the answer data to the server. The server uses a generative AI model to automatically score the test-taker's answers and analyzes the score for each subject, the percentage of correct answers, and weak areas and weaknesses. The input data is the user's answer data, and the output data is a report of the analysis results.

[1007] Step 4:

[1008] Based on the analysis results, the server generates detailed explanations for the incorrect answers, which are then sent to the device for viewing by the user. Based on the analysis data, prompts are generated, and the AI ​​model then creates explanations accordingly.

[1009] Step 5:

[1010] The server recommends the most suitable online learning materials and resources based on the user's analysis results and learning progress. The recommended learning materials are notified to the user's device, where they can be viewed and used. Based on the analysis results, the server searches for and recommends the most suitable learning materials from a database of related learning materials.

[1011] Step 6:

[1012] If a user has difficulty with a particular problem, the server automatically generates similar problems related to that problem using a generative AI model. The generated similar problems are sent to the device, where the user can solve them for training. Using the user's answer data and analysis results as input, a prompt to generate similar problems is created and the problems are generated by the AI ​​model.

[1013] Step 7:

[1014] The user's facial expression data is collected through the camera and sent to the server. The server uses an emotion analysis engine to analyze the user's emotional state during training. This data is the user's facial expression data, and the emotional state is output as the analysis result. Analysis is performed in real time based on the emotional data.

[1015] Step 8:

[1016] Based on the results of the emotion analysis, the server generates feedback according to the user's emotional state. For example, if the user is confused, the server sends an encouraging message or advice to relax to the device, thereby supporting the user's mental state. The server uses the emotional state data as input and generates an appropriate feedback message.

[1017] Step 9:

[1018] In physical stores, customer facial expression data is collected and sent to a server. The server uses an emotion analysis engine to analyze the customer's emotions in real time. Based on the analyzed emotion data, the system recommends the most appropriate products and services. For example, if a customer is confused, corresponding products will be displayed on the smart device. Emotional state data is used to generate prompts and recommend products using an AI model.

[1019] In this way, the system effectively utilizes generative AI models and emotion engines at each step to provide advanced assistance to test takers and brick-and-mortar customers.

[1020] The specific processing unit 290 transmits the result of the specific processing to the smart glasses 214. In the smart glasses 214, the control unit 46A causes the speaker 240 to output the result of the specific processing. The microphone 238 acquires audio indicating a user input regarding the result of the specific processing. The control unit 46A transmits audio data indicating the user input acquired by the microphone 238 to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the audio data.

[1021] The data generation model 58 is a so-called generative AI (Artificial Intelligence). An example of the data generation model 58 is ChatGPT (Internet Search<URL: https: / / openai.com / blog / chatgpt> ), Gemini (Internet search <url: https: gemini.google.com ?hl="ja">) and other generation AIs. The data generation model 58 is obtained by performing deep learning on a neural network. A prompt including an instruction is input to the data generation model 58, and inference data such as voice data indicating voice, text data indicating text, and image data indicating an image is also input. The data generation model 58 performs inference on the input inference data in accordance with the instruction indicated by the prompt, and outputs the inference result in a data format such as voice data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[1022] In the above embodiment, an example in which the specific processing is performed by the data processing device 12 has been given, but the technology of the present disclosure is not limited to this, and the specific processing may be performed by the smart glasses 214.

[1023] [Third embodiment]

[1024] FIG. 5 shows an example of the configuration of a data processing system 310 according to the third embodiment.

[1025] 5, the data processing system 310 includes the data processing device 12 and a headset terminal 314. An example of the data processing device 12 is a server.

[1026] The data processing device 12 includes a computer 22, a database 24, and a communication I / F 26. The computer 22 is an example of a "computer" according to the technology of the present disclosure. The computer 22 includes a processor 28, a RAM 30, and a storage 32. The processor 28, the RAM 30, and the storage 32 are connected to a bus 34. The database 24 and the communication I / F 26 are also connected to the bus 34. The communication I / F 26 is connected to a network 54. Examples of the network 54 include a WAN (Wide Area Network) and / or a LAN (Local Area Network).

[1027] The headset type terminal 314 includes a computer 36, a microphone 238, a speaker 240, a camera 42, a communication I / F 44, and a display 343. The computer 36 includes a processor 46, a RAM 48, and a storage 50. The processor 46, the RAM 48, and the storage 50 are connected to a bus 52. The microphone 238, the speaker 240, the camera 42, and the display 343 are also connected to the bus 52.

[1028] The microphone 238 receives instructions and the like from the user 20 by receiving voice uttered by the user 20. The microphone 238 captures the voice uttered by the user 20, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio in accordance with instructions from the processor 46.

[1029] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an imaging element such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, and captures images of the surroundings of user 20 (for example, an imaging range defined by an angle of view equivalent to the field of vision of a typical healthy person).

[1030] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 are responsible for the exchange of various information between the processor 46 and the processor 28 via the network 54. The exchange of various information between the processor 46 and the processor 28 using the communication I / Fs 44 and 26 is carried out in a secure state.

[1031] Fig. 6 shows an example of the main functions of the data processing device 12 and the headset type terminal 314. As shown in Fig. 6, in the data processing device 12, a specific process is performed by the processor 28. A specific process program 56 is stored in the storage 32.

[1032] The specific processing program 56 is an example of a "program" according to the technology of the present disclosure. The processor 28 reads the specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific processing is realized by the processor 28 operating as a specific processing unit 290 in accordance with the specific processing program 56 executed on the RAM 30.

[1033] The storage 32 stores a data generation model 58 and an emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290.

[1034] In the headset type terminal 314, a reception output process is performed by the processor 46. A reception output program 60 is stored in the storage 50. The processor 46 reads the reception output program 60 from the storage 50 and executes the read reception output program 60 on the RAM 48. The reception output process is realized by the processor 46 operating as the control unit 46A in accordance with the reception output program 60 executed on the RAM 48.

[1035] Next, a description will be given of the identification process performed by the identification processing unit 290 of the data processing device 12. In the following description, the data processing device 12 will be referred to as the "server" and the headset type terminal 314 will be referred to as the "terminal."

[1036] The present invention is a system that efficiently supports test takers in studying for exams using generative artificial intelligence. This system includes a user interface means for inputting the user's desired school information and basic information, a test question generation means for automatically generating test questions, an analysis means for analyzing mock test results, an answer explanation means for providing explanations based on the analysis results, a learning material recommendation means for recommending appropriate learning materials, and a similar question generation means for generating similar questions based on weak areas.

[1037] User Interface Means

[1038] Users access this system and enter their desired school, exam subjects, and basic information (name, email address, etc.), which completes the initial registration.

[1039] Test question generation means

[1040] The server uses AI to automatically generate appropriate exam questions based on the user's desired school information and exam subjects. The generated questions are sent to the user's device, where they can be viewed and answered.

[1041] Analysis means

[1042] When a user completes a mock test and submits their answers, the server receives the answer data and automatically scores and analyzes it using generative AI, which clarifies the score for each subject, the percentage of correct answers, and weak areas and weaknesses.

[1043] Answer explanation method

[1044] Based on the analysis results, the server generates detailed explanations for the questions that the user got wrong, providing step-by-step instructions on how to solve the problem. This explanation data is then sent to the user's device for viewing.

[1045] Teaching material recommendation method

[1046] The server recommends optimal online learning materials and resources based on the analysis results and the user's learning progress, allowing the user to study efficiently.

[1047] Similar problem generation means

[1048] If a user has difficulty with a particular problem, the server automatically generates similar problems related to that problem using a generation AI. These similar problems are sent to the device, and the user can answer them as training.

[1049] Statistical analysis and comparison tools

[1050] This system has the ability to statistically analyze accumulated test-taker data. This data is provided to educational institutions and companies, supporting strategic data utilization in the field of education. Furthermore, by performing comparative analysis with past test-taker data, it is possible to provide more specific feedback to users.

[1051] Specific examples

[1052] A user logs into the system and enters "XYZ University" as their preferred school and "Mathematics, English, and Physics" as their exam subjects. The server then uses generative AI to automatically generate mock exams for mathematics, English, and physics based on past exam information and data on successful candidates, and sends them to the device. When the user completes the mock exam and submits their answers, the server immediately analyzes the answers and provides detailed feedback and explanations. Based on the analysis results, the server determines that the user has particular weaknesses in English grammar and recommends specialized grammar questions and explanatory videos. Furthermore, the server generates similar questions related to English grammar that the user can use for review.

[1053] In this way, the system efficiently provides learning support that is optimized for each examinee's individual situation.

[1054] The processing flow will be explained below.

[1055] User Registration Process

[1056] Step 1:

[1057] A user accesses the system and opens a login or registration form.

[1058] Step 2:

[1059] The user enters basic information such as the school of choice, exam subjects, name, and email address.

[1060] Step 3:

[1061] The terminal transmits the input information to the server.

[1062] Step 4:

[1063] The server stores the received information in a database.

[1064] Step 5:

[1065] The server generates a registration success message and sends it to the terminal.

[1066] Step 6:

[1067] The terminal displays a registration success message to the user.

[1068] Automatic generation process for mock exams

[1069] Step 1:

[1070] The user selects "Take a Practice Exam" from the dashboard.

[1071] Step 2:

[1072] The terminal sends a request to generate a mock test to the server.

[1073] Step 3:

[1074] The server references data based on the user's desired school and exam subjects, and uses a generation AI to generate mock exam questions.

[1075] Step 4:

[1076] The server stores the generated mock test questions in a database and sends them to the terminal.

[1077] Step 5:

[1078] The terminal displays the practice questions to the user and provides an answer input form.

[1079] Test result analysis process

[1080] Step 1:

[1081] The user completes the practice test and clicks the "Submit" button.

[1082] Step 2:

[1083] The terminal sends the answer data to the server.

[1084] Step 3:

[1085] The server receives the answer data and automatically scores and analyzes it using the generating AI.

[1086] Step 4:

[1087] The server calculates the score, accuracy rate, and weak areas for each subject and generates detailed feedback.

[1088] Step 5:

[1089] The server sends the analysis results and feedback to the device.

[1090] Step 6:

[1091] The device displays the feedback to the user.

[1092] Answer explanation process

[1093] Step 1:

[1094] If the user reviews the feedback and needs a detailed explanation of the incorrect question, they can click the "Show Explanation" button.

[1095] Step 2:

[1096] The device sends a description request to the server.

[1097] Step 3:

[1098] The server uses a generative AI to generate the answer process for the incorrect question and creates an explanatory text.

[1099] Step 4:

[1100] The server transmits the generated commentary data to the terminal.

[1101] Step 5:

[1102] The terminal displays the explanation to the user.

[1103] Online Material Recommendation Process

[1104] Step 1:

[1105] After the user checks the feedback, they select "View online learning materials."

[1106] Step 2:

[1107] The terminal sends a learning material request to the server.

[1108] Step 3:

[1109] The server uses AI to recommend optimal learning materials based on the user's learning progress data.

[1110] Step 4:

[1111] The server transmits the recommended teaching material information to the terminal.

[1112] Step 5:

[1113] The device displays the recommended learning materials to the user.

[1114] Similar problem generation process

[1115] Step 1:

[1116] The user selects "Generate similar questions."

[1117] Step 2:

[1118] The device sends a request to the server.

[1119] Step 3:

[1120] The server automatically generates similar questions using AI based on the user's weak areas.

[1121] Step 4:

[1122] The server sends the generated similar questions to the terminal.

[1123] Step 5:

[1124] The terminal displays similar questions to the user and provides an answer form.

[1125] Statistical Information Provision Process

[1126] Step 1:

[1127] The server periodically collects data on all test takers and performs statistical analysis.

[1128] Step 2:

[1129] The server generates statistical reports and publishes them to educational institutions and businesses.

[1130] Step 3:

[1131] Educational institutions or companies can access statistical reports on their devices to help improve and strategize their teaching.

[1132] Example 1

[1133] Next, a description will be given of Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the headset type terminal 314 will be referred to as a "terminal."

[1134] Today's test-takers need to access a wealth of information and learning resources, making it difficult to determine which resources are most appropriate. It is also difficult to objectively analyze their own academic abilities and weaknesses and create a study plan based on that. Furthermore, they need to find the questions and study materials that are best suited to them and study efficiently.

[1135] The specific processing by the specific processing unit 290 of the data processing device 12 in the first embodiment is realized by the following means.

[1136] In this invention, the server includes a user interface means for inputting the examinee's desired school and basic information, a test question generation means for automatically generating test questions based on the examinee's desired school information and exam subjects, an analysis means for receiving the mock test results answered by the examinee and automatically scoring and analyzing them to clarify the score and correct answer rate, an answer explanation means for generating and displaying detailed explanations for questions answered incorrectly based on the analysis results, a learning material recommendation means for recommending online learning materials and resources suitable for the examinee's learning progress, and a similar question generation means for automatically generating similar questions based on the examinee's awareness of difficulty with specific questions. This allows the examinee to accurately grasp their own academic ability and efficiently progress in their studies.

[1137] "Generative AI" is an AI technology that uses natural language processing and machine learning techniques to automatically generate text and data.

[1138] A "candidate" is an individual who is taking a particular examination or entrance exam.

[1139] "User interface means" refers to input and output devices and software that allow a user to interact with the system.

[1140] "Test question generation means" refers to a function or device that automatically generates test questions based on input information.

[1141] A "generative AI model" is a mathematical model that uses machine learning algorithms to generate text and data.

[1142] "Analysis means" refers to a function or device that analyzes the test taker's answer data and identifies the test taker's score, correct answer rate, and weak points.

[1143] The "answer explanation means" is a function or device that generates detailed explanations based on the analysis results and provides them to the user.

[1144] The "teaching material recommendation means" is a function or device that recommends optimal teaching materials and resources based on the test-taker's learning progress and analysis results.

[1145] The "similar question generating means" is a function or device that automatically generates similar questions related to the subject area in which the examinee is weak.

[1146] "Statistical analysis means" refers to a function or device that statistically analyzes accumulated data and extracts specific patterns or trends.

[1147] A "comparison tool" is a function or device that compares past data with current data and analyzes specific patterns or differences.

[1148] The present invention provides a system for efficiently supporting test takers in their exam preparation using generative artificial intelligence, which includes a user interface, test question generation, analysis, answer explanation, teaching material recommendation, similar question generation, statistical analysis, and comparison.

[1149] First, a user accesses the system and uses an interface to input their desired school, exam subjects, and basic information (such as name and email address). This information is stored in a database by the server. For example, a user inputs "ABC University as their desired school" and "Mathematics, English, and Physics as their exam subjects."

[1150] Next, the server automatically generates appropriate exam questions using a generative AI model (e.g., GPT-4) based on the user's desired school information and exam subjects. The generated exam questions are sent to the user's device, where they can be viewed and answered. For example, it generates "mathematics mock exam questions based on past questions from ABC University."

[1151] When a user enters answers to practice test questions and sends them to a server, the server receives the data and automatically scores and analyzes it using a generative AI model (e.g., BERT). This analysis clarifies the score and correct answer rate for each subject, as well as weak areas and areas of weakness. For example, the result may be, "Mathematics score: 80 points, English correct answer rate: 70%."

[1152] Based on the analysis results, the server generates detailed explanations for the incorrect questions, providing step-by-step instructions on the solution process. This explanation data is sent to the user's device and can be viewed by the user. For example, it provides a "detailed explanation for English grammar questions."

[1153] Furthermore, the server recommends the most suitable online learning materials and resources based on the analysis results and the user's learning progress, allowing the user to study efficiently. For example, it might recommend an online video course specializing in English grammar.

[1154] If a user has difficulty with a particular problem, the server uses a generative AI model to automatically generate similar problems related to that problem. These similar problems are sent to the user's device, and the user can answer them as training. For example, it generates "similar practice problems related to English grammar questions."

[1155] Furthermore, the server uses statistical analysis tools to statistically analyze the accumulated data on test takers and provide reports to educational institutions and companies, enabling strategic use of data in educational settings.

[1156] Finally, through a comparison means, the server compares the past test-taker data with the current test-taker data and provides specific feedback, such as "Your English grades are in the top 20% compared to other test-takers."

[1157] Prompt Sentence Examples

[1158] "Enter ABC University as your preferred school and select Mathematics, English, and Physics as your exam subjects."

[1159] This allows test takers to accurately understand their own academic ability and study efficiently.The system utilizes generative AI models to provide optimal learning support tailored to the diverse needs of test takers.

[1160] The flow of the identification process in the first embodiment will be described with reference to FIG.

[1161] Step 1:

[1162] Users access this system and use the interface to create an account. Specifically, they enter basic information such as their name, email address, and password. The entered data is sent to the server and stored in a database. The entered basic information is used for future individual learning support.

[1163] Step 2:

[1164] Users log in with their account and enter detailed information such as their preferred school and exam subjects. This information includes, for example, "ABC University as the preferred school" and "Mathematics, English, and Physics as the exam subjects." This information is sent to the server and stored in a database. The entered details are used to automatically generate exam questions.

[1165] Step 3:

[1166] The server automatically generates appropriate test questions using a generative AI model (e.g., GPT-4) based on the desired school information and exam subjects. The server references past test data and a question database based on the information entered by the user, and generates an optimal combination of question sets. The generated test questions are then sent to the user's device.

[1167] Step 4:

[1168] The user inputs answers to the test questions received on the device. Once the answer is complete, the device sends the answer data to the server. The sent data includes the user's answer and related metadata (such as the time it took to answer).

[1169] Step 5:

[1170] The server automatically scores and analyzes the received answer data using a generative AI model (e.g., BERT). This analysis clarifies the score and correct answer rate for each subject, as well as weak areas and areas of weakness. For example, the result may be "Mathematics score: 80 points, English correct answer rate: 70%." The analysis results are stored in a database.

[1171] Step 6:

[1172] Based on the analysis results, the server generates detailed explanations for the questions where the user got the answer wrong. The generated explanation data is sent to the user's device and can be viewed by the user. For example, it can provide a "detailed explanation for an English grammar question." The explanation data is important information for the user to restudy.

[1173] Step 7:

[1174] The server recommends optimal online learning materials and resources based on the analysis results and the user's learning progress, allowing the user to study efficiently. For example, it might recommend an "online video course specializing in English grammar." The recommended learning material information is sent to the user's device.

[1175] Step 8:

[1176] If a user has difficulty with a particular problem, the server uses a generative AI model to automatically generate similar problems related to that problem. These similar problems are sent to the user's device, and the user can answer them as training. For example, it generates "similar practice problems related to English grammar questions." The server also references the user's past answer data when generating similar problems.

[1177] Step 9:

[1178] The server statistically analyzes the accumulated test-taker data and provides reports to educational institutions and companies. For example, it provides educational institutions with "statistical data on test-taker weaknesses." The server also compares past test-taker data with current test-taker data and provides specific feedback. For example, it may provide feedback such as, "Your English performance is in the top 20% compared to other test-takers."

[1179] Through these steps, this system provides multifaceted support for test takers' learning, enabling them to study efficiently.

[1180] (Application example 1)

[1181] Next, a description will be given of Application Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the headset type terminal 314 will be referred to as a "terminal."

[1182] Conventional exam study support systems have had issues with providing optimal study plans tailored to each student's learning situation and areas of weakness, and with variations in the quality of automatically generated exam questions and answer explanations. It is also difficult to recommend optimal online learning materials based on students' learning progress, and there was a need for a system that could quickly score and analyze students' mock exam results and provide appropriate feedback based on that.

[1183] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 1 is realized by the following means.

[1184] In this invention, the server includes a user interface means for inputting the examinee's desired school and basic information, a test question generation means for automatically generating test questions based on the examinee's desired school information, an analysis means for analyzing the mock test results answered by the examinee and visualizing weak areas and areas of weakness, an answer explanation means for generating and displaying explanations based on the analysis results, a learning material recommendation means for recommending online learning materials suitable for the examinee's learning situation, a similar question generation means for automatically generating similar questions based on the examinee's weak areas, a scoring analysis means for using a generative AI model to score and analyze the examinee's answers, and a recommendation means for recommending optimal online learning materials based on the examinee's learning progress. This enables efficient learning support tailored to the learning progress of each examinee, as well as rapid feedback and improvement.

[1185] "User interface means" refers to a device, software, or a combination thereof that allows examinees to input their preferred schools and basic information.

[1186] The "exam question generation means" is a system that has the function of automatically generating appropriate exam questions based on the examinee's desired school information.

[1187] The "analysis method" is a system that has the function of analyzing the mock test results given by test takers and visualizing their weak areas and weaknesses.

[1188] The "answer explanation means" is a system that has the function of generating and displaying detailed explanations based on the analysis results.

[1189] The "material recommendation means" is a system that has the function of recommending online materials and resources that are appropriate for the student's learning situation.

[1190] The "similar question generation means" is a system that has the function of automatically generating similar questions based on the examinee's weak areas.

[1191] A "generative AI model" is a technology that uses generative artificial intelligence to generate content and feedback.

[1192] The "scoring and analysis means" is a system that has the functionality to use a generative AI model to score and analyze test takers' answers.

[1193] The "recommendation method" is a system that has the function of recommending the most suitable online learning materials based on the student's learning progress.

[1194] This invention is a system that efficiently supports test takers in studying for exams by using generative artificial intelligence (generative AI model). The system includes the following means.

[1195] User Interface Means

[1196] The user accesses the system from a terminal and enters the school of choice, exam subjects, and basic information (name, email address, etc.), which completes the initial registration.

[1197] Test question generation means

[1198] The server automatically generates appropriate test questions using a generative AI model based on the user's desired school information and exam subjects. The generated questions are sent to the user's device, where they can be viewed and answered.

[1199] Analysis means

[1200] When a user completes a mock test and submits their answers, the server receives the answer data and automatically scores and analyzes it using a generative AI model, revealing the score for each subject, the percentage of correct answers, and areas of weakness.

[1201] Answer explanation method

[1202] Based on the analysis results, the server generates detailed explanations for the questions that the user got wrong, providing step-by-step instructions on how to solve the problem. This explanation data is then sent to the user's device for viewing.

[1203] Teaching material recommendation method

[1204] The server recommends optimal online learning materials and resources based on the analysis results and the user's learning progress, allowing the user to study efficiently.

[1205] Similar problem generation means

[1206] If a user has difficulty with a particular problem, the server automatically generates similar problems related to that problem using a generative AI model. These similar problems are sent to the device, and the user can answer them as training.

[1207] Scoring and analysis methods

[1208] It uses a generative AI model to grade and analyze test-taker answer data, and provides detailed feedback on users' scores, accuracy rates, and weak areas based on the analysis results.

[1209] Recommendation method

[1210] Based on the analysis results and the user's learning progress, the system recommends the most suitable online learning materials, allowing users to study efficiently.

[1211] Specific examples

[1212] For example, a user logs into the system and enters "ABC University" as their preferred school and "Mathematics, English, and Physics" as their exam subjects. The server then uses a generative AI model to automatically generate mock exams for mathematics, English, and physics based on past exam information and data on successful candidates, and sends them to the device. When the user completes the mock exam and submits their answers, the server immediately analyzes the answers and provides detailed feedback and explanations. Based on the analysis results, the server determines that the user has particular weaknesses in English grammar and recommends specialized grammar questions and explanatory videos. Furthermore, it generates similar questions related to English grammar that the user can use for review.

[1213] Prompt Sentence Examples

[1214] "Generate practice math exam questions to help me get into ABC University."

[1215] "Generate an explanation for the English grammar question based on this answer."

[1216] To implement this system, we need to build a generative AI model using the OpenAI API, manage communication between the server and the device using a web application framework such as Flask, and build a comprehensive system, including designing the database and user interface.

[1217] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[1218] Step 1:

[1219] Initial registration

[1220] Input: The user inputs the school of choice, exam subjects, and basic information (name, email address, etc.) on the terminal.

[1221] Processing: The terminal sends the input data to the server.

[1222] Data processing: The server stores the received data in a database and performs any necessary preprocessing.

[1223] Output: The server sends a confirmation message to the terminal indicating that registration is complete.

[1224] Action: The user reconfirms the registration details on the terminal and receives a completion message.

[1225] Step 2:

[1226] Automatic generation of exam questions

[1227] Input: The server references the desired school information and exam subject data entered by the user.

[1228] Processing: The generative AI model is instructed to generate exam questions based on the student's desired school and exam subjects.

[1229] Data processing: A generative AI model generates test questions and structures the data.

[1230] Output: Send the created test questions to the terminal.

[1231] Operation: The user receives and views the generated test questions on the terminal.

[1232] Step 3:

[1233] Mock test answers and submission

[1234] Input: The user answers the practice questions on the terminal and sends the answer data after completion.

[1235] Processing: The terminal sends the answer data to the server.

[1236] Data processing: The server preprocesses the received answer data and formats it for analysis.

[1237] Output: A transmission confirmation message is displayed on the user's terminal.

[1238] Action: The user sees the delivery confirmation message.

[1239] Step 4:

[1240] Answer scoring and analysis

[1241] Input: The server uses the answer data received from the user.

[1242] Processing: Answers are graded and analyzed using a generative AI model.

[1243] Data processing: Extract scores for each subject, correct answer rate, weak areas and weaknesses, and generate analysis results.

[1244] Output: Sends the analysis results to the user's terminal and displays detailed explanations.

[1245] How it works: The user views the analysis results and explanations on their device.

[1246] Step 5:

[1247] Recommendation of teaching materials

[1248] Input: The server uses the analysis results and the user's learning progress data.

[1249] Processing: Using generative AI models to select the best online learning materials and resources.

[1250] Data processing: Format appropriate teaching material information and display it to the user as appropriate.

[1251] Output: Send recommended teaching material information to the terminal.

[1252] How it works: The user checks the recommended learning materials on their device and proceeds with their studies.

[1253] Step 6:

[1254] Generating and providing similar questions

[1255] Input: The server uses the user's weakness data.

[1256] Processing: Use a generative AI model to generate similar questions related to weak areas.

[1257] Data processing: The generated similar problem data is formatted and provided to the user.

[1258] Output: Similar problems are sent to the user's terminal.

[1259] How it works: Users view similar questions on their device and use them for training.

[1260] As a concrete example, if a user inputs "ABC University" as the school of choice and "Mathematics, English, and Physics" as the subjects to be tested, the server will use this information to generate test questions using a generative AI model. The generated test questions are sent to the user's device, and the user answers and submits them. The server analyzes the received answers and provides detailed feedback. Based on the analysis results, suitable study materials and similar questions are also recommended to the user.

[1261] Prompt Sentence Examples

[1262] "Generate practice math exam questions to help me get into ABC University."

[1263] "Generate an explanation for the English grammar question based on this answer."

[1264] Furthermore, an emotion engine that estimates the user's emotion may be further combined. That is, the identification processing unit 290 may estimate the user's emotion using the emotion identification model 59, and perform identification processing using the user's emotion.

[1265] The present invention is a system that efficiently supports test takers in studying for exams by utilizing generative artificial intelligence and an emotion engine. This system includes a user interface means for inputting the user's desired school information and basic information, an exam question generation means for automatically generating exam questions, an analysis means for analyzing mock exam results, an answer explanation means for providing explanations based on the analysis results, a study material recommendation means for recommending appropriate study materials, a similar question generation means for generating similar questions based on weak areas, and an emotion engine for recognizing the user's emotions.

[1266] User Interface Means

[1267] Users access this system and enter their desired school, exam subjects, and basic information (name, email address, etc.), which completes the initial registration.

[1268] Test question generation means

[1269] The server uses AI to automatically generate appropriate exam questions based on the user's desired school information and exam subjects. The generated questions are sent to the user's device, where they can be viewed and answered.

[1270] Analysis means

[1271] When a user completes a mock test and submits their answers, the server receives the answer data and automatically scores and analyzes it using generative AI, which clarifies the score for each subject, the percentage of correct answers, and weak areas and weaknesses.

[1272] Answer explanation method

[1273] Based on the analysis results, the server generates detailed explanations for the questions that the user got wrong, providing step-by-step instructions on how to solve the problem. This explanation data is then sent to the user's device for viewing.

[1274] Teaching material recommendation method

[1275] The server recommends optimal online learning materials and resources based on the analysis results and the user's learning progress, allowing the user to study efficiently.

[1276] Similar problem generation means

[1277] If a user has difficulty with a particular problem, the server automatically generates similar problems related to that problem using a generation AI. These similar problems are sent to the device, and the user can answer them as training.

[1278] Emotion Engine

[1279] The emotion engine collects the user's facial expression recognition data and analyzes the user's emotional state during learning. For example, when the user sends their facial expression to the system through the camera, the server uses the emotion engine to analyze the facial expression and identify the emotional state that will affect the learning progress.

[1280] Emotion-based feedback

[1281] The server generates feedback based on the user's emotional state based on the results of analysis using the emotion engine. For example, if the user is feeling stressed, it will provide appropriate study advice or relaxation techniques. It also dynamically adjusts learning materials and learning approaches based on the user's emotional state to maximize learning efficiency.

[1282] Specific examples

[1283] A user logs into the system and enters "XYZ University" as their preferred school and "Mathematics, English, and Physics" as their exam subjects. The server then uses generative AI to automatically generate mock exams for mathematics, English, and physics based on past exam information and data on successful candidates, and sends them to the device. When the user completes the mock exam and submits their answers, the server immediately analyzes the answers and provides detailed feedback and explanations.

[1284] Based on the analysis results, the server determines that the user has particular weaknesses in English grammar and recommends grammar questions and explanatory videos specific to that area. It also generates similar questions related to English grammar for the user to use for review.

[1285] At the same time, the user's facial expression data is sent to the system and analyzed by the server's emotion engine. For example, if the user shows a confused expression while answering a question, the server will detect that emotional state and provide an encouraging message or advice on how to relax.

[1286] In this way, this system combines generative artificial intelligence and an emotion engine to efficiently provide learning support optimized for each test-taker's individual situation and emotions.

[1287] The processing flow will be explained below.

[1288] Processing steps of the invention combined with emotion engine

[1289] User Registration Process

[1290] Step 1:

[1291] A user accesses the system and opens a login or registration form.

[1292] Step 2:

[1293] The user enters basic information such as the school of choice, exam subjects, name, and email address.

[1294] Step 3:

[1295] The terminal transmits the input information to the server.

[1296] Step 4:

[1297] The server stores the received information in a database.

[1298] Step 5:

[1299] The server generates a registration success message and sends it to the terminal.

[1300] Step 6:

[1301] The terminal displays a registration success message to the user.

[1302] Automatic generation process for mock exams

[1303] Step 1:

[1304] The user selects "Take a Practice Exam" from the dashboard.

[1305] Step 2:

[1306] The terminal sends a request to generate a mock test to the server.

[1307] Step 3:

[1308] The server references data based on the user's desired school and exam subjects, and uses a generation AI to generate mock exam questions.

[1309] Step 4:

[1310] The server stores the generated mock test questions in a database and sends them to the terminal.

[1311] Step 5:

[1312] The terminal displays the practice questions to the user and provides an answer input form.

[1313] Test result analysis process

[1314] Step 1:

[1315] The user completes the practice test and clicks the "Submit" button.

[1316] Step 2:

[1317] The terminal sends the answer data to the server.

[1318] Step 3:

[1319] The server receives the answer data and automatically scores and analyzes it using the generating AI.

[1320] Step 4:

[1321] The server calculates the score for each subject, the percentage of correct answers, and weak areas, and generates detailed feedback.

[1322] Step 5:

[1323] The server sends the analysis results and feedback to the device.

[1324] Step 6:

[1325] The device displays the feedback to the user.

[1326] Answer explanation process

[1327] Step 1:

[1328] If the user reviews the feedback and needs a detailed explanation of the incorrect question, they can click the "Show Explanation" button.

[1329] Step 2:

[1330] The device sends a description request to the server.

[1331] Step 3:

[1332] The server uses a generative AI to generate the answer process for the incorrect question and creates an explanatory text.

[1333] Step 4:

[1334] The server transmits the generated commentary data to the terminal.

[1335] Step 5:

[1336] The terminal displays the explanation to the user.

[1337] Online Material Recommendation Process

[1338] Step 1:

[1339] After the user checks the feedback, they select "View online learning materials."

[1340] Step 2:

[1341] The terminal sends a learning material request to the server.

[1342] Step 3:

[1343] The server uses AI to recommend optimal learning materials based on the user's learning progress data.

[1344] Step 4:

[1345] The server transmits the recommended teaching material information to the terminal.

[1346] Step 5:

[1347] The device displays the recommended learning materials to the user.

[1348] Similar problem generation process

[1349] Step 1:

[1350] The user selects "Generate similar questions."

[1351] Step 2:

[1352] The device sends a request to the server.

[1353] Step 3:

[1354] The server automatically generates similar questions using AI based on the user's weak areas.

[1355] Step 4:

[1356] The server sends the generated similar questions to the terminal.

[1357] Step 5:

[1358] The terminal displays similar questions to the user and provides an answer form.

[1359] Emotion Engine Process

[1360] Step 1:

[1361] During training, the user sends emotional data (e.g., facial expressions and tone of voice) to the system via a camera or microphone.

[1362] Step 2:

[1363] The device transmits the collected emotion data to a server.

[1364] Step 3:

[1365] The server uses an emotion engine to analyze the emotion data and identify the current emotional state (e.g., stress, confusion, concentration).

[1366] Step 4:

[1367] The server generates optimal feedback and learning advice based on the emotional state.

[1368] Step 5:

[1369] The server transmits the generated feedback to the terminal.

[1370] Step 6:

[1371] The device displays emotion-based feedback and advice to the user.

[1372] Specific examples

[1373] A user logs into the system and enters "XYZ University" as their preferred school and "Mathematics, English, and Physics" as their exam subjects. The server then uses generative AI to automatically generate mock exams for mathematics, English, and physics based on past exam information and data on successful candidates, and sends them to the device. When the user completes the mock exam and submits their answers, the server immediately analyzes the answers and provides detailed feedback and explanations.

[1374] Based on the analysis results, the server determines that the user has particular weaknesses in English grammar and recommends grammar questions and explanatory videos specific to that area. It also generates similar questions related to English grammar for the user to use for review.

[1375] While the user is learning, the server monitors the user's facial expressions via a camera, and if it detects a confused expression, the emotion engine analyzes that state. As a result of the analysis, the server determines that the user is feeling stressed and provides an encouraging message or advice on how to relax. For example, a message such as "Take a deep breath and relax. Next, I'll introduce some ways to relax" is displayed.

[1376] In this way, this system combines generative artificial intelligence and an emotion engine to efficiently provide learning support optimized for each test-taker's individual situation and emotions.

[1377] Example 2

[1378] Next, a description will be given of Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the headset type terminal 314 will be referred to as a "terminal."

[1379] Conventional exam study support systems lack personalized learning support tailored to each student's learning progress and areas of weakness, making it difficult for them to study efficiently. Furthermore, they do not provide appropriate feedback that takes into account the student's emotional state, making it difficult for them to maintain their motivation to study and often causing stress.

[1380] The specific processing by the specific processing unit 290 of the data processing device 12 in the second embodiment is realized by the following means.

[1381] In this invention, the server includes user interface means for inputting the examinee's desired school and basic information, test question generation means for automatically generating test questions based on the examinee's desired school information, analysis means for analyzing the mock test results answered by the examinee and visualizing weak areas and areas of weakness, answer explanation means for generating and displaying explanations based on the analysis results, learning material recommendation means for recommending online learning materials suited to the examinee's learning situation, similar question generation means for automatically generating similar questions based on the examinee's weak areas, emotion recognition means for recognizing and analyzing the examinee's emotional state, and emotion feedback means for providing feedback based on the emotion recognition results. This enables efficient and personalized learning support according to the learning situation and emotional state of each examinee.

[1382] "Generative artificial intelligence" refers to sophisticated algorithms that automatically generate information and data based on user input and prompts.

[1383] "Exam taker" refers to an individual studying for a particular exam or entrance examination.

[1384] "User interface means" refers to the interactive input means by which examinees input their preferred schools and basic information into the system.

[1385] "Exam question generation means" refers to a system function that automatically generates appropriate exam questions based on the desired school information and exam subjects entered by the examinee.

[1386] "Analysis means" refers to the system function that analyzes the mock test results given by test takers and clarifies their weak areas and weaknesses.

[1387] The "answer explanation means" refers to a function that generates and displays detailed explanations, especially for incorrect questions, based on the analysis results.

[1388] "Materials recommendation means" refers to the system function that recommends the most appropriate online materials and resources based on the candidate's learning progress and analysis results.

[1389] "Similar question generation means" refers to a function that automatically generates similar questions related to the examinee's weak areas.

[1390] "Emotion recognition means" refers to a function that analyzes the examinee's facial expressions and behavior to identify their current emotional state.

[1391] "Emotion feedback means" refers to a system function that provides appropriate feedback to test takers based on emotion recognition results.

[1392] The present invention is a system that efficiently supports test takers in studying for exams by utilizing generative artificial intelligence and an emotion engine. The system includes a user interface, test question generation, analysis, answer explanation, learning material recommendation, similar question generation, emotion recognition, and emotion feedback.

[1393] Users access the system and perform initial registration by entering their desired school, exam subjects, and basic information (name, email address, etc.). At this time, the information entered by the user is sent to the server and stored in a database.

[1394] The server automatically generates appropriate exam questions using a generative AI model based on the user's desired school information and exam subjects. The generated exam questions are sent to the device so that the user can view and answer them. Specifically, the server uses a generative AI model (e.g., GPT-4) to process data using Python scripts and MongoDB.

[1395] When a user completes a mock test and submits their answers, the server receives the answer data and automatically scores and analyzes it using a generative AI model. This results in clear scores for each subject, the percentage of correct answers, and areas of weakness. Scikit-learn and PostgreSQL are used for this analysis.

[1396] Based on the analysis results, the server generates detailed explanations for questions where the student got the answer wrong. The explanation data is sent to the device and can be viewed by the user. This explanation generation also uses a generative AI model and API communication (REST).

[1397] The server recommends the most suitable online learning materials and resources based on the analysis results and the user's learning progress. This is done using a recommendation engine (e.g., TensorFlow) and Elasticsearch. The recommended learning materials help the user progress efficiently.

[1398] If a user has difficulty with a particular problem, the server automatically generates similar problems related to that problem using a generative AI model. These similar problems are sent to the device and the user can use them for review. At this stage, a NoSQL database such as Firebase is used.

[1399] Furthermore, the user's facial expression data is analyzed using an emotion recognition means. When the user transmits their facial expressions through the camera while studying, the server analyzes the expressions using an emotion engine (e.g., Azure Face API) and generates useful feedback for the user's progress. This feedback may include encouraging messages or suggestions for relaxation techniques depending on the user's emotional state.

[1400] As a specific example, a user logs into the system, sets "ABC University" as their preferred school, and enters "Mathematics, English, and Physics" as their exam subjects. Based on this, the server uses past exam data and data on the trends of successful candidates to automatically generate mock exams for mathematics, English, and physics using generative AI. This mock exam data is sent to the device, and the user takes the mock exam and submits their answers after completing it. The server immediately analyzes the answers and provides detailed feedback and explanations. For example, it might recommend "videos explaining English grammar questions" or "similar questions specialized in grammar." Additionally, if the user's facial expressions during study indicate difficulty or stress, the server will provide advice and messages based on that.

[1401] Examples of prompts include:

[1402] "Please generate mock exams for Mathematics, English, and Physics for ABC University."

[1403] "Analyze users' practice test results and provide feedback with special emphasis on the area of ​​English grammar."

[1404] "Analyze facial expression data sent by the user using a camera and suggest relaxation methods when the user is feeling stressed."

[1405] In this way, the present invention combines generative artificial intelligence and an emotion engine to efficiently provide optimal learning support tailored to the individual circumstances and emotions of each test-taker.

[1406] The flow of the identification process in the second embodiment will be described with reference to FIG.

[1407] Step 1:

[1408] Initial registration

[1409] Users access the system and enter their desired school, exam subjects, and basic information (name, email address, etc.).

[1410] Input: desired school information, exam subject information, basic information (name, email address)

[1411] Output: Save to user profile database

[1412] Specific operation: A form is displayed on the user interface, and the user enters the school of choice and exam subjects and presses the submit button. The submitted data is transferred to the server and stored in a database. This process uses HTML forms, JavaScript, Python, and Django.

[1413] Step 2:

[1414] Automatic generation of exam questions

[1415] The server automatically generates appropriate exam questions using a generative AI model based on the desired school information and exam subjects entered by the user.

[1416] Input: desired school information, exam subject information

[1417] Output: Generated test question data

[1418] Specific operation: The server retrieves information about the school of choice and exam subjects from the user database and sends them as prompts to the generative AI model. The generative AI generates exam questions and returns them to the server. The server then sends the generated exam questions to the device. This process uses a generative AI model (e.g., GPT-4), Python scripts, and a database (MongoDB).

[1419] Step 3:

[1420] Mock exams and answer submission

[1421] The generated test questions are sent to the terminal, and the user takes the test. After completing the test, the answers are sent to the server.

[1422] Input: Generated test questions, user answer data

[1423] Output: Send answer data to the server

[1424] Specific operation: The test questions are displayed on the device, and when the user enters the answers and presses the submit button, the answer data is sent to the server. This process is done using React.js and Node.js.

[1425] Step 4:

[1426] Scoring and Analysis

[1427] The server receives the submitted answer data and automatically scores and analyzes it using a generative AI model.

[1428] Input: User's answer data

[1429] Output: Analysis results for each subject, score, correct answer rate, weak areas and weaknesses

[1430] How it works: The server passes the answer data to the analysis engine, which determines whether each question is correct or not. It also scores the answers and identifies areas where the user is weak. Scikit-learn and PostgreSQL are used for this analysis.

[1431] Step 5:

[1432] Providing answer explanations

[1433] Based on the analysis results, the server generates detailed explanations for the incorrect questions, and the explanation data is sent to the terminal for the user to view.

[1434] Input: Analysis results

[1435] Output: Detailed explanatory data

[1436] Specific operation: Based on the analysis results, the server sends prompts to the generative AI model to generate detailed explanations, which are then sent to the device. This process uses the generative AI model and API communication (REST).

[1437] Step 6:

[1438] Recommendation of teaching materials

[1439] The server recommends the most appropriate online learning materials and resources based on the analysis results and the user's learning progress.

[1440] Input: Analysis results, learning history

[1441] Output: Recommended online learning materials and resources

[1442] Specific operation: The server refers to the analysis results database, checks the user's past learning history and progress, selects appropriate learning materials, and notifies the user. This process uses a recommendation engine (TensorFlow) and Elasticsearch.

[1443] Step 7:

[1444] Generating similar problems

[1445] If a user feels uncomfortable with a particular problem, the server automatically generates similar problems related to that problem using a generative AI model.

[1446] Input: Weakness data

[1447] Output: Generated similar problem data

[1448] Specific operation: The server sends data on weak areas to the generative AI model as prompts, which generate similar questions. These are then sent to the device. This process uses the generative AI model and a NoSQL database such as Firebase.

[1449] Step 8:

[1450] Emotional Recognition and Feedback

[1451] The emotion engine collects the user's facial expression data and analyzes the user's emotional state during training. The server generates feedback based on the results and sends it to the device.

[1452] Input: User's facial expression data

[1453] Output: Sentiment analysis results, feedback data

[1454] Specific operation: Facial expression data collected through the camera is passed to the emotion engine, and the analysis results are obtained. The server generates appropriate feedback based on these results and sends it to the device. This process uses an emotion recognition API (e.g., Azure Face API) and a real-time database (Firebase).

[1455] (Application example 2)

[1456] Next, a description will be given of Application Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the headset type terminal 314 will be referred to as a "terminal."

[1457] Conventional test-taking support systems have limited functionality for analyzing test-takers' learning progress and weak areas, making them unable to adequately address individual learning needs. Furthermore, they provide uniform feedback without taking test-takers' emotional state into consideration, making it difficult to provide effective learning support. Furthermore, they are unable to recommend optimal products and services in real time, limiting their ability to improve customer experience in physical stores. The present invention aims to solve these problems.

[1458] The specific processing by the specific processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means. In this invention, the server includes a user interface means for inputting the examinee's desired school and basic information, a test question generation means for automatically generating test questions based on the examinee's desired school information, an analysis means for analyzing the mock test results answered by the examinee and visualizing the examinee's weak areas and areas of weakness, an answer explanation means for generating and displaying explanations based on the analysis results, a learning material recommendation means for recommending online learning materials suited to the examinee's learning situation, a similar question generation means for automatically generating similar questions based on the examinee's weak areas, an emotion analysis means for collecting customer facial expression recognition data and analyzing the emotional state, and a feedback means for providing feedback according to the emotional state. This enables efficient learning support tailored to individual learning needs and further improves customer experience by recommending optimal products and services in real time.

[1459] "Candidate" refers to any student studying or individual taking an examination.

[1460] "User interface means" refers to the interface through which prospective students and customers input basic information and information about their preferred schools.

[1461] "Exam question generation means" refers to a function that automatically creates exam questions based on information input by examinees.

[1462] "Analysis means" refers to the function that analyzes the mock test results submitted by test takers and analyzes weak areas and correct answer rates.

[1463] "Answer explanation means" refers to a function that provides explanations based on an analysis of mock test results to encourage understanding among test takers.

[1464] "Material recommendation means" refers to a function that recommends optimal learning resources and materials based on the test-taker's learning situation and areas of weakness.

[1465] "Similar problem generation means" refers to a function that automatically generates similar problems related to problems that are difficult to solve.

[1466] "Emotion analysis means" refers to the function of analyzing facial expressions and behavioral data of test takers and customers to analyze their emotional state.

[1467] "Feedback means" refers to the function of providing appropriate feedback or encouraging messages based on the results of sentiment analysis.

[1468] The present invention is a system that efficiently supports test takers and customers of brick-and-mortar stores by utilizing generative artificial intelligence and an emotion engine. Each means of the system will be specifically described below.

[1469] User Interface Means

[1470] Users access the system and input their desired school, exam subjects, basic information (name, email address, etc.) or customer information (name, preferred product category, etc.). This information is stored by the server and becomes the basic data for responding to the individual needs of the user.

[1471] Test question generation means

[1472] Based on the student's desired school information and exam subjects, the server uses AI to automatically generate appropriate exam questions. The generated questions are sent to the device, where the user can view and answer them.

[1473] Analysis means

[1474] When a user completes a mock test and submits their answers, the server receives the answer data and automatically scores and analyzes it using generative AI, which clarifies the score for each subject, the percentage of correct answers, and weak areas and weaknesses.

[1475] Answer explanation method

[1476] Based on the analysis results, the server generates detailed explanations for the questions that the user got wrong, providing step-by-step instructions on how to solve the problem. This explanation data is then sent to the user's device for viewing.

[1477] Teaching material recommendation method

[1478] The server recommends optimal online learning materials and resources based on the analysis results and the user's learning progress, allowing the user to study efficiently.

[1479] Similar problem generation means

[1480] If a user has difficulty with a particular problem, the server automatically generates similar problems related to that problem using a generation AI. These similar problems are sent to the device, and the user can answer them as training.

[1481] Emotion analysis means

[1482] The server collects facial expression data from the user through the camera and uses the emotion engine to analyze the user's emotional state during learning. For example, when the user looks at the camera, the server uses the emotion engine to analyze the user's facial expression and identify the emotional state that will affect the user's learning progress.

[1483] Feedback Methods

[1484] Based on the results of emotion analysis, the server generates feedback according to the user's emotional state. For example, if the user is confused, it will display relaxation advice or encouraging messages. It also improves the customer experience by recommending optimal products and services based on the results of analyzing customers' facial expressions in the store.

[1485] Specific examples

[1486] 1. A user logs into the system and enters "ABC University" as their preferred school and "Mathematics, English, and Physics" as their exam subjects. The server then uses AI to automatically generate mock exams for mathematics, English, and physics based on past exam information and data on successful candidates, and sends them to the device.

[1487] 2. Once a user completes a mock test and submits their answers, the server instantly analyzes the answers and provides detailed feedback and explanations. Based on the analysis results, the server determines that the user has particular weaknesses in English grammar and recommends grammar questions and explanatory videos specific to that area. Furthermore, the server generates similar questions related to English grammar for the user to review.

[1488] 3. The user's facial expression data is sent to the system via the camera and analyzed by the server's emotion engine. For example, if the user shows a confused expression while answering a question, the server will detect that emotional state and provide an encouraging message or advice on how to relax.

[1489] 4. Even in physical stores, when customers send facial expression data via camera, it is analyzed by the emotion engine and the most suitable products and promotions are recommended in real time.

[1490] Prompt Sentence Examples

[1491] "Use your emotion engine to provide optimal product recommendations when customers are confused."

[1492] "Implement a product recommendation algorithm based on historical purchase data and real-time sentiment analysis."

[1493] In this way, the system combines generative artificial intelligence and an emotion engine to efficiently provide support optimized for the individual situations and emotions of test takers and customers in brick-and-mortar stores.

[1494] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[1495] Step 1:

[1496] The user accesses the system and inputs the school of choice, exam subjects, basic information (name, email address, etc.), or customer information (name, preferred product category, etc.) through the user interface. The input information is sent to the server and saved in the database. This completes the initial setup based on the user's individual needs. The input data is processed by checking the format of each item and saving it as the appropriate data type.

[1497] Step 2:

[1498] Based on the examinee's desired school information and exam subjects, the server uses a generative AI model to automatically generate appropriate exam questions. The generated questions are sent to the terminal so that the user can view and answer them. In this step, prompts are generated based on the user's input data, and the AI ​​model generates questions accordingly.

[1499] Step 3:

[1500] Users answer mock exam questions and send the answer data to the server. The server uses a generative AI model to automatically score the test-taker's answers and analyzes the score for each subject, the percentage of correct answers, and weak areas and weaknesses. The input data is the user's answer data, and the output data is a report of the analysis results.

[1501] Step 4:

[1502] Based on the analysis results, the server generates detailed explanations for the incorrect answers, which are then sent to the device for viewing by the user. Based on the analysis data, prompts are generated, and the AI ​​model then creates explanations accordingly.

[1503] Step 5:

[1504] The server recommends the most suitable online learning materials and resources based on the user's analysis results and learning progress. The recommended learning materials are notified to the user's device, where they can be viewed and used. Based on the analysis results, the server searches for and recommends the most suitable learning materials from a database of related learning materials.

[1505] Step 6:

[1506] If a user has difficulty with a particular problem, the server automatically generates similar problems related to that problem using a generative AI model. The generated similar problems are sent to the device, where the user can solve them for training. Using the user's answer data and analysis results as input, a prompt to generate similar problems is created and the problems are generated by the AI ​​model.

[1507] Step 7:

[1508] The user's facial expression data is collected through the camera and sent to the server. The server uses an emotion analysis engine to analyze the user's emotional state during training. This data is the user's facial expression data, and the emotional state is output as the analysis result. Analysis is performed in real time based on the emotional data.

[1509] Step 8:

[1510] Based on the results of the emotion analysis, the server generates feedback according to the user's emotional state. For example, if the user is confused, the server sends an encouraging message or advice to relax to the device, thereby supporting the user's mental state. The server uses the emotional state data as input and generates an appropriate feedback message.

[1511] Step 9:

[1512] In physical stores, customer facial expression data is collected and sent to a server. The server uses an emotion analysis engine to analyze the customer's emotions in real time. Based on the analyzed emotion data, the system recommends the most appropriate products and services. For example, if a customer is confused, corresponding products will be displayed on the smart device. Emotional state data is used to generate prompts and recommend products using an AI model.

[1513] In this way, the system effectively utilizes generative AI models and emotion engines at each step to provide advanced assistance to test takers and brick-and-mortar customers.

[1514] The specific processing unit 290 transmits the result of the specific processing to the headset type terminal 314. In the headset type terminal 314, the control unit 46A causes the speaker 240 and the display 343 to output the result of the specific processing. The microphone 238 acquires audio indicating a user input regarding the result of the specific processing. The control unit 46A transmits audio data indicating the user input acquired by the microphone 238 to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the audio data.

[1515] The data generation model 58 is a so-called generative AI (Artificial Intelligence). An example of the data generation model 58 is ChatGPT (Internet Search<URL: https: / / openai.com / blog / chatgpt> ), Gemini (Internet search <url: https: gemini.google.com ?hl="ja">) and other generation AIs. The data generation model 58 is obtained by performing deep learning on a neural network. A prompt including an instruction is input to the data generation model 58, and inference data such as voice data indicating voice, text data indicating text, and image data indicating an image is also input. The data generation model 58 performs inference on the input inference data in accordance with the instruction indicated by the prompt, and outputs the inference result in a data format such as voice data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[1516] In the above embodiment, an example was given in which the specific processing is performed by the data processing device 12, but the technology of the present disclosure is not limited to this, and the specific processing may be performed by the headset type terminal 314.

[1517] [Fourth embodiment]

[1518] FIG. 7 shows an example of the configuration of a data processing system 410 according to the fourth embodiment.

[1519] 7, a data processing system 410 includes a data processing device 12 and a robot 414. An example of the data processing device 12 is a server.

[1520] The data processing device 12 includes a computer 22, a database 24, and a communication I / F 26. The computer 22 is an example of a "computer" according to the technology of the present disclosure. The computer 22 includes a processor 28, a RAM 30, and a storage 32. The processor 28, the RAM 30, and the storage 32 are connected to a bus 34. The database 24 and the communication I / F 26 are also connected to the bus 34. The communication I / F 26 is connected to a network 54. Examples of the network 54 include a WAN (Wide Area Network) and / or a LAN (Local Area Network).

[1521] The robot 414 includes a computer 36, a microphone 238, a speaker 240, a camera 42, a communication I / F 44, and a control target 443. The computer 36 includes a processor 46, a RAM 48, and a storage 50. The processor 46, the RAM 48, and the storage 50 are connected to a bus 52. The microphone 238, the speaker 240, the camera 42, and the control target 443 are also connected to the bus 52.

[1522] The microphone 238 receives instructions and the like from the user 20 by receiving voice uttered by the user 20. The microphone 238 captures the voice uttered by the user 20, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio in accordance with instructions from the processor 46.

[1523] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an imaging element such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, and captures images of the surroundings of user 20 (for example, an imaging range defined by an angle of view equivalent to the field of vision of a typical healthy person).

[1524] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 are responsible for the exchange of various information between the processor 46 and the processor 28 via the network 54. The exchange of various information between the processor 46 and the processor 28 using the communication I / Fs 44 and 26 is carried out in a secure state.

[1525] The control object 443 includes a display device, LEDs in the eyes, and motors for driving the arms, hands, and feet. The posture and gestures of the robot 414 are controlled by controlling the motors of the arms, hands, and feet. Some of the emotions of the robot 414 can be expressed by controlling these motors. In addition, the facial expressions of the robot 414 can also be expressed by controlling the light emission state of the LEDs in the eyes of the robot 414.

[1526] Fig. 8 shows an example of the main functions of the data processing device 12 and the robot 414. As shown in Fig. 8, in the data processing device 12, a specific process is performed by the processor 28. A specific process program 56 is stored in the storage 32.

[1527] The specific processing program 56 is an example of a "program" according to the technology of the present disclosure. The processor 28 reads the specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific processing is realized by the processor 28 operating as a specific processing unit 290 in accordance with the specific processing program 56 executed on the RAM 30.

[1528] The storage 32 stores a data generation model 58 and an emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290.

[1529] In the robot 414, the processor 46 performs the reception output process. A reception output program 60 is stored in the storage 50. The processor 46 reads the reception output program 60 from the storage 50 and executes the read reception output program 60 on the RAM 48. The reception output process is realized by the processor 46 operating as the control unit 46A in accordance with the reception output program 60 executed on the RAM 48.

[1530] Next, a description will be given of the specific processing performed by the specific processing unit 290 of the data processing device 12. In the following description, the data processing device 12 will be referred to as a "server" and the robot 414 will be referred to as a "terminal."

[1531] The present invention is a system that efficiently supports test takers in studying for exams using generative artificial intelligence. This system includes a user interface means for inputting the user's desired school information and basic information, a test question generation means for automatically generating test questions, an analysis means for analyzing mock test results, an answer explanation means for providing explanations based on the analysis results, a learning material recommendation means for recommending appropriate learning materials, and a similar question generation means for generating similar questions based on weak areas.

[1532] User Interface Means

[1533] Users access this system and enter their desired school, exam subjects, and basic information (name, email address, etc.), which completes the initial registration.

[1534] Test question generation means

[1535] The server uses AI to automatically generate appropriate exam questions based on the user's desired school information and exam subjects. The generated questions are sent to the user's device, where they can be viewed and answered.

[1536] Analysis means

[1537] When a user completes a mock test and submits their answers, the server receives the answer data and automatically scores and analyzes it using generative AI, which clarifies the score for each subject, the percentage of correct answers, and weak areas and weaknesses.

[1538] Answer explanation method

[1539] Based on the analysis results, the server generates detailed explanations for the questions that the user got wrong, providing step-by-step instructions on how to solve the problem. This explanation data is then sent to the user's device for viewing.

[1540] Teaching material recommendation method

[1541] The server recommends optimal online learning materials and resources based on the analysis results and the user's learning progress, allowing the user to study efficiently.

[1542] Similar problem generation means

[1543] If a user has difficulty with a particular problem, the server automatically generates similar problems related to that problem using a generation AI. These similar problems are sent to the device, and the user can answer them as training.

[1544] Statistical analysis and comparison tools

[1545] This system has the ability to statistically analyze accumulated test-taker data. This data is provided to educational institutions and companies, supporting strategic data utilization in the field of education. Furthermore, by performing comparative analysis with past test-taker data, it is possible to provide more specific feedback to users.

[1546] Specific examples

[1547] A user logs into the system and enters "XYZ University" as their preferred school and "Mathematics, English, and Physics" as their exam subjects. The server then uses generative AI to automatically generate mock exams for mathematics, English, and physics based on past exam information and data on successful candidates, and sends them to the device. When the user completes the mock exam and submits their answers, the server immediately analyzes the answers and provides detailed feedback and explanations. Based on the analysis results, the server determines that the user has particular weaknesses in English grammar and recommends specialized grammar questions and explanatory videos. Furthermore, the server generates similar questions related to English grammar that the user can use for review.

[1548] In this way, the system efficiently provides learning support that is optimized for each examinee's individual situation.

[1549] The processing flow will be explained below.

[1550] User Registration Process

[1551] Step 1:

[1552] A user accesses the system and opens a login or registration form.

[1553] Step 2:

[1554] The user enters basic information such as the school of choice, exam subjects, name, and email address.

[1555] Step 3:

[1556] The terminal transmits the input information to the server.

[1557] Step 4:

[1558] The server stores the received information in a database.

[1559] Step 5:

[1560] The server generates a registration success message and sends it to the terminal.

[1561] Step 6:

[1562] The terminal displays a registration success message to the user.

[1563] Automatic generation process for mock exams

[1564] Step 1:

[1565] The user selects "Take a Practice Exam" from the dashboard.

[1566] Step 2:

[1567] The terminal sends a request to generate a mock test to the server.

[1568] Step 3:

[1569] The server references data based on the user's desired school and exam subjects, and uses a generation AI to generate mock exam questions.

[1570] Step 4:

[1571] The server stores the generated mock test questions in a database and sends them to the terminal.

[1572] Step 5:

[1573] The terminal displays the practice questions to the user and provides an answer input form.

[1574] Test result analysis process

[1575] Step 1:

[1576] The user completes the practice test and clicks the "Submit" button.

[1577] Step 2:

[1578] The terminal sends the answer data to the server.

[1579] Step 3:

[1580] The server receives the answer data and automatically scores and analyzes it using the generating AI.

[1581] Step 4:

[1582] The server calculates the score, accuracy rate, and weak areas for each subject and generates detailed feedback.

[1583] Step 5:

[1584] The server sends the analysis results and feedback to the device.

[1585] Step 6:

[1586] The device displays the feedback to the user.

[1587] Answer explanation process

[1588] Step 1:

[1589] If the user reviews the feedback and needs a detailed explanation of the incorrect question, they can click the "Show Explanation" button.

[1590] Step 2:

[1591] The device sends a description request to the server.

[1592] Step 3:

[1593] The server uses a generative AI to generate the answer process for the incorrect question and creates an explanatory text.

[1594] Step 4:

[1595] The server transmits the generated commentary data to the terminal.

[1596] Step 5:

[1597] The terminal displays the explanation to the user.

[1598] Online Material Recommendation Process

[1599] Step 1:

[1600] After the user checks the feedback, they select "View online learning materials."

[1601] Step 2:

[1602] The terminal sends a learning material request to the server.

[1603] Step 3:

[1604] The server uses AI to recommend optimal learning materials based on the user's learning progress data.

[1605] Step 4:

[1606] The server transmits the recommended teaching material information to the terminal.

[1607] Step 5:

[1608] The device displays the recommended learning materials to the user.

[1609] Similar problem generation process

[1610] Step 1:

[1611] The user selects "Generate similar questions."

[1612] Step 2:

[1613] The device sends a request to the server.

[1614] Step 3:

[1615] The server automatically generates similar questions using AI based on the user's weak areas.

[1616] Step 4:

[1617] The server sends the generated similar questions to the terminal.

[1618] Step 5:

[1619] The terminal displays similar questions to the user and provides an answer form.

[1620] Statistical Information Provision Process

[1621] Step 1:

[1622] The server periodically collects data on all test takers and performs statistical analysis.

[1623] Step 2:

[1624] The server generates statistical reports and publishes them to educational institutions and businesses.

[1625] Step 3:

[1626] Educational institutions or companies can access statistical reports on their devices to help improve and strategize their teaching.

[1627] Example 1

[1628] Next, a description will be given of Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the robot 414 will be referred to as a "terminal."

[1629] Today's test-takers need to access a wealth of information and learning resources, making it difficult to determine which resources are most appropriate. It is also difficult to objectively analyze their own academic abilities and weaknesses and create a study plan based on that. Furthermore, they need to find the questions and study materials that are best suited to them and study efficiently.

[1630] The specific processing by the specific processing unit 290 of the data processing device 12 in the first embodiment is realized by the following means.

[1631] In this invention, the server includes a user interface means for inputting the examinee's desired school and basic information, a test question generation means for automatically generating test questions based on the examinee's desired school information and exam subjects, an analysis means for receiving the mock test results answered by the examinee and automatically scoring and analyzing them to clarify the score and correct answer rate, an answer explanation means for generating and displaying detailed explanations for questions answered incorrectly based on the analysis results, a learning material recommendation means for recommending online learning materials and resources suitable for the examinee's learning progress, and a similar question generation means for automatically generating similar questions based on the examinee's awareness of difficulty with specific questions. This allows the examinee to accurately grasp their own academic ability and efficiently progress in their studies.

[1632] "Generative AI" is an AI technology that uses natural language processing and machine learning techniques to automatically generate text and data.

[1633] A "candidate" is an individual who is taking a particular examination or entrance exam.

[1634] "User interface means" refers to input and output devices and software that allow a user to interact with the system.

[1635] "Test question generation means" refers to a function or device that automatically generates test questions based on input information.

[1636] A "generative AI model" is a mathematical model that uses machine learning algorithms to generate text and data.

[1637] "Analysis means" refers to a function or device that analyzes the test taker's answer data and identifies the test taker's score, correct answer rate, and weak points.

[1638] The "answer explanation means" is a function or device that generates detailed explanations based on the analysis results and provides them to the user.

[1639] The "teaching material recommendation means" is a function or device that recommends optimal teaching materials and resources based on the test-taker's learning progress and analysis results.

[1640] The "similar question generating means" is a function or device that automatically generates similar questions related to the subject area in which the examinee is weak.

[1641] "Statistical analysis means" refers to a function or device that statistically analyzes accumulated data and extracts specific patterns or trends.

[1642] A "comparison tool" is a function or device that compares past data with current data and analyzes specific patterns or differences.

[1643] The present invention provides a system for efficiently supporting test takers in their exam preparation using generative artificial intelligence, which includes a user interface, test question generation, analysis, answer explanation, teaching material recommendation, similar question generation, statistical analysis, and comparison.

[1644] First, a user accesses the system and uses an interface to input their desired school, exam subjects, and basic information (such as name and email address). This information is stored in a database by the server. For example, a user inputs "ABC University as their desired school" and "Mathematics, English, and Physics as their exam subjects."

[1645] Next, the server automatically generates appropriate exam questions using a generative AI model (e.g., GPT-4) based on the user's desired school information and exam subjects. The generated exam questions are sent to the user's device, where they can be viewed and answered. For example, it generates "mathematics mock exam questions based on past questions from ABC University."

[1646] When a user enters answers to practice test questions and sends them to a server, the server receives the data and automatically scores and analyzes it using a generative AI model (e.g., BERT). This analysis clarifies the score and correct answer rate for each subject, as well as weak areas and areas of weakness. For example, the result may be, "Mathematics score: 80 points, English correct answer rate: 70%."

[1647] Based on the analysis results, the server generates detailed explanations for the incorrect questions, providing step-by-step instructions on the solution process. This explanation data is sent to the user's device and can be viewed by the user. For example, it provides a "detailed explanation for English grammar questions."

[1648] Furthermore, the server recommends the most suitable online learning materials and resources based on the analysis results and the user's learning progress, allowing the user to study efficiently. For example, it might recommend an online video course specializing in English grammar.

[1649] If a user has difficulty with a particular problem, the server uses a generative AI model to automatically generate similar problems related to that problem. These similar problems are sent to the user's device, and the user can answer them as training. For example, it generates "similar practice problems related to English grammar questions."

[1650] Furthermore, the server uses statistical analysis tools to statistically analyze the accumulated data on test takers and provide reports to educational institutions and companies, enabling strategic use of data in educational settings.

[1651] Finally, through a comparison means, the server compares the past test-taker data with the current test-taker data and provides specific feedback, such as "Your English grades are in the top 20% compared to other test-takers."

[1652] Prompt Sentence Examples

[1653] "Enter ABC University as your preferred school and select Mathematics, English, and Physics as your exam subjects."

[1654] This allows test takers to accurately understand their own academic ability and study efficiently.The system utilizes generative AI models to provide optimal learning support tailored to the diverse needs of test takers.

[1655] The flow of the identification process in the first embodiment will be described with reference to FIG.

[1656] Step 1:

[1657] Users access this system and use the interface to create an account. Specifically, they enter basic information such as their name, email address, and password. The entered data is sent to the server and stored in a database. The entered basic information is used for future individual learning support.

[1658] Step 2:

[1659] Users log in with their account and enter detailed information such as their preferred school and exam subjects. This information includes, for example, "ABC University as the preferred school" and "Mathematics, English, and Physics as the exam subjects." This information is sent to the server and stored in a database. The entered details are used to automatically generate exam questions.

[1660] Step 3:

[1661] The server automatically generates appropriate test questions using a generative AI model (e.g., GPT-4) based on the desired school information and exam subjects. The server references past test data and a question database based on the information entered by the user, and generates an optimal combination of question sets. The generated test questions are then sent to the user's device.

[1662] Step 4:

[1663] The user inputs answers to the test questions received on the device. Once the answer is complete, the device sends the answer data to the server. The sent data includes the user's answer and related metadata (such as the time it took to answer).

[1664] Step 5:

[1665] The server automatically scores and analyzes the received answer data using a generative AI model (e.g., BERT). This analysis clarifies the score and correct answer rate for each subject, as well as weak areas and areas of weakness. For example, the result may be "Mathematics score: 80 points, English correct answer rate: 70%." The analysis results are stored in a database.

[1666] Step 6:

[1667] Based on the analysis results, the server generates detailed explanations for the questions where the user got the answer wrong. The generated explanation data is sent to the user's device and can be viewed by the user. For example, it can provide a "detailed explanation for an English grammar question." The explanation data is important information for the user to restudy.

[1668] Step 7:

[1669] The server recommends optimal online learning materials and resources based on the analysis results and the user's learning progress, allowing the user to study efficiently. For example, it might recommend an "online video course specializing in English grammar." The recommended learning material information is sent to the user's device.

[1670] Step 8:

[1671] If a user has difficulty with a particular problem, the server uses a generative AI model to automatically generate similar problems related to that problem. These similar problems are sent to the user's device, and the user can answer them as training. For example, it generates "similar practice problems related to English grammar questions." The server also references the user's past answer data when generating similar problems.

[1672] Step 9:

[1673] The server statistically analyzes the accumulated test-taker data and provides reports to educational institutions and companies. For example, it provides educational institutions with "statistical data on test-taker weaknesses." The server also compares past test-taker data with current test-taker data and provides specific feedback. For example, it may provide feedback such as, "Your English performance is in the top 20% compared to other test-takers."

[1674] Through these steps, this system provides multifaceted support for test takers' learning, enabling them to study efficiently.

[1675] (Application example 1)

[1676] Next, a description will be given of Application Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the robot 414 will be referred to as a "terminal."

[1677] Conventional exam study support systems have had issues with providing optimal study plans tailored to each student's learning situation and areas of weakness, and with variations in the quality of automatically generated exam questions and answer explanations. It is also difficult to recommend optimal online learning materials based on students' learning progress, and there was a need for a system that could quickly score and analyze students' mock exam results and provide appropriate feedback based on that.

[1678] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 1 is realized by the following means.

[1679] In this invention, the server includes a user interface means for inputting the examinee's desired school and basic information, a test question generation means for automatically generating test questions based on the examinee's desired school information, an analysis means for analyzing the mock test results answered by the examinee and visualizing weak areas and areas of weakness, an answer explanation means for generating and displaying explanations based on the analysis results, a learning material recommendation means for recommending online learning materials suitable for the examinee's learning situation, a similar question generation means for automatically generating similar questions based on the examinee's weak areas, a scoring analysis means for using a generative AI model to score and analyze the examinee's answers, and a recommendation means for recommending optimal online learning materials based on the examinee's learning progress. This enables efficient learning support tailored to the learning progress of each examinee, as well as rapid feedback and improvement.

[1680] "User interface means" refers to a device, software, or a combination thereof that allows examinees to input their preferred schools and basic information.

[1681] The "exam question generation means" is a system that has the function of automatically generating appropriate exam questions based on the examinee's desired school information.

[1682] The "analysis method" is a system that has the function of analyzing the mock test results given by test takers and visualizing their weak areas and weaknesses.

[1683] The "answer explanation means" is a system that has the function of generating and displaying detailed explanations based on the analysis results.

[1684] The "material recommendation means" is a system that has the function of recommending online materials and resources that are appropriate for the student's learning situation.

[1685] The "similar question generation means" is a system that has the function of automatically generating similar questions based on the examinee's weak areas.

[1686] A "generative AI model" is a technology that uses generative artificial intelligence to generate content and feedback.

[1687] The "scoring and analysis means" is a system that has the functionality to use a generative AI model to score and analyze test takers' answers.

[1688] The "recommendation method" is a system that has the function of recommending the most suitable online learning materials based on the student's learning progress.

[1689] This invention is a system that efficiently supports test takers in studying for exams by using generative artificial intelligence (generative AI model). The system includes the following means.

[1690] User Interface Means

[1691] The user accesses the system from a terminal and enters the school of choice, exam subjects, and basic information (name, email address, etc.), which completes the initial registration.

[1692] Test question generation means

[1693] The server automatically generates appropriate test questions using a generative AI model based on the user's desired school information and exam subjects. The generated questions are sent to the user's device, where they can be viewed and answered.

[1694] Analysis means

[1695] When a user completes a mock test and submits their answers, the server receives the answer data and automatically scores and analyzes it using a generative AI model, revealing the score for each subject, the percentage of correct answers, and areas of weakness.

[1696] Answer explanation method

[1697] Based on the analysis results, the server generates detailed explanations for the questions that the user got wrong, providing step-by-step instructions on how to solve the problem. This explanation data is then sent to the user's device for viewing.

[1698] Teaching material recommendation method

[1699] The server recommends optimal online learning materials and resources based on the analysis results and the user's learning progress, allowing the user to study efficiently.

[1700] Similar problem generation means

[1701] If a user has difficulty with a particular problem, the server automatically generates similar problems related to that problem using a generative AI model. These similar problems are sent to the device, and the user can answer them as training.

[1702] Scoring and analysis methods

[1703] It uses a generative AI model to grade and analyze test-taker answer data, and provides detailed feedback on users' scores, accuracy rates, and weak areas based on the analysis results.

[1704] Recommendation method

[1705] Based on the analysis results and the user's learning progress, the system recommends the most suitable online learning materials, allowing users to study efficiently.

[1706] Specific examples

[1707] For example, a user logs into the system and enters "ABC University" as their preferred school and "Mathematics, English, and Physics" as their exam subjects. The server then uses a generative AI model to automatically generate mock exams for mathematics, English, and physics based on past exam information and data on successful candidates, and sends them to the device. When the user completes the mock exam and submits their answers, the server immediately analyzes the answers and provides detailed feedback and explanations. Based on the analysis results, the server determines that the user has particular weaknesses in English grammar and recommends specialized grammar questions and explanatory videos. Furthermore, it generates similar questions related to English grammar that the user can use for review.

[1708] Prompt Sentence Examples

[1709] "Generate practice math exam questions to help me get into ABC University."

[1710] "Generate an explanation for the English grammar question based on this answer."

[1711] To implement this system, we need to build a generative AI model using the OpenAI API, manage communication between the server and the device using a web application framework such as Flask, and build a comprehensive system, including designing the database and user interface.

[1712] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[1713] Step 1:

[1714] Initial registration

[1715] Input: The user inputs the school of choice, exam subjects, and basic information (name, email address, etc.) on the terminal.

[1716] Processing: The terminal sends the input data to the server.

[1717] Data processing: The server stores the received data in a database and performs any necessary preprocessing.

[1718] Output: The server sends a confirmation message to the terminal indicating that registration is complete.

[1719] Action: The user reconfirms the registration details on the terminal and receives a completion message.

[1720] Step 2:

[1721] Automatic generation of exam questions

[1722] Input: The server references the desired school information and exam subject data entered by the user.

[1723] Processing: The generative AI model is instructed to generate exam questions based on the student's desired school and exam subjects.

[1724] Data processing: A generative AI model generates test questions and structures the data.

[1725] Output: Send the created test questions to the terminal.

[1726] Operation: The user receives and views the generated test questions on the terminal.

[1727] Step 3:

[1728] Mock test answers and submission

[1729] Input: The user answers the practice questions on the terminal and sends the answer data after completion.

[1730] Processing: The terminal sends the answer data to the server.

[1731] Data processing: The server preprocesses the received answer data and formats it for analysis.

[1732] Output: A transmission confirmation message is displayed on the user's terminal.

[1733] Action: The user sees the delivery confirmation message.

[1734] Step 4:

[1735] Answer scoring and analysis

[1736] Input: The server uses the answer data received from the user.

[1737] Processing: Answers are graded and analyzed using a generative AI model.

[1738] Data processing: Extract scores for each subject, correct answer rate, weak areas and weaknesses, and generate analysis results.

[1739] Output: Sends the analysis results to the user's terminal and displays detailed explanations.

[1740] How it works: The user views the analysis results and explanations on their device.

[1741] Step 5:

[1742] Recommendation of teaching materials

[1743] Input: The server uses the analysis results and the user's learning progress data.

[1744] Processing: Using generative AI models to select the best online learning materials and resources.

[1745] Data processing: Format appropriate teaching material information and display it to the user as appropriate.

[1746] Output: Send recommended teaching material information to the terminal.

[1747] How it works: The user checks the recommended learning materials on their device and proceeds with their studies.

[1748] Step 6:

[1749] Generating and providing similar questions

[1750] Input: The server uses the user's weakness data.

[1751] Processing: Use a generative AI model to generate similar questions related to weak areas.

[1752] Data processing: The generated similar problem data is formatted and provided to the user.

[1753] Output: Similar problems are sent to the user's terminal.

[1754] How it works: Users view similar questions on their device and use them for training.

[1755] As a concrete example, if a user inputs "ABC University" as the school of choice and "Mathematics, English, and Physics" as the subjects to be tested, the server will use this information to generate test questions using a generative AI model. The generated test questions are sent to the user's device, and the user answers and submits them. The server analyzes the received answers and provides detailed feedback. Based on the analysis results, suitable study materials and similar questions are also recommended to the user.

[1756] Prompt Sentence Examples

[1757] "Generate practice math exam questions to help me get into ABC University."

[1758] "Generate an explanation for the English grammar question based on this answer."

[1759] Furthermore, an emotion engine that estimates the user's emotion may be further combined. That is, the identification processing unit 290 may estimate the user's emotion using the emotion identification model 59, and perform identification processing using the user's emotion.

[1760] The present invention is a system that efficiently supports test takers in studying for exams by utilizing generative artificial intelligence and an emotion engine. This system includes a user interface means for inputting the user's desired school information and basic information, an exam question generation means for automatically generating exam questions, an analysis means for analyzing mock exam results, an answer explanation means for providing explanations based on the analysis results, a study material recommendation means for recommending appropriate study materials, a similar question generation means for generating similar questions based on weak areas, and an emotion engine for recognizing the user's emotions.

[1761] User Interface Means

[1762] Users access this system and enter their desired school, exam subjects, and basic information (name, email address, etc.), which completes the initial registration.

[1763] Test question generation means

[1764] The server uses AI to automatically generate appropriate exam questions based on the user's desired school information and exam subjects. The generated questions are sent to the user's device, where they can be viewed and answered.

[1765] Analysis means

[1766] When a user completes a mock test and submits their answers, the server receives the answer data and automatically scores and analyzes it using generative AI, which clarifies the score for each subject, the percentage of correct answers, and weak areas and weaknesses.

[1767] Answer explanation method

[1768] Based on the analysis results, the server generates detailed explanations for the questions that the user got wrong, providing step-by-step instructions on how to solve the problem. This explanation data is then sent to the user's device for viewing.

[1769] Teaching material recommendation method

[1770] The server recommends optimal online learning materials and resources based on the analysis results and the user's learning progress, allowing the user to study efficiently.

[1771] Similar problem generation means

[1772] If a user has difficulty with a particular problem, the server automatically generates similar problems related to that problem using a generation AI. These similar problems are sent to the device, and the user can answer them as training.

[1773] Emotion Engine

[1774] The emotion engine collects the user's facial expression recognition data and analyzes the user's emotional state during learning. For example, when the user sends their facial expression to the system through the camera, the server uses the emotion engine to analyze the facial expression and identify the emotional state that will affect the learning progress.

[1775] Emotion-based feedback

[1776] The server generates feedback based on the user's emotional state based on the results of analysis using the emotion engine. For example, if the user is feeling stressed, it will provide appropriate study advice or relaxation techniques. It also dynamically adjusts learning materials and learning approaches based on the user's emotional state to maximize learning efficiency.

[1777] Specific examples

[1778] A user logs into the system and enters "XYZ University" as their preferred school and "Mathematics, English, and Physics" as their exam subjects. The server then uses generative AI to automatically generate mock exams for mathematics, English, and physics based on past exam information and data on successful candidates, and sends them to the device. When the user completes the mock exam and submits their answers, the server immediately analyzes the answers and provides detailed feedback and explanations.

[1779] Based on the analysis results, the server determines that the user has particular weaknesses in English grammar and recommends grammar questions and explanatory videos specific to that area. It also generates similar questions related to English grammar for the user to use for review.

[1780] At the same time, the user's facial expression data is sent to the system and analyzed by the server's emotion engine. For example, if the user shows a confused expression while answering a question, the server will detect that emotional state and provide an encouraging message or advice on how to relax.

[1781] In this way, this system combines generative artificial intelligence and an emotion engine to efficiently provide learning support optimized for each test-taker's individual situation and emotions.

[1782] The processing flow will be explained below.

[1783] Processing steps of the invention combined with emotion engine

[1784] User Registration Process

[1785] Step 1:

[1786] A user accesses the system and opens a login or registration form.

[1787] Step 2:

[1788] The user enters basic information such as the school of choice, exam subjects, name, and email address.

[1789] Step 3:

[1790] The terminal transmits the input information to the server.

[1791] Step 4:

[1792] The server stores the received information in a database.

[1793] Step 5:

[1794] The server generates a registration success message and sends it to the terminal.

[1795] Step 6:

[1796] The terminal displays a registration success message to the user.

[1797] Automatic generation process for mock exams

[1798] Step 1:

[1799] The user selects "Take a Practice Exam" from the dashboard.

[1800] Step 2:

[1801] The terminal sends a request to generate a mock test to the server.

[1802] Step 3:

[1803] The server references data based on the user's desired school and exam subjects, and uses a generation AI to generate mock exam questions.

[1804] Step 4:

[1805] The server stores the generated mock test questions in a database and sends them to the terminal.

[1806] Step 5:

[1807] The terminal displays the practice questions to the user and provides an answer input form.

[1808] Test result analysis process

[1809] Step 1:

[1810] The user completes the practice test and clicks the "Submit" button.

[1811] Step 2:

[1812] The terminal sends the answer data to the server.

[1813] Step 3:

[1814] The server receives the answer data and automatically scores and analyzes it using the generating AI.

[1815] Step 4:

[1816] The server calculates the score for each subject, the percentage of correct answers, and weak areas, and generates detailed feedback.

[1817] Step 5:

[1818] The server sends the analysis results and feedback to the device.

[1819] Step 6:

[1820] The device displays the feedback to the user.

[1821] Answer explanation process

[1822] Step 1:

[1823] If the user reviews the feedback and needs a detailed explanation of the incorrect question, they can click the "Show Explanation" button.

[1824] Step 2:

[1825] The device sends a description request to the server.

[1826] Step 3:

[1827] The server uses a generative AI to generate the answer process for the incorrect question and creates an explanatory text.

[1828] Step 4:

[1829] The server transmits the generated commentary data to the terminal.

[1830] Step 5:

[1831] The terminal displays the explanation to the user.

[1832] Online Material Recommendation Process

[1833] Step 1:

[1834] After the user checks the feedback, they select "View online learning materials."

[1835] Step 2:

[1836] The terminal sends a learning material request to the server.

[1837] Step 3:

[1838] The server uses AI to recommend optimal learning materials based on the user's learning progress data.

[1839] Step 4:

[1840] The server transmits the recommended teaching material information to the terminal.

[1841] Step 5:

[1842] The device displays the recommended learning materials to the user.

[1843] Similar problem generation process

[1844] Step 1:

[1845] The user selects "Generate similar questions."

[1846] Step 2:

[1847] The device sends a request to the server.

[1848] Step 3:

[1849] The server automatically generates similar questions using AI based on the user's weak areas.

[1850] Step 4:

[1851] The server sends the generated similar questions to the terminal.

[1852] Step 5:

[1853] The terminal displays similar questions to the user and provides an answer form.

[1854] Emotion Engine Process

[1855] Step 1:

[1856] During training, the user sends emotional data (e.g., facial expressions and tone of voice) to the system via a camera or microphone.

[1857] Step 2:

[1858] The device transmits the collected emotion data to a server.

[1859] Step 3:

[1860] The server uses an emotion engine to analyze the emotion data and identify the current emotional state (e.g., stress, confusion, concentration).

[1861] Step 4:

[1862] The server generates optimal feedback and learning advice based on the emotional state.

[1863] Step 5:

[1864] The server transmits the generated feedback to the terminal.

[1865] Step 6:

[1866] The device displays emotion-based feedback and advice to the user.

[1867] Specific examples

[1868] A user logs into the system and enters "XYZ University" as their preferred school and "Mathematics, English, and Physics" as their exam subjects. The server then uses generative AI to automatically generate mock exams for mathematics, English, and physics based on past exam information and data on successful candidates, and sends them to the device. When the user completes the mock exam and submits their answers, the server immediately analyzes the answers and provides detailed feedback and explanations.

[1869] Based on the analysis results, the server determines that the user has particular weaknesses in English grammar and recommends grammar questions and explanatory videos specific to that area. It also generates similar questions related to English grammar for the user to use for review.

[1870] While the user is learning, the server monitors the user's facial expressions via a camera, and if it detects a confused expression, the emotion engine analyzes that state. As a result of the analysis, the server determines that the user is feeling stressed and provides an encouraging message or advice on how to relax. For example, a message such as "Take a deep breath and relax. Next, I'll introduce some ways to relax" is displayed.

[1871] In this way, this system combines generative artificial intelligence and an emotion engine to efficiently provide learning support optimized for each test-taker's individual situation and emotions.

[1872] Example 2

[1873] Next, a description will be given of Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the robot 414 will be referred to as a "terminal."

[1874] Conventional exam study support systems lack personalized learning support tailored to each student's learning progress and areas of weakness, making it difficult for them to study efficiently. Furthermore, they do not provide appropriate feedback that takes into account the student's emotional state, making it difficult for them to maintain their motivation to study and often causing stress.

[1875] The specific processing by the specific processing unit 290 of the data processing device 12 in the second embodiment is realized by the following means.

[1876] In this invention, the server includes user interface means for inputting the examinee's desired school and basic information, test question generation means for automatically generating test questions based on the examinee's desired school information, analysis means for analyzing the mock test results answered by the examinee and visualizing weak areas and areas of weakness, answer explanation means for generating and displaying explanations based on the analysis results, learning material recommendation means for recommending online learning materials suited to the examinee's learning situation, similar question generation means for automatically generating similar questions based on the examinee's weak areas, emotion recognition means for recognizing and analyzing the examinee's emotional state, and emotion feedback means for providing feedback based on the emotion recognition results. This enables efficient and personalized learning support according to the learning situation and emotional state of each examinee.

[1877] "Generative artificial intelligence" refers to sophisticated algorithms that automatically generate information and data based on user input and prompts.

[1878] "Exam taker" refers to an individual studying for a particular exam or entrance examination.

[1879] "User interface means" refers to the interactive input means by which examinees input their preferred schools and basic information into the system.

[1880] "Exam question generation means" refers to a system function that automatically generates appropriate exam questions based on the desired school information and exam subjects entered by the examinee.

[1881] "Analysis means" refers to the system function that analyzes the mock test results given by test takers and clarifies their weak areas and weaknesses.

[1882] The "answer explanation means" refers to a function that generates and displays detailed explanations, especially for incorrect questions, based on the analysis results.

[1883] "Materials recommendation means" refers to the system function that recommends the most appropriate online materials and resources based on the candidate's learning progress and analysis results.

[1884] "Similar question generation means" refers to a function that automatically generates similar questions related to the examinee's weak areas.

[1885] "Emotion recognition means" refers to a function that analyzes the examinee's facial expressions and behavior to identify their current emotional state.

[1886] "Emotion feedback means" refers to a system function that provides appropriate feedback to test takers based on emotion recognition results.

[1887] The present invention is a system that efficiently supports test takers in studying for exams by utilizing generative artificial intelligence and an emotion engine. The system includes a user interface, test question generation, analysis, answer explanation, learning material recommendation, similar question generation, emotion recognition, and emotion feedback.

[1888] Users access the system and perform initial registration by entering their desired school, exam subjects, and basic information (name, email address, etc.). At this time, the information entered by the user is sent to the server and stored in a database.

[1889] The server automatically generates appropriate exam questions using a generative AI model based on the user's desired school information and exam subjects. The generated exam questions are sent to the device so that the user can view and answer them. Specifically, the server uses a generative AI model (e.g., GPT-4) to process data using Python scripts and MongoDB.

[1890] When a user completes a mock test and submits their answers, the server receives the answer data and automatically scores and analyzes it using a generative AI model. This results in clear scores for each subject, the percentage of correct answers, and areas of weakness. Scikit-learn and PostgreSQL are used for this analysis.

[1891] Based on the analysis results, the server generates detailed explanations for questions where the student got the answer wrong. The explanation data is sent to the device and can be viewed by the user. This explanation generation also uses a generative AI model and API communication (REST).

[1892] The server recommends the most suitable online learning materials and resources based on the analysis results and the user's learning progress. This is done using a recommendation engine (e.g., TensorFlow) and Elasticsearch. The recommended learning materials help the user progress efficiently.

[1893] If a user has difficulty with a particular problem, the server automatically generates similar problems related to that problem using a generative AI model. These similar problems are sent to the device and the user can use them for review. At this stage, a NoSQL database such as Firebase is used.

[1894] Furthermore, the user's facial expression data is analyzed using an emotion recognition means. When the user transmits their facial expressions through the camera while studying, the server analyzes the expressions using an emotion engine (e.g., Azure Face API) and generates useful feedback for the user's progress. This feedback may include encouraging messages or suggestions for relaxation techniques depending on the user's emotional state.

[1895] As a specific example, a user logs into the system, sets "ABC University" as their preferred school, and enters "Mathematics, English, and Physics" as their exam subjects. Based on this, the server uses past exam data and data on the trends of successful candidates to automatically generate mock exams for mathematics, English, and physics using generative AI. This mock exam data is sent to the device, and the user takes the mock exam and submits their answers after completing it. The server immediately analyzes the answers and provides detailed feedback and explanations. For example, it might recommend "videos explaining English grammar questions" or "similar questions specialized in grammar." Additionally, if the user's facial expressions during study indicate difficulty or stress, the server will provide advice and messages based on that.

[1896] Examples of prompts include:

[1897] "Please generate mock exams for Mathematics, English, and Physics for ABC University."

[1898] "Analyze users' practice test results and provide feedback with special emphasis on the area of ​​English grammar."

[1899] "Analyze facial expression data sent by the user using a camera and suggest relaxation methods when the user is feeling stressed."

[1900] In this way, the present invention combines generative artificial intelligence and an emotion engine to efficiently provide optimal learning support tailored to the individual circumstances and emotions of each test-taker.

[1901] The flow of the identification process in the second embodiment will be described with reference to FIG.

[1902] Step 1:

[1903] Initial registration

[1904] Users access the system and enter their desired school, exam subjects, and basic information (name, email address, etc.).

[1905] Input: desired school information, exam subject information, basic information (name, email address)

[1906] Output: Save to user profile database

[1907] Specific operation: A form is displayed on the user interface, and the user enters the school of choice and exam subjects and presses the submit button. The submitted data is transferred to the server and stored in a database. This process uses HTML forms, JavaScript, Python, and Django.

[1908] Step 2:

[1909] Automatic generation of exam questions

[1910] The server automatically generates appropriate exam questions using a generative AI model based on the desired school information and exam subjects entered by the user.

[1911] Input: desired school information, exam subject information

[1912] Output: Generated test question data

[1913] Specific operation: The server retrieves information about the school of choice and exam subjects from the user database and sends them as prompts to the generative AI model. The generative AI generates exam questions and returns them to the server. The server then sends the generated exam questions to the device. This process uses a generative AI model (e.g., GPT-4), Python scripts, and a database (MongoDB).

[1914] Step 3:

[1915] Mock exams and answer submission

[1916] The generated test questions are sent to the terminal, and the user takes the test. After completing the test, the answers are sent to the server.

[1917] Input: Generated test questions, user answer data

[1918] Output: Send answer data to the server

[1919] Specific operation: The test questions are displayed on the device, and when the user enters the answers and presses the submit button, the answer data is sent to the server. This process is done using React.js and Node.js.

[1920] Step 4:

[1921] Scoring and Analysis

[1922] The server receives the submitted answer data and automatically scores and analyzes it using a generative AI model.

[1923] Input: User's answer data

[1924] Output: Analysis results for each subject, score, correct answer rate, weak areas and weaknesses

[1925] How it works: The server passes the answer data to the analysis engine, which determines whether each question is correct or not. It also scores the answers and identifies areas where the user is weak. Scikit-learn and PostgreSQL are used for this analysis.

[1926] Step 5:

[1927] Providing answer explanations

[1928] Based on the analysis results, the server generates detailed explanations for the incorrect questions, and the explanation data is sent to the terminal for the user to view.

[1929] Input: Analysis results

[1930] Output: Detailed explanatory data

[1931] Specific operation: Based on the analysis results, the server sends prompts to the generative AI model to generate detailed explanations, which are then sent to the device. This process uses the generative AI model and API communication (REST).

[1932] Step 6:

[1933] Recommendation of teaching materials

[1934] The server recommends the most appropriate online learning materials and resources based on the analysis results and the user's learning progress.

[1935] Input: Analysis results, learning history

[1936] Output: Recommended online learning materials and resources

[1937] Specific operation: The server refers to the analysis results database, checks the user's past learning history and progress, selects appropriate learning materials, and notifies the user. This process uses a recommendation engine (TensorFlow) and Elasticsearch.

[1938] Step 7:

[1939] Generating similar problems

[1940] If a user feels uncomfortable with a particular problem, the server automatically generates similar problems related to that problem using a generative AI model.

[1941] Input: Weakness data

[1942] Output: Generated similar problem data

[1943] Specific operation: The server sends data on weak areas to the generative AI model as prompts, which generate similar questions. These are then sent to the device. This process uses the generative AI model and a NoSQL database such as Firebase.

[1944] Step 8:

[1945] Emotional Recognition and Feedback

[1946] The emotion engine collects the user's facial expression data and analyzes the user's emotional state during training. The server generates feedback based on the results and sends it to the device.

[1947] Input: User's facial expression data

[1948] Output: Sentiment analysis results, feedback data

[1949] Specific operation: Facial expression data collected through the camera is passed to the emotion engine, and the analysis results are obtained. The server generates appropriate feedback based on these results and sends it to the device. This process uses an emotion recognition API (e.g., Azure Face API) and a real-time database (Firebase).

[1950] (Application example 2)

[1951] Next, a description will be given of Application Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the robot 414 will be referred to as a "terminal."

[1952] Conventional test-taking support systems have limited functionality for analyzing test-takers' learning progress and weak areas, making them unable to adequately address individual learning needs. Furthermore, they provide uniform feedback without taking test-takers' emotional state into consideration, making it difficult to provide effective learning support. Furthermore, they are unable to recommend optimal products and services in real time, limiting their ability to improve customer experience in physical stores. The present invention aims to solve these problems.

[1953] The specific processing by the specific processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means. In this invention, the server includes a user interface means for inputting the examinee's desired school and basic information, a test question generation means for automatically generating test questions based on the examinee's desired school information, an analysis means for analyzing the mock test results answered by the examinee and visualizing the examinee's weak areas and areas of weakness, an answer explanation means for generating and displaying explanations based on the analysis results, a learning material recommendation means for recommending online learning materials suited to the examinee's learning situation, a similar question generation means for automatically generating similar questions based on the examinee's weak areas, an emotion analysis means for collecting customer facial expression recognition data and analyzing the emotional state, and a feedback means for providing feedback according to the emotional state. This enables efficient learning support tailored to individual learning needs and further improves customer experience by recommending optimal products and services in real time.

[1954] "Candidate" refers to any student studying or individual taking an examination.

[1955] "User interface means" refers to the interface through which prospective students and customers input basic information and information about their preferred schools.

[1956] "Exam question generation means" refers to a function that automatically creates exam questions based on information input by examinees.

[1957] "Analysis means" refers to the function that analyzes the mock test results submitted by test takers and analyzes weak areas and correct answer rates.

[1958] "Answer explanation means" refers to a function that provides explanations based on an analysis of mock test results to encourage understanding among test takers.

[1959] "Material recommendation means" refers to a function that recommends optimal learning resources and materials based on the test-taker's learning situation and areas of weakness.

[1960] "Similar problem generation means" refers to a function that automatically generates similar problems related to problems that are difficult to solve.

[1961] "Emotion analysis means" refers to the function of analyzing facial expressions and behavioral data of test takers and customers to analyze their emotional state.

[1962] "Feedback means" refers to the function of providing appropriate feedback or encouraging messages based on the results of sentiment analysis.

[1963] The present invention is a system that efficiently supports test takers and customers of brick-and-mortar stores by utilizing generative artificial intelligence and an emotion engine. Each means of the system will be specifically described below.

[1964] User Interface Means

[1965] Users access the system and input their desired school, exam subjects, basic information (name, email address, etc.) or customer information (name, preferred product category, etc.). This information is stored by the server and becomes the basic data for responding to the individual needs of the user.

[1966] Test question generation means

[1967] Based on the student's desired school information and exam subjects, the server uses AI to automatically generate appropriate exam questions. The generated questions are sent to the device, where the user can view and answer them.

[1968] Analysis means

[1969] When a user completes a mock test and submits their answers, the server receives the answer data and automatically scores and analyzes it using generative AI, which clarifies the score for each subject, the percentage of correct answers, and weak areas and weaknesses.

[1970] Answer explanation method

[1971] Based on the analysis results, the server generates detailed explanations for the questions that the user got wrong, providing step-by-step instructions on how to solve the problem. This explanation data is then sent to the user's device for viewing.

[1972] Teaching material recommendation method

[1973] The server recommends optimal online learning materials and resources based on the analysis results and the user's learning progress, allowing the user to study efficiently.

[1974] Similar problem generation means

[1975] If a user has difficulty with a particular problem, the server automatically generates similar problems related to that problem using a generation AI. These similar problems are sent to the device, and the user can answer them as training.

[1976] Emotion analysis means

[1977] The server collects facial expression data from the user through the camera and uses the emotion engine to analyze the user's emotional state during learning. For example, when the user looks at the camera, the server uses the emotion engine to analyze the user's facial expression and identify the emotional state that will affect the user's learning progress.

[1978] Feedback Methods

[1979] Based on the results of emotion analysis, the server generates feedback according to the user's emotional state. For example, if the user is confused, it will display relaxation advice or encouraging messages. It also improves the customer experience by recommending optimal products and services based on the results of analyzing customers' facial expressions in the store.

[1980] Specific examples

[1981] 1. A user logs into the system and enters "ABC University" as their preferred school and "Mathematics, English, and Physics" as their exam subjects. The server then uses AI to automatically generate mock exams for mathematics, English, and physics based on past exam information and data on successful candidates, and sends them to the device.

[1982] 2. Once a user completes a mock test and submits their answers, the server instantly analyzes the answers and provides detailed feedback and explanations. Based on the analysis results, the server determines that the user has particular weaknesses in English grammar and recommends grammar questions and explanatory videos specific to that area. Furthermore, the server generates similar questions related to English grammar for the user to review.

[1983] 3. The user's facial expression data is sent to the system via the camera and analyzed by the server's emotion engine. For example, if the user shows a confused expression while answering a question, the server will detect that emotional state and provide an encouraging message or advice on how to relax.

[1984] 4. Even in physical stores, when customers send facial expression data via camera, it is analyzed by the emotion engine and the most suitable products and promotions ...

Claims

1. A system that uses generative artificial intelligence to support students studying for exams, a user interface means for inputting the examinee's desired school and basic information; A test question generation means for automatically generating test questions based on information about the examinee's preferred school; Analyzing the mock exam results given by test takers and visualizing their weak areas and weaknesses, an answer explanation means for generating and displaying an explanation based on the analysis result; a teaching material recommendation means for recommending online teaching materials suitable for the learning situation of the examinee; a similar question generation means for automatically generating similar questions based on the weak areas of the examinee; A system including:

2. 10. The system of claim 1, further comprising a statistical analysis means for statistically analyzing data of test takers and providing reports to educational institutions or businesses.

3. 2. The system according to claim 1, further comprising a comparison means for comparing the mock test results of the examinee with past examinee data.

Images