system

Abstract

To provide a system.SOLUTION: A system includes: means for inputting the objectives of a test taker and the results of a simulation test per field; means for analyzing weak areas and strong areas on the basis of the results of the input simulation test; means for displaying a learning plan on the basis of the input objectives of the test taker and the results of the simulation test; means for detecting the feeling state of the test taker; and means for inputting the learning implementation situation of the test taker and changing the learning plan on the basis of the learning implementation situation and a change in the feeling of the test taker.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 taking exams are faced with the challenge of "I can't see the path to passing! I don't know what to do!" [Means for solving the problem]

[0005] The system inputs the test-taker's goals and mock test results into a generative AI system that analyzes their areas of strength and weakness. Based on the results, it displays the optimal study content, method, and schedule leading up to the test. Furthermore, it provides a system that inputs the student's study progress every day and makes corrections as needed. [Brief explanation of the drawings]

[0006] [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. 2 is a sequence diagram showing a flow of processing in the data processing system according to the first embodiment of the first form example. [Figure 12] FIG. 10 is a sequence diagram showing the flow of processing in the data processing system in Application Example 1 of Embodiment 1. [Figure 13] FIG. 10 is a sequence diagram showing a processing flow of a data processing system in a second embodiment of the second form example. [Figure 14] FIG. 10 is a sequence diagram showing the flow of processing in the data processing system in Application Example 2 of Embodiment 2. [Figure 15] FIG. 10 is a sequence diagram showing the flow of processing in a data processing system according to a third embodiment of the third embodiment. [Figure 16] FIG. 10 is a sequence diagram showing the flow of processing in the data processing system in Application Example 3 of Embodiment 3. [Figure 17]FIG. 10 is a sequence diagram showing the flow of processing in the data processing system in the first embodiment of the first form example when an emotion engine is combined. [Figure 18] FIG. 10 is a sequence diagram showing the flow of processing in the data processing system in Application Example 1 of Form Example 1 when an emotion engine is combined. [Figure 19] FIG. 10 is a sequence diagram showing the flow of processing in the data processing system in the second embodiment of the second form example when an emotion engine is combined. [Figure 20] FIG. 10 is a sequence diagram showing the flow of processing in the data processing system in Application Example 2 of Form Example 2 when an emotion engine is combined. [Figure 21] FIG. 10 is a sequence diagram showing the flow of processing in the data processing system in the third embodiment of the third form example when an emotion engine is combined. [Figure 22] FIG. 10 is a sequence diagram showing the flow of processing in the data processing system in Application Example 3 of Form Example 3 when an emotion engine is combined. DETAILED DESCRIPTION OF THE INVENTION

[0007] 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.

[0008] First, the terms used in the following description will be explained.

[0009] 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, the 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), an APU (Accelerated Processing Unit), or a TPU (TENSOR PROCESSING UNIT (registered trademark)).

[0010] 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.

[0011] 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.

[0012] 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.

[0013] 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."

[0014] [First embodiment]

[0015] FIG. 1 shows an example of the configuration of a data processing system 10 according to the first embodiment.

[0016] 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.

[0017] 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).

[0018] 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.

[0019] 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.

[0020] 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.

[0021] 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.

[0022] FIG. 2 shows an example of the main functions of the data processing device 12 and the smart device 14.

[0023] 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.

[0024] 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.

[0025] 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.

[0026] Next, the specific processing by the specific processing unit 290 of the data processing device 12 will be described.

[0027] "Example 1"

[0028] In one embodiment of the present invention, test takers enter their goals and mock test results into the system through a dedicated input interface, such as a form running on a web browser. The input information is analyzed by generative AI to identify the test taker's strengths and weaknesses.

[0029] "Example 2"

[0030] Next, the generative AI calculates the optimal study content, method, and schedule for the exam and displays it to the test-taker. The display is typically in the form of a calendar, showing specific study content and time for each day.

[0031] "Example 3"

[0032] Furthermore, test-takers enter their daily study schedules into the system. This is done, for example, through a dedicated application, and specific study time and content are recorded. Based on this information, the system makes adjustments as needed and updates the optimal study schedule.

[0033] The processing flow of each embodiment will be described below.

[0034] "Example 1"

[0035] Step 1: The test-taker enters their goals and mock test results into the system through a dedicated input interface, such as a form that runs on a web browser.

[0036] Step 2: The input information is analyzed by generative AI to identify the candidate's areas of strength and weakness. This analysis is carried out using deep learning techniques, for example.

[0037] "Example 2"

[0038] Step 1: The generative AI calculates the optimal study content, method, and schedule for the exam. This calculation is done using techniques such as reinforcement learning.

[0039] Step 2: The calculated optimal study content, method, and schedule are displayed to the test-taker. The display is, for example, in a calendar format, showing specific study content and time for each day.

[0040] "Example 3"

[0041] Step 1: The candidate enters their daily study history into the system. This is done, for example, through a dedicated application, and the specific study time and content are recorded.

[0042] Step 2: Based on this information, the system adjusts course as needed and updates the optimal study schedule. This adjustment is done using, for example, a genetic algorithm.

[0043] Example 1

[0044] Next, a description will be given of Example 1 of Form 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."

[0045] Conventional learning support systems for test takers have had difficulty effectively utilizing test takers' goals and mock test results to identify individual areas of strength and weakness. Furthermore, they were unable to provide appropriate feedback or course corrections according to test takers' learning status, resulting in a decline in learning efficiency.

[0046] The specific processing by the specific processing unit 290 of the data processing device 12 in Example 1 is realized by the following means. In this invention, the server includes a means for inputting the examinee's goals and mock test results, a means for analyzing the examinee's strong and weak areas, a means for displaying the optimal study content, method, and schedule leading up to the exam, a means for inputting the study progress status every day and correcting the course as needed, a means for accessing a dedicated input form using a web browser, a means for passing the input data to the generative AI model, a means for the generative AI model to analyze the data and return the analysis results, and a means for displaying the analysis results to the user. This enables effective learning support tailored to the examinee's individual learning needs.

[0047] "Exam takers' goals" refers to the specific learning goals and schools that exam takers want to achieve.

[0048] "Mock test results" refers to the scores and grades for each subject in the mock test.

[0049] "Means of input" refers to the interface that allows test takers to input their goals and mock test results into the system.

[0050] "Means of analysis" refers to the function for analyzing the input data and identifying the test-taker's areas of weakness and strength.

[0051] "Means of display" refers to the function for visually presenting analysis results and study plans to test takers.

[0052] "Means for course correction" refers to the function of adjusting the study plan according to the student's learning situation.

[0053] "Web browser" refers to software for viewing web pages on the Internet.

[0054] "Specialized input form" refers to a form on a web page designed for test takers to enter their goals and mock test results.

[0055] A "generative AI model" refers to an artificial intelligence model that analyzes input data and generates a specific result.

[0056] "Means of analysis" refers to the functionality that a generative AI model has to process input data and derive a specific result.

[0057] "Means for returning analysis results" refers to the function for the generative AI model to return the analysis results to the server.

[0058] "Means for displaying to the user" refers to the function that the server uses to present the analysis results to the test-taker.

[0059] This invention is a system that allows test-takers to input their goals and mock test results, and based on that, identifies areas of strength and weakness, and provides an optimal study plan. Specific embodiments of this system are described below.

[0060] Hardware and software used

[0061] Hardware:

[0062] Server: A server that receives data, analyzes it, and returns the results

[0063] Terminal: A computer or smartphone that allows users to input information

[0064] software:

[0065] Web browser: Software that allows users to access dedicated input forms (e.g., GOOGLE CHROME (registered trademark), Safari)

[0066] Generative AI model: An artificial intelligence model that analyzes input data and generates a specific result (e.g., OpenAI's GPT-4).

[0067] System Operation

[0068] User Action:

[0069] The user opens a web browser on their computer or smartphone and accesses the system's URL. A dedicated input form is displayed, where the user inputs their goal (e.g., passing the first science course at the University of Tokyo) and mock exam results (e.g., 80 points in math, 70 points in English, 60 points in physics, and 50 points in chemistry). Once the input is complete, the user clicks the submit button.

[0070] Server Action:

[0071] The server receives the data sent by the user. This data is sent as an HTTP POST request. The received data is passed to a generative AI model. The generative AI model uses, for example, OpenAI's GPT-4.

[0072] Analysis of generative AI models:

[0073] The generative AI model analyzes the received data and identifies the test-taker's areas of strength and weakness. This analysis uses natural language processing technology and machine learning algorithms. The analysis results are returned to the server in JSON format.

[0074] Server results:

[0075] The server receives the analysis results returned by the generative AI model and displays them to the user. The user can check the analysis results on a web browser. The analysis results are displayed in an easy-to-read format using HTML and CSS.

[0076] Examples of concrete examples and prompts

[0077] As a specific example, consider the case where a test-taker inputs the following information:

[0078] Goal: Pass the First Class Science Course at the University of Tokyo

[0079] Mock exam results: Math 80 points, English 70 points, Physics 60 points, Chemistry 50 points

[0080] When a user enters this information into the input form and clicks the submit button, the server receives this data and passes it to the generative AI model, which then analyzes it using prompt statements like the following:

[0081] Example prompt sentence:

[0082] The student's goal is to pass the entrance exam for the first science course at the University of Tokyo. The results of the mock exam are as follows:

[0083] Mathematics: 80 points

[0084] English: 70 points

[0085] Physics: 60 points

[0086] Chemistry: 50 points

[0087] Use this information to identify the candidate's areas of weakness and strength.

[0088] The generative AI model analyzes this prompt sentence and returns a result such as the following:

[0089] Example of analysis results:

[0090] Specialties: Mathematics, English

[0091] Weak areas: Physics, chemistry

[0092] The server displays the analysis results to the user, allowing the test-taker to use them as a reference when making future study plans.

[0093] The flow of the identification process in the first embodiment will be described with reference to FIG.

[0094] Step 1:

[0095] A user opens a web browser. A user opens a web browser on their computer or smartphone, for example by double-clicking a desktop icon or tapping an app on their smartphone. The input is the user's action, and the output is the launch of the web browser.

[0096] Step 2:

[0097] The user accesses a dedicated input form. The user accesses the dedicated input form by entering the system's URL (e.g., https: / / example.com). This form is built with HTML and JavaScript (registered trademark). The user enters the URL in the address bar and presses the Enter key. The input is the input of the URL, and the output is the display of the input form.

[0098] Step 3:

[0099] The user inputs their goal and mock exam results. The user inputs their goal (e.g., passing the first science course at the University of Tokyo) and their mock exam results (e.g., 80 points for math, 70 points for English, 60 points for physics, 50 points for chemistry) into the form. Text boxes are provided for entering scores for each subject. The input is the goal and mock exam results, and the output is the generation of the input data.

[0100] Step 4:

[0101] The user submits the input. The user clicks the submit button on the form. This sends the input data to the server. The submit button is an HTML <button>It is implemented with tags. The input is clicking the submit button, and the output is sending the data.

[0102] Step 5:

[0103] The server receives input data. The server receives data submitted by the user. This data is sent as an HTTP POST request. The server temporarily stores the received data. The input is the HTTP POST request, and the output is the stored data.

[0104] Step 6:

[0105] The server passes data to the generative AI model. The server passes the received data to the generative AI model. This generative AI model is, for example, OpenAI's GPT-4. The data is sent as an API request. The server sends an HTTP POST request to the API endpoint. The input is the stored data, and the output is the sending of the API request.

[0106] Step 7:

[0107] The generative AI model analyzes the data it receives. Specifically, it identifies the test-taker's areas of strength and weakness based on their goals and mock test results. Natural language processing technology and machine learning algorithms are used for the analysis. The input is the API request, and the output is the analysis results.

[0108] Step 8:

[0109] The generative AI model returns the analysis results to the server. The generative AI model returns the analysis results to the server. The analysis results are returned in JSON format. The server receives this JSON data. The input is the JSON data of the analysis results, and the output is receiving the data.

[0110] Step 9:

[0111] The server displays the analysis results to the user. The server receives the analysis results and displays them to the user. The user can check the analysis results on a web browser. The analysis results are displayed in an easy-to-read format using HTML and CSS. The input is the received analysis results, and the output is the display of the analysis results.

[0112] (Application example 1)

[0113] Next, a description will be given of Application Example 1 of Embodiment 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."

[0114] With conventional learning support systems, it was difficult to create an optimal individual study plan based on the student's goals and mock test results, and they often did not provide appropriate feedback or course corrections according to the student's learning progress. This resulted in students being unable to study efficiently, making it difficult for them to achieve their goals.

[0115] 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.

[0116] In this invention, the server includes means for inputting the test-taker's goals and mock test results, means for analyzing the test-taker's strengths and weaknesses, means for displaying the optimal study content, method, and schedule leading up to the test, means for inputting the study progress on a daily basis and correcting the course as needed, means for identifying the test-taker's strengths and weaknesses using generative AI and recommending optimal study content, and means for tracking the test-taker's progress and providing regular feedback. This enables test-taker to create an individually optimized study plan and study efficiently.

[0117] "Exam takers" are students who are studying with the aim of passing an exam.

[0118] A "goal" is a specific objective that a test-taker wants to achieve, such as passing an exam or improving their grades.

[0119] A "mock exam" is a mock test that students take in preparation for the actual exam.

[0120] The "means of input" is the interface that allows test takers to input their goals and mock test results into the system.

[0121] "Means for analysis" refers to a method or device for analyzing input data and identifying the examinee's areas of strength and weakness.

[0122] "Display means" refers to a method or device for visually presenting the analysis results and study plan to the examinee.

[0123] "Means for course correction" are methods or devices for adjusting the study plan according to the student's learning progress.

[0124] "Generative AI" is artificial intelligence that generates new information and analytical results based on input data.

[0125] "Learning content" refers to educational resources such as study materials and question sets that test takers use to study.

[0126] "Tracking" means the continuous monitoring and recording of a student's learning progress.

[0127] "Feedback" refers to providing information to test takers to inform them of their learning progress and areas for improvement.

[0128] To implement this invention, a terminal used by a test-taker, a server, and a generative AI model are used. Specific embodiments are described below.

[0129] 1. System Configuration

[0130] The system includes a device used by test takers, a server that processes data, and a generative AI model. The device can be a smartphone, tablet, or PC, and the server can be a cloud server or an on-premise server. The generative AI model uses an advanced natural language processing model such as OpenAI's GPT-3 (registered trademark).

[0131] 2. Program Processing

[0132] Enter the student's goals and mock test results

[0133] Candidates use the terminal to input their goals and mock test results. The input interface is a form that runs on a web browser and is designed to allow test takers to easily enter data.

[0134] Data analysis

[0135] The server receives the test-taker's input goals and mock test results and sends them to the generative AI model, which analyzes this data and identifies the test-taker's strengths and weaknesses.

[0136] Learning content recommendations

[0137] The server recommends optimal learning content to test-takers based on the analysis results from the generative AI model, and the recommended learning content is displayed on the device screen.

[0138] Progress tracking and feedback

[0139] As the student progresses through their studies, the device tracks their progress and sends it to the server. The server then periodically generates feedback based on the student's progress and sends it to the device. The feedback provides the student with information to check their progress and make course corrections as necessary.

[0140] 3. Hardware and software used

[0141] Hardware: Smartphones, tablets, PCs, cloud or on-premise servers

[0142] Software: Web browser, generative AI model (OpenAI GPT-3)

[0143] 4. Specific Examples

[0144] Example of student's goals and mock test results

[0145] A student sets the goal of "passing the entrance exam for the University of Tokyo" and enters the results of the mock exam as follows:

[0146] Student's goal: Passing the entrance exam to the University of Tokyo

[0147] Mock test results: {"Math": 70, "English": 85, "Physics": 60, "Chemistry": 75}

[0148] Examples of identifying areas of weakness and strength

[0149] The generative AI model identifies the individual as "bad at physics, good at English."

[0150] Examples of recommended learning content

[0151] The generative AI model recommends learning content as follows:

[0152] Weakness: Physics

[0153] Specialty: English

[0154] Recommend the best learning content.

[0155] In this way, test takers can create individually optimized study plans and progress with their studies efficiently.

[0156] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[0157] Step 1:

[0158] The user uses the terminal to input the goal and the results of the mock test.

[0159] The input interface is a form that runs on a web browser, where the user inputs their goal (e.g., "Pass the entrance exam for Tokyo University") and mock exam results (e.g., "Math: 70, English: 85, Physics: 60, Chemistry: 75") The input data is sent to the server in JSON format.

[0160] Step 2:

[0161] The server sends the received data to the generative AI model.

[0162] The server generates and sends prompts to a generative AI model (e.g., OpenAI GPT-3) to analyze the user's submitted goals and practice test results. An example of a prompt is shown below.

[0163] Student's goal: Passing the entrance exam to the University of Tokyo

[0164] Mock test results: {"Math": 70, "English": 85, "Physics": 60, "Chemistry": 75}

[0165] Identify your areas of weakness and strength.

[0166] The generative AI model analyzes this prompt and identifies areas of strength and weakness.

[0167] Step 3:

[0168] The generative AI model returns the analysis results to the server.

[0169] The generative AI model returns analysis results such as "I'm not good at physics, but I'm good at English" to the server. The server receives this information and proceeds to the next step.

[0170] Step 4:

[0171] The server recommends the most suitable learning content based on the analysis results.

[0172] Based on the analysis results from the generative AI model, the server generates a prompt to recommend the most suitable learning content to the user and sends it back to the generative AI model. An example of a prompt is as follows:

[0173] Weakness: Physics

[0174] Specialty: English

[0175] Recommend the best learning content.

[0176] The generative AI model generates optimal learning content based on this prompt and returns it to the server.

[0177] Step 5:

[0178] The server transmits the recommended learning content to the terminal.

[0179] The server receives the learning content returned by the generative AI model and sends it to the user's device, which receives this information and visually displays it to the user.

[0180] Step 6:

[0181] As the user progresses through their studies, the device tracks their progress and sends it to the server.

[0182] As the user progresses with their studies, the device continuously monitors their progress and periodically sends the data to the server, including study time, study content, progress status, and other information.

[0183] Step 7:

[0184] The server generates feedback based on the learning progress and sends it to the device.

[0185] The server analyzes the user's learning progress data and generates feedback as needed. The generated feedback includes information for checking the user's learning progress and making necessary course corrections. The server sends this feedback to the terminal, which then visually displays it to the user.

[0186] In this way, test takers can create individually optimized study plans and progress with their studies efficiently.

[0187] Example 2

[0188] Next, a description will be given of Example 2 of Form 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."

[0189] Conventional learning support systems have difficulty automatically generating and displaying optimal learning plans that match each student's individual learning situation and goals. Furthermore, they lacked the functionality to flexibly modify schedules according to the student's learning progress, making it difficult for students to study efficiently. Furthermore, there were also insufficient means to visually display the generated learning plans in an easy-to-understand manner.

[0190] 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.

[0191] In this invention, the server includes a means for inputting the examinee's goals and mock test results, a means for analyzing the examinee's strengths and weaknesses, a means for displaying the optimal study content, method, and schedule leading up to the exam, a means for inputting the study progress on a daily basis and correcting the course as needed, a means for inputting prompts into the generative AI model to generate the optimal study content, method, and schedule, a means for converting the generated schedule into a calendar format, and a means for displaying the calendar-format schedule. This makes it possible to automatically generate an optimal study plan tailored to the examinee's individual learning situation and display it in a visually easy-to-understand manner. Furthermore, the schedule can be flexibly modified according to the examinee's learning progress, allowing the examinee to study efficiently.

[0192] "Exam takers' goals" refer to the learning objectives and goals that exam takers want to achieve.

[0193] "Mock test results" refers to the grades or scores that a candidate obtained in a mock test.

[0194] "Weak areas" refer to areas of study that test-takers find particularly difficult to understand or master.

[0195] "Areas of strength" refers to areas of study that the candidate finds particularly easy to understand and master.

[0196] "Optimal learning content" refers to the learning items that are judged to be most effective in helping test takers achieve their goals.

[0197] "Optimal study methods" refer to specific study methods and approaches that maximize a test-taker's learning efficiency.

[0198] An "optimal schedule" refers to a timetable or dates planned to allow test takers to study efficiently.

[0199] A "generative AI model" refers to an algorithm or system that uses artificial intelligence technology to analyze data and generate an optimal learning plan.

[0200] A "prompt" refers to an instruction or question input to a generative AI model.

[0201] "Calendar format" refers to a format that visually displays learning content and schedules by date.

[0202] "Study implementation status" refers to the progress and results of the learning activities actually undertaken by the examinee.

[0203] "Correcting course" refers to adjusting plans and schedules according to the progress of learning.

[0204] The present invention is a system for automatically generating an optimal study plan according to the individual learning situation of each examinee and displaying the plan in a visually easy-to-understand manner. A specific embodiment of this system will be described below.

[0205] First, the user logs in to the system. The user enters their username and password on the system login screen and clicks the "Login" button. If the login is successful, the user's dashboard will be displayed.

[0206] Next, the user enters their learning goals (e.g., to improve their math grades) and their current academic level (e.g., their mock test scores) on the dashboard, and this information is sent to the server.

[0207] The server collects the user's past learning history data from the database. This includes the percentage of correct answers to questions previously solved and the results of mock exams. For example, it retrieves the data using an SQL query such as "SELECT FROM learning history WHERE user ID = '12345'".

[0208] Next, the server inputs a prompt into the generative AI model based on the collected data. The prompt includes the user's learning goals, academic level, and learning history data. An example of a specific prompt is, "This student wants to improve their math grades. Their past academic performance data is as follows. Please generate the optimal study content, method, and schedule in calendar format."

[0209] The generative AI model analyzes the prompt and generates the optimal learning content, method, and schedule for the user, creating a specific study plan such as "Spend two hours on math problems on Monday" or "Spend one hour on English listening on Tuesday."

[0210] The server converts the learned schedule obtained from the generative AI model into a calendar format using a JavaScript library to convert the schedule into a format that can be displayed visually.

[0211] Finally, the device displays a calendar-style schedule to the user. Users can check the study content and time for each day on the device screen and plan their studies accordingly. For example, they can check the schedule through an app on their smartphone or tablet.

[0212] This system automatically generates optimal study plans tailored to each student's individual learning situation, allowing them to visually confirm the plans. It also allows students to flexibly adjust their schedules according to their learning progress, enabling them to study efficiently.

[0213] The flow of the identification process in the second embodiment will be described with reference to FIG.

[0214] Step 1:

[0215] A user logs in to the system.

[0216] The user enters their username and password on the system's login screen and clicks the "Login" button. The entered username and password are sent to the server, which then checks the database for authentication. If authentication is successful, the user's dashboard is displayed.

[0217] Input: Username, Password

[0218] Output: User's dashboard screen

[0219] Step 2:

[0220] The user inputs their learning goals and current academic level.

[0221] The user enters their learning goal (e.g., "I want to improve my math grades") and their current academic level (e.g., their mock test score) into the form on the dashboard and clicks the "Submit" button. This information is sent to the server.

[0222] Input: Learning goals, current academic level

[0223] Output: Learning objectives and academic level sent to the server

[0224] Step 3:

[0225] The server collects the user's learning history data.

[0226] The server queries and collects the user's past learning history data from the database, including the percentage of correct answers to questions previously answered and the results of practice tests. For example, it retrieves the data using an SQL query such as "SELECT FROM learning history WHERE user ID = '12345'".

[0227] Input: User ID

[0228] Output: User learning history data

[0229] Step 4:

[0230] The server inputs a prompt sentence into the generative AI model.

[0231] The server inputs prompts into the generative AI model based on the collected data. The prompts include the user's learning goals, academic level, and learning history data. An example of a specific prompt is, "This student wants to improve their math grades. Their past academic performance data is as follows. Please generate the optimal study content, methods, and schedule in a calendar format."

[0232] Input: Learning goals, academic level, learning history data

[0233] Output: Prompt sentence to the generative AI model

[0234] Step 5:

[0235] A generative AI model generates optimal learning content, methods, and schedules.

[0236] The generative AI model analyzes the prompt and generates the optimal learning content, method, and schedule for the user, creating a specific study plan such as "Spend two hours on math problems on Monday" or "Spend one hour on English listening on Tuesday."

[0237] Input: prompt statement

[0238] Output: Optimal learning content, methods, and schedule

[0239] Step 6:

[0240] The server converts the generated schedule into a calendar format.

[0241] The server converts the learned schedule obtained from the generative AI model into a calendar format using a JavaScript library to convert the schedule into a format that can be displayed visually.

[0242] Input: Optimal learning content, methods, and schedule

[0243] Output: Calendar format schedule

[0244] Step 7:

[0245] The terminal displays the schedule to the user.

[0246] The device displays a calendar-style schedule to the user. Users can check the study content and time for each day on the device screen and plan their studies accordingly. For example, they can check their schedule through an app on their smartphone or tablet.

[0247] Input: Calendar-style schedule

[0248] Output: The schedule as seen by the user

[0249] (Application example 2)

[0250] Next, a description will be given of Application Example 2 of Form 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."

[0251] With conventional exam preparation support systems, it was difficult to generate an optimal study schedule based on the student's goals and mock test results, and the course corrections based on the student's study progress had to be done manually, making it difficult to study efficiently.Furthermore, the generated schedule was not displayed in a visually easy-to-understand manner, making it difficult for the student to understand the plan.

[0252] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 2 is realized by the following means.

[0253] In this invention, the server includes a means for inputting the examinee's goals and mock test results, a means for analyzing the examinee's strengths and weaknesses, a means for displaying the optimal study content, method, and schedule leading up to the exam, a means for inputting the study progress status every day and correcting the course as needed, a means for generating an optimal study schedule using a generative AI model, and a means for displaying the generated schedule in calendar format. This allows the examinee to efficiently and effectively create a study plan and make appropriate course corrections according to their progress.

[0254] "Exam takers' goals" refers to the specific learning goals and schools that exam takers want to achieve.

[0255] "Mock test results" refers to evaluation data such as mock test scores, marks, and deviation values.

[0256] "Weak areas" refer to areas of study or subjects that test-takers find particularly difficult to understand or master.

[0257] "Areas of strength" refers to areas of study or subjects that are particularly easy for a candidate to understand and master, and in which they achieve high grades.

[0258] "Optimal study content" refers to the learning content that is most effective for helping test-takers achieve their goals.

[0259] "Method" refers to the specific means or approach to studying.

[0260] A "schedule" refers to a plan that arranges study content and methods in terms of time.

[0261] A "generative AI model" refers to an algorithm or system that uses artificial intelligence technology to generate data and calculate the optimal study schedule.

[0262] "Calendar format" refers to a format that visually displays study content and schedules by date.

[0263] "Correcting your course" means adjusting your plan according to your study progress and keeping it in optimal condition.

[0264] A system for implementing this invention includes a means for inputting the test-taker's goals and mock test results, a means for analyzing the test-taker's strengths and weaknesses, a means for displaying the optimal study content, method, and schedule leading up to the test, a means for inputting the study progress status every day and correcting the course as needed, a means for generating an optimal study schedule using a generative AI model, and a means for displaying the generated schedule in calendar format.

[0265] Program processing explanation

[0266] The server provides an interface for students to input their goals and mock test results. Students input their goals and mock test results using devices such as smartphones or PCs. This data is sent to the server and stored in a database.

[0267] Next, the server uses a generative AI model to analyze the student's strengths and weaknesses. The generative AI model generates an optimal study schedule based on the input data. It also uses OpenAI's API to generate prompts and input them into the AI ​​model.

[0268] The generated study schedule is displayed in calendar format. Students can check the study content and method for each date on their smartphone or computer screen. For example, use the following prompts:

[0269] Example prompt sentence:

[0270] Generate an optimal study schedule for the following subjects for students taking the exam on 2023-12-01: Mathematics, English, Physics

[0271] Furthermore, students can input their daily study progress. Based on this data, the server uses the generative AI model again to correct the schedule, allowing students to maintain an optimal study plan at all times.

[0272] Specific examples

[0273] For example, if a student needs to study three subjects: mathematics, English, and physics, the server generates the following schedule:

[0274] 2023-11-01: Mathematics - Calculus

[0275] 2023-11-02: English - Grammar

[0276] 2023-11-03: Physics - Mechanics

[0277] This schedule is displayed in a calendar format, allowing students to easily check their daily study content. Furthermore, the schedule is automatically updated according to their study progress, enabling efficient study.

[0278] The hardware used is a smartphone or a PC, allowing test-takers to plan their studies efficiently and effectively, and to make appropriate course corrections as they progress.

[0279] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[0280] Step 1:

[0281] Users use devices such as smartphones or PCs to input their test-taking goals and mock test results. The input data is sent to a server and stored in a database. The input data includes the test-taker's preferred school, target score, mock test results, etc.

[0282] Step 2:

[0283] The server uses a generative AI model to analyze the student's strengths and weaknesses based on their goals and mock test results. Specifically, it analyzes the input grade data and calculates the score distribution and deviation value for each subject. This allows it to identify areas where the student needs to particularly improve and areas where they are already strong.

[0284] Step 3:

[0285] The server uses a generative AI model to generate an optimal study schedule based on the student's strengths and weaknesses. It generates prompts and inputs them into the AI ​​model to calculate the study content and methods for each subject. For example, the following prompts can be used:

[0286] Generate an optimal study schedule for the following subjects for students taking the exam on 2023-12-01: Mathematics, English, Physics

[0287] The generated schedule will specify the study content and time for each day.

[0288] Step 4:

[0289] The server displays the generated study schedule in calendar format. Users can check the study content and method for each date on their smartphone or computer screen. The calendar format makes it visually easy to understand and makes it easy to plan.

[0290] Step 5:

[0291] Users enter their daily study progress on their device. The entered data is sent to the server and stored in a database. By recording their study progress and what they have done, they can check the degree to which they have achieved their plan.

[0292] Step 6:

[0293] The server then uses the generative AI model again to correct the schedule based on the user's study progress input. Specifically, it analyzes progress and adjusts study content and methods as necessary. This allows test-takers to maintain an optimal study plan at all times.

[0294] Step 7:

[0295] The server then displays the revised schedule in calendar format, allowing the user to check the updated schedule and plan their next study. This allows for efficient and effective study.

[0296] Example 3

[0297] Next, a description will be given of a third embodiment of the third embodiment. 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."

[0298] Conventional learning management systems have difficulty automatically generating optimal study schedules based on students' learning status and correcting their course in real time. Furthermore, there was a lack of a way to efficiently manage the generated schedules and provide them to users, which meant that the effectiveness of learning could not be maximized.

[0299] The specific processing by the specific processing unit 290 of the data processing device 12 in the third embodiment is realized by the following means.

[0300] In this invention, the server includes means for inputting the examinee's goals and mock test results, means for analyzing the examinee's strengths and weaknesses, means for displaying the optimal study content, method, and schedule leading up to the exam, means for inputting the study progress status every day and correcting the course as needed, means for sending prompts to the generative AI model to generate an optimal study schedule, and means for saving the generated study schedule in a database and sending it to the user's terminal. This makes it possible to generate an optimal study schedule in real time based on the examinee's study status and efficiently manage and provide it.

[0301] "Exam takers' goals" refer to the learning objectives and goals that exam takers want to achieve.

[0302] "Mock test results" refers to the grades and evaluations that test takers receive in mock tests.

[0303] "Weak areas" refer to subjects or topics that test-takers find particularly difficult to understand or master.

[0304] "Areas of strength" refers to subjects or topics that a candidate finds particularly easy to understand and master.

[0305] "Study content" refers to the specific subjects and topics that test takers will study.

[0306] "Study methods" refer to the specific techniques and approaches that test takers use to advance their studies.

[0307] A "study schedule" refers to the timetable and dates planned for a test-taker to study.

[0308] "Study implementation status" refers to the content and amount of study that the test taker actually undertook.

[0309] "Correcting the course" refers to reviewing and optimizing a student's study plan.

[0310] A "generative AI model" refers to a model that uses artificial intelligence to analyze data and generate an optimal learning schedule.

[0311] A "prompt" refers to an instruction or question input to a generative AI model.

[0312] "Database" refers to an information management system for storing test takers' learning data and generated learning schedules.

[0313] "User's device" refers to electronic devices such as smartphones and tablets used by test takers.

[0314] This invention is a system for managing the learning status of test takers and providing them with an optimal study schedule. The system includes means for inputting the test taker's goals and mock test results, means for analyzing their strengths and weaknesses, means for displaying the optimal study content, method, and schedule leading up to the test, means for inputting the study progress status every day and correcting the course as needed, means for sending prompts to a generative AI model to generate an optimal study schedule, and means for saving the generated study schedule in a database and sending it to the user's terminal.

[0315] Users use a dedicated application to input their study status from devices such as smartphones or tablets. The input data includes specific study time and content. For example, information such as "October 1st: 2 hours of math, 1 hour of English" may be entered.

[0316] The terminal sends the entered data to the server. This transmission is securely performed using the HTTPS protocol. The server stores the received data in a MySQL (registered trademark) database. The stored data is used to record the student's learning status in detail.

[0317] The server sends a prompt to the generative AI model based on the saved data. The prompt includes past learning history. For example, the server might send the following to the generative AI model: "Test-taker A's study time and content over the past week are as follows. Based on this, please suggest the optimal study schedule for the next week."

[0318] The generative AI model generates an optimal study schedule based on the prompt. For example, it might generate a schedule such as "October 4th: 1.5 hours of math, 1.5 hours of English." The generated schedule is returned to the server.

[0319] The server saves the generated schedule in a database and sends it to the user's device. The user can check the new study schedule through the device application. For example, a schedule such as "October 4th: 1.5 hours of math, 1.5 hours of English" may be displayed.

[0320] This system allows test-takers to receive an optimal study schedule in real time, enabling them to study efficiently. Furthermore, by using a generative AI model, it is possible to provide a customized schedule according to each individual's learning situation. The flow of the specific processing in Example 3 will be explained using FIG. 15.

[0321] Step 1:

[0322] The user inputs their study status.

[0323] The user opens a dedicated application and inputs the study time and content. For example, they input specific information such as "October 1st: 2 hours of math, 1 hour of English." The input data is temporarily stored in the device's memory.

[0324] Step 2:

[0325] The terminal sends the input data to the server.

[0326] The terminal sends the data entered by the user to the server. The input data is sent in the format of "October 1st: 2 hours of math, 1 hour of English." The server analyzes the received data and prepares it to be saved in the database.

[0327] Step 3:

[0328] The server stores the data in a database.

[0329] The server parses the received JSON data and inserts it into the "Study Record" table in the MySQL database. For example, data such as "October 1st: 2 hours of math, 1 hour of English" is saved in the database. This records the user's study status.

[0330] Step 4:

[0331] The server sends a prompt to the generative AI model.

[0332] The server sends a prompt to the generative AI model based on the stored data. The prompt includes past learning history. For example, the following sentence is sent to the generative AI model: "Test-taker A's study time and content for the past week are as follows. Based on this, please suggest the optimal study schedule for the next week." The input data is the study record for the past week, and the output is the prompt sent to the generative AI model.

[0333] Step 5:

[0334] A generative AI model generates an optimal learning schedule.

[0335] The generative AI model receives prompts and generates an optimal learning schedule. For example, it generates a schedule such as "October 4th: 1.5 hours of math, 1.5 hours of English." The input data is the prompts, and the output is the generated learning schedule.

[0336] Step 6:

[0337] The server stores the generated schedule in a database.

[0338] The server inserts the schedule received from the generative AI model into the "Study Schedule" table in the database. For example, data such as "October 4th: 1.5 hours of math, 1.5 hours of English" is saved. This records the generated schedule.

[0339] Step 7:

[0340] The server transmits the schedule to the user's terminal.

[0341] The server transmits the stored schedule to the user's terminal. The input data is the generated schedule, and the output is the data transmitted to the user's terminal.

[0342] Step 8:

[0343] The user checks the schedule.

[0344] The user opens the app's "Schedule" screen and checks the new study schedule. For example, a schedule like "October 4th: 1.5 hours of math, 1.5 hours of English" is displayed. This allows the user to confirm and implement the optimal study plan.

[0345] (Application example 3)

[0346] Next, a description will be given of Application Example 3 of Form Example 3. 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."

[0347] Conventional study management systems for test takers provide study schedules based on test takers' goals and mock test results, but do not adequately adjust their study schedules in real time according to their current study status. Furthermore, they lack a means to efficiently manage the operating status and work content of factory robots and generate optimal work schedules. This leads to problems such as reduced learning efficiency for test takers and reduced work efficiency for factory robots.

[0348] The specific processing by the specific processing unit 290 of the data processing device 12 in Application Example 3 is realized by the following means. In this invention, the server includes a means for inputting the examinee's goals and mock test results, a means for analyzing the examinee's strengths and weaknesses, a means for displaying the optimal study content, method, and schedule leading up to the exam, a means for inputting the study progress status daily and correcting the course as needed, a means for recording the robot's operating status and work content, a means for generating and updating an optimal work schedule based on the recorded data, a means for generating an optimal schedule using a generative AI model, a means for generating prompt sentences and sending them to the generative AI model, and a means for obtaining the optimal schedule from the generative AI model. This makes it possible to improve the examinee's learning efficiency and maximize the work efficiency of factory robots.

[0349] "Exam takers' goals" refer to the learning objectives and goals that exam takers want to achieve.

[0350] "Mock test results" refers to the grades and evaluations of the mock test.

[0351] "Weak areas" refer to areas of study that test-takers find particularly difficult to understand or master.

[0352] "Areas of strength" refers to areas of study that are particularly easy for the candidate to understand and master.

[0353] "Study content" refers to the specific subjects and topics that test takers will study.

[0354] "Study methods" refer to the methods and techniques that test takers use to advance their studies.

[0355] "Schedule" refers to the timetable or plan for a test-taker's studies.

[0356] "Study implementation status" refers to the progress and content of the study that the test-taker actually undertook.

[0357] "Correcting the course" refers to reviewing and optimizing a student's study plan.

[0358] "Robot operation status" refers to the progress and status of the work that a factory robot is actually performing.

[0359] "Work content" refers to the specific work or tasks that a factory robot will perform.

[0360] "Recorded data" refers to saved information about the robot's operating status and work content.

[0361] A "generative AI model" refers to a model that uses artificial intelligence to analyze data and generate optimal schedules and plans.

[0362] A "prompt" refers to an instruction or question that is input to a generative AI model.

[0363] An "optimal schedule" refers to a plan or timetable generated to maximize the efficiency of students or robots.

[0364] A system for implementing this invention includes means for inputting the test-taker's goals and mock test results, means for analyzing the test-taker's strengths and weaknesses, means for displaying the optimal study content, method, and schedule leading up to the test, means for inputting the study progress status every day and correcting the course each time, means for recording the robot's operating status and work content, means for generating and updating an optimal work schedule based on the recorded data, means for generating an optimal schedule using a generative AI model, means for generating prompt text and sending it to the generative AI model, and means for obtaining the optimal schedule from the generative AI model.

[0365] The server provides an interface for students to input their goals and mock exam results. Students input this information through a dedicated application. The entered data is used on the server to analyze their strengths and weaknesses. Based on the analysis results, the server generates optimal study content, methods, and schedules leading up to the exam and displays them to the student.

[0366] Furthermore, students enter their daily study progress into the application. Based on this information, the server uses a generative AI model to generate an optimal schedule and makes course corrections as necessary. The server generates prompt sentences and sends them to the generative AI model to obtain the optimal schedule.

[0367] As a concrete example, if a test-taker inputs study content such as "Solve math problems for two hours," the server records that information and sends the following prompt to the generative AI model:

[0368] Example prompt sentence:

[0369] Current schedule: 2 hours of math worksheets

[0370] Generate the optimal schedule.

[0371] On the other hand, factory robots require sensors and a logging system to record the operating status and work content of each robot. The robots send their operating status and work content to a server, and the server generates and updates an optimal work schedule based on that data. A generative AI model is used to generate prompt sentences and obtain the optimal schedule.

[0372] The hardware used includes smartphones and tablets to accept input from test takers, sensors and logging systems to record the operating status of factory robots, and software using Python, OpenAI APIs, and standard libraries for data processing (e.g., datetime, json).

[0373] This system will improve the learning efficiency of test takers and maximize the work efficiency of factory robots.

[0374] The flow of the specific processing in Application Example 3 will be described with reference to FIG.

[0375] Step 1:

[0376] The user (candidate) enters their goals and mock test results through a dedicated application. The entered data is sent to the server, which receives the data and stores it in a database. The input data includes the candidate's goals, mock test scores, and scores for each subject.

[0377] Step 2:

[0378] The server analyzes the test-taker's areas of strength and weakness based on the test-taker's input data. Specifically, it analyzes mock test results and calculates the score distribution for each subject. Subjects with low scores are classified as weak areas, and subjects with high scores are classified as strong areas. The analysis results are saved in a database.

[0379] Step 3:

[0380] The server generates the optimal study content, method, and schedule for the exam based on the analysis results. The generated schedule takes into consideration the test-taker's goals and weak areas. The generated schedule is displayed in the user's (test-taker's) application.

[0381] Step 4:

[0382] The user (candidate) enters their daily study status into the application. The input data includes subjects studied, study time, study content, etc. The input data is sent to the server and saved in the database.

[0383] Step 5:

[0384] The server uses a generative AI model to generate an optimal schedule based on the student's study progress. Specifically, it generates a prompt and sends it to the generative AI model. The prompt includes the student's current schedule and progress.

[0385] Step 6:

[0386] The generative AI model receives the prompt sentence and generates an optimal schedule. The generated schedule is sent to the server, which receives the schedule and stores it in a database.

[0387] Step 7:

[0388] The server displays the generated optimal schedule in the user's (candidate's) application, and the user can proceed with their studies based on the new schedule.

[0389] Step 8:

[0390] In the case of factory robots, the robots send their operating status and work details to a server via sensors and a logging system, and the server receives this data and stores it in a database.

[0391] Step 9:

[0392] The server uses a generative AI model to generate an optimal work schedule based on the robot's operating status and work content. It generates a prompt statement and sends it to the generative AI model. The prompt statement includes the current work schedule and operating status.

[0393] Step 10:

[0394] The generative AI model receives the prompt sentence and generates an optimal work schedule. The generated schedule is sent to the server, which receives the schedule and stores it in a database.

[0395] Step 11:

[0396] The server sends the generated optimal work schedule to the robot, which can then proceed with its work based on the new schedule.

[0397] 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.

[0398] "Example 1"

[0399] As one embodiment of the present invention, a system including an emotion engine for recognizing the emotions of test-takers is provided. This emotion engine infers emotions from the test-takers' facial expressions, tone of voice, study behavior, etc. while they are studying. Specifically, when the test-takers are using a study device (e.g., a PC or tablet), the system captures the test-takers' facial expressions and voice using the device's camera and microphone, and analyzes this information to infer emotions.

[0400] "Example 2"

[0401] The emotion engine also detects changes in the student's emotions depending on their learning status and provides feedback to the generative AI. Specifically, if the emotion engine detects worsening emotions, such as when the student is struggling with their studies or their motivation to study is declining, it will pass that information on to the generative AI.

[0402] "Example 3"

[0403] The generative AI optimizes the student's study schedule based on feedback from the emotion engine. Specifically, if the emotion engine receives information indicating a worsening emotion, such as when the student is struggling with their studies or their motivation to study is declining, the generative AI will adjust the study schedule taking that information into account. For example, it will reduce the study time for subjects the student is weak in and increase the study time for subjects they are strong in.

[0404] The processing flow of each embodiment will be described below.

[0405] "Example 1"

[0406] Step 1: The student begins studying using a study device (e.g., computer or tablet).

[0407] Step 2: Use the device's camera and microphone to capture the test taker's facial expressions and voice.

[0408] Step 3: The captured facial and voice information is sent to the emotion engine.

[0409] Step 4: The emotion engine analyzes the information and estimates the test-taker's emotions.

[0410] "Example 2"

[0411] Step 1: The emotion engine detects changes in emotions according to the test-taker's learning situation.

[0412] Step 2: If the emotion engine detects an aggravating emotion, it communicates that information to the generative AI.

[0413] "Example 3"

[0414] Step 1: The generative AI receives feedback from the emotion engine.

[0415] Step 2: The generative AI takes into account the information it receives and adjusts the student's study schedule.

[0416] Step 3: For example, make adjustments such as reducing the study time for areas in which the test-taker is weak and increasing the study time for areas in which the test-taker is strong.

[0417] Example 1

[0418] Next, a description will be given of Example 1 of Form 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."

[0419] Conventional support systems for test takers can input test taker goals and mock test results and analyze their strengths and weaknesses, but they do not provide learning support that takes test takers' emotions into consideration. As a result, it is difficult to properly manage test takers' motivation and concentration, and there is an issue of not being able to achieve optimal learning results.

[0420] 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.

[0421] In this invention, the server includes a means for inputting the examinee's goals and mock test results, a means for analyzing the examinee's strengths and weaknesses, a means for displaying the optimal study content, method, and schedule leading up to the exam, a means for inputting the examinee's study progress every day and correcting the course as needed, and a means for capturing the examinee's facial expressions and voice and analyzing their emotions. This makes it possible to provide comprehensive study support that takes into account not only the examinee's learning progress but also their emotional state.

[0422] "Exam takers' goals" refer to the specific learning goals and schools they wish to attend.

[0423] "Mock test results" refers to data showing the scores and grades of test takers on mock tests.

[0424] "Means of input" refers to the interface or device that allows test takers to input their goals and mock test results into the system.

[0425] "Means of analysis" refers to algorithms or software that analyze the input data and identify the test-taker's areas of strength and weakness.

[0426] "Means of display" refers to a display or screen used to visually present analysis results and study plans to test takers.

[0427] "Tracking tools" refers to algorithms and software that adjust study plans based on a student's learning situation.

[0428] "Means for capturing facial expressions and voices" refers to cameras and microphones used to collect the facial expressions and voices of test takers.

[0429] "Means for analyzing emotions" refers to algorithms or software that analyze collected facial and vocal data to estimate the test-taker's emotional state.

[0430] "Generative AI" refers to artificial intelligence that analyzes and generates data based on input data.

[0431] An "emotion engine" refers to software or algorithms that analyze test-takers' facial expressions and voice data to estimate their emotions.

[0432] This invention is a system that inputs the test-taker's goals and mock test results, analyzes their areas of strength and weakness, displays the optimal study content, method, and schedule leading up to the test, inputs the student's study progress every day, and makes corrections as needed. It also includes a function to capture the student's facial expressions and voice and analyze their emotions.

[0433] System configuration

[0434] 1. Enter the student's goals and mock test results

[0435] Users access a dedicated form on a web browser and enter their goals and mock exam results. For example, using Google Chrome, they can enter "Preferred university: University of Tokyo" and "Mock exam results: Math 80 points, English 70 points, Physics 60 points." Once they've finished entering the information, they click the submit button.

[0436] 2. Data Analysis

[0437] The server receives the data sent by the user. The received data is passed to a generative AI model (e.g., OpenAI's GPT-4). The generative AI model analyzes the input data and processes the data using statistical methods based on the scores for each subject.

[0438] 3. Identify your weaknesses and strengths

[0439] The server receives the analysis results from the generative AI model and identifies the user's areas of strength and weakness. For example, if a student's score is high in math and low in physics, math is identified as a strong area and physics as a weak area. The identified information is reflected in the user's study plan.

[0440] 4. Use of Learning Devices

[0441] A user begins learning using a learning device such as a PC or tablet, for example by accessing an online learning platform and viewing learning content.

[0442] 5. Capturing facial expressions and voice

[0443] The device captures the user's facial expressions and voice in real time during learning using a camera and microphone, such as the built-in camera and microphone of a PC.

[0444] 6. Emotion Analysis

[0445] The server receives the facial expression and voice data sent from the device. The received data is passed to an emotion engine (for example, Microsoft® Azure® Emotion API). The emotion engine analyzes the facial expression and tone of voice to estimate the user's emotion. For example, if the user is smiling, it is estimated to be "positive," and if they are frowning, it is estimated to be "negative."

[0446] Specific examples

[0447] Enter the student's goals and mock test results

[0448] The user enters "University of choice: University of Tokyo" and "Mock exam results: Math 80 points, English 70 points, Physics 60 points" into the form on the web browser and clicks the submit button.

[0449] Data analysis

[0450] The server passes the received data to a generative AI model (GPT-4) and analyzes the scores for each subject. For example, it verifies that the score for math is 80 points.

[0451] Identifying areas of weakness and strength

[0452] Based on the analysis results, the server identifies areas where the user is strong in mathematics and weak in physics, and reflects this in the user's study plan.

[0453] Use of learning devices

[0454] Users use their computers to access the online learning platform and solve math problems.

[0455] Capturing facial expressions and voice

[0456] The device uses a camera and microphone to capture the user smiling and solving problems while studying.

[0457] Emotion Analysis

[0458] The server receives the data sent from the device and uses the Emotion API to analyze the user's smile as "positive."

[0459] Prompt Sentence Examples

[0460] "Please explain a system that inputs a student's goals and practice test results and uses generative AI to identify their areas of strength and weakness. Also, explain how an emotion engine can be used to recognize emotions during learning."

[0461] The flow of the identification process in the first embodiment will be described with reference to FIG.

[0462] Step 1:

[0463] The user enters their goals and practice test results.

[0464] The user accesses a dedicated form on a web browser and enters "University of choice: University of Tokyo" and "Mock exam results: Math 80 points, English 70 points, Physics 60 points." Once the information is complete, the user clicks the send button. The input data is sent to the server.

[0465] Step 2:

[0466] The server receives the input data and analyzes it using a generative AI model.

[0467] The server receives the goal and mock test results data sent by the user. The received data is passed to a generative AI model (e.g., GPT-4). The generative AI model analyzes the scores for each subject and processes the data using statistical methods. For example, it verifies that the math score is 80 points. The analysis results are returned to the server.

[0468] Step 3:

[0469] The server identifies areas of weakness and strength based on the analysis results.

[0470] The server receives the analysis results from the generative AI model and identifies the user's areas of strength and weakness. For example, if a user's score is high in mathematics and low in physics, mathematics is identified as a strong area and physics as a weak area. The identified information is reflected in the user's study plan. The study plan is sent from the server to the user.

[0471] Step 4:

[0472] The user studies using a learning device.

[0473] Users begin learning using a learning device such as a PC or tablet. For example, they access an online learning platform and view learning content. Data from the learning process is stored on the device.

[0474] Step 5:

[0475] The device captures the user's facial expressions and voice through a camera and microphone.

[0476] The device captures the user's facial expressions and voice in real time using a camera and microphone, such as the built-in camera and microphone of a PC, and the captured data is sent to a server.

[0477] Step 6:

[0478] The server analyzes the user's emotions using an emotion engine.

[0479] The server receives the facial expression and voice data sent from the device. The received data is passed to the emotion engine. The emotion engine analyzes the facial expression and tone of voice to estimate the user's emotion. For example, if the user is smiling, it is estimated to be "positive," and if they are frowning, it is estimated to be "negative." The analysis results are stored on the server and fed back to the user as needed.

[0480] (Application example 1)

[0481] Next, a description will be given of Application Example 1 of Embodiment 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."

[0482] Conventional learning support systems can input the student's goals and mock test results and analyze their strengths and weaknesses, but there was no system that could analyze the worker's skills and work efficiency and propose optimal work arrangements. There was also a lack of means to recognize the worker's emotions and provide support to reduce stress and fatigue. This meant that work efficiency was not being improved sufficiently and worker health management was not being carried out sufficiently.

[0483] The specific processing by the specific processing unit 290 of the data processing device 12 in Application Example 1 is realized by the following means. In this invention, the server includes means for inputting the examinee's goals and mock test results, means for analyzing the examinee's strengths and weaknesses, means for displaying the optimal study content, method, and schedule leading up to the exam, means for inputting the study progress status every day and correcting the course as needed, means for inputting the worker's skills and work efficiency, means for analyzing the worker's strengths and weaknesses, means for analyzing the worker's facial expressions and tone of voice to estimate emotions, and means for providing support to reduce the worker's stress and fatigue. This not only provides study support for examinees, but also enables the worker's work efficiency to be improved and health management to be achieved.

[0484] "Exam takers' goals" are specific goals regarding learning and exams that exam takers want to achieve.

[0485] "Mock test results" are data showing the scores and evaluations of mock tests.

[0486] "Input means" refers to an interface or device for inputting information into a system.

[0487] "Weak areas" are areas or subjects that examinees or workers find particularly difficult to understand or perform.

[0488] "Area of ​​expertise" refers to an area or subject in which a candidate or worker is particularly good.

[0489] "Means for analysis" are methods or tools for analyzing input data and extracting specific information.

[0490] "Optimal study content, methods, and schedule" refers to the study plans and techniques that are most suitable for test-takers to study efficiently.

[0491] "Display means" refers to a device or interface for visually displaying analysis results and proposals.

[0492] "Study implementation status" refers to the record of the study activities and progress that the examinee actually undertook.

[0493] "Course correction tools" are methods and tools for adjusting learning plans and work plans as needed.

[0494] "Worker skills" refers to the level of technique and ability that a worker possesses.

[0495] "Work efficiency" is an index that indicates how efficiently a worker can perform work within a certain period of time.

[0496] "Means for analyzing facial expressions and tone of voice to estimate emotions" refers to methods and tools for analyzing changes in a worker's facial expressions and voice to estimate their emotional state.

[0497] "Measures to provide support for reducing stress and fatigue" are methods and tools that provide suggestions and support to reduce stress and fatigue in workers.

[0498] The system for carrying out the present invention includes a program for inputting and analyzing the goals and results of examinees and workers. A specific embodiment of this system will be described below.

[0499] System configuration

[0500] The server includes the following means:

[0501] 1. A way to input test-taker goals and mock test results

[0502] 2. A way to analyze your strengths and weaknesses

[0503] 3. A way to display the optimal study content, method, and schedule leading up to the exam

[0504] 4. A way to input your study progress every day and make adjustments as needed

[0505] 5. Means of inputting worker skills and work efficiency

[0506] 6. A means of analyzing workers' strengths and weaknesses

[0507] 7. A method for estimating emotions by analyzing a worker's facial expressions and tone of voice

[0508] 8. Measures to support workers in reducing stress and fatigue

[0509] Hardware and software used

[0510] Hardware: Camera, microphone, computer or tablet

[0511] Software: OpenCV, Keras, TENSORFLOW (registered trademark), web browser

[0512] Data processing and calculation

[0513] The server uses a camera and microphone to capture the worker's facial expressions and tone of voice. This data is then processed and input into an emotion recognition model. The emotion recognition model estimates the worker's emotions and provides support for reducing stress and fatigue based on the results.

[0514] Specific examples

[0515] For example, if a worker is tired, the system will analyze their facial expressions and tone of voice and suggest taking a break. Also, if a test-taker has weaknesses in a particular subject, the system will suggest a study schedule that focuses on that subject.

[0516] Prompt Sentence Examples

[0517] "Design a system that analyzes a worker's facial expressions and tone of voice and suggests a break if they are feeling fatigued or stressed."

[0518] In this way, the server can analyze data on test takers and workers and provide optimal learning and working environments.

[0519] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[0520] Step 1:

[0521] The user inputs their goals and mock test results. The user inputs their goals and mock test results using a form on a web browser. The input data is sent to the server. The input data includes the student's goals, mock test scores, and subject scores.

[0522] Step 2:

[0523] The server receives the input data and inputs it into the generative AI model. The server preprocesses the received data and inputs it into the generative AI model. The generative AI model analyzes the data to identify the test-taker's strengths and weaknesses. The analysis results are output as the strengths and weaknesses of each subject.

[0524] Step 3:

[0525] The server generates the optimal study content, method, and schedule based on the analysis results.The server generates the optimal study content, method, and schedule for the test-taker based on the output of the generative AI model.The generated schedule includes a specific study plan aimed at achieving the test-taker's goals.

[0526] Step 4:

[0527] The server displays the generated schedule to the user. The server displays the generated study schedule on a web browser. The user checks the displayed schedule and begins studying.

[0528] Step 5:

[0529] The user enters their study progress every day. The user enters their daily study progress into a form on a web browser. The input data includes the content studied, study time, level of understanding, etc.

[0530] Step 6:

[0531] The server receives the study progress data and makes course corrections. The server analyzes the received study progress data and modifies the study schedule as necessary. The modified schedule is then displayed to the user again.

[0532] Step 7:

[0533] The user inputs their work skills and work efficiency. The user inputs their work skills and work efficiency into a form on a web browser. The input data includes the work content, work time, work efficiency, etc.

[0534] Step 8:

[0535] The server receives the input data and analyzes the worker's strengths and weaknesses. The server preprocesses the received data and inputs it into the generative AI model. The generative AI model analyzes the data to identify the worker's strengths and weaknesses. The analysis results output the worker's strengths and weaknesses for each task.

[0536] Step 9:

[0537] The server captures the worker's facial expressions and tone of voice. The server uses a camera and microphone to capture the worker's facial expressions and tone of voice. The captured data is sent to the server in real time.

[0538] Step 10:

[0539] The server analyzes the captured data and estimates emotions. The server processes the captured facial and voice data and inputs it into an emotion recognition model. The emotion recognition model estimates the worker's emotions and outputs the results.

[0540] Step 11:

[0541] The server provides support for reducing stress and fatigue based on the emotion recognition results. Based on the output of the emotion recognition model, the server generates suggestions to reduce the worker's stress and fatigue. For example, if the worker is tired, the server suggests taking a break. The generated suggestions are notified to the user.

[0542] Example 2

[0543] Next, a description will be given of Example 2 of Form 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."

[0544] Conventional learning support systems have limited means for optimizing students' study plans, and are particularly unable to respond to changes in students' emotions. As a result, students may feel stressed about studying or lose motivation, resulting in poor learning efficiency. Furthermore, the system lacks the ability to automatically correct course based on the students' progress, making it difficult for them to study effectively.

[0545] 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.

[0546] In this invention, the server includes means for inputting the examinee's goals and mock test results, means for analyzing the examinee's strengths and weaknesses, means for displaying the optimal study content, method, and schedule leading up to the exam, means for inputting the study progress every day and correcting the course as needed, means for detecting changes in the examinee's emotions, and means for recalculating and adjusting the study schedule based on the detected changes in emotions. This maximizes the examinee's learning efficiency and makes it possible to flexibly respond to changes in emotions.

[0547] "Exam takers' goals" refer to the learning outcomes and grades that exam takers want to achieve.

[0548] "Mock test results" refers to the grades and evaluations that candidates receive in mock tests.

[0549] "Weak areas" refer to subjects or topics that test-takers find particularly difficult to understand or master.

[0550] "Areas of strength" refers to subjects or topics that test takers find particularly easy to understand and master.

[0551] "Optimal learning content" refers to the specific learning items and materials that test takers need to study efficiently.

[0552] "Optimal study methods" refer to specific study techniques and approaches that allow test-takers to study efficiently.

[0553] An "optimal schedule" refers to the specific study time and dates planned to allow test-takers to study efficiently.

[0554] "Study implementation status" refers to the progress and results of the study that the examinee actually undertook.

[0555] "Correcting course" refers to reviewing a test-taker's study plan and schedule and making changes as necessary.

[0556] "Changes in emotions" refers to changes in the psychological state of test-takers, such as their motivation to study or stress.

[0557] A "generative AI model" refers to an artificial intelligence model that generates optimal study plans based on test-taker learning data.

[0558] "Recalculation" refers to recalculating a test-taker's study plan and schedule based on new data and conditions.

[0559] MODE FOR CARRYING OUT THE INVENTION

[0560] This invention is a system for maximizing the learning efficiency of test-takers and flexibly responding to changes in their emotions. A specific embodiment of this system is described below.

[0561] System configuration

[0562] This system consists of three main components: a server, a terminal, and a user. The server runs a program that includes a generative AI model and an emotion engine. The terminal provides an interface for users to input their learning data and check their learning schedule. The user uses the system as a test-taker.

[0563] Hardware and software used

[0564] The server is a high-performance computer that runs the generative AI model using Python and TensorFlow. The emotion engine is built using Python and OpenCV. The terminal is a personal computer or smartphone operated by the user, with a dedicated application installed.

[0565] Data processing and calculation

[0566] The server receives learning data entered by the user and analyzes it using a generative AI model. Specifically, it calculates the optimal learning content, method, and schedule based on data such as the subject, study time, progress, and goals. The calculation results are sent to the device in JSON format.

[0567] The device displays the received data in a calendar format. The user proceeds with their study while looking at the calendar, and when they finish studying, they enter their progress into the device. The device then sends the entered progress data to the server.

[0568] The server uses an emotion engine to detect changes in the user's emotions. The emotion engine analyzes the user's facial expressions and voice data to detect stress and loss of motivation. The detected changes in emotions are fed back to the server and conveyed to the generative AI model.

[0569] The generative AI model recalculates the learning schedule based on the feedback and makes adjustments as needed, and the recalculated schedule is sent back to the device and displayed to the user.

[0570] Specific examples

[0571] For example, consider a case where a user is working on a math problem set but is stressed because they are unable to solve many of the problems. The emotion engine detects stress from the user's facial expressions and voice and relays this information to the generative AI model. The generative AI model then adjusts the next day's schedule to reduce stress and includes relaxing activities (such as studying a favorite subject or taking a short break).

[0572] Prompt Sentence Examples

[0573] "Based on the student's learning data, calculate the optimal study content, method, and schedule, and display it in a calendar format. Also, detect changes in the student's emotions and adjust the study schedule as necessary."

[0574] In this way, the system can maximize the learning efficiency of test-takers and respond flexibly to changes in their emotions.

[0575] The flow of the identification process in the second embodiment will be described with reference to FIG.

[0576] Step 1:

[0577] The user uses the device to input study data. Specifically, they input study subjects, study time, progress, goals, etc. The input data is sent from the device to the server. The input data includes information such as "Mathematics, 2 hours, 50% completed, 80 points or more on the next mock exam."

[0578] Step 2:

[0579] The server receives the training data sent by the user and inputs it into the generative AI model. The generative AI model is built using Python and TensorFlow, and calculates the optimal training content, method, and schedule based on past training data and statistical information. The calculation results are output in JSON format.

[0580] Step 3:

[0581] The server sends the calculation results obtained from the generative AI model to the device, which then displays the received data in a calendar format. For example, it displays a specific schedule such as "2 hours of math workbooks" on Monday and "1 hour of English listening" on Tuesday.

[0582] Step 4:

[0583] The user studies while looking at the calendar on the device. When the study is finished, the user enters the progress on the device. For example, the user enters information such as "Completed 2 hours of math problems." The entered progress data is sent from the device to the server.

[0584] Step 5:

[0585] The server uses an emotion engine to detect changes in the user's emotions. The emotion engine is built using Python and OpenCV and analyzes the user's facial expressions and voice data. For example, if the user frowns or sighs, the emotion engine detects stress. The detected changes in emotions are fed back to the server.

[0586] Step 6:

[0587] The server receives feedback from the emotion engine and relays it to the generative AI model. The generative AI model recalculates the study schedule based on the feedback and makes adjustments as necessary. For example, if the user is feeling stressed about math, it will adjust the schedule for the next day and add relaxing content (such as studying a favorite subject or taking a short break). The recalculated schedule is again output in JSON format.

[0588] Step 7:

[0589] The server then sends the recalculated schedule to the device, which then displays it in calendar format to the user. The user then continues their studies according to the new schedule. This process is repeated to maximize the user's learning efficiency and flexibly respond to emotional changes.

[0590] (Application example 2)

[0591] Next, a description will be given of Application Example 2 of Form 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."

[0592] Conventional study support systems for test takers have difficulty responding to changes in test takers' emotions and motivation, resulting in a decline in study efficiency. Furthermore, in the shopping experience at physical stores, optimal suggestions based on the user's emotions and stress level are not provided, resulting in a decline in shopping satisfaction. To solve these issues, a system that can detect the user's emotions in real time and make optimal suggestions based on that information is needed.

[0593] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 2 is realized by the following means.

[0594] In this invention, the server includes a means for inputting the test-taker's goals and mock test results, a means for analyzing the test-taker's strengths and weaknesses, a means for displaying the optimal study content, method, and schedule leading up to the test, a means for inputting the study progress every day and correcting the course as needed, a means for detecting the user's emotions, and a means for making optimal suggestions based on the user's emotions. This improves the test-taker's learning efficiency and also makes it possible to increase user satisfaction in the shopping experience at a physical store.

[0595] "Exam takers' goals" refers to the specific learning goals and schools that exam takers want to achieve.

[0596] "Mock test results" refers to data showing the scores and evaluations of mock tests.

[0597] "Weak areas" refer to areas of study that test-takers find particularly difficult to understand or master.

[0598] "Areas of strength" refers to areas of study that are particularly easy for the candidate to understand and master.

[0599] "Optimal study content" refers to the learning content that is most effective for helping test-takers achieve their goals.

[0600] "Method" refers to the specific means and techniques used to advance your studies.

[0601] A "schedule" refers to a timetable or plan for studying.

[0602] "Study implementation status" refers to the progress and results of the learning activities that the test-taker actually undertakes.

[0603] "Correcting course" refers to changing your study plan or method as needed.

[0604] "User emotion" refers to the psychological state or mood that a user is feeling.

[0605] "Optimal suggestions" refers to providing the most appropriate advice or recommendations based on the user's situation and emotions.

[0606] The following system configuration will be described as an embodiment of the present invention.

[0607] System Configuration

[0608] This system consists of a server, a user terminal, and an emotion detection device. The server generates a test-taker's study plan using a generative AI model and detects the user's emotions using an emotion engine. The user terminal is a device such as a smartphone or tablet, and is used by the user to check the study plan and enter the progress status. The emotion detection device detects the user's emotions in real time using the smartphone's camera and microphone.

[0609] Program processing

[0610] The server performs the following process.

[0611] 1. A way to input test-taker goals and mock test results

[0612] The test-taker's goals and mock test results are entered on the user's device and sent to the server, which then grasps the test-taker's current academic ability and goals.

[0613] 2. A way to analyze your strengths and weaknesses

[0614] The server analyzes the test taker's mock exam results and identifies their areas of strength and weakness using data analysis software (e.g., Python's Pandas library).

[0615] 3. A way to display optimal study content, methods, and schedules

[0616] The server uses a generative AI model to calculate the optimal study content, method, and schedule for each test-taker, and displays it in a calendar format on the user's device. The generative AI model uses machine learning libraries (e.g., TensorFlow, PyTorch).

[0617] 4. A way to input your study progress every day and make adjustments as needed

[0618] Students enter their study progress daily from their devices and send it to the server, which then automatically adjusts their study plan based on their progress.

[0619] 5. How to detect user emotions

[0620] Detect user emotions in real time using emotion detection devices (smartphone cameras and microphones) and analyze user emotion data using emotion recognition APIs (e.g., Microsoft Azure Emotion API).

[0621] 6. A way to make optimal suggestions based on user emotions

[0622] The server optimizes study plans and shopping lists based on the user's emotional data obtained from the emotion engine. For example, if the user is feeling stressed, the server suggests products and study methods that will help them relax.

[0623] Specific examples

[0624] When a user is shopping in a physical store, their facial expressions are read using a smartphone camera, and the emotion engine detects "fatigue." Based on this information, the generative AI adds chocolate to the shopping list as a "relaxing product."

[0625] Prompt Sentence Examples

[0626] "When a user is shopping in a physical store, their facial expressions are read using their smartphone camera, and the emotion engine detects their emotions. Based on that information, the generative AI creates an optimal shopping list and suggests it to the user."

[0627] The above is an embodiment of the present invention.

[0628] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[0629] Step 1:

[0630] The user's device inputs the student's goals and mock exam results, and sends them to the server. The input data includes the student's desired school, target score, and mock exam results. The server receives this data and stores it in a database.

[0631] Step 2:

[0632] The server analyzes the test-taker's mock test results and identifies their areas of strength and weakness. Specifically, it uses Python's Pandas library to analyze the mock test score data and calculate the score distribution for each subject. This allows it to identify the test-taker's areas of strength and weakness.

[0633] Step 3:

[0634] The server uses a generative AI model to calculate the optimal study content, method, and schedule for each test-taker. Input data includes the test-taker's goals, areas of weakness, and areas of strength. The generative AI model generates an optimal study plan based on this data. The output data is a study schedule in calendar format, which is sent to the user's device.

[0635] Step 4:

[0636] The user's device inputs their study progress every day and sends it to the server. The input data includes the actual study content, time, and progress. The server receives this data and stores it in a database.

[0637] Step 5:

[0638] The server automatically adjusts the learning plan based on the student's progress. Specifically, it uses a machine learning algorithm to analyze the student's progress data and update the learning plan as needed. The updated learning plan is then sent back to the user's device.

[0639] Step 6:

[0640] An emotion detection device (such as a smartphone camera or microphone) detects the user's emotions in real time and sends the data to a server. The input data includes the user's facial expressions and voice. The server then uses an emotion recognition API (e.g., Microsoft Azure Emotion API) to analyze this data and identify the user's emotional state.

[0641] Step 7:

[0642] The server optimizes study plans and shopping lists based on the user's emotional data obtained from the emotion engine. Specifically, if the user is feeling stressed, the server suggests products and study methods that will help them relax. The generated suggestions are sent to the user's device.

[0643] The above are the specific processing steps of this system.

[0644] Example 3

[0645] Next, a description will be given of a third embodiment of the third embodiment. 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."

[0646] Conventional learning support systems have difficulty in dynamically optimizing learning schedules that take into account the student's study status and emotional state. This has led to problems such as a decline in motivation and learning efficiency. Furthermore, there has been a lack of effective ways to balance the student's strengths and weaknesses.

[0647] The specific processing by the specific processing unit 290 of the data processing device 12 in the third embodiment is realized by the following means.

[0648] In this invention, the server includes a means for inputting the test-taker's goals and mock test results, a means for analyzing the test-taker's strengths and weaknesses, a means for displaying the optimal study content, method, and schedule leading up to the test, a means for inputting the study progress status every day and correcting the course as needed, a means for analyzing the emotional state and providing feedback, a means for optimizing the study schedule using a generative AI model, and a means for providing the test-taker with the optimized study schedule. This makes it possible to provide an effective study schedule while maximizing the test-taker's learning efficiency and maintaining their motivation.

[0649] "Test-taker's goals" refer to the learning objectives and target scores that test-taker wants to achieve.

[0650] "Mock test results" refers to the grades or scores that a candidate receives on a mock test.

[0651] "Weak areas" refer to subjects or topics that test-takers find particularly difficult to understand or master.

[0652] "Areas of strength" refers to subjects or topics that a candidate finds particularly easy to understand and master.

[0653] "Study implementation status" refers to the content and amount of study that test takers actually undertake.

[0654] "Emotional state" refers to the psychological state of test-takers, such as their motivation to study and stress.

[0655] "Feedback" refers to advice and information provided based on the analysis of emotional state and learning progress.

[0656] "Generative AI model" refers to an artificial intelligence model that uses machine learning algorithms to optimize learning schedules.

[0657] A "study schedule" refers to a schedule that shows which subjects a test-taker plans to study and at what times.

[0658] "Optimization" refers to adjusting a test-taker's study schedule to maximize their learning efficiency.

[0659] The present invention relates to a learning support system for maximizing the learning efficiency of test takers. A specific embodiment of this system will be described below.

[0660] System configuration

[0661] Hardware and Software

[0662] The system is implemented using the following hardware and software.

[0663] Server: Stores data, analyzes it, and runs generative AI models. Specifically, it uses a database (such as MySQL or PostgreSQL) and a machine learning framework (such as TensorFlow or PyTorch).

[0664] Terminal: A device that allows users to input their study progress. Specifically, mobile devices such as smartphones and tablets are used.

[0665] Dedicated application: An application that allows users to input their study progress and check an optimized study schedule. Specifically, an application such as "StudyTracker" is used.

[0666] System Operation

[0667] Data Entry

[0668] The user uses a dedicated application to input their daily study status. The input data includes the subjects studied, study time, and study content. For example, the user might input, "I studied calculus for two hours."

[0669] Data transmission

[0670] The terminal transmits the input data to a server in real time via the Internet.

[0671] Data storage

[0672] The server stores the received data in a database, using a relational database such as MySQL or PostgreSQL.

[0673] Emotional state analysis

[0674] The server analyzes the test-taker's emotional state using an emotion engine, which generates feedback such as "motivation is declining" or "struggle to study" based on the user's input data and past learning history.

[0675] Optimizing your study schedule

[0676] The server inputs the study progress data stored in the database and feedback from the emotion engine into the generative AI model. The generative AI model then optimizes the study schedule based on this data. Specifically, it makes adjustments such as reducing study time in areas where the student is weak and increasing study time in areas where the student is strong.

[0677] Schedule provision

[0678] The server provides the user with an optimized learning schedule output from the generative AI model, and the user can check the new schedule through a dedicated application.

[0679] Specific examples

[0680] As a concrete example, consider a situation where a user is not good at calculus, and their motivation decreases as the time spent studying increases. In this case, the emotion engine sends feedback of "decreased motivation" to the generative AI model. Based on this information, the generative AI model adjusts the schedule to reduce the time spent studying calculus and increase the time spent studying English, which is their strong point.

[0681] Prompt Sentence Examples

[0682] Generate a program to optimize the student's study schedule based on the student's study progress and feedback from the emotion engine. Adjust the program to reduce the time spent studying areas where the student is weak and increase the time spent studying areas where the student is strong.

[0683] In this way, the system provides an optimal schedule for maximizing the learning efficiency of the examinee. The flow of the specification process in the third embodiment will be described with reference to FIG.

[0684] Step 1:

[0685] The user inputs the study progress status.

[0686] The user uses a dedicated application to input the subjects they studied, the study time, and the content of their studies. For example, they might input "I studied calculus for two hours." The input data is saved in the application in the form of subjects, study time, and content of their studies.

[0687] Step 2:

[0688] The terminal sends the input data to the server.

[0689] The device (smartphone) sends the data on the user's study progress entered by the user to a server in real time via the Internet. The data arrives at the server in the form of study subjects, study time, and study content.

[0690] Step 3:

[0691] The server stores the data in a database.

[0692] The server stores the received study progress data in a database using a relational database such as MySQL or PostgreSQL. The data is stored in the database in the form of study subjects, study time, and study content.

[0693] Step 4:

[0694] The server receives feedback from the emotion engine.

[0695] The server uses an emotion engine to analyze the test-taker's emotional state. Based on the user's input data and past learning history, the emotion engine generates feedback such as "motivation is declining" or "struggle to learn." The analysis results are sent to the server as emotional state feedback.

[0696] Step 5:

[0697] The server inputs data into the generative AI model.

[0698] The server inputs the study progress data stored in the database and feedback from the emotion engine into the generative AI model. The generative AI model is built using machine learning frameworks such as TensorFlow and PyTorch. Input data is provided to the generative AI model in the form of study subjects, study time, study content, and emotional state.

[0699] Step 6:

[0700] Generative AI models optimize learning schedules.

[0701] The generative AI model optimizes the student's study schedule based on the input data. Specifically, it makes adjustments such as reducing study time in areas the student is weak in and increasing study time in areas they are strong in. The optimized schedule is generated in the form of study subjects, study time, and study content.

[0702] Step 7:

[0703] The server provides the optimized schedule to the user.

[0704] The server provides the user with an optimized study schedule output from the generative AI model. The user can check the new schedule through a dedicated application. The provided schedule is displayed in the application in the form of study subjects, study time, and study content.

[0705] (Application example 3)

[0706] Next, a description will be given of Application Example 3 of Form Example 3. 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."

[0707] Conventional learning schedule management systems do not take into account the emotional state and motivation of test-takers, resulting in poor learning efficiency. Furthermore, they are unable to monitor learning situations in real time or deliver optimal learning content, meaning they are unable to provide sufficient learning support tailored to the individual needs of test-takers.

[0708] The specific processing by the specific processing unit 290 of the data processing device 12 in Application Example 3 is realized by the following means. In this invention, the server includes a means for inputting the examinee's goals and mock test results, a means for analyzing the examinee's strong and weak areas, a means for displaying the optimal study content, method, and schedule leading up to the exam, a means for inputting the study progress status every day and correcting the course as needed, a means for adjusting the study schedule based on feedback from the emotion engine, and a means for monitoring the study status and emotional state in real time and delivering optimal study content. This makes it possible to provide an optimal study schedule that takes into account the examinee's emotional state and learning motivation, and to monitor the study status in real time and deliver optimal study content.

[0709] "Exam takers' goals" refers to the specific learning goals and schools that exam takers want to achieve.

[0710] "Mock test results" refers to the grades and evaluations that test takers receive in mock tests.

[0711] "Weak areas" refer to subjects or topics in which a test-taker has particularly poor understanding or poor performance in their studies.

[0712] "Areas of strength" refers to subjects or topics in which a candidate has particularly strong understanding or achievement in their studies.

[0713] "Study content" refers to the specific subjects and topics that test takers will study.

[0714] "Study methods" refer to the specific techniques and approaches that test takers use to advance their studies.

[0715] A "schedule" refers to the timetable or dates planned for a test-taker to study.

[0716] "Study implementation status" refers to the progress and content of the study that the test-taker actually undertook.

[0717] "Correcting the course" refers to adjusting and optimizing a test-taker's study plan and schedule.

[0718] An "emotion engine" is a system that analyzes the emotional state of test takers and provides feedback.

[0719] "Adjusting study schedule" refers to changing a test-taker's study plan based on feedback from the emotion engine.

[0720] "Monitoring learning status" refers to monitoring the learning progress and implementation status of test takers in real time.

[0721] "Delivery of learning content" refers to providing test takers with the most appropriate learning materials and teaching materials.

[0722] The system for implementing this invention consists of three main elements: a server, a terminal, and a user. The following explains how each element functions.

[0723] server

[0724] The server includes a means for inputting the test-taker's goals and mock test results, a means for analyzing the test-taker's areas of strength and weakness, a means for displaying the optimal study content, method and schedule leading up to the test, a means for inputting the study progress status every day and correcting the course as needed, a means for adjusting the study schedule based on feedback from the emotion engine, and a means for monitoring the study status and emotional state in real time and delivering the optimal study content.

[0725] The server is built using programming languages ​​such as Python and Java (registered trademark), and uses MySQL or PostgreSQL as a database management system (DBMS). The emotion engine analyzes the user's emotional state using natural language processing (NLP) techniques, and the generative AI model is built using machine learning frameworks such as TensorFlow and PyTorch.

[0726] Terminal

[0727] The terminal is a device through which the user inputs learning data and receives feedback. It can be a smartphone, tablet, or PC. A dedicated application is installed on the terminal, and the user inputs learning data through this application.

[0728] The application is developed using cross-platform frameworks such as React Native and Flutter (registered trademark), providing an intuitive interface for users. The application communicates with the server and sends and receives data in real time.

[0729] User

[0730] The user is a student taking an exam and inputs their daily study status through a terminal. The user uses the application to input study data and receives feedback from the emotion engine. This allows the user to receive the optimal study schedule and content.

[0731] Specific examples

[0732] For example, if a user is bad at math but good at English, and the emotional feedback is negative, the server will adjust the schedule to reduce the time spent studying math and increase the time spent studying English. The user enters the following prompt sentence into the application:

[0733] Prompt Sentence Examples

[0734] User ID: 1

[0735] Training data: {'date': '2023-10-01', 'weak_subject_time': 60, 'strong_subject_time': 30}

[0736] Emotional feedback: 'negative'

[0737] Based on this prompt, the server optimizes the study schedule and provides feedback to the user, allowing them to study efficiently.

[0738] The flow of the specific processing in Application Example 3 will be described with reference to FIG.

[0739] Step 1:

[0740] The user uses a device to input study data. Specifically, the user opens the application and inputs information such as the subjects studied, study time, and emotional state. The input data includes the date, study time for weak subjects, study time for strong subjects, emotional feedback, etc. This data is then sent from the device to the server.

[0741] Input: Study data (e.g., date, study time for weak subjects, study time for strong subjects, emotional feedback)

[0742] Output: Training data sent to the server

[0743] Step 2:

[0744] The server stores the received learning data in a database. The server analyzes the received data and stores it in a database. The database stores each user's learning history and emotional feedback.

[0745] Input: Training data sent from the device

[0746] Output: Training data stored in a database

[0747] Step 3:

[0748] The server uses an emotion engine to analyze the user's emotional feedback, which uses natural language processing techniques to analyze the user's emotional state and generate positive, neutral, or negative feedback.

[0749] Input: Emotional feedback included in the training data

[0750] Output: Parsed emotional feedback (e.g., positive, neutral, negative)

[0751] Step 4:

[0752] The server uses a generative AI model to optimize the study schedule. The generative AI model generates an optimal study schedule based on the user's learning data and emotional feedback. For example, if negative feedback is received, the study time for weak subjects will be reduced and the study time for strong subjects will be increased.

[0753] Input: Training data, analyzed emotional feedback

[0754] Output: Optimized study schedule

[0755] Step 5:

[0756] The server transmits the optimized study schedule to the terminal, and the server transmits the generated study schedule to the user's terminal so that the user can check it.

[0757] Input: Optimized study schedule

[0758] Output: Study schedule sent to the device

[0759] Step 6:

[0760] The device displays the optimized study schedule. The user can check the optimized study schedule sent from the server through the device application, which allows the user to study efficiently.

[0761] Input: Study schedule sent from the server

[0762] Output: Study schedule displayed on the device

[0763] Step 7:

[0764] The user proceeds with their studies according to the new study schedule. The user proceeds with their daily studies according to the optimized study schedule displayed on the device. Once the study is complete, they return to step 1 and enter their study data again.

[0765] Input: Optimized study schedule

[0766] Output: New training data

[0767] 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.

[0768] The data generation model 58 is a so-called generative AI (Artificial Intelligence). An example of the data generation model 58 is ChatGPT (registered trademark) (Internet search engine).<URL: https: / / openai.com / blog / chatgpt> ) 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.

[0769] Another example of generative AI is Gemini (registered trademark) (Internet search engine). <url: https: gemini.google.com ?hl="ja">) are listed.

[0770] 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.

[0771] [Second embodiment]

[0772] FIG. 3 shows an example of the configuration of a data processing system 210 according to the second embodiment.

[0773] 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.

[0774] 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.

[0775] The processor 28, RAM 30, and storage 32 are connected to a bus 34. The database 24 and 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).

[0776] 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.

[0777] 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.

[0778] 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).

[0779] 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.

[0780] 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.

[0781] 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.

[0782] 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.

[0783] 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.

[0784] Next, the specific processing by the specific processing unit 290 of the data processing device 12 will be described.

[0785] "Example 1"

[0786] In one embodiment of the present invention, test takers enter their goals and mock test results into the system through a dedicated input interface, such as a form running on a web browser. The input information is analyzed by generative AI to identify the test taker's strengths and weaknesses.

[0787] "Example 2"

[0788] Next, the generative AI calculates the optimal study content, method, and schedule for the exam and displays it to the test-taker. The display is typically in the form of a calendar, showing specific study content and time for each day.

[0789] "Example 3"

[0790] Furthermore, test-takers enter their daily study schedules into the system. This is done, for example, through a dedicated application, and specific study time and content are recorded. Based on this information, the system makes adjustments as needed and updates the optimal study schedule.

[0791] The processing flow of each embodiment will be described below.

[0792] "Example 1"

[0793] Step 1: The test-taker enters their goals and mock test results into the system through a dedicated input interface, such as a form that runs on a web browser.

[0794] Step 2: The input information is analyzed by generative AI to identify the candidate's areas of strength and weakness. This analysis is carried out using deep learning techniques, for example.

[0795] "Example 2"

[0796] Step 1: The generative AI calculates the optimal study content, method, and schedule for the exam. This calculation is done using techniques such as reinforcement learning.

[0797] Step 2: The calculated optimal study content, method, and schedule are displayed to the test-taker. The display is, for example, in a calendar format, showing specific study content and time for each day.

[0798] "Example 3"

[0799] Step 1: The candidate enters their daily study history into the system. This is done, for example, through a dedicated application, and the specific study time and content are recorded.

[0800] Step 2: Based on this information, the system adjusts course as needed and updates the optimal study schedule. This adjustment is done using, for example, a genetic algorithm.

[0801] Example 1

[0802] Next, a description will be given of Example 1 of Form 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."

[0803] Conventional learning support systems for test takers have had difficulty effectively utilizing test takers' goals and mock test results to identify individual areas of strength and weakness. Furthermore, they were unable to provide appropriate feedback or course corrections according to test takers' learning status, resulting in a decline in learning efficiency.

[0804] The specific processing by the specific processing unit 290 of the data processing device 12 in Example 1 is realized by the following means. In this invention, the server includes a means for inputting the examinee's goals and mock test results, a means for analyzing the examinee's strong and weak areas, a means for displaying the optimal study content, method, and schedule leading up to the exam, a means for inputting the study progress status every day and correcting the course as needed, a means for accessing a dedicated input form using a web browser, a means for passing the input data to the generative AI model, a means for the generative AI model to analyze the data and return the analysis results, and a means for displaying the analysis results to the user. This enables effective learning support tailored to the examinee's individual learning needs.

[0805] "Exam takers' goals" refers to the specific learning goals and schools that exam takers want to achieve.

[0806] "Mock test results" refers to the scores and grades for each subject in the mock test.

[0807] "Means of input" refers to the interface that allows test takers to input their goals and mock test results into the system.

[0808] "Means of analysis" refers to the function for analyzing the input data and identifying the test-taker's areas of weakness and strength.

[0809] "Means of display" refers to the function for visually presenting analysis results and study plans to test takers.

[0810] "Means for course correction" refers to the function of adjusting the study plan according to the student's learning situation.

[0811] "Web browser" refers to software for viewing web pages on the Internet.

[0812] "Specialized input form" refers to a form on a web page designed for test takers to enter their goals and mock test results.

[0813] A "generative AI model" refers to an artificial intelligence model that analyzes input data and generates a specific result.

[0814] "Means of analysis" refers to the functionality that a generative AI model has to process input data and derive a specific result.

[0815] "Means for returning analysis results" refers to the function for the generative AI model to return the analysis results to the server.

[0816] "Means for displaying to the user" refers to the function that the server uses to present the analysis results to the test-taker.

[0817] This invention is a system that allows test-takers to input their goals and mock test results, and based on that, identifies areas of strength and weakness, and provides an optimal study plan. Specific embodiments of this system are described below.

[0818] Hardware and software used

[0819] Hardware:

[0820] Server: A server that receives data, analyzes it, and returns the results

[0821] Terminal: A computer or smartphone that allows users to input information

[0822] software:

[0823] Web browser: Software that allows users to access dedicated input forms (e.g., Google Chrome, Safari)

[0824] Generative AI model: An artificial intelligence model that analyzes input data and generates a specific result (e.g., OpenAI's GPT-4)

[0825] System Operation

[0826] User Action:

[0827] The user opens a web browser on their computer or smartphone and accesses the system's URL. A dedicated input form is displayed, where the user inputs their goal (e.g., passing the first science course at the University of Tokyo) and mock exam results (e.g., 80 points in math, 70 points in English, 60 points in physics, and 50 points in chemistry). Once the input is complete, the user clicks the submit button.

[0828] Server Action:

[0829] The server receives the data sent by the user. This data is sent as an HTTP POST request. The received data is passed to a generative AI model. The generative AI model uses, for example, OpenAI's GPT-4.

[0830] Analysis of generative AI models:

[0831] The generative AI model analyzes the received data and identifies the test-taker's areas of strength and weakness. This analysis uses natural language processing technology and machine learning algorithms. The analysis results are returned to the server in JSON format.

[0832] Server results:

[0833] The server receives the analysis results returned by the generative AI model and displays them to the user. The user can check the analysis results on a web browser. The analysis results are displayed in an easy-to-read format using HTML and CSS.

[0834] Examples of concrete examples and prompts

[0835] As a specific example, consider the case where a test-taker inputs the following information:

[0836] Goal: Pass the First Class Science Course at the University of Tokyo

[0837] Mock exam results: Math 80 points, English 70 points, Physics 60 points, Chemistry 50 points

[0838] When a user enters this information into the input form and clicks the submit button, the server receives this data and passes it to the generative AI model, which then analyzes it using prompt statements like the following:

[0839] Example prompt sentence:

[0840] The student's goal is to pass the entrance exam for the first science course at the University of Tokyo. The results of the mock exam are as follows:

[0841] Mathematics: 80 points

[0842] English: 70 points

[0843] Physics: 60 points

[0844] Chemistry: 50 points

[0845] Use this information to identify the candidate's areas of weakness and strength.

[0846] The generative AI model analyzes this prompt sentence and returns a result such as the following:

[0847] Example of analysis results:

[0848] Specialties: Mathematics, English

[0849] Weak areas: Physics, chemistry

[0850] The server displays the analysis results to the user, allowing the test-taker to use them as a reference when making future study plans.

[0851] The flow of the identification process in the first embodiment will be described with reference to FIG.

[0852] Step 1:

[0853] A user opens a web browser. A user opens a web browser (e.g., Google Chrome or Safari) on their computer or smartphone. For example, by double-clicking a desktop icon or tapping an app on their smartphone. The input is the user's action, and the output is the launch of the web browser.

[0854] Step 2:

[0855] The user accesses a dedicated input form. The user accesses the dedicated input form by entering the system's URL (e.g., https: / / example.com). This form is built with HTML and JavaScript. The user enters the URL in the address bar and presses the Enter key. The input is the URL, and the output is the display of the input form.

[0856] Step 3:

[0857] The user inputs their goal and mock exam results. The user inputs their goal (e.g., passing the first science course at the University of Tokyo) and their mock exam results (e.g., 80 points for math, 70 points for English, 60 points for physics, 50 points for chemistry) into the form. Text boxes are provided for entering scores for each subject. The input is the goal and mock exam results, and the output is the generation of the input data.

[0858] Step 4:

[0859] The user submits the input. The user clicks the submit button on the form. This sends the input data to the server. The submit button is an HTML< / url:> < / button> <button>It is implemented with tags. The input is clicking the submit button, and the output is sending the data.

[0860] Step 5:

[0861] The server receives input data. The server receives data submitted by the user. This data is sent as an HTTP POST request. The server temporarily stores the received data. The input is the HTTP POST request, and the output is the stored data.

[0862] Step 6:

[0863] The server passes data to the generative AI model. The server passes the received data to the generative AI model. This generative AI model is, for example, OpenAI's GPT-4. The data is sent as an API request. The server sends an HTTP POST request to the API endpoint. The input is the stored data, and the output is the sending of the API request.

[0864] Step 7:

[0865] The generative AI model analyzes the data it receives. Specifically, it identifies the test-taker's areas of strength and weakness based on their goals and mock test results. Natural language processing technology and machine learning algorithms are used for the analysis. The input is the API request, and the output is the analysis results.

[0866] Step 8:

[0867] The generative AI model returns the analysis results to the server. The generative AI model returns the analysis results to the server. The analysis results are returned in JSON format. The server receives this JSON data. The input is the JSON data of the analysis results, and the output is receiving the data.

[0868] Step 9:

[0869] The server displays the analysis results to the user. The server receives the analysis results and displays them to the user. The user can check the analysis results on a web browser. The analysis results are displayed in an easy-to-read format using HTML and CSS. The input is the received analysis results, and the output is the display of the analysis results.

[0870] (Application example 1)

[0871] Next, a description will be given of Application Example 1 of Form 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."

[0872] With conventional learning support systems, it was difficult to create an optimal individual study plan based on the student's goals and mock test results, and they often did not provide appropriate feedback or course corrections according to the student's learning progress. This resulted in students being unable to study efficiently, making it difficult for them to achieve their goals.

[0873] 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.

[0874] In this invention, the server includes means for inputting the test-taker's goals and mock test results, means for analyzing the test-taker's strengths and weaknesses, means for displaying the optimal study content, method, and schedule leading up to the test, means for inputting the study progress on a daily basis and correcting the course as needed, means for identifying the test-taker's strengths and weaknesses using generative AI and recommending optimal study content, and means for tracking the test-taker's progress and providing regular feedback. This enables test-taker to create an individually optimized study plan and study efficiently.

[0875] "Exam takers" are students who are studying with the aim of passing an exam.

[0876] A "goal" is a specific objective that a test-taker wants to achieve, such as passing an exam or improving their grades.

[0877] A "mock exam" is a mock test that students take in preparation for the actual exam.

[0878] The "means of input" is the interface that allows test takers to input their goals and mock test results into the system.

[0879] "Means for analysis" refers to a method or device for analyzing input data and identifying the examinee's areas of strength and weakness.

[0880] "Display means" refers to a method or device for visually presenting the analysis results and study plan to the examinee.

[0881] "Means for course correction" are methods or devices for adjusting the study plan according to the student's learning progress.

[0882] "Generative AI" is artificial intelligence that generates new information and analytical results based on input data.

[0883] "Learning content" refers to educational resources such as study materials and question sets that test takers use to study.

[0884] "Tracking" means the continuous monitoring and recording of a student's learning progress.

[0885] "Feedback" refers to providing information to test takers to inform them of their learning progress and areas for improvement.

[0886] To implement this invention, a terminal used by a test-taker, a server, and a generative AI model are used. Specific embodiments are described below.

[0887] 1. System Configuration

[0888] The system includes a device used by test takers, a server that processes data, and a generative AI model. The device can be a smartphone, tablet, or PC, and the server can be a cloud server or an on-premise server. The generative AI model uses an advanced natural language processing model such as OpenAI's GPT-3.

[0889] 2. Program Processing

[0890] Enter the student's goals and mock test results

[0891] Candidates use the terminal to input their goals and mock test results. The input interface is a form that runs on a web browser and is designed to allow test takers to easily enter data.

[0892] Data analysis

[0893] The server receives the test-taker's input goals and mock test results and sends them to the generative AI model, which analyzes this data and identifies the test-taker's strengths and weaknesses.

[0894] Learning content recommendations

[0895] The server recommends optimal learning content to test-takers based on the analysis results from the generative AI model, and the recommended learning content is displayed on the device screen.

[0896] Progress tracking and feedback

[0897] As the student progresses through their studies, the device tracks their progress and sends it to the server. The server then periodically generates feedback based on the student's progress and sends it to the device. The feedback provides the student with information to check their progress and make course corrections as necessary.

[0898] 3. Hardware and software used

[0899] Hardware: Smartphones, tablets, PCs, cloud or on-premise servers

[0900] Software: Web browser, generative AI model (OpenAI GPT-3)

[0901] 4. Specific Examples

[0902] Example of student's goals and mock test results

[0903] A student sets the goal of "passing the entrance exam for the University of Tokyo" and enters the results of the mock exam as follows:

[0904] Student's goal: Passing the entrance exam to the University of Tokyo

[0905] Mock test results: {"Math": 70, "English": 85, "Physics": 60, "Chemistry": 75}

[0906] Examples of identifying areas of weakness and strength

[0907] The generative AI model identifies the individual as "bad at physics, good at English."

[0908] Examples of recommended learning content

[0909] The generative AI model recommends learning content as follows:

[0910] Weakness: Physics

[0911] Specialty: English

[0912] Recommend the best learning content.

[0913] In this way, test takers can create individually optimized study plans and progress with their studies efficiently.

[0914] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[0915] Step 1:

[0916] The user uses the terminal to input the goal and the results of the mock test.

[0917] The input interface is a form that runs on a web browser, where the user inputs their goal (e.g., "Pass the entrance exam for Tokyo University") and mock exam results (e.g., "Math: 70, English: 85, Physics: 60, Chemistry: 75") The input data is sent to the server in JSON format.

[0918] Step 2:

[0919] The server sends the received data to the generative AI model.

[0920] The server generates and sends prompts to a generative AI model (e.g., OpenAI GPT-3) to analyze the user's submitted goals and practice test results. An example of a prompt is shown below.

[0921] Student's goal: Passing the entrance exam to the University of Tokyo

[0922] Mock test results: {"Math": 70, "English": 85, "Physics": 60, "Chemistry": 75}

[0923] Identify your areas of weakness and strength.

[0924] The generative AI model analyzes this prompt and identifies areas of strength and weakness.

[0925] Step 3:

[0926] The generative AI model returns the analysis results to the server.

[0927] The generative AI model returns analysis results such as "I'm not good at physics, but I'm good at English" to the server. The server receives this information and proceeds to the next step.

[0928] Step 4:

[0929] The server recommends the most suitable learning content based on the analysis results.

[0930] Based on the analysis results from the generative AI model, the server generates a prompt to recommend the most suitable learning content to the user and sends it back to the generative AI model. An example of a prompt is as follows:

[0931] Weakness: Physics

[0932] Specialty: English

[0933] Recommend the best learning content.

[0934] The generative AI model generates optimal learning content based on this prompt and returns it to the server.

[0935] Step 5:

[0936] The server transmits the recommended learning content to the terminal.

[0937] The server receives the learning content returned by the generative AI model and sends it to the user's device, which receives this information and visually displays it to the user.

[0938] Step 6:

[0939] As the user progresses through their studies, the device tracks their progress and sends it to the server.

[0940] As the user progresses with their studies, the device continuously monitors their progress and periodically sends the data to the server, including study time, study content, progress status, and other information.

[0941] Step 7:

[0942] The server generates feedback based on the learning progress and sends it to the device.

[0943] The server analyzes the user's learning progress data and generates feedback as needed. The generated feedback includes information for checking the user's learning progress and making necessary course corrections. The server sends this feedback to the terminal, which then visually displays it to the user.

[0944] In this way, test takers can create individually optimized study plans and progress with their studies efficiently.

[0945] Example 2

[0946] Next, a description will be given of Example 2 of Form 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."

[0947] Conventional learning support systems have difficulty automatically generating and displaying optimal learning plans that match each student's individual learning situation and goals. Furthermore, they lacked the functionality to flexibly modify schedules according to the student's learning progress, making it difficult for students to study efficiently. Furthermore, there were also insufficient means to visually display the generated learning plans in an easy-to-understand manner.

[0948] 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.

[0949] In this invention, the server includes a means for inputting the examinee's goals and mock test results, a means for analyzing the examinee's strengths and weaknesses, a means for displaying the optimal study content, method, and schedule leading up to the exam, a means for inputting the study progress on a daily basis and correcting the course as needed, a means for inputting prompts into the generative AI model to generate the optimal study content, method, and schedule, a means for converting the generated schedule into a calendar format, and a means for displaying the calendar-format schedule. This makes it possible to automatically generate an optimal study plan tailored to the examinee's individual learning situation and display it in a visually easy-to-understand manner. Furthermore, the schedule can be flexibly modified according to the examinee's learning progress, allowing the examinee to study efficiently.

[0950] "Exam takers' goals" refer to the learning objectives and goals that exam takers want to achieve.

[0951] "Mock test results" refers to the grades or scores that a candidate obtained in a mock test.

[0952] "Weak areas" refer to areas of study that test-takers find particularly difficult to understand or master.

[0953] "Areas of strength" refers to areas of study that the candidate finds particularly easy to understand and master.

[0954] "Optimal learning content" refers to the learning items that are judged to be most effective in helping test takers achieve their goals.

[0955] "Optimal study methods" refer to specific study methods and approaches that maximize a test-taker's learning efficiency.

[0956] An "optimal schedule" refers to a timetable or dates planned to allow test takers to study efficiently.

[0957] A "generative AI model" refers to an algorithm or system that uses artificial intelligence technology to analyze data and generate an optimal learning plan.

[0958] A "prompt" refers to an instruction or question input to a generative AI model.

[0959] "Calendar format" refers to a format that visually displays learning content and schedules by date.

[0960] "Study implementation status" refers to the progress and results of the learning activities actually undertaken by the examinee.

[0961] "Correcting course" refers to adjusting plans and schedules according to the progress of learning.

[0962] The present invention is a system for automatically generating an optimal study plan according to the individual learning situation of each examinee and displaying the plan in a visually easy-to-understand manner. A specific embodiment of this system will be described below.

[0963] First, the user logs in to the system. The user enters their username and password on the system login screen and clicks the "Login" button. If the login is successful, the user's dashboard will be displayed.

[0964] Next, the user enters their learning goals (e.g., to improve their math grades) and their current academic level (e.g., their mock test scores) on the dashboard, and this information is sent to the server.

[0965] The server collects the user's past learning history data from the database. This includes the percentage of correct answers to questions previously solved and the results of mock exams. For example, it retrieves the data using an SQL query such as "SELECT FROM learning history WHERE user ID = '12345'".

[0966] Next, the server inputs a prompt into the generative AI model based on the collected data. The prompt includes the user's learning goals, academic level, and learning history data. An example of a specific prompt is, "This student wants to improve their math grades. Their past academic performance data is as follows. Please generate the optimal study content, method, and schedule in calendar format."

[0967] The generative AI model analyzes the prompt and generates the optimal learning content, method, and schedule for the user, creating a specific study plan such as "Spend two hours on math problems on Monday" or "Spend one hour on English listening on Tuesday."

[0968] The server converts the learned schedule obtained from the generative AI model into a calendar format using a JavaScript library to convert the schedule into a format that can be displayed visually.

[0969] Finally, the device displays a calendar-style schedule to the user. Users can check the study content and time for each day on the device screen and plan their studies accordingly. For example, they can check the schedule through an app on their smartphone or tablet.

[0970] This system automatically generates optimal study plans tailored to each student's individual learning situation, allowing them to visually confirm the plans. It also allows students to flexibly adjust their schedules according to their learning progress, enabling them to study efficiently.

[0971] The flow of the identification process in the second embodiment will be described with reference to FIG.

[0972] Step 1:

[0973] A user logs in to the system.

[0974] The user enters their username and password on the system's login screen and clicks the "Login" button. The entered username and password are sent to the server, which then checks the database for authentication. If authentication is successful, the user's dashboard is displayed.

[0975] Input: Username, Password

[0976] Output: User's dashboard screen

[0977] Step 2:

[0978] The user inputs their learning goals and current academic level.

[0979] The user enters their learning goal (e.g., "I want to improve my math grades") and their current academic level (e.g., their mock test score) into the form on the dashboard and clicks the "Submit" button. This information is sent to the server.

[0980] Input: Learning goals, current academic level

[0981] Output: Learning objectives and academic level sent to the server

[0982] Step 3:

[0983] The server collects the user's learning history data.

[0984] The server queries and collects the user's past learning history data from the database, including the percentage of correct answers to questions previously answered and the results of practice tests. For example, it retrieves the data using an SQL query such as "SELECT FROM learning history WHERE user ID = '12345'".

[0985] Input: User ID

[0986] Output: User learning history data

[0987] Step 4:

[0988] The server inputs a prompt sentence into the generative AI model.

[0989] The server inputs prompts into the generative AI model based on the collected data. The prompts include the user's learning goals, academic level, and learning history data. An example of a specific prompt is, "This student wants to improve their math grades. Their past academic performance data is as follows. Please generate the optimal study content, methods, and schedule in a calendar format."

[0990] Input: Learning goals, academic level, learning history data

[0991] Output: Prompt sentence to the generative AI model

[0992] Step 5:

[0993] A generative AI model generates optimal learning content, methods, and schedules.

[0994] The generative AI model analyzes the prompt and generates the optimal learning content, method, and schedule for the user, creating a specific study plan such as "Spend two hours on math problems on Monday" or "Spend one hour on English listening on Tuesday."

[0995] Input: prompt statement

[0996] Output: Optimal learning content, methods, and schedule

[0997] Step 6:

[0998] The server converts the generated schedule into a calendar format.

[0999] The server converts the learned schedule obtained from the generative AI model into a calendar format using a JavaScript library to convert the schedule into a format that can be displayed visually.

[1000] Input: Optimal learning content, methods, and schedule

[1001] Output: Calendar format schedule

[1002] Step 7:

[1003] The terminal displays the schedule to the user.

[1004] The device displays a calendar-style schedule to the user. Users can check the study content and time for each day on the device screen and plan their studies accordingly. For example, they can check their schedule through an app on their smartphone or tablet.

[1005] Input: Calendar-style schedule

[1006] Output: The schedule as seen by the user

[1007] (Application example 2)

[1008] Next, a description will be given of Application Example 2 of Form 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."

[1009] With conventional exam preparation support systems, it was difficult to generate an optimal study schedule based on the student's goals and mock test results, and the course corrections based on the student's study progress had to be done manually, making it difficult to study efficiently.Furthermore, the generated schedule was not displayed in a visually easy-to-understand manner, making it difficult for the student to understand the plan.

[1010] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 2 is realized by the following means.

[1011] In this invention, the server includes a means for inputting the examinee's goals and mock test results, a means for analyzing the examinee's strengths and weaknesses, a means for displaying the optimal study content, method, and schedule leading up to the exam, a means for inputting the study progress status every day and correcting the course as needed, a means for generating an optimal study schedule using a generative AI model, and a means for displaying the generated schedule in calendar format. This allows the examinee to efficiently and effectively create a study plan and make appropriate course corrections according to their progress.

[1012] "Exam takers' goals" refers to the specific learning goals and schools that exam takers want to achieve.

[1013] "Mock test results" refers to evaluation data such as mock test scores, marks, and deviation values.

[1014] "Weak areas" refer to areas of study or subjects that test-takers find particularly difficult to understand or master.

[1015] "Areas of strength" refers to areas of study or subjects that are particularly easy for a candidate to understand and master, and in which they achieve high grades.

[1016] "Optimal study content" refers to the learning content that is most effective for helping test-takers achieve their goals.

[1017] "Method" refers to the specific means or approach to studying.

[1018] A "schedule" refers to a plan that arranges study content and methods in terms of time.

[1019] A "generative AI model" refers to an algorithm or system that uses artificial intelligence technology to generate data and calculate the optimal study schedule.

[1020] "Calendar format" refers to a format that visually displays study content and schedules by date.

[1021] "Correcting your course" means adjusting your plan according to your study progress and keeping it in optimal condition.

[1022] A system for implementing this invention includes a means for inputting the test-taker's goals and mock test results, a means for analyzing the test-taker's strengths and weaknesses, a means for displaying the optimal study content, method, and schedule leading up to the test, a means for inputting the study progress status every day and correcting the course as needed, a means for generating an optimal study schedule using a generative AI model, and a means for displaying the generated schedule in calendar format.

[1023] Program processing explanation

[1024] The server provides an interface for students to input their goals and mock test results. Students input their goals and mock test results using devices such as smartphones or PCs. This data is sent to the server and stored in a database.

[1025] Next, the server uses a generative AI model to analyze the student's strengths and weaknesses. The generative AI model generates an optimal study schedule based on the input data. It also uses OpenAI's API to generate prompts and input them into the AI ​​model.

[1026] The generated study schedule is displayed in calendar format. Students can check the study content and method for each date on their smartphone or computer screen. For example, use the following prompts:

[1027] Example prompt sentence:

[1028] Generate an optimal study schedule for the following subjects for students taking the exam on 2023-12-01: Mathematics, English, Physics

[1029] Furthermore, students can input their daily study progress. Based on this data, the server uses the generative AI model again to correct the schedule, allowing students to maintain an optimal study plan at all times.

[1030] Specific examples

[1031] For example, if a student needs to study three subjects: mathematics, English, and physics, the server generates the following schedule:

[1032] 2023-11-01: Mathematics - Calculus

[1033] 2023-11-02: English - Grammar

[1034] 2023-11-03: Physics - Mechanics

[1035] This schedule is displayed in a calendar format, allowing students to easily check their daily study content. Furthermore, the schedule is automatically updated according to their study progress, enabling efficient study.

[1036] The hardware used is a smartphone or a PC, allowing test-takers to plan their studies efficiently and effectively, and to make appropriate course corrections as they progress.

[1037] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[1038] Step 1:

[1039] Users use devices such as smartphones or PCs to input their test-taking goals and mock test results. The input data is sent to a server and stored in a database. The input data includes the test-taker's preferred school, target score, mock test results, etc.

[1040] Step 2:

[1041] The server uses a generative AI model to analyze the student's strengths and weaknesses based on their goals and mock test results. Specifically, it analyzes the input grade data and calculates the score distribution and deviation value for each subject. This allows it to identify areas where the student needs to particularly improve and areas where they are already strong.

[1042] Step 3:

[1043] The server uses a generative AI model to generate an optimal study schedule based on the student's strengths and weaknesses. It generates prompts and inputs them into the AI ​​model to calculate the study content and methods for each subject. For example, the following prompts can be used:

[1044] Generate an optimal study schedule for the following subjects for students taking the exam on 2023-12-01: Mathematics, English, Physics

[1045] The generated schedule will specify the study content and time for each day.

[1046] Step 4:

[1047] The server displays the generated study schedule in calendar format. Users can check the study content and method for each date on their smartphone or computer screen. The calendar format makes it visually easy to understand and makes it easy to plan.

[1048] Step 5:

[1049] Users enter their daily study progress on their device. The entered data is sent to the server and stored in a database. By recording their study progress and what they have done, they can check the degree to which they have achieved their plan.

[1050] Step 6:

[1051] The server then uses the generative AI model again to correct the schedule based on the user's study progress input. Specifically, it analyzes progress and adjusts study content and methods as necessary. This allows test-takers to maintain an optimal study plan at all times.

[1052] Step 7:

[1053] The server then displays the revised schedule in calendar format, allowing the user to check the updated schedule and plan their next study. This allows for efficient and effective study.

[1054] Example 3

[1055] Next, a description will be given of Example 3 of Form Example 3. 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."

[1056] Conventional learning management systems have difficulty automatically generating optimal study schedules based on students' learning status and correcting their course in real time. Furthermore, there was a lack of a way to efficiently manage the generated schedules and provide them to users, which meant that the effectiveness of learning could not be maximized.

[1057] The specific processing by the specific processing unit 290 of the data processing device 12 in the third embodiment is realized by the following means.

[1058] In this invention, the server includes means for inputting the examinee's goals and mock test results, means for analyzing the examinee's strengths and weaknesses, means for displaying the optimal study content, method, and schedule leading up to the exam, means for inputting the study progress status every day and correcting the course as needed, means for sending prompts to the generative AI model to generate an optimal study schedule, and means for saving the generated study schedule in a database and sending it to the user's terminal. This makes it possible to generate an optimal study schedule in real time based on the examinee's study status and efficiently manage and provide it.

[1059] "Exam takers' goals" refer to the learning objectives and goals that exam takers want to achieve.

[1060] "Mock test results" refers to the grades and evaluations that test takers receive in mock tests.

[1061] "Weak areas" refer to subjects or topics that test-takers find particularly difficult to understand or master.

[1062] "Areas of strength" refers to subjects or topics that a candidate finds particularly easy to understand and master.

[1063] "Study content" refers to the specific subjects and topics that test takers will study.

[1064] "Study methods" refer to the specific techniques and approaches that test takers use to advance their studies.

[1065] A "study schedule" refers to the timetable and dates planned for a test-taker to study.

[1066] "Study implementation status" refers to the content and amount of study that the test taker actually undertook.

[1067] "Correcting the course" refers to reviewing and optimizing a student's study plan.

[1068] A "generative AI model" refers to a model that uses artificial intelligence to analyze data and generate an optimal learning schedule.

[1069] A "prompt" refers to an instruction or question input to a generative AI model.

[1070] "Database" refers to an information management system for storing test takers' learning data and generated learning schedules.

[1071] "User's device" refers to electronic devices such as smartphones and tablets used by test takers.

[1072] This invention is a system for managing the learning status of test takers and providing them with an optimal study schedule. The system includes means for inputting the test taker's goals and mock test results, means for analyzing their strengths and weaknesses, means for displaying the optimal study content, method, and schedule leading up to the test, means for inputting the study progress status every day and correcting the course as needed, means for sending prompts to a generative AI model to generate an optimal study schedule, and means for saving the generated study schedule in a database and sending it to the user's terminal.

[1073] Users use a dedicated application to input their study status from devices such as smartphones or tablets. The input data includes specific study time and content. For example, information such as "October 1st: 2 hours of math, 1 hour of English" may be entered.

[1074] The device sends the entered data to the server. This transmission is secure using the HTTPS protocol. The server stores the received data in a MySQL database. The stored data is used to record the student's learning progress in detail.

[1075] The server sends a prompt to the generative AI model based on the saved data. The prompt includes past learning history. For example, the server might send the following to the generative AI model: "Test-taker A's study time and content over the past week are as follows. Based on this, please suggest the optimal study schedule for the next week."

[1076] The generative AI model generates an optimal study schedule based on the prompt. For example, it might generate a schedule such as "October 4th: 1.5 hours of math, 1.5 hours of English." The generated schedule is returned to the server.

[1077] The server saves the generated schedule in a database and sends it to the user's device. The user can check the new study schedule through the device application. For example, a schedule such as "October 4th: 1.5 hours of math, 1.5 hours of English" may be displayed.

[1078] This system allows test-takers to receive an optimal study schedule in real time, enabling them to study efficiently. Furthermore, by using a generative AI model, it is possible to provide a customized schedule according to each individual's learning situation. The flow of the specific processing in Example 3 will be explained using FIG. 15.

[1079] Step 1:

[1080] The user inputs their study status.

[1081] The user opens a dedicated application and inputs the study time and content. For example, they input specific information such as "October 1st: 2 hours of math, 1 hour of English." The input data is temporarily stored in the device's memory.

[1082] Step 2:

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

[1084] The terminal sends the data entered by the user to the server. The input data is sent in the format of "October 1st: 2 hours of math, 1 hour of English." The server analyzes the received data and prepares it to be saved in the database.

[1085] Step 3:

[1086] The server stores the data in a database.

[1087] The server parses the received JSON data and inserts it into the "Study Record" table in the MySQL database. For example, data such as "October 1st: 2 hours of math, 1 hour of English" is saved in the database. This records the user's study status.

[1088] Step 4:

[1089] The server sends a prompt to the generative AI model.

[1090] The server sends a prompt to the generative AI model based on the stored data. The prompt includes past learning history. For example, the following sentence is sent to the generative AI model: "Test-taker A's study time and content for the past week are as follows. Based on this, please suggest the optimal study schedule for the next week." The input data is the study record for the past week, and the output is the prompt sent to the generative AI model.

[1091] Step 5:

[1092] A generative AI model generates an optimal learning schedule.

[1093] The generative AI model receives prompts and generates an optimal learning schedule. For example, it generates a schedule such as "October 4th: 1.5 hours of math, 1.5 hours of English." The input data is the prompts, and the output is the generated learning schedule.

[1094] Step 6:

[1095] The server stores the generated schedule in a database.

[1096] The server inserts the schedule received from the generative AI model into the "Study Schedule" table in the database. For example, data such as "October 4th: 1.5 hours of math, 1.5 hours of English" is saved. This records the generated schedule.

[1097] Step 7:

[1098] The server transmits the schedule to the user's terminal.

[1099] The server transmits the stored schedule to the user's terminal. The input data is the generated schedule, and the output is the data transmitted to the user's terminal.

[1100] Step 8:

[1101] The user checks the schedule.

[1102] The user opens the app's "Schedule" screen and checks the new study schedule. For example, a schedule like "October 4th: 1.5 hours of math, 1.5 hours of English" is displayed. This allows the user to confirm and implement the optimal study plan.

[1103] (Application example 3)

[1104] Next, a description will be given of Application Example 3 of Form Example 3. 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."

[1105] Conventional study management systems for test takers provide study schedules based on test takers' goals and mock test results, but do not adequately adjust their study schedules in real time according to their current study status. Furthermore, they lack a means to efficiently manage the operating status and work content of factory robots and generate optimal work schedules. This leads to problems such as reduced learning efficiency for test takers and reduced work efficiency for factory robots.

[1106] The specific processing by the specific processing unit 290 of the data processing device 12 in Application Example 3 is realized by the following means. In this invention, the server includes a means for inputting the examinee's goals and mock test results, a means for analyzing the examinee's strengths and weaknesses, a means for displaying the optimal study content, method, and schedule leading up to the exam, a means for inputting the study progress status daily and correcting the course as needed, a means for recording the robot's operating status and work content, a means for generating and updating an optimal work schedule based on the recorded data, a means for generating an optimal schedule using a generative AI model, a means for generating prompt sentences and sending them to the generative AI model, and a means for obtaining the optimal schedule from the generative AI model. This makes it possible to improve the examinee's learning efficiency and maximize the work efficiency of factory robots.

[1107] "Exam takers' goals" refer to the learning objectives and goals that exam takers want to achieve.

[1108] "Mock test results" refers to the grades and evaluations of the mock test.

[1109] "Weak areas" refer to areas of study that test-takers find particularly difficult to understand or master.

[1110] "Areas of strength" refers to areas of study that are particularly easy for the candidate to understand and master.

[1111] "Study content" refers to the specific subjects and topics that test takers will study.

[1112] "Study methods" refer to the methods and techniques that test takers use to advance their studies.

[1113] "Schedule" refers to the timetable or plan for a test-taker's studies.

[1114] "Study implementation status" refers to the progress and content of the study that the test-taker actually undertook.

[1115] "Correcting the course" refers to reviewing and optimizing a student's study plan.

[1116] "Robot operation status" refers to the progress and status of the work that a factory robot is actually performing.

[1117] "Work content" refers to the specific work or tasks that a factory robot will perform.

[1118] "Recorded data" refers to saved information about the robot's operating status and work content.

[1119] A "generative AI model" refers to a model that uses artificial intelligence to analyze data and generate optimal schedules and plans.

[1120] A "prompt" refers to an instruction or question that is input to a generative AI model.

[1121] An "optimal schedule" refers to a plan or timetable generated to maximize the efficiency of students or robots.

[1122] A system for implementing this invention includes means for inputting the test-taker's goals and mock test results, means for analyzing the test-taker's strengths and weaknesses, means for displaying the optimal study content, method, and schedule leading up to the test, means for inputting the study progress status every day and correcting the course each time, means for recording the robot's operating status and work content, means for generating and updating an optimal work schedule based on the recorded data, means for generating an optimal schedule using a generative AI model, means for generating prompt text and sending it to the generative AI model, and means for obtaining the optimal schedule from the generative AI model.

[1123] The server provides an interface for students to input their goals and mock exam results. Students input this information through a dedicated application. The entered data is used on the server to analyze their strengths and weaknesses. Based on the analysis results, the server generates optimal study content, methods, and schedules leading up to the exam and displays them to the student.

[1124] Furthermore, students enter their daily study progress into the application. Based on this information, the server uses a generative AI model to generate an optimal schedule and makes course corrections as necessary. The server generates prompt sentences and sends them to the generative AI model to obtain the optimal schedule.

[1125] As a concrete example, if a test-taker inputs study content such as "Solve math problems for two hours," the server records that information and sends the following prompt to the generative AI model:

[1126] Example prompt sentence:

[1127] Current schedule: 2 hours of math worksheets

[1128] Generate the optimal schedule.

[1129] On the other hand, factory robots require sensors and a logging system to record the operating status and work content of each robot. The robots send their operating status and work content to a server, and the server generates and updates an optimal work schedule based on that data. A generative AI model is used to generate prompt sentences and obtain the optimal schedule.

[1130] The hardware used includes smartphones and tablets to accept input from test takers, sensors and logging systems to record the operating status of factory robots, and software using Python, OpenAI APIs, and standard libraries for data processing (e.g., datetime, json).

[1131] This system will improve the learning efficiency of test takers and maximize the work efficiency of factory robots.

[1132] The flow of the specific processing in Application Example 3 will be described with reference to FIG.

[1133] Step 1:

[1134] The user (candidate) enters their goals and mock test results through a dedicated application. The entered data is sent to the server, which receives the data and stores it in a database. The input data includes the candidate's goals, mock test scores, and scores for each subject.

[1135] Step 2:

[1136] The server analyzes the test-taker's areas of strength and weakness based on the test-taker's input data. Specifically, it analyzes mock test results and calculates the score distribution for each subject. Subjects with low scores are classified as weak areas, and subjects with high scores are classified as strong areas. The analysis results are saved in a database.

[1137] Step 3:

[1138] The server generates the optimal study content, method, and schedule for the exam based on the analysis results. The generated schedule takes into consideration the test-taker's goals and weak areas. The generated schedule is displayed in the user's (test-taker's) application.

[1139] Step 4:

[1140] The user (candidate) enters their daily study status into the application. The input data includes subjects studied, study time, study content, etc. The input data is sent to the server and saved in the database.

[1141] Step 5:

[1142] The server uses a generative AI model to generate an optimal schedule based on the student's study progress. Specifically, it generates a prompt and sends it to the generative AI model. The prompt includes the student's current schedule and progress.

[1143] Step 6:

[1144] The generative AI model receives the prompt sentence and generates an optimal schedule. The generated schedule is sent to the server, which receives the schedule and stores it in a database.

[1145] Step 7:

[1146] The server displays the generated optimal schedule in the user's (candidate's) application, and the user can proceed with their studies based on the new schedule.

[1147] Step 8:

[1148] In the case of factory robots, the robots send their operating status and work details to a server via sensors and a logging system, and the server receives this data and stores it in a database.

[1149] Step 9:

[1150] The server uses a generative AI model to generate an optimal work schedule based on the robot's operating status and work content. It generates a prompt statement and sends it to the generative AI model. The prompt statement includes the current work schedule and operating status.

[1151] Step 10:

[1152] The generative AI model receives the prompt sentence and generates an optimal work schedule. The generated schedule is sent to the server, which receives the schedule and stores it in a database.

[1153] Step 11:

[1154] The server sends the generated optimal work schedule to the robot, which can then proceed with its work based on the new schedule.

[1155] 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.

[1156] "Example 1"

[1157] As one embodiment of the present invention, a system including an emotion engine for recognizing the emotions of test-takers is provided. This emotion engine infers emotions from the test-takers' facial expressions, tone of voice, study behavior, etc. while they are studying. Specifically, when the test-takers are using a study device (e.g., a PC or tablet), the system captures the test-takers' facial expressions and voice using the device's camera and microphone, and analyzes this information to infer emotions.

[1158] "Example 2"

[1159] The emotion engine also detects changes in the student's emotions depending on their learning status and provides feedback to the generative AI. Specifically, if the emotion engine detects worsening emotions, such as when the student is struggling with their studies or their motivation to study is declining, it will pass that information on to the generative AI.

[1160] "Example 3"

[1161] The generative AI optimizes the student's study schedule based on feedback from the emotion engine. Specifically, if the emotion engine receives information indicating a worsening emotion, such as when the student is struggling with their studies or their motivation to study is declining, the generative AI will adjust the study schedule taking that information into account. For example, it will reduce the study time for subjects the student is weak in and increase the study time for subjects they are strong in.

[1162] The processing flow of each embodiment will be described below.

[1163] "Example 1"

[1164] Step 1: The student begins studying using a study device (e.g., computer or tablet).

[1165] Step 2: Use the device's camera and microphone to capture the test taker's facial expressions and voice.

[1166] Step 3: The captured facial and voice information is sent to the emotion engine.

[1167] Step 4: The emotion engine analyzes the information and estimates the test-taker's emotions.

[1168] "Example 2"

[1169] Step 1: The emotion engine detects changes in emotions according to the test-taker's learning situation.

[1170] Step 2: If the emotion engine detects an aggravating emotion, it communicates that information to the generative AI.

[1171] "Example 3"

[1172] Step 1: The generative AI receives feedback from the emotion engine.

[1173] Step 2: The generative AI takes into account the information it receives and adjusts the student's study schedule.

[1174] Step 3: For example, make adjustments such as reducing the study time for areas in which the test-taker is weak and increasing the study time for areas in which the test-taker is strong.

[1175] Example 1

[1176] Next, a description will be given of Example 1 of Form 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."

[1177] Conventional support systems for test takers can input test taker goals and mock test results and analyze their strengths and weaknesses, but they do not provide learning support that takes test takers' emotions into consideration. As a result, it is difficult to properly manage test takers' motivation and concentration, and there is an issue of not being able to achieve optimal learning results.

[1178] 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.

[1179] In this invention, the server includes a means for inputting the examinee's goals and mock test results, a means for analyzing the examinee's strengths and weaknesses, a means for displaying the optimal study content, method, and schedule leading up to the exam, a means for inputting the examinee's study progress every day and correcting the course as needed, and a means for capturing the examinee's facial expressions and voice and analyzing their emotions. This makes it possible to provide comprehensive study support that takes into account not only the examinee's learning progress but also their emotional state.

[1180] "Exam takers' goals" refer to the specific learning goals and schools they wish to attend.

[1181] "Mock test results" refers to data showing the scores and grades of test takers on mock tests.

[1182] "Means of input" refers to the interface or device that allows test takers to input their goals and mock test results into the system.

[1183] "Means of analysis" refers to algorithms or software that analyze the input data and identify the test-taker's areas of strength and weakness.

[1184] "Means of display" refers to a display or screen used to visually present analysis results and study plans to test takers.

[1185] "Tracking tools" refers to algorithms and software that adjust study plans based on a student's learning situation.

[1186] "Means for capturing facial expressions and voices" refers to cameras and microphones used to collect the facial expressions and voices of test takers.

[1187] "Means for analyzing emotions" refers to algorithms or software that analyze collected facial and vocal data to estimate the test-taker's emotional state.

[1188] "Generative AI" refers to artificial intelligence that analyzes and generates data based on input data.

[1189] An "emotion engine" refers to software or algorithms that analyze test-takers' facial expressions and voice data to estimate their emotions.

[1190] This invention is a system that inputs the test-taker's goals and mock test results, analyzes their areas of strength and weakness, displays the optimal study content, method, and schedule leading up to the test, inputs the student's study progress every day, and makes corrections as needed. It also includes a function to capture the student's facial expressions and voice and analyze their emotions.

[1191] System configuration

[1192] 1. Enter the student's goals and mock test results

[1193] Users access a dedicated form on a web browser and enter their goals and mock exam results. For example, using Google Chrome, they can enter "Preferred university: University of Tokyo" and "Mock exam results: Math 80 points, English 70 points, Physics 60 points." Once they've finished entering the information, they click the submit button.

[1194] 2. Data Analysis

[1195] The server receives the data sent by the user. The received data is passed to a generative AI model (e.g., OpenAI's GPT-4). The generative AI model analyzes the input data and processes the data using statistical methods based on the scores for each subject.

[1196] 3. Identify your weaknesses and strengths

[1197] The server receives the analysis results from the generative AI model and identifies the user's areas of strength and weakness. For example, if a student's score is high in math and low in physics, math is identified as a strong area and physics as a weak area. The identified information is reflected in the user's study plan.

[1198] 4. Use of Learning Devices

[1199] A user begins learning using a learning device such as a PC or tablet, for example by accessing an online learning platform and viewing learning content.

[1200] 5. Capturing facial expressions and voice

[1201] The device captures the user's facial expressions and voice in real time during learning using a camera and microphone, such as the built-in camera and microphone of a PC.

[1202] 6. Emotion Analysis

[1203] The server receives the facial expression and voice data sent from the device. The received data is passed to the emotion engine. The emotion engine analyzes the facial expression and tone of voice to estimate the user's emotion. For example, if the user is smiling, it is estimated to be "positive," and if they are frowning, it is estimated to be "negative."

[1204] Specific examples

[1205] Enter the student's goals and mock test results

[1206] The user enters "University of choice: University of Tokyo" and "Mock exam results: Math 80 points, English 70 points, Physics 60 points" into the form on the web browser and clicks the submit button.

[1207] Data analysis

[1208] The server passes the received data to a generative AI model (GPT-4) and analyzes the scores for each subject. For example, it verifies that the score for math is 80 points.

[1209] Identifying areas of weakness and strength

[1210] Based on the analysis results, the server identifies areas where the user is strong in mathematics and weak in physics, and reflects this in the user's study plan.

[1211] Use of learning devices

[1212] Users use their computers to access the online learning platform and solve math problems.

[1213] Capturing facial expressions and voice

[1214] The device uses a camera and microphone to capture the user smiling and solving problems while studying.

[1215] Emotion Analysis

[1216] The server receives the data sent from the device and uses the Emotion API to analyze the user's smile as "positive."

[1217] Prompt Sentence Examples

[1218] "Please explain a system that inputs a student's goals and practice test results and uses generative AI to identify their areas of strength and weakness. Also, explain how an emotion engine can be used to recognize emotions during learning."

[1219] The flow of the identification process in the first embodiment will be described with reference to FIG.

[1220] Step 1:

[1221] The user enters their goals and practice test results.

[1222] The user accesses a dedicated form on a web browser and enters "University of choice: University of Tokyo" and "Mock exam results: Math 80 points, English 70 points, Physics 60 points." Once the information is complete, the user clicks the send button. The input data is sent to the server.

[1223] Step 2:

[1224] The server receives the input data and analyzes it using a generative AI model.

[1225] The server receives the goal and mock test results data sent by the user. The received data is passed to a generative AI model (e.g., GPT-4). The generative AI model analyzes the scores for each subject and processes the data using statistical methods. For example, it verifies that the math score is 80 points. The analysis results are returned to the server.

[1226] Step 3:

[1227] The server identifies areas of weakness and strength based on the analysis results.

[1228] The server receives the analysis results from the generative AI model and identifies the user's areas of strength and weakness. For example, if a user's score is high in mathematics and low in physics, mathematics is identified as a strong area and physics as a weak area. The identified information is reflected in the user's study plan. The study plan is sent from the server to the user.

[1229] Step 4:

[1230] The user studies using a learning device.

[1231] Users begin learning using a learning device such as a PC or tablet. For example, they access an online learning platform and view learning content. Data from the learning process is stored on the device.

[1232] Step 5:

[1233] The device captures the user's facial expressions and voice through a camera and microphone.

[1234] The device captures the user's facial expressions and voice in real time using a camera and microphone, such as the built-in camera and microphone of a PC, and the captured data is sent to a server.

[1235] Step 6:

[1236] The server analyzes the user's emotions using an emotion engine.

[1237] The server receives the facial expression and voice data sent from the device. The received data is passed to the emotion engine. The emotion engine analyzes the facial expression and tone of voice to estimate the user's emotion. For example, if the user is smiling, it is estimated to be "positive," and if they are frowning, it is estimated to be "negative." The analysis results are stored on the server and fed back to the user as needed.

[1238] (Application example 1)

[1239] Next, a description will be given of Application Example 1 of Form 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."

[1240] Conventional learning support systems can input the student's goals and mock test results and analyze their strengths and weaknesses, but there was no system that could analyze the worker's skills and work efficiency and propose optimal work arrangements. There was also a lack of means to recognize the worker's emotions and provide support to reduce stress and fatigue. This meant that work efficiency was not being improved sufficiently and worker health management was not being carried out sufficiently.

[1241] The specific processing by the specific processing unit 290 of the data processing device 12 in Application Example 1 is realized by the following means. In this invention, the server includes means for inputting the examinee's goals and mock test results, means for analyzing the examinee's strengths and weaknesses, means for displaying the optimal study content, method, and schedule leading up to the exam, means for inputting the study progress status every day and correcting the course as needed, means for inputting the worker's skills and work efficiency, means for analyzing the worker's strengths and weaknesses, means for analyzing the worker's facial expressions and tone of voice to estimate emotions, and means for providing support to reduce the worker's stress and fatigue. This not only provides study support for examinees, but also enables the worker's work efficiency to be improved and health management to be achieved.

[1242] "Exam takers' goals" are specific goals regarding learning and exams that exam takers want to achieve.

[1243] "Mock test results" are data showing the scores and evaluations of mock tests.

[1244] "Input means" refers to an interface or device for inputting information into a system.

[1245] "Weak areas" are areas or subjects that examinees or workers find particularly difficult to understand or perform.

[1246] "Area of ​​expertise" refers to an area or subject in which a candidate or worker is particularly good.

[1247] "Means for analysis" are methods or tools for analyzing input data and extracting specific information.

[1248] "Optimal study content, methods, and schedule" refers to the study plans and techniques that are most suitable for test-takers to study efficiently.

[1249] "Display means" refers to a device or interface for visually displaying analysis results and proposals.

[1250] "Study implementation status" refers to the record of the study activities and progress that the examinee actually undertook.

[1251] "Course correction tools" are methods and tools for adjusting learning plans and work plans as needed.

[1252] "Worker skills" refers to the level of technique and ability that a worker possesses.

[1253] "Work efficiency" is an index that indicates how efficiently a worker can perform work within a certain period of time.

[1254] "Means for analyzing facial expressions and tone of voice to estimate emotions" refers to methods and tools for analyzing changes in a worker's facial expressions and voice to estimate their emotional state.

[1255] "Measures to provide support for reducing stress and fatigue" are methods and tools that provide suggestions and support to reduce stress and fatigue in workers.

[1256] The system for carrying out the present invention includes a program for inputting and analyzing the goals and results of examinees and workers. A specific embodiment of this system will be described below.

[1257] System configuration

[1258] The server includes the following means:

[1259] 1. A way to input test-taker goals and mock test results

[1260] 2. A way to analyze your strengths and weaknesses

[1261] 3. A way to display the optimal study content, method, and schedule leading up to the exam

[1262] 4. A way to input your study progress every day and make adjustments as needed

[1263] 5. Means of inputting worker skills and work efficiency

[1264] 6. A means of analyzing workers' strengths and weaknesses

[1265] 7. A method for estimating emotions by analyzing a worker's facial expressions and tone of voice

[1266] 8. Measures to support workers in reducing stress and fatigue

[1267] Hardware and software used

[1268] Hardware: Camera, microphone, computer or tablet

[1269] Software: Web browser

[1270] Data processing and calculation

[1271] The server uses a camera and microphone to capture the worker's facial expressions and tone of voice. This data is then processed and input into an emotion recognition model. The emotion recognition model estimates the worker's emotions and provides support for reducing stress and fatigue based on the results.

[1272] Specific examples

[1273] For example, if a worker is tired, the system will analyze their facial expressions and tone of voice and suggest taking a break. Also, if a test-taker has weaknesses in a particular subject, the system will suggest a study schedule that focuses on that subject.

[1274] Prompt Sentence Examples

[1275] "Design a system that analyzes a worker's facial expressions and tone of voice and suggests a break if they are feeling fatigued or stressed."

[1276] In this way, the server can analyze data on test takers and workers and provide optimal learning and working environments.

[1277] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[1278] Step 1:

[1279] The user inputs their goals and mock test results. The user inputs their goals and mock test results using a form on a web browser. The input data is sent to the server. The input data includes the student's goals, mock test scores, and subject scores.

[1280] Step 2:

[1281] The server receives the input data and inputs it into the generative AI model. The server preprocesses the received data and inputs it into the generative AI model. The generative AI model analyzes the data to identify the test-taker's strengths and weaknesses. The analysis results are output as the strengths and weaknesses of each subject.

[1282] Step 3:

[1283] The server generates the optimal study content, method, and schedule based on the analysis results.The server generates the optimal study content, method, and schedule for the test-taker based on the output of the generative AI model.The generated schedule includes a specific study plan aimed at achieving the test-taker's goals.

[1284] Step 4:

[1285] The server displays the generated schedule to the user. The server displays the generated study schedule on a web browser. The user checks the displayed schedule and begins studying.

[1286] Step 5:

[1287] The user enters their study progress every day. The user enters their daily study progress into a form on a web browser. The input data includes the content studied, study time, level of understanding, etc.

[1288] Step 6:

[1289] The server receives the study progress data and makes course corrections. The server analyzes the received study progress data and modifies the study schedule as necessary. The modified schedule is then displayed to the user again.

[1290] Step 7:

[1291] The user inputs their work skills and work efficiency. The user inputs their work skills and work efficiency into a form on a web browser. The input data includes the work content, work time, work efficiency, etc.

[1292] Step 8:

[1293] The server receives the input data and analyzes the worker's strengths and weaknesses. The server preprocesses the received data and inputs it into the generative AI model. The generative AI model analyzes the data to identify the worker's strengths and weaknesses. The analysis results output the worker's strengths and weaknesses for each task.

[1294] Step 9:

[1295] The server captures the worker's facial expressions and tone of voice. The server uses a camera and microphone to capture the worker's facial expressions and tone of voice. The captured data is sent to the server in real time.

[1296] Step 10:

[1297] The server analyzes the captured data and estimates emotions. The server processes the captured facial and voice data and inputs it into an emotion recognition model. The emotion recognition model estimates the worker's emotions and outputs the results.

[1298] Step 11:

[1299] The server provides support for reducing stress and fatigue based on the emotion recognition results. Based on the output of the emotion recognition model, the server generates suggestions to reduce the worker's stress and fatigue. For example, if the worker is tired, the server suggests taking a break. The generated suggestions are notified to the user.

[1300] Example 2

[1301] Next, a description will be given of Example 2 of Form 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."

[1302] Conventional learning support systems have limited means for optimizing students' study plans, and are particularly unable to respond to changes in students' emotions. As a result, students may feel stressed about studying or lose motivation, resulting in poor learning efficiency. Furthermore, the system lacks the ability to automatically correct course based on the students' progress, making it difficult for them to study effectively.

[1303] 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.

[1304] In this invention, the server includes means for inputting the examinee's goals and mock test results, means for analyzing the examinee's strengths and weaknesses, means for displaying the optimal study content, method, and schedule leading up to the exam, means for inputting the study progress every day and correcting the course as needed, means for detecting changes in the examinee's emotions, and means for recalculating and adjusting the study schedule based on the detected changes in emotions. This maximizes the examinee's learning efficiency and makes it possible to flexibly respond to changes in emotions.

[1305] "Exam takers' goals" refer to the learning outcomes and grades that exam takers want to achieve.

[1306] "Mock test results" refers to the grades and evaluations that candidates receive in mock tests.

[1307] "Weak areas" refer to subjects or topics that test-takers find particularly difficult to understand or master.

[1308] "Areas of strength" refers to subjects or topics that test takers find particularly easy to understand and master.

[1309] "Optimal learning content" refers to the specific learning items and materials that test takers need to study efficiently.

[1310] "Optimal study methods" refer to specific study techniques and approaches that allow test-takers to study efficiently.

[1311] An "optimal schedule" refers to the specific study time and dates planned to allow test-takers to study efficiently.

[1312] "Study implementation status" refers to the progress and results of the study that the examinee actually undertook.

[1313] "Correcting course" refers to reviewing a test-taker's study plan and schedule and making changes as necessary.

[1314] "Changes in emotions" refers to changes in the psychological state of test-takers, such as their motivation to study or stress.

[1315] A "generative AI model" refers to an artificial intelligence model that generates optimal study plans based on test-taker learning data.

[1316] "Recalculation" refers to recalculating a test-taker's study plan and schedule based on new data and conditions.

[1317] MODE FOR CARRYING OUT THE INVENTION

[1318] This invention is a system for maximizing the learning efficiency of test-takers and flexibly responding to changes in their emotions. A specific embodiment of this system is described below.

[1319] System configuration

[1320] This system consists of three main components: a server, a terminal, and a user. The server runs a program that includes a generative AI model and an emotion engine. The terminal provides an interface for users to input their learning data and check their learning schedule. The user uses the system as a test-taker.

[1321] Hardware and software used

[1322] The server is a high-performance computer that runs the generative AI model using Python and TensorFlow. The emotion engine is built using Python and OpenCV. The terminal is a personal computer or smartphone operated by the user, with a dedicated application installed.

[1323] Data processing and calculation

[1324] The server receives learning data entered by the user and analyzes it using a generative AI model. Specifically, it calculates the optimal learning content, method, and schedule based on data such as the subject, study time, progress, and goals. The calculation results are sent to the device in JSON format.

[1325] The device displays the received data in a calendar format. The user proceeds with their study while looking at the calendar, and when they finish studying, they enter their progress into the device. The device then sends the entered progress data to the server.

[1326] The server uses an emotion engine to detect changes in the user's emotions. The emotion engine analyzes the user's facial expressions and voice data to detect stress and loss of motivation. The detected changes in emotions are fed back to the server and conveyed to the generative AI model.

[1327] The generative AI model recalculates the learning schedule based on the feedback and makes adjustments as needed, and the recalculated schedule is sent back to the device and displayed to the user.

[1328] Specific examples

[1329] For example, consider a case where a user is working on a math problem set but is stressed because they are unable to solve many of the problems. The emotion engine detects stress from the user's facial expressions and voice and relays this information to the generative AI model. The generative AI model then adjusts the next day's schedule to reduce stress and includes relaxing activities (such as studying a favorite subject or taking a short break).

[1330] Prompt Sentence Examples

[1331] "Based on the student's learning data, calculate the optimal study content, method, and schedule, and display it in a calendar format. Also, detect changes in the student's emotions and adjust the study schedule as necessary."

[1332] In this way, the system can maximize the learning efficiency of test-takers and respond flexibly to changes in their emotions.

[1333] The flow of the identification process in the second embodiment will be described with reference to FIG.

[1334] Step 1:

[1335] The user uses the device to input study data. Specifically, they input study subjects, study time, progress, goals, etc. The input data is sent from the device to the server. The input data includes information such as "Mathematics, 2 hours, 50% completed, 80 points or more on the next mock exam."

[1336] Step 2:

[1337] The server receives the training data sent by the user and inputs it into the generative AI model. The generative AI model is built using Python and TensorFlow, and calculates the optimal training content, method, and schedule based on past training data and statistical information. The calculation results are output in JSON format.

[1338] Step 3:

[1339] The server sends the calculation results obtained from the generative AI model to the device, which then displays the received data in a calendar format. For example, it displays a specific schedule such as "2 hours of math workbooks" on Monday and "1 hour of English listening" on Tuesday.

[1340] Step 4:

[1341] The user studies while looking at the calendar on the device. When the study is finished, the user enters the progress on the device. For example, the user enters information such as "Completed 2 hours of math problems." The entered progress data is sent from the device to the server.

[1342] Step 5:

[1343] The server uses an emotion engine to detect changes in the user's emotions. The emotion engine is built using Python and OpenCV and analyzes the user's facial expressions and voice data. For example, if the user frowns or sighs, the emotion engine detects stress. The detected changes in emotions are fed back to the server.

[1344] Step 6:

[1345] The server receives feedback from the emotion engine and relays it to the generative AI model. The generative AI model recalculates the study schedule based on the feedback and makes adjustments as necessary. For example, if the user is feeling stressed about math, it will adjust the schedule for the next day and add relaxing content (such as studying a favorite subject or taking a short break). The recalculated schedule is again output in JSON format.

[1346] Step 7:

[1347] The server then sends the recalculated schedule to the device, which then displays it in calendar format to the user. The user then continues their studies according to the new schedule. This process is repeated to maximize the user's learning efficiency and flexibly respond to emotional changes.

[1348] (Application example 2)

[1349] Next, a description will be given of Application Example 2 of Form 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."

[1350] Conventional study support systems for test takers have difficulty responding to changes in test takers' emotions and motivation, resulting in a decline in study efficiency. Furthermore, in the shopping experience at physical stores, optimal suggestions based on the user's emotions and stress level are not provided, resulting in a decline in shopping satisfaction. To solve these issues, a system that can detect the user's emotions in real time and make optimal suggestions based on that information is needed.

[1351] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 2 is realized by the following means.

[1352] In this invention, the server includes a means for inputting the test-taker's goals and mock test results, a means for analyzing the test-taker's strengths and weaknesses, a means for displaying the optimal study content, method, and schedule leading up to the test, a means for inputting the study progress every day and correcting the course as needed, a means for detecting the user's emotions, and a means for making optimal suggestions based on the user's emotions. This improves the test-taker's learning efficiency and also makes it possible to increase user satisfaction in the shopping experience at a physical store.

[1353] "Exam takers' goals" refers to the specific learning goals and schools that exam takers want to achieve.

[1354] "Mock test results" refers to data showing the scores and evaluations of mock tests.

[1355] "Weak areas" refer to areas of study that test-takers find particularly difficult to understand or master.

[1356] "Areas of strength" refers to areas of study that are particularly easy for the candidate to understand and master.

[1357] "Optimal study content" refers to the learning content that is most effective for helping test-takers achieve their goals.

[1358] "Method" refers to the specific means and techniques used to advance your studies.

[1359] A "schedule" refers to a timetable or plan for studying.

[1360] "Study implementation status" refers to the progress and results of the learning activities that the test-taker actually undertakes.

[1361] "Correcting course" refers to changing your study plan or method as needed.

[1362] "User emotion" refers to the psychological state or mood that a user is feeling.

[1363] "Optimal suggestions" refers to providing the most appropriate advice or recommendations based on the user's situation and emotions.

[1364] The following system configuration will be described as an embodiment of the present invention.

[1365] System Configuration

[1366] This system consists of a server, a user terminal, and an emotion detection device. The server generates a test-taker's study plan using a generative AI model and detects the user's emotions using an emotion engine. The user terminal is a device such as a smartphone or tablet, and is used by the user to check the study plan and enter the progress status. The emotion detection device detects the user's emotions in real time using the smartphone's camera and microphone.

[1367] Program processing

[1368] The server performs the following process.

[1369] 1. A way to input test-taker goals and mock test results

[1370] The test-taker's goals and mock test results are entered on the user's device and sent to the server, which then grasps the test-taker's current academic ability and goals.

[1371] 2. A way to analyze your strengths and weaknesses

[1372] The server analyzes the test taker's mock exam results and identifies their areas of strength and weakness using data analysis software (e.g., Python's Pandas library).

[1373] 3. A way to display optimal study content, methods, and schedules

[1374] The server uses a generative AI model to calculate the optimal study content, method, and schedule for each test-taker, and displays it in a calendar format on the user's device. The generative AI model uses machine learning libraries (e.g., TensorFlow, PyTorch).

[1375] 4. A way to input your study progress every day and make adjustments as needed

[1376] Students enter their study progress daily from their devices and send it to the server, which then automatically adjusts their study plan based on their progress.

[1377] 5. How to detect user emotions

[1378] Detect user emotions in real time using emotion detection devices (smartphone cameras and microphones) and analyze user emotion data using emotion recognition APIs (e.g., Microsoft Azure Emotion API).

[1379] 6. A way to make optimal suggestions based on user emotions

[1380] The server optimizes study plans and shopping lists based on the user's emotional data obtained from the emotion engine. For example, if the user is feeling stressed, the server suggests products and study methods that will help them relax.

[1381] Specific examples

[1382] When a user is shopping in a physical store, their facial expressions are read using a smartphone camera, and the emotion engine detects "fatigue." Based on this information, the generative AI adds chocolate to the shopping list as a "relaxing product."

[1383] Prompt Sentence Examples

[1384] "When a user is shopping in a physical store, their facial expressions are read using their smartphone camera, and the emotion engine detects their emotions. Based on that information, the generative AI creates an optimal shopping list and suggests it to the user."

[1385] The above is an embodiment of the present invention.

[1386] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[1387] Step 1:

[1388] The user's device inputs the student's goals and mock exam results, and sends them to the server. The input data includes the student's desired school, target score, and mock exam results. The server receives this data and stores it in a database.

[1389] Step 2:

[1390] The server analyzes the test-taker's mock test results and identifies their areas of strength and weakness. Specifically, it uses Python's Pandas library to analyze the mock test score data and calculate the score distribution for each subject. This allows it to identify the test-taker's areas of strength and weakness.

[1391] Step 3:

[1392] The server uses a generative AI model to calculate the optimal study content, method, and schedule for each test-taker. Input data includes the test-taker's goals, areas of weakness, and areas of strength. The generative AI model generates an optimal study plan based on this data. The output data is a study schedule in calendar format, which is sent to the user's device.

[1393] Step 4:

[1394] The user's device inputs their study progress every day and sends it to the server. The input data includes the actual study content, time, and progress. The server receives this data and stores it in a database.

[1395] Step 5:

[1396] The server automatically adjusts the learning plan based on the student's progress. Specifically, it uses a machine learning algorithm to analyze the student's progress data and update the learning plan as needed. The updated learning plan is then sent back to the user's device.

[1397] Step 6:

[1398] An emotion detection device (such as a smartphone camera or microphone) detects the user's emotions in real time and sends the data to a server. The input data includes the user's facial expressions and voice. The server then uses an emotion recognition API (e.g., Microsoft Azure Emotion API) to analyze this data and identify the user's emotional state.

[1399] Step 7:

[1400] The server optimizes study plans and shopping lists based on the user's emotional data obtained from the emotion engine. Specifically, if the user is feeling stressed, the server suggests products and study methods that will help them relax. The generated suggestions are sent to the user's device.

[1401] The above are the specific processing steps of this system.

[1402] Example 3

[1403] Next, a description will be given of Example 3 of Form Example 3. 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."

[1404] Conventional learning support systems have difficulty in dynamically optimizing learning schedules that take into account the student's study status and emotional state. This has led to problems such as a decline in motivation and learning efficiency. Furthermore, there has been a lack of effective ways to balance the student's strengths and weaknesses.

[1405] The specific processing by the specific processing unit 290 of the data processing device 12 in the third embodiment is realized by the following means.

[1406] In this invention, the server includes a means for inputting the test-taker's goals and mock test results, a means for analyzing the test-taker's strengths and weaknesses, a means for displaying the optimal study content, method, and schedule leading up to the test, a means for inputting the study progress status every day and correcting the course as needed, a means for analyzing the emotional state and providing feedback, a means for optimizing the study schedule using a generative AI model, and a means for providing the test-taker with the optimized study schedule. This makes it possible to provide an effective study schedule while maximizing the test-taker's learning efficiency and maintaining their motivation.

[1407] "Test-taker's goals" refer to the learning objectives and target scores that test-taker wants to achieve.

[1408] "Mock test results" refers to the grades or scores that a candidate receives on a mock test.

[1409] "Weak areas" refer to subjects or topics that test-takers find particularly difficult to understand or master.

[1410] "Areas of strength" refers to subjects or topics that a candidate finds particularly easy to understand and master.

[1411] "Study implementation status" refers to the content and amount of study that test takers actually undertake.

[1412] "Emotional state" refers to the psychological state of test-takers, such as their motivation to study and stress.

[1413] "Feedback" refers to advice and information provided based on the analysis of emotional state and learning progress.

[1414] "Generative AI model" refers to an artificial intelligence model that uses machine learning algorithms to optimize learning schedules.

[1415] A "study schedule" refers to a schedule that shows which subjects a test-taker plans to study and at what times.

[1416] "Optimization" refers to adjusting a test-taker's study schedule to maximize their learning efficiency.

[1417] The present invention relates to a learning support system for maximizing the learning efficiency of test takers. A specific embodiment of this system will be described below.

[1418] System configuration

[1419] Hardware and Software

[1420] The system is implemented using the following hardware and software.

[1421] Server: Stores data, analyzes it, and runs generative AI models. Specifically, it uses a database (such as MySQL or PostgreSQL) and a machine learning framework (such as TensorFlow or PyTorch).

[1422] Terminal: A device that allows users to input their study progress. Specifically, mobile devices such as smartphones and tablets are used.

[1423] Dedicated application: An application that allows users to input their study progress and check an optimized study schedule. Specifically, an application such as "StudyTracker" is used.

[1424] System Operation

[1425] Data Entry

[1426] The user uses a dedicated application to input their daily study status. The input data includes the subjects studied, study time, and study content. For example, the user might input, "I studied calculus for two hours."

[1427] Data transmission

[1428] The terminal transmits the input data to a server in real time via the Internet.

[1429] Data storage

[1430] The server stores the received data in a database, using a relational database such as MySQL or PostgreSQL.

[1431] Emotional state analysis

[1432] The server analyzes the test-taker's emotional state using an emotion engine, which generates feedback such as "motivation is declining" or "struggle to study" based on the user's input data and past learning history.

[1433] Optimizing your study schedule

[1434] The server inputs the study progress data stored in the database and feedback from the emotion engine into the generative AI model. The generative AI model then optimizes the study schedule based on this data. Specifically, it makes adjustments such as reducing study time in areas where the student is weak and increasing study time in areas where the student is strong.

[1435] Schedule provision

[1436] The server provides the user with an optimized learning schedule output from the generative AI model, and the user can check the new schedule through a dedicated application.

[1437] Specific examples

[1438] As a concrete example, consider a situation where a user is not good at calculus, and their motivation decreases as the time spent studying increases. In this case, the emotion engine sends feedback of "decreased motivation" to the generative AI model. Based on this information, the generative AI model adjusts the schedule to reduce the time spent studying calculus and increase the time spent studying English, which is their strong point.

[1439] Prompt Sentence Examples

[1440] Generate a program to optimize the student's study schedule based on the student's study progress and feedback from the emotion engine. Adjust the program to reduce the time spent studying areas where the student is weak and increase the time spent studying areas where the student is strong.

[1441] In this way, the system provides an optimal schedule for maximizing the learning efficiency of the examinee. The flow of the specification process in the third embodiment will be described with reference to FIG.

[1442] Step 1:

[1443] The user inputs the study progress status.

[1444] The user uses a dedicated application to input the subjects they studied, the study time, and the content of their studies. For example, they might input "I studied calculus for two hours." The input data is saved in the application in the form of subjects, study time, and content of their studies.

[1445] Step 2:

[1446] The terminal sends the input data to the server.

[1447] The device (smartphone) sends the data on the user's study progress entered by the user to a server in real time via the Internet. The data arrives at the server in the form of study subjects, study time, and study content.

[1448] Step 3:

[1449] The server stores the data in a database.

[1450] The server stores the received study progress data in a database using a relational database such as MySQL or PostgreSQL. The data is stored in the database in the form of study subjects, study time, and study content.

[1451] Step 4:

[1452] The server receives feedback from the emotion engine.

[1453] The server uses an emotion engine to analyze the test-taker's emotional state. Based on the user's input data and past learning history, the emotion engine generates feedback such as "motivation is declining" or "struggle to learn." The analysis results are sent to the server as emotional state feedback.

[1454] Step 5:

[1455] The server inputs data into the generative AI model.

[1456] The server inputs the study progress data stored in the database and feedback from the emotion engine into the generative AI model. The generative AI model is built using machine learning frameworks such as TensorFlow and PyTorch. Input data is provided to the generative AI model in the form of study subjects, study time, study content, and emotional state.

[1457] Step 6:

[1458] Generative AI models optimize learning schedules.

[1459] The generative AI model optimizes the student's study schedule based on the input data. Specifically, it makes adjustments such as reducing study time in areas the student is weak in and increasing study time in areas they are strong in. The optimized schedule is generated in the form of study subjects, study time, and study content.

[1460] Step 7:

[1461] The server provides the optimized schedule to the user.

[1462] The server provides the user with an optimized study schedule output from the generative AI model. The user can check the new schedule through a dedicated application. The provided schedule is displayed in the application in the form of study subjects, study time, and study content.

[1463] (Application example 3)

[1464] Next, a description will be given of Application Example 3 of Form Example 3. 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."

[1465] Conventional learning schedule management systems do not take into account the emotional state and motivation of test-takers, resulting in poor learning efficiency. Furthermore, they are unable to monitor learning situations in real time or deliver optimal learning content, meaning they are unable to provide sufficient learning support tailored to the individual needs of test-takers.

[1466] The specific processing by the specific processing unit 290 of the data processing device 12 in Application Example 3 is realized by the following means. In this invention, the server includes a means for inputting the examinee's goals and mock test results, a means for analyzing the examinee's strong and weak areas, a means for displaying the optimal study content, method, and schedule leading up to the exam, a means for inputting the study progress status every day and correcting the course as needed, a means for adjusting the study schedule based on feedback from the emotion engine, and a means for monitoring the study status and emotional state in real time and delivering optimal study content. This makes it possible to provide an optimal study schedule that takes into account the examinee's emotional state and learning motivation, and to monitor the study status in real time and deliver optimal study content.

[1467] "Exam takers' goals" refers to the specific learning goals and schools that exam takers want to achieve.

[1468] "Mock test results" refers to the grades and evaluations that test takers receive in mock tests.

[1469] "Weak areas" refer to subjects or topics in which a test-taker has particularly poor understanding or poor performance in their studies.

[1470] "Areas of strength" refers to subjects or topics in which a candidate has particularly strong understanding or achievement in their studies.

[1471] "Study content" refers to the specific subjects and topics that test takers will study.

[1472] "Study methods" refer to the specific techniques and approaches that test takers use to advance their studies.

[1473] A "schedule" refers to the timetable or dates planned for a test-taker to study.

[1474] "Study implementation status" refers to the progress and content of the study that the test-taker actually undertook.

[1475] "Correcting the course" refers to adjusting and optimizing a test-taker's study plan and schedule.

[1476] An "emotion engine" is a system that analyzes the emotional state of test takers and provides feedback.

[1477] "Adjusting study schedule" refers to changing a test-taker's study plan based on feedback from the emotion engine.

[1478] "Monitoring learning status" refers to monitoring the learning progress and implementation status of test takers in real time.

[1479] "Delivery of learning content" refers to providing test takers with the most appropriate learning materials and teaching materials.

[1480] The system for implementing this invention consists of three main elements: a server, a terminal, and a user. The following explains how each element functions.

[1481] server

[1482] The server includes a means for inputting the test-taker's goals and mock test results, a means for analyzing the test-taker's areas of strength and weakness, a means for displaying the optimal study content, method and schedule leading up to the test, a means for inputting the study progress status every day and correcting the course as needed, a means for adjusting the study schedule based on feedback from the emotion engine, and a means for monitoring the study status and emotional state in real time and delivering the optimal study content.

[1483] The server is built using programming languages ​​such as Python or Java, and uses MySQL or PostgreSQL as the database management system (DBMS). The emotion engine analyzes the user's emotional state using natural language processing (NLP) techniques, and the generative AI model is built using machine learning frameworks such as TensorFlow and PyTorch.

[1484] Terminal

[1485] The terminal is a device through which the user inputs learning data and receives feedback. It can be a smartphone, tablet, or PC. A dedicated application is installed on the terminal, and the user inputs learning data through this application.

[1486] The application is developed using cross-platform frameworks such as React Native and Flutter, providing an intuitive interface for users to use. The application communicates with the server and sends and receives data in real time.

[1487] User

[1488] The user is a student taking an exam and inputs their daily study status through a terminal. The user uses the application to input study data and receives feedback from the emotion engine. This allows the user to receive the optimal study schedule and content.

[1489] Specific examples

[1490] For example, if a user is bad at math but good at English, and the emotional feedback is negative, the server will adjust the schedule to reduce the time spent studying math and increase the time spent studying English. The user enters the following prompt sentence into the application:

[1491] Prompt Sentence Examples

[1492] User ID: 1

[1493] Training data: {'date': '2023-10-01', 'weak_subject_time': 60, 'strong_subject_time': 30}

[1494] Emotional feedback: 'negative'

[1495] Based on this prompt, the server optimizes the study schedule and provides feedback to the user, allowing them to study efficiently.

[1496] The flow of the specific processing in Application Example 3 will be described with reference to FIG.

[1497] Step 1:

[1498] The user uses a device to input study data. Specifically, the user opens the application and inputs information such as the subjects studied, study time, and emotional state. The input data includes the date, study time for weak subjects, study time for strong subjects, emotional feedback, etc. This data is then sent from the device to the server.

[1499] Input: Study data (e.g., date, study time for weak subjects, study time for strong subjects, emotional feedback)

[1500] Output: Training data sent to the server

[1501] Step 2:

[1502] The server stores the received learning data in a database. The server analyzes the received data and stores it in a database. The database stores each user's learning history and emotional feedback.

[1503] Input: Training data sent from the device

[1504] Output: Training data stored in a database

[1505] Step 3:

[1506] The server uses an emotion engine to analyze the user's emotional feedback, which uses natural language processing techniques to analyze the user's emotional state and generate positive, neutral, or negative feedback.

[1507] Input: Emotional feedback included in the training data

[1508] Output: Parsed emotional feedback (e.g., positive, neutral, negative)

[1509] Step 4:

[1510] The server uses a generative AI model to optimize the study schedule. The generative AI model generates an optimal study schedule based on the user's learning data and emotional feedback. For example, if negative feedback is received, the study time for weak subjects will be reduced and the study time for strong subjects will be increased.

[1511] Input: Training data, analyzed emotional feedback

[1512] Output: Optimized study schedule

[1513] Step 5:

[1514] The server transmits the optimized study schedule to the terminal, and the server transmits the generated study schedule to the user's terminal so that the user can check it.

[1515] Input: Optimized study schedule

[1516] Output: Study schedule sent to the device

[1517] Step 6:

[1518] The device displays the optimized study schedule. The user can check the optimized study schedule sent from the server through the device application, which allows the user to study efficiently.

[1519] Input: Study schedule sent from the server

[1520] Output: Study schedule displayed on the device

[1521] Step 7:

[1522] The user proceeds with their studies according to the new study schedule. The user proceeds with their daily studies according to the optimized study schedule displayed on the device. Once the study is complete, they return to step 1 and enter their study data again.

[1523] Input: Optimized study schedule

[1524] Output: New training data

[1525] 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.

[1526] 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> ) 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.

[1527] Another example of generative AI is Gemini (internet search engine). <url: https: gemini.google.com ?hl="ja">) are listed.

[1528] 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.

[1529] [Third embodiment]

[1530] FIG. 5 shows an example of the configuration of a data processing system 310 according to the third embodiment.

[1531] 5, the data processing system 310 includes the data processing device 12 and a headset type terminal 314. An example of the data processing device 12 is a server.

[1532] 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).

[1533] 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.

[1534] 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.

[1535] 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).

[1536] 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.

[1537] 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.

[1538] 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.

[1539] 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.

[1540] 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.

[1541] Next, the specific processing by the specific processing unit 290 of the data processing device 12 will be described.

[1542] "Example 1"

[1543] In one embodiment of the present invention, test takers enter their goals and mock test results into the system through a dedicated input interface, such as a form running on a web browser. The input information is analyzed by generative AI to identify the test taker's strengths and weaknesses.

[1544] "Example 2"

[1545] Next, the generative AI calculates the optimal study content, method, and schedule for the exam and displays it to the test-taker. The display is typically in the form of a calendar, showing specific study content and time for each day.

[1546] "Example 3"

[1547] Furthermore, test-takers enter their daily study schedules into the system. This is done, for example, through a dedicated application, and specific study time and content are recorded. Based on this information, the system makes adjustments as needed and updates the optimal study schedule.

[1548] The processing flow of each embodiment will be described below.

[1549] "Example 1"

[1550] Step 1: The test-taker enters their goals and mock test results into the system through a dedicated input interface, such as a form that runs on a web browser.

[1551] Step 2: The input information is analyzed by generative AI to identify the candidate's areas of strength and weakness. This analysis is carried out using deep learning techniques, for example.

[1552] "Example 2"

[1553] Step 1: The generative AI calculates the optimal study content, method, and schedule for the exam. This calculation is done using techniques such as reinforcement learning.

[1554] Step 2: The calculated optimal study content, method, and schedule are displayed to the test-taker. The display is, for example, in a calendar format, showing specific study content and time for each day.

[1555] "Example 3"

[1556] Step 1: The candidate enters their daily study history into the system. This is done, for example, through a dedicated application, and the specific study time and content are recorded.

[1557] Step 2: Based on this information, the system adjusts course as needed and updates the optimal study schedule. This adjustment is done using, for example, a genetic algorithm.

[1558] Example 1

[1559] Next, a description will be given of Example 1 of Form 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."

[1560] Conventional learning support systems for test takers have had difficulty effectively utilizing test takers' goals and mock test results to identify individual areas of strength and weakness. Furthermore, they were unable to provide appropriate feedback or course corrections according to test takers' learning status, resulting in a decline in learning efficiency.

[1561] The specific processing by the specific processing unit 290 of the data processing device 12 in Example 1 is realized by the following means. In this invention, the server includes a means for inputting the examinee's goals and mock test results, a means for analyzing the examinee's strong and weak areas, a means for displaying the optimal study content, method, and schedule leading up to the exam, a means for inputting the study progress status every day and correcting the course as needed, a means for accessing a dedicated input form using a web browser, a means for passing the input data to the generative AI model, a means for the generative AI model to analyze the data and return the analysis results, and a means for displaying the analysis results to the user. This enables effective learning support tailored to the examinee's individual learning needs.

[1562] "Exam takers' goals" refers to the specific learning goals and schools that exam takers want to achieve.

[1563] "Mock test results" refers to the scores and grades for each subject in the mock test.

[1564] "Means of input" refers to the interface that allows test takers to input their goals and mock test results into the system.

[1565] "Means of analysis" refers to the function for analyzing the input data and identifying the test-taker's areas of weakness and strength.

[1566] "Means of display" refers to the function for visually presenting analysis results and study plans to test takers.

[1567] "Means for course correction" refers to the function of adjusting the study plan according to the student's learning situation.

[1568] "Web browser" refers to software for viewing web pages on the Internet.

[1569] "Specialized input form" refers to a form on a web page designed for test takers to enter their goals and mock test results.

[1570] A "generative AI model" refers to an artificial intelligence model that analyzes input data and generates a specific result.

[1571] "Means of analysis" refers to the functionality that a generative AI model has to process input data and derive a specific result.

[1572] "Means for returning analysis results" refers to the function for the generative AI model to return the analysis results to the server.

[1573] "Means for displaying to the user" refers to the function that the server uses to present the analysis results to the test-taker.

[1574] This invention is a system that allows test-takers to input their goals and mock test results, and based on that, identifies areas of strength and weakness, and provides an optimal study plan. Specific embodiments of this system are described below.

[1575] Hardware and software used

[1576] Hardware:

[1577] Server: A server that receives data, analyzes it, and returns the results

[1578] Terminal: A computer or smartphone that allows users to input information

[1579] software:

[1580] Web browser: Software that allows users to access dedicated input forms (e.g., Google Chrome, Safari)

[1581] Generative AI model: An artificial intelligence model that analyzes input data and generates a specific result (e.g., OpenAI's GPT-4)

[1582] System Operation

[1583] User Action:

[1584] The user opens a web browser on their computer or smartphone and accesses the system's URL. A dedicated input form is displayed, where the user inputs their goal (e.g., passing the first science course at the University of Tokyo) and mock exam results (e.g., 80 points in math, 70 points in English, 60 points in physics, and 50 points in chemistry). Once the input is complete, the user clicks the submit button.

[1585] Server Action:

[1586] The server receives the data sent by the user. This data is sent as an HTTP POST request. The received data is passed to a generative AI model. The generative AI model uses, for example, OpenAI's GPT-4.

[1587] Analysis of generative AI models:

[1588] The generative AI model analyzes the received data and identifies the test-taker's areas of strength and weakness. This analysis uses natural language processing technology and machine learning algorithms. The analysis results are returned to the server in JSON format.

[1589] Server results:

[1590] The server receives the analysis results returned by the generative AI model and displays them to the user. The user can check the analysis results on a web browser. The analysis results are displayed in an easy-to-read format using HTML and CSS.

[1591] Examples of concrete examples and prompts

[1592] As a specific example, consider the case where a test-taker inputs the following information:

[1593] Goal: Pass the First Class Science Course at the University of Tokyo

[1594] Mock exam results: Math 80 points, English 70 points, Physics 60 points, Chemistry 50 points

[1595] When a user enters this information into the input form and clicks the submit button, the server receives this data and passes it to the generative AI model, which then analyzes it using prompt statements like the following:

[1596] Example prompt sentence:

[1597] The student's goal is to pass the entrance exam for the first science course at the University of Tokyo. The results of the mock exam are as follows:

[1598] Mathematics: 80 points

[1599] English: 70 points

[1600] Physics: 60 points

[1601] Chemistry: 50 points

[1602] Use this information to identify the candidate's areas of weakness and strength.

[1603] The generative AI model analyzes this prompt sentence and returns a result such as the following:

[1604] Example of analysis results:

[1605] Specialties: Mathematics, English

[1606] Weak areas: Physics, chemistry

[1607] The server displays the analysis results to the user, allowing the test-taker to use them as a reference when making future study plans.

[1608] The flow of the identification process in the first embodiment will be described with reference to FIG.

[1609] Step 1:

[1610] A user opens a web browser. A user opens a web browser (e.g., Google Chrome or Safari) on their computer or smartphone. For example, by double-clicking a desktop icon or tapping an app on their smartphone. The input is the user's action, and the output is the launch of the web browser.

[1611] Step 2:

[1612] The user accesses a dedicated input form. The user accesses the dedicated input form by entering the system's URL (e.g., https: / / example.com). This form is built with HTML and JavaScript. The user enters the URL in the address bar and presses the Enter key. The input is the URL, and the output is the display of the input form.

[1613] Step 3:

[1614] The user inputs their goal and mock exam results. The user inputs their goal (e.g., passing the first science course at the University of Tokyo) and their mock exam results (e.g., 80 points for math, 70 points for English, 60 points for physics, 50 points for chemistry) into the form. Text boxes are provided for entering scores for each subject. The input is the goal and mock exam results, and the output is the generation of the input data.

[1615] Step 4:

[1616] The user submits the input. The user clicks the submit button on the form. This sends the input data to the server. The submit button is an HTML< / url:> < / button> <button>It is implemented with tags. The input is clicking the submit button, and the output is sending the data.

[1617] Step 5:

[1618] The server receives input data. The server receives data submitted by the user. This data is sent as an HTTP POST request. The server temporarily stores the received data. The input is the HTTP POST request, and the output is the stored data.

[1619] Step 6:

[1620] The server passes data to the generative AI model. The server passes the received data to the generative AI model. This generative AI model is, for example, OpenAI's GPT-4. The data is sent as an API request. The server sends an HTTP POST request to the API endpoint. The input is the stored data, and the output is the sending of the API request.

[1621] Step 7:

[1622] The generative AI model analyzes the data it receives. Specifically, it identifies the test-taker's areas of strength and weakness based on their goals and mock test results. Natural language processing technology and machine learning algorithms are used for the analysis. The input is the API request, and the output is the analysis results.

[1623] Step 8:

[1624] The generative AI model returns the analysis results to the server. The generative AI model returns the analysis results to the server. The analysis results are returned in JSON format. The server receives this JSON data. The input is the JSON data of the analysis results, and the output is receiving the data.

[1625] Step 9:

[1626] The server displays the analysis results to the user. The server receives the analysis results and displays them to the user. The user can check the analysis results on a web browser. The analysis results are displayed in an easy-to-read format using HTML and CSS. The input is the received analysis results, and the output is the display of the analysis results.

[1627] (Application example 1)

[1628] Next, a description will be given of Application Example 1 of Form 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."

[1629] With conventional learning support systems, it was difficult to create an optimal individual study plan based on the student's goals and mock test results, and they often did not provide appropriate feedback or course corrections according to the student's learning progress. This resulted in students being unable to study efficiently, making it difficult for them to achieve their goals.

[1630] 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.

[1631] In this invention, the server includes means for inputting the test-taker's goals and mock test results, means for analyzing the test-taker's strengths and weaknesses, means for displaying the optimal study content, method, and schedule leading up to the test, means for inputting the study progress on a daily basis and correcting the course as needed, means for identifying the test-taker's strengths and weaknesses using generative AI and recommending optimal study content, and means for tracking the test-taker's progress and providing regular feedback. This enables test-taker to create an individually optimized study plan and study efficiently.

[1632] "Exam takers" are students who are studying with the aim of passing an exam.

[1633] A "goal" is a specific objective that a test-taker wants to achieve, such as passing an exam or improving their grades.

[1634] A "mock exam" is a mock test that students take in preparation for the actual exam.

[1635] The "means of input" is the interface that allows test takers to input their goals and mock test results into the system.

[1636] "Means for analysis" refers to a method or device for analyzing input data and identifying the examinee's areas of strength and weakness.

[1637] "Display means" refers to a method or device for visually presenting the analysis results and study plan to the examinee.

[1638] "Means for course correction" are methods or devices for adjusting the study plan according to the student's learning progress.

[1639] "Generative AI" is artificial intelligence that generates new information and analytical results based on input data.

[1640] "Learning content" refers to educational resources such as study materials and question sets that test takers use to study.

[1641] "Tracking" means the continuous monitoring and recording of a student's learning progress.

[1642] "Feedback" refers to providing information to test takers to inform them of their learning progress and areas for improvement.

[1643] To implement this invention, a terminal used by a test-taker, a server, and a generative AI model are used. Specific embodiments are described below.

[1644] 1. System Configuration

[1645] The system includes a device used by test takers, a server that processes data, and a generative AI model. The device can be a smartphone, tablet, or PC, and the server can be a cloud server or an on-premise server. The generative AI model uses an advanced natural language processing model such as OpenAI's GPT-3.

[1646] 2. Program Processing

[1647] Enter the student's goals and mock test results

[1648] Candidates use the terminal to input their goals and mock test results. The input interface is a form that runs on a web browser and is designed to allow test takers to easily enter data.

[1649] Data analysis

[1650] The server receives the test-taker's input goals and mock test results and sends them to the generative AI model, which analyzes this data and identifies the test-taker's strengths and weaknesses.

[1651] Learning content recommendations

[1652] The server recommends optimal learning content to test-takers based on the analysis results from the generative AI model, and the recommended learning content is displayed on the device screen.

[1653] Progress tracking and feedback

[1654] As the student progresses through their studies, the device tracks their progress and sends it to the server. The server then periodically generates feedback based on the student's progress and sends it to the device. The feedback provides the student with information to check their progress and make course corrections as necessary.

[1655] 3. Hardware and software used

[1656] Hardware: Smartphones, tablets, PCs, cloud or on-premise servers

[1657] Software: Web browser, generative AI model (OpenAI GPT-3)

[1658] 4. Specific Examples

[1659] Example of student's goals and mock test results

[1660] A student sets the goal of "passing the entrance exam for the University of Tokyo" and enters the results of the mock exam as follows:

[1661] Student's goal: Passing the entrance exam to the University of Tokyo

[1662] Mock test results: {"Math": 70, "English": 85, "Physics": 60, "Chemistry": 75}

[1663] Examples of identifying areas of weakness and strength

[1664] The generative AI model identifies the individual as "bad at physics, good at English."

[1665] Examples of recommended learning content

[1666] The generative AI model recommends learning content as follows:

[1667] Weakness: Physics

[1668] Specialty: English

[1669] Recommend the best learning content.

[1670] In this way, test takers can create individually optimized study plans and progress with their studies efficiently.

[1671] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[1672] Step 1:

[1673] The user uses the terminal to input the goal and the results of the mock test.

[1674] The input interface is a form that runs on a web browser, where the user inputs their goal (e.g., "Pass the entrance exam for Tokyo University") and mock exam results (e.g., "Math: 70, English: 85, Physics: 60, Chemistry: 75") The input data is sent to the server in JSON format.

[1675] Step 2:

[1676] The server sends the received data to the generative AI model.

[1677] The server generates and sends prompts to a generative AI model (e.g., OpenAI GPT-3) to analyze the user's submitted goals and practice test results. An example of a prompt is shown below.

[1678] Student's goal: Passing the entrance exam to the University of Tokyo

[1679] Mock test results: {"Math": 70, "English": 85, "Physics": 60, "Chemistry": 75}

[1680] Identify your areas of weakness and strength.

[1681] The generative AI model analyzes this prompt and identifies areas of strength and weakness.

[1682] Step 3:

[1683] The generative AI model returns the analysis results to the server.

[1684] The generative AI model returns analysis results such as "I'm not good at physics, but I'm good at English" to the server. The server receives this information and proceeds to the next step.

[1685] Step 4:

[1686] The server recommends the most suitable learning content based on the analysis results.

[1687] Based on the analysis results from the generative AI model, the server generates a prompt to recommend the most suitable learning content to the user and sends it back to the generative AI model. An example of a prompt is as follows:

[1688] Weakness: Physics

[1689] Specialty: English

[1690] Recommend the best learning content.

[1691] The generative AI model generates optimal learning content based on this prompt and returns it to the server.

[1692] Step 5:

[1693] The server transmits the recommended learning content to the terminal.

[1694] The server receives the learning content returned by the generative AI model and sends it to the user's device, which receives this information and visually displays it to the user.

[1695] Step 6:

[1696] As the user progresses through their studies, the device tracks their progress and sends it to the server.

[1697] As the user progresses with their studies, the device continuously monitors their progress and periodically sends the data to the server, including study time, study content, progress status, and other information.

[1698] Step 7:

[1699] The server generates feedback based on the learning progress and sends it to the device.

[1700] The server analyzes the user's learning progress data and generates feedback as needed. The generated feedback includes information for checking the user's learning progress and making necessary course corrections. The server sends this feedback to the terminal, which then visually displays it to the user.

[1701] In this way, test takers can create individually optimized study plans and progress with their studies efficiently.

[1702] Example 2

[1703] Next, a description will be given of Example 2 of Form 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."

[1704] Conventional learning support systems have difficulty automatically generating and displaying optimal learning plans that match each student's individual learning situation and goals. Furthermore, they lacked the functionality to flexibly modify schedules according to the student's learning progress, making it difficult for students to study efficiently. Furthermore, there were also insufficient means to visually display the generated learning plans in an easy-to-understand manner.

[1705] 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.

[1706] In this invention, the server includes a means for inputting the examinee's goals and mock test results, a means for analyzing the examinee's strengths and weaknesses, a means for displaying the optimal study content, method, and schedule leading up to the exam, a means for inputting the study progress on a daily basis and correcting the course as needed, a means for inputting prompts into the generative AI model to generate the optimal study content, method, and schedule, a means for converting the generated schedule into a calendar format, and a means for displaying the calendar-format schedule. This makes it possible to automatically generate an optimal study plan tailored to the examinee's individual learning situation and display it in a visually easy-to-understand manner. Furthermore, the schedule can be flexibly modified according to the examinee's learning progress, allowing the examinee to study efficiently.

[1707] "Exam takers' goals" refer to the learning objectives and goals that exam takers want to achieve.

[1708] "Mock test results" refers to the grades or scores that a candidate obtained in a mock test.

[1709] "Weak areas" refer to areas of study that test-takers find particularly difficult to understand or master.

[1710] "Areas of strength" refers to areas of study that the candidate finds particularly easy to understand and master.

[1711] "Optimal learning content" refers to the learning items that are judged to be most effective in helping test takers achieve their goals.

[1712] "Optimal study methods" refer to specific study methods and approaches that maximize a test-taker's learning efficiency.

[1713] An "optimal schedule" refers to a timetable or dates planned to allow test takers to study efficiently.

[1714] A "generative AI model" refers to an algorithm or system that uses artificial intelligence technology to analyze data and generate an optimal learning plan.

[1715] A "prompt" refers to an instruction or question input to a generative AI model.

[1716] "Calendar format" refers to a format that visually displays learning content and schedules by date.

[1717] "Study implementation status" refers to the progress and results of the learning activities actually undertaken by the examinee.

[1718] "Correcting course" refers to adjusting plans and schedules according to the progress of learning.

[1719] The present invention is a system for automatically generating an optimal study plan according to the individual learning situation of each examinee and displaying the plan in a visually easy-to-understand manner. A specific embodiment of this system will be described below.

[1720] First, the user logs in to the system. The user enters their username and password on the system login screen and clicks the "Login" button. If the login is successful, the user's dashboard will be displayed.

[1721] Next, the user enters their learning goals (e.g., to improve their math grades) and their current academic level (e.g., their mock test scores) on the dashboard, and this information is sent to the server.

[1722] The server collects the user's past learning history data from the database. This includes the percentage of correct answers to questions previously solved and the results of mock exams. For example, it retrieves the data using an SQL query such as "SELECT FROM learning history WHERE user ID = '12345'".

[1723] Next, the server inputs a prompt into the generative AI model based on the collected data. The prompt includes the user's learning goals, academic level, and learning history data. An example of a specific prompt is, "This student wants to improve their math grades. Their past academic performance data is as follows. Please generate the optimal study content, method, and schedule in calendar format."

[1724] The generative AI model analyzes the prompt and generates the optimal learning content, method, and schedule for the user, creating a specific study plan such as "Spend two hours on math problems on Monday" or "Spend one hour on English listening on Tuesday."

[1725] The server converts the learned schedule obtained from the generative AI model into a calendar format using a JavaScript library to convert the schedule into a format that can be displayed visually.

[1726] Finally, the device displays a calendar-style schedule to the user. Users can check the study content and time for each day on the device screen and plan their studies accordingly. For example, they can check the schedule through an app on their smartphone or tablet.

[1727] This system automatically generates optimal study plans tailored to each student's individual learning situation, allowing them to visually confirm the plans. It also allows students to flexibly adjust their schedules according to their learning progress, enabling them to study efficiently.

[1728] The flow of the identification process in the second embodiment will be described with reference to FIG.

[1729] Step 1:

[1730] A user logs in to the system.

[1731] The user enters their username and password on the system's login screen and clicks the "Login" button. The entered username and password are sent to the server, which then checks the database for authentication. If authentication is successful, the user's dashboard is displayed.

[1732] Input: Username, Password

[1733] Output: User's dashboard screen

[1734] Step 2:

[1735] The user inputs their learning goals and current academic level.

[1736] The user enters their learning goal (e.g., "I want to improve my math grades") and their current academic level (e.g., their mock test score) into the form on the dashboard and clicks the "Submit" button. This information is sent to the server.

[1737] Input: Learning goals, current academic level

[1738] Output: Learning objectives and academic level sent to the server

[1739] Step 3:

[1740] The server collects the user's learning history data.

[1741] The server queries and collects the user's past learning history data from the database, including the percentage of correct answers to questions previously answered and the results of practice tests. For example, it retrieves the data using an SQL query such as "SELECT FROM learning history WHERE user ID = '12345'".

[1742] Input: User ID

[1743] Output: User learning history data

[1744] Step 4:

[1745] The server inputs a prompt sentence into the generative AI model.

[1746] The server inputs prompts into the generative AI model based on the collected data. The prompts include the user's learning goals, academic level, and learning history data. An example of a specific prompt is, "This student wants to improve their math grades. Their past academic performance data is as follows. Please generate the optimal study content, methods, and schedule in a calendar format."

[1747] Input: Learning goals, academic level, learning history data

[1748] Output: Prompt sentence to the generative AI model

[1749] Step 5:

[1750] A generative AI model generates optimal learning content, methods, and schedules.

[1751] The generative AI model analyzes the prompt and generates the optimal learning content, method, and schedule for the user, creating a specific study plan such as "Spend two hours on math problems on Monday" or "Spend one hour on English listening on Tuesday."

[1752] Input: prompt statement

[1753] Output: Optimal learning content, methods, and schedule

[1754] Step 6:

[1755] The server converts the generated schedule into a calendar format.

[1756] The server converts the learned schedule obtained from the generative AI model into a calendar format using a JavaScript library to convert the schedule into a format that can be displayed visually.

[1757] Input: Optimal learning content, methods, and schedule

[1758] Output: Calendar format schedule

[1759] Step 7:

[1760] The terminal displays the schedule to the user.

[1761] The device displays a calendar-style schedule to the user. Users can check the study content and time for each day on the device screen and plan their studies accordingly. For example, they can check their schedule through an app on their smartphone or tablet.

[1762] Input: Calendar-style schedule

[1763] Output: The schedule as seen by the user

[1764] (Application example 2)

[1765] Next, a description will be given of Application Example 2 of Form 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."

[1766] With conventional exam preparation support systems, it was difficult to generate an optimal study schedule based on the student's goals and mock test results, and the course corrections based on the student's study progress had to be done manually, making it difficult to study efficiently.Furthermore, the generated schedule was not displayed in a visually easy-to-understand manner, making it difficult for the student to understand the plan.

[1767] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 2 is realized by the following means.

[1768] In this invention, the server includes a means for inputting the examinee's goals and mock test results, a means for analyzing the examinee's strengths and weaknesses, a means for displaying the optimal study content, method, and schedule leading up to the exam, a means for inputting the study progress status every day and correcting the course as needed, a means for generating an optimal study schedule using a generative AI model, and a means for displaying the generated schedule in calendar format. This allows the examinee to efficiently and effectively create a study plan and make appropriate course corrections according to their progress.

[1769] "Exam takers' goals" refers to the specific learning goals and schools that exam takers want to achieve.

[1770] "Mock test results" refers to evaluation data such as mock test scores, marks, and deviation values.

[1771] "Weak areas" refer to areas of study or subjects that test-takers find particularly difficult to understand or master.

[1772] "Areas of strength" refers to areas of study or subjects that are particularly easy for a candidate to understand and master, and in which they achieve high grades.

[1773] "Optimal study content" refers to the learning content that is most effective for helping test-takers achieve their goals.

[1774] "Method" refers to the specific means or approach to studying.

[1775] A "schedule" refers to a plan that arranges study content and methods in terms of time.

[1776] A "generative AI model" refers to an algorithm or system that uses artificial intelligence technology to generate data and calculate the optimal study schedule.

[1777] "Calendar format" refers to a format that visually displays study content and schedules by date.

[1778] "Correcting your course" means adjusting your plan according to your study progress and keeping it in optimal condition.

[1779] A system for implementing this invention includes a means for inputting the test-taker's goals and mock test results, a means for analyzing the test-taker's strengths and weaknesses, a means for displaying the optimal study content, method, and schedule leading up to the test, a means for inputting the study progress status every day and correcting the course as needed, a means for generating an optimal study schedule using a generative AI model, and a means for displaying the generated schedule in calendar format.

[1780] Program processing explanation

[1781] The server provides an interface for students to input their goals and mock test results. Students input their goals and mock test results using devices such as smartphones or PCs. This data is sent to the server and stored in a database.

[1782] Next, the server uses a generative AI model to analyze the student's strengths and weaknesses. The generative AI model generates an optimal study schedule based on the input data. It also uses OpenAI's API to generate prompts and input them into the AI ​​model.

[1783] The generated study schedule is displayed in calendar format. Students can check the study content and method for each date on their smartphone or computer screen. For example, use the following prompts:

[1784] Example prompt sentence:

[1785] Generate an optimal study schedule for the following subjects for students taking the exam on 2023-12-01: Mathematics, English, Physics

[1786] Furthermore, students can input their daily study progress. Based on this data, the server uses the generative AI model again to correct the schedule, allowing students to maintain an optimal study plan at all times.

[1787] Specific examples

[1788] For example, if a student needs to study three subjects: mathematics, English, and physics, the server generates the following schedule:

[1789] 2023-11-01: Mathematics - Calculus

[1790] 2023-11-02: English - Grammar

[1791] 2023-11-03: Physics - Mechanics

[1792] ...

[1793] This schedule is displayed in a calendar format, allowing students to easily check their daily study content. Furthermore, the schedule is automatically updated according to their study progress, enabling efficient study.

[1794] The hardware used is a smartphone or a PC, allowing test-takers to plan their studies efficiently and effectively, and to make appropriate course corrections as they progress.

[1795] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[1796] Step 1:

[1797] Users use devices such as smartphones or PCs to input their test-taking goals and mock test results. The input data is sent to a server and stored in a database. The input data includes the test-taker's preferred school, target score, mock test results, etc.

[1798] Step 2:

[1799] The server uses a generative AI model to analyze the student's strengths and weaknesses based on their goals and mock test results. Specifically, it analyzes the input grade data and calculates the score distribution and deviation value for each subject. This allows it to identify areas where the student needs to particularly improve and areas where they are already strong.

[1800] Step 3:

[1801] The server uses a generative AI model to generate an optimal study schedule based on the student's strengths and weaknesses. It generates prompts and inputs them into the AI ​​model to calculate the study content and methods for each subject. For example, the following prompts can be used:

[1802] Generate an optimal study schedule for the following subjects for students taking the exam on 2023-12-01: Mathematics, English, Physics

[1803] The generated schedule will specify the study content and time for each day.

[1804] Step 4:

[1805] The server displays the generated study schedule in calendar format. Users can check the study content and method for each date on their smartphone or computer screen. The calendar format makes it visually easy to understand and makes it easy to plan.

[1806] Step 5:

[1807] Users enter their daily study progress on their device. The entered data is sent to the server and stored in a database. By recording their study progress and what they have done, they can check the degree to which they have achieved their plan.

[1808] Step 6:

[1809] The server then uses the generative AI model again to correct the schedule based on the user's study progress input. Specifically, it analyzes progress and adjusts study content and methods as necessary. This allows test-takers to maintain an optimal study plan at all times.

[1810] Step 7:

[1811] The server then displays the revised schedule in calendar format, allowing the user to check the updated schedule and plan their next study. This allows for efficient and effective study.

[1812] Example 3

[1813] Next, a third embodiment of the third embodiment will be described. 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."

[1814] Conventional learning management systems have difficulty automatically generating optimal study schedules based on students' learning status and correcting their course in real time. Furthermore, there was a lack of a way to efficiently manage the generated schedules and provide them to users, which meant that the effectiveness of learning could not be maximized.

[1815] The specific processing by the specific processing unit 290 of the data processing device 12 in the third embodiment is realized by the following means.

[1816] In this invention, the server includes means for inputting the examinee's goals and mock test results, means for analyzing the examinee's strengths and weaknesses, means for displaying the optimal study content, method, and schedule leading up to the exam, means for inputting the study progress status every day and correcting the course as needed, means for sending prompts to the generative AI model to generate an optimal study schedule, and means for saving the generated study schedule in a database and sending it to the user's terminal. This makes it possible to generate an optimal study schedule in real time based on the examinee's study status and efficiently manage and provide it.

[1817] "Exam takers' goals" refer to the learning objectives and goals that exam takers want to achieve.

[1818] "Mock test results" refers to the grades and evaluations that test takers receive in mock tests.

[1819] "Weak areas" refer to subjects or topics that test-takers find particularly difficult to understand or master.

[1820] "Areas of strength" refers to subjects or topics that a candidate finds particularly easy to understand and master.

[1821] "Study content" refers to the specific subjects and topics that test takers will study.

[1822] "Study methods" refer to the specific techniques and approaches that test takers use to advance their studies.

[1823] A "study schedule" refers to the timetable and dates planned for a test-taker to study.

[1824] "Study implementation status" refers to the content and amount of study that the test taker actually undertook.

[1825] "Correcting the course" refers to reviewing and optimizing a student's study plan.

[1826] A "generative AI model" refers to a model that uses artificial intelligence to analyze data and generate an optimal learning schedule.

[1827] A "prompt" refers to an instruction or question input to a generative AI model.

[1828] "Database" refers to an information management system for storing test takers' learning data and generated learning schedules.

[1829] "User's device" refers to electronic devices such as smartphones and tablets used by test takers.

[1830] This invention is a system for managing the learning status of test takers and providing them with an optimal study schedule. The system includes means for inputting the test taker's goals and mock test results, means for analyzing their strengths and weaknesses, means for displaying the optimal study content, method, and schedule leading up to the test, means for inputting the study progress status every day and correcting the course as needed, means for sending prompts to a generative AI model to generate an optimal study schedule, and means for saving the generated study schedule in a database and sending it to the user's terminal.

[1831] Users use a dedicated application to input their study status from devices such as smartphones or tablets. The input data includes specific study time and content. For example, information such as "October 1st: 2 hours of math, 1 hour of English" may be entered.

[1832] The device sends the entered data to the server. This transmission is secure using the HTTPS protocol. The server stores the received data in a MySQL database. The stored data is used to record the student's learning progress in detail.

[1833] The server sends a prompt to the generative AI model based on the saved data. The prompt includes past learning history. For example, the server might send the following to the generative AI model: "Test-taker A's study time and content over the past week are as follows. Based on this, please suggest the optimal study schedule for the next week."

[1834] The generative AI model generates an optimal study schedule based on the prompt. For example, it might generate a schedule such as "October 4th: 1.5 hours of math, 1.5 hours of English." The generated schedule is returned to the server.

[1835] The server saves the generated schedule in a database and sends it to the user's device. The user can check the new study schedule through the device application. For example, a schedule such as "October 4th: 1.5 hours of math, 1.5 hours of English" may be displayed.

[1836] This system allows test-takers to receive an optimal study schedule in real time, enabling them to study efficiently. Furthermore, by using a generative AI model, it is possible to provide a customized schedule according to each individual's learning situation. The flow of the specific processing in Example 3 will be explained using FIG. 15.

[1837] Step 1:

[1838] The user inputs their study status.

[1839] The user opens a dedicated application and inputs the study time and content. For example, they input specific information such as "October 1st: 2 hours of math, 1 hour of English." The input data is temporarily stored in the device's memory.

[1840] Step 2:

[1841] The terminal sends the input data to the server.

[1842] The terminal sends the data entered by the user to the server. The input data is sent in the format of "October 1st: 2 hours of math, 1 hour of English." The server analyzes the received data and prepares it to be saved in the database.

[1843] Step 3:

[1844] The server stores the data in a database.

[1845] The server parses the received JSON data and inserts it into the "Study Record" table in the MySQL database. For example, data such as "October 1st: 2 hours of math, 1 hour of English" is saved in the database. This records the user's study status.

[1846] Step 4:

[1847] The server sends a prompt to the generative AI model.

[1848] The server sends a prompt to the generative AI model based on the stored data. The prompt includes past learning history. For example, the following sentence is sent to the generative AI model: "Test-taker A's study time and content for the past week are as follows. Based on this, please suggest the optimal study schedule for the next week." The input data is the study record for the past week, and the output is the prompt sent to the generative AI model.

[1849] Step 5:

[1850] A generative AI model generates an optimal learning schedule.

[1851] The generative AI model receives prompts and generates an optimal learning schedule. For example, it generates a schedule such as "October 4th: 1.5 hours of math, 1.5 hours of English." The input data is the prompts, and the output is the generated learning schedule.

[1852] Step 6:

[1853] The server stores the generated schedule in a database.

[1854] The server inserts the schedule received from the generative AI model into the "Study Schedule" table in the database. For example, data such as "October 4th: 1.5 hours of math, 1.5 hours of English" is saved. This records the generated schedule.

[1855] Step 7:

[1856] The server transmits the schedule to the user's terminal.

[1857] The server transmits the stored schedule to the user's terminal. The input data is the generated schedule, and the output is the data transmitted to the user's terminal.

[1858] Step 8:

[1859] The user checks the schedule.

[1860] The user opens the app's "Schedule" screen and checks the new study schedule. For example, a schedule like "October 4th: 1.5 hours of math, 1.5 hours of English" is displayed. This allows the user to confirm and implement the optimal study plan.

[1861] (Application example 3)

[1862] Next, a description will be given of Application Example 3 of Form Example 3. 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."

[1863] Conventional study management systems for test takers provide study schedules based on test takers' goals and mock test results, but do not ade...

Claims

1. A means for inputting the examinee's goals and the results of mock exams for each field; A means for analyzing areas of strength and weakness based on the inputted results of the mock test; a means for displaying a study plan in a calendar format, the study plan being created by inputting a prompt sentence including the input goal of the examinee, the result of the mock test, and an instruction to generate study content, method, and schedule into a generative AI model; means for detecting the emotional state of the examinee by analyzing facial expression or voice data of the examinee using an emotion engine; A means for correcting the course of the study plan each time by inputting the daily study status of the examinee into the generative AI model; When the emotion engine detects that the examinee's emotions are getting worse, information about the worsening emotions is fed back to the generative AI model, thereby adjusting the schedule so that the examinee's study time in weak areas is reduced and the study time in strong areas is increased; A system including:

2. and a means for suggesting to the examinee to buy a product that will help them relax when it is determined that the examinee is feeling stressed based on the input learning status of the examinee and the detected emotional state of the examinee. The system of claim 1 .

Images