system

Abstract

We provide the system. [Solution] A means of receiving test results, evaluations, and learning history from users, A means for preprocessing the received data, A means for identifying a user's strong and weak subjects based on pre-processed data, A method for proposing exam preparation based on identified strengths and weaknesses, A method for recommending schools based on strengths and weaknesses in subjects, A means of displaying proposed exam preparation strategies and educational options to the user, A system that includes this.

Description

Technical Field

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

Background Art

[0002] Patent Document 1 discloses a method for controlling a persona chatbot, which is performed by at least one processor, and includes steps of receiving a user utterance, adding the user utterance to a prompt including an instruction sentence related to an explanation of a character of the chatbot, encoding the prompt, and inputting the encoded prompt into a language model to generate a chatbot utterance in response to the user utterance.

Prior Art Documents

Patent Documents

[0003]

Patent Document 1

Summary of the Invention

Problems to be Solved by the Invention

[0004] In conventional learning support systems, it has been difficult to accurately identify a user's strong and weak subjects and to provide appropriate exam countermeasures and suggestions for further education based on them. In addition, when a user determines exam countermeasures and further education by themselves, sufficient information and analysis cannot be obtained, and it has been difficult to make an efficient learning plan. Therefore, there is a need for a system that automatically provides exam countermeasures and recommendations for further education according to the characteristics of individual users and provides effective learning support.

Means for Solving the Problems

[0006] A "user" refers to an individual who uses this system to input their test results, evaluations, and learning history, and receives learning support and suggestions for further education.

[0007] "Test results" refers to the scores or grades a user has obtained in tests they have taken in the past.

[0008] "Evaluation" refers to grades and feedback information given based on the user's learning progress and test results.

[0009] "Learning history" refers to a record of the user's past learning activities and study time.

[0010] "Preprocessing" refers to processes such as interpolation, normalization, and cleansing performed to prepare collected data for analysis.

[0011] "Favorite subjects" refer to subjects in which the user has achieved particularly high scores or evaluations.

[0012] "Subjects that the user struggles with" refers to subjects in which the user receives low scores or evaluations.

[0013] "Exam preparation" refers to plans and materials that help users effectively study for exams.

[0014] "Place of study" refers to the educational institution or faculty that the user aims to attend in the future.

[0015] A "machine learning algorithm" refers to a mathematical model or method used to learn patterns and rules from data and perform predictions and classifications.

[0016] "Feedback data" refers to the analysis results provided to the user, including the identification of strong and weak subjects, suggestions for exam preparation, and recommendations for higher education institutions.

[0017] A "terminal" refers to a computer device used by users to input data or receive feedback from a server.

[0018] A "server" refers to a central processing unit that collects, preprocesses, analyzes, and generates feedback from user data. [Brief explanation of the drawing]

[0019] [Figure 1] This is a conceptual diagram showing an example of the configuration of a data processing system according to the first embodiment. [Figure 2] This is a conceptual diagram showing an example of the essential functions of a data processing device and a smart device according to the first embodiment. [Figure 3] This is a conceptual diagram showing an example of the configuration of a data processing system according to the second embodiment. [Figure 4] This is a conceptual diagram showing an example of the main functions of a data processing device and smart glasses according to the second embodiment. [Figure 5] This is a conceptual diagram showing an example of the configuration of a data processing system according to the third embodiment. [Figure 6] This is a conceptual diagram showing an example of the main functions of a data processing device and a headset-type terminal according to the third embodiment. [Figure 7] This is a conceptual diagram showing an example of the configuration of a data processing system according to the fourth embodiment. [Figure 8]It is a conceptual diagram showing an example of the main functions of a data processing device and a robot according to the fourth embodiment. [Figure 9] It shows an emotion map to which a plurality of emotions are mapped. [Figure 10] It shows an emotion map to which a plurality of emotions are mapped. [Figure 11] It is a sequence diagram showing the processing flow of the data processing system in Example 1. [Figure 12] It is a sequence diagram showing the processing flow of the data processing system in Application Example 1. [Figure 13] It is a sequence diagram showing the processing flow of the data processing system in Example 2 when an emotion engine is combined. [Figure 14] It is a sequence diagram showing the processing flow of the data processing system in Application Example 2 when an emotion engine is combined.

Embodiments for Carrying Out the Invention

[0020] Hereinafter, an example of an embodiment of a system according to the technology of the present disclosure will be described with reference to the accompanying drawings.

[0021] First, the terminology used in the following description will be explained.

[0022] In the following embodiments, a processor with a reference numeral (hereinafter simply referred to as "processor") may be a single arithmetic unit or a combination of a plurality of arithmetic units. Also, the processor may be a single type of arithmetic unit or a combination of a plurality of types of arithmetic units. Examples of arithmetic units include a CPU (Central Processing Unit), a GPU (Graphics Processing Unit), a GPGPU (General-Purpose computing on Graphics Processing Units), an APU (Accelerated Processing Unit), and the like.

[0023] In the following embodiments, signed RAM (Random Access Memory) is a memory that temporarily stores information and is used as work memory by the processor.

[0024] In the following embodiments, the signed storage is one or more non-volatile storage devices that store various programs and various parameters. Examples of non-volatile storage devices include flash memory (SSD (Solid State Drive)), magnetic disks (e.g., hard disks), or magnetic tapes.

[0025] In the following embodiments, the signed communication interface (I / F) is an interface that includes a communication processor and an antenna, etc. The communication interface manages communication between multiple computers. Examples of communication standards applicable to the communication interface include wireless communication standards such as 5G (5th Generation Mobile Communication System), Wi-Fi (registered trademark), or Bluetooth (registered trademark).

[0026] In the following embodiments, "A and / or B" is synonymous with "at least one of A and B." That is, "A and / or B" means that it may be A alone, or B alone, or a combination of A and B. Furthermore, in this specification, the same concept as "A and / or B" applies when expressing three or more things linked by "and / or."

[0027] [First Embodiment]

[0028] Figure 1 shows an example of the configuration of the data processing system 10 according to the first embodiment.

[0029] As shown in Figure 1, the data processing system 10 includes a data processing device 12 and a smart device 14. An example of the data processing device 12 is a server.

[0030] The data processing device 12 comprises a computer 22, a database 24, and a communication interface 26. The computer 22 is an example of a "computer" related to the technology of this disclosure. The computer 22 comprises a processor 28, RAM 30, and storage 32. The processor 28, RAM 30, and storage 32 are connected to a bus 34. The database 24 and the communication interface 26 are also connected to the bus 34. The communication interface 26 is connected to a network 54. An example of the network 54 is a WAN (Wide Area Network) and / or a LAN (Local Area Network).

[0031] The smart device 14 comprises a computer 36, a reception device 38, an output device 40, a camera 42, and a communication interface 44. The computer 36 comprises a processor 46, RAM 48, and storage 50. The processor 46, RAM 48, and storage 50 are connected to a bus 52. The reception device 38, output device 40, and camera 42 are also connected to the bus 52.

[0032] The reception device 38 is equipped with a touch panel 38A and a microphone 38B, etc., and receives user input. The touch panel 38A receives user input by detecting contact with an object (e.g., a pen or finger). The microphone 38B receives user input by detecting the user's voice. The control unit 46A transmits data indicating the user input received by the touch panel 38A and microphone 38B to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the data indicating the user input.

[0033] The output device 40 includes a display 40A and a speaker 40B, and presents data to the user 20 by outputting the data in a form perceptible to the user 20 (e.g., audio and / or text). The display 40A displays visible information such as text and images according to instructions from the processor 46. The speaker 40B outputs audio according to instructions from the processor 46. The camera 42 is a small digital camera equipped with an optical system such as a lens, aperture, and shutter, and an image sensor such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor.

[0034] Communication interface 44 is connected to network 54. Communication interfaces 44 and 26 are responsible for the exchange of various types of information between processor 46 and processor 28 via network 54.

[0035] Figure 2 shows an example of the main functions of the data processing device 12 and the smart device 14.

[0036] As shown in Figure 2, in the data processing device 12, a specific processing is performed by the processor 28. A specific processing program 56 is stored in the storage 32. The specific processing program 56 is an example of a "program" related to the technology of this disclosure. The processor 28 reads the specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific processing is realized by the processor 28 operating as a specific processing unit 290 according to the specific processing program 56 executed on the RAM 30.

[0037] The storage 32 stores the data generation model 58 and the emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290.

[0038] In the smart device 14, the processor 46 performs the reception output processing. The storage 50 stores the reception output program 60. The reception output program 60 is used in conjunction with a specific processing program 56 by the data processing system 10. The processor 46 reads the reception output program 60 from the storage 50 and executes the read reception output program 60 on the RAM 48. The reception output processing is realized by the processor 46 operating as a control unit 46A according to the reception output program 60 executed on the RAM 48.

[0039] Next, the specific processing performed by the specific processing unit 290 of the data processing device 12 will be described. In the following description, the data processing device 12 will be referred to as the "server" and the smart device 14 as the "terminal".

[0040] The system of this invention analyzes a user's strengths and weaknesses in different subjects and provides exam preparation strategies and recommendations for higher education based on that analysis. This system mainly consists of a terminal where the user inputs data, a server that processes and analyzes the data, and a terminal that receives feedback from the server.

[0041] System Overview

[0042] User: Data entry

[0043] Users input test results, evaluations, and learning history into the system via their devices. For example, they might input specific data such as, "I got 90 points on last year's math exam," or "My English grade was a B."

[0044] Terminal: Data transmission

[0045] The terminal sends the entered data to the server. When sending the data, it is important to send it in an appropriate format (such as JSON or XML) so that the server can receive the data accurately.

[0046] Server: Data collection and preprocessing

[0047] The server collects data sent from the terminal and stores it in a temporary data store. Then, it performs preprocessing on the collected data. Specifically, it imputes missing values ​​with the mean or median, and normalizes data from different scales to unify them.

[0048] Server: Identifying strong and weak subjects

[0049] Based on the pre-processed data, the server identifies the user's strong and weak subjects. Here, machine learning algorithms (e.g., random forest or support vector machine) are used to analyze the scoring patterns for each subject. Subjects with high scores are identified as "strong subjects," and subjects with low scores are identified as "weak subjects."

[0050] Server: Suggestions for exam preparation

[0051] The server suggests exam preparation strategies based on identified strengths and weaknesses. For example, it recommends video tutorials and additional practice problems for weak subjects, and provides application problems and mock exams for strong subjects. Specifically, this might include suggestions like "watch a 30-minute English video tutorial every day" or "solve application problems in mathematics on the weekend."

[0052] Server: Recommended by the school you will be attending

[0053] The server matches the user's strengths in subjects with information on potential universities. Considering the user's strengths and interests, it selects the most suitable university from the database. For example, it might suggest a university like "A science and engineering university's information science department would be suitable because you excel in mathematics."

[0054] Server: Generating feedback data

[0055] The server generates feedback data based on previous analysis results, suggested exam preparation strategies, and recommended educational institutions. This feedback data is then provided to the user.

[0056] Device: Displaying feedback to the user

[0057] The device displays feedback data received from the server to the user. The displayed feedback includes specific details such as, "Your weakest subject is English. Watch English video tutorials for 30 minutes every day. Also, a computer science department at a science and engineering university would be a good fit for you."

[0058] User: Creating a study plan

[0059] Users create their own study plans based on feedback displayed on their devices. They can set specific study schedules and goals based on recommended test preparation and information about potential schools.

[0060] Specific example

[0061] 1. User input example

[0062] Test results: Math 90 points, English 70 points, Science 85 points

[0063] Grades: Math A, English B, Science A

[0064] Learning history: Data from the past year

[0065] 2. Example of server processing

[0066] Data collection: Collect user test results, evaluations, and learning history.

[0067] Data preprocessing: Imputation of missing values, normalization of statistical data.

[0068] Identifying my strong and weak subjects: My strong subject is "Mathematics," and my weak subject is "English."

[0069] Suggestions for exam preparation: "Watch English video tutorials for 30 minutes every day" and "Solve applied math problems every weekend."

[0070] Recommended university: "Information science department at a science and engineering university"

[0071] 3. Example of terminal output

[0072] We recommend that users "watch English video tutorials for 30 minutes every day" and "solve applied math problems every weekend."

[0073] Provide users with information on admissions to the "Information Science Department of a science and engineering university."

[0074] This allows users to prepare for exams best suited to their individual strengths and choose the appropriate educational institution. In this way, users can create more effective study plans and gain an advantage in future educational and career choices.

[0075] The following describes the processing flow.

[0076] Step 1:

[0077] Users use their devices to input their test results, grades, and learning history. For example, they might input specific data such as "I scored 90 points on last year's math exam," "My English grade was a B," and "I studied math for 3 hours a week."

[0078] Step 2:

[0079] The terminal sends data entered by the user to the server. This input data is often sent in formats such as JSON or XML.

[0080] Step 3:

[0081] The server receives data sent from the terminal and stores it in a temporary database. Here, it checks the data's integrity and sends an error message to the terminal if any inconsistencies are found.

[0082] Step 4:

[0083] The server preprocesses the collected data. Specifically, it performs data imputation (such as imputing with the mean or median) and data normalization (unifying different scales).

[0084] Step 5:

[0085] Based on pre-processed data, the server uses machine learning algorithms to identify the user's strong and weak subjects. For example, it might use a random forest or support vector machine to analyze the user's scoring patterns, identifying subjects with high scores as "strong subjects" and subjects with low scores as "weak subjects."

[0086] Step 6:

[0087] Based on the user's identified strengths and weaknesses in different subjects, the server suggests exam preparation strategies. For example, it might generate specific strategies such as "Watch English video tutorials for 30 minutes every day" or "Solve applied math problems every weekend."

[0088] Step 7:

[0089] The server matches the user's strengths in subjects with information on potential universities and selects the most suitable university from the database. For example, it might identify a university with a strong focus on science and engineering, such as "a science and engineering university's information science department, as the user excels in mathematics."

[0090] Step 8:

[0091] The server generates feedback data based on previous analysis results, suggested exam preparation strategies, and recommended educational institutions. This feedback data serves as a reference for users to create concrete study plans.

[0092] Step 9:

[0093] The device displays feedback data received from the server to the user. For example, it might display specific advice such as, "Watch English video tutorials for 30 minutes every day," or "A science and engineering university's information science department would be suitable."

[0094] Step 10:

[0095] Users create a specific study plan based on feedback displayed on their device. They then implement recommended test preparation strategies and progress towards their goals.

[0096] (Example 1)

[0097] Next, we will describe Example 1. In the following description, the data processing device 12 will be referred to as the "server," and the smart device 14 will be referred to as the "terminal."

[0098] Traditional educational support systems struggle to accurately identify each user's individual learning situation, strengths, and weaknesses, and to provide appropriate test preparation and recommendations for higher education based on that information. In particular, insufficient preprocessing, such as imputing missing values ​​or unifying data from different scales, prevents accurate analysis. Furthermore, the suggested test preparation and educational recommendations are often vague and therefore impractical for users.

[0099] The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 1 is realized by the following means.

[0100] In this invention, the server includes means for receiving education-related data (test results, evaluations, learning history) from the user, means for preprocessing the received data, means for normalizing the data and imputing missing values, means for identifying the user's strengths and weaknesses based on the preprocessed data, means for identifying them using machine learning algorithms (e.g., random forest or support vector machine), means for proposing educational support based on the identified strengths and weaknesses, means for recommending educational institutions based on the strengths and weaknesses, and means for displaying the proposed educational support and educational institutions to the user. This enables accurate learning analysis tailored to the user's individual circumstances and specific and effective recommendations for test preparation and further education.

[0101] "Education-related data" refers to the totality of information related to a user's learning, including test results, evaluations, and learning history.

[0102] "Preprocessing" is the process of converting received data into a format that can be properly analyzed. Specifically, this involves tasks such as imputing missing values ​​and normalizing the data.

[0103] "Normalization" is a process for unifying data at different scales, and is a means of making data comparison and analysis easier.

[0104] "Missing value imputation" is the procedure of filling in missing data in a dataset using a specific method (e.g., the mean or median).

[0105] A "machine learning algorithm" is a mathematical model used to analyze patterns in data and make predictions or classifications based on specific objectives.

[0106] "Areas of expertise" refers to learning areas where a user demonstrates particularly high performance.

[0107] A "weakness area" refers to a learning area where a user shows relatively low performance.

[0108] "Educational support" is a general term for the support provided to achieve specific learning objectives, and specifically includes study plans, practice problems, video tutorials, and so on.

[0109] "Educational institutions" refers to all learning facilities and educational programs related to a user's learning or further education.

[0110] "Feedback data" refers to information that includes advice and recommendations generated based on the user's learning progress, strengths, and weaknesses.

[0111] Users input educational data using a terminal. Specifically, they input information such as test results, evaluations, and learning history, and this information is sent to the system. The terminal is equipped with at least a user interface for inputting data and a function to convert that data into an appropriate format (e.g., JSON or XML) and send it.

[0112] Data sent from the terminal is received by the server. This server preprocesses the data by storing it in a temporary data store, and then performs tasks such as imputing missing values ​​and normalizing the data. This process ensures data consistency and enables accurate analysis.

[0113] The pre-processed data is used on the server to identify areas of strength and weakness. Machine learning algorithms such as random forests and support vector machines are applied here. This identifies areas where the user performs well as "strengths" and areas where performance is poor as "weaknesses."

[0114] The server then proposes specific educational support based on these identified strengths and weaknesses. For example, for English, which is a weak area, it might suggest "watching 30 minutes of English video tutorials every day," and for mathematics, which is a strong area, it might suggest "solving applied math problems on weekends."

[0115] Furthermore, the server matches the user's areas of expertise with information about their educational background to recommend the most suitable institution. For example, it might recommend a "Department of Information Science at a science and engineering university" to a user who excels in mathematics. This recommendation information is also provided to the user as part of the feedback.

[0116] These analysis results, suggestions, and recommendations for higher education are generated as feedback data and provided to the user. The device displays this feedback data to the user. The displayed content includes specific instructions such as, "Your weak area is English. Please watch English video tutorials for 30 minutes every day. Also, the information science department of a science and engineering university would be suitable for you."

[0117] Users can use this feedback data to set specific learning plans. For example, they can create action plans such as "watch 30 minutes of English video tutorials every day" or "solve applied math problems on weekends."

[0118] Example of a prompt

[0119] 1. "Based on your learning history over the past year, identify your strengths and weaknesses in different subjects, and then propose exam preparation strategies and college options accordingly."

[0120] 2. "Analyze the test results, evaluations, and learning history entered by the user, and recommend the most suitable test preparation methods and educational institutions."

[0121] This allows users to receive educational support best suited to their circumstances and choose the appropriate educational institution. Users can also develop more effective study plans and be in a more advantageous position when choosing future education or careers.

[0122] The flow of the specific processing in Example 1 will be explained using Figure 11.

[0123] Step 1:

[0124] Users input educational data using their devices. Specifically, they input information such as test results, grades, and learning history. For example, they might input data such as "I got 90 points on last year's math exam" or "My English grade was a B."

[0125] Input: Test results, evaluation, learning history

[0126] Output: Educational data stored in the device's temporary data store.

[0127] Step 2:

[0128] The terminal converts the input data into an appropriate format (e.g., JSON or XML) and sends it to the server. Before sending the data, it verifies that the data is formatted correctly.

[0129] Input: Educational data stored on the device

[0130] Output: Send formatted educational data (in JSON or XML format) to the server.

[0131] Step 3:

[0132] The server stores the data received from the terminal in a temporary data store and begins data preprocessing. First, it imputes any missing values ​​and normalizes the data. This is done using missing value imputation algorithms and normalization algorithms. For example, missing test result values ​​are imputed with the average value for that subject.

[0133] Input: Formatted education-related data

[0134] Output: Preprocessed education-related data (missing values ​​imputed, normalized)

[0135] Step 4:

[0136] The server uses pre-processed data to identify the user's strengths and weaknesses. Machine learning algorithms such as random forests and support vector machines are used here. For example, if a user scores highly in math and low in English, math is identified as a strength and English as a weakness.

[0137] Input: Preprocessed education-related data

[0138] Output: User's strengths and weaknesses

[0139] Step 5:

[0140] Based on the user's strengths and weaknesses, the server proposes specific educational support. For example, it might suggest "watching 30 minutes of English video tutorials daily" to a user who struggles with English, or "solving applied math problems on weekends" to a user who excels at math.

[0141] Input: User's strengths and weaknesses

[0142] Output: Suggestions for educational support tailored to the user.

[0143] Step 6:

[0144] The server matches the user's areas of expertise with educational institution information to recommend the most suitable institution. For example, a user who excels in mathematics would be recommended a "Department of Information Science at a science and engineering university."

[0145] Input: User's areas of expertise and educational institution information

[0146] Output: Recommendations for the most suitable educational institutions for the user.

[0147] Step 7:

[0148] The server compiles the analysis results, exam preparation suggestions, and recommended schools to generate feedback data. This feedback data is provided to the user.

[0149] Input: Areas of expertise and weaknesses, suggestions for educational support, recommendations for educational institutions.

[0150] Output: Feedback data

[0151] Step 8:

[0152] The terminal displays feedback data received from the server to the user. The displayed content includes specific instructions such as, "Your weak point is English. Watch English video tutorials for 30 minutes every day. Also, a computer science department at a science and engineering university would be a good fit for you."

[0153] Input: Feedback data

[0154] Output: Specific feedback displayed to the user

[0155] Step 9:

[0156] Users create their own learning plans based on feedback from their devices. They set specific study schedules and goals based on recommended test preparation and educational institution information. For example, they might create action plans such as "watch 30 minutes of English video tutorials every day" or "solve applied math problems on weekends."

[0157] Input: Feedback data

[0158] Output: Specific learning plan set by the user

[0159] (Application Example 1)

[0160] Next, we will explain Application Example 1. In the following explanation, the data processing device 12 will be referred to as the "server," and the smart device 14 will be referred to as the "terminal."

[0161] In modern education systems, providing appropriate learning support based on each student's strengths and weaknesses is crucial. However, traditional systems have made it difficult to comprehensively identify students' strengths and weaknesses, resulting in an inability to provide effective learning strategies. Furthermore, recommending appropriate educational institutions and suggesting individually optimized educational content has been challenging. This has led to problems such as students being unable to create a suitable learning plan, resulting in decreased learning efficiency and motivation.

[0162] The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 1 is realized by the following means.

[0163] In this invention, the server includes means for recommending appropriate learning content based on the user's strengths and weaknesses; means for receiving test results, evaluations, and learning history from the user; means for pre-processing the received data; means for identifying the user's strengths and weaknesses based on the pre-processed data; means for suggesting test preparation strategies based on the strengths and weaknesses; means for recommending higher education options based on the strengths and weaknesses; means for displaying the suggested test preparation strategies and higher education options to the user; and means for transmitting data from the user's terminal to the server and receiving feedback from the server. This enables the suggestion of educational content optimized for individual students, and allows for effective learning strategies and recommendations for higher education options.

[0164] A "user" is an individual who uses the system to input data such as test results, evaluations, and learning history, and receives learning support and recommendations for further education.

[0165] "Test results" refer to data that shows the scores and grades a user obtained in each subject of the exam.

[0166] "Evaluation" refers to data that indicates a teacher's or educational institution's assessment of a user's learning performance, and is usually represented by letters or numbers.

[0167] "Learning history" refers to data that records a user's past learning activities and performance.

[0168] "Means of receiving data" refers to devices or software that have the function of acquiring data entered by the user and sending it to the server.

[0169] "Preprocessing methods" refer to devices or software used to prepare received data for analysis by imputing missing values ​​and normalizing the data.

[0170] "Means of identification" refers to devices or software that have the function of identifying a user's strong and weak subjects based on pre-processed data.

[0171] "Machine learning algorithm" is a term that refers to an algorithm used by computers to learn from data and recognize patterns.

[0172] "Means of suggesting exam preparation strategies" refers to devices or software that have the function of recommending learning methods and materials suitable for the user based on their identified strengths and weaknesses in different subjects.

[0173] "Means of recommending educational institutions" refers to devices or software that have the function of suggesting the most suitable educational institutions based on the user's strengths and interests.

[0174] "Feedback data" refers to data that includes summaries of information provided to users, such as exam preparation strategies and recommendations for higher education institutions.

[0175] "Means of displaying to the user" refers to devices or software that visually present feedback data received from the server to the user.

[0176] "Means for recommending appropriate learning content" refers to devices or software that suggest optimal educational content based on the user's learning needs and current proficiency level.

[0177] A "terminal" is a device used by a user to input data and communicate with a server, and includes smartphones, tablets, and personal computers.

[0178] This invention is a system that analyzes a user's strengths and weaknesses in different subjects and provides exam preparation strategies and recommendations for higher education based on that analysis. The following describes an embodiment of the system in detail.

[0179] User data entry

[0180] Users input data such as test results, evaluations, and learning history using devices such as smartphones, tablets, or personal computers. This data includes specific information such as, "I scored 90 points on last year's math exam," or "My English grade is a B."

[0181] Data transmission and preprocessing

[0182] The terminal sends the data entered by the user to the server in JSON format or another appropriate format. The server temporarily stores the received data and performs preprocessing such as imputing missing values ​​and normalizing the data. Python libraries such as Pandas and Scikit-learn are used for this process.

[0183] Identifying your strengths and weaknesses in different subjects.

[0184] The server uses machine learning algorithms to identify strong and weak subjects based on pre-processed data. For example, algorithms such as Random Forest and Support Vector Machine (SVM) are used. This allows the system to identify subjects with high scores as "strong subjects" and subjects with low scores as "weak subjects."

[0185] Exam preparation and suggestions for higher education options

[0186] The server suggests appropriate exam preparation based on the user's strengths and weaknesses. For example, it generates specific study plans such as "watch English video tutorials for 30 minutes every day" or "solve applied math problems on weekends." It also matches the user's strengths with information on potential universities to recommend the most suitable institutions. For example, if the user's strength is mathematics, it might suggest "a computer science department at a science and engineering university would be a good fit."

[0187] Displaying feedback

[0188] The feedback data generated by the server is sent to the terminal in real time and displayed to the user. Users can use this feedback to create their study plans. Because the feedback includes specific study strategies and information on potential schools, users can study more effectively.

[0189] Specific examples and prompt statements

[0190] As a concrete example, consider the case where the user's input data was as follows:

[0191] Test results: Math 90 points, English 70 points, Science 85 points

[0192] Grades: Math A, English B, Science A

[0193] Learning history: Data from the past year

[0194] Server processing example:

[0195] Data Collection and Preprocessing: Collect user test results, evaluations, and training history, and perform data imputation and normalization.

[0196] Identifying strengths and weaknesses: Analyzed strengths as "mathematics" and weaknesses as "English".

[0197] Suggestions for exam preparation: "Watch English video tutorials for 30 minutes every day," "Solve applied math problems every weekend," etc.

[0198] Recommended university: We recommend the Faculty of Information Science at a science and engineering university.

[0199] Examples of prompts for a generative AI model:

[0200] "Develop a system that analyzes a user's strengths and weaknesses in specific subjects based on their test results, evaluations, and learning history. Based on these results, it will suggest appropriate learning content and also provide information on potential higher education options. The following is an example of user input."

[0201] Test results: Math 90 points, English 70 points, Science 85 points

[0202] Grades: Math A, English B, Science A

[0203] Learning history: Data from the past year

[0204] Based on this data, please identify the student's strengths and weaknesses in different subjects and provide feedback on specific study plans and potential educational paths.

[0205] As described above, the present invention provides optimal learning support to individual users and constructs a system that enables improved learning efficiency and appropriate choices for further education.

[0206] The flow of a specific process in Application Example 1 will be explained using Figure 12.

[0207] Step 1:

[0208] Users input data such as test results, evaluations, and learning history using a device (smartphone, tablet, or PC). Specifically, they input test results such as 90 points in mathematics, 70 points in English, and 85 points in science, as well as evaluations for each subject (e.g., Mathematics A, English B, Science A).

[0209] Input: Test results, evaluation, learning history

[0210] Output: User data in JSON format

[0211] Step 2:

[0212] The terminal converts the entered user data into JSON format and sends it to the server. It uses an HTTP POST request to send the data to the specified API endpoint.

[0213] Input: User data in JSON format

[0214] Output: Results of sending data to the server

[0215] Step 3:

[0216] The server temporarily stores the received data. Then, it performs preprocessing such as imputing missing values ​​and normalizing the data. Here, data cleaning is performed using Pandas or Scikit-learn.

[0217] Input: User data in JSON format

[0218] Output: Preprocessed data

[0219] Step 4:

[0220] The server applies machine learning algorithms (e.g., Random Forest or SVM) to preprocessed data to identify subjects in which the user excels and struggles. This allows for an analysis of academic performance trends for each subject, thereby identifying strengths and weaknesses.

[0221] Input: Preprocessed data

[0222] Output: Identification of strong and weak subjects

[0223] Step 5:

[0224] Based on the identification of the user's strengths and weaknesses, the server suggests appropriate test preparation strategies. For example, it might suggest watching 30 minutes of video tutorials daily for English, which is a weak subject, and recommend solving application problems on weekends for mathematics, which is a strong subject.

[0225] Input: Results of identifying strong and weak subjects

[0226] Output: Suggestions for exam preparation

[0227] Step 6:

[0228] The server matches the user's preferred subjects and college application information to recommend the most suitable college. For example, if the user's preferred subject is mathematics, the server will suggest a computer science department at a science and engineering university as a college option.

[0229] Input: Database of preferred subjects and universities / schools attended

[0230] Output: Recommended content from prospective schools

[0231] Step 7:

[0232] The server generates feedback data, including exam preparation strategies and recommendations for higher education institutions, and sends it to the terminal in real time. The generated feedback data is packaged in a format that is easy for the user to review.

[0233] Input: Suggestions for exam preparation, recommendations for universities to attend.

[0234] Output: Feedback data

[0235] Step 8:

[0236] The device displays feedback data received from the server to the user. Based on this feedback data, the user can create their own learning plan. Specifically, concrete plans such as "watch English video tutorials for 30 minutes every day" or "solve applied math problems on the weekend" are provided.

[0237] Input: Feedback data

[0238] Output: Displaying feedback to the user

[0239] Furthermore, an emotion engine that estimates the user's emotions may be incorporated. That is, the identification processing unit 290 may use the emotion identification model 59 to estimate the user's emotions and perform identification processing using the user's emotions.

[0240] The system of this invention analyzes a user's strengths and weaknesses in different subjects and provides exam preparation strategies and recommendations for higher education based on that analysis. Furthermore, it incorporates an emotion engine that recognizes the user's emotions to provide more personalized learning support. This system mainly consists of a terminal where the user inputs data, a server that processes and analyzes the data, and a terminal that receives feedback from the server.

[0241] System Overview

[0242] User: Data entry

[0243] Users input test results, evaluations, and learning history into the system via their devices. For example, they might input specific data such as "I scored 90 points on last year's math exam," "My English grade was a B," and "I studied math for 3 hours a week." Users can also input their emotional state.

[0244] Terminal: Data transmission

[0245] The terminal sends the entered data to the server. When sending the data, it is important to send it in an appropriate format (such as JSON or XML) so that the server can receive the data accurately.

[0246] Server: Data collection and preprocessing

[0247] The server receives data sent from the terminal and stores it in a temporary database. It then performs preprocessing on the collected data. Specifically, this includes imputing missing data (such as using the mean or median) and normalizing the data (unifying different scales).

[0248] Server: Identifying strong and weak subjects

[0249] Based on the pre-processed data, the server identifies the user's strong and weak subjects. Here, machine learning algorithms (e.g., random forest or support vector machine) are used to analyze the scoring patterns for each subject. Subjects with high scores are identified as "strong subjects," and subjects with low scores are identified as "weak subjects."

[0250] Server: Emotion recognition by emotion engine

[0251] The server uses an emotion engine to estimate user emotions from input data and learning history. For example, it analyzes stress levels and satisfaction levels during learning, and uses this emotional data to support learning.

[0252] Server: Suggestions for exam preparation

[0253] The server suggests exam preparation strategies based on identified strengths and weaknesses. For example, it provides video tutorials and additional practice problems for weak subjects, and application problems and mock exams for strong subjects. It also suggests learning methods to help users relax if they are experiencing stress.

[0254] Server: Recommended by the school you will be attending

[0255] The server matches the user's strengths in subjects with information on potential universities and selects the most suitable university from the database. For example, it might recommend a science and engineering university's information science department to a user who excels in mathematics and has high emotional stability.

[0256] Server: Generating feedback data

[0257] The server generates feedback data based on previous analysis results, suggested exam preparation strategies, and recommended educational institutions. This feedback data includes advice that takes the user's emotional state into consideration.

[0258] Device: Displaying feedback to the user

[0259] The device displays feedback data received from the server to the user. For example, it may display specific advice such as "Watch English video tutorials for 30 minutes every day" or "A science and engineering university's information science department would be suitable for you." It may also display emotion-based advice such as "Your stress levels have been high recently, so take short breaks to relax."

[0260] User: Creating a study plan

[0261] Users create their own learning plans based on feedback displayed on their devices. They implement recommended test preparation strategies and progress towards their goals. They can leverage emotionally driven advice to create plans that maximize learning effectiveness. They also reassess their emotional state in a timely manner and adjust their learning methods as needed.

[0262] Specific example

[0263] 1. User input example

[0264] Test results: Math 90 points, English 70 points, Science 85 points

[0265] Grades: Math A, English B, Science A

[0266] Learning history: Data from the past year

[0267] Emotional state: High stress levels recently

[0268] 2. Example of server processing

[0269] Data collection: Collect user test results, ratings, learning history, and sentiment status.

[0270] Data preprocessing: Imputation of missing values, normalization of statistical data.

[0271] Identifying my strong and weak subjects: My strong subject is "Mathematics," and my weak subject is "English."

[0272] Suggestions for exam preparation: "Watch English video tutorials for 30 minutes every day" and "Solve applied math problems every weekend."

[0273] Recommended university: "Information science department at a science and engineering university"

[0274] Utilizing the emotional engine: Due to high stress levels, "take short breaks."

[0275] 3. Example of terminal output

[0276] We recommend that users "watch English video tutorials for 30 minutes every day" and "solve applied math problems every weekend."

[0277] Provide users with information on admissions to the "Information Science Department of a science and engineering university."

[0278] We recommend that users take short breaks to relax because their stress levels are high.

[0279] As a result, the user can choose the test countermeasures most suitable for their characteristics and the school to enter in consideration of their emotional situation. In this way, the user can make a more effective study plan and gain an advantageous position in future school entrance and career choices.

[0280] The following describes the process flow.

[0281] Step 1:

[0282] The user uses the terminal to input their test results, evaluations, and learning history. For example, input specific data such as "90 points in last year's math test", "English evaluation is B", "Math learning time is 3 hours per week", etc. Also, input the user's emotional situation (e.g., stress level).

[0283] Step 2:

[0284] The terminal sends the data input by the user to the server. When sending, send the data in an appropriate format (e.g., JSON or XML, etc.) so that the server can receive the data accurately.

[0285] Step 3:

[0286] The server receives the data sent from the terminal and saves it in a temporary database. Here, check the data consistency, and if there is an inconsistency, send an error message to the terminal.

[0287] Step 4:

[0288] The server performs preprocessing on the collected data. Specifically, implement the complementation of missing data (complementation with the average value or median, etc.) and the normalization of data (unification of different scales).

[0289] Step 5:

[0290] Based on pre-processed data, the server uses machine learning algorithms to identify the user's strong and weak subjects. For example, it might use a random forest or support vector machine to analyze the user's scoring patterns, identifying subjects with high scores as "strong subjects" and subjects with low scores as "weak subjects."

[0291] Step 6:

[0292] The server uses an emotion engine to estimate the user's emotions from their input data and learning history. For example, it estimates stress levels from the user's learning time and pace, and evaluates their emotional stability.

[0293] Step 7:

[0294] Based on the server's identified strengths and weaknesses, it suggests exam preparation strategies. For example, it generates specific strategies such as "watch English video tutorials for 30 minutes every day" or "solve applied math problems every weekend." At the same time, it also suggests ways to reduce stress (e.g., "take short breaks") based on the user's emotional state.

[0295] Step 8:

[0296] The server matches the user's strengths in subjects with information on potential universities and selects the most suitable university from the database. For example, it might recommend a science and engineering university's information science department to a user who excels in mathematics and has high emotional stability.

[0297] Step 9:

[0298] The server generates feedback data based on previous analysis results, suggested exam preparation strategies, and recommended educational institutions. This feedback data includes advice that takes the user's emotional state into consideration.

[0299] Step 10:

[0300] The device displays feedback data received from the server to the user. For example, it may display specific advice such as "Watch English video tutorials for 30 minutes every day" or "A science and engineering university's information science department would be suitable for you." It may also display emotion-based advice such as "Your stress levels have been high recently, so take a short break to relax."

[0301] Step 11:

[0302] Users create their own study plans based on feedback displayed on their devices. They implement recommended test preparation strategies and progress towards their goals. They can utilize emotionally driven advice to create plans that maximize learning effectiveness. They also reassess their emotional state in a timely manner and adjust their learning methods as needed.

[0303] (Example 2)

[0304] Next, we will describe Example 2. In the following description, the data processing device 12 will be referred to as the "server" and the smart device 14 as the "terminal".

[0305] Traditional learning support systems could identify a user's strengths and weaknesses based on their test results and evaluations, and suggest test preparation strategies and educational options. However, no system existed that adequately considered the user's emotional state while providing support. As a result, it was difficult to maximize the user's learning efficiency and motivation, and it was not possible to optimally address individual learning needs.

[0306] The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 2 is realized by the following means.

[0307] In this invention, the server includes means for receiving test results, evaluations, learning histories, and emotional states from a user, means for preprocessing the received data, means for identifying the user's strong and weak subjects based on the preprocessed data, means for proposing test countermeasures based on the strong and weak subjects, means for recommending further education destinations based on the strong and weak subjects and the emotional state, and means for presenting the proposed test countermeasures, further education destinations, and emotion-based advice to the user. By doing so, it becomes possible to optimally respond to individual learning needs while considering the user's emotional state, and to maximize learning efficiency and motivation.

[0308] The "user" refers to an end-user who inputs test results, evaluations, learning histories, and emotional states using the system.

[0309] The "test results" refer to data indicating the scores and grades of the tests taken by the user.

[0310] The "evaluation" refers to data indicating the ratings and grades from teachers or educational institutions for the subjects and tasks the user has received.

[0311] <所 The "learning history" refers to the records and data of the learning activities the user has carried out so far.

[0312] The "emotional state" refers to data indicating the emotions and psychological states of the user during learning.

[0313] The "preprocessing of data" refers to the process of complementing missing values, normalizing data, and verifying consistency for the collected data.

[0314] The "strong subject" refers to a subject in which the user has achieved high scores or evaluations.

[0315] The "weak subject" refers to a subject in which the user has achieved low scores or evaluations.

[0316] A "machine learning algorithm" refers to a mathematical model or computational method used to analyze large amounts of data and learn patterns and rules.

[0317] "Exam preparation" refers to learning methods and materials suggested to users to prepare for an exam.

[0318] "Recommended educational institution" refers to the educational institution or faculty that the user is advised to attend.

[0319] "Emotion-based advice" refers to advice on learning methods and stress management techniques that takes the user's emotional state into consideration.

[0320] "Feedback data" refers to data that provides users with a compilation of analysis results, exam preparation tips, recommendations for higher education institutions, and emotionally-based advice.

[0321] The system of this invention analyzes a user's strengths and weaknesses in different subjects and provides exam preparation strategies and recommendations for higher education based on that analysis. Furthermore, it incorporates an emotion engine that recognizes the user's emotions to provide more personalized learning support. This system consists of a terminal for the user to input data, a server that processes and analyzes the data, and a terminal that receives feedback from the server.

[0322] Hardware and software to be used

[0323] The following hardware and software are required to implement the system:

[0324] Devices: PC, smartphone, tablet, etc.

[0325] Server: High-performance computing server

[0326] Database Management Systems (DBMS): MySQL (registered trademark), PostgreSQL, etc.

[0327] Machine learning libraries: Scikit-learn, TENSORFLOW®, etc.

[0328] Emotion recognition software: Emotion API, OpenVINO, etc.

[0329] Data entry

[0330] Users use their devices to input their test results, evaluations, learning history, and emotional state. For example, they might input "Mathematics 90 points" as a test result, "English B" as an evaluation, "3 hours of math study per week" as a learning history, and "Recent stress levels are high" as an emotional state. This data is sent to the server via the device.

[0331] Sending data

[0332] The terminal converts the data entered by the user into JSON or XML format and sends it to the server. The data is encrypted in transit, ensuring secure communication.

[0333] Data preprocessing

[0334] The server receives data sent from the terminal and stores it in a temporary database. It then performs preprocessing such as imputing missing data (e.g., using the mean or median) and normalizing the data (unifying different scales). It also verifies data integrity and removes inappropriate data.

[0335] Identifying your strengths and weaknesses

[0336] The server uses pre-processed data and applies machine learning algorithms (e.g., random forest, support vector machine) to identify the user's strong and weak subjects. For example, if a user scores highly in mathematics and low in English, it will be determined that "mathematics is a strong subject" and "English is a weak subject."

[0337] emotion recognition

[0338] The server uses an emotion engine to estimate the user's emotions at the time of learning (e.g., stress level and satisfaction level) based on emotion data entered by the user and their learning history.

[0339] Suggestions for exam preparation

[0340] The server suggests test preparation strategies based on identified strengths and weaknesses. For example, it provides video tutorials and additional practice problems for English, which is a weak subject, and application problems and mock exams for mathematics, which is a strong subject. It also suggests relaxation methods based on emotional data if stress levels are high.

[0341] Recommended schools

[0342] The server matches information on the user's strengths in subjects and their potential educational paths to select the most suitable university from the database. For example, it might suggest a specific university, such as "For a user who excels in mathematics and has high emotional stability, we recommend a science and engineering-related university's information science department."

[0343] Generating and displaying feedback

[0344] The server generates feedback data based on the user's strengths and weaknesses in subjects, as well as emotional data. This feedback data includes exam preparation based on strengths and weaknesses, recommendations for higher education, and emotional advice. The generated feedback data is sent to the device and displayed in a format that the user can view. For example, it may display specific advice such as "Watch English video tutorials for 30 minutes every day" or "Solve applied math problems every weekend," as well as emotional advice such as "Take a short break because your stress level is high."

[0345] Specific example

[0346] User input example

[0347] Test results: Math 90 points, English 70 points, Science 85 points

[0348] Grades: Math A, English B, Science A

[0349] Learning history: Data from the past year

[0350] Emotional state: High stress levels recently

[0351] Server Processing Example

[0352] Data collection: Collect user test results, ratings, learning history, and sentiment status.

[0353] Data preprocessing: Imputation of missing values, normalization of data

[0354] Identifying my strong and weak subjects: My strong subject is "Mathematics," and my weak subject is "English."

[0355] Suggestions for exam preparation: "Watch English video tutorials for 30 minutes every day" and "Solve applied math problems every weekend."

[0356] Recommended university: "Information science department at a science and engineering university"

[0357] Utilizing the emotional engine: Due to high stress levels, "take short breaks."

[0358] Example of terminal output

[0359] We recommend that users "watch English video tutorials for 30 minutes every day" and "solve applied math problems every weekend."

[0360] Provide users with information on admissions to the "Information Science Department of a science and engineering university."

[0361] We recommend that users take short breaks to relax because their stress levels are high.

[0362] Example of a prompt

[0363] "Based on the entered test results and evaluation data, identify the user's strengths and weaknesses in different subjects. Furthermore, consider the user's learning history and emotional state to generate feedback messages that provide appropriate test preparation strategies and recommendations for further education."

[0364] The flow of the specific processing in Example 2 will be explained using Figure 13.

[0365] Step 1: User data entry

[0366] Users input their test results, evaluations, learning history, and emotional state through their device. Specific input examples include: "I scored 90 points on last year's math exam," "My English grade is a B," "I studied math for 3 hours a week," and "My stress level has been high recently." Once this data is entered into the device, the process proceeds to the next step.

[0367] Input: Test results, evaluation, learning history, emotional state

[0368] Output: User data entered into the terminal

[0369] Step 2: Data transmission by the terminal

[0370] The terminal converts the data entered by the user into JSON or XML format and sends it to the server. Data is encrypted during transmission to ensure secure communication.

[0371] Input: User data entered into the terminal

[0372] Output: Data in JSON or XML format sent to the server

[0373] Step 3: Server-based data collection and preprocessing

[0374] The server receives data sent from the terminal and stores it in a temporary database. It then performs preprocessing such as imputing missing data (using mean or median values) and normalizing the data (unifying different scales). It also verifies data integrity and removes inappropriate data.

[0375] Input: Data in JSON or XML format received by the server

[0376] Output: Preprocessed user data

[0377] Step 4: Server identifies strengths and weaknesses in subjects

[0378] The server uses pre-processed data to apply machine learning algorithms (e.g., random forest, support vector machine) to identify the user's strong and weak subjects. For example, if a user scores highly in mathematics and low in English, it will be determined that "mathematics is a strong subject" and "English is a weak subject."

[0379] Input: Preprocessed user data

[0380] Output: Identified strong subjects and subjects with high earnings

[0381] Step 5: Emotion Recognition by Server

[0382] The server uses an emotion engine to estimate emotions (e.g., stress levels and satisfaction levels) from emotion data and learning history obtained from users. For example, it analyzes emotions using natural language processing and facial recognition technology.

[0383] Input: User sentiment data, learning history

[0384] Output: Estimated emotions (stress level, satisfaction level, etc.)

[0385] Step 6: Server-based test preparation suggestions

[0386] The server suggests test preparation strategies based on identified strengths and weaknesses. For example, it provides video tutorials and additional practice problems for English, which is a weak subject, and application problems and mock exams for mathematics, which is a strong subject. It also suggests relaxation methods based on emotional data if stress levels are high.

[0387] Input: Identified strengths and weaknesses in subjects, estimated sentiment data

[0388] Output: Proposed exam preparation

[0389] Step 7: Server-based recommendation of educational institutions

[0390] The server matches information on the user's strengths in subjects and their desired educational institutions to select the most suitable institution from the database. For example, it might suggest a specific institution such as, "For a user who excels in mathematics and has high emotional stability, we recommend a science and engineering-related university's information science department."

[0391] Input: Strong subjects and weak subjects, and college admissions information database

[0392] Output: Recommended schools to attend

[0393] Step 8: Server generates feedback data

[0394] The server generates feedback data based on identified strengths and weaknesses in subjects, as well as emotional data. This feedback data includes test preparation tips, recommendations for higher education institutions, and emotionally-based advice.

[0395] Input: Identified strengths and weaknesses in subjects, emotional data

[0396] Output: Feedback data

[0397] Step 9: Displaying user feedback via the device

[0398] The device displays feedback data received from the server to the user. Specifically, it displays concrete advice such as "Watch English video tutorials for 30 minutes every day" and "Solve applied math problems every weekend," as well as emotion-based advice such as "Take a short break because your stress level is high."

[0399] Input: Feedback data received from the server

[0400] Output: Feedback presented to the user

[0401] Step 10: User creates learning plan

[0402] Users review feedback data through their devices and create learning plans based on it. They implement recommended test preparation strategies and leverage the emotional engine's advice to create plans that maximize learning efficiency. They reassess their emotional state in a timely manner and adjust their learning methods as needed.

[0403] Input: Feedback data

[0404] Output: Newly created study plan

[0405] (Application Example 2)

[0406] Next, we will explain application example 2. In the following explanation, the data processing device 12 will be referred to as a "server" and the smart device 14 as a "terminal".

[0407] Traditional learning support systems identified a user's strengths and weaknesses based on their test results and learning history, and then provided learning support accordingly. However, learning support provided without considering the user's emotional state had the problem of not reflecting the user's stress level or satisfaction level, resulting in ineffective learning support. Furthermore, similarly, product recommendations lacked personalization that took the user's emotional state into account, resulting in insufficient user satisfaction.

[0408] The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means.

[0409] In this invention, the server includes means for receiving test results, evaluations, learning history, and sentiment data from the user; means for pre-processing the received data; and means for identifying the user's strong and weak subjects based on the pre-processed data. This enables personalized test preparation and product recommendations that take the user's emotions into consideration.

[0410] Definitions of important words

[0411] "Test results" refer to data showing the scores and evaluations of tests taken by a user within a certain period of time.

[0412] "Evaluation" refers to the grades and feedback given based on the user's test results and learning progress.

[0413] "Learning history" refers to a record of a user's past learning activities, including data such as study time and learning materials used.

[0414] "Emotional data" refers to data that indicates a user's emotional state, including parameters such as stress levels and satisfaction levels.

[0415] "Preprocessing" refers to the process of modifying received data, such as imputing missing values ​​or normalizing the data.

[0416] A "favorite subject" is a subject in which a user consistently scores or receives high marks compared to other subjects.

[0417] A "subject a user struggles with" is a subject in which the user consistently scores or receives lower marks compared to other subjects.

[0418] "Exam preparation" refers to learning support methods and materials provided based on the user's strengths and weaknesses in different subjects.

[0419] "Recommended educational institution" refers to the educational institution or faculty that the user is advised to pursue next.

[0420] An "emotion recognition engine" is a system that estimates and analyzes emotions based on user input data and learning history.

[0421] "Feedback data" refers to data that includes advice and recommendations provided to users.

[0422] Modes for carrying out the invention

[0423] The system of this invention identifies the user's strengths and weaknesses in subjects based on their learning history and emotional data, and provides personalized learning support. The main components of this system include a terminal where the user inputs data, a server that processes and analyzes the data, and a terminal that receives feedback from the server.

[0424] System Overview

[0425] User: Input Data

[0426] Users input test results, evaluations, learning history, and sentiment data into the system via their devices. For example, they might input data such as "I scored 90 on last year's math exam," "My English grade is a B," "I studied math for 3 hours a week," and "My stress level has been high recently."

[0427] Terminal: Data transmission

[0428] The terminal sends the entered data to the server. The data is sent in an appropriate format, such as JSON or XML, ensuring that the server receives the data accurately.

[0429] Server: Data processing and preprocessing

[0430] The server receives data sent from the terminal and stores it in a temporary database. It then performs preprocessing such as imputing missing data and normalizing the data.

[0431] Server: Identifying strong and weak subjects

[0432] Based on the pre-processed data, the server uses machine learning algorithms (such as random forests or support vector machines) to identify subjects the student excels at and subjects they struggle with. Subjects with high scores are classified as "strong subjects," and subjects with low scores are classified as "weak subjects."

[0433] Server: Emotion analysis by emotion recognition engine

[0434] The server uses an emotion recognition engine to analyze the user's emotional state. For example, it analyzes stress levels and satisfaction levels during learning, and uses this emotional data to support learning.

[0435] Server: Providing exam preparation suggestions and recommendations for higher education institutions.

[0436] The server suggests exam preparation strategies based on identified strengths and weaknesses, and also selects potential universities from its database. For example, it might suggest specific strategies such as "watch 30 minutes of English video tutorials daily" or "solve applied math problems every weekend." It can also recommend a "Department of Information Science at a science and engineering university" as a suitable university.

[0437] Server: Feedback to users

[0438] The server generates feedback data based on previous analysis results, exam preparation suggestions, and recommended educational institutions. This feedback data also includes advice based on the user's emotional state.

[0439] Device: Show feedback

[0440] The device displays feedback received from the server to the user. For example, it might show advice such as "Watch English video tutorials for 30 minutes every day," "Solve applied math problems every weekend," or "Consider applying to the information science department of a science and engineering university." It might also recommend "Take a short break because your stress level is high."

[0441] Hardware and software to be used

[0442] The system uses the following hardware and software:

[0443] Hardware: Servers, user terminals (smartphones and tablets)

[0444] Software: Machine learning algorithms (random forest, support vector machine), database system, sentiment recognition engine

[0445] Specific example

[0446] User A enters the following data through the terminal:

[0447] Test results: Math 90 points, English 70 points

[0448] Grades: Math A, English B

[0449] Learning history: Math study time 3 hours / week

[0450] Emotional state: High stress level

[0451] The server receives this data, performs preprocessing, and then identifies the user's strengths and weaknesses. Considering learning history and sentiment data, it provides specific advice to the user, such as "watch English video tutorials for 30 minutes every day" or "a science and engineering university's information science department would be suitable for you."

[0452] Example of a prompt

[0453] "User A's purchase history includes electronic products (rated 5 stars) and books (rated 3 stars). They also have a high stress level recently. Please recommend products suitable for User A."

[0454] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[0455] Program processing steps

[0456] Step 1: Enter and submit user data.

[0457] Users input test results, evaluations, learning history, and sentiment data through their devices. This includes specific scores, evaluations, past learning time, and recent sentiment status. The devices then send this data to the server in JSON or XML format.

[0458] Input: User test results, evaluations, learning history, sentiment data

[0459] Output: Data in JSON or XML format provided by the terminal.

[0460] Specific operation: The user enters information into each field within the application and presses the "Submit" button.

[0461] Step 2: Server receives and temporarily stores data.

[0462] The server receives data sent from the terminal and stores it in a temporary database. This data is used in subsequent processing steps.

[0463] Input: User data in JSON or XML format

[0464] Output: Raw data stored in the database

[0465] Specific operation: The server receives requests at a specific API endpoint and saves the received data to the database.

[0466] Step 3: Data Preprocessing

[0467] The server performs preprocessing on the temporarily stored data, such as imputing missing data and normalizing the data. Specifically, it uses Python libraries (e.g., pandas, scikit-learn) to format the data.

[0468] Input: Raw data

[0469] Output: Preprocessed dataset

[0470] Specific operation: The server executes a script to impute missing values ​​(e.g., mean and median) and normalize the data.

[0471] Step 4: Identifying your strengths and weaknesses in different subjects

[0472] Based on the pre-processed data, the server uses machine learning algorithms (e.g., random forest, support vector machine) to identify the user's strengths and weaknesses in different subjects.

[0473] Input: Preprocessed dataset

[0474] Output: List of subjects you excel at and subjects you struggle with

[0475] Specific operation: The server uses a pre-trained model to make predictions and lists subjects the student excels at and struggles with.

[0476] Step 5: Emotion analysis using an emotion recognition engine

[0477] The server uses an emotion recognition engine to analyze the user's emotional state. This allows the user's stress level and satisfaction level to be understood numerically.

[0478] Input: User sentiment data

[0479] Output: Analyzed emotional data (e.g., stress level, satisfaction level)

[0480] Specific operation: The server invokes an emotion recognition engine, analyzes the input data, and obtains numerical values ​​for stress and satisfaction.

[0481] Step 6: Suggestions for exam preparation and recommendations for higher education options.

[0482] The server suggests optimal exam preparation strategies and educational options to the user based on their strengths and weaknesses in different subjects, as well as analyzed emotional data. This includes specific study methods and information on recommended educational institutions.

[0483] Input: Favorite subjects, least favorite subjects, analyzed emotional data

[0484] Output: Suggestions for exam preparation and a list of potential schools to attend.

[0485] Specific operation: The server uses an algorithm to provide the user with a suitable learning plan and educational options.

[0486] Step 7: Generate and send feedback

[0487] The server generates feedback data based on the analysis results so far and sends it to the terminal. This data includes recommendations for specific learning methods and schools to attend.

[0488] Input: Suggestions for exam preparation, list of universities to attend.

[0489] Output: User feedback data

[0490] Specific operation: The server sends the generated feedback to the terminal in JSON format.

[0491] Step 8: Displaying user feedback

[0492] The terminal displays feedback data received from the server to the user. This allows the user to obtain specific information on exam preparation and potential schools.

[0493] Input: Feedback data from the server

[0494] Output: Feedback information displayed on the terminal

[0495] Specific operation: The terminal analyzes the received data and displays it on the user interface.

[0496] This makes it possible for the present invention system to provide personalized learning support and product recommendations that take into account the user's emotions.

[0497] The specific processing unit 290 transmits the result of the specific processing to the smart device 14. In the smart device 14, the control unit 46A causes the output device 40 to output the result of the specific processing. The microphone 38B acquires audio indicating user input for the result of the specific processing. The control unit 46A transmits the audio data indicating user input acquired by the microphone 38B to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the audio data.

[0498] Data generation model 58 is a so-called generative AI (Artificial Intelligence). An example of data generation model 58 is ChatGPT (registered trademark) (Internet search).<URL: https: / / openai.com / blog / chatgpt> ), Gemini (registered trademark) (Internet search) <url: https: gemini.google.com ?hl="ja">Examples of generative AI include those described above. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 is input with prompts containing instructions, and with inference data such as audio data representing speech, text data representing text, and image data representing images. The data generation model 58 infers from the input inference data according to the instructions shown by the prompts, and outputs the inference results in data formats such as audio data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[0499] In the above embodiment, an example was given in which specific processing is performed by the data processing device 12, but the technology of this disclosure is not limited thereto, and the specific processing may also be performed by the smart device 14.

[0500] [Second Embodiment]

[0501] Figure 3 shows an example of the configuration of the data processing system 210 according to the second embodiment.

[0502] As shown in Figure 3, the data processing system 210 includes a data processing device 12 and smart glasses 214. An example of the data processing device 12 is a server.

[0503] The data processing device 12 comprises a computer 22, a database 24, and a communication interface 26. The computer 22 is an example of a "computer" related to the technology of this disclosure. The computer 22 comprises a processor 28, RAM 30, and storage 32. The processor 28, RAM 30, and storage 32 are connected to a bus 34. The database 24 and the communication interface 26 are also connected to the bus 34. The communication interface 26 is connected to a network 54. An example of the network 54 is a WAN (Wide Area Network) and / or a LAN (Local Area Network).

[0504] The smart glasses 214 include a computer 36, a microphone 238, a speaker 240, a camera 42, and a communication interface 44. The computer 36 includes a processor 46, RAM 48, and storage 50. The processor 46, RAM 48, and storage 50 are connected to a bus 52. The microphone 238, speaker 240, and camera 42 are also connected to the bus 52.

[0505] The microphone 238 receives voice signals from the user 20 and receives instructions from the user 20. The microphone 238 captures the voice signals from the user 20, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio according to the instructions from the processor 46.

[0506] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an image sensor such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, and captures images of the area around the user 20 (for example, an imaging range defined by a field of view equivalent to the width of a typical healthy person's field of vision).

[0507] Communication interface 44 is connected to network 54. Communication interfaces 44 and 26 are responsible for the exchange of various information between processor 46 and processor 28 via network 54. The exchange of various information between processor 46 and processor 28 using communication interfaces 44 and 26 is performed in a secure manner.

[0508] Figure 4 shows an example of the main functions of the data processing device 12 and the smart glasses 214. As shown in Figure 4, the data processing device 12 performs specific processing using the processor 28. The storage 32 stores the specific processing program 56.

[0509] The specific processing program 56 is an example of a "program" relating to the technology of this disclosure. The processor 28 reads the specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific processing is realized by the processor 28 operating as a specific processing unit 290 in accordance with the specific processing program 56 executed on the RAM 30.

[0510] The storage 32 stores the data generation model 58 and the emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290.

[0511] In the smart glasses 214, the processor 46 performs the reception output processing. The storage 50 stores the reception output program 60. The processor 46 reads the reception output program 60 from the storage 50 and executes the read reception output program 60 on the RAM 48. The reception output processing is realized by the processor 46 operating as a control unit 46A according to the reception output program 60 executed on the RAM 48.

[0512] Next, the identification processing performed by the identification processing unit 290 of the data processing device 12 will be described. In the following description, the data processing device 12 will be referred to as the "server" and the smart glasses 214 will be referred to as the "terminal".

[0513] The system of this invention analyzes a user's strengths and weaknesses in different subjects and provides exam preparation strategies and recommendations for higher education based on that analysis. This system mainly consists of a terminal where the user inputs data, a server that processes and analyzes the data, and a terminal that receives feedback from the server.

[0514] System Overview

[0515] User: Data entry

[0516] Users input test results, evaluations, and learning history into the system via their devices. For example, they might input specific data such as, "I got 90 points on last year's math exam," or "My English grade was a B."

[0517] Terminal: Data transmission

[0518] The terminal sends the entered data to the server. When sending the data, it is important to send it in an appropriate format (such as JSON or XML) so that the server can receive the data accurately.

[0519] Server: Data collection and preprocessing

[0520] The server collects data sent from the terminal and stores it in a temporary data store. Then, it performs preprocessing on the collected data. Specifically, it imputes missing values ​​with the mean or median, and normalizes data from different scales to unify them.

[0521] Server: Identifying strong and weak subjects

[0522] Based on the pre-processed data, the server identifies the user's strong and weak subjects. Here, machine learning algorithms (e.g., random forest or support vector machine) are used to analyze the scoring patterns for each subject. Subjects with high scores are identified as "strong subjects," and subjects with low scores are identified as "weak subjects."

[0523] Server: Suggestions for exam preparation

[0524] The server suggests exam preparation strategies based on identified strengths and weaknesses. For example, it recommends video tutorials and additional practice problems for weak subjects, and provides application problems and mock exams for strong subjects. Specifically, this might include suggestions like "watch a 30-minute English video tutorial every day" or "solve application problems in mathematics on the weekend."

[0525] Server: Recommended by the school you will be attending

[0526] The server matches the user's strengths in subjects with information on potential universities. Considering the user's strengths and interests, it selects the most suitable university from the database. For example, it might suggest a university like "A science and engineering university's information science department would be suitable because you excel in mathematics."

[0527] Server: Generating feedback data

[0528] The server generates feedback data based on previous analysis results, suggested exam preparation strategies, and recommended educational institutions. This feedback data is then provided to the user.

[0529] Device: Displaying feedback to the user

[0530] The device displays feedback data received from the server to the user. The displayed feedback includes specific details such as, "Your weakest subject is English. Watch English video tutorials for 30 minutes every day. Also, a computer science department at a science and engineering university would be a good fit for you."

[0531] User: Creating a study plan

[0532] Users create their own study plans based on feedback displayed on their devices. They can set specific study schedules and goals based on recommended test preparation and information about potential schools.

[0533] Specific example

[0534] 1. User input example

[0535] Test results: Math 90 points, English 70 points, Science 85 points

[0536] Grades: Math A, English B, Science A

[0537] Learning history: Data from the past year

[0538] 2. Example of server processing

[0539] Data collection: Collect user test results, evaluations, and learning history.

[0540] Data preprocessing: Imputation of missing values, normalization of statistical data.

[0541] Identifying my strong and weak subjects: My strong subject is "Mathematics," and my weak subject is "English."

[0542] Suggestions for exam preparation: "Watch English video tutorials for 30 minutes every day" and "Solve applied math problems every weekend."

[0543] Recommended university: "Information science department at a science and engineering university"

[0544] 3. Example of terminal output

[0545] We recommend that users "watch English video tutorials for 30 minutes every day" and "solve applied math problems every weekend."

[0546] Provide users with information on admissions to the "Information Science Department of a science and engineering university."

[0547] This allows users to prepare for exams best suited to their individual strengths and choose the appropriate educational institution. In this way, users can create more effective study plans and gain an advantage in future educational and career choices.

[0548] The following describes the processing flow.

[0549] Step 1:

[0550] Users use their devices to input their test results, grades, and learning history. For example, they might input specific data such as "I scored 90 points on last year's math exam," "My English grade was a B," and "I studied math for 3 hours a week."

[0551] Step 2:

[0552] The terminal sends data entered by the user to the server. This input data is often sent in formats such as JSON or XML.

[0553] Step 3:

[0554] The server receives data sent from the terminal and stores it in a temporary database. Here, it checks the data's integrity and sends an error message to the terminal if any inconsistencies are found.

[0555] Step 4:

[0556] The server preprocesses the collected data. Specifically, it performs data imputation (such as imputing with the mean or median) and data normalization (unifying different scales).

[0557] Step 5:

[0558] Based on pre-processed data, the server uses machine learning algorithms to identify the user's strong and weak subjects. For example, it might use a random forest or support vector machine to analyze the user's scoring patterns, identifying subjects with high scores as "strong subjects" and subjects with low scores as "weak subjects."

[0559] Step 6:

[0560] Based on the user's identified strengths and weaknesses in different subjects, the server suggests exam preparation strategies. For example, it might generate specific strategies such as "Watch English video tutorials for 30 minutes every day" or "Solve applied math problems every weekend."

[0561] Step 7:

[0562] The server matches the user's strengths in subjects with information on potential universities and selects the most suitable university from the database. For example, it might identify a university with a strong focus on science and engineering, such as "a science and engineering university's information science department, as the user excels in mathematics."

[0563] Step 8:

[0564] The server generates feedback data based on previous analysis results, suggested exam preparation strategies, and recommended educational institutions. This feedback data serves as a reference for users to create concrete study plans.

[0565] Step 9:

[0566] The device displays feedback data received from the server to the user. For example, it might display specific advice such as, "Watch English video tutorials for 30 minutes every day," or "A science and engineering university's information science department would be suitable."

[0567] Step 10:

[0568] Users create a specific study plan based on feedback displayed on their device. They then implement recommended test preparation strategies and progress towards their goals.

[0569] (Example 1)

[0570] Next, we will describe Example 1. In the following description, the data processing device 12 will be referred to as the "server," and the smart glasses 214 will be referred to as the "terminal."

[0571] Traditional educational support systems struggle to accurately identify each user's individual learning situation, strengths, and weaknesses, and to provide appropriate test preparation and recommendations for higher education based on that information. In particular, insufficient preprocessing, such as imputing missing values ​​or unifying data from different scales, prevents accurate analysis. Furthermore, the suggested test preparation and educational recommendations are often vague and therefore impractical for users.

[0572] The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 1 is realized by the following means.

[0573] In this invention, the server includes means for receiving education-related data (test results, evaluations, learning history) from the user, means for preprocessing the received data, means for normalizing the data and imputing missing values, means for identifying the user's strengths and weaknesses based on the preprocessed data, means for identifying them using machine learning algorithms (e.g., random forest or support vector machine), means for proposing educational support based on the identified strengths and weaknesses, means for recommending educational institutions based on the strengths and weaknesses, and means for displaying the proposed educational support and educational institutions to the user. This enables accurate learning analysis tailored to the user's individual circumstances and specific and effective recommendations for test preparation and further education.

[0574] "Education-related data" refers to the totality of information related to a user's learning, including test results, evaluations, and learning history.

[0575] "Preprocessing" is the process of converting received data into a format that can be properly analyzed. Specifically, this involves tasks such as imputing missing values ​​and normalizing the data.

[0576] "Normalization" is a process for unifying data at different scales, and is a means of making data comparison and analysis easier.

[0577] "Missing value imputation" is the procedure of filling in missing data in a dataset using a specific method (e.g., the mean or median).

[0578] A "machine learning algorithm" is a mathematical model used to analyze patterns in data and make predictions or classifications based on specific objectives.

[0579] "Areas of expertise" refers to learning areas where a user demonstrates particularly high performance.

[0580] A "weakness area" refers to a learning area where a user shows relatively low performance.

[0581] "Educational support" is a general term for the support provided to achieve specific learning objectives, and specifically includes study plans, practice problems, video tutorials, and so on.

[0582] "Educational institutions" refers to all learning facilities and educational programs related to a user's learning or further education.

[0583] "Feedback data" refers to information that includes advice and recommendations generated based on the user's learning progress, strengths, and weaknesses.

[0584] Users input educational data using a terminal. Specifically, they input information such as test results, evaluations, and learning history, and this information is sent to the system. The terminal is equipped with at least a user interface for inputting data and a function to convert that data into an appropriate format (e.g., JSON or XML) and send it.

[0585] Data sent from the terminal is received by the server. This server preprocesses the data by storing it in a temporary data store, and then performs tasks such as imputing missing values ​​and normalizing the data. This process ensures data consistency and enables accurate analysis.

[0586] The pre-processed data is used on the server to identify areas of strength and weakness. Machine learning algorithms such as random forests and support vector machines are applied here. This identifies areas where the user performs well as "strengths" and areas where performance is poor as "weaknesses."

[0587] The server then proposes specific educational support based on these identified strengths and weaknesses. For example, for English, which is a weak area, it might suggest "watching 30 minutes of English video tutorials every day," and for mathematics, which is a strong area, it might suggest "solving applied math problems on weekends."

[0588] Furthermore, the server matches the user's areas of expertise with information about their educational background to recommend the most suitable institution. For example, it might recommend a "Department of Information Science at a science and engineering university" to a user who excels in mathematics. This recommendation information is also provided to the user as part of the feedback.

[0589] These analysis results, suggestions, and recommendations for higher education are generated as feedback data and provided to the user. The device displays this feedback data to the user. The displayed content includes specific instructions such as, "Your weak area is English. Please watch English video tutorials for 30 minutes every day. Also, the information science department of a science and engineering university would be suitable for you."

[0590] Users can use this feedback data to set specific learning plans. For example, they can create action plans such as "watch 30 minutes of English video tutorials every day" or "solve applied math problems on weekends."

[0591] Example of a prompt

[0592] 1. "Based on your learning history over the past year, identify your strengths and weaknesses in different subjects, and then propose exam preparation strategies and college options accordingly."

[0593] 2. "Analyze the test results, evaluations, and learning history entered by the user, and recommend the most suitable test preparation methods and educational institutions."

[0594] This allows users to receive educational support best suited to their circumstances and choose the appropriate educational institution. Users can also develop more effective study plans and be in a more advantageous position when choosing future education or careers.

[0595] The flow of the specific processing in Example 1 will be explained using Figure 11.

[0596] Step 1:

[0597] Users input educational data using their devices. Specifically, they input information such as test results, grades, and learning history. For example, they might input data such as "I got 90 points on last year's math exam" or "My English grade was a B."

[0598] Input: Test results, evaluation, learning history

[0599] Output: Educational data stored in the device's temporary data store.

[0600] Step 2:

[0601] The terminal converts the input data into an appropriate format (e.g., JSON or XML) and sends it to the server. Before sending the data, it verifies that the data is formatted correctly.

[0602] Input: Educational data stored on the device

[0603] Output: Send formatted educational data (in JSON or XML format) to the server.

[0604] Step 3:

[0605] The server stores the data received from the terminal in a temporary data store and begins data preprocessing. First, it imputes any missing values ​​and normalizes the data. This is done using missing value imputation algorithms and normalization algorithms. For example, missing test result values ​​are imputed with the average value for that subject.

[0606] Input: Formatted education-related data

[0607] Output: Preprocessed education-related data (missing values ​​imputed, normalized)

[0608] Step 4:

[0609] The server uses pre-processed data to identify the user's strengths and weaknesses. Machine learning algorithms such as random forests and support vector machines are used here. For example, if a user scores highly in math and low in English, math is identified as a strength and English as a weakness.

[0610] Input: Preprocessed education-related data

[0611] Output: User's strengths and weaknesses

[0612] Step 5:

[0613] Based on the user's strengths and weaknesses, the server proposes specific educational support. For example, it might suggest "watching 30 minutes of English video tutorials daily" to a user who struggles with English, or "solving applied math problems on weekends" to a user who excels at math.

[0614] Input: User's strengths and weaknesses

[0615] Output: Suggestions for educational support tailored to the user.

[0616] Step 6:

[0617] The server matches the user's areas of expertise with educational institution information to recommend the most suitable institution. For example, a user who excels in mathematics would be recommended a "Department of Information Science at a science and engineering university."

[0618] Input: User's areas of expertise and educational institution information

[0619] Output: Recommendations for the most suitable educational institutions for the user.

[0620] Step 7:

[0621] The server compiles the analysis results, exam preparation suggestions, and recommended schools to generate feedback data. This feedback data is provided to the user.

[0622] Input: Areas of expertise and weaknesses, suggestions for educational support, recommendations for educational institutions.

[0623] Output: Feedback data

[0624] Step 8:

[0625] The terminal displays feedback data received from the server to the user. The displayed content includes specific instructions such as, "Your weak point is English. Watch English video tutorials for 30 minutes every day. Also, a computer science department at a science and engineering university would be a good fit for you."

[0626] Input: Feedback data

[0627] Output: Specific feedback displayed to the user

[0628] Step 9:

[0629] Users create their own learning plans based on feedback from their devices. They set specific study schedules and goals based on recommended test preparation and educational institution information. For example, they might create action plans such as "watch 30 minutes of English video tutorials every day" or "solve applied math problems on weekends."

[0630] Input: Feedback data

[0631] Output: Specific learning plan set by the user

[0632] (Application Example 1)

[0633] Next, we will explain Application Example 1. In the following explanation, the data processing device 12 will be referred to as the "server," and the smart glasses 214 will be referred to as the "terminal."

[0634] In modern education systems, providing appropriate learning support based on each student's strengths and weaknesses is crucial. However, traditional systems have made it difficult to comprehensively identify students' strengths and weaknesses, resulting in an inability to provide effective learning strategies. Furthermore, recommending appropriate educational institutions and suggesting individually optimized educational content has been challenging. This has led to problems such as students being unable to create a suitable learning plan, resulting in decreased learning efficiency and motivation.

[0635] The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 1 is realized by the following means.

[0636] In this invention, the server includes means for recommending appropriate learning content based on the user's strengths and weaknesses; means for receiving test results, evaluations, and learning history from the user; means for pre-processing the received data; means for identifying the user's strengths and weaknesses based on the pre-processed data; means for suggesting test preparation strategies based on the strengths and weaknesses; means for recommending higher education options based on the strengths and weaknesses; means for displaying the suggested test preparation strategies and higher education options to the user; and means for transmitting data from the user's terminal to the server and receiving feedback from the server. This enables the suggestion of educational content optimized for individual students, and allows for effective learning strategies and recommendations for higher education options.

[0637] A "user" is an individual who uses the system to input data such as test results, evaluations, and learning history, and receives learning support and recommendations for further education.

[0638] "Test results" refer to data that shows the scores and grades a user obtained in each subject of the exam.

[0639] "Evaluation" refers to data that indicates a teacher's or educational institution's assessment of a user's learning performance, and is usually represented by letters or numbers.

[0640] "Learning history" refers to data that records a user's past learning activities and performance.

[0641] "Means of receiving data" refers to devices or software that have the function of acquiring data entered by the user and sending it to the server.

[0642] "Preprocessing methods" refer to devices or software used to prepare received data for analysis by imputing missing values ​​and normalizing the data.

[0643] "Means of identification" refers to devices or software that have the function of identifying a user's strong and weak subjects based on pre-processed data.

[0644] "Machine learning algorithm" is a term that refers to an algorithm used by computers to learn from data and recognize patterns.

[0645] "Means of suggesting exam preparation strategies" refers to devices or software that have the function of recommending learning methods and materials suitable for the user based on their identified strengths and weaknesses in different subjects.

[0646] "Means of recommending educational institutions" refers to devices or software that have the function of suggesting the most suitable educational institutions based on the user's strengths and interests.

[0647] "Feedback data" refers to data that includes summaries of information provided to users, such as exam preparation strategies and recommendations for higher education institutions.

[0648] "Means of displaying to the user" refers to devices or software that visually present feedback data received from the server to the user.

[0649] "Means for recommending appropriate learning content" refers to devices or software that suggest optimal educational content based on the user's learning needs and current proficiency level.

[0650] A "terminal" is a device used by a user to input data and communicate with a server, and includes smartphones, tablets, and personal computers.

[0651] This invention is a system that analyzes a user's strengths and weaknesses in different subjects and provides exam preparation strategies and recommendations for higher education based on that analysis. The following describes an embodiment of the system in detail.

[0652] User data entry

[0653] Users input data such as test results, evaluations, and learning history using devices such as smartphones, tablets, or personal computers. This data includes specific information such as, "I scored 90 points on last year's math exam," or "My English grade is a B."

[0654] Data transmission and preprocessing

[0655] The terminal sends the data entered by the user to the server in JSON format or another appropriate format. The server temporarily stores the received data and performs preprocessing such as imputing missing values ​​and normalizing the data. Python libraries such as Pandas and Scikit-learn are used for this process.

[0656] Identifying your strengths and weaknesses in different subjects.

[0657] The server uses machine learning algorithms to identify strong and weak subjects based on pre-processed data. For example, algorithms such as Random Forest and Support Vector Machine (SVM) are used. This allows the system to identify subjects with high scores as "strong subjects" and subjects with low scores as "weak subjects."

[0658] Exam preparation and suggestions for higher education options

[0659] The server suggests appropriate exam preparation based on the user's strengths and weaknesses. For example, it generates specific study plans such as "watch English video tutorials for 30 minutes every day" or "solve applied math problems on weekends." It also matches the user's strengths with information on potential universities to recommend the most suitable institutions. For example, if the user's strength is mathematics, it might suggest "a computer science department at a science and engineering university would be a good fit."

[0660] Displaying feedback

[0661] The feedback data generated by the server is sent to the terminal in real time and displayed to the user. Users can use this feedback to create their study plans. Because the feedback includes specific study strategies and information on potential schools, users can study more effectively.

[0662] Specific examples and prompt statements

[0663] As a concrete example, consider the case where the user's input data was as follows:

[0664] Test results: Math 90 points, English 70 points, Science 85 points

[0665] Grades: Math A, English B, Science A

[0666] Learning history: Data from the past year

[0667] Server processing example:

[0668] Data Collection and Preprocessing: Collect user test results, evaluations, and training history, and perform data imputation and normalization.

[0669] Identifying strengths and weaknesses: Analyzed strengths as "mathematics" and weaknesses as "English".

[0670] Suggestions for exam preparation: "Watch English video tutorials for 30 minutes every day," "Solve applied math problems every weekend," etc.

[0671] Recommended university: We recommend the Faculty of Information Science at a science and engineering university.

[0672] Examples of prompts for a generative AI model:

[0673] "Develop a system that analyzes a user's strengths and weaknesses in specific subjects based on their test results, evaluations, and learning history. Based on these results, it will suggest appropriate learning content and also provide information on potential higher education options. The following is an example of user input."

[0674] Test results: Math 90 points, English 70 points, Science 85 points

[0675] Grades: Math A, English B, Science A

[0676] Learning history: Data from the past year

[0677] Based on this data, please identify the student's strengths and weaknesses in different subjects and provide feedback on specific study plans and potential educational paths.

[0678] As described above, the present invention provides optimal learning support to individual users and constructs a system that enables improved learning efficiency and appropriate choices for further education.

[0679] The flow of a specific process in Application Example 1 will be explained using Figure 12.

[0680] Step 1:

[0681] Users input data such as test results, evaluations, and learning history using a device (smartphone, tablet, or PC). Specifically, they input test results such as 90 points in mathematics, 70 points in English, and 85 points in science, as well as evaluations for each subject (e.g., Mathematics A, English B, Science A).

[0682] Input: Test results, evaluation, learning history

[0683] Output: User data in JSON format

[0684] Step 2:

[0685] The terminal converts the entered user data into JSON format and sends it to the server. It uses an HTTP POST request to send the data to the specified API endpoint.

[0686] Input: User data in JSON format

[0687] Output: Results of sending data to the server

[0688] Step 3:

[0689] The server temporarily stores the received data. Then, it performs preprocessing such as imputing missing values ​​and normalizing the data. Here, data cleaning is performed using Pandas or Scikit-learn.

[0690] Input: User data in JSON format

[0691] Output: Preprocessed data

[0692] Step 4:

[0693] The server applies machine learning algorithms (e.g., Random Forest or SVM) to preprocessed data to identify subjects in which the user excels and struggles. This allows for an analysis of academic performance trends for each subject, thereby identifying strengths and weaknesses.

[0694] Input: Preprocessed data

[0695] Output: Identification of strong and weak subjects

[0696] Step 5:

[0697] Based on the identification of the user's strengths and weaknesses, the server suggests appropriate test preparation strategies. For example, it might suggest watching 30 minutes of video tutorials daily for English, which is a weak subject, and recommend solving application problems on weekends for mathematics, which is a strong subject.

[0698] Input: Results of identifying strong and weak subjects

[0699] Output: Suggestions for exam preparation

[0700] Step 6:

[0701] The server matches the user's preferred subjects and college application information to recommend the most suitable college. For example, if the user's preferred subject is mathematics, the server will suggest a computer science department at a science and engineering university as a college option.

[0702] Input: Database of preferred subjects and universities / schools attended

[0703] Output: Recommended content from prospective schools

[0704] Step 7:

[0705] The server generates feedback data, including exam preparation strategies and recommendations for higher education institutions, and sends it to the terminal in real time. The generated feedback data is packaged in a format that is easy for the user to review.

[0706] Input: Suggestions for exam preparation, recommendations for universities to attend.

[0707] Output: Feedback data

[0708] Step 8:

[0709] The device displays feedback data received from the server to the user. Based on this feedback data, the user can create their own learning plan. Specifically, concrete plans such as "watch English video tutorials for 30 minutes every day" or "solve applied math problems on the weekend" are provided.

[0710] Input: Feedback data

[0711] Output: Displaying feedback to the user

[0712] Furthermore, an emotion engine that estimates the user's emotions may be incorporated. That is, the identification processing unit 290 may use the emotion identification model 59 to estimate the user's emotions and perform identification processing using the user's emotions.

[0713] The system of this invention analyzes a user's strengths and weaknesses in different subjects and provides exam preparation strategies and recommendations for higher education based on that analysis. Furthermore, it incorporates an emotion engine that recognizes the user's emotions to provide more personalized learning support. This system mainly consists of a terminal where the user inputs data, a server that processes and analyzes the data, and a terminal that receives feedback from the server.

[0714] System Overview

[0715] User: Data entry

[0716] Users input test results, evaluations, and learning history into the system via their devices. For example, they might input specific data such as "I scored 90 points on last year's math exam," "My English grade was a B," and "I studied math for 3 hours a week." Users can also input their emotional state.

[0717] Terminal: Data transmission

[0718] The terminal sends the entered data to the server. When sending the data, it is important to send it in an appropriate format (such as JSON or XML) so that the server can receive the data accurately.

[0719] Server: Data collection and preprocessing

[0720] The server receives data sent from the terminal and stores it in a temporary database. It then performs preprocessing on the collected data. Specifically, this includes imputing missing data (such as using the mean or median) and normalizing the data (unifying different scales).

[0721] Server: Identifying strong and weak subjects

[0722] Based on the pre-processed data, the server identifies the user's strong and weak subjects. Here, machine learning algorithms (e.g., random forest or support vector machine) are used to analyze the scoring patterns for each subject. Subjects with high scores are identified as "strong subjects," and subjects with low scores are identified as "weak subjects."

[0723] Server: Emotion recognition by emotion engine

[0724] The server uses an emotion engine to estimate user emotions from input data and learning history. For example, it analyzes stress levels and satisfaction levels during learning, and uses this emotional data to support learning.

[0725] Server: Suggestions for exam preparation

[0726] The server suggests exam preparation strategies based on identified strengths and weaknesses. For example, it provides video tutorials and additional practice problems for weak subjects, and application problems and mock exams for strong subjects. It also suggests learning methods to help users relax if they are experiencing stress.

[0727] Server: Recommended by the school you will be attending

[0728] The server matches the user's strengths in subjects with information on potential universities and selects the most suitable university from the database. For example, it might recommend a science and engineering university's information science department to a user who excels in mathematics and has high emotional stability.

[0729] Server: Generating feedback data

[0730] The server generates feedback data based on previous analysis results, suggested exam preparation strategies, and recommended educational institutions. This feedback data includes advice that takes the user's emotional state into consideration.

[0731] Device: Displaying feedback to the user

[0732] The device displays feedback data received from the server to the user. For example, it may display specific advice such as "Watch English video tutorials for 30 minutes every day" or "A science and engineering university's information science department would be suitable for you." It may also display emotion-based advice such as "Your stress levels have been high recently, so take short breaks to relax."

[0733] User: Creating a study plan

[0734] Users create their own learning plans based on feedback displayed on their devices. They implement recommended test preparation strategies and progress towards their goals. They can leverage emotionally driven advice to create plans that maximize learning effectiveness. They also reassess their emotional state in a timely manner and adjust their learning methods as needed.

[0735] Specific example

[0736] 1. User input example

[0737] Test results: Math 90 points, English 70 points, Science 85 points

[0738] Grades: Math A, English B, Science A

[0739] Learning history: Data from the past year

[0740] Emotional state: High stress levels recently

[0741] 2. Example of server processing

[0742] Data collection: Collect user test results, ratings, learning history, and sentiment status.

[0743] Data preprocessing: Imputation of missing values, normalization of statistical data.

[0744] Identifying my strong and weak subjects: My strong subject is "Mathematics," and my weak subject is "English."

[0745] Suggestions for exam preparation: "Watch English video tutorials for 30 minutes every day" and "Solve applied math problems every weekend."

[0746] Recommended university: "Information science department at a science and engineering university"

[0747] Utilizing the emotional engine: Due to high stress levels, "take short breaks."

[0748] 3. Example of terminal output

[0749] We recommend that users "watch English video tutorials for 30 minutes every day" and "solve applied math problems every weekend."

[0750] Provide users with information on admissions to the "Information Science Department of a science and engineering university."

[0751] We recommend that users take short breaks to relax because their stress levels are high.

[0752] This allows users to choose test preparation methods best suited to their individual characteristics and educational options that take their emotional state into consideration. In this way, users can create more effective study plans and gain an advantage in future educational and career choices.

[0753] The following describes the processing flow.

[0754] Step 1:

[0755] Users use their devices to input their test results, evaluations, and learning history. For example, they might input specific data such as "I scored 90 points on last year's math exam," "My English grade is a B," and "I studied math for 3 hours a week." They also input their emotional state (e.g., stress level).

[0756] Step 2:

[0757] The terminal sends data entered by the user to the server. When sending the data, it is important to send it in an appropriate format (e.g., JSON or XML) so that the server can receive the data accurately.

[0758] Step 3:

[0759] The server receives data sent from the terminal and stores it in a temporary database. Here, it checks the data's integrity and sends an error message to the terminal if any inconsistencies are found.

[0760] Step 4:

[0761] The server preprocesses the collected data. Specifically, it performs data imputation (such as imputing with the mean or median) and data normalization (unifying different scales).

[0762] Step 5:

[0763] Based on pre-processed data, the server uses machine learning algorithms to identify the user's strong and weak subjects. For example, it might use a random forest or support vector machine to analyze the user's scoring patterns, identifying subjects with high scores as "strong subjects" and subjects with low scores as "weak subjects."

[0764] Step 6:

[0765] The server uses an emotion engine to estimate the user's emotions from their input data and learning history. For example, it estimates stress levels from the user's learning time and pace, and evaluates their emotional stability.

[0766] Step 7:

[0767] Based on the server's identified strengths and weaknesses, it suggests exam preparation strategies. For example, it generates specific strategies such as "watch English video tutorials for 30 minutes every day" or "solve applied math problems every weekend." At the same time, it also suggests ways to reduce stress (e.g., "take short breaks") based on the user's emotional state.

[0768] Step 8:

[0769] The server matches the user's strengths in subjects with information on potential universities and selects the most suitable university from the database. For example, it might recommend a science and engineering university's information science department to a user who excels in mathematics and has high emotional stability.

[0770] Step 9:

[0771] The server generates feedback data based on previous analysis results, suggested exam preparation strategies, and recommended educational institutions. This feedback data includes advice that takes the user's emotional state into consideration.

[0772] Step 10:

[0773] The device displays feedback data received from the server to the user. For example, it may display specific advice such as "Watch English video tutorials for 30 minutes every day" or "A science and engineering university's information science department would be suitable for you." It may also display emotion-based advice such as "Your stress levels have been high recently, so take a short break to relax."

[0774] Step 11:

[0775] Users create their own study plans based on feedback displayed on their devices. They implement recommended test preparation strategies and progress towards their goals. They can utilize emotionally driven advice to create plans that maximize learning effectiveness. They also reassess their emotional state in a timely manner and adjust their learning methods as needed.

[0776] (Example 2)

[0777] Next, we will describe Example 2. In the following description, the data processing device 12 will be referred to as the "server" and the smart glasses 214 will be referred to as the "terminal".

[0778] Traditional learning support systems could identify a user's strengths and weaknesses based on their test results and evaluations, and suggest test preparation strategies and educational options. However, no system existed that adequately considered the user's emotional state while providing support. As a result, it was difficult to maximize the user's learning efficiency and motivation, and it was not possible to optimally address individual learning needs.

[0779] The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 2 is realized by the following means.

[0780] In this invention, the server includes means for receiving test results, evaluations, learning history, and emotional status from the user; means for pre-processing the received data; means for identifying the user's strong and weak subjects based on the pre-processed data; means for suggesting test preparation strategies based on the strong and weak subjects; means for recommending schools to attend based on the strong and weak subjects and emotional status; and means for presenting the user with the suggested test preparation strategies, schools to attend, and advice based on their emotional status. This makes it possible to optimally respond to individual learning needs while taking into account the user's emotional status, and to maximize learning efficiency and motivation.

[0781] A "user" refers to an end-user who uses the system to input test results, evaluations, learning history, and emotional status.

[0782] "Test results" refers to data showing the scores and performance of tests taken by the user.

[0783] "Evaluation" refers to data that shows the grades and ratings from teachers and educational institutions for subjects and assignments that a user has taken.

[0784] "Learning history" refers to the records and data of the learning activities a user has undertaken so far.

[0785] "Emotional state" refers to data that indicates the user's emotions and psychological state during learning.

[0786] "Data preprocessing" refers to the process of imputing missing values, normalizing data, and verifying data integrity in collected data.

[0787] A "favorite subject" refers to a subject in which the user has achieved high scores or evaluations.

[0788] A "subject a user struggles with" refers to a subject in which the user consistently achieves low scores or evaluations.

[0789] A "machine learning algorithm" refers to a mathematical model or computational method used to analyze large amounts of data and learn patterns and rules.

[0790] "Exam preparation" refers to learning methods and materials suggested to users to prepare for an exam.

[0791] "Recommended educational institution" refers to the educational institution or faculty that the user is advised to attend.

[0792] "Emotion-based advice" refers to advice on learning methods and stress management techniques that takes the user's emotional state into consideration.

[0793] "Feedback data" refers to data that provides users with a compilation of analysis results, exam preparation tips, recommendations for higher education institutions, and emotionally-based advice.

[0794] The system of this invention analyzes a user's strengths and weaknesses in different subjects and provides exam preparation strategies and recommendations for higher education based on that analysis. Furthermore, it incorporates an emotion engine that recognizes the user's emotions to provide more personalized learning support. This system consists of a terminal for the user to input data, a server that processes and analyzes the data, and a terminal that receives feedback from the server.

[0795] Hardware and software to be used

[0796] The following hardware and software are required to implement the system:

[0797] Devices: PC, smartphone, tablet, etc.

[0798] Server: High-performance computing server

[0799] Database Management Systems (DBMS): MySQL, PostgreSQL, etc.

[0800] Machine learning libraries: Scikit-learn, TensorFlow, etc.

[0801] Emotion recognition software: Emotion API, OpenVINO, etc.

[0802] Data entry

[0803] Users use their devices to input their test results, evaluations, learning history, and emotional state. For example, they might input "Mathematics 90 points" as a test result, "English B" as an evaluation, "3 hours of math study per week" as a learning history, and "Recent stress levels are high" as an emotional state. This data is sent to the server via the device.

[0804] Sending data

[0805] The terminal converts the data entered by the user into JSON or XML format and sends it to the server. The data is encrypted in transit, ensuring secure communication.

[0806] Data preprocessing

[0807] The server receives data sent from the terminal and stores it in a temporary database. It then performs preprocessing such as imputing missing data (e.g., using the mean or median) and normalizing the data (unifying different scales). It also verifies data integrity and removes inappropriate data.

[0808] Identifying your strengths and weaknesses

[0809] The server uses pre-processed data and applies machine learning algorithms (e.g., random forest, support vector machine) to identify the user's strong and weak subjects. For example, if a user scores highly in mathematics and low in English, it will be determined that "mathematics is a strong subject" and "English is a weak subject."

[0810] emotion recognition

[0811] The server uses an emotion engine to estimate the user's emotions at the time of learning (e.g., stress level and satisfaction level) based on emotion data entered by the user and their learning history.

[0812] Suggestions for exam preparation

[0813] The server suggests test preparation strategies based on identified strengths and weaknesses. For example, it provides video tutorials and additional practice problems for English, which is a weak subject, and application problems and mock exams for mathematics, which is a strong subject. It also suggests relaxation methods based on emotional data if stress levels are high.

[0814] Recommended schools

[0815] The server matches information on the user's strengths in subjects and their potential educational paths to select the most suitable university from the database. For example, it might suggest a specific university, such as "For a user who excels in mathematics and has high emotional stability, we recommend a science and engineering-related university's information science department."

[0816] Generating and displaying feedback

[0817] The server generates feedback data based on the user's strengths and weaknesses in subjects, as well as emotional data. This feedback data includes exam preparation based on strengths and weaknesses, recommendations for higher education, and emotional advice. The generated feedback data is sent to the device and displayed in a format that the user can view. For example, it may display specific advice such as "Watch English video tutorials for 30 minutes every day" or "Solve applied math problems every weekend," as well as emotional advice such as "Take a short break because your stress level is high."

[0818] Specific example

[0819] User input example

[0820] Test results: Math 90 points, English 70 points, Science 85 points

[0821] Grades: Math A, English B, Science A

[0822] Learning history: Data from the past year

[0823] Emotional state: High stress levels recently

[0824] Server Processing Example

[0825] Data collection: Collect user test results, ratings, learning history, and sentiment status.

[0826] Data preprocessing: Imputation of missing values, normalization of data

[0827] Identifying my strong and weak subjects: My strong subject is "Mathematics," and my weak subject is "English."

[0828] Suggestions for exam preparation: "Watch English video tutorials for 30 minutes every day" and "Solve applied math problems every weekend."

[0829] Recommended university: "Information science department at a science and engineering university"

[0830] Utilizing the emotional engine: Due to high stress levels, "take short breaks."

[0831] Example of terminal output

[0832] We recommend that users "watch English video tutorials for 30 minutes every day" and "solve applied math problems every weekend."

[0833] Provide users with information on admissions to the "Information Science Department of a science and engineering university."

[0834] We recommend that users take short breaks to relax because their stress levels are high.

[0835] Example of a prompt

[0836] "Based on the entered test results and evaluation data, identify the user's strengths and weaknesses in different subjects. Furthermore, consider the user's learning history and emotional state to generate feedback messages that provide appropriate test preparation strategies and recommendations for further education."

[0837] The flow of the specific processing in Example 2 will be explained using Figure 13.

[0838] Step 1: User data entry

[0839] Users input their test results, evaluations, learning history, and emotional state through their device. Specific input examples include: "I scored 90 points on last year's math exam," "My English grade is a B," "I studied math for 3 hours a week," and "My stress level has been high recently." Once this data is entered into the device, the process proceeds to the next step.

[0840] Input: Test results, evaluation, learning history, emotional state

[0841] Output: User data entered into the terminal

[0842] Step 2: Data transmission by the terminal

[0843] The terminal converts the data entered by the user into JSON or XML format and sends it to the server. Data is encrypted during transmission to ensure secure communication.

[0844] Input: User data entered into the terminal

[0845] Output: Data in JSON or XML format sent to the server

[0846] Step 3: Server-based data collection and preprocessing

[0847] The server receives data sent from the terminal and stores it in a temporary database. It then performs preprocessing such as imputing missing data (using mean or median values) and normalizing the data (unifying different scales). It also verifies data integrity and removes inappropriate data.

[0848] Input: Data in JSON or XML format received by the server

[0849] Output: Preprocessed user data

[0850] Step 4: Server identifies strengths and weaknesses in subjects

[0851] The server uses pre-processed data to apply machine learning algorithms (e.g., random forest, support vector machine) to identify the user's strong and weak subjects. For example, if a user scores highly in mathematics and low in English, it will be determined that "mathematics is a strong subject" and "English is a weak subject."

[0852] Input: Preprocessed user data

[0853] Output: Identified strong subjects and subjects with high earnings

[0854] Step 5: Emotion Recognition by Server

[0855] The server uses an emotion engine to estimate emotions (e.g., stress levels and satisfaction levels) from emotion data and learning history obtained from users. For example, it analyzes emotions using natural language processing and facial recognition technology.

[0856] Input: User sentiment data, learning history

[0857] Output: Estimated emotions (stress level, satisfaction level, etc.)

[0858] Step 6: Server-based test preparation suggestions

[0859] The server suggests test preparation strategies based on identified strengths and weaknesses. For example, it provides video tutorials and additional practice problems for English, which is a weak subject, and application problems and mock exams for mathematics, which is a strong subject. It also suggests relaxation methods based on emotional data if stress levels are high.

[0860] Input: Identified strengths and weaknesses in subjects, estimated sentiment data

[0861] Output: Proposed exam preparation

[0862] Step 7: Server-based recommendation of educational institutions

[0863] The server matches information on the user's strengths in subjects and their desired educational institutions to select the most suitable institution from the database. For example, it might suggest a specific institution such as, "For a user who excels in mathematics and has high emotional stability, we recommend a science and engineering-related university's information science department."

[0864] Input: Strong subjects and weak subjects, and college admissions information database

[0865] Output: Recommended schools to attend

[0866] Step 8: Server generates feedback data

[0867] The server generates feedback data based on identified strengths and weaknesses in subjects, as well as emotional data. This feedback data includes test preparation tips, recommendations for higher education institutions, and emotionally-based advice.

[0868] Input: Identified strengths and weaknesses in subjects, emotional data

[0869] Output: Feedback data

[0870] Step 9: Displaying user feedback via the device

[0871] The device displays feedback data received from the server to the user. Specifically, it displays concrete advice such as "Watch English video tutorials for 30 minutes every day" and "Solve applied math problems every weekend," as well as emotion-based advice such as "Take a short break because your stress level is high."

[0872] Input: Feedback data received from the server

[0873] Output: Feedback presented to the user

[0874] Step 10: User creates learning plan

[0875] Users review feedback data through their devices and create learning plans based on it. They implement recommended test preparation strategies and leverage the emotional engine's advice to create plans that maximize learning efficiency. They reassess their emotional state in a timely manner and adjust their learning methods as needed.

[0876] Input: Feedback data

[0877] Output: Newly created study plan

[0878] (Application Example 2)

[0879] Next, we will explain application example 2. In the following explanation, the data processing device 12 will be referred to as the "server," and the smart glasses 214 will be referred to as the "terminal."

[0880] Traditional learning support systems identified a user's strengths and weaknesses based on their test results and learning history, and then provided learning support accordingly. However, learning support provided without considering the user's emotional state had the problem of not reflecting the user's stress level or satisfaction level, resulting in ineffective learning support. Furthermore, similarly, product recommendations lacked personalization that took the user's emotional state into account, resulting in insufficient user satisfaction.

[0881] The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means.

[0882] In this invention, the server includes means for receiving test results, evaluations, learning history, and sentiment data from the user; means for pre-processing the received data; and means for identifying the user's strong and weak subjects based on the pre-processed data. This enables personalized test preparation and product recommendations that take the user's emotions into consideration.

[0883] Definitions of important words

[0884] "Test results" refer to data showing the scores and evaluations of tests taken by a user within a certain period of time.

[0885] "Evaluation" refers to the grades and feedback given based on the user's test results and learning progress.

[0886] "Learning history" refers to a record of a user's past learning activities, including data such as study time and learning materials used.

[0887] "Emotional data" refers to data that indicates a user's emotional state, including parameters such as stress levels and satisfaction levels.

[0888] "Preprocessing" refers to the process of modifying received data, such as imputing missing values ​​or normalizing the data.

[0889] A "favorite subject" is a subject in which a user consistently scores or receives high marks compared to other subjects.

[0890] A "subject a user struggles with" is a subject in which the user consistently scores or receives lower marks compared to other subjects.

[0891] "Exam preparation" refers to learning support methods and materials provided based on the user's strengths and weaknesses in different subjects.

[0892] "Recommended educational institution" refers to the educational institution or faculty that the user is advised to pursue next.

[0893] An "emotion recognition engine" is a system that estimates and analyzes emotions based on user input data and learning history.

[0894] "Feedback data" refers to data that includes advice and recommendations provided to users.

[0895] Modes for carrying out the invention

[0896] The system of this invention identifies the user's strengths and weaknesses in subjects based on their learning history and emotional data, and provides personalized learning support. The main components of this system include a terminal where the user inputs data, a server that processes and analyzes the data, and a terminal that receives feedback from the server.

[0897] System Overview

[0898] User: Input Data

[0899] Users input test results, evaluations, learning history, and sentiment data into the system via their devices. For example, they might input data such as "I scored 90 on last year's math exam," "My English grade is a B," "I studied math for 3 hours a week," and "My stress level has been high recently."

[0900] Terminal: Data transmission

[0901] The terminal sends the entered data to the server. The data is sent in an appropriate format, such as JSON or XML, ensuring that the server receives the data accurately.

[0902] Server: Data processing and preprocessing

[0903] The server receives data sent from the terminal and stores it in a temporary database. It then performs preprocessing such as imputing missing data and normalizing the data.

[0904] Server: Identifying strong and weak subjects

[0905] Based on the pre-processed data, the server uses machine learning algorithms (such as random forests or support vector machines) to identify subjects the student excels at and subjects they struggle with. Subjects with high scores are classified as "strong subjects," and subjects with low scores are classified as "weak subjects."

[0906] Server: Emotion analysis by emotion recognition engine

[0907] The server uses an emotion recognition engine to analyze the user's emotional state. For example, it analyzes stress levels and satisfaction levels during learning, and uses this emotional data to support learning.

[0908] Server: Providing exam preparation suggestions and recommendations for higher education institutions.

[0909] The server suggests exam preparation strategies based on identified strengths and weaknesses, and also selects potential universities from its database. For example, it might suggest specific strategies such as "watch 30 minutes of English video tutorials daily" or "solve applied math problems every weekend." It can also recommend a "Department of Information Science at a science and engineering university" as a suitable university.

[0910] Server: Feedback to users

[0911] The server generates feedback data based on previous analysis results, exam preparation suggestions, and recommended educational institutions. This feedback data also includes advice based on the user's emotional state.

[0912] Device: Show feedback

[0913] The device displays feedback received from the server to the user. For example, it might show advice such as "Watch English video tutorials for 30 minutes every day," "Solve applied math problems every weekend," or "Consider applying to the information science department of a science and engineering university." It might also recommend "Take a short break because your stress level is high."

[0914] Hardware and software to be used

[0915] The system uses the following hardware and software:

[0916] Hardware: Servers, user terminals (smartphones and tablets)

[0917] Software: Machine learning algorithms (random forest, support vector machine), database system, sentiment recognition engine

[0918] Specific example

[0919] User A enters the following data through the terminal:

[0920] Test results: Math 90 points, English 70 points

[0921] Grades: Math A, English B

[0922] Learning history: Math study time 3 hours / week

[0923] Emotional state: High stress level

[0924] The server receives this data, performs preprocessing, and then identifies the user's strengths and weaknesses. Considering learning history and sentiment data, it provides specific advice to the user, such as "watch English video tutorials for 30 minutes every day" or "a science and engineering university's information science department would be suitable for you."

[0925] Example of a prompt

[0926] "User A's purchase history includes electronic products (rated 5 stars) and books (rated 3 stars). They also have a high stress level recently. Please recommend products suitable for User A."

[0927] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[0928] Program processing steps

[0929] Step 1: Enter and submit user data.

[0930] Users input test results, evaluations, learning history, and sentiment data through their devices. This includes specific scores, evaluations, past learning time, and recent sentiment status. The devices then send this data to the server in JSON or XML format.

[0931] Input: User test results, evaluations, learning history, sentiment data

[0932] Output: Data in JSON or XML format provided by the terminal.

[0933] Specific operation: The user enters information into each field within the application and presses the "Submit" button.

[0934] Step 2: Server receives and temporarily stores data.

[0935] The server receives data sent from the terminal and stores it in a temporary database. This data is used in subsequent processing steps.

[0936] Input: User data in JSON or XML format

[0937] Output: Raw data stored in the database

[0938] Specific operation: The server receives requests at a specific API endpoint and saves the received data to the database.

[0939] Step 3: Data Preprocessing

[0940] The server performs preprocessing on the temporarily stored data, such as imputing missing data and normalizing the data. Specifically, it uses Python libraries (e.g., pandas, scikit-learn) to format the data.

[0941] Input: Raw data

[0942] Output: Preprocessed dataset

[0943] Specific operation: The server executes a script to impute missing values ​​(e.g., mean and median) and normalize the data.

[0944] Step 4: Identifying your strengths and weaknesses in different subjects

[0945] Based on the pre-processed data, the server uses machine learning algorithms (e.g., random forest, support vector machine) to identify the user's strengths and weaknesses in different subjects.

[0946] Input: Preprocessed dataset

[0947] Output: List of subjects you excel at and subjects you struggle with

[0948] Specific operation: The server uses a pre-trained model to make predictions and lists subjects the student excels at and struggles with.

[0949] Step 5: Emotion analysis using an emotion recognition engine

[0950] The server uses an emotion recognition engine to analyze the user's emotional state. This allows the user's stress level and satisfaction level to be understood numerically.

[0951] Input: User sentiment data

[0952] Output: Analyzed emotional data (e.g., stress level, satisfaction level)

[0953] Specific operation: The server invokes an emotion recognition engine, analyzes the input data, and obtains numerical values ​​for stress and satisfaction.

[0954] Step 6: Suggestions for exam preparation and recommendations for higher education options.

[0955] The server suggests optimal exam preparation strategies and educational options to the user based on their strengths and weaknesses in different subjects, as well as analyzed emotional data. This includes specific study methods and information on recommended educational institutions.

[0956] Input: Favorite subjects, least favorite subjects, analyzed emotional data

[0957] Output: Suggestions for exam preparation and a list of potential schools to attend.

[0958] Specific operation: The server uses an algorithm to provide the user with a suitable learning plan and educational options.

[0959] Step 7: Generate and send feedback

[0960] The server generates feedback data based on the analysis results so far and sends it to the terminal. This data includes recommendations for specific learning methods and schools to attend.

[0961] Input: Suggestions for exam preparation, list of universities to attend.

[0962] Output: User feedback data

[0963] Specific operation: The server sends the generated feedback to the terminal in JSON format.

[0964] Step 8: Displaying user feedback

[0965] The terminal displays feedback data received from the server to the user. This allows the user to obtain specific information on exam preparation and potential schools.

[0966] Input: Feedback data from the server

[0967] Output: Feedback information displayed on the terminal

[0968] Specific operation: The terminal analyzes the received data and displays it on the user interface.

[0969] This makes it possible for the present invention system to provide personalized learning support and product recommendations that take into account the user's emotions.

[0970] The specific processing unit 290 transmits the result of the specific processing to the smart glasses 214. In the smart glasses 214, the control unit 46A causes the speaker 240 to output the result of the specific processing. The microphone 238 acquires audio indicating user input for the result of the specific processing. The control unit 46A transmits the audio data indicating user input acquired by the microphone 238 to the data processing unit 12. In the data processing unit 12, the specific processing unit 290 acquires the audio data.

[0971] Data generation model 58 is a type of so-called generative AI (Artificial Intelligence). One example of data generation model 58 is ChatGPT (Internet search<URL: https: / / openai.com / blog / chatgpt> ), Gemini (Internet search) <url: https: gemini.google.com ?hl="ja">Examples of generative AI include those described above. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 is input with prompts containing instructions, and with inference data such as audio data representing speech, text data representing text, and image data representing images. The data generation model 58 infers from the input inference data according to the instructions shown by the prompts, and outputs the inference results in data formats such as audio data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[0972] In the above embodiment, an example was given in which specific processing is performed by the data processing device 12, but the technology of this disclosure is not limited thereto, and the specific processing may also be performed by the smart glasses 214.

[0973] [Third Embodiment]

[0974] Figure 5 shows an example of the configuration of the data processing system 310 according to the third embodiment.

[0975] As shown in Figure 5, the data processing system 310 includes a data processing device 12 and a headset terminal 314. An example of the data processing device 12 is a server.

[0976] The data processing device 12 comprises a computer 22, a database 24, and a communication interface 26. The computer 22 is an example of a "computer" related to the technology of this disclosure. The computer 22 comprises a processor 28, RAM 30, and storage 32. The processor 28, RAM 30, and storage 32 are connected to a bus 34. The database 24 and the communication interface 26 are also connected to the bus 34. The communication interface 26 is connected to a network 54. An example of the network 54 is a WAN (Wide Area Network) and / or a LAN (Local Area Network).

[0977] The headset terminal 314 includes a computer 36, a microphone 238, a speaker 240, a camera 42, a communication interface 44, and a display 343. The computer 36 includes a processor 46, RAM 48, and storage 50. The processor 46, RAM 48, and storage 50 are connected to a bus 52. The microphone 238, speaker 240, camera 42, and display 343 are also connected to the bus 52.

[0978] The microphone 238 receives voice signals from the user 20 and receives instructions from the user 20. The microphone 238 captures the voice signals from the user 20, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio according to the instructions from the processor 46.

[0979] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an image sensor such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, and captures images of the area around the user 20 (for example, an imaging range defined by a field of view equivalent to the width of a typical healthy person's field of vision).

[0980] Communication interface 44 is connected to network 54. Communication interfaces 44 and 26 are responsible for the exchange of various information between processor 46 and processor 28 via network 54. The exchange of various information between processor 46 and processor 28 using communication interfaces 44 and 26 is performed in a secure manner.

[0981] Figure 6 shows an example of the main functions of the data processing device 12 and the headset terminal 314. As shown in Figure 6, the data processing device 12 performs specific processing using the processor 28. The storage 32 stores the specific processing program 56.

[0982] The specific processing program 56 is an example of a "program" relating to the technology of this disclosure. The processor 28 reads the specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific processing is realized by the processor 28 operating as a specific processing unit 290 in accordance with the specific processing program 56 executed on the RAM 30.

[0983] The storage 32 stores the data generation model 58 and the emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290.

[0984] In the headset terminal 314, the processor 46 performs the reception output processing. The storage 50 stores the reception output program 60. The processor 46 reads the reception output program 60 from the storage 50 and executes the read reception output program 60 on the RAM 48. The reception output processing is realized by the processor 46 operating as a control unit 46A according to the reception output program 60 executed on the RAM 48.

[0985] Next, the specific processing performed by the specific processing unit 290 of the data processing device 12 will be described. In the following description, the data processing device 12 will be referred to as the "server" and the headset terminal 314 will be referred to as the "terminal".

[0986] The system of this invention analyzes a user's strengths and weaknesses in different subjects and provides exam preparation strategies and recommendations for higher education based on that analysis. This system mainly consists of a terminal where the user inputs data, a server that processes and analyzes the data, and a terminal that receives feedback from the server.

[0987] System Overview

[0988] User: Data entry

[0989] Users input test results, evaluations, and learning history into the system via their devices. For example, they might input specific data such as, "I got 90 points on last year's math exam," or "My English grade was a B."

[0990] Terminal: Data transmission

[0991] The terminal sends the entered data to the server. When sending the data, it is important to send it in an appropriate format (such as JSON or XML) so that the server can receive the data accurately.

[0992] Server: Data collection and preprocessing

[0993] The server collects data sent from the terminal and stores it in a temporary data store. Then, it performs preprocessing on the collected data. Specifically, it imputes missing values ​​with the mean or median, and normalizes data from different scales to unify them.

[0994] Server: Identifying strong and weak subjects

[0995] Based on the pre-processed data, the server identifies the user's strong and weak subjects. Here, machine learning algorithms (e.g., random forest or support vector machine) are used to analyze the scoring patterns for each subject. Subjects with high scores are identified as "strong subjects," and subjects with low scores are identified as "weak subjects."

[0996] Server: Suggestions for exam preparation

[0997] The server suggests exam preparation strategies based on identified strengths and weaknesses. For example, it recommends video tutorials and additional practice problems for weak subjects, and provides application problems and mock exams for strong subjects. Specifically, this might include suggestions like "watch a 30-minute English video tutorial every day" or "solve application problems in mathematics on the weekend."

[0998] Server: Recommended by the school you will be attending

[0999] The server matches the user's strengths in subjects with information on potential universities. Considering the user's strengths and interests, it selects the most suitable university from the database. For example, it might suggest a university like "A science and engineering university's information science department would be suitable because you excel in mathematics."

[1000] Server: Generating feedback data

[1001] The server generates feedback data based on previous analysis results, suggested exam preparation strategies, and recommended educational institutions. This feedback data is then provided to the user.

[1002] Device: Displaying feedback to the user

[1003] The device displays feedback data received from the server to the user. The displayed feedback includes specific details such as, "Your weakest subject is English. Watch English video tutorials for 30 minutes every day. Also, a computer science department at a science and engineering university would be a good fit for you."

[1004] User: Creating a study plan

[1005] Users create their own study plans based on feedback displayed on their devices. They can set specific study schedules and goals based on recommended test preparation and information about potential schools.

[1006] Specific example

[1007] 1. User input example

[1008] Test results: Math 90 points, English 70 points, Science 85 points

[1009] Grades: Math A, English B, Science A

[1010] Learning history: Data from the past year

[1011] 2. Example of server processing

[1012] Data collection: Collect user test results, evaluations, and learning history.

[1013] Data preprocessing: Imputation of missing values, normalization of statistical data.

[1014] Identifying my strong and weak subjects: My strong subject is "Mathematics," and my weak subject is "English."

[1015] Suggestions for exam preparation: "Watch English video tutorials for 30 minutes every day" and "Solve applied math problems every weekend."

[1016] Recommended university: "Information science department at a science and engineering university"

[1017] 3. Example of terminal output

[1018] We recommend that users "watch English video tutorials for 30 minutes every day" and "solve applied math problems every weekend."

[1019] Provide users with information on admissions to the "Information Science Department of a science and engineering university."

[1020] This allows users to prepare for exams best suited to their individual strengths and choose the appropriate educational institution. In this way, users can create more effective study plans and gain an advantage in future educational and career choices.

[1021] The following describes the processing flow.

[1022] Step 1:

[1023] Users use their devices to input their test results, grades, and learning history. For example, they might input specific data such as "I scored 90 points on last year's math exam," "My English grade was a B," and "I studied math for 3 hours a week."

[1024] Step 2:

[1025] The terminal sends data entered by the user to the server. This input data is often sent in formats such as JSON or XML.

[1026] Step 3:

[1027] The server receives data sent from the terminal and stores it in a temporary database. Here, it checks the data's integrity and sends an error message to the terminal if any inconsistencies are found.

[1028] Step 4:

[1029] The server preprocesses the collected data. Specifically, it performs data imputation (such as imputing with the mean or median) and data normalization (unifying different scales).

[1030] Step 5:

[1031] Based on pre-processed data, the server uses machine learning algorithms to identify the user's strong and weak subjects. For example, it might use a random forest or support vector machine to analyze the user's scoring patterns, identifying subjects with high scores as "strong subjects" and subjects with low scores as "weak subjects."

[1032] Step 6:

[1033] Based on the user's identified strengths and weaknesses in different subjects, the server suggests exam preparation strategies. For example, it might generate specific strategies such as "Watch English video tutorials for 30 minutes every day" or "Solve applied math problems every weekend."

[1034] Step 7:

[1035] The server matches the user's strengths in subjects with information on potential universities and selects the most suitable university from the database. For example, it might identify a university with a strong focus on science and engineering, such as "a science and engineering university's information science department, as the user excels in mathematics."

[1036] Step 8:

[1037] The server generates feedback data based on previous analysis results, suggested exam preparation strategies, and recommended educational institutions. This feedback data serves as a reference for users to create concrete study plans.

[1038] Step 9:

[1039] The device displays feedback data received from the server to the user. For example, it might display specific advice such as, "Watch English video tutorials for 30 minutes every day," or "A science and engineering university's information science department would be suitable."

[1040] Step 10:

[1041] Users create a specific study plan based on feedback displayed on their device. They then implement recommended test preparation strategies and progress towards their goals.

[1042] (Example 1)

[1043] Next, we will describe Example 1. In the following description, the data processing device 12 will be referred to as the "server," and the headset-type terminal 314 will be referred to as the "terminal."

[1044] Traditional educational support systems struggle to accurately identify each user's individual learning situation, strengths, and weaknesses, and to provide appropriate test preparation and recommendations for higher education based on that information. In particular, insufficient preprocessing, such as imputing missing values ​​or unifying data from different scales, prevents accurate analysis. Furthermore, the suggested test preparation and educational recommendations are often vague and therefore impractical for users.

[1045] The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 1 is realized by the following means.

[1046] In this invention, the server includes means for receiving education-related data (test results, evaluations, learning history) from the user, means for preprocessing the received data, means for normalizing the data and imputing missing values, means for identifying the user's strengths and weaknesses based on the preprocessed data, means for identifying them using machine learning algorithms (e.g., random forest or support vector machine), means for proposing educational support based on the identified strengths and weaknesses, means for recommending educational institutions based on the strengths and weaknesses, and means for displaying the proposed educational support and educational institutions to the user. This enables accurate learning analysis tailored to the user's individual circumstances and specific and effective recommendations for test preparation and further education.

[1047] "Education-related data" refers to the totality of information related to a user's learning, including test results, evaluations, and learning history.

[1048] "Preprocessing" is the process of converting received data into a format that can be properly analyzed. Specifically, this involves tasks such as imputing missing values ​​and normalizing the data.

[1049] "Normalization" is a process for unifying data at different scales, and is a means of making data comparison and analysis easier.

[1050] "Missing value imputation" is the procedure of filling in missing data in a dataset using a specific method (e.g., the mean or median).

[1051] A "machine learning algorithm" is a mathematical model used to analyze patterns in data and make predictions or classifications based on specific objectives.

[1052] "Areas of expertise" refers to learning areas where a user demonstrates particularly high performance.

[1053] A "weakness area" refers to a learning area where a user shows relatively low performance.

[1054] "Educational support" is a general term for the support provided to achieve specific learning objectives, and specifically includes study plans, practice problems, video tutorials, and so on.

[1055] "Educational institutions" refers to all learning facilities and educational programs related to a user's learning or further education.

[1056] "Feedback data" refers to information that includes advice and recommendations generated based on the user's learning progress, strengths, and weaknesses.

[1057] Users input educational data using a terminal. Specifically, they input information such as test results, evaluations, and learning history, and this information is sent to the system. The terminal is equipped with at least a user interface for inputting data and a function to convert that data into an appropriate format (e.g., JSON or XML) and send it.

[1058] Data sent from the terminal is received by the server. This server preprocesses the data by storing it in a temporary data store, and then performs tasks such as imputing missing values ​​and normalizing the data. This process ensures data consistency and enables accurate analysis.

[1059] The pre-processed data is used on the server to identify areas of strength and weakness. Machine learning algorithms such as random forests and support vector machines are applied here. This identifies areas where the user performs well as "strengths" and areas where performance is poor as "weaknesses."

[1060] The server then proposes specific educational support based on these identified strengths and weaknesses. For example, for English, which is a weak area, it might suggest "watching 30 minutes of English video tutorials every day," and for mathematics, which is a strong area, it might suggest "solving applied math problems on weekends."

[1061] Furthermore, the server matches the user's areas of expertise with information about their educational background to recommend the most suitable institution. For example, it might recommend a "Department of Information Science at a science and engineering university" to a user who excels in mathematics. This recommendation information is also provided to the user as part of the feedback.

[1062] These analysis results, suggestions, and recommendations for higher education are generated as feedback data and provided to the user. The device displays this feedback data to the user. The displayed content includes specific instructions such as, "Your weak area is English. Please watch English video tutorials for 30 minutes every day. Also, the information science department of a science and engineering university would be suitable for you."

[1063] Users can use this feedback data to set specific learning plans. For example, they can create action plans such as "watch 30 minutes of English video tutorials every day" or "solve applied math problems on weekends."

[1064] Example of a prompt

[1065] 1. "Based on your learning history over the past year, identify your strengths and weaknesses in different subjects, and then propose exam preparation strategies and college options accordingly."

[1066] 2. "Analyze the test results, evaluations, and learning history entered by the user, and recommend the most suitable test preparation methods and educational institutions."

[1067] This allows users to receive educational support best suited to their circumstances and choose the appropriate educational institution. Users can also develop more effective study plans and be in a more advantageous position when choosing future education or careers.

[1068] The flow of the specific processing in Example 1 will be explained using Figure 11.

[1069] Step 1:

[1070] Users input educational data using their devices. Specifically, they input information such as test results, grades, and learning history. For example, they might input data such as "I got 90 points on last year's math exam" or "My English grade was a B."

[1071] Input: Test results, evaluation, learning history

[1072] Output: Educational data stored in the device's temporary data store.

[1073] Step 2:

[1074] The terminal converts the input data into an appropriate format (e.g., JSON or XML) and sends it to the server. Before sending the data, it verifies that the data is formatted correctly.

[1075] Input: Educational data stored on the device

[1076] Output: Send formatted educational data (in JSON or XML format) to the server.

[1077] Step 3:

[1078] The server stores the data received from the terminal in a temporary data store and begins data preprocessing. First, it imputes any missing values ​​and normalizes the data. This is done using missing value imputation algorithms and normalization algorithms. For example, missing test result values ​​are imputed with the average value for that subject.

[1079] Input: Formatted education-related data

[1080] Output: Preprocessed education-related data (missing values ​​imputed, normalized)

[1081] Step 4:

[1082] The server uses pre-processed data to identify the user's strengths and weaknesses. Machine learning algorithms such as random forests and support vector machines are used here. For example, if a user scores highly in math and low in English, math is identified as a strength and English as a weakness.

[1083] Input: Preprocessed education-related data

[1084] Output: User's strengths and weaknesses

[1085] Step 5:

[1086] Based on the user's strengths and weaknesses, the server proposes specific educational support. For example, it might suggest "watching 30 minutes of English video tutorials daily" to a user who struggles with English, or "solving applied math problems on weekends" to a user who excels at math.

[1087] Input: User's strengths and weaknesses

[1088] Output: Suggestions for educational support tailored to the user.

[1089] Step 6:

[1090] The server matches the user's areas of expertise with educational institution information to recommend the most suitable institution. For example, a user who excels in mathematics would be recommended a "Department of Information Science at a science and engineering university."

[1091] Input: User's areas of expertise and educational institution information

[1092] Output: Recommendations for the most suitable educational institutions for the user.

[1093] Step 7:

[1094] The server compiles the analysis results, exam preparation suggestions, and recommended schools to generate feedback data. This feedback data is provided to the user.

[1095] Input: Areas of expertise and weaknesses, suggestions for educational support, recommendations for educational institutions.

[1096] Output: Feedback data

[1097] Step 8:

[1098] The terminal displays feedback data received from the server to the user. The displayed content includes specific instructions such as, "Your weak point is English. Watch English video tutorials for 30 minutes every day. Also, a computer science department at a science and engineering university would be a good fit for you."

[1099] Input: Feedback data

[1100] Output: Specific feedback displayed to the user

[1101] Step 9:

[1102] Users create their own learning plans based on feedback from their devices. They set specific study schedules and goals based on recommended test preparation and educational institution information. For example, they might create action plans such as "watch 30 minutes of English video tutorials every day" or "solve applied math problems on weekends."

[1103] Input: Feedback data

[1104] Output: Specific learning plan set by the user

[1105] (Application Example 1)

[1106] Next, we will explain Application Example 1. In the following explanation, the data processing device 12 will be referred to as the "server," and the headset-type terminal 314 will be referred to as the "terminal."

[1107] In modern education systems, providing appropriate learning support based on each student's strengths and weaknesses is crucial. However, traditional systems have made it difficult to comprehensively identify students' strengths and weaknesses, resulting in an inability to provide effective learning strategies. Furthermore, recommending appropriate educational institutions and suggesting individually optimized educational content has been challenging. This has led to problems such as students being unable to create a suitable learning plan, resulting in decreased learning efficiency and motivation.

[1108] The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 1 is realized by the following means.

[1109] In this invention, the server includes means for recommending appropriate learning content based on the user's strengths and weaknesses; means for receiving test results, evaluations, and learning history from the user; means for pre-processing the received data; means for identifying the user's strengths and weaknesses based on the pre-processed data; means for suggesting test preparation strategies based on the strengths and weaknesses; means for recommending higher education options based on the strengths and weaknesses; means for displaying the suggested test preparation strategies and higher education options to the user; and means for transmitting data from the user's terminal to the server and receiving feedback from the server. This enables the suggestion of educational content optimized for individual students, and allows for effective learning strategies and recommendations for higher education options.

[1110] A "user" is an individual who uses the system to input data such as test results, evaluations, and learning history, and receives learning support and recommendations for further education.

[1111] "Test results" refer to data that shows the scores and grades a user obtained in each subject of the exam.

[1112] "Evaluation" refers to data that indicates a teacher's or educational institution's assessment of a user's learning performance, and is usually represented by letters or numbers.

[1113] "Learning history" refers to data that records a user's past learning activities and performance.

[1114] "Means of receiving data" refers to devices or software that have the function of acquiring data entered by the user and sending it to the server.

[1115] "Preprocessing methods" refer to devices or software used to prepare received data for analysis by imputing missing values ​​and normalizing the data.

[1116] "Means of identification" refers to devices or software that have the function of identifying a user's strong and weak subjects based on pre-processed data.

[1117] "Machine learning algorithm" is a term that refers to an algorithm used by computers to learn from data and recognize patterns.

[1118] "Means of suggesting exam preparation strategies" refers to devices or software that have the function of recommending learning methods and materials suitable for the user based on their identified strengths and weaknesses in different subjects.

[1119] "Means of recommending educational institutions" refers to devices or software that have the function of suggesting the most suitable educational institutions based on the user's strengths and interests.

[1120] "Feedback data" refers to data that includes summaries of information provided to users, such as exam preparation strategies and recommendations for higher education institutions.

[1121] "Means of displaying to the user" refers to devices or software that visually present feedback data received from the server to the user.

[1122] "Means for recommending appropriate learning content" refers to devices or software that suggest optimal educational content based on the user's learning needs and current proficiency level.

[1123] A "terminal" is a device used by a user to input data and communicate with a server, and includes smartphones, tablets, and personal computers.

[1124] This invention is a system that analyzes a user's strengths and weaknesses in different subjects and provides exam preparation strategies and recommendations for higher education based on that analysis. The following describes an embodiment of the system in detail.

[1125] User data entry

[1126] Users input data such as test results, evaluations, and learning history using devices such as smartphones, tablets, or personal computers. This data includes specific information such as, "I scored 90 points on last year's math exam," or "My English grade is a B."

[1127] Data transmission and preprocessing

[1128] The terminal sends the data entered by the user to the server in JSON format or another appropriate format. The server temporarily stores the received data and performs preprocessing such as imputing missing values ​​and normalizing the data. Python libraries such as Pandas and Scikit-learn are used for this process.

[1129] Identifying your strengths and weaknesses in different subjects.

[1130] The server uses machine learning algorithms to identify strong and weak subjects based on pre-processed data. For example, algorithms such as Random Forest and Support Vector Machine (SVM) are used. This allows the system to identify subjects with high scores as "strong subjects" and subjects with low scores as "weak subjects."

[1131] Exam preparation and suggestions for higher education options

[1132] The server suggests appropriate exam preparation based on the user's strengths and weaknesses. For example, it generates specific study plans such as "watch English video tutorials for 30 minutes every day" or "solve applied math problems on weekends." It also matches the user's strengths with information on potential universities to recommend the most suitable institutions. For example, if the user's strength is mathematics, it might suggest "a computer science department at a science and engineering university would be a good fit."

[1133] Displaying feedback

[1134] The feedback data generated by the server is sent to the terminal in real time and displayed to the user. Users can use this feedback to create their study plans. Because the feedback includes specific study strategies and information on potential schools, users can study more effectively.

[1135] Specific examples and prompt statements

[1136] As a concrete example, consider the case where the user's input data was as follows:

[1137] Test results: Math 90 points, English 70 points, Science 85 points

[1138] Grades: Math A, English B, Science A

[1139] Learning history: Data from the past year

[1140] Server processing example:

[1141] Data Collection and Preprocessing: Collect user test results, evaluations, and training history, and perform data imputation and normalization.

[1142] Identifying strengths and weaknesses: Analyzed strengths as "mathematics" and weaknesses as "English".

[1143] Suggestions for exam preparation: "Watch English video tutorials for 30 minutes every day," "Solve applied math problems every weekend," etc.

[1144] Recommended university: We recommend the Faculty of Information Science at a science and engineering university.

[1145] Examples of prompts for a generative AI model:

[1146] "Develop a system that analyzes a user's strengths and weaknesses in specific subjects based on their test results, evaluations, and learning history. Based on these results, it will suggest appropriate learning content and also provide information on potential higher education options. The following is an example of user input."

[1147] Test results: Math 90 points, English 70 points, Science 85 points

[1148] Grades: Math A, English B, Science A

[1149] Learning history: Data from the past year

[1150] Based on this data, please identify the student's strengths and weaknesses in different subjects and provide feedback on specific study plans and potential educational paths.

[1151] As described above, the present invention provides optimal learning support to individual users and constructs a system that enables improved learning efficiency and appropriate choices for further education.

[1152] The flow of a specific process in Application Example 1 will be explained using Figure 12.

[1153] Step 1:

[1154] Users input data such as test results, evaluations, and learning history using a device (smartphone, tablet, or PC). Specifically, they input test results such as 90 points in mathematics, 70 points in English, and 85 points in science, as well as evaluations for each subject (e.g., Mathematics A, English B, Science A).

[1155] Input: Test results, evaluation, learning history

[1156] Output: User data in JSON format

[1157] Step 2:

[1158] The terminal converts the entered user data into JSON format and sends it to the server. It uses an HTTP POST request to send the data to the specified API endpoint.

[1159] Input: User data in JSON format

[1160] Output: Results of sending data to the server

[1161] Step 3:

[1162] The server temporarily stores the received data. Then, it performs preprocessing such as imputing missing values ​​and normalizing the data. Here, data cleaning is performed using Pandas or Scikit-learn.

[1163] Input: User data in JSON format

[1164] Output: Preprocessed data

[1165] Step 4:

[1166] The server applies machine learning algorithms (e.g., Random Forest or SVM) to preprocessed data to identify subjects in which the user excels and struggles. This allows for an analysis of academic performance trends for each subject, thereby identifying strengths and weaknesses.

[1167] Input: Preprocessed data

[1168] Output: Identification of strong and weak subjects

[1169] Step 5:

[1170] Based on the identification of the user's strengths and weaknesses, the server suggests appropriate test preparation strategies. For example, it might suggest watching 30 minutes of video tutorials daily for English, which is a weak subject, and recommend solving application problems on weekends for mathematics, which is a strong subject.

[1171] Input: Results of identifying strong and weak subjects

[1172] Output: Suggestions for exam preparation

[1173] Step 6:

[1174] The server matches the user's preferred subjects and college application information to recommend the most suitable college. For example, if the user's preferred subject is mathematics, the server will suggest a computer science department at a science and engineering university as a college option.

[1175] Input: Database of preferred subjects and universities / schools attended

[1176] Output: Recommended content from prospective schools

[1177] Step 7:

[1178] The server generates feedback data, including exam preparation strategies and recommendations for higher education institutions, and sends it to the terminal in real time. The generated feedback data is packaged in a format that is easy for the user to review.

[1179] Input: Suggestions for exam preparation, recommendations for universities to attend.

[1180] Output: Feedback data

[1181] Step 8:

[1182] The device displays feedback data received from the server to the user. Based on this feedback data, the user can create their own learning plan. Specifically, concrete plans such as "watch English video tutorials for 30 minutes every day" or "solve applied math problems on the weekend" are provided.

[1183] Input: Feedback data

[1184] Output: Displaying feedback to the user

[1185] Furthermore, an emotion engine that estimates the user's emotions may be incorporated. That is, the identification processing unit 290 may use the emotion identification model 59 to estimate the user's emotions and perform identification processing using the user's emotions.

[1186] The system of this invention analyzes a user's strengths and weaknesses in different subjects and provides exam preparation strategies and recommendations for higher education based on that analysis. Furthermore, it incorporates an emotion engine that recognizes the user's emotions to provide more personalized learning support. This system mainly consists of a terminal where the user inputs data, a server that processes and analyzes the data, and a terminal that receives feedback from the server.

[1187] System Overview

[1188] User: Data entry

[1189] Users input test results, evaluations, and learning history into the system via their devices. For example, they might input specific data such as "I scored 90 points on last year's math exam," "My English grade was a B," and "I studied math for 3 hours a week." Users can also input their emotional state.

[1190] Terminal: Data transmission

[1191] The terminal sends the entered data to the server. When sending the data, it is important to send it in an appropriate format (such as JSON or XML) so that the server can receive the data accurately.

[1192] Server: Data collection and preprocessing

[1193] The server receives data sent from the terminal and stores it in a temporary database. It then performs preprocessing on the collected data. Specifically, this includes imputing missing data (such as using the mean or median) and normalizing the data (unifying different scales).

[1194] Server: Identifying strong and weak subjects

[1195] Based on the pre-processed data, the server identifies the user's strong and weak subjects. Here, machine learning algorithms (e.g., random forest or support vector machine) are used to analyze the scoring patterns for each subject. Subjects with high scores are identified as "strong subjects," and subjects with low scores are identified as "weak subjects."

[1196] Server: Emotion recognition by emotion engine

[1197] The server uses an emotion engine to estimate user emotions from input data and learning history. For example, it analyzes stress levels and satisfaction levels during learning, and uses this emotional data to support learning.

[1198] Server: Suggestions for exam preparation

[1199] The server suggests exam preparation strategies based on identified strengths and weaknesses. For example, it provides video tutorials and additional practice problems for weak subjects, and application problems and mock exams for strong subjects. It also suggests learning methods to help users relax if they are experiencing stress.

[1200] Server: Recommended by the school you will be attending

[1201] The server matches the user's strengths in subjects with information on potential universities and selects the most suitable university from the database. For example, it might recommend a science and engineering university's information science department to a user who excels in mathematics and has high emotional stability.

[1202] Server: Generating feedback data

[1203] The server generates feedback data based on previous analysis results, suggested exam preparation strategies, and recommended educational institutions. This feedback data includes advice that takes the user's emotional state into consideration.

[1204] Device: Displaying feedback to the user

[1205] The device displays feedback data received from the server to the user. For example, it may display specific advice such as "Watch English video tutorials for 30 minutes every day" or "A science and engineering university's information science department would be suitable for you." It may also display emotion-based advice such as "Your stress levels have been high recently, so take short breaks to relax."

[1206] User: Creating a study plan

[1207] Users create their own learning plans based on feedback displayed on their devices. They implement recommended test preparation strategies and progress towards their goals. They can leverage emotionally driven advice to create plans that maximize learning effectiveness. They also reassess their emotional state in a timely manner and adjust their learning methods as needed.

[1208] Specific example

[1209] 1. User input example

[1210] Test results: Math 90 points, English 70 points, Science 85 points

[1211] Grades: Math A, English B, Science A

[1212] Learning history: Data from the past year

[1213] Emotional state: High stress levels recently

[1214] 2. Example of server processing

[1215] Data collection: Collect user test results, ratings, learning history, and sentiment status.

[1216] Data preprocessing: Imputation of missing values, normalization of statistical data.

[1217] Identifying my strong and weak subjects: My strong subject is "Mathematics," and my weak subject is "English."

[1218] Suggestions for exam preparation: "Watch English video tutorials for 30 minutes every day" and "Solve applied math problems every weekend."

[1219] Recommended university: "Information science department at a science and engineering university"

[1220] Utilizing the emotional engine: Due to high stress levels, "take short breaks."

[1221] 3. Example of terminal output

[1222] We recommend that users "watch English video tutorials for 30 minutes every day" and "solve applied math problems every weekend."

[1223] Provide users with information on admissions to the "Information Science Department of a science and engineering university."

[1224] We recommend that users take short breaks to relax because their stress levels are high.

[1225] This allows users to choose test preparation methods best suited to their individual characteristics and educational options that take their emotional state into consideration. In this way, users can create more effective study plans and gain an advantage in future educational and career choices.

[1226] The following describes the processing flow.

[1227] Step 1:

[1228] Users use their devices to input their test results, evaluations, and learning history. For example, they might input specific data such as "I scored 90 points on last year's math exam," "My English grade is a B," and "I studied math for 3 hours a week." They also input their emotional state (e.g., stress level).

[1229] Step 2:

[1230] The terminal sends data entered by the user to the server. When sending the data, it is important to send it in an appropriate format (e.g., JSON or XML) so that the server can receive the data accurately.

[1231] Step 3:

[1232] The server receives data sent from the terminal and stores it in a temporary database. Here, it checks the data's integrity and sends an error message to the terminal if any inconsistencies are found.

[1233] Step 4:

[1234] The server preprocesses the collected data. Specifically, it performs data imputation (such as imputing with the mean or median) and data normalization (unifying different scales).

[1235] Step 5:

[1236] Based on pre-processed data, the server uses machine learning algorithms to identify the user's strong and weak subjects. For example, it might use a random forest or support vector machine to analyze the user's scoring patterns, identifying subjects with high scores as "strong subjects" and subjects with low scores as "weak subjects."

[1237] Step 6:

[1238] The server uses an emotion engine to estimate the user's emotions from their input data and learning history. For example, it estimates stress levels from the user's learning time and pace, and evaluates their emotional stability.

[1239] Step 7:

[1240] Based on the server's identified strengths and weaknesses, it suggests exam preparation strategies. For example, it generates specific strategies such as "watch English video tutorials for 30 minutes every day" or "solve applied math problems every weekend." At the same time, it also suggests ways to reduce stress (e.g., "take short breaks") based on the user's emotional state.

[1241] Step 8:

[1242] The server matches the user's strengths in subjects with information on potential universities and selects the most suitable university from the database. For example, it might recommend a science and engineering university's information science department to a user who excels in mathematics and has high emotional stability.

[1243] Step 9:

[1244] The server generates feedback data based on previous analysis results, suggested exam preparation strategies, and recommended educational institutions. This feedback data includes advice that takes the user's emotional state into consideration.

[1245] Step 10:

[1246] The device displays feedback data received from the server to the user. For example, it may display specific advice such as "Watch English video tutorials for 30 minutes every day" or "A science and engineering university's information science department would be suitable for you." It may also display emotion-based advice such as "Your stress levels have been high recently, so take a short break to relax."

[1247] Step 11:

[1248] Users create their own study plans based on feedback displayed on their devices. They implement recommended test preparation strategies and progress towards their goals. They can utilize emotionally driven advice to create plans that maximize learning effectiveness. They also reassess their emotional state in a timely manner and adjust their learning methods as needed.

[1249] (Example 2)

[1250] Next, we will describe Example 2. In the following description, the data processing device 12 will be referred to as the "server," and the headset-type terminal 314 will be referred to as the "terminal."

[1251] Traditional learning support systems could identify a user's strengths and weaknesses based on their test results and evaluations, and suggest test preparation strategies and educational options. However, no system existed that adequately considered the user's emotional state while providing support. As a result, it was difficult to maximize the user's learning efficiency and motivation, and it was not possible to optimally address individual learning needs.

[1252] The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 2 is realized by the following means.

[1253] In this invention, the server includes means for receiving test results, evaluations, learning history, and emotional status from the user; means for pre-processing the received data; means for identifying the user's strong and weak subjects based on the pre-processed data; means for suggesting test preparation strategies based on the strong and weak subjects; means for recommending schools to attend based on the strong and weak subjects and emotional status; and means for presenting the user with the suggested test preparation strategies, schools to attend, and advice based on their emotional status. This makes it possible to optimally respond to individual learning needs while taking into account the user's emotional status, and to maximize learning efficiency and motivation.

[1254] A "user" refers to an end-user who uses the system to input test results, evaluations, learning history, and emotional status.

[1255] "Test results" refers to data showing the scores and performance of tests taken by the user.

[1256] "Evaluation" refers to data that shows the grades and ratings from teachers and educational institutions for subjects and assignments that a user has taken.

[1257] "Learning history" refers to the records and data of the learning activities a user has undertaken so far.

[1258] "Emotional state" refers to data that indicates the user's emotions and psychological state during learning.

[1259] "Data preprocessing" refers to the process of imputing missing values, normalizing data, and verifying data integrity in collected data.

[1260] A "favorite subject" refers to a subject in which the user has achieved high scores or evaluations.

[1261] A "subject a user struggles with" refers to a subject in which the user consistently achieves low scores or evaluations.

[1262] A "machine learning algorithm" refers to a mathematical model or computational method used to analyze large amounts of data and learn patterns and rules.

[1263] "Exam preparation" refers to learning methods and materials suggested to users to prepare for an exam.

[1264] "Recommended educational institution" refers to the educational institution or faculty that the user is advised to attend.

[1265] "Emotion-based advice" refers to advice on learning methods and stress management techniques that takes the user's emotional state into consideration.

[1266] "Feedback data" refers to data that provides users with a compilation of analysis results, exam preparation tips, recommendations for higher education institutions, and emotionally-based advice.

[1267] The system of this invention analyzes a user's strengths and weaknesses in different subjects and provides exam preparation strategies and recommendations for higher education based on that analysis. Furthermore, it incorporates an emotion engine that recognizes the user's emotions to provide more personalized learning support. This system consists of a terminal for the user to input data, a server that processes and analyzes the data, and a terminal that receives feedback from the server.

[1268] Hardware and software to be used

[1269] The following hardware and software are required to implement the system:

[1270] Devices: PC, smartphone, tablet, etc.

[1271] Server: High-performance computing server

[1272] Database Management Systems (DBMS): MySQL, PostgreSQL, etc.

[1273] Machine learning libraries: Scikit-learn, TensorFlow, etc.

[1274] Emotion recognition software: Emotion API, OpenVINO, etc.

[1275] Data entry

[1276] Users use their devices to input their test results, evaluations, learning history, and emotional state. For example, they might input "Mathematics 90 points" as a test result, "English B" as an evaluation, "3 hours of math study per week" as a learning history, and "Recent stress levels are high" as an emotional state. This data is sent to the server via the device.

[1277] Sending data

[1278] The terminal converts the data entered by the user into JSON or XML format and sends it to the server. The data is encrypted in transit, ensuring secure communication.

[1279] Data preprocessing

[1280] The server receives data sent from the terminal and stores it in a temporary database. It then performs preprocessing such as imputing missing data (e.g., using the mean or median) and normalizing the data (unifying different scales). It also verifies data integrity and removes inappropriate data.

[1281] Identifying your strengths and weaknesses

[1282] The server uses pre-processed data and applies machine learning algorithms (e.g., random forest, support vector machine) to identify the user's strong and weak subjects. For example, if a user scores highly in mathematics and low in English, it will be determined that "mathematics is a strong subject" and "English is a weak subject."

[1283] emotion recognition

[1284] The server uses an emotion engine to estimate the user's emotions at the time of learning (e.g., stress level and satisfaction level) based on emotion data entered by the user and their learning history.

[1285] Suggestions for exam preparation

[1286] The server suggests test preparation strategies based on identified strengths and weaknesses. For example, it provides video tutorials and additional practice problems for English, which is a weak subject, and application problems and mock exams for mathematics, which is a strong subject. It also suggests relaxation methods based on emotional data if stress levels are high.

[1287] Recommended schools

[1288] The server matches information on the user's strengths in subjects and their potential educational paths to select the most suitable university from the database. For example, it might suggest a specific university, such as "For a user who excels in mathematics and has high emotional stability, we recommend a science and engineering-related university's information science department."

[1289] Generating and displaying feedback

[1290] The server generates feedback data based on the user's strengths and weaknesses in subjects, as well as emotional data. This feedback data includes exam preparation based on strengths and weaknesses, recommendations for higher education, and emotional advice. The generated feedback data is sent to the device and displayed in a format that the user can view. For example, it may display specific advice such as "Watch English video tutorials for 30 minutes every day" or "Solve applied math problems every weekend," as well as emotional advice such as "Take a short break because your stress level is high."

[1291] Specific example

[1292] User input example

[1293] Test results: Math 90 points, English 70 points, Science 85 points

[1294] Grades: Math A, English B, Science A

[1295] Learning history: Data from the past year

[1296] Emotional state: High stress levels recently

[1297] Server Processing Example

[1298] Data collection: Collect user test results, ratings, learning history, and sentiment status.

[1299] Data preprocessing: Imputation of missing values, normalization of data

[1300] Identifying my strong and weak subjects: My strong subject is "Mathematics," and my weak subject is "English."

[1301] Suggestions for exam preparation: "Watch English video tutorials for 30 minutes every day" and "Solve applied math problems every weekend."

[1302] Recommended university: "Information science department at a science and engineering university"

[1303] Utilizing the emotional engine: Due to high stress levels, "take short breaks."

[1304] Example of terminal output

[1305] We recommend that users "watch English video tutorials for 30 minutes every day" and "solve applied math problems every weekend."

[1306] Provide users with information on admissions to the "Information Science Department of a science and engineering university."

[1307] We recommend that users take short breaks to relax because their stress levels are high.

[1308] Example of a prompt

[1309] "Based on the entered test results and evaluation data, identify the user's strengths and weaknesses in different subjects. Furthermore, consider the user's learning history and emotional state to generate feedback messages that provide appropriate test preparation strategies and recommendations for further education."

[1310] The flow of the specific processing in Example 2 will be explained using Figure 13.

[1311] Step 1: User data entry

[1312] Users input their test results, evaluations, learning history, and emotional state through their device. Specific input examples include: "I scored 90 points on last year's math exam," "My English grade is a B," "I studied math for 3 hours a week," and "My stress level has been high recently." Once this data is entered into the device, the process proceeds to the next step.

[1313] Input: Test results, evaluation, learning history, emotional state

[1314] Output: User data entered into the terminal

[1315] Step 2: Data transmission by the terminal

[1316] The terminal converts the data entered by the user into JSON or XML format and sends it to the server. Data is encrypted during transmission to ensure secure communication.

[1317] Input: User data entered into the terminal

[1318] Output: Data in JSON or XML format sent to the server

[1319] Step 3: Server-based data collection and preprocessing

[1320] The server receives data sent from the terminal and stores it in a temporary database. It then performs preprocessing such as imputing missing data (using mean or median values) and normalizing the data (unifying different scales). It also verifies data integrity and removes inappropriate data.

[1321] Input: Data in JSON or XML format received by the server

[1322] Output: Preprocessed user data

[1323] Step 4: Server identifies strengths and weaknesses in subjects

[1324] The server uses pre-processed data to apply machine learning algorithms (e.g., random forest, support vector machine) to identify the user's strong and weak subjects. For example, if a user scores highly in mathematics and low in English, it will be determined that "mathematics is a strong subject" and "English is a weak subject."

[1325] Input: Preprocessed user data

[1326] Output: Identified strong subjects and subjects with high earnings

[1327] Step 5: Emotion Recognition by Server

[1328] The server uses an emotion engine to estimate emotions (e.g., stress levels and satisfaction levels) from emotion data and learning history obtained from users. For example, it analyzes emotions using natural language processing and facial recognition technology.

[1329] Input: User sentiment data, learning history

[1330] Output: Estimated emotions (stress level, satisfaction level, etc.)

[1331] Step 6: Server-based test preparation suggestions

[1332] The server suggests test preparation strategies based on identified strengths and weaknesses. For example, it provides video tutorials and additional practice problems for English, which is a weak subject, and application problems and mock exams for mathematics, which is a strong subject. It also suggests relaxation methods based on emotional data if stress levels are high.

[1333] Input: Identified strengths and weaknesses in subjects, estimated sentiment data

[1334] Output: Proposed exam preparation

[1335] Step 7: Server-based recommendation of educational institutions

[1336] The server matches information on the user's strengths in subjects and their desired educational institutions to select the most suitable institution from the database. For example, it might suggest a specific institution such as, "For a user who excels in mathematics and has high emotional stability, we recommend a science and engineering-related university's information science department."

[1337] Input: Strong subjects and weak subjects, and college admissions information database

[1338] Output: Recommended schools to attend

[1339] Step 8: Server generates feedback data

[1340] The server generates feedback data based on identified strengths and weaknesses in subjects, as well as emotional data. This feedback data includes test preparation tips, recommendations for higher education institutions, and emotionally-based advice.

[1341] Input: Identified strengths and weaknesses in subjects, emotional data

[1342] Output: Feedback data

[1343] Step 9: Displaying user feedback via the device

[1344] The device displays feedback data received from the server to the user. Specifically, it displays concrete advice such as "Watch English video tutorials for 30 minutes every day" and "Solve applied math problems every weekend," as well as emotion-based advice such as "Take a short break because your stress level is high."

[1345] Input: Feedback data received from the server

[1346] Output: Feedback presented to the user

[1347] Step 10: User creates learning plan

[1348] Users review feedback data through their devices and create learning plans based on it. They implement recommended test preparation strategies and leverage the emotional engine's advice to create plans that maximize learning efficiency. They reassess their emotional state in a timely manner and adjust their learning methods as needed.

[1349] Input: Feedback data

[1350] Output: Newly created study plan

[1351] (Application Example 2)

[1352] Next, we will explain application example 2. In the following explanation, the data processing device 12 will be referred to as the "server," and the headset-type terminal 314 will be referred to as the "terminal."

[1353] Traditional learning support systems identified a user's strengths and weaknesses based on their test results and learning history, and then provided learning support accordingly. However, learning support provided without considering the user's emotional state had the problem of not reflecting the user's stress level or satisfaction level, resulting in ineffective learning support. Furthermore, similarly, product recommendations lacked personalization that took the user's emotional state into account, resulting in insufficient user satisfaction.

[1354] The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means.

[1355] In this invention, the server includes means for receiving test results, evaluations, learning history, and sentiment data from the user; means for pre-processing the received data; and means for identifying the user's strong and weak subjects based on the pre-processed data. This enables personalized test preparation and product recommendations that take the user's emotions into consideration.

[1356] Definitions of important words

[1357] "Test results" refer to data showing the scores and evaluations of tests taken by a user within a certain period of time.

[1358] "Evaluation" refers to the grades and feedback given based on the user's test results and learning progress.

[1359] "Learning history" refers to a record of a user's past learning activities, including data such as study time and learning materials used.

[1360] "Emotional data" refers to data that indicates a user's emotional state, including parameters such as stress levels and satisfaction levels.

[1361] "Preprocessing" refers to the process of modifying received data, such as imputing missing values ​​or normalizing the data.

[1362] A "favorite subject" is a subject in which a user consistently scores or receives high marks compared to other subjects.

[1363] A "subject a user struggles with" is a subject in which the user consistently scores or receives lower marks compared to other subjects.

[1364] "Exam preparation" refers to learning support methods and materials provided based on the user's strengths and weaknesses in different subjects.

[1365] "Recommended educational institution" refers to the educational institution or faculty that the user is advised to pursue next.

[1366] An "emotion recognition engine" is a system that estimates and analyzes emotions based on user input data and learning history.

[1367] "Feedback data" refers to data that includes advice and recommendations provided to users.

[1368] Modes for carrying out the invention

[1369] The system of this invention identifies the user's strengths and weaknesses in subjects based on their learning history and emotional data, and provides personalized learning support. The main components of this system include a terminal where the user inputs data, a server that processes and analyzes the data, and a terminal that receives feedback from the server.

[1370] System Overview

[1371] User: Input Data

[1372] Users input test results, evaluations, learning history, and sentiment data into the system via their devices. For example, they might input data such as "I scored 90 on last year's math exam," "My English grade is a B," "I studied math for 3 hours a week," and "My stress level has been high recently."

[1373] Terminal: Data transmission

[1374] The terminal sends the entered data to the server. The data is sent in an appropriate format, such as JSON or XML, ensuring that the server receives the data accurately.

[1375] Server: Data processing and preprocessing

[1376] The server receives data sent from the terminal and stores it in a temporary database. It then performs preprocessing such as imputing missing data and normalizing the data.

[1377] Server: Identifying strong and weak subjects

[1378] Based on the pre-processed data, the server uses machine learning algorithms (such as random forests or support vector machines) to identify subjects the student excels at and subjects they struggle with. Subjects with high scores are classified as "strong subjects," and subjects with low scores are classified as "weak subjects."

[1379] Server: Emotion analysis by emotion recognition engine

[1380] The server uses an emotion recognition engine to analyze the user's emotional state. For example, it analyzes stress levels and satisfaction levels during learning, and uses this emotional data to support learning.

[1381] Server: Providing exam preparation suggestions and recommendations for higher education institutions.

[1382] The server suggests exam preparation strategies based on identified strengths and weaknesses, and also selects potential universities from its database. For example, it might suggest specific strategies such as "watch 30 minutes of English video tutorials daily" or "solve applied math problems every weekend." It can also recommend a "Department of Information Science at a science and engineering university" as a suitable university.

[1383] Server: Feedback to users

[1384] The server generates feedback data based on previous analysis results, exam preparation suggestions, and recommended educational institutions. This feedback data also includes advice based on the user's emotional state.

[1385] Device: Show feedback

[1386] The device displays feedback received from the server to the user. For example, it might show advice such as "Watch English video tutorials for 30 minutes every day," "Solve applied math problems every weekend," or "Consider applying to the information science department of a science and engineering university." It might also recommend "Take a short break because your stress level is high."

[1387] Hardware and software to be used

[1388] The system uses the following hardware and software:

[1389] Hardware: Servers, user terminals (smartphones and tablets)

[1390] Software: Machine learning algorithms (random forest, support vector machine), database system, sentiment recognition engine

[1391] Specific example

[1392] User A enters the following data through the terminal:

[1393] Test results: Math 90 points, English 70 points

[1394] Grades: Math A, English B

[1395] Learning history: Math study time 3 hours / week

[1396] Emotional state: High stress level

[1397] The server receives this data, performs preprocessing, and then identifies the user's strengths and weaknesses. Considering learning history and sentiment data, it provides specific advice to the user, such as "watch English video tutorials for 30 minutes every day" or "a science and engineering university's information science department would be suitable for you."

[1398] Example of a prompt

[1399] "User A's purchase history includes electronic products (rated 5 stars) and books (rated 3 stars). They also have a high stress level recently. Please recommend products suitable for User A."

[1400] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[1401] Program processing steps

[1402] Step 1: Enter and submit user data.

[1403] Users input test results, evaluations, learning history, and sentiment data through their devices. This includes specific scores, evaluations, past learning time, and recent sentiment status. The devices then send this data to the server in JSON or XML format.

[1404] Input: User test results, evaluations, learning history, sentiment data

[1405] Output: Data in JSON or XML format provided by the terminal.

[1406] Specific operation: The user enters information into each field within the application and presses the "Submit" button.

[1407] Step 2: Server receives and temporarily stores data.

[1408] The server receives data sent from the terminal and stores it in a temporary database. This data is used in subsequent processing steps.

[1409] Input: User data in JSON or XML format

[1410] Output: Raw data stored in the database

[1411] Specific operation: The server receives requests at a specific API endpoint and saves the received data to the database.

[1412] Step 3: Data Preprocessing

[1413] The server performs preprocessing on the temporarily stored data, such as imputing missing data and normalizing the data. Specifically, it uses Python libraries (e.g., pandas, scikit-learn) to format the data.

[1414] Input: Raw data

[1415] Output: Preprocessed dataset

[1416] Specific operation: The server executes a script to impute missing values ​​(e.g., mean and median) and normalize the data.

[1417] Step 4: Identifying your strengths and weaknesses in different subjects

[1418] Based on the pre-processed data, the server uses machine learning algorithms (e.g., random forest, support vector machine) to identify the user's strengths and weaknesses in different subjects.

[1419] Input: Preprocessed dataset

[1420] Output: List of subjects you excel at and subjects you struggle with

[1421] Specific operation: The server uses a pre-trained model to make predictions and lists subjects the student excels at and struggles with.

[1422] Step 5: Emotion analysis using an emotion recognition engine

[1423] The server uses an emotion recognition engine to analyze the user's emotional state. This allows the user's stress level and satisfaction level to be understood numerically.

[1424] Input: User sentiment data

[1425] Output: Analyzed emotional data (e.g., stress level, satisfaction level)

[1426] Specific operation: The server invokes an emotion recognition engine, analyzes the input data, and obtains numerical values ​​for stress and satisfaction.

[1427] Step 6: Suggestions for exam preparation and recommendations for higher education options.

[1428] The server suggests optimal exam preparation strategies and educational options to the user based on their strengths and weaknesses in different subjects, as well as analyzed emotional data. This includes specific study methods and information on recommended educational institutions.

[1429] Input: Favorite subjects, least favorite subjects, analyzed emotional data

[1430] Output: Suggestions for exam preparation and a list of potential schools to attend.

[1431] Specific operation: The server uses an algorithm to provide the user with a suitable learning plan and educational options.

[1432] Step 7: Generate and send feedback

[1433] The server generates feedback data based on the analysis results so far and sends it to the terminal. This data includes recommendations for specific learning methods and schools to attend.

[1434] Input: Suggestions for exam preparation, list of universities to attend.

[1435] Output: User feedback data

[1436] Specific operation: The server sends the generated feedback to the terminal in JSON format.

[1437] Step 8: Displaying user feedback

[1438] The terminal displays feedback data received from the server to the user. This allows the user to obtain specific information on exam preparation and potential schools.

[1439] Input: Feedback data from the server

[1440] Output: Feedback information displayed on the terminal

[1441] Specific operation: The terminal analyzes the received data and displays it on the user interface.

[1442] This makes it possible for the present invention system to provide personalized learning support and product recommendations that take into account the user's emotions.

[1443] The specific processing unit 290 transmits the result of the specific processing to the headset terminal 314. In the headset terminal 314, the control unit 46A causes the speaker 240 and display 343 to output the result of the specific processing. The microphone 238 acquires audio indicating user input for the result of the specific processing. The control unit 46A transmits the audio data indicating user input acquired by the microphone 238 to the data processing unit 12. In the data processing unit 12, the specific processing unit 290 acquires the audio data.

[1444] Data generation model 58 is a type of so-called generative AI (Artificial Intelligence). One example of data generation model 58 is ChatGPT (Internet search<URL: https: / / openai.com / blog / chatgpt> ), Gemini (Internet search) <url: https: gemini.google.com ?hl="ja">Examples of generative AI include those described above. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 is input with prompts containing instructions, and with inference data such as audio data representing speech, text data representing text, and image data representing images. The data generation model 58 infers from the input inference data according to the instructions shown by the prompts, and outputs the inference results in data formats such as audio data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[1445] In the above embodiment, an example was given in which specific processing is performed by the data processing device 12, but the technology of this disclosure is not limited thereto, and specific processing may also be performed by the headset terminal 314.

[1446] [Fourth Embodiment]

[1447] Figure 7 shows an example of the configuration of the data processing system 410 according to the fourth embodiment.

[1448] As shown in Figure 7, the data processing system 410 includes a data processing device 12 and a robot 414. An example of the data processing device 12 is a server.

[1449] The data processing device 12 comprises a computer 22, a database 24, and a communication interface 26. The computer 22 is an example of a "computer" related to the technology of this disclosure. The computer 22 comprises a processor 28, RAM 30, and storage 32. The processor 28, RAM 30, and storage 32 are connected to a bus 34. The database 24 and the communication interface 26 are also connected to the bus 34. The communication interface 26 is connected to a network 54. An example of the network 54 is a WAN (Wide Area Network) and / or a LAN (Local Area Network).

[1450] The robot 414 includes a computer 36, a microphone 238, a speaker 240, a camera 42, a communication interface 44, and a controlled object 443. The computer 36 includes a processor 46, RAM 48, and storage 50. The processor 46, RAM 48, and storage 50 are connected to a bus 52. The microphone 238, speaker 240, camera 42, and controlled object 443 are also connected to the bus 52.

[1451] The microphone 238 receives voice signals from the user 20 and receives instructions from the user 20. The microphone 238 captures the voice signals from the user 20, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio according to the instructions from the processor 46.

[1452] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an image sensor such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, and captures images of the area around the user 20 (for example, an imaging range defined by a field of view equivalent to the width of a typical healthy person's field of vision).

[1453] Communication interface 44 is connected to network 54. Communication interfaces 44 and 26 are responsible for the exchange of various information between processor 46 and processor 28 via network 54. The exchange of various information between processor 46 and processor 28 using communication interfaces 44 and 26 is performed in a secure manner.

[1454] The controlled object 443 includes a display device, LEDs in the eyes, and motors that drive the arms, hands, and feet. The posture and gestures of the robot 414 are controlled by controlling the motors of the arms, hands, and feet. Some of the robot 414's emotions can be expressed by controlling these motors. Furthermore, the robot 414's facial expressions can also be expressed by controlling the illumination state of the LEDs in its eyes.

[1455] Figure 8 shows an example of the main functions of the data processing device 12 and the robot 414. As shown in Figure 8, the data processing device 12 performs specific processing using the processor 28. The storage 32 stores the specific processing program 56.

[1456] The specific processing program 56 is an example of a "program" relating to the technology of this disclosure. The processor 28 reads the specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific processing is realized by the processor 28 operating as a specific processing unit 290 in accordance with the specific processing program 56 executed on the RAM 30.

[1457] The storage 32 stores the data generation model 58 and the emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290.

[1458] In robot 414, the processor 46 performs the reception output processing. The storage 50 stores the reception output program 60. The processor 46 reads the reception output program 60 from the storage 50 and executes the read reception output program 60 on the RAM 48. The reception output processing is realized by the processor 46 operating as a control unit 46A according to the reception output program 60 executed on the RAM 48.

[1459] Next, the specific processing performed by the specific processing unit 290 of the data processing device 12 will be described. In the following description, the data processing device 12 will be referred to as the "server" and the robot 414 as the "terminal".

[1460] The system of this invention analyzes a user's strengths and weaknesses in different subjects and provides exam preparation strategies and recommendations for higher education based on that analysis. This system mainly consists of a terminal where the user inputs data, a server that processes and analyzes the data, and a terminal that receives feedback from the server.

[1461] System Overview

[1462] User: Data entry

[1463] Users input test results, evaluations, and learning history into the system via their devices. For example, they might input specific data such as, "I got 90 points on last year's math exam," or "My English grade was a B."

[1464] Terminal: Data transmission

[1465] The terminal sends the entered data to the server. When sending the data, it is important to send it in an appropriate format (such as JSON or XML) so that the server can receive the data accurately.

[1466] Server: Data collection and preprocessing

[1467] The server collects data sent from the terminal and stores it in a temporary data store. Then, it performs preprocessing on the collected data. Specifically, it imputes missing values ​​with the mean or median, and normalizes data from different scales to unify them.

[1468] Server: Identifying strong and weak subjects

[1469] Based on the pre-processed data, the server identifies the user's strong and weak subjects. Here, machine learning algorithms (e.g., random forest or support vector machine) are used to analyze the scoring patterns for each subject. Subjects with high scores are identified as "strong subjects," and subjects with low scores are identified as "weak subjects."

[1470] Server: Suggestions for exam preparation

[1471] The server suggests exam preparation strategies based on identified strengths and weaknesses. For example, it recommends video tutorials and additional practice problems for weak subjects, and provides application problems and mock exams for strong subjects. Specifically, this might include suggestions like "watch a 30-minute English video tutorial every day" or "solve application problems in mathematics on the weekend."

[1472] Server: Recommended by the school you will be attending

[1473] The server matches the user's strengths in subjects with information on potential universities. Considering the user's strengths and interests, it selects the most suitable university from the database. For example, it might suggest a university like "A science and engineering university's information science department would be suitable because you excel in mathematics."

[1474] Server: Generating feedback data

[1475] The server generates feedback data based on previous analysis results, suggested exam preparation strategies, and recommended educational institutions. This feedback data is then provided to the user.

[1476] Device: Displaying feedback to the user

[1477] The device displays feedback data received from the server to the user. The displayed feedback includes specific details such as, "Your weakest subject is English. Watch English video tutorials for 30 minutes every day. Also, a computer science department at a science and engineering university would be a good fit for you."

[1478] User: Creating a study plan

[1479] Users create their own study plans based on feedback displayed on their devices. They can set specific study schedules and goals based on recommended test preparation and information about potential schools.

[1480] Specific example

[1481] 1. User input example

[1482] Test results: Math 90 points, English 70 points, Science 85 points

[1483] Grades: Math A, English B, Science A

[1484] Learning history: Data from the past year

[1485] 2. Example of server processing

[1486] Data collection: Collect user test results, evaluations, and learning history.

[1487] Data preprocessing: Imputation of missing values, normalization of statistical data.

[1488] Identifying my strong and weak subjects: My strong subject is "Mathematics," and my weak subject is "English."

[1489] Suggestions for exam preparation: "Watch English video tutorials for 30 minutes every day" and "Solve applied math problems every weekend."

[1490] Recommended university: "Information science department at a science and engineering university"

[1491] 3. Example of terminal output

[1492] We recommend that users "watch English video tutorials for 30 minutes every day" and "solve applied math problems every weekend."

[1493] Provide users with information on admissions to the "Information Science Department of a science and engineering university."

[1494] This allows users to prepare for exams best suited to their individual strengths and choose the appropriate educational institution. In this way, users can create more effective study plans and gain an advantage in future educational and career choices.

[1495] The following describes the processing flow.

[1496] Step 1:

[1497] Users use their devices to input their test results, grades, and learning history. For example, they might input specific data such as "I scored 90 points on last year's math exam," "My English grade was a B," and "I studied math for 3 hours a week."

[1498] Step 2:

[1499] The terminal sends data entered by the user to the server. This input data is often sent in formats such as JSON or XML.

[1500] Step 3:

[1501] The server receives data sent from the terminal and stores it in a temporary database. Here, it checks the data's integrity and sends an error message to the terminal if any inconsistencies are found.

[1502] Step 4:

[1503] The server preprocesses the collected data. Specifically, it performs data imputation (such as imputing with the mean or median) and data normalization (unifying different scales).

[1504] Step 5:

[1505] Based on pre-processed data, the server uses machine learning algorithms to identify the user's strong and weak subjects. For example, it might use a random forest or support vector machine to analyze the user's scoring patterns, identifying subjects with high scores as "strong subjects" and subjects with low scores as "weak subjects."

[1506] Step 6:

[1507] Based on the user's identified strengths and weaknesses in different subjects, the server suggests exam preparation strategies. For example, it might generate specific strategies such as "Watch English video tutorials for 30 minutes every day" or "Solve applied math problems every weekend."

[1508] Step 7:

[1509] The server matches the user's strengths in subjects with information on potential universities and selects the most suitable university from the database. For example, it might identify a university with a strong focus on science and engineering, such as "a science and engineering university's information science department, as the user excels in mathematics."

[1510] Step 8:

[1511] The server generates feedback data based on previous analysis results, suggested exam preparation strategies, and recommended educational institutions. This feedback data serves as a reference for users to create concrete study plans.

[1512] Step 9:

[1513] The device displays feedback data received from the server to the user. For example, it might display specific advice such as, "Watch English video tutorials for 30 minutes every day," or "A science and engineering university's information science department would be suitable."

[1514] Step 10:

[1515] Users create a specific study plan based on feedback displayed on their device. They then implement recommended test preparation strategies and progress towards their goals.

[1516] (Example 1)

[1517] Next, we will describe Example 1. In the following description, the data processing device 12 will be referred to as the "server" and the robot 414 as the "terminal".

[1518] Traditional educational support systems struggle to accurately identify each user's individual learning situation, strengths, and weaknesses, and to provide appropriate test preparation and recommendations for higher education based on that information. In particular, insufficient preprocessing, such as imputing missing values ​​or unifying data from different scales, prevents accurate analysis. Furthermore, the suggested test preparation and educational recommendations are often vague and therefore impractical for users.

[1519] The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 1 is realized by the following means.

[1520] In this invention, the server includes means for receiving education-related data (test results, evaluations, learning history) from the user, means for preprocessing the received data, means for normalizing the data and imputing missing values, means for identifying the user's strengths and weaknesses based on the preprocessed data, means for identifying them using machine learning algorithms (e.g., random forest or support vector machine), means for proposing educational support based on the identified strengths and weaknesses, means for recommending educational institutions based on the strengths and weaknesses, and means for displaying the proposed educational support and educational institutions to the user. This enables accurate learning analysis tailored to the user's individual circumstances and specific and effective recommendations for test preparation and further education.

[1521] "Education-related data" refers to the totality of information related to a user's learning, including test results, evaluations, and learning history.

[1522] "Preprocessing" is the process of converting received data into a format that can be properly analyzed. Specifically, this involves tasks such as imputing missing values ​​and normalizing the data.

[1523] "Normalization" is a process for unifying data at different scales, and is a means of making data comparison and analysis easier.

[1524] "Missing value imputation" is the procedure of filling in missing data in a dataset using a specific method (e.g., the mean or median).

[1525] A "machine learning algorithm" is a mathematical model used to analyze patterns in data and make predictions or classifications based on specific objectives.

[1526] "Areas of expertise" refers to learning areas where a user demonstrates particularly high performance.

[1527] A "weakness area" refers to a learning area where a user shows relatively low performance.

[1528] "Educational support" is a general term for the support provided to achieve specific learning objectives, and specifically includes study plans, practice problems, video tutorials, and so on.

[1529] "Educational institutions" refers to all learning facilities and educational programs related to a user's learning or further education.

[1530] "Feedback data" refers to information that includes advice and recommendations generated based on the user's learning progress, strengths, and weaknesses.

[1531] Users input educational data using a terminal. Specifically, they input information such as test results, evaluations, and learning history, and this information is sent to the system. The terminal is equipped with at least a user interface for inputting data and a function to convert that data into an appropriate format (e.g., JSON or XML) and send it.

[1532] Data sent from the terminal is received by the server. This server preprocesses the data by storing it in a temporary data store, and then performs tasks such as imputing missing values ​​and normalizing the data. This process ensures data consistency and enables accurate analysis.

[1533] The pre-processed data is used on the server to identify areas of strength and weakness. Machine learning algorithms such as random forests and support vector machines are applied here. This identifies areas where the user performs well as "strengths" and areas where performance is poor as "weaknesses."

[1534] The server then proposes specific educational support based on these identified strengths and weaknesses. For example, for English, which is a weak area, it might suggest "watching 30 minutes of English video tutorials every day," and for mathematics, which is a strong area, it might suggest "solving applied math problems on weekends."

[1535] Furthermore, the server matches the user's areas of expertise with information about their educational background to recommend the most suitable institution. For example, it might recommend a "Department of Information Science at a science and engineering university" to a user who excels in mathematics. This recommendation information is also provided to the user as part of the feedback.

[1536] These analysis results, suggestions, and recommendations for higher education are generated as feedback data and provided to the user. The device displays this feedback data to the user. The displayed content includes specific instructions such as, "Your weak area is English. Please watch English video tutorials for 30 minutes every day. Also, the information science department of a science and engineering university would be suitable for you."

[1537] Users can use this feedback data to set specific learning plans. For example, they can create action plans such as "watch 30 minutes of English video tutorials every day" or "solve applied math problems on weekends."

[1538] Example of a prompt

[1539] 1. "Based on your learning history over the past year, identify your strengths and weaknesses in different subjects, and then propose exam preparation strategies and college options accordingly."

[1540] 2. "Analyze the test results, evaluations, and learning history entered by the user, and recommend the most suitable test preparation methods and educational institutions."

[1541] This allows users to receive educational support best suited to their circumstances and choose the appropriate educational institution. Users can also develop more effective study plans and be in a more advantageous position when choosing future education or careers.

[1542] The flow of the specific processing in Example 1 will be explained using Figure 11.

[1543] Step 1:

[1544] Users input educational data using their devices. Specifically, they input information such as test results, grades, and learning history. For example, they might input data such as "I got 90 points on last year's math exam" or "My English grade was a B."

[1545] Input: Test results, evaluation, learning history

[1546] Output: Educational data stored in the device's temporary data store.

[1547] Step 2:

[1548] The terminal converts the input data into an appropriate format (e.g., JSON or XML) and sends it to the server. Before sending the data, it verifies that the data is formatted correctly.

[1549] Input: Educational data stored on the device

[1550] Output: Send formatted educational data (in JSON or XML format) to the server.

[1551] Step 3:

[1552] The server stores the data received from the terminal in a temporary data store and begins data preprocessing. First, it imputes any missing values ​​and normalizes the data. This is done using missing value imputation algorithms and normalization algorithms. For example, missing test result values ​​are imputed with the average value for that subject.

[1553] Input: Formatted education-related data

[1554] Output: Preprocessed education-related data (missing values ​​imputed, normalized)

[1555] Step 4:

[1556] The server uses pre-processed data to identify the user's strengths and weaknesses. Machine learning algorithms such as random forests and support vector machines are used here. For example, if a user scores highly in math and low in English, math is identified as a strength and English as a weakness.

[1557] Input: Preprocessed education-related data

[1558] Output: User's strengths and weaknesses

[1559] Step 5:

[1560] Based on the user's strengths and weaknesses, the server proposes specific educational support. For example, it might suggest "watching 30 minutes of English video tutorials daily" to a user who struggles with English, or "solving applied math problems on weekends" to a user who excels at math.

[1561] Input: User's strengths and weaknesses

[1562] Output: Suggestions for educational support tailored to the user.

[1563] Step 6:

[1564] The server matches the user's areas of expertise with educational institution information to recommend the most suitable institution. For example, a user who excels in mathematics would be recommended a "Department of Information Science at a science and engineering university."

[1565] Input: User's areas of expertise and educational institution information

[1566] Output: Recommendations for the most suitable educational institutions for the user.

[1567] Step 7:

[1568] The server compiles the analysis results, exam preparation suggestions, and recommended schools to generate feedback data. This feedback data is provided to the user.

[1569] Input: Areas of expertise and weaknesses, suggestions for educational support, recommendations for educational institutions.

[1570] Output: Feedback data

[1571] Step 8:

[1572] The terminal displays feedback data received from the server to the user. The displayed content includes specific instructions such as, "Your weak point is English. Watch English video tutorials for 30 minutes every day. Also, a computer science department at a science and engineering university would be a good fit for you."

[1573] Input: Feedback data

[1574] Output: Specific feedback displayed to the user

[1575] Step 9:

[1576] Users create their own learning plans based on feedback from their devices. They set specific study schedules and goals based on recommended test preparation and educational institution information. For example, they might create action plans such as "watch 30 minutes of English video tutorials every day" or "solve applied math problems on weekends."

[1577] Input: Feedback data

[1578] Output: Specific learning plan set by the user

[1579] (Application Example 1)

[1580] Next, we will explain Application Example 1. In the following explanation, the data processing device 12 will be referred to as the "server" and the robot 414 as the "terminal".

[1581] In modern education systems, providing appropriate learning support based on each student's strengths and weaknesses is crucial. However, traditional systems have made it difficult to comprehensively identify students' strengths and weaknesses, resulting in an inability to provide effective learning strategies. Furthermore, recommending appropriate educational institutions and suggesting individually optimized educational content has been challenging. This has led to problems such as students being unable to create a suitable learning plan, resulting in decreased learning efficiency and motivation.

[1582] The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 1 is realized by the following means.

[1583] In this invention, the server includes means for recommending appropriate learning content based on the user's strengths and weaknesses; means for receiving test results, evaluations, and learning history from the user; means for pre-processing the received data; means for identifying the user's strengths and weaknesses based on the pre-processed data; means for suggesting test preparation strategies based on the strengths and weaknesses; means for recommending higher education options based on the strengths and weaknesses; means for displaying the suggested test preparation strategies and higher education options to the user; and means for transmitting data from the user's terminal to the server and receiving feedback from the server. This enables the suggestion of educational content optimized for individual students, and allows for effective learning strategies and recommendations for higher education options.

[1584] A "user" is an individual who uses the system to input data such as test results, evaluations, and learning history, and receives learning support and recommendations for further education.

[1585] "Test results" refer to data that shows the scores and grades a user obtained in each subject of the exam.

[1586] "Evaluation" refers to data that indicates a teacher's or educational institution's assessment of a user's learning performance, and is usually represented by letters or numbers.

[1587] "Learning history" refers to data that records a user's past learning activities and performance.

[1588] "Means of receiving data" refers to devices or software that have the function of acquiring data entered by the user and sending it to the server.

[1589] "Preprocessing methods" refer to devices or software used to prepare received data for analysis by imputing missing values ​​and normalizing the data.

[1590] "Means of identification" refers to devices or software that have the function of identifying a user's strong and weak subjects based on pre-processed data.

[1591] "Machine learning algorithm" is a term that refers to an algorithm used by computers to learn from data and recognize patterns.

[1592] "Means of suggesting exam preparation strategies" refers to devices or software that have the function of recommending learning methods and materials suitable for the user based on their identified strengths and weaknesses in different subjects.

[1593] "Means of recommending educational institutions" refers to devices or software that have the function of suggesting the most suitable educational institutions based on the user's strengths and interests.

[1594] "Feedback data" refers to data that includes summaries of information provided to users, such as exam preparation strategies and recommendations for higher education institutions.

[1595] "Means of displaying to the user" refers to devices or software that visually present feedback data received from the server to the user.

[1596] "Means for recommending appropriate learning content" refers to devices or software that suggest optimal educational content based on the user's learning needs and current proficiency level.

[1597] A "terminal" is a device used by a user to input data and communicate with a server, and includes smartphones, tablets, and personal computers.

[1598] This invention is a system that analyzes a user's strengths and weaknesses in different subjects and provides exam preparation strategies and recommendations for higher education based on that analysis. The following describes an embodiment of the system in detail.

[1599] User data entry

[1600] Users input data such as test results, evaluations, and learning history using devices such as smartphones, tablets, or personal computers. This data includes specific information such as, "I scored 90 points on last year's math exam," or "My English grade is a B."

[1601] Data transmission and preprocessing

[1602] The terminal sends the data entered by the user to the server in JSON format or another appropriate format. The server temporarily stores the received data and performs preprocessing such as imputing missing values ​​and normalizing the data. Python libraries such as Pandas and Scikit-learn are used for this process.

[1603] Identifying your strengths and weaknesses in different subjects.

[1604] The server uses machine learning algorithms to identify strong and weak subjects based on pre-processed data. For example, algorithms such as Random Forest and Support Vector Machine (SVM) are used. This allows the system to identify subjects with high scores as "strong subjects" and subjects with low scores as "weak subjects."

[1605] Exam preparation and suggestions for higher education options

[1606] The server suggests appropriate exam preparation based on the user's strengths and weaknesses. For example, it generates specific study plans such as "watch English video tutorials for 30 minutes every day" or "solve applied math problems on weekends." It also matches the user's strengths with information on potential universities to recommend the most suitable institutions. For example, if the user's strength is mathematics, it might suggest "a computer science department at a science and engineering university would be a good fit."

[1607] Displaying feedback

[1608] The feedback data generated by the server is sent to the terminal in real time and displayed to the user. Users can use this feedback to create their study plans. Because the feedback includes specific study strategies and information on potential schools, users can study more effectively.

[1609] Specific examples and prompt statements

[1610] As a concrete example, consider the case where the user's input data was as follows:

[1611] Test results: Math 90 points, English 70 points, Science 85 points

[1612] Grades: Math A, English B, Science A

[1613] Learning history: Data from the past year

[1614] Server processing example:

[1615] Data Collection and Preprocessing: Collect user test results, evaluations, and training history, and perform data imputation and normalization.

[1616] Identifying strengths and weaknesses: Analyzed strengths as "mathematics" and weaknesses as "English".

[1617] Suggestions for exam preparation: "Watch English video tutorials for 30 minutes every day," "Solve applied math problems every weekend," etc.

[1618] Recommended university: We recommend the Faculty of Information Science at a science and engineering university.

[1619] Examples of prompts for a generative AI model:

[1620] "Develop a system that analyzes a user's strengths and weaknesses in specific subjects based on their test results, evaluations, and learning history. Based on these results, it will suggest appropriate learning content and also provide information on potential higher education options. The following is an example of user input."

[1621] Test results: Math 90 points, English 70 points, Science 85 points

[1622] Grades: Math A, English B, Science A

[1623] Learning history: Data from the past year

[1624] Based on this data, please identify the student's strengths and weaknesses in different subjects and provide feedback on specific study plans and potential educational paths.

[1625] As described above, the present invention provides optimal learning support to individual users and constructs a system that enables improved learning efficiency and appropriate choices for further education.

[1626] The flow of a specific process in Application Example 1 will be explained using Figure 12.

[1627] Step 1:

[1628] Users input data such as test results, evaluations, and learning history using a device (smartphone, tablet, or PC). Specifically, they input test results such as 90 points in mathematics, 70 points in English, and 85 points in science, as well as evaluations for each subject (e.g., Mathematics A, English B, Science A).

[1629] Input: Test results, evaluation, learning history

[1630] Output: User data in JSON format

[1631] Step 2:

[1632] The terminal converts the entered user data into JSON format and sends it to the server. It uses an HTTP POST request to send the data to the specified API endpoint.

[1633] Input: User data in JSON format

[1634] Output: Results of sending data to the server

[1635] Step 3:

[1636] The server temporarily stores the received data. Then, it performs preprocessing such as imputing missing values ​​and normalizing the data. Here, data cleaning is performed using Pandas or Scikit-learn.

[1637] Input: User data in JSON format

[1638] Output: Preprocessed data

[1639] Step 4:

[1640] The server applies machine learning algorithms (e.g., Random Forest or SVM) to preprocessed data to identify subjects in which the user excels and struggles. This allows for an analysis of academic performance trends for each subject, thereby identifying strengths and weaknesses.

[1641] Input: Preprocessed data

[1642] Output: Identification of strong and weak subjects

[1643] Step 5:

[1644] Based on the identification of the user's strengths and weaknesses, the server suggests appropriate test preparation strategies. For example, it might suggest watching 30 minutes of video tutorials daily for English, which is a weak subject, and recommend solving application problems on weekends for mathematics, which is a strong subject.

[1645] Input: Results of identifying strong and weak subjects

[1646] Output: Suggestions for exam preparation

[1647] Step 6:

[1648] The server matches the user's preferred subjects and college application information to recommend the most suitable college. For example, if the user's preferred subject is mathematics, the server will suggest a computer science department at a science and engineering university as a college option.

[1649] Input: Database of preferred subjects and universities / schools attended

[1650] Output: Recommended content from prospective schools

[1651] Step 7:

[1652] The server generates feedback data, including exam preparation strategies and recommendations for higher education institutions, and sends it to the terminal in real time. The generated feedback data is packaged in a format that is easy for the user to review.

[1653] Input: Suggestions for exam preparation, recommendations for universities to attend.

[1654] Output: Feedback data

[1655] Step 8:

[1656] The device displays feedback data received from the server to the user. Based on this feedback data, the user can create their own learning plan. Specifically, concrete plans such as "watch English video tutorials for 30 minutes every day" or "solve applied math problems on the weekend" are provided.

[1657] Input: Feedback data

[1658] Output: Displaying feedback to the user

[1659] Furthermore, an emotion engine that estimates the user's emotions may be incorporated. That is, the identification processing unit 290 may use the emotion identification model 59 to estimate the user's emotions and perform identification processing using the user's emotions.

[1660] The system of this invention analyzes a user's strengths and weaknesses in different subjects and provides exam preparation strategies and recommendations for higher education based on that analysis. Furthermore, it incorporates an emotion engine that recognizes the user's emotions to provide more personalized learning support. This system mainly consists of a terminal where the user inputs data, a server that processes and analyzes the data, and a terminal that receives feedback from the server.

[1661] System Overview

[1662] User: Data entry

[1663] Users input test results, evaluations, and learning history into the system via their devices. For example, they might input specific data such as "I scored 90 points on last year's math exam," "My English grade was a B," and "I studied math for 3 hours a week." Users can also input their emotional state.

[1664] Terminal: Data transmission

[1665] The terminal sends the entered data to the server. When sending the data, it is important to send it in an appropriate format (such as JSON or XML) so that the server can receive the data accurately.

[1666] Server: Data collection and preprocessing

[1667] The server receives data sent from the terminal and stores it in a temporary database. It then performs preprocessing on the collected data. Specifically, this includes imputing missing data (such as using the mean or median) and normalizing the data (unifying different scales).

[1668] Server: Identifying strong and weak subjects

[1669] Based on the pre-processed data, the server identifies the user's strong and weak subjects. Here, machine learning algorithms (e.g., random forest or support vector machine) are used to analyze the scoring patterns for each subject. Subjects with high scores are identified as "strong subjects," and subjects with low scores are identified as "weak subjects."

[1670] Server: Emotion recognition by emotion engine

[1671] The server uses an emotion engine to estimate user emotions from input data and learning history. For example, it analyzes stress levels and satisfaction levels during learning, and uses this emotional data to support learning.

[1672] Server: Suggestions for exam preparation

[1673] The server suggests exam preparation strategies based on identified strengths and weaknesses. For example, it provides video tutorials and additional practice problems for weak subjects, and application problems and mock exams for strong subjects. It also suggests learning methods to help users relax if they are experiencing stress.

[1674] Server: Recommended by the school you will be attending

[1675] The server matches the user's strengths in subjects with information on potential universities and selects the most suitable university from the database. For example, it might recommend a science and engineering university's information science department to a user who excels in mathematics and has high emotional stability.

[1676] Server: Generating feedback data

[1677] The server generates feedback data based on previous analysis results, suggested exam preparation strategies, and recommended educational institutions. This feedback data includes advice that takes the user's emotional state into consideration.

[1678] Device: Displaying feedback to the user

[1679] The device displays feedback data received from the server to the user. For example, it may display specific advice such as "Watch English video tutorials for 30 minutes every day" or "A science and engineering university's information science department would be suitable for you." It may also display emotion-based advice such as "Your stress levels have been high recently, so take short breaks to relax."

[1680] User: Creating a study plan

[1681] Users create their own learning plans based on feedback displayed on their devices. They implement recommended test preparation strategies and progress towards their goals. They can leverage emotionally driven advice to create plans that maximize learning effectiveness. They also reassess their emotional state in a timely manner and adjust their learning methods as needed.

[1682] Specific example

[1683] 1. User input example

[1684] Test results: Math 90 points, English 70 points, Science 85 points

[1685] Grades: Math A, English B, Science A

[1686] Learning history: Data from the past year

[1687] Emotional state: High stress levels recently

[1688] 2. Example of server processing

[1689] Data collection: Collect user test results, ratings, learning history, and sentiment status.

[1690] Data preprocessing: Imputation of missing values, normalization of statistical data.

[1691] Identifying my strong and weak subjects: My strong subject is "Mathematics," and my weak subject is "English."

[1692] Suggestions for exam preparation: "Watch English video tutorials for 30 minutes every day" and "Solve applied math problems every weekend."

[1693] Recommended university: "Information science department at a science and engineering university"

[1694] Utilizing the emotional engine: Due to high stress levels, "take short breaks."

[1695] 3. Example of terminal output

[1696] We recommend that users "watch English video tutorials for 30 minutes every day" and "solve applied math problems every weekend."

[1697] Provide users with information on admissions to the "Information Science Department of a science and engineering university."

[1698] We recommend that users take short breaks to relax because their stress levels are high.

[1699] This allows users to choose test preparation methods best suited to their individual characteristics and educational options that take their emotional state into consideration. In this way, users can create more effective study plans and gain an advantage in future educational and career choices.

[1700] The following describes the processing flow.

[1701] Step 1:

[1702] Users use their devices to input their test results, evaluations, and learning history. For example, they might input specific data such as "I scored 90 points on last year's math exam," "My English grade is a B," and "I studied math for 3 hours a week." They also input their emotional state (e.g., stress level).

[1703] Step 2:

[1704] The terminal sends data entered by the user to the server. When sending the data, it is important to send it in an appropriate format (e.g., JSON or XML) so that the server can receive the data accurately.

[1705] Step 3:

[1706] The server receives data sent from the terminal and stores it in a temporary database. Here, it checks the data's integrity and sends an error message to the terminal if any inconsistencies are found.

[1707] Step 4:

[1708] The server preprocesses the collected data. Specifically, it performs data imputation (such as imputing with the mean or median) and data normalization (unifying different scales).

[1709] Step 5:

[1710] Based on pre-processed data, the server uses machine learning algorithms to identify the user's strong and weak subjects. For example, it might use a random forest or support vector machine to analyze the user's scoring patterns, identifying subjects with high scores as "strong subjects" and subjects with low scores as "weak subjects."

[1711] Step 6:

[1712] The server uses an emotion engine to estimate the user's emotions from their input data and learning history. For example, it estimates stress levels from the user's learning time and pace, and evaluates their emotional stability.

[1713] Step 7:

[1714] Based on the server's identified strengths and weaknesses, it suggests exam preparation strategies. For example, it generates specific strategies such as "watch English video tutorials for 30 minutes every day" or "solve applied math problems every weekend." At the same time, it also suggests ways to reduce stress (e.g., "take short breaks") based on the user's emotional state.

[1715] Step 8:

[1716] The server matches the user's strengths in subjects with information on potential universities and selects the most suitable university from the database. For example, it might recommend a science and engineering university's information science department to a user who excels in mathematics and has high emotional stability.

[1717] Step 9:

[1718] The server generates feedback data based on previous analysis results, suggested exam preparation strategies, and recommended educational institutions. This feedback data includes advice that takes the user's emotional state into consideration.

[1719] Step 10:

[1720] The device displays feedback data received from the server to the user. For example, it may display specific advice such as "Watch English video tutorials for 30 minutes every day" or "A science and engineering university's information science department would be suitable for you." It may also display emotion-based advice such as "Your stress levels have been high recently, so take a short break to relax."

[1721] Step 11:

[1722] Users create their own study plans based on feedback displayed on their devices. They implement recommended test preparation strategies and progress towards their goals. They can utilize emotionally driven advice to create plans that maximize learning effectiveness. They also reassess their emotional state in a timely manner and adjust their learning methods as needed.

[1723] (Example 2)

[1724] Next, we will describe Example 2. In the following description, the data processing device 12 will be referred to as the "server" and the robot 414 as the "terminal".

[1725] Traditional learning support systems could identify a user's strengths and weaknesses based on their test results and evaluations, and suggest test preparation strategies and educational options. However, no system existed that adequately considered the user's emotional state while providing support. As a result, it was difficult to maximize the user's learning efficiency and motivation, and it was not possible to optimally address individual learning needs.

[1726] The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 2 is realized by the following means.

[1727] In this invention, the server includes means for receiving test results, evaluations, learning history, and emotional status from the user; means for pre-processing the received data; means for identifying the user's strong and weak subjects based on the pre-processed data; means for suggesting test preparation strategies based on the strong and weak subjects; means for recommending schools to attend based on the strong and weak subjects and emotional status; and means for presenting the user with the suggested test preparation strategies, schools to attend, and advice based on their emotional status. This makes it possible to optimally respond to individual learning needs while taking into account the user's emotional status, and to maximize learning efficiency and motivation.

[1728] A "user" refers to an end-user who uses the system to input test results, evaluations, learning history, and emotional status.

[1729] "Test results" refers to data showing the scores and performance of tests taken by the user.

[1730] "Evaluation" refers to data that shows the grades and ratings from teachers and educational institutions for subjects and assignments that a user has taken.

[1731] "Learning history" refers to the records and data of the learning activities a user has undertaken so far.

[1732] "Emotional state" refers to data that indicates the user's emotions and psychological state during learning.

[1733] "Data preprocessing" refers to the process of imputing missing values, normalizing data, and verifying data integrity in collected data.

[1734] A "favorite subject" refers to a subject in which the user has achieved high scores or evaluations.

[1735] A "subject a user struggles with" refers to a subject in which the user consistently achieves low scores or evaluations.

[1736] A "machine learning algorithm" refers to a mathematical model or computational method used to analyze large amounts of data and learn patterns and rules.

[1737] "Exam preparation" refers to learning methods and materials suggested to users to prepare for an exam.

[1738] "Recommended educational institution" refers to the educational institution or faculty that the user is advised to attend.

[1739] "Emotion-based advice" refers to advice on learning methods and stress management techniques that takes the user's emotional state into consideration.

[1740] "Feedback data" refers to data that provides users with a compilation of analysis results, exam preparation tips, recommendations for higher education institutions, and emotionally-based advice.

[1741] The system of this invention analyzes a user's strengths and weaknesses in different subjects and provides exam preparation strategies and recommendations for higher education based on that analysis. Furthermore, it incorporates an emotion engine that recognizes the user's emotions to provide more personalized learning support. This system consists of a terminal for the user to input data, a server that processes and analyzes the data, and a terminal that receives feedback from the server.

[1742] Hardware and software to be used

[1743] The following hardware and software are required to implement the system:

[1744] Devices: PC, smartphone, tablet, etc.

[1745] Server: High-performance computing server

[1746] Database Management Systems (DBMS): MySQL, PostgreSQL, etc.

[1747] Machine learning libraries: Scikit-learn, TensorFlow, etc.

[1748] Emotion recognition software: Emotion API, OpenVINO, etc.

[1749] Data entry

[1750] Users use their devices to input their test results, evaluations, learning history, and emotional state. For example, they might input "Mathematics 90 points" as a test result, "English B" as an evaluation, "3 hours of math study per week" as a learning history, and "Recent stress levels are high" as an emotional state. This data is sent to the server via the device.

[1751] Sending data

[1752] The terminal converts the data entered by the user into JSON or XML format and sends it to the server. The data is encrypted in transit, ensuring secure communication.

[1753] Data preprocessing

[1754] The server receives data sent from the terminal and stores it in a temporary database. It then performs preprocessing such as imputing missing data (e.g., using the mean or median) and normalizing the data (unifying different scales). It also verifies data integrity and removes inappropriate data.

[1755] Identifying your strengths and weaknesses

[1756] The server uses pre-processed data and applies machine learning algorithms (e.g., random forest, support vector machine) to identify the user's strong and weak subjects. For example, if a user scores highly in mathematics and low in English, it will be determined that "mathematics is a strong subject" and "English is a weak subject."

[1757] emotion recognition

[1758] The server uses an emotion engine to estimate the user's emotions at the time of learning (e.g., stress level and satisfaction level) based on emotion data entered by the user and their learning history.

[1759] Suggestions for exam preparation

[1760] The server suggests test preparation strategies based on identified strengths and weaknesses. For example, it provides video tutorials and additional practice problems for English, which is a weak subject, and application problems and mock exams for mathematics, which is a strong subject. It also suggests relaxation methods based on emotional data if stress levels are high.

[1761] Recommended schools

[1762] The server matches information on the user's strengths in subjects and their potential educational paths to select the most suitable university from the database. For example, it might suggest a specific university, such as "For a user who excels in mathematics and has high emotional stability, we recommend a science and engineering-related university's information science department."

[1763] Generating and displaying feedback

[1764] The server generates feedback data based on the user's strengths and weaknesses in subjects, as well as emotional data. This feedback data includes exam preparation based on strengths and weaknesses, recommendations for higher education, and emotional advice. The generated feedback data is sent to the device and displayed in a format that the user can view. For example, it may display specific advice such as "Watch English video tutorials for 30 minutes every day" or "Solve applied math problems every weekend," as well as emotional advice such as "Take a short break because your stress level is high."

[1765] Specific example

[1766] User input example

[1767] Test results: Math 90 points, English 70 points, Science 85 points

[1768] Grades: Math A, English B, Science A

[1769] Learning history: Data from the past year

[1770] Emotional state: High stress levels recently

[1771] Server Processing Example

[1772] Data collection: Collect user test results, ratings, learning history, and sentiment status.

[1773] Data preprocessing: Imputation of missing values, normalization of data

[1774] Identifying my strong and weak subjects: My strong subject is "Mathematics," and my weak subject is "English."

[1775] Suggestions for exam preparation: "Watch English video tutorials for 30 minutes every day" and "Solve applied math problems every weekend."

[1776] Recommended university: "Information science department at a science and engineering university"

[1777] Utilizing the emotional engine: Due to high stress levels, "take short breaks."

[1778] Example of terminal output

[1779] We recommend that users "watch English video tutorials for 30 minutes every day" and "solve applied math problems every weekend."

[1780] Provide users with information on admissions to the "Information Science Department of a science and engineering university."

[1781] We recommend that users take short breaks to relax because their stress levels are high.

[1782] Example of a prompt

[1783] "Based on the entered test results and evaluation data, identify the user's strengths and weaknesses in different subjects. Furthermore, consider the user's learning history and emotional state to generate feedback messages that provide appropriate test preparation strategies and recommendations for further education."

[1784] The flow of the specific processing in Example 2 will be explained using Figure 13.

[1785] Step 1: User data entry

[1786] Users input their test results, evaluations, learning history, and emotional state through their device. Specific input examples include: "I scored 90 points on last year's math exam," "My English grade is a B," "I studied math for 3 hours a week," and "My stress level has been high recently." Once this data is entered into the device, the process proceeds to the next step.

[1787] Input: Test results, evaluation, learning history, emotional state

[1788] Output: User data entered into the terminal

[1789] Step 2: Data transmission by the terminal

[1790] The terminal converts the data entered by the user into JSON or XML format and sends it to the server. Data is encrypted during transmission to ensure secure communication.

[1791] Input: User data entered into the terminal

[1792] Output: Data in JSON or XML format sent to the server

[1793] Step 3: Server-based data collection and preprocessing

[1794] The server receives data sent from the terminal and stores it in a temporary database. It then performs preprocessing such as imputing missing data (using mean or median values) and normalizing the data (unifying different scales). It also verifies data integrity and removes inappropriate data.

[1795] Input: Data in JSON or XML format received by the server

[1796] Output: Preprocessed user data

[1797] Step 4: Server identifies strengths and weaknesses in subjects

[1798] The server uses pre-processed data to apply machine learning algorithms (e.g., random forest, support vector machine) to identify the user's strong and weak subjects. For example, if a user scores highly in mathematics and low in English, it will be determined that "mathematics is a strong subject" and "English is a weak subject."

[1799] Input: Preprocessed user data

[1800] Output: Identified strong subjects and subjects with high earnings

[1801] Step 5: Emotion Recognition by Server

[1802] The server uses an emotion engine to estimate emotions (e.g., stress levels and satisfaction levels) from emotion data and learning history obtained from users. For example, it analyzes emotions using natural language processing and facial recognition technology.

[1803] Input: User sentiment data, learning history

[1804] Output: Estimated emotions (stress level, satisfaction level, etc.)

[1805] Step 6: Server-based test preparation suggestions

[1806] The server suggests test preparation strategies based on identified strengths and weaknesses. For example, it provides video tutorials and additional practice problems for English, which is a weak subject, and application problems and mock exams for mathematics, which is a strong subject. It also suggests relaxation methods based on emotional data if stress levels are high.

[1807] Input: Identified strengths and weaknesses in subjects, estimated sentiment data

[1808] Output: Proposed exam preparation

[1809] Step 7: Server-based recommendation of educational institutions

[1810] The server matches information on the user's strengths in subjects and their desired educational institutions to select the most suitable institution from the database. For example, it might suggest a specific institution such as, "For a user who excels in mathematics and has high emotional stability, we recommend a science and engineering-related university's information science department."

[1811] Input: Strong subjects and weak subjects, and college admissions information database

[1812] Output: Recommended schools to attend

[1813] Step 8: Server generates feedback data

[1814] The server generates feedback data based on identified strengths and weaknesses in subjects, as well as emotional data. This feedback data includes test preparation tips, recommendations for higher education institutions, and emotionally-based advice.

[1815] Input: Identified strengths and weaknesses in subjects, emotional data

[1816] Output: Feedback data

[1817] Step 9: Displaying user feedback via the device

[1818] The device displays feedback data received from the server to the user. Specifically, it displays concrete advice such as "Watch English video tutorials for 30 minutes every day" and "Solve applied math problems every weekend," as well as emotion-based advice such as "Take a short break because your stress level is high."

[1819] Input: Feedback data received from the server

[1820] Output: Feedback presented to the user

[1821] Step 10: User creates learning plan

[1822] Users review feedback data through their devices and create learning plans based on it. They implement recommended test preparation strategies and leverage the emotional engine's advice to create plans that maximize learning efficiency. They reassess their emotional state in a timely manner and adjust their learning methods as needed.

[1823] Input: Feedback data

[1824] Output: Newly created study plan

[1825] (Application Example 2)

[1826] Next, we will explain application example 2. In the following explanation, the data processing device 12 will be referred to as the "server" and the robot 414 as the "terminal".

[1827] Traditional learning support systems identified a user's strengths and weaknesses based on their test results and learning history, and then provided learning support accordingly. However, learning support provided without considering the user's emotional state had the problem of not reflecting the user's stress level or satisfaction level, resulting in ineffective learning support. Furthermore, similarly, product recommendations lacked personalization that took the user's emotional state into account, resulting in insufficient user satisfaction.

[1828] The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means.

[1829] In this invention, the server includes means for receiving test results, evaluations, learning history, and sentiment data from the user; means for pre-processing the received data; and means for identifying the user's strong and weak subjects based on the pre-processed data. This enables personalized test preparation and product recommendations that take the user's emotions into consideration.

[1830] Definitions of important words

[1831] "Test results" refer to data showing the scores and evaluations of tests taken by a user within a certain period of time.

[1832] "Evaluation" refers to the grades and feedback given based on the user's test results and learning progress.

[1833] "Learning history" refers to a record of a user's past learning activities, including data such as study time and learning materials used.

[1834] "Emotional data" refers to data that indicates a user's emotional state, including parameters such as stress levels and satisfaction levels.

[1835] "Preprocessing" refers to the process of modifying received data, such as imputing missing values ​​or normalizing the data.

[1836] A "favorite subject" is a subject in which a user consistently scores or receives high marks compared to other subjects.

[1837] A "subject a user struggles with" is a subject in which the user consistently scores or receives lower marks compared to other subjects.

[1838] "Exam preparation" refers to learning support methods and materials provided based on the user's strengths and weaknesses in different subjects.

[1839] "Recommended educational institution" refers to the educational institution or faculty that the user is advised to pursue next.

[1840] An "emotion recognition engine" is a system that estimates and analyzes emotions based on user input data and learning history.

[1841] "Feedback data" refers to data that includes advice and recommendations provided to users.

[1842] Modes for carrying out the invention

[1843] The system of this invention identifies the user's strengths and weaknesses in subjects based on their learning history and emotional data, and provides personalized learning support. The main components of this system include a terminal where the user inputs data, a server that processes and analyzes the data, and a terminal that receives feedback from the server.

[1844] System Overview

[1845] User: Input Data

[1846] Users input test results, evaluations, learning history, and sentiment data into the system via their devices. For example, they might input data such as "I scored 90 on last year's math exam," "My English grade is a B," "I studied math for 3 hours a week," and "My stress level has been high recently."

[1847] Terminal: Data transmission

[1848] The terminal sends the entered data to the server. The data is sent in an appropriate format, such as JSON or XML, ensuring that the server receives the data accurately.

[1849] Server: Data processing and preprocessing

[1850] The server receives data sent from the terminal and stores it in a temporary database. It then performs preprocessing such as imputing missing data and normalizing the data.

[1851] Server: Identifying strong and weak subjects

[1852] Based on the pre-processed data, the server uses machine learning algorithms (such as random forests or support vector machines) to identify subjects the student excels at and subjects they struggle with. Subjects with high scores are classified as "strong subjects," and subjects with low scores are classified as "weak subjects."

[1853] Server: Emotion analysis by emotion recognition engine

[1854] The server uses an emotion recognition engine to analyze the user's emotional state. For example, it analyzes stress levels and satisfaction levels during learning, and uses this emotional data to support learning.

[1855] Server: Providing exam preparation suggestions and recommendations for higher education institutions.

[1856] The server suggests exam preparation strategies based on identified strengths and weaknesses, and also selects potential universities from its database. For example, it might suggest specific strategies such as "watch 30 minutes of English video tutorials daily" or "solve applied math problems every weekend." It can also recommend a "Department of Information Science at a science and engineering university" as a suitable university.

[1857] Server: Feedback to users

[1858] The server generates feedback data based on previous analysis results, exam preparation suggestions, and recommended educational institutions. This feedback data also includes advice based on the user's emotional state.

[1859] Device: Show feedback

[1860] The device displays feedback received from the server to the user. For example, it might show advice such as "Watch English video tutorials for 30 minutes every day," "Solve applied math problems every weekend," or "Consider applying to the information science department of a science and engineering university." It might also recommend "Take a short break because your stress level is high."

[1861] Hardware and software to be used

[1862] The system uses the following hardware and software:

[1863] Hardware: Servers, user terminals (smartphones and tablets)

[1864] Software: Machine learning algorithms (random forest, support vector machine), database system, sentiment recognition engine

[1865] Specific example

[1866] User A enters the following data through the terminal:

[1867] Test results: Math 90 points, English 70 points

[1868] Grades: Math A, English B

[1869] Learning history: Math study time 3 hours / week

[1870] Emotional state: High stress level

[1871] The server receives this data, performs preprocessing, and then identifies the user's strengths and weaknesses. Considering learning history and sentiment data, it provides specific advice to the user, such as "watch English video tutorials for 30 minutes every day" or "a science and engineering university's information science department would be suitable for you."

[1872] Example of a prompt

[1873] "User A's purchase history includes electronic products (rated 5 stars) and books (rated 3 stars). They also have a high stress level recently. Please recommend products suitable for User A."

[1874] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[1875] Program processing steps

[1876] Step 1: Enter and submit user data.

[1877] Users input test results, evaluations, learning history, and sentiment data through their devices. This includes specific scores, evaluations, past learning time, and recent sentiment status. The devices then send this data to the server in JSON or XML format.

[1878] Input: User test results, evaluations, learning history, sentiment data

[1879] Output: Data in JSON or XML format provided by the terminal.

[1880] Specific operation: The user enters information into each field within the application and presses the "Submit" button.

[1881] Step 2: Server receives and temporarily stores data.

[1882] The server receives data sent from the terminal and stores it in a temporary database. This data is used in subsequent processing steps.

[1883] Input: User data in JSON or XML format

[1884] Output: Raw data stored in the database

[1885] Specific operation: The server receives requests at a specific API endpoint and saves the received data to the database.

[1886] Step 3: Data Preprocessing

[1887] The server performs preprocessing on the temporarily stored data, such as imputing missing data and normalizing the data. Specifically, it uses Python libraries (e.g., ...

Claims

1. A means of receiving test results, evaluations, and learning history from users, A means for preprocessing the received data, A means for identifying a user's strong and weak subjects based on pre-processed data, A method for proposing exam preparation based on identified strengths and weaknesses, A method for recommending schools based on strengths and weaknesses in subjects, A means of displaying proposed exam preparation strategies and educational options to the user, A system that includes this.

2. The system according to claim 1, wherein the means for identifying strong and weak subjects is to use a machine learning algorithm for identification.

3. The system according to claim 1, further comprising means for generating feedback data for the user based on preprocessed data.

Images