system

Abstract

Provide a system. The method includes: a means for collecting input test scores and report card performance data of learners; A means for analyzing the academic ability of learners based on the collected data; A means for estimating the probability of admission to the desired school based on the analysis results; A means for generating a list of preferred schools and a list of backup schools according to the estimated pass rate; means for displaying the generated list; and means for creating a study plan for the learner based on said display means.

Description

[Technical Field]

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

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

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

[0004] In conventional education systems, it was difficult to provide specific, individualized study plans to efficiently support students' academic improvement and admission to their desired schools. It was also difficult to accurately estimate pass rates based on test scores and report card performance data, or to present appropriate study content. Furthermore, there was a lack of a mechanism for flexibly adjusting study plans based on daily learning progress. [Means for solving the problem]

[0005] The present invention provides a system including: means for collecting input test scores and report card performance data of a learner; means for analyzing the learner's academic ability based on the collected data; means for estimating the pass rate for a preferred school based on the analysis results; means for generating a list of preferred schools and a list of safety schools according to the estimated pass rate; means for displaying the generated lists; and means for creating a study plan for the learner based on the display means. Furthermore, by including means for inputting the learner's daily study progress and collecting the study progress data, and means for adjusting the study plan based on the collected progress data, effective study support can be realized. Furthermore, by including means for identifying the learner's weak areas and challenges to overcome based on the estimated pass rate and providing specific study methods and materials to address the identified challenges, the system can efficiently support the learner's academic improvement.

[0006] "Inputted student test scores and report card grade data" refers to the scores of each test the student has taken in the past and the grades for each subject issued by the school.

[0007] "Means for analyzing learners' academic ability" is a function for evaluating a learner's current academic ability and determining their strengths and weaknesses based on input test scores and grade data.

[0008] A "means for estimating the chances of getting into a school of choice" is a system for calculating the chances of getting into a school of choice based on the results of an analysis of the learner's academic ability.

[0009] The "means for generating a list of preferred schools and a list of backup schools" is a function that creates a list of schools from first to third choice based on the estimated pass rate, as well as a list of schools selected as a safety net in case the student is not accepted into the preferred school.

[0010] The "means for displaying the generated list" is a function for visually showing the learner the list of preferred schools and the list of backup schools.

[0011] "Means for creating a learner's study plan" is a function that allows learners to create specific plans for studying efficiently based on the analysis results and the displayed list.

[0012] "Means for inputting learners' daily learning progress" is a function that allows learners to record their daily study progress in the system.

[0013] The "means for collecting learning progress data" is a function for collecting and managing progress data entered by learners in one place.

[0014] "Means for adjusting learning plans" refers to a mechanism for amending and updating learning plans in accordance with the current situation based on collected learning progress data.

[0015] "Means for identifying weak areas and issues that need to be overcome" is a function for identifying areas where students perform particularly poorly or topics where they lack understanding from the results of analyzing their grades.

[0016] "Means of providing specific study methods and learning materials" is a function that suggests the optimal study methods for overcoming identified challenges and provides learners with the necessary learning materials and reference books. [Brief explanation of the drawings]

[0017] [Figure 1] 1 is a conceptual diagram showing an example of the configuration of a data processing system according to a first embodiment. [Figure 2] 1 is a conceptual diagram showing an example of main functions of a data processing device and a smart device according to a first embodiment. [Figure 3] FIG. 10 is a conceptual diagram showing an example of the configuration of a data processing system according to a second embodiment. [Figure 4] FIG. 10 is a conceptual diagram showing an example of main functions of a data processing device and smart glasses according to a second embodiment. [Figure 5] FIG. 10 is a conceptual diagram showing an example of the configuration of a data processing system according to a third embodiment. [Figure 6] FIG. 11 is a conceptual diagram showing an example of main functions of a data processing device and a headset-type terminal according to a third embodiment. [Figure 7] FIG. 10 is a conceptual diagram showing an example of the configuration of a data processing system according to a fourth embodiment. [Figure 8] FIG. 10 is a conceptual diagram showing an example of main functions of a data processing device and a robot according to a fourth embodiment. [Figure 9] 1 shows an emotion map onto which multiple emotions are mapped. [Figure 10] 1 shows an emotion map onto which multiple emotions are mapped. [Figure 11] FIG. 3 is a sequence diagram showing a processing flow of the data processing system according to the first embodiment. [Figure 12] FIG. 10 is a sequence diagram showing the flow of processing in the data processing system in Application Example 1. [Figure 13] FIG. 10 is a sequence diagram showing the flow of processing in the data processing system according to the second embodiment when an emotion engine is combined. [Figure 14] FIG. 10 is a sequence diagram showing the flow of processing in the data processing system in Application Example 2 when an emotion engine is combined. DETAILED DESCRIPTION OF THE INVENTION

[0018] An example of an embodiment of a system according to the technology of the present disclosure will be described below with reference to the accompanying drawings.

[0019] First, the terms used in the following description will be explained.

[0020] In the following embodiments, a coded processor (hereinafter simply referred to as a "processor") may be a single arithmetic device or a combination of multiple arithmetic devices. Furthermore, a processor may be a single type of arithmetic device or a combination of multiple types of arithmetic devices. Examples of arithmetic devices include a CPU (Central Processing Unit), a GPU (Graphics Processing Unit), a GPGPU (General-Purpose computing on Graphics Processing Units), and an APU (Accelerated Processing Unit).

[0021] In the following embodiments, a coded RAM (Random Access Memory) is a memory in which information is temporarily stored and is used as a working memory by a processor.

[0022] In the following embodiments, the coded storage is one or more non-volatile storage devices that store various programs, various parameters, etc. Examples of non-volatile storage devices include flash memory (SSD (Solid State Drive)), magnetic disks (e.g., hard disks), and magnetic tapes.

[0023] In the following embodiments, a communication I / F (Interface) with a symbol is an interface including a communication processor, an antenna, etc. The communication I / F controls communication between multiple computers. Examples of communication standards applied to the communication I / F include wireless communication standards including 5G (5th Generation Mobile Communication System), Wi-Fi (registered trademark), Bluetooth (registered trademark), etc.

[0024] In the following embodiments, "A and / or B" is synonymous with "at least one of A and B." In other words, "A and / or B" means that it may be only A, only B, or a combination of A and B. Furthermore, in this specification, the same concept as "A and / or B" is also applied when three or more things are expressed connected by "and / or."

[0025] [First embodiment]

[0026] FIG. 1 shows an example of the configuration of a data processing system 10 according to the first embodiment.

[0027] 1, a data processing system 10 includes a data processing device 12 and a smart device 14. An example of the data processing device 12 is a server.

[0028] The data processing device 12 includes a computer 22, a database 24, and a communication I / F 26. The computer 22 is an example of a "computer" according to the technology of the present disclosure. The computer 22 includes a processor 28, a RAM 30, and a storage 32. The processor 28, the RAM 30, and the storage 32 are connected to a bus 34. The database 24 and the communication I / F 26 are also connected to the bus 34. The communication I / F 26 is connected to a network 54. Examples of the network 54 include a WAN (Wide Area Network) and / or a LAN (Local Area Network).

[0029] The smart device 14 includes a computer 36, a reception device 38, an output device 40, a camera 42, and a communication I / F 44. The computer 36 includes a processor 46, a RAM 48, and a storage 50. The processor 46, the RAM 48, and the storage 50 are connected to a bus 52. The reception device 38, the output device 40, and the camera 42 are also connected to the bus 52.

[0030] The reception device 38 includes a touch panel 38A, a microphone 38B, and the like, and receives user input. The touch panel 38A detects contact with an indicator (for example, a pen or a finger) to receive user input by the touch of the indicator. The microphone 38B detects the user's voice to receive user input by voice. The control unit 46A transmits data indicating the user input received by the touch panel 38A and the microphone 38B to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the data indicating the user input.

[0031] The output device 40 includes a display 40A and a speaker 40B, and presents data to the user 20 by outputting the data in a form of expression that the user 20 can perceive (for example, audio and / or text). The display 40A displays visible information such as text and images in accordance with instructions from the processor 46. The speaker 40B outputs audio in accordance with instructions from the processor 46. The camera 42 is a compact digital camera equipped with an optical system including a lens, aperture, and shutter, and an imaging element such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor.

[0032] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 control the exchange of various information between the processor 46 and the processor 28 via the network 54.

[0033] FIG. 2 shows an example of the main functions of the data processing device 12 and the smart device 14.

[0034] 2, in the data processing device 12, a specific process is performed by the processor 28. A specific processing program 56 is stored in the storage 32. The specific processing program 56 is an example of a "program" according to the technology of the present disclosure. The processor 28 reads the specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific process is realized by the processor 28 operating as a specific processing unit 290 in accordance with the specific processing program 56 executed on the RAM 30.

[0035] The storage 32 stores a data generation model 58 and an emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290.

[0036] In the smart device 14, the processor 46 performs the reception output process. The storage 50 stores a reception output program 60. The reception output program 60 is used in conjunction with the specific processing program 56 by the data processing system 10. The processor 46 reads the reception output program 60 from the storage 50 and executes the read reception output program 60 on the RAM 48. The reception output process is realized by the processor 46 operating as the control unit 46A in accordance with the reception output program 60 executed on the RAM 48.

[0037] Next, a description will be given of the specific processing performed by the specific processing unit 290 of the data processing device 12. In the following description, the data processing device 12 will be referred to as a "server" and the smart device 14 will be referred to as a "terminal."

[0038] This system uses students' test scores and report card performance data to generate a list of schools of choice and backup schools, and indicates necessary study and challenges to overcome. The system consists of a server, terminals, and users (students).

[0039] System Configuration

[0040] 1. Data Collection

[0041] User (student):

[0042] Students enter their midterm and final exam scores, as well as their report card grades, into the terminal.

[0043] The data entered by the learner is saved on the device.

[0044] Device:

[0045] The terminal collects the input data and sends it to the server.

[0046] The terminal is equipped with an application and a web interface to provide a user interface.

[0047] 2. Data Analysis

[0048] server:

[0049] Receives data sent from the device and stores it in a database.

[0050] Check your data for outliers and missing values ​​and correct them if necessary.

[0051] Learners' test scores and grade data are analyzed to evaluate their performance in each subject.

[0052] Based on the analysis results, the learner's strengths and weaknesses are identified and their academic ability is evaluated.

[0053] 3. Pass rate estimation and list generation

[0054] server:

[0055] Based on the results of the student's academic assessment, the chances of them being accepted into their preferred school are estimated.

[0056] Refer to the data and statistics of past successful applicants for the school of your choice.

[0057] Generate a list of preferred schools (first to third choice) and a list of backup schools based on the acceptance rate.

[0058] Send your list of preferred schools and backup schools to your device.

[0059] 4. Feedback and learning plan creation

[0060] Device:

[0061] The generated list of preferred schools and backup schools is displayed to the learner.

[0062] Support the learner in creating an individualized learning plan based on the list they have reviewed.

[0063] server:

[0064] Based on an analysis of grades for each subject, weak areas and specific challenges are identified.

[0065] Recommend specific study methods and materials for identified issues.

[0066] Recommended study materials and methods are sent to your device.

[0067] 5. Learning progress management and feedback

[0068] User (student):

[0069] Daily study progress is entered into the device, including how much of each subject has been studied and the progress made.

[0070] Device:

[0071] The entered progress data is collected and sent to the server.

[0072] server:

[0073] Analyze your progress data to ensure your learning plan is on track.

[0074] Adjust the learning plan as needed and notify the learner.

[0075] Provide ongoing feedback to support effective learning.

[0076] Specific examples

[0077] Example 1: Test score analysis and feedback

[0078] User (student):

[0079] Enter 80 points for math, 70 points for English, 60 points for science, and 90 points for Japanese into the terminal.

[0080] The terminal collects the data and sends it to the server.

[0081] server:

[0082] The grade data is analyzed and it is determined that mathematics and Japanese are strong subjects, while science and English are weak subjects.

[0083] Calculate the acceptance rate for your desired school and make a list of your first, second, and third choice schools.

[0084] Recommended study methods include using problem sets that focus on specific areas of science and strengthening English vocabulary.

[0085] Device:

[0086] The analysis results are displayed to the learner and recommended learning methods are provided.

[0087] Example 2: Managing learning progress

[0088] User (student):

[0089] Enter your English study progress from the previous month into the device.

[0090] The device collects progress data and sends it to the server.

[0091] server:

[0092] Analyze progress data to determine if learning is not progressing as planned.

[0093] Adjust your English study plan and propose new ones.

[0094] Device:

[0095] Display the adjusted learning plan to the learner and provide feedback.

[0096] The above is an embodiment of the system of the present invention, which makes it possible to provide learners with individually optimized study plans and support for further education.

[0097] The processing flow will be explained below.

[0098] Step 1:

[0099] Students use the device to input their scores for each subject in midterm and final exams, as well as their report card grades. Specifically, they input their grades for each semester and their grades for each subject via the device's application or web interface.

[0100] Step 2:

[0101] The device collects test score and report card data entered by the user, which is then properly formatted and prepared for transmission to the server.

[0102] Step 3:

[0103] The terminal transmits the collected data to the server. This transmission is performed securely over a network.

[0104] Step 4:

[0105] The server receives the data sent from the device, stores it in a database, and uses it for subsequent analysis.

[0106] Step 5:

[0107] The server pre-processes the received data, which includes outlier detection and missing value imputation. Anomaly detection algorithms are applied to ensure data integrity and quality.

[0108] Step 6:

[0109] The server analyzes the preprocessed data and evaluates the user's academic ability. Specifically, it calculates a deviation score based on the scores for each subject and identifies strengths and weaknesses.

[0110] Step 7:

[0111] The server estimates the probability of passing the desired school based on the analysis results, comparing them with past successful applicant data and the school's passing criteria to calculate the user's chances of passing.

[0112] Step 8:

[0113] The server generates a list of preferred schools and a list of backup schools based on the estimated pass rate. The list includes first- to third-choice schools and recommended backup schools.

[0114] Step 9:

[0115] The server sends the generated list and analysis results to the device, formatting the data in a way that is easily accessible to the user.

[0116] Step 10:

[0117] The terminal displays the list of preferred schools and the list of backup schools sent from the server to the user, who can use this information to help formulate their own study plan.

[0118] Step 11:

[0119] The server identifies weak areas and issues that need to be overcome based on the results of the user's performance analysis, and selects specific study methods and recommended learning materials for the identified issues.

[0120] Step 12:

[0121] The server then sends the selected study methods and recommended learning materials to the device, allowing the user to study effectively.

[0122] Step 13:

[0123] The user inputs their daily learning progress into the terminal, and the input progress data is collected by the terminal.

[0124] Step 14:

[0125] The device sends the collected progress data to a server, which enables real-time learning progress management.

[0126] Step 15:

[0127] The server analyzes the progress data to ensure the learning plan is on track, adjusts it as needed, and generates a new plan.

[0128] Step 16:

[0129] The server sends the adjusted learning plan and feedback to the device, which the user can then confirm and continue learning.

[0130] Example 1

[0131] Next, a description will be given of Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the smart device 14 will be referred to as a "terminal."

[0132] In modern education, there is a demand for accurate assessment of each learner's academic ability and the provision of individualized learning plans based on that assessment. In particular, when selecting a school to attend, it is important to consider a learner's strengths and weaknesses and present effective learning methods. However, the current system does not adequately manage the creation of learning plans or learning progress, limiting the extent to which students can improve their academic ability. This makes it difficult to select a school to attend and create an effective learning plan, leading to problems such as reduced learning efficiency and motivation.

[0133] The specific processing by the specific processing unit 290 of the data processing device 12 in the first embodiment is realized by the following means.

[0134] In this invention, the server includes means for collecting input assessment data of learners, means for analyzing the learners' academic ability based on the collected data, means for estimating the pass rate for the desired school based on the analysis results, means for generating a list of educational institutions according to the pass rate estimated, means for displaying the generated list, means for creating a study plan for the learner based on the display means, and means for following up on the study plan. This allows for the evaluation of the learner's academic ability, selection of a school to attend, creation of an effective study plan, and progress management and feedback to be carried out in an integrated manner, thereby enabling the learner to improve their learning efficiency and achieve their goals.

[0135] "Inputted learner assessment data" refers to data such as test scores and report card grades entered by the learner.

[0136] "Means for analyzing academic ability" is a function that identifies a learner's strong and weak subjects based on collected evaluation data and evaluates the learner's overall academic ability.

[0137] "Means for estimating pass rates" is a function that statistically estimates the probability that a learner will be accepted into their desired school based on the results of academic ability analysis.

[0138] An "educational institution list" is a list of schools that a learner wishes to apply to, including their preferred school and backup schools.

[0139] The "means for displaying" is a function for providing the generated list of educational institutions to the learner and visually displaying it.

[0140] "Means for creating a study plan" is a function that allows learners to create a specific study plan to achieve their goals based on the displayed list of educational institutions.

[0141] "Means for following up on study plans" refers to a function for managing the progress of the study plans that have been created and adjusting the plans as necessary.

[0142] "Study progress data" refers to data such as the learning progress status and study time for each subject that is entered by the learner daily.

[0143] "Learning methods and materials" refers to the specific learning methods for a particular task and the instructions for the materials to be used.

[0144] This system uses student evaluation data to generate a list of schools of choice and backup schools, and creates and follows up on study plans. The system consists of a server, terminals, and users (student).

[0145] System Configuration

[0146] Data collection

[0147] User (learner):

[0148] The user enters into the terminal his or her test scores and report card grades for each subject, including, for example, math, English, science, and Japanese.

[0149] Device:

[0150] The terminal collects performance data entered by the user and sends it to the server. The terminal is equipped with an application or web interface and functions as a user interface. HTTP requests and JSON format data can be used for communication.

[0151] Data analysis

[0152] server:

[0153] The server receives the data sent from the device and stores it in a database system (e.g., MySQL (registered trademark) or PostgreSQL). Next, it cleans the data and corrects outliers and missing values. It then uses a generative AI model (e.g., using Python's Pandas or Scikit-learn library) to analyze the learner's performance data and evaluate their performance in each subject.

[0154] Pass rate estimation and list generation

[0155] server:

[0156] Based on the analysis results, the system estimates the student's chances of getting into their preferred school. This estimation uses data on past successful applicants and statistical data. Next, a list of educational institutions (first choice, third choice, and backup schools) is generated based on the chances of getting into the school and sent to the device.

[0157] Feedback and learning plan creation

[0158] Device:

[0159] The device displays the generated list of preferred schools and backup schools to the user, and supports the user in creating an individualized study plan based on the lists they have reviewed.

[0160] server:

[0161] Based on the results of the analysis of grades, the system identifies areas where the learner is weak and specific challenges. Specific learning methods and learning materials are recommended for the identified challenges and sent to the device.

[0162] Learning progress management and feedback

[0163] User (learner):

[0164] Users enter their daily study progress into the device, for example, recording which subjects they studied and how many hours they spent studying.

[0165] Device:

[0166] The device collects the progress data entered and sends it to the server, which analyzes the progress data to check whether the learning plan is progressing as planned, adjusts the learning plan as necessary, and notifies the user.

[0167] Specific examples

[0168] Example 1: Test score analysis and feedback

[0169] User (learner):

[0170] Enter 80 points for math, 70 points for English, 60 points for science, and 90 points for Japanese into the terminal.

[0171] Device:

[0172] The terminal collects the data and sends it to the server.

[0173] server:

[0174] The server analyzes the grade data, evaluates students' strengths and weaknesses, calculates their chances of getting into their preferred schools, and generates a list of schools they can apply to. It also recommends using workbooks that focus on specific science subjects and improving English vocabulary.

[0175] Device:

[0176] The device displays the analysis results and recommended learning methods to the learner.

[0177] Example 2: Managing learning progress

[0178] User (learner):

[0179] Enter your English study progress from the previous month into the device.

[0180] Device:

[0181] The device collects progress data and sends it to the server.

[0182] server:

[0183] The server analyzes the progress data and determines if the student's learning is not going as planned. It adjusts the student's English learning plan and proposes a new plan.

[0184] Device:

[0185] The device displays the adjusted learning plan to the learner and provides feedback.

[0186] Prompt Sentence Examples

[0187] "Write a program where the user inputs grades for each subject, the system determines which subjects the user is good at and which subjects they are bad at, and generates a list of schools they want to apply to. Specifically, the system will analyze grade data for 80 points in math, 70 points in English, 60 points in science, and 90 points in Japanese, and generate a list of schools they want to apply to."

[0188] The above is an embodiment of the invention. This system makes it possible to provide learners with individually optimized learning plans and support for further education.

[0189] The flow of the identification process in the first embodiment will be described with reference to FIG.

[0190] Step 1:

[0191] The user (student) enters performance data:

[0192] Users enter their test scores and report card grades for each subject using a device application or a web interface. The data entered includes the grades for each subject (e.g., math 80 points, English 70 points, science 60 points, Japanese 90 points).

[0193] Input: Grade data for each subject

[0194] Output: Achievement data saved on the device

[0195] Step 2:

[0196] Device collects and transmits performance data:

[0197] The terminal temporarily stores the performance data entered by the user and sends it to the server. The data is encoded in JSON format and sent via an HTTP request.

[0198] Input: Achievement data saved on the device

[0199] Output: Achievement data sent to the server

[0200] Step 3:

[0201] The server receives and stores the performance data:

[0202] The server receives the grade data sent from the device and stores it in a database (e.g., MySQL or PostgreSQL). The received data includes grade information for each subject.

[0203] Input: Performance data sent from the device

[0204] Output: Achievement data stored in a database

[0205] Step 4:

[0206] The server parses the data:

[0207] The server retrieves the stored grade data and performs data cleaning, checking for outliers and missing values ​​and correcting them as necessary. It then uses a generative AI model (using, for example, Python's Pandas or Scikit-learn libraries) to evaluate performance in each subject and identify strong and weak subjects.

[0208] Input: Achievement data stored in the database

[0209] Output: Analysis results including strong and weak subjects

[0210] Step 5:

[0211] The server estimates the pass rate and generates a list:

[0212] Based on the analysis results, the server evaluates the student's academic ability and statistically estimates the student's chances of being accepted into their preferred school. This estimation uses data on past successful applicants and statistical data. It then generates a list of preferred schools and a list of backup schools.

[0213] Input: Analysis results including strong and weak subjects

[0214] Output: List of preferred schools and backup schools

[0215] Step 6:

[0216] The server sends the list to the device:

[0217] The generated list of preferred schools and alternative schools is sent to the device. The data is encoded in JSON format and sent via an HTTP request.

[0218] Input: List of preferred schools and backup schools

[0219] Output: List of preferred schools and backup schools sent to the terminal

[0220] Step 7:

[0221] The terminal displays the list to the user:

[0222] The terminal displays the received list of preferred schools and backup schools to the user, using an application or web page as the user interface.

[0223] Input: List of preferred schools and backup schools sent to the device

[0224] Output: A list of preferred and alternative schools displayed to the user

[0225] Step 8:

[0226] User enters learning progress data:

[0227] Users input their daily study progress into the device, for example, recording the study time and progress for each subject (e.g., studied English for 2 hours).

[0228] Input: Daily learning progress data

[0229] Output: Learning progress data saved on the device

[0230] Step 9:

[0231] Your device collects and transmits learning progress data:

[0232] The device collects learning progress data entered by the user and sends it to the server, where it is encoded in JSON format and sent via an HTTP request.

[0233] Input: Learning progress data stored on the device

[0234] Output: Learning progress data sent to the server

[0235] Step 10:

[0236] The server analyzes the progress data and provides feedback:

[0237] The server analyzes the received progress data, checks whether the learning plan is progressing as planned, adjusts the learning plan if necessary, creates a new learning plan, and notifies the user.

[0238] Input: Learning progress data sent to the server

[0239] Output: Feedback and adjusted learning plan provided to the user

[0240] (Application example 1)

[0241] Next, a description will be given of Application Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the smart device 14 will be referred to as a "terminal."

[0242] Conventional educational support systems are limited to analyzing students' academic performance data and estimating their chances of getting into their preferred schools, and do not adequately create specific study plans or manage progress. Furthermore, they do not provide specific learning materials or methods to help students overcome their weaknesses, limiting the effectiveness of improving their learning efficiency. Furthermore, these functions needed to be integrated into an educational support application provided in a virtual store. The present invention aims to provide a system that solves these problems.

[0243] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 1 is realized by the following means.

[0244] In this invention, the server includes means for collecting input test scores and performance data of learners, means for analyzing the learner's academic ability based on the collected data, means for estimating the pass rate for the desired school based on the analysis results, means for generating a list of desired schools and a list of backup schools according to the estimated pass rate, means for displaying the generated lists, means for creating a study plan for the learner based on the display means, means for recommending learning materials and study methods to help the learner overcome weaknesses based on the study plan and list of desired schools, and means for collecting and analyzing the learner's progress with the recommended learning materials and study methods. This enables learning support and support for further education that are individually optimized for each learner.

[0245] A "learner" is someone who belongs to an educational institution and takes tests and assessments.

[0246] A "test score" is the score or marks a learner receives when taking an exam or assessment.

[0247] "Academic performance data" refers to information indicating a learner's academic performance as assessed in the form of a report card, a report, or the like.

[0248] "Means for analyzing academic ability" refers to methods or systems for analyzing learners' test scores and grade data and evaluating their academic ability in each subject and overall.

[0249] A "means for estimating pass rates" is a method or algorithm for calculating the probability of a student being accepted into a school of their choice based on their current academic ability data.

[0250] A "school of choice list" is a list of schools that a student wishes to attend, ranked based on their acceptance rate.

[0251] A "safety school list" is a list of schools that have a high chance of acceptance in case you are not accepted into your preferred school.

[0252] "Display means" refers to the method or device for visually presenting the generated school preference list and other information to the learner.

[0253] A "means for creating a study plan" is a method or system for constructing daily study content and schedules to help learners achieve their goals.

[0254] "Means for recommending learning materials and learning methods" are systems or algorithms that suggest appropriate learning materials and effective learning methods to address learners' weaknesses and challenges.

[0255] "Means for collecting and analyzing progress" refers to methods and systems for recording learners' daily learning activities and evaluating whether they are progressing as planned.

[0256] A "virtual store" is a virtual shop or platform that provides educational services and teaching materials via the Internet.

[0257] This system uses a student's test scores and report card grade data to generate a list of schools of choice and backup schools, and indicates necessary study and challenges to overcome. This system is composed of a server, a terminal (such as a smartphone or PC), and a user (a student).

[0258] System Configuration

[0259] 1. Data Collection

[0260] User (learner):

[0261] Students enter their midterm and final exam scores, as well as their report card grades, into the terminal.

[0262] The data entered by the learner is saved on the device.

[0263] Device:

[0264] The terminal collects the input data and sends it to the server.

[0265] The terminal is equipped with an application and a web interface to provide a user interface.

[0266] 2. Data Analysis

[0267] server:

[0268] Receives data sent from the device and stores it in a database.

[0269] Check your data for outliers and missing values ​​and correct them if necessary.

[0270] Learners' test scores and grade data are analyzed to evaluate their performance in each subject.

[0271] Based on the analysis results, the learner's strengths and weaknesses are identified and their academic ability is evaluated.

[0272] 3. Pass rate estimation and list generation

[0273] server:

[0274] Based on the results of the student's academic assessment, the chances of them being accepted into their preferred school are estimated.

[0275] Refer to the data and statistics of past successful applicants for the school of your choice.

[0276] Generate a list of preferred schools (first to third choice) and a list of backup schools based on the acceptance rate.

[0277] Send your list of preferred schools and backup schools to your device.

[0278] 4. Feedback and learning plan creation

[0279] Device:

[0280] The generated list of preferred schools and backup schools is displayed to the learner.

[0281] Support the learner in creating an individualized learning plan based on the list they have reviewed.

[0282] server:

[0283] Based on an analysis of grades for each subject, weak areas and specific challenges are identified.

[0284] Recommend specific study methods and materials for identified issues.

[0285] Recommended study materials and methods are sent to your device.

[0286] 5. Learning progress management and feedback

[0287] User (learner):

[0288] Daily study progress is entered into the device, including how much of each subject has been studied and the progress made.

[0289] Device:

[0290] The entered progress data is collected and sent to the server.

[0291] server:

[0292] Analyze your progress data to ensure your learning plan is on track.

[0293] Adjust the learning plan as needed and notify the learner.

[0294] Provide ongoing feedback to support effective learning.

[0295] Specific examples

[0296] User (learner):

[0297] Enter 80 points for math, 70 points for English, 60 points for science, and 90 points for Japanese into the terminal.

[0298] The terminal collects the data and sends it to the server.

[0299] server:

[0300] The grade data is analyzed and it is determined that mathematics and Japanese are strong subjects, while science and English are weak subjects.

[0301] Calculate the acceptance rate for your desired school and make a list of your first, second, and third choice schools.

[0302] Recommended study methods include using problem sets that focus on specific areas of science and strengthening English vocabulary.

[0303] Device:

[0304] The analysis results are displayed to the learner and recommended learning methods are provided.

[0305] The above series of processes realizes learning support that is optimized for each learner. As a concrete example, let us consider the following prompt sentence as input to the generative AI model.

[0306] Example prompt sentence:

[0307] "A student's test scores are: Math 80, English 70, Science 60, Japanese 90. In this case, please list the student's first, second, and third choice schools. Also, please suggest the best study methods for English and Science, which are the weaker subjects."

[0308] In this way, by utilizing generative AI models, it is possible to provide more accurate learning assistance.

[0309] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[0310] Step 1:

[0311] Users input test scores and grade data. Specifically, learners input their midterm and final exam scores and report card scores into a smartphone or PC device. The input data includes the scores for each subject. After input, the data is temporarily stored on the device.

[0312] Step 2:

[0313] The device sends the collected data to a server. The device is equipped with an application or web interface that formats the data entered by the user and sends it to the server. The data is encrypted before being sent.

[0314] Step 3:

[0315] The server receives the data and stores it in the database. The server checks the integrity of the data and corrects any outliers or missing values. For example, if a math score is over 100, it is treated as an outlier. After checking that the data is in the correct format, it is stored in the database.

[0316] Step 4:

[0317] The server analyzes the learner's test scores and performance data. It uses analytical algorithms to evaluate performance in each subject. Specifically, it calculates the mean and standard deviation of scores and identifies strengths and weaknesses in each subject. Algorithms used here include XGBoost and linear regression models.

[0318] Step 5:

[0319] The server estimates the pass rate for the student's desired school based on the analysis results. It compares the student's scores with past successful applicant data and statistical data to calculate the pass rate for the desired school. For example, using the XGBoost model, the pass rate can be estimated by inputting data for 80 points in math, 70 points in English, 60 points in science, and 90 points in Japanese.

[0320] Step 6:

[0321] The server generates a list of preferred schools and a list of backup schools according to the pass rate. Based on the calculated pass rate, lists of first-choice, second-choice, third-choice, etc. are created. A list of backup schools with relatively high pass rates is also generated at the same time.

[0322] Step 7:

[0323] The server sends the generated list to the terminal. After generating the list, the server sends it to the terminal. At this time, the data is encrypted again and sent. The data is formatted in the appropriate format so that it can be displayed correctly on the terminal.

[0324] Step 8:

[0325] The device displays the student's list of preferred schools and backup schools. The list is displayed for easy access by the student through the device's application or web interface. Specifically, the list is displayed in list format along with the acceptance rate for each preferred school.

[0326] Step 9:

[0327] The server analyzes the learner's weak areas and the challenges they need to overcome. Based on the results of the analysis, it identifies subjects and areas where students have particularly low scores and evaluates what learning methods are most effective.

[0328] Step 10:

[0329] The server then recommends learning materials and methods that address the identified issues. For example, it might recommend a workbook focused on a specific area of ​​science or an app to improve English vocabulary. This recommendation information is selected using an analytical algorithm.

[0330] Step 11:

[0331] The device will display recommended learning materials and methods to the learner, who can then review the recommended materials and methods and incorporate them into their own learning plans.

[0332] Step 12:

[0333] The user inputs their daily learning progress into the device. The learner inputs their daily learning content and progress and saves it on the device. The input data includes the subjects studied, the time spent, and the progress status.

[0334] Step 13:

[0335] The terminal sends the entered progress data to the server. The terminal formats the progress data entered by the learner and sends it to the server.

[0336] Step 14:

[0337] The server analyzes the progress data to check whether the learning plan is progressing as planned. Based on the progress data, the server evaluates whether the learner's plan is progressing properly and makes adjustments as necessary.

[0338] Step 15:

[0339] The server sends the results of the adjustments to the learning plan to the device. If the plan is not progressing as planned, a new learning plan will be proposed and sent to the device.

[0340] Step 16:

[0341] The device will then display the adjusted study plan to the learner. By presenting the new plan, the learner can study more efficiently.

[0342] The above processing steps enable learners to receive individually optimized learning support and maximize their learning outcomes. Specifically, by inputting the following prompt sentences into the generative AI model, highly accurate analysis and feedback can be obtained.

[0343] Example prompt sentence:

[0344] "A student's test scores are: Math 80, English 70, Science 60, Japanese 90. In this case, please list the student's first, second, and third choice schools. Also, please suggest the best study methods for English and Science, which are the weaker subjects."

[0345] Furthermore, an emotion engine that estimates the user's emotion may be combined. That is, the identification processing unit 290 may estimate the user's emotion using the emotion identification model 59 and perform identification processing using the user's emotion.

[0346] This invention combines a system that uses a learner's test scores and report card grade data to generate a list of preferred and backup schools, and indicates necessary study and challenges to overcome, with an emotion engine that recognizes the user's emotions. The system is composed of a server, terminals, and users (students).

[0347] System Configuration

[0348] 1. Data Collection

[0349] User (student):

[0350] Students input their scores for each subject in midterm and final exams, as well as their report card grades, into the terminal using a terminal application or a web interface.

[0351] Device:

[0352] The terminal collects the entered data, formats it appropriately, and sends it to the server.

[0353] 2. Data Analysis

[0354] server:

[0355] The server receives the data sent from the terminal and stores it in a database.

[0356] Preprocessing such as outlier detection and missing value completion is performed on the received data.

[0357] Analyze the pre-processed data to evaluate the learner's academic ability, identifying scores, deviation values, strengths and weaknesses for each subject.

[0358] 3. Pass rate estimation and list generation

[0359] server:

[0360] Based on the results of the academic assessment, the system estimates the chances of passing the desired school. It also calculates the user's chances of passing by referencing past passing data and the school's passing criteria.

[0361] Based on the estimated pass rate, a list of preferred schools (first to third choice) and a list of backup schools are generated.

[0362] Send your list of preferred schools and backup schools to your device.

[0363] 4. Feedback and learning plan creation

[0364] Device:

[0365] The data received from the server is displayed to the user, who can then check the list of schools of choice and the results of the grade analysis.

[0366] Based on the results of the analysis of a learner's grades, we identify areas of weakness and challenges that need to be overcome, and then present specific study methods and recommended materials to address these challenges.

[0367] server:

[0368] Specific study methods and recommended study materials to overcome weak areas are selected and sent to the device.

[0369] 5. Emotional awareness and learning plan adjustment

[0370] Emotion Engine:

[0371] It recognizes emotions from the user's facial expressions, tone of voice, input content, etc., and identifies the user's current emotional state.

[0372] server:

[0373] The learning plan is adjusted based on the recognized emotional data, for example, adjusting the amount or difficulty of learning if the user is feeling stressed.

[0374] Depending on the recognized emotion, encouraging messages and appropriate feedback are generated and sent to the device.

[0375] 6. Learning progress management and feedback

[0376] User (student):

[0377] Daily study progress is entered into the device, including how much of each subject has been studied and the progress made.

[0378] Device:

[0379] The entered progress data is collected and sent to the server.

[0380] server:

[0381] Analyze progress data to ensure your learning plan is on track, adjust it if necessary, and generate a new plan.

[0382] The adjusted learning plan and feedback are sent to the device, where the user can confirm and continue learning.

[0383] Specific examples

[0384] Example 1: Test score analysis and feedback

[0385] User (student):

[0386] The student enters their scores into the terminal: 80 points for math, 70 points for English, 60 points for science, and 90 points for Japanese. The terminal collects the data and sends it to the server.

[0387] server:

[0388] The grade data is analyzed and it is determined that mathematics and Japanese are strong subjects, while science and English are weak subjects.

[0389] Calculate the acceptance rate for your desired school and make a list of your first, second, and third choice schools.

[0390] Recommended study methods include using problem sets that focus on specific areas of science and strengthening English vocabulary.

[0391] Device:

[0392] The analysis results are displayed to the learner and recommended learning methods are provided.

[0393] Emotion Engine:

[0394] The system recognizes whether the user is feeling anxious or stressed from their facial expressions and tone of voice while they are typing.

[0395] server:

[0396] Based on the recognized emotion data, the system generates encouraging messages and suggests adjustments to the amount of study. For example, it provides messages such as, "You seem to be good at math! Keep it up!"

[0397] Example 2: Managing learning progress

[0398] User (student):

[0399] The user enters their English study progress from the previous month into the device, which then collects the progress data and sends it to the server.

[0400] server:

[0401] Analyze progress data to determine if learning is not progressing as planned.

[0402] Adjust your English study plan and propose new ones.

[0403] Emotion Engine:

[0404] The emotion engine recognizes that the user is feeling stressed from their facial expressions and voice when entering their progress.

[0405] server:

[0406] Based on the recognized emotions, the system suggests educational materials that can be understood quickly and efficiently to reduce stress.

[0407] Device:

[0408] Provide users with tailored learning plans and feedback to support their learning.

[0409] summary

[0410] The system of the present invention allows learners to receive efficient and personalized learning support based on their own performance data and progress. Furthermore, by combining it with an emotion engine, appropriate feedback and adjustments to the learning plan are made according to the user's emotional state, enabling effective learning while reducing stress.

[0411] The processing flow will be explained below.

[0412] Step 1:

[0413] Students use the device to input their scores for each subject in midterm and final exams, as well as their report card grades. Specifically, they input their grades for each semester and their grades for each subject via the device's application or web interface.

[0414] Step 2:

[0415] The device collects test score and report card data entered by the user, which is then prepared and properly formatted for transmission to the server.

[0416] Step 3:

[0417] The terminal transmits the collected data to the server. This transmission is performed securely over a network.

[0418] Step 4:

[0419] The server receives the data sent from the device, stores it in a database, and uses it for subsequent analysis.

[0420] Step 5:

[0421] The server pre-processes the received data, which includes outlier detection and missing value imputation. Anomaly detection algorithms are applied to ensure data integrity and quality.

[0422] Step 6:

[0423] The server analyzes the preprocessed data and evaluates the user's academic ability. Specifically, it calculates a deviation score based on the scores for each subject and identifies strengths and weaknesses.

[0424] Step 7:

[0425] The server estimates the probability of passing the desired school based on the analysis results, comparing them with past successful applicant data and the school's passing criteria to calculate the user's chances of passing.

[0426] Step 8:

[0427] The server generates a list of preferred schools and a list of backup schools based on the estimated pass rate. The list includes first- to third-choice schools and recommended backup schools.

[0428] Step 9:

[0429] The server sends the generated list and analysis results to the device, formatting the data in a way that is easily accessible to the user.

[0430] Step 10:

[0431] The terminal displays the list of preferred schools and the list of backup schools sent from the server to the user, who can use this information to help formulate their own study plan.

[0432] Step 11:

[0433] The server identifies weak areas and issues that need to be overcome based on the results of the user's performance analysis, and selects specific study methods and recommended learning materials for the identified issues.

[0434] Step 12:

[0435] The server then sends the selected study methods and recommended learning materials to the device, allowing the user to study effectively.

[0436] Step 13:

[0437] The emotion engine recognizes emotions from the user's facial expressions, tone of voice, and input content to identify the user's current emotional state.

[0438] Step 14:

[0439] The server receives the emotion data recognized by the emotion engine and adjusts the study plan, for example, reducing the amount of study or lowering the difficulty level if the user is feeling stressed.

[0440] Step 15:

[0441] The server generates encouraging messages and appropriate feedback based on the recognized emotion data and sends them to the device, such as "You seem to be good at math! Keep it up!"

[0442] Step 16:

[0443] Users enter their daily study progress into the terminal, including how much they studied and what subjects they studied, as well as their progress.

[0444] Step 17:

[0445] The terminal collects the entered progress data and transmits it to the server.

[0446] Step 18:

[0447] The server analyzes the progress data to ensure the learning plan is on track, adjusts it as needed, and generates a new plan.

[0448] Step 19:

[0449] The server sends the adjusted learning plan and feedback to the device, which the user can then confirm and continue learning.

[0450] The above is a specific flow of processing in the system of the present invention. By providing individually optimized learning support while taking into consideration the user's emotions, learning efficiency is improved and stress is reduced.

[0451] Example 2

[0452] Next, a description will be given of Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the smart device 14 will be referred to as a "terminal."

[0453] In conventional educational systems, learning plans are often created based on a learner's academic performance data, but they lack the ability to adjust to the learner's individual emotional state. This can lead to learners feeling stressed or anxious, which can hinder their ability to perform at their best and result in less than optimal learning outcomes. There is a need for a system that provides a comprehensive approach that takes into account not only academic performance data but also daily learning progress and emotional state.

[0454] The identification process by the identification processing unit 290 of the data processing device 12 in the second embodiment is realized by the following means. In this invention, the server includes means for collecting input academic performance data of the learner, means for analyzing the learner's academic ability based on the collected data, means for estimating the pass rate for the desired school based on the analysis results, means for generating a list of desired schools and a list of backup schools according to the estimated pass rate, means for displaying the generated lists, means for creating a study plan for the learner based on the display means, means for recognizing the learner's emotional state, and means for adjusting the study plan based on the recognized emotional state. This enables comprehensive learning support that takes into account the learner's emotional state.

[0455] "Academic performance data" refers to data including the scores obtained by a learner in each subject and the grades on their report cards.

[0456] "Academic ability" refers to the results of assessing a learner's scores in each subject and their overall learning ability.

[0457] "Analysis results" refers to the output of a learner's academic ability assessment based on the collected data.

[0458] "Preferred school" refers to the educational institution that a learner wishes to attend.

[0459] The "pass rate" is a value indicating the probability that a learner will pass the entrance examination to the school of their choice.

[0460] A "preferred school list" is a list of educational institutions that a learner wishes to attend, ranked in order.

[0461] A "safety school list" is a list of educational institutions that a student may consider attending if they are not accepted into their preferred school.

[0462] "Display means" refers to a device or method for displaying the generated list, analysis results, etc. to the learner.

[0463] A "study plan" refers to the specific learning content and schedule set out to help learners progress effectively in their studies.

[0464] "Emotional state" refers to the learner's current emotional state, including, for example, stress, anxiety, and motivation.

[0465] The present invention is a system that combines a learner's performance data and emotional state to provide an optimal study plan. This system is composed of a server, a terminal, and a user (learner).

[0466] server:

[0467] The server receives the grade data sent from the device and stores it in a database. It then analyzes the grade data to evaluate the learner's academic ability. Specifically, it performs preprocessing such as outlier detection and missing value imputation. Based on the preprocessed data, it calculates the deviation score for each subject, as well as the student's strong and weak subjects. Based on the analysis results, it estimates the student's chances of getting into their preferred school. Using this chance as a reference, it generates a list of first- to third-choice schools and a list of safety schools. The server also has the ability to recognize the learner's emotional state and reflect this data in the study plan. For example, if the learner is feeling stressed, it can reduce the amount of study or adjust the difficulty level.

[0468] Device:

[0469] The terminal provides an interface for users to input grade data and progress data. For example, learners use a terminal application or web interface to input their grades for each subject and their report card grades. The terminal then converts the received data into an appropriate format and sends it to the server. The terminal then displays the analysis results, preferred school list, study plan, and emotional feedback sent from the server to the user. A dashboard using a graphical user interface (GUI) is provided to make it easy for learners to check the data.

[0470] User (learner):

[0471] Users input their scores for each subject in midterm and final exams, as well as report card grades, through the device. They also input their daily learning progress into the device and send it to the server as appropriate. Learning progresses based on the learning plan and feedback received from the device. The device's camera and microphone are also used to recognize the user's emotional state, providing an appropriate learning method that matches their emotional state.

[0472] Examples:

[0473] For example, if a user inputs "80 points in math, 70 points in English, 60 points in science, and 90 points in Japanese" into the device, the device converts the data into JSON format and sends it to the server. The server analyzes the grade data and determines that math and Japanese are strong subjects, while science and English are weak subjects. The server calculates the pass rate and displays it as 70% for the first choice school, 50% for the second choice school, and 90% for the third choice school. Recommended study methods include using workbooks that focus on specific areas of science and strengthening English vocabulary. As the user inputs progress data into the device, the server analyzes the progress and adjusts the study plan.

[0474] Furthermore, the emotion engine recognizes that if the user frowns while typing, they are feeling anxious, and adjusts the amount of learning they are doing, sending encouraging messages such as, "You seem to be good at math! Keep it up!"

[0475] This system not only provides learners with optimal study plans based on their performance data, but also provides flexible feedback and study adjustments that are tailored to their emotional state at the time, enabling efficient and stress-free learning.

[0476] The flow of the identification process in the second embodiment will be described with reference to FIG.

[0477] Step 1:

[0478] User: The learner uses a terminal application or a web interface to input the scores for each subject in the midterm and final exams, as well as the grade data from the report card. For example, the learner enters "80 points for math, 70 points for English, 60 points for science, and 90 points for Japanese."

[0479] Input: Score and grade data for each subject entered by the user

[0480] Output: Performance data sent to the device

[0481] Step 2:

[0482] Terminal: The terminal collects the grade data entered by the user and converts it into an appropriate format. Specifically, it converts the input data into JSON format. For example, it formats it as follows: {"Subject": {"Math": 80, "English": 70, "Science": 60, "Japanese": 90}}.

[0483] Input: User-entered grade data

[0484] Output: Formatted data (JSON format)

[0485] Step 3:

[0486] Terminal: Sends the collected and formatted performance data to the server, for example, using HTTP requests.

[0487] Input: Formatted data (JSON format)

[0488] Output: Grade data sent to the server

[0489] Step 4:

[0490] Server: The server receives the performance data sent from the device and stores it in a database. When storing the data, it associates it with each user's ID.

[0491] Input: Performance data sent from the device

[0492] Output: Achievement data stored in the database

[0493] Step 5:

[0494] Server: Preprocesses the saved grade data. Performs outlier detection and missing value imputation to ensure data accuracy. An outlier, for example, would be a negative score for each subject, and corrects it to within the normal range.

[0495] Input: Achievement data stored in the database

[0496] Output: Preprocessed grade data

[0497] Step 6:

[0498] Server: Analyzes the pre-processed data and evaluates the user's academic ability. Specifically, it calculates the deviation score and strong and weak subjects based on the scores for each subject.

[0499] Input: Preprocessed grade data

[0500] Output: Academic ability analysis results (deviation score for each subject, strong and weak subjects)

[0501] Step 7:

[0502] Server: Based on the results of the academic ability analysis, estimate the probability of admission to the user's desired school. In this case, past admission data and school standards are used as reference.

[0503] Input: Academic ability analysis results

[0504] Output: Pass rate estimation result

[0505] Step 8:

[0506] Server: Based on the estimated pass rate, it generates a list of preferred schools and a list of backup schools and sends this to the terminal.

[0507] Input: Pass rate estimation result

[0508] Output: List of preferred schools, list of backup schools

[0509] Step 9:

[0510] Terminal: Displays the list of schools of choice sent from the server and the results of the academic ability analysis to the user. The user can check the analysis results and the list.

[0511] Input: Preferred school list sent from the server, academic ability analysis results

[0512] Output: Displayed list of preferred schools, academic ability analysis results

[0513] Step 10:

[0514] Server: Selects specific study methods and recommended learning materials to help learners overcome their weak areas and sends them to the device.

[0515] Input: Academic ability analysis results (weak subjects)

[0516] Output: Study methods and recommended materials

[0517] Step 11:

[0518] Device: Displays study methods and recommended learning materials to the user. The user creates a study plan based on the information provided.

[0519] Input: Study methods and recommended materials sent from the server

[0520] Output: Displayed study methods and recommended materials

[0521] Step 12:

[0522] Emotion engine: Recognizes emotions from the user's facial expressions, tone of voice, and input content to identify their current emotional state. For example, if the user frowns while typing, it determines that they are feeling anxious.

[0523] Input: User facial expressions, tone of voice, and input

[0524] Output: Perceived emotional state

[0525] Step 13:

[0526] Server: Adjusts the study plan based on the recognized emotion data. For example, if the user is feeling stressed, the server suggests adjusting the amount of study or difficulty.

[0527] Input: Perceived emotional state

[0528] Output: Adjusted lesson plan

[0529] Step 14:

[0530] Server: Generates encouraging messages and appropriate feedback based on the recognized emotions and sends them to the device. For example, it provides a message like, "You seem to be good at math! Keep it up!"

[0531] Input: Perceived emotional state

[0532] Output: Encouraging message, feedback

[0533] Step 15:

[0534] Device: Displays tailored study plans and encouraging messages to users, allowing them to receive appropriate study methods tailored to their emotional state.

[0535] Input: Tailored study plan and encouraging messages sent from the server

[0536] Output: A displayed lesson plan and encouraging messages

[0537] Step 16:

[0538] User: Enters daily learning progress into the device. For example, progress information such as "English: Study 3 hours a week, Science: Study 2 hours a week" is recorded.

[0539] Input: Daily learning progress

[0540] Output: Progress data sent to the device

[0541] Step 17:

[0542] Terminal: Sends the collected progress data to the server, for example, using HTTP requests.

[0543] Input: Collected progress data

[0544] Output: Progress data sent to the server

[0545] Step 18:

[0546] Server: Analyzes progress data and checks whether the lesson plan is on track. If it is behind schedule, adjusts the plan and generates a new lesson plan.

[0547] Input: Progress data

[0548] Output: Progress analysis results, adjusted learning plan

[0549] Step 19:

[0550] Server: Sends the adjusted learning plan and feedback to the device, allowing the user to receive an appropriate learning plan based on their current progress.

[0551] Input: Tailored learning plan, feedback

[0552] Output: Learning plan and feedback sent to the device

[0553] Step 20:

[0554] Device: The adjusted learning plan and feedback are displayed to the user to support their learning. The user can then review the plan and continue their learning.

[0555] Input: Learning plan and feedback sent from the server

[0556] Output: Displayed lesson plan, feedback

[0557] (Application example 2)

[0558] Next, a description will be given of Application Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the smart device 14 will be referred to as a "terminal."

[0559] Modern factories require robots to improve the efficiency and optimization of their work, but there are limitations to systems that can accurately evaluate a robot's operating status and work efficiency and suggest improvement measures. Furthermore, there is a lack of functionality to recognize a robot's stress or illness using an emotion engine and propose appropriate countermeasures. Therefore, there is a need for a system that can improve the efficiency of robots and flexibly adjust work plans according to the robot's condition.

[0560] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 2 is realized by the following means.

[0561] In this invention, the server includes means for collecting input worker data, means for analyzing worker efficiency based on the collected data, means for estimating a work plan based on the analysis results, means for generating efficiency improvement measures in accordance with the estimated work plan, means for displaying the generated efficiency improvement measures, means for creating a work plan for the worker based on the display means, means for inputting the worker's daily work progress and collecting the work progress data, means for adjusting the work plan based on the collected progress data, and means for identifying the worker's weak areas and challenges to overcome based on the estimated work plan and providing specific work methods and tools to address the identified challenges. This enables improved robot work efficiency and flexible adjustment of the work plan in response to the robot's stress or illness.

[0562] "Workers" refers to factory robots and the personnel who operate and manage them.

[0563] "Work data" refers to data that includes information such as the operating status of factory robots, work progress, and error rates.

[0564] "Efficiency analysis" is the process of analyzing and evaluating the work efficiency of workers and robots based on collected work data.

[0565] A "work plan" is a plan that specifies the work content and procedures to be performed by workers and robots.

[0566] "Efficiency improvement measures" are proposals that include specific methods and actions to improve the work efficiency of workers and robots.

[0567] The "emotion engine" is a system that analyzes the state of workers and robots and recognizes emotions such as stress and illness.

[0568] A "work method" is a specific operational procedure or technique used by a worker or robot to perform a specific task.

[0569] "Tools" refers to the equipment and tools used by workers and robots when performing work.

[0570] System Configuration

[0571] The system that realizes this application example consists of three main elements: a server, a terminal, and a user (operator).

[0572] 1. Data Collection

[0573] User (worker)

[0574] During their daily work, workers input work data via devices such as tablets or smartphones, including specific work items, progress, and any problems that arise.

[0575] Terminal

[0576] The terminal collects the input work data, formats it appropriately, and sends it to the server. The terminal is also connected to peripheral devices such as a camera and microphone, which can be used to monitor the work status in real time.

[0577] 2. Data Analysis

[0578] server

[0579] The server receives the data sent from the terminal and stores it in a database. The received data undergoes preprocessing, such as outlier detection and missing value completion. The preprocessed data is then analyzed to evaluate the worker's work efficiency. Specifically, the progress and error rate of each work item are analyzed to identify the strengths and weaknesses of the work.

[0580] 3. Estimating and generating work plans

[0581] server

[0582] The server estimates the optimal work plan based on the results of the work efficiency evaluation. It calculates the worker's work plan by referencing past work data and efficiency standards. At this time, it also makes suggestions, including measures to improve efficiency. Furthermore, based on the estimation results, it suggests the optimal work method and tools that the worker should use.

[0583] 4. Suggestions and Feedback

[0584] Terminal

[0585] The data received from the server is displayed to the worker, who checks the estimated work plan and efficiency improvement measures and proceeds with the work accordingly.

[0586] 5. Managing and adjusting learning progress

[0587] User (worker)

[0588] Daily work progress is entered into the terminal, including how much progress has been made on each task and the progress status.

[0589] Terminal

[0590] The entered progress data is collected and sent to the server.

[0591] server

[0592] Analyze progress data to see if the work plan is progressing as planned. Adjust the work plan as needed and generate a new plan. Send the adjusted work plan and feedback to the device.

[0593] 6. Emotion recognition and work plan adjustment

[0594] Emotion Engine

[0595] It recognizes emotions from the worker's facial expressions, tone of voice, input content, etc., and identifies the worker's current emotional state.

[0596] server

[0597] The system adjusts the work plan based on the recognized emotion data. For example, if the worker is feeling stressed, it adjusts the workload or difficulty level. Depending on the recognized emotion, it generates encouraging messages or appropriate feedback and sends them to the device.

[0598] Specific examples

[0599] Specific examples including example prompts

[0600] Analyze the operating status of Area A and evaluate daily work efficiency and error rates. In addition, recognize emotions based on the robot's operating sounds and posture data, identify signs of stress, and propose appropriate improvement measures.

[0601] The above is an embodiment of the present invention. This system enables efficient and flexible generation of work plans and adjustments according to the emotional state of the worker.

[0602] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[0603] Step 1:

[0604] Data entry by the user (operator)

[0605] While working, workers input work data via devices such as tablets or smartphones, including specific work items, progress, and any problems that have occurred. The input data is temporarily stored on the device.

[0606] Input: Work items, progress, issues encountered

[0607] Output: raw data collected

[0608] Step 2:

[0609] Data collection and transmission by the device

[0610] The device collects the work data entered by the user, formats it appropriately, and transmits it to the server. The collected data, including real-time work status information obtained from the camera and microphone, is converted into a format that can be analyzed by the device.

[0611] Input: Raw data collected

[0612] Output: Formatted data

[0613] Step 3:

[0614] Data reception and preprocessing by the server

[0615] The server receives the data sent from the device and stores it in a database. It then performs preprocessing on the received data, such as outlier detection and missing value imputation, to improve the reliability of the data and make it suitable for subsequent analysis steps.

[0616] Input: Formatted data

[0617] Output: Preprocessed data

[0618] Step 4:

[0619] Data analysis by server

[0620] The server analyzes the preprocessed data and evaluates the worker's work efficiency. Specifically, it analyzes the progress and error rate of each work item and performs data calculations to identify the strengths and weaknesses of the work.

[0621] Input: Preprocessed data

[0622] Output: Efficiency analysis results

[0623] Step 5:

[0624] Server-based estimation and generation of work plans

[0625] The server estimates the optimal work plan based on the work efficiency evaluation results. It calculates the worker's work plan by referencing past work data and efficiency standards. At the same time, it generates and proposes efficiency improvement measures.

[0626] Input: Efficiency analysis results, past work data

[0627] Output: Estimated work plan, efficiency improvement measures

[0628] Step 6:

[0629] Device suggestions and feedback

[0630] The terminal displays the work plan and efficiency improvement measures received from the server to the worker. The worker checks these suggestions and proceeds with the work based on them. If necessary, the work plan can be adjusted.

[0631] Input: Estimated work plan, efficiency improvement measures

[0632] Output: Feedback and suggestions to the worker

[0633] Step 7:

[0634] Input of daily work progress by users (workers)

[0635] Workers input their daily work progress into the terminal, including how much progress has been made on each task and the progress status. The input data is temporarily saved on the terminal.

[0636] Input: Daily work progress

[0637] Output: Collected progress data

[0638] Step 8:

[0639] Progress data collection and transmission by the device

[0640] The terminal collects daily work progress data entered by the user, formats it appropriately, and transmits it to the server, where it is converted into a format suitable for subsequent analysis.

[0641] Input: Collected progress data

[0642] Output: Formatted progress data

[0643] Step 9:

[0644] Server analysis and adjustment of progress data

[0645] The server analyzes the formatted progress data to verify that the work plan is progressing as planned, adjusts the work plan as necessary, generates a new plan, and sends the adjusted work plan and feedback to the device.

[0646] Input: Formatted progress data

[0647] Output: Coordinated work plan, feedback

[0648] Step 10:

[0649] Emotion recognition by emotion engine

[0650] The emotion engine installed on the terminal or server recognizes emotions from the worker's facial expressions, tone of voice, input content, etc., and identifies the worker's current emotional state.

[0651] Input: Facial expression data, tone of voice, input content

[0652] Output: Emotion recognition result

[0653] Step 11:

[0654] Server adjusts work plan based on emotion data

[0655] The server adjusts the work plan based on the emotional data recognized by the emotion engine. If the user is feeling stressed, it adjusts the workload and difficulty, generates appropriate encouraging messages and feedback, and sends them to the device.

[0656] Input: Emotion recognition results

[0657] Output: Coordinated work plan, encouraging messages

[0658] Through the above processing steps, the system as a whole generates efficient and flexible work plans and makes adjustments according to the emotional state of the worker.

[0659] The specific processing unit 290 transmits the result of the specific processing to the smart device 14. In the smart device 14, the control unit 46A causes the output device 40 to output the result of the specific processing. The microphone 38B acquires audio indicating a user input regarding the result of the specific processing. The control unit 46A transmits audio data indicating the user input acquired by the microphone 38B to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the audio data.

[0660] The data generation model 58 is a so-called generative AI (Artificial Intelligence). An example of the data generation model 58 is ChatGPT (registered trademark) (Internet search engine).<URL: https: / / openai.com / blog / chatgpt> ), Gemini (registered trademark) (Internet search <url: https: gemini.google.com ?hl="ja">) and other generation AIs. The data generation model 58 is obtained by performing deep learning on a neural network. A prompt including an instruction is input to the data generation model 58, and inference data such as voice data indicating voice, text data indicating text, and image data indicating an image is also input. The data generation model 58 performs inference on the input inference data in accordance with the instruction indicated by the prompt, and outputs the inference result in a data format such as voice data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[0661] In the above embodiment, an example in which the specific process is performed by the data processing device 12 has been given, but the technology of the present disclosure is not limited to this, and the specific process may be performed by the smart device 14.

[0662] [Second embodiment]

[0663] FIG. 3 shows an example of the configuration of a data processing system 210 according to the second embodiment.

[0664] 3, the data processing system 210 includes the data processing device 12 and smart glasses 214. An example of the data processing device 12 is a server.

[0665] The data processing device 12 includes a computer 22, a database 24, and a communication I / F 26. The computer 22 is an example of a "computer" according to the technology of the present disclosure. The computer 22 includes a processor 28, a RAM 30, and a storage 32. The processor 28, the RAM 30, and the storage 32 are connected to a bus 34. The database 24 and the communication I / F 26 are also connected to the bus 34. The communication I / F 26 is connected to a network 54. Examples of the network 54 include a WAN (Wide Area Network) and / or a LAN (Local Area Network).

[0666] The smart glasses 214 include a computer 36, a microphone 238, a speaker 240, a camera 42, and a communication I / F 44. The computer 36 includes a processor 46, a RAM 48, and a storage 50. The processor 46, the RAM 48, and the storage 50 are connected to a bus 52. The microphone 238, the speaker 240, and the camera 42 are also connected to the bus 52.

[0667] The microphone 238 receives instructions and the like from the user 20 by receiving voice uttered by the user 20. The microphone 238 captures the voice uttered by the user 20, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio in accordance with instructions from the processor 46.

[0668] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an imaging element such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, and captures images of the surroundings of user 20 (for example, an imaging range defined by an angle of view equivalent to the field of vision of a typical healthy person).

[0669] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 are responsible for the exchange of various information between the processor 46 and the processor 28 via the network 54. The exchange of various information between the processor 46 and the processor 28 using the communication I / Fs 44 and 26 is carried out in a secure state.

[0670] Fig. 4 shows an example of the main functions of the data processing device 12 and the smart glasses 214. As shown in Fig. 4, in the data processing device 12, a specific process is performed by the processor 28. A specific process program 56 is stored in the storage 32.

[0671] The specific processing program 56 is an example of a "program" according to the technology of the present disclosure. The processor 28 reads the specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific processing is realized by the processor 28 operating as a specific processing unit 290 in accordance with the specific processing program 56 executed on the RAM 30.

[0672] The storage 32 stores a data generation model 58 and an emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290.

[0673] In the smart glasses 214, the processor 46 performs the reception output process. A reception output program 60 is stored in the storage 50. The processor 46 reads the reception output program 60 from the storage 50 and executes the read reception output program 60 on the RAM 48. The reception output process is realized by the processor 46 operating as the control unit 46A in accordance with the reception output program 60 executed on the RAM 48.

[0674] Next, a description will be given of the identification process performed by the identification processing unit 290 of the data processing device 12. In the following description, the data processing device 12 will be referred to as the "server" and the smart glasses 214 will be referred to as the "terminal."

[0675] This system uses students' test scores and report card performance data to generate a list of schools of choice and backup schools, and indicates necessary study and challenges to overcome. The system consists of a server, terminals, and users (students).

[0676] System Configuration

[0677] 1. Data Collection

[0678] User (student):

[0679] Students enter their midterm and final exam scores, as well as their report card grades, into the terminal.

[0680] The data entered by the learner is saved on the device.

[0681] Device:

[0682] The terminal collects the input data and sends it to the server.

[0683] The terminal is equipped with an application and a web interface to provide a user interface.

[0684] 2. Data Analysis

[0685] server:

[0686] Receives data sent from the device and stores it in a database.

[0687] Check your data for outliers and missing values ​​and correct them if necessary.

[0688] Learners' test scores and grade data are analyzed to evaluate their performance in each subject.

[0689] Based on the analysis results, the learner's strengths and weaknesses are identified and their academic ability is evaluated.

[0690] 3. Pass rate estimation and list generation

[0691] server:

[0692] Based on the results of the student's academic assessment, the chances of them being accepted into their preferred school are estimated.

[0693] Refer to the data and statistics of past successful applicants for the school of your choice.

[0694] Generate a list of preferred schools (first to third choice) and a list of backup schools based on the acceptance rate.

[0695] Send your list of preferred schools and backup schools to your device.

[0696] 4. Feedback and learning plan creation

[0697] Device:

[0698] The generated list of preferred schools and backup schools is displayed to the learner.

[0699] Support the learner in creating an individualized learning plan based on the list they have reviewed.

[0700] server:

[0701] Based on an analysis of grades for each subject, weak areas and specific challenges are identified.

[0702] Recommend specific study methods and materials for identified issues.

[0703] Recommended study materials and methods are sent to your device.

[0704] 5. Learning progress management and feedback

[0705] User (student):

[0706] Daily study progress is entered into the device, including how much of each subject has been studied and the progress made.

[0707] Device:

[0708] The entered progress data is collected and sent to the server.

[0709] server:

[0710] Analyze your progress data to ensure your learning plan is on track.

[0711] Adjust the learning plan as needed and notify the learner.

[0712] Provide ongoing feedback to support effective learning.

[0713] Specific examples

[0714] Example 1: Test score analysis and feedback

[0715] User (student):

[0716] Enter 80 points for math, 70 points for English, 60 points for science, and 90 points for Japanese into the terminal.

[0717] The terminal collects the data and sends it to the server.

[0718] server:

[0719] The grade data is analyzed and it is determined that mathematics and Japanese are strong subjects, while science and English are weak subjects.

[0720] Calculate the acceptance rate for your desired school and make a list of your first, second, and third choice schools.

[0721] Recommended study methods include using problem sets that focus on specific areas of science and strengthening English vocabulary.

[0722] Device:

[0723] The analysis results are displayed to the learner and recommended learning methods are provided.

[0724] Example 2: Managing learning progress

[0725] User (student):

[0726] Enter your English study progress from the previous month into the device.

[0727] The device collects progress data and sends it to the server.

[0728] server:

[0729] Analyze progress data to determine if learning is not progressing as planned.

[0730] Adjust your English study plan and propose new ones.

[0731] Device:

[0732] Display the adjusted learning plan to the learner and provide feedback.

[0733] The above is an embodiment of the system of the present invention, which makes it possible to provide learners with individually optimized study plans and support for further education.

[0734] The processing flow will be explained below.

[0735] Step 1:

[0736] Students use the device to input their scores for each subject in midterm and final exams, as well as their report card grades. Specifically, they input their grades for each semester and their grades for each subject via the device's application or web interface.

[0737] Step 2:

[0738] The device collects test score and report card data entered by the user, which is then properly formatted and prepared for transmission to the server.

[0739] Step 3:

[0740] The terminal transmits the collected data to the server. This transmission is performed securely over a network.

[0741] Step 4:

[0742] The server receives the data sent from the device, stores it in a database, and uses it for subsequent analysis.

[0743] Step 5:

[0744] The server pre-processes the received data, which includes outlier detection and missing value imputation. Anomaly detection algorithms are applied to ensure data integrity and quality.

[0745] Step 6:

[0746] The server analyzes the preprocessed data and evaluates the user's academic ability. Specifically, it calculates a deviation score based on the scores for each subject and identifies strengths and weaknesses.

[0747] Step 7:

[0748] The server estimates the probability of passing the desired school based on the analysis results, comparing them with past successful applicant data and the school's passing criteria to calculate the user's chances of passing.

[0749] Step 8:

[0750] The server generates a list of preferred schools and a list of backup schools based on the estimated pass rate. The list includes first- to third-choice schools and recommended backup schools.

[0751] Step 9:

[0752] The server sends the generated list and analysis results to the device, formatting the data in a way that is easily accessible to the user.

[0753] Step 10:

[0754] The terminal displays the list of preferred schools and the list of backup schools sent from the server to the user, who can use this information to help formulate their own study plan.

[0755] Step 11:

[0756] The server identifies weak areas and issues that need to be overcome based on the results of the user's performance analysis, and selects specific study methods and recommended learning materials for the identified issues.

[0757] Step 12:

[0758] The server then sends the selected study methods and recommended learning materials to the device, allowing the user to study effectively.

[0759] Step 13:

[0760] The user inputs their daily learning progress into the terminal, and the input progress data is collected by the terminal.

[0761] Step 14:

[0762] The device sends the collected progress data to a server, which enables real-time learning progress management.

[0763] Step 15:

[0764] The server analyzes the progress data to ensure the learning plan is on track, adjusts it as needed, and generates a new plan.

[0765] Step 16:

[0766] The server sends the adjusted learning plan and feedback to the device, which the user can then confirm and continue learning.

[0767] Example 1

[0768] Next, a description will be given of Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the smart glasses 214 will be referred to as a "terminal."

[0769] In modern education, there is a demand for accurate assessment of each learner's academic ability and the provision of individualized learning plans based on that assessment. In particular, when selecting a school to attend, it is important to consider a learner's strengths and weaknesses and present effective learning methods. However, the current system does not adequately manage the creation of learning plans or learning progress, limiting the extent to which students can improve their academic ability. This makes it difficult to select a school to attend and create an effective learning plan, leading to problems such as reduced learning efficiency and motivation.

[0770] The specific processing by the specific processing unit 290 of the data processing device 12 in the first embodiment is realized by the following means.

[0771] In this invention, the server includes means for collecting input assessment data of learners, means for analyzing the learners' academic ability based on the collected data, means for estimating the pass rate for the desired school based on the analysis results, means for generating a list of educational institutions according to the pass rate estimated, means for displaying the generated list, means for creating a study plan for the learner based on the display means, and means for following up on the study plan. This allows for the evaluation of the learner's academic ability, selection of a school to attend, creation of an effective study plan, and progress management and feedback to be carried out in an integrated manner, thereby enabling the learner to improve their learning efficiency and achieve their goals.

[0772] "Inputted learner assessment data" refers to data such as test scores and report card grades entered by the learner.

[0773] "Means for analyzing academic ability" is a function that identifies a learner's strong and weak subjects based on collected evaluation data and evaluates the learner's overall academic ability.

[0774] "Means for estimating pass rates" is a function that statistically estimates the probability that a learner will be accepted into their desired school based on the results of academic ability analysis.

[0775] An "educational institution list" is a list of schools that a learner wishes to apply to, including their preferred school and backup schools.

[0776] The "means for displaying" is a function for providing the generated list of educational institutions to the learner and visually displaying it.

[0777] "Means for creating a study plan" is a function that allows learners to create a specific study plan to achieve their goals based on the displayed list of educational institutions.

[0778] "Means for following up on study plans" refers to a function for managing the progress of the study plans that have been created and adjusting the plans as necessary.

[0779] "Study progress data" refers to data such as the learning progress status and study time for each subject that is entered by the learner daily.

[0780] "Learning methods and materials" refers to the specific learning methods for a particular task and the instructions for the materials to be used.

[0781] This system uses student evaluation data to generate a list of schools of choice and backup schools, and creates and follows up on study plans. The system consists of a server, terminals, and users (student).

[0782] System Configuration

[0783] Data collection

[0784] User (learner):

[0785] The user enters into the terminal his or her test scores and report card grades for each subject, including, for example, math, English, science, and Japanese.

[0786] Device:

[0787] The terminal collects performance data entered by the user and sends it to the server. The terminal is equipped with an application or web interface and functions as a user interface. HTTP requests and JSON format data can be used for communication.

[0788] Data analysis

[0789] server:

[0790] The server receives the data sent from the device and stores it in a database system (e.g., MySQL or PostgreSQL). Next, it cleans the data and corrects outliers and missing values. It then uses a generative AI model (e.g., using Python's Pandas or Scikit-learn library) to analyze the learner's performance data and evaluate their performance in each subject.

[0791] Pass rate estimation and list generation

[0792] server:

[0793] Based on the analysis results, the system estimates the student's chances of getting into their preferred school. This estimation uses data on past successful applicants and statistical data. Next, a list of educational institutions (first choice, third choice, and backup schools) is generated based on the chances of getting into the school and sent to the device.

[0794] Feedback and learning plan creation

[0795] Device:

[0796] The device displays the generated list of preferred schools and backup schools to the user, and supports the user in creating an individualized study plan based on the lists they have reviewed.

[0797] server:

[0798] Based on the results of the analysis of grades, the system identifies areas where the learner is weak and specific challenges. Specific learning methods and learning materials are recommended for the identified challenges and sent to the device.

[0799] Learning progress management and feedback

[0800] User (learner):

[0801] Users enter their daily study progress into the device, for example, recording which subjects they studied and how many hours they spent studying.

[0802] Device:

[0803] The device collects the progress data entered and sends it to the server, which analyzes the progress data to check whether the learning plan is progressing as planned, adjusts the learning plan as necessary, and notifies the user.

[0804] Specific examples

[0805] Example 1: Test score analysis and feedback

[0806] User (learner):

[0807] Enter 80 points for math, 70 points for English, 60 points for science, and 90 points for Japanese into the terminal.

[0808] Device:

[0809] The terminal collects the data and sends it to the server.

[0810] server:

[0811] The server analyzes the grade data, evaluates students' strengths and weaknesses, calculates their chances of getting into their preferred schools, and generates a list of schools they can apply to. It also recommends using workbooks that focus on specific science subjects and improving English vocabulary.

[0812] Device:

[0813] The device displays the analysis results and recommended learning methods to the learner.

[0814] Example 2: Managing learning progress

[0815] User (learner):

[0816] Enter your English study progress from the previous month into the device.

[0817] Device:

[0818] The device collects progress data and sends it to the server.

[0819] server:

[0820] The server analyzes the progress data and determines if the student's learning is not going as planned. It adjusts the student's English learning plan and proposes a new plan.

[0821] Device:

[0822] The device displays the adjusted learning plan to the learner and provides feedback.

[0823] Prompt Sentence Examples

[0824] "Write a program where the user inputs grades for each subject, the system determines which subjects the user is good at and which subjects they are bad at, and generates a list of schools they want to apply to. Specifically, the system will analyze grade data for 80 points in math, 70 points in English, 60 points in science, and 90 points in Japanese, and generate a list of schools they want to apply to."

[0825] The above is an embodiment of the invention. This system makes it possible to provide learners with individually optimized learning plans and support for further education.

[0826] The flow of the identification process in the first embodiment will be described with reference to FIG.

[0827] Step 1:

[0828] The user (student) enters performance data:

[0829] Users enter their test scores and report card grades for each subject using a device application or a web interface. The data entered includes the grades for each subject (e.g., math 80 points, English 70 points, science 60 points, Japanese 90 points).

[0830] Input: Grade data for each subject

[0831] Output: Achievement data saved on the device

[0832] Step 2:

[0833] Device collects and transmits performance data:

[0834] The terminal temporarily stores the performance data entered by the user and sends it to the server. The data is encoded in JSON format and sent via an HTTP request.

[0835] Input: Achievement data saved on the device

[0836] Output: Achievement data sent to the server

[0837] Step 3:

[0838] The server receives and stores the performance data:

[0839] The server receives the grade data sent from the device and stores it in a database (e.g., MySQL or PostgreSQL). The received data includes grade information for each subject.

[0840] Input: Performance data sent from the device

[0841] Output: Achievement data stored in a database

[0842] Step 4:

[0843] The server parses the data:

[0844] The server retrieves the stored grade data and performs data cleaning, checking for outliers and missing values ​​and correcting them as necessary. It then uses a generative AI model (using, for example, Python's Pandas or Scikit-learn libraries) to evaluate performance in each subject and identify strong and weak subjects.

[0845] Input: Achievement data stored in the database

[0846] Output: Analysis results including strong and weak subjects

[0847] Step 5:

[0848] The server estimates the pass rate and generates a list:

[0849] Based on the analysis results, the server evaluates the student's academic ability and statistically estimates the student's chances of being accepted into their preferred school. This estimation uses data on past successful applicants and statistical data. It then generates a list of preferred schools and a list of backup schools.

[0850] Input: Analysis results including strong and weak subjects

[0851] Output: List of preferred schools and backup schools

[0852] Step 6:

[0853] The server sends the list to the device:

[0854] The generated list of preferred schools and alternative schools is sent to the device. The data is encoded in JSON format and sent via an HTTP request.

[0855] Input: List of preferred schools and backup schools

[0856] Output: List of preferred schools and backup schools sent to the terminal

[0857] Step 7:

[0858] The terminal displays the list to the user:

[0859] The terminal displays the received list of preferred schools and backup schools to the user, using an application or web page as the user interface.

[0860] Input: List of preferred schools and backup schools sent to the device

[0861] Output: A list of preferred and alternative schools displayed to the user

[0862] Step 8:

[0863] User enters learning progress data:

[0864] Users input their daily study progress into the device, for example, recording the study time and progress for each subject (e.g., studied English for 2 hours).

[0865] Input: Daily learning progress data

[0866] Output: Learning progress data saved on the device

[0867] Step 9:

[0868] Your device collects and transmits learning progress data:

[0869] The device collects learning progress data entered by the user and sends it to the server, where it is encoded in JSON format and sent via an HTTP request.

[0870] Input: Learning progress data stored on the device

[0871] Output: Learning progress data sent to the server

[0872] Step 10:

[0873] The server analyzes the progress data and provides feedback:

[0874] The server analyzes the received progress data, checks whether the learning plan is progressing as planned, adjusts the learning plan if necessary, creates a new learning plan, and notifies the user.

[0875] Input: Learning progress data sent to the server

[0876] Output: Feedback and adjusted learning plan provided to the user

[0877] (Application example 1)

[0878] Next, a description will be given of Application Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the smart glasses 214 will be referred to as a "terminal."

[0879] Conventional educational support systems are limited to analyzing students' academic performance data and estimating their chances of getting into their preferred schools, and do not adequately create specific study plans or manage progress. Furthermore, they do not provide specific learning materials or methods to help students overcome their weaknesses, limiting the effectiveness of improving their learning efficiency. Furthermore, these functions needed to be integrated into an educational support application provided in a virtual store. The present invention aims to provide a system that solves these problems.

[0880] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 1 is realized by the following means.

[0881] In this invention, the server includes means for collecting input test scores and performance data of learners, means for analyzing the learner's academic ability based on the collected data, means for estimating the pass rate for the desired school based on the analysis results, means for generating a list of desired schools and a list of backup schools according to the estimated pass rate, means for displaying the generated lists, means for creating a study plan for the learner based on the display means, means for recommending learning materials and study methods to help the learner overcome weaknesses based on the study plan and list of desired schools, and means for collecting and analyzing the learner's progress with the recommended learning materials and study methods. This enables learning support and support for further education that are individually optimized for each learner.

[0882] A "learner" is someone who belongs to an educational institution and takes tests and assessments.

[0883] A "test score" is the score or marks a learner receives when taking an exam or assessment.

[0884] "Academic performance data" refers to information indicating a learner's academic performance as assessed in the form of a report card, a report, or the like.

[0885] "Means for analyzing academic ability" refers to methods or systems for analyzing learners' test scores and grade data and evaluating their academic ability in each subject and overall.

[0886] A "means for estimating pass rates" is a method or algorithm for calculating the probability of a student being accepted into a school of their choice based on their current academic ability data.

[0887] A "school of choice list" is a list of schools that a student wishes to attend, ranked based on their acceptance rate.

[0888] A "safety school list" is a list of schools that have a high chance of acceptance in case you are not accepted into your preferred school.

[0889] "Display means" refers to the method or device for visually presenting the generated school preference list and other information to the learner.

[0890] A "means for creating a study plan" is a method or system for constructing daily study content and schedules to help learners achieve their goals.

[0891] "Means for recommending learning materials and learning methods" are systems or algorithms that suggest appropriate learning materials and effective learning methods to address learners' weaknesses and challenges.

[0892] "Means for collecting and analyzing progress" refers to methods and systems for recording learners' daily learning activities and evaluating whether they are progressing as planned.

[0893] A "virtual store" is a virtual shop or platform that provides educational services and teaching materials via the Internet.

[0894] This system uses a student's test scores and report card grade data to generate a list of schools of choice and backup schools, and indicates necessary study and challenges to overcome. This system is composed of a server, a terminal (such as a smartphone or PC), and a user (a student).

[0895] System Configuration

[0896] 1. Data Collection

[0897] User (learner):

[0898] Students enter their midterm and final exam scores, as well as their report card grades, into the terminal.

[0899] The data entered by the learner is saved on the device.

[0900] Device:

[0901] The terminal collects the input data and sends it to the server.

[0902] The terminal is equipped with an application and a web interface to provide a user interface.

[0903] 2. Data Analysis

[0904] server:

[0905] Receives data sent from the device and stores it in a database.

[0906] Check your data for outliers and missing values ​​and correct them if necessary.

[0907] Learners' test scores and grade data are analyzed to evaluate their performance in each subject.

[0908] Based on the analysis results, the learner's strengths and weaknesses are identified and their academic ability is evaluated.

[0909] 3. Pass rate estimation and list generation

[0910] server:

[0911] Based on the results of the student's academic assessment, the chances of them being accepted into their preferred school are estimated.

[0912] Refer to the data and statistics of past successful applicants for the school of your choice.

[0913] Generate a list of preferred schools (first to third choice) and a list of backup schools based on the acceptance rate.

[0914] Send your list of preferred schools and backup schools to your device.

[0915] 4. Feedback and learning plan creation

[0916] Device:

[0917] The generated list of preferred schools and backup schools is displayed to the learner.

[0918] Support the learner in creating an individualized learning plan based on the list they have reviewed.

[0919] server:

[0920] Based on an analysis of grades for each subject, weak areas and specific challenges are identified.

[0921] Recommend specific study methods and materials for identified issues.

[0922] Recommended study materials and methods are sent to your device.

[0923] 5. Learning progress management and feedback

[0924] User (learner):

[0925] Daily study progress is entered into the device, including how much of each subject has been studied and the progress made.

[0926] Device:

[0927] The entered progress data is collected and sent to the server.

[0928] server:

[0929] Analyze your progress data to ensure your learning plan is on track.

[0930] Adjust the learning plan as needed and notify the learner.

[0931] Provide ongoing feedback to support effective learning.

[0932] Specific examples

[0933] User (learner):

[0934] Enter 80 points for math, 70 points for English, 60 points for science, and 90 points for Japanese into the terminal.

[0935] The terminal collects the data and sends it to the server.

[0936] server:

[0937] The grade data is analyzed and it is determined that mathematics and Japanese are strong subjects, while science and English are weak subjects.

[0938] Calculate the acceptance rate for your desired school and make a list of your first, second, and third choice schools.

[0939] Recommended study methods include using problem sets that focus on specific areas of science and strengthening English vocabulary.

[0940] Device:

[0941] The analysis results are displayed to the learner and recommended learning methods are provided.

[0942] The above series of processes realizes learning support that is optimized for each learner. As a concrete example, let us consider the following prompt sentence as input to the generative AI model.

[0943] Example prompt sentence:

[0944] "A student's test scores are: Math 80, English 70, Science 60, Japanese 90. In this case, please list the student's first, second, and third choice schools. Also, please suggest the best study methods for English and Science, which are the weaker subjects."

[0945] In this way, by utilizing generative AI models, it is possible to provide more accurate learning assistance.

[0946] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[0947] Step 1:

[0948] Users input test scores and grade data. Specifically, learners input their midterm and final exam scores and report card scores into a smartphone or PC device. The input data includes the scores for each subject. After input, the data is temporarily stored on the device.

[0949] Step 2:

[0950] The device sends the collected data to a server. The device is equipped with an application or web interface that formats the data entered by the user and sends it to the server. The data is encrypted before being sent.

[0951] Step 3:

[0952] The server receives the data and stores it in the database. The server checks the integrity of the data and corrects any outliers or missing values. For example, if a math score is over 100, it is treated as an outlier. After checking that the data is in the correct format, it is stored in the database.

[0953] Step 4:

[0954] The server analyzes the learner's test scores and performance data. It uses analytical algorithms to evaluate performance in each subject. Specifically, it calculates the mean and standard deviation of scores and identifies strengths and weaknesses in each subject. Algorithms used here include XGBoost and linear regression models.

[0955] Step 5:

[0956] The server estimates the pass rate for the student's desired school based on the analysis results. It compares the student's scores with past successful applicant data and statistical data to calculate the pass rate for the desired school. For example, using the XGBoost model, the pass rate can be estimated by inputting data for 80 points in math, 70 points in English, 60 points in science, and 90 points in Japanese.

[0957] Step 6:

[0958] The server generates a list of preferred schools and a list of backup schools according to the pass rate. Based on the calculated pass rate, lists of first-choice, second-choice, third-choice, etc. are created. A list of backup schools with relatively high pass rates is also generated at the same time.

[0959] Step 7:

[0960] The server sends the generated list to the terminal. After generating the list, the server sends it to the terminal. At this time, the data is encrypted again and sent. The data is formatted in the appropriate format so that it can be displayed correctly on the terminal.

[0961] Step 8:

[0962] The device displays the student's list of preferred schools and backup schools. The list is displayed for easy access by the student through the device's application or web interface. Specifically, the list is displayed in list format along with the acceptance rate for each preferred school.

[0963] Step 9:

[0964] The server analyzes the learner's weak areas and the challenges they need to overcome. Based on the results of the analysis, it identifies subjects and areas where students have particularly low scores and evaluates what learning methods are most effective.

[0965] Step 10:

[0966] The server then recommends learning materials and methods that address the identified issues. For example, it might recommend a workbook focused on a specific area of ​​science or an app to improve English vocabulary. This recommendation information is selected using an analytical algorithm.

[0967] Step 11:

[0968] The device will display recommended learning materials and methods to the learner, who can then review the recommended materials and methods and incorporate them into their own learning plans.

[0969] Step 12:

[0970] The user inputs their daily learning progress into the device. The learner inputs their daily learning content and progress and saves it on the device. The input data includes the subjects studied, the time spent, and the progress status.

[0971] Step 13:

[0972] The terminal sends the entered progress data to the server. The terminal formats the progress data entered by the learner and sends it to the server.

[0973] Step 14:

[0974] The server analyzes the progress data to check whether the learning plan is progressing as planned. Based on the progress data, the server evaluates whether the learner's plan is progressing properly and makes adjustments as necessary.

[0975] Step 15:

[0976] The server sends the results of the adjustments to the learning plan to the device. If the plan is not progressing as planned, a new learning plan will be proposed and sent to the device.

[0977] Step 16:

[0978] The device will then display the adjusted study plan to the learner. By presenting the new plan, the learner can study more efficiently.

[0979] The above processing steps enable learners to receive individually optimized learning support and maximize their learning outcomes. Specifically, by inputting the following prompt sentences into the generative AI model, highly accurate analysis and feedback can be obtained.

[0980] Example prompt sentence:

[0981] "A student's test scores are: Math 80, English 70, Science 60, Japanese 90. In this case, please list the student's first, second, and third choice schools. Also, please suggest the best study methods for English and Science, which are the weaker subjects."

[0982] Furthermore, an emotion engine that estimates the user's emotion may be further combined. That is, the identification processing unit 290 may estimate the user's emotion using the emotion identification model 59, and perform identification processing using the user's emotion.

[0983] This invention combines a system that uses a learner's test scores and report card grade data to generate a list of preferred and backup schools, and indicates necessary study and challenges to overcome, with an emotion engine that recognizes the user's emotions. The system is composed of a server, terminals, and users (students).

[0984] System Configuration

[0985] 1. Data Collection

[0986] User (student):

[0987] Students input their scores for each subject in midterm and final exams, as well as their report card grades, into the terminal using a terminal application or a web interface.

[0988] Device:

[0989] The terminal collects the entered data, formats it appropriately, and sends it to the server.

[0990] 2. Data Analysis

[0991] server:

[0992] The server receives the data sent from the terminal and stores it in a database.

[0993] Preprocessing such as outlier detection and missing value completion is performed on the received data.

[0994] Analyze the pre-processed data to evaluate the learner's academic ability, identifying scores, deviation values, strengths and weaknesses for each subject.

[0995] 3. Pass rate estimation and list generation

[0996] server:

[0997] Based on the results of the academic assessment, the system estimates the chances of passing the desired school. It also calculates the user's chances of passing by referencing past passing data and the school's passing criteria.

[0998] Based on the estimated pass rate, a list of preferred schools (first to third choice) and a list of backup schools are generated.

[0999] Send your list of preferred schools and backup schools to your device.

[1000] 4. Feedback and learning plan creation

[1001] Device:

[1002] The data received from the server is displayed to the user, who can then check the list of schools of choice and the results of the grade analysis.

[1003] Based on the results of the analysis of a learner's grades, we identify areas of weakness and challenges that need to be overcome, and then present specific study methods and recommended materials to address these challenges.

[1004] server:

[1005] Specific study methods and recommended study materials to overcome weak areas are selected and sent to the device.

[1006] 5. Emotional awareness and learning plan adjustment

[1007] Emotion Engine:

[1008] It recognizes emotions from the user's facial expressions, tone of voice, input content, etc., and identifies the user's current emotional state.

[1009] server:

[1010] The learning plan is adjusted based on the recognized emotional data, for example, adjusting the amount or difficulty of learning if the user is feeling stressed.

[1011] Depending on the recognized emotion, encouraging messages and appropriate feedback are generated and sent to the device.

[1012] 6. Learning progress management and feedback

[1013] User (student):

[1014] Daily study progress is entered into the device, including how much of each subject has been studied and the progress made.

[1015] Device:

[1016] The entered progress data is collected and sent to the server.

[1017] server:

[1018] Analyze progress data to ensure your learning plan is on track, adjust it if necessary, and generate a new plan.

[1019] The adjusted learning plan and feedback are sent to the device, where the user can confirm and continue learning.

[1020] Specific examples

[1021] Example 1: Test score analysis and feedback

[1022] User (student):

[1023] The student enters their scores into the terminal: 80 points for math, 70 points for English, 60 points for science, and 90 points for Japanese. The terminal collects the data and sends it to the server.

[1024] server:

[1025] The grade data is analyzed and it is determined that mathematics and Japanese are strong subjects, while science and English are weak subjects.

[1026] Calculate the acceptance rate for your desired school and make a list of your first, second, and third choice schools.

[1027] Recommended study methods include using problem sets that focus on specific areas of science and strengthening English vocabulary.

[1028] Device:

[1029] The analysis results are displayed to the learner and recommended learning methods are provided.

[1030] Emotion Engine:

[1031] The system recognizes whether the user is feeling anxious or stressed from their facial expressions and tone of voice while they are typing.

[1032] server:

[1033] Based on the recognized emotion data, the system generates encouraging messages and suggests adjustments to the amount of study. For example, it provides messages such as, "You seem to be good at math! Keep it up!"

[1034] Example 2: Managing learning progress

[1035] User (student):

[1036] The user enters their English study progress from the previous month into the device, which then collects the progress data and sends it to the server.

[1037] server:

[1038] Analyze progress data to determine if learning is not progressing as planned.

[1039] Adjust your English study plan and propose new ones.

[1040] Emotion Engine:

[1041] The emotion engine recognizes that the user is feeling stressed from their facial expressions and voice when entering their progress.

[1042] server:

[1043] Based on the recognized emotions, the system suggests educational materials that can be understood quickly and efficiently to reduce stress.

[1044] Device:

[1045] Provide users with tailored learning plans and feedback to support their learning.

[1046] summary

[1047] The system of the present invention allows learners to receive efficient and personalized learning support based on their own performance data and progress. Furthermore, by combining it with an emotion engine, appropriate feedback and adjustments to the learning plan are made according to the user's emotional state, enabling effective learning while reducing stress.

[1048] The processing flow will be explained below.

[1049] Step 1:

[1050] Students use the device to input their scores for each subject in midterm and final exams, as well as their report card grades. Specifically, they input their grades for each semester and their grades for each subject via the device's application or web interface.

[1051] Step 2:

[1052] The device collects test score and report card data entered by the user, which is then prepared and properly formatted for transmission to the server.

[1053] Step 3:

[1054] The terminal transmits the collected data to the server. This transmission is performed securely over a network.

[1055] Step 4:

[1056] The server receives the data sent from the device, stores it in a database, and uses it for subsequent analysis.

[1057] Step 5:

[1058] The server pre-processes the received data, which includes outlier detection and missing value imputation. Anomaly detection algorithms are applied to ensure data integrity and quality.

[1059] Step 6:

[1060] The server analyzes the preprocessed data and evaluates the user's academic ability. Specifically, it calculates a deviation score based on the scores for each subject and identifies strengths and weaknesses.

[1061] Step 7:

[1062] The server estimates the probability of passing the desired school based on the analysis results, comparing them with past successful applicant data and the school's passing criteria to calculate the user's chances of passing.

[1063] Step 8:

[1064] The server generates a list of preferred schools and a list of backup schools based on the estimated pass rate. The list includes first- to third-choice schools and recommended backup schools.

[1065] Step 9:

[1066] The server sends the generated list and analysis results to the device, formatting the data in a way that is easily accessible to the user.

[1067] Step 10:

[1068] The terminal displays the list of preferred schools and the list of backup schools sent from the server to the user, who can use this information to help formulate their own study plan.

[1069] Step 11:

[1070] The server identifies weak areas and issues that need to be overcome based on the results of the user's performance analysis, and selects specific study methods and recommended learning materials for the identified issues.

[1071] Step 12:

[1072] The server then sends the selected study methods and recommended learning materials to the device, allowing the user to study effectively.

[1073] Step 13:

[1074] The emotion engine recognizes emotions from the user's facial expressions, tone of voice, and input content to identify the user's current emotional state.

[1075] Step 14:

[1076] The server receives the emotion data recognized by the emotion engine and adjusts the study plan, for example, reducing the amount of study or lowering the difficulty level if the user is feeling stressed.

[1077] Step 15:

[1078] The server generates encouraging messages and appropriate feedback based on the recognized emotion data and sends them to the device, such as "You seem to be good at math! Keep it up!"

[1079] Step 16:

[1080] Users enter their daily study progress into the terminal, including how much they studied and what subjects they studied, as well as their progress.

[1081] Step 17:

[1082] The terminal collects the entered progress data and transmits it to the server.

[1083] Step 18:

[1084] The server analyzes the progress data to ensure the learning plan is on track, adjusts it as needed, and generates a new plan.

[1085] Step 19:

[1086] The server sends the adjusted learning plan and feedback to the device, which the user can then confirm and continue learning.

[1087] The above is a specific flow of processing in the system of the present invention. By providing individually optimized learning support while taking into consideration the user's emotions, learning efficiency is improved and stress is reduced.

[1088] Example 2

[1089] Next, a description will be given of Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the smart glasses 214 will be referred to as a "terminal."

[1090] In conventional educational systems, learning plans are often created based on a learner's academic performance data, but they lack the ability to adjust to the learner's individual emotional state. This can lead to learners feeling stressed or anxious, which can hinder their ability to perform at their best and result in less than optimal learning outcomes. There is a need for a system that provides a comprehensive approach that takes into account not only academic performance data but also daily learning progress and emotional state.

[1091] The identification process by the identification processing unit 290 of the data processing device 12 in the second embodiment is realized by the following means. In this invention, the server includes means for collecting input academic performance data of the learner, means for analyzing the learner's academic ability based on the collected data, means for estimating the pass rate for the desired school based on the analysis results, means for generating a list of desired schools and a list of backup schools according to the estimated pass rate, means for displaying the generated lists, means for creating a study plan for the learner based on the display means, means for recognizing the learner's emotional state, and means for adjusting the study plan based on the recognized emotional state. This enables comprehensive learning support that takes into account the learner's emotional state.

[1092] "Academic performance data" refers to data including the scores obtained by a learner in each subject and the grades on their report cards.

[1093] "Academic ability" refers to the results of assessing a learner's scores in each subject and their overall learning ability.

[1094] "Analysis results" refers to the output of a learner's academic ability assessment based on the collected data.

[1095] "Preferred school" refers to the educational institution that a learner wishes to attend.

[1096] The "pass rate" is a value indicating the probability that a learner will pass the entrance examination to the school of their choice.

[1097] A "preferred school list" is a list of educational institutions that a learner wishes to attend, ranked in order.

[1098] A "safety school list" is a list of educational institutions that a student may consider attending if they are not accepted into their preferred school.

[1099] "Display means" refers to a device or method for displaying the generated list, analysis results, etc. to the learner.

[1100] A "study plan" refers to the specific learning content and schedule set out to help learners progress effectively in their studies.

[1101] "Emotional state" refers to the learner's current emotional state, including, for example, stress, anxiety, and motivation.

[1102] The present invention is a system that combines a learner's performance data and emotional state to provide an optimal study plan. This system is composed of a server, a terminal, and a user (learner).

[1103] server:

[1104] The server receives the grade data sent from the device and stores it in a database. It then analyzes the grade data to evaluate the learner's academic ability. Specifically, it performs preprocessing such as outlier detection and missing value imputation. Based on the preprocessed data, it calculates the deviation score for each subject, as well as the student's strong and weak subjects. Based on the analysis results, it estimates the student's chances of getting into their preferred school. Using this chance as a reference, it generates a list of first- to third-choice schools and a list of safety schools. The server also has the ability to recognize the learner's emotional state and reflect this data in the study plan. For example, if the learner is feeling stressed, it can reduce the amount of study or adjust the difficulty level.

[1105] Device:

[1106] The terminal provides an interface for users to input grade data and progress data. For example, learners use a terminal application or web interface to input their grades for each subject and their report card grades. The terminal then converts the received data into an appropriate format and sends it to the server. The terminal then displays the analysis results, preferred school list, study plan, and emotional feedback sent from the server to the user. A dashboard using a graphical user interface (GUI) is provided to make it easy for learners to check the data.

[1107] User (learner):

[1108] Users input their scores for each subject in midterm and final exams, as well as report card grades, through the device. They also input their daily learning progress into the device and send it to the server as appropriate. Learning progresses based on the learning plan and feedback received from the device. The device's camera and microphone are also used to recognize the user's emotional state, providing an appropriate learning method that matches their emotional state.

[1109] Examples:

[1110] For example, if a user inputs "80 points in math, 70 points in English, 60 points in science, and 90 points in Japanese" into the device, the device converts the data into JSON format and sends it to the server. The server analyzes the grade data and determines that math and Japanese are strong subjects, while science and English are weak subjects. The server calculates the pass rate and displays it as 70% for the first choice school, 50% for the second choice school, and 90% for the third choice school. Recommended study methods include using workbooks that focus on specific areas of science and strengthening English vocabulary. As the user inputs progress data into the device, the server analyzes the progress and adjusts the study plan.

[1111] Furthermore, the emotion engine recognizes that if the user frowns while typing, they are feeling anxious, and adjusts the amount of learning they are doing, sending encouraging messages such as, "You seem to be good at math! Keep it up!"

[1112] This system not only provides learners with optimal study plans based on their performance data, but also provides flexible feedback and study adjustments that are tailored to their emotional state at the time, enabling efficient and stress-free learning.

[1113] The flow of the identification process in the second embodiment will be described with reference to FIG.

[1114] Step 1:

[1115] User: The learner uses a terminal application or a web interface to input the scores for each subject in the midterm and final exams, as well as the grade data from the report card. For example, the learner enters "80 points for math, 70 points for English, 60 points for science, and 90 points for Japanese."

[1116] Input: Score and grade data for each subject entered by the user

[1117] Output: Performance data sent to the device

[1118] Step 2:

[1119] Terminal: The terminal collects the grade data entered by the user and converts it into an appropriate format. Specifically, it converts the input data into JSON format. For example, it formats it as follows: {"Subject": {"Math": 80, "English": 70, "Science": 60, "Japanese": 90}}.

[1120] Input: User-entered grade data

[1121] Output: Formatted data (JSON format)

[1122] Step 3:

[1123] Terminal: Sends the collected and formatted performance data to the server, for example, using HTTP requests.

[1124] Input: Formatted data (JSON format)

[1125] Output: Grade data sent to the server

[1126] Step 4:

[1127] Server: The server receives the performance data sent from the device and stores it in a database. When storing the data, it associates it with each user's ID.

[1128] Input: Performance data sent from the device

[1129] Output: Achievement data stored in the database

[1130] Step 5:

[1131] Server: Preprocesses the saved grade data. Performs outlier detection and missing value imputation to ensure data accuracy. An outlier, for example, would be a negative score for each subject, and corrects it to within the normal range.

[1132] Input: Achievement data stored in the database

[1133] Output: Preprocessed grade data

[1134] Step 6:

[1135] Server: Analyzes the pre-processed data and evaluates the user's academic ability. Specifically, it calculates the deviation score and strong and weak subjects based on the scores for each subject.

[1136] Input: Preprocessed grade data

[1137] Output: Academic ability analysis results (deviation score for each subject, strong and weak subjects)

[1138] Step 7:

[1139] Server: Based on the results of the academic ability analysis, estimate the probability of admission to the user's desired school. In this case, past admission data and school standards are used as reference.

[1140] Input: Academic ability analysis results

[1141] Output: Pass rate estimation result

[1142] Step 8:

[1143] Server: Based on the estimated pass rate, it generates a list of preferred schools and a list of backup schools and sends this to the terminal.

[1144] Input: Pass rate estimation result

[1145] Output: List of preferred schools, list of backup schools

[1146] Step 9:

[1147] Terminal: Displays the list of schools of choice sent from the server and the results of the academic ability analysis to the user. The user can check the analysis results and the list.

[1148] Input: Preferred school list sent from the server, academic ability analysis results

[1149] Output: Displayed list of preferred schools, academic ability analysis results

[1150] Step 10:

[1151] Server: Selects specific study methods and recommended learning materials to help learners overcome their weak areas and sends them to the device.

[1152] Input: Academic ability analysis results (weak subjects)

[1153] Output: Study methods and recommended materials

[1154] Step 11:

[1155] Device: Displays study methods and recommended learning materials to the user. The user creates a study plan based on the information provided.

[1156] Input: Study methods and recommended materials sent from the server

[1157] Output: Displayed study methods and recommended materials

[1158] Step 12:

[1159] Emotion engine: Recognizes emotions from the user's facial expressions, tone of voice, and input content to identify their current emotional state. For example, if the user frowns while typing, it determines that they are feeling anxious.

[1160] Input: User facial expressions, tone of voice, and input

[1161] Output: Perceived emotional state

[1162] Step 13:

[1163] Server: Adjusts the study plan based on the recognized emotion data. For example, if the user is feeling stressed, the server suggests adjusting the amount of study or difficulty.

[1164] Input: Perceived emotional state

[1165] Output: Adjusted lesson plan

[1166] Step 14:

[1167] Server: Generates encouraging messages and appropriate feedback based on the recognized emotions and sends them to the device. For example, it provides a message like, "You seem to be good at math! Keep it up!"

[1168] Input: Perceived emotional state

[1169] Output: Encouraging message, feedback

[1170] Step 15:

[1171] Device: Displays tailored study plans and encouraging messages to users, allowing them to receive appropriate study methods tailored to their emotional state.

[1172] Input: Tailored study plan and encouraging messages sent from the server

[1173] Output: A displayed lesson plan and encouraging messages

[1174] Step 16:

[1175] User: Enters daily learning progress into the device. For example, progress information such as "English: Study 3 hours a week, Science: Study 2 hours a week" is recorded.

[1176] Input: Daily learning progress

[1177] Output: Progress data sent to the device

[1178] Step 17:

[1179] Terminal: Sends the collected progress data to the server, for example, using HTTP requests.

[1180] Input: Collected progress data

[1181] Output: Progress data sent to the server

[1182] Step 18:

[1183] Server: Analyzes progress data and checks whether the lesson plan is on track. If it is behind schedule, adjusts the plan and generates a new lesson plan.

[1184] Input: Progress data

[1185] Output: Progress analysis results, adjusted learning plan

[1186] Step 19:

[1187] Server: Sends the adjusted learning plan and feedback to the device, allowing the user to receive an appropriate learning plan based on their current progress.

[1188] Input: Tailored learning plan, feedback

[1189] Output: Learning plan and feedback sent to the device

[1190] Step 20:

[1191] Device: The adjusted learning plan and feedback are displayed to the user to support their learning. The user can then review the plan and continue their learning.

[1192] Input: Learning plan and feedback sent from the server

[1193] Output: Displayed lesson plan, feedback

[1194] (Application example 2)

[1195] Next, a description will be given of Application Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the smart glasses 214 will be referred to as a "terminal."

[1196] Modern factories require robots to improve the efficiency and optimization of their work, but there are limitations to systems that can accurately evaluate a robot's operating status and work efficiency and suggest improvement measures. Furthermore, there is a lack of functionality to recognize a robot's stress or illness using an emotion engine and propose appropriate countermeasures. Therefore, there is a need for a system that can improve the efficiency of robots and flexibly adjust work plans according to the robot's condition.

[1197] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 2 is realized by the following means.

[1198] In this invention, the server includes means for collecting input worker data, means for analyzing worker efficiency based on the collected data, means for estimating a work plan based on the analysis results, means for generating efficiency improvement measures in accordance with the estimated work plan, means for displaying the generated efficiency improvement measures, means for creating a work plan for the worker based on the display means, means for inputting the worker's daily work progress and collecting the work progress data, means for adjusting the work plan based on the collected progress data, and means for identifying the worker's weak areas and challenges to overcome based on the estimated work plan and providing specific work methods and tools to address the identified challenges. This enables improved robot work efficiency and flexible adjustment of the work plan in response to the robot's stress or illness.

[1199] "Workers" refers to factory robots and the personnel who operate and manage them.

[1200] "Work data" refers to data that includes information such as the operating status of factory robots, work progress, and error rates.

[1201] "Efficiency analysis" is the process of analyzing and evaluating the work efficiency of workers and robots based on collected work data.

[1202] A "work plan" is a plan that specifies the work content and procedures to be performed by workers and robots.

[1203] "Efficiency improvement measures" are proposals that include specific methods and actions to improve the work efficiency of workers and robots.

[1204] The "emotion engine" is a system that analyzes the state of workers and robots and recognizes emotions such as stress and illness.

[1205] A "work method" is a specific operational procedure or technique used by a worker or robot to perform a specific task.

[1206] "Tools" refers to the equipment and tools used by workers and robots when performing work.

[1207] System Configuration

[1208] The system that realizes this application example consists of three main elements: a server, a terminal, and a user (operator).

[1209] 1. Data Collection

[1210] User (worker)

[1211] During their daily work, workers input work data via devices such as tablets or smartphones, including specific work items, progress, and any problems that arise.

[1212] Terminal

[1213] The terminal collects the input work data, formats it appropriately, and sends it to the server. The terminal is also connected to peripheral devices such as a camera and microphone, which can be used to monitor the work status in real time.

[1214] 2. Data Analysis

[1215] server

[1216] The server receives the data sent from the terminal and stores it in a database. The received data undergoes preprocessing, such as outlier detection and missing value completion. The preprocessed data is then analyzed to evaluate the worker's work efficiency. Specifically, the progress and error rate of each work item are analyzed to identify the strengths and weaknesses of the work.

[1217] 3. Estimating and generating work plans

[1218] server

[1219] The server estimates the optimal work plan based on the results of the work efficiency evaluation. It calculates the worker's work plan by referencing past work data and efficiency standards. At this time, it also makes suggestions, including measures to improve efficiency. Furthermore, based on the estimation results, it suggests the optimal work method and tools that the worker should use.

[1220] 4. Suggestions and Feedback

[1221] Terminal

[1222] The data received from the server is displayed to the worker, who checks the estimated work plan and efficiency improvement measures and proceeds with the work accordingly.

[1223] 5. Managing and adjusting learning progress

[1224] User (worker)

[1225] Daily work progress is entered into the terminal, including how much progress has been made on each task and the progress status.

[1226] Terminal

[1227] The entered progress data is collected and sent to the server.

[1228] server

[1229] Analyze progress data to see if the work plan is progressing as planned. Adjust the work plan as needed and generate a new plan. Send the adjusted work plan and feedback to the device.

[1230] 6. Emotion recognition and work plan adjustment

[1231] Emotion Engine

[1232] It recognizes emotions from the worker's facial expressions, tone of voice, input content, etc., and identifies the worker's current emotional state.

[1233] server

[1234] The system adjusts the work plan based on the recognized emotion data. For example, if the worker is feeling stressed, it adjusts the workload or difficulty level. Depending on the recognized emotion, it generates encouraging messages or appropriate feedback and sends them to the device.

[1235] Specific examples

[1236] Specific examples including example prompts

[1237] Analyze the operating status of Area A and evaluate daily work efficiency and error rates. In addition, recognize emotions based on the robot's operating sounds and posture data, identify signs of stress, and propose appropriate improvement measures.

[1238] The above is an embodiment of the present invention. This system enables efficient and flexible generation of work plans and adjustments according to the emotional state of the worker.

[1239] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[1240] Step 1:

[1241] Data entry by the user (operator)

[1242] While working, workers input work data via devices such as tablets or smartphones, including specific work items, progress, and any problems that have occurred. The input data is temporarily stored on the device.

[1243] Input: Work items, progress, issues encountered

[1244] Output: raw data collected

[1245] Step 2:

[1246] Data collection and transmission by the device

[1247] The device collects the work data entered by the user, formats it appropriately, and transmits it to the server. The collected data, including real-time work status information obtained from the camera and microphone, is converted into a format that can be analyzed by the device.

[1248] Input: Raw data collected

[1249] Output: Formatted data

[1250] Step 3:

[1251] Data reception and preprocessing by the server

[1252] The server receives the data sent from the device and stores it in a database. It then performs preprocessing on the received data, such as outlier detection and missing value imputation, to improve the reliability of the data and make it suitable for subsequent analysis steps.

[1253] Input: Formatted data

[1254] Output: Preprocessed data

[1255] Step 4:

[1256] Data analysis by server

[1257] The server analyzes the preprocessed data and evaluates the worker's work efficiency. Specifically, it analyzes the progress and error rate of each work item and performs data calculations to identify the strengths and weaknesses of the work.

[1258] Input: Preprocessed data

[1259] Output: Efficiency analysis results

[1260] Step 5:

[1261] Server-based estimation and generation of work plans

[1262] The server estimates the optimal work plan based on the work efficiency evaluation results. It calculates the worker's work plan by referencing past work data and efficiency standards. At the same time, it generates and proposes efficiency improvement measures.

[1263] Input: Efficiency analysis results, past work data

[1264] Output: Estimated work plan, efficiency improvement measures

[1265] Step 6:

[1266] Device suggestions and feedback

[1267] The terminal displays the work plan and efficiency improvement measures received from the server to the worker. The worker checks these suggestions and proceeds with the work based on them. If necessary, the work plan can be adjusted.

[1268] Input: Estimated work plan, efficiency improvement measures

[1269] Output: Feedback and suggestions to the worker

[1270] Step 7:

[1271] Input of daily work progress by users (workers)

[1272] Workers input their daily work progress into the terminal, including how much progress has been made on each task and the progress status. The input data is temporarily saved on the terminal.

[1273] Input: Daily work progress

[1274] Output: Collected progress data

[1275] Step 8:

[1276] Progress data collection and transmission by the device

[1277] The terminal collects daily work progress data entered by the user, formats it appropriately, and transmits it to the server, where it is converted into a format suitable for subsequent analysis.

[1278] Input: Collected progress data

[1279] Output: Formatted progress data

[1280] Step 9:

[1281] Server analysis and adjustment of progress data

[1282] The server analyzes the formatted progress data to verify that the work plan is progressing as planned, adjusts the work plan as necessary, generates a new plan, and sends the adjusted work plan and feedback to the device.

[1283] Input: Formatted progress data

[1284] Output: Coordinated work plan, feedback

[1285] Step 10:

[1286] Emotion recognition by emotion engine

[1287] The emotion engine installed on the terminal or server recognizes emotions from the worker's facial expressions, tone of voice, input content, etc., and identifies the worker's current emotional state.

[1288] Input: Facial expression data, tone of voice, input content

[1289] Output: Emotion recognition result

[1290] Step 11:

[1291] Server adjusts work plan based on emotion data

[1292] The server adjusts the work plan based on the emotional data recognized by the emotion engine. If the user is feeling stressed, it adjusts the workload and difficulty, generates appropriate encouraging messages and feedback, and sends them to the device.

[1293] Input: Emotion recognition results

[1294] Output: Coordinated work plan, encouraging messages

[1295] Through the above processing steps, the system as a whole generates efficient and flexible work plans and makes adjustments according to the emotional state of the worker.

[1296] The specific processing unit 290 transmits the result of the specific processing to the smart glasses 214. In the smart glasses 214, the control unit 46A causes the speaker 240 to output the result of the specific processing. The microphone 238 acquires audio indicating a user input regarding the result of the specific processing. The control unit 46A transmits audio data indicating the user input acquired by the microphone 238 to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the audio data.

[1297] The data generation model 58 is a so-called generative AI (Artificial Intelligence). An example of the data generation model 58 is ChatGPT (Internet Search<URL: https: / / openai.com / blog / chatgpt> ), Gemini (Internet search <url: https: gemini.google.com ?hl="ja">) and other generation AIs. The data generation model 58 is obtained by performing deep learning on a neural network. A prompt including an instruction is input to the data generation model 58, and inference data such as voice data indicating voice, text data indicating text, and image data indicating an image is also input. The data generation model 58 performs inference on the input inference data in accordance with the instruction indicated by the prompt, and outputs the inference result in a data format such as voice data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[1298] In the above embodiment, an example in which the specific processing is performed by the data processing device 12 has been given, but the technology of the present disclosure is not limited to this, and the specific processing may be performed by the smart glasses 214.

[1299] [Third embodiment]

[1300] FIG. 5 shows an example of the configuration of a data processing system 310 according to the third embodiment.

[1301] 5, the data processing system 310 includes the data processing device 12 and a headset type terminal 314. An example of the data processing device 12 is a server.

[1302] The data processing device 12 includes a computer 22, a database 24, and a communication I / F 26. The computer 22 is an example of a "computer" according to the technology of the present disclosure. The computer 22 includes a processor 28, a RAM 30, and a storage 32. The processor 28, the RAM 30, and the storage 32 are connected to a bus 34. The database 24 and the communication I / F 26 are also connected to the bus 34. The communication I / F 26 is connected to a network 54. Examples of the network 54 include a WAN (Wide Area Network) and / or a LAN (Local Area Network).

[1303] The headset type terminal 314 includes a computer 36, a microphone 238, a speaker 240, a camera 42, a communication I / F 44, and a display 343. The computer 36 includes a processor 46, a RAM 48, and a storage 50. The processor 46, the RAM 48, and the storage 50 are connected to a bus 52. The microphone 238, the speaker 240, the camera 42, and the display 343 are also connected to the bus 52.

[1304] The microphone 238 receives instructions and the like from the user 20 by receiving voice uttered by the user 20. The microphone 238 captures the voice uttered by the user 20, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio in accordance with instructions from the processor 46.

[1305] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an imaging element such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, and captures images of the surroundings of user 20 (for example, an imaging range defined by an angle of view equivalent to the field of vision of a typical healthy person).

[1306] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 are responsible for the exchange of various information between the processor 46 and the processor 28 via the network 54. The exchange of various information between the processor 46 and the processor 28 using the communication I / Fs 44 and 26 is carried out in a secure state.

[1307] Fig. 6 shows an example of the main functions of the data processing device 12 and the headset type terminal 314. As shown in Fig. 6, in the data processing device 12, a specific process is performed by the processor 28. A specific process program 56 is stored in the storage 32.

[1308] The specific processing program 56 is an example of a "program" according to the technology of the present disclosure. The processor 28 reads the specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific processing is realized by the processor 28 operating as a specific processing unit 290 in accordance with the specific processing program 56 executed on the RAM 30.

[1309] The storage 32 stores a data generation model 58 and an emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290.

[1310] In the headset type terminal 314, a reception output process is performed by the processor 46. A reception output program 60 is stored in the storage 50. The processor 46 reads the reception output program 60 from the storage 50 and executes the read reception output program 60 on the RAM 48. The reception output process is realized by the processor 46 operating as the control unit 46A in accordance with the reception output program 60 executed on the RAM 48.

[1311] Next, a description will be given of the identification process performed by the identification processing unit 290 of the data processing device 12. In the following description, the data processing device 12 will be referred to as the "server" and the headset type terminal 314 will be referred to as the "terminal."

[1312] This system uses students' test scores and report card performance data to generate a list of schools of choice and backup schools, and indicates necessary study and challenges to overcome. The system consists of a server, terminals, and users (students).

[1313] System Configuration

[1314] 1. Data Collection

[1315] User (student):

[1316] Students enter their midterm and final exam scores, as well as their report card grades, into the terminal.

[1317] The data entered by the learner is saved on the device.

[1318] Device:

[1319] The terminal collects the input data and sends it to the server.

[1320] The terminal is equipped with an application and a web interface to provide a user interface.

[1321] 2. Data Analysis

[1322] server:

[1323] Receives data sent from the device and stores it in a database.

[1324] Check your data for outliers and missing values ​​and correct them if necessary.

[1325] Learners' test scores and grade data are analyzed to evaluate their performance in each subject.

[1326] Based on the analysis results, the learner's strengths and weaknesses are identified and their academic ability is evaluated.

[1327] 3. Pass rate estimation and list generation

[1328] server:

[1329] Based on the results of the student's academic assessment, the chances of them being accepted into their preferred school are estimated.

[1330] Refer to the data and statistics of past successful applicants for the school of your choice.

[1331] Generate a list of preferred schools (first to third choice) and a list of backup schools based on the acceptance rate.

[1332] Send your list of preferred schools and backup schools to your device.

[1333] 4. Feedback and learning plan creation

[1334] Device:

[1335] The generated list of preferred schools and backup schools is displayed to the learner.

[1336] Support the learner in creating an individualized learning plan based on the list they have reviewed.

[1337] server:

[1338] Based on an analysis of grades for each subject, weak areas and specific challenges are identified.

[1339] Recommend specific study methods and materials for identified issues.

[1340] Recommended study materials and methods are sent to your device.

[1341] 5. Learning progress management and feedback

[1342] User (student):

[1343] Daily study progress is entered into the device, including how much of each subject has been studied and the progress made.

[1344] Device:

[1345] The entered progress data is collected and sent to the server.

[1346] server:

[1347] Analyze your progress data to ensure your learning plan is on track.

[1348] Adjust the learning plan as needed and notify the learner.

[1349] Provide ongoing feedback to support effective learning.

[1350] Specific examples

[1351] Example 1: Test score analysis and feedback

[1352] User (student):

[1353] Enter 80 points for math, 70 points for English, 60 points for science, and 90 points for Japanese into the terminal.

[1354] The terminal collects the data and sends it to the server.

[1355] server:

[1356] The grade data is analyzed and it is determined that mathematics and Japanese are strong subjects, while science and English are weak subjects.

[1357] Calculate the acceptance rate for your desired school and make a list of your first, second, and third choice schools.

[1358] Recommended study methods include using problem sets that focus on specific areas of science and strengthening English vocabulary.

[1359] Device:

[1360] The analysis results are displayed to the learner and recommended learning methods are provided.

[1361] Example 2: Managing learning progress

[1362] User (student):

[1363] Enter your English study progress from the previous month into the device.

[1364] The device collects progress data and sends it to the server.

[1365] server:

[1366] Analyze progress data to determine if learning is not progressing as planned.

[1367] Adjust your English study plan and propose new ones.

[1368] Device:

[1369] Display the adjusted learning plan to the learner and provide feedback.

[1370] The above is an embodiment of the system of the present invention, which makes it possible to provide learners with individually optimized study plans and support for further education.

[1371] The processing flow will be explained below.

[1372] Step 1:

[1373] Students use the device to input their scores for each subject in midterm and final exams, as well as their report card grades. Specifically, they input their grades for each semester and their grades for each subject via the device's application or web interface.

[1374] Step 2:

[1375] The device collects test score and report card data entered by the user, which is then properly formatted and prepared for transmission to the server.

[1376] Step 3:

[1377] The terminal transmits the collected data to the server. This transmission is performed securely over a network.

[1378] Step 4:

[1379] The server receives the data sent from the device, stores it in a database, and uses it for subsequent analysis.

[1380] Step 5:

[1381] The server pre-processes the received data, which includes outlier detection and missing value imputation. Anomaly detection algorithms are applied to ensure data integrity and quality.

[1382] Step 6:

[1383] The server analyzes the preprocessed data and evaluates the user's academic ability. Specifically, it calculates a deviation score based on the scores for each subject and identifies strengths and weaknesses.

[1384] Step 7:

[1385] The server estimates the probability of passing the desired school based on the analysis results, comparing them with past successful applicant data and the school's passing criteria to calculate the user's chances of passing.

[1386] Step 8:

[1387] The server generates a list of preferred schools and a list of backup schools based on the estimated pass rate. The list includes first- to third-choice schools and recommended backup schools.

[1388] Step 9:

[1389] The server sends the generated list and analysis results to the device, formatting the data in a way that is easily accessible to the user.

[1390] Step 10:

[1391] The terminal displays the list of preferred schools and the list of backup schools sent from the server to the user, who can use this information to help formulate their own study plan.

[1392] Step 11:

[1393] The server identifies weak areas and issues that need to be overcome based on the results of the user's performance analysis, and selects specific study methods and recommended learning materials for the identified issues.

[1394] Step 12:

[1395] The server then sends the selected study methods and recommended learning materials to the device, allowing the user to study effectively.

[1396] Step 13:

[1397] The user inputs their daily learning progress into the terminal, and the input progress data is collected by the terminal.

[1398] Step 14:

[1399] The device sends the collected progress data to a server, which enables real-time learning progress management.

[1400] Step 15:

[1401] The server analyzes the progress data to ensure the learning plan is on track, adjusts it as needed, and generates a new plan.

[1402] Step 16:

[1403] The server sends the adjusted learning plan and feedback to the device, which the user can then confirm and continue learning.

[1404] Example 1

[1405] Next, a description will be given of Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the headset type terminal 314 will be referred to as a "terminal."

[1406] In modern education, there is a demand for accurate assessment of each learner's academic ability and the provision of individualized learning plans based on that assessment. In particular, when selecting a school to attend, it is important to consider a learner's strengths and weaknesses and present effective learning methods. However, the current system does not adequately manage the creation of learning plans or learning progress, limiting the extent to which students can improve their academic ability. This makes it difficult to select a school to attend and create an effective learning plan, leading to problems such as reduced learning efficiency and motivation.

[1407] The specific processing by the specific processing unit 290 of the data processing device 12 in the first embodiment is realized by the following means.

[1408] In this invention, the server includes means for collecting input assessment data of learners, means for analyzing the learners' academic ability based on the collected data, means for estimating the pass rate for the desired school based on the analysis results, means for generating a list of educational institutions according to the pass rate estimated, means for displaying the generated list, means for creating a study plan for the learner based on the display means, and means for following up on the study plan. This allows for the evaluation of the learner's academic ability, selection of a school to attend, creation of an effective study plan, and progress management and feedback to be carried out in an integrated manner, thereby enabling the learner to improve their learning efficiency and achieve their goals.

[1409] "Inputted learner assessment data" refers to data such as test scores and report card grades entered by the learner.

[1410] "Means for analyzing academic ability" is a function that identifies a learner's strong and weak subjects based on collected evaluation data and evaluates the learner's overall academic ability.

[1411] "Means for estimating pass rates" is a function that statistically estimates the probability that a learner will be accepted into their desired school based on the results of academic ability analysis.

[1412] An "educational institution list" is a list of schools that a learner wishes to apply to, including their preferred school and backup schools.

[1413] The "means for displaying" is a function for providing the generated list of educational institutions to the learner and visually displaying it.

[1414] "Means for creating a study plan" is a function that allows learners to create a specific study plan to achieve their goals based on the displayed list of educational institutions.

[1415] "Means for following up on study plans" refers to a function for managing the progress of the study plans that have been created and adjusting the plans as necessary.

[1416] "Study progress data" refers to data such as the learning progress status and study time for each subject that is entered by the learner daily.

[1417] "Learning methods and materials" refers to the specific learning methods for a particular task and the instructions for the materials to be used.

[1418] This system uses student evaluation data to generate a list of schools of choice and backup schools, and creates and follows up on study plans. The system consists of a server, terminals, and users (student).

[1419] System Configuration

[1420] Data collection

[1421] User (learner):

[1422] The user enters into the terminal his or her test scores and report card grades for each subject, including, for example, math, English, science, and Japanese.

[1423] Device:

[1424] The terminal collects performance data entered by the user and sends it to the server. The terminal is equipped with an application or web interface and functions as a user interface. HTTP requests and JSON format data can be used for communication.

[1425] Data analysis

[1426] server:

[1427] The server receives the data sent from the device and stores it in a database system (e.g., MySQL or PostgreSQL). Next, it cleans the data and corrects outliers and missing values. It then uses a generative AI model (e.g., using Python's Pandas or Scikit-learn library) to analyze the learner's performance data and evaluate their performance in each subject.

[1428] Pass rate estimation and list generation

[1429] server:

[1430] Based on the analysis results, the system estimates the student's chances of getting into their preferred school. This estimation uses data on past successful applicants and statistical data. Next, a list of educational institutions (first choice, third choice, and backup schools) is generated based on the chances of getting into the school and sent to the device.

[1431] Feedback and learning plan creation

[1432] Device:

[1433] The device displays the generated list of preferred schools and backup schools to the user, and supports the user in creating an individualized study plan based on the lists they have reviewed.

[1434] server:

[1435] Based on the results of the analysis of grades, the system identifies areas where the learner is weak and specific challenges. Specific learning methods and learning materials are recommended for the identified challenges and sent to the device.

[1436] Learning progress management and feedback

[1437] User (learner):

[1438] Users enter their daily study progress into the device, for example, recording which subjects they studied and how many hours they spent studying.

[1439] Device:

[1440] The device collects the progress data entered and sends it to the server, which analyzes the progress data to check whether the learning plan is progressing as planned, adjusts the learning plan as necessary, and notifies the user.

[1441] Specific examples

[1442] Example 1: Test score analysis and feedback

[1443] User (learner):

[1444] Enter 80 points for math, 70 points for English, 60 points for science, and 90 points for Japanese into the terminal.

[1445] Device:

[1446] The terminal collects the data and sends it to the server.

[1447] server:

[1448] The server analyzes the grade data, evaluates students' strengths and weaknesses, calculates their chances of getting into their preferred schools, and generates a list of schools they can apply to. It also recommends using workbooks that focus on specific science subjects and improving English vocabulary.

[1449] Device:

[1450] The device displays the analysis results and recommended learning methods to the learner.

[1451] Example 2: Managing learning progress

[1452] User (learner):

[1453] Enter your English study progress from the previous month into the device.

[1454] Device:

[1455] The device collects progress data and sends it to the server.

[1456] server:

[1457] The server analyzes the progress data and determines if the student's learning is not going as planned. It adjusts the student's English learning plan and proposes a new plan.

[1458] Device:

[1459] The device displays the adjusted learning plan to the learner and provides feedback.

[1460] Prompt Sentence Examples

[1461] "Write a program where the user inputs grades for each subject, the system determines which subjects the user is good at and which subjects they are bad at, and generates a list of schools they want to apply to. Specifically, the system will analyze grade data for 80 points in math, 70 points in English, 60 points in science, and 90 points in Japanese, and generate a list of schools they want to apply to."

[1462] The above is an embodiment of the invention. This system makes it possible to provide learners with individually optimized learning plans and support for further education.

[1463] The flow of the identification process in the first embodiment will be described with reference to FIG.

[1464] Step 1:

[1465] The user (student) enters performance data:

[1466] Users enter their test scores and report card grades for each subject using a device application or a web interface. The data entered includes the grades for each subject (e.g., math 80 points, English 70 points, science 60 points, Japanese 90 points).

[1467] Input: Grade data for each subject

[1468] Output: Achievement data saved on the device

[1469] Step 2:

[1470] Device collects and transmits performance data:

[1471] The terminal temporarily stores the performance data entered by the user and sends it to the server. The data is encoded in JSON format and sent via an HTTP request.

[1472] Input: Achievement data saved on the device

[1473] Output: Achievement data sent to the server

[1474] Step 3:

[1475] The server receives and stores the performance data:

[1476] The server receives the grade data sent from the device and stores it in a database (e.g., MySQL or PostgreSQL). The received data includes grade information for each subject.

[1477] Input: Performance data sent from the device

[1478] Output: Achievement data stored in a database

[1479] Step 4:

[1480] The server parses the data:

[1481] The server retrieves the stored grade data and performs data cleaning, checking for outliers and missing values ​​and correcting them as necessary. It then uses a generative AI model (using, for example, Python's Pandas or Scikit-learn libraries) to evaluate performance in each subject and identify strong and weak subjects.

[1482] Input: Achievement data stored in the database

[1483] Output: Analysis results including strong and weak subjects

[1484] Step 5:

[1485] The server estimates the pass rate and generates a list:

[1486] Based on the analysis results, the server evaluates the student's academic ability and statistically estimates the student's chances of being accepted into their preferred school. This estimation uses data on past successful applicants and statistical data. It then generates a list of preferred schools and a list of backup schools.

[1487] Input: Analysis results including strong and weak subjects

[1488] Output: List of preferred schools and backup schools

[1489] Step 6:

[1490] The server sends the list to the device:

[1491] The generated list of preferred schools and alternative schools is sent to the device. The data is encoded in JSON format and sent via an HTTP request.

[1492] Input: List of preferred schools and backup schools

[1493] Output: List of preferred schools and backup schools sent to the terminal

[1494] Step 7:

[1495] The terminal displays the list to the user:

[1496] The terminal displays the received list of preferred schools and backup schools to the user, using an application or web page as the user interface.

[1497] Input: List of preferred schools and backup schools sent to the device

[1498] Output: A list of preferred and alternative schools displayed to the user

[1499] Step 8:

[1500] User enters learning progress data:

[1501] Users input their daily study progress into the device, for example, recording the study time and progress for each subject (e.g., studied English for 2 hours).

[1502] Input: Daily learning progress data

[1503] Output: Learning progress data saved on the device

[1504] Step 9:

[1505] Your device collects and transmits learning progress data:

[1506] The device collects learning progress data entered by the user and sends it to the server, where it is encoded in JSON format and sent via an HTTP request.

[1507] Input: Learning progress data stored on the device

[1508] Output: Learning progress data sent to the server

[1509] Step 10:

[1510] The server analyzes the progress data and provides feedback:

[1511] The server analyzes the received progress data, checks whether the learning plan is progressing as planned, adjusts the learning plan if necessary, creates a new learning plan, and notifies the user.

[1512] Input: Learning progress data sent to the server

[1513] Output: Feedback and adjusted learning plan provided to the user

[1514] (Application example 1)

[1515] Next, a description will be given of Application Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the headset type terminal 314 will be referred to as a "terminal."

[1516] Conventional educational support systems are limited to analyzing students' academic performance data and estimating their chances of getting into their preferred schools, and do not adequately create specific study plans or manage progress. Furthermore, they do not provide specific learning materials or methods to help students overcome their weaknesses, limiting the effectiveness of improving their learning efficiency. Furthermore, these functions needed to be integrated into an educational support application provided in a virtual store. The present invention aims to provide a system that solves these problems.

[1517] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 1 is realized by the following means.

[1518] In this invention, the server includes means for collecting input test scores and performance data of learners, means for analyzing the learner's academic ability based on the collected data, means for estimating the pass rate for the desired school based on the analysis results, means for generating a list of desired schools and a list of backup schools according to the estimated pass rate, means for displaying the generated lists, means for creating a study plan for the learner based on the display means, means for recommending learning materials and study methods to help the learner overcome weaknesses based on the study plan and list of desired schools, and means for collecting and analyzing the learner's progress with the recommended learning materials and study methods. This enables learning support and support for further education that are individually optimized for each learner.

[1519] A "learner" is someone who belongs to an educational institution and takes tests and assessments.

[1520] A "test score" is the score or marks a learner receives when taking an exam or assessment.

[1521] "Academic performance data" refers to information indicating a learner's academic performance as assessed in the form of a report card, a report, or the like.

[1522] "Means for analyzing academic ability" refers to methods or systems for analyzing learners' test scores and grade data and evaluating their academic ability in each subject and overall.

[1523] A "means for estimating pass rates" is a method or algorithm for calculating the probability of a student being accepted into a school of their choice based on their current academic ability data.

[1524] A "school of choice list" is a list of schools that a student wishes to attend, ranked based on their acceptance rate.

[1525] A "safety school list" is a list of schools that have a high chance of acceptance in case you are not accepted into your preferred school.

[1526] "Display means" refers to the method or device for visually presenting the generated school preference list and other information to the learner.

[1527] A "means for creating a study plan" is a method or system for constructing daily study content and schedules to help learners achieve their goals.

[1528] "Means for recommending learning materials and learning methods" are systems or algorithms that suggest appropriate learning materials and effective learning methods to address learners' weaknesses and challenges.

[1529] "Means for collecting and analyzing progress" refers to methods and systems for recording learners' daily learning activities and evaluating whether they are progressing as planned.

[1530] A "virtual store" is a virtual shop or platform that provides educational services and teaching materials via the Internet.

[1531] This system uses a student's test scores and report card grade data to generate a list of schools of choice and backup schools, and indicates necessary study and challenges to overcome. This system is composed of a server, a terminal (such as a smartphone or PC), and a user (a student).

[1532] System Configuration

[1533] 1. Data Collection

[1534] User (learner):

[1535] Students enter their midterm and final exam scores, as well as their report card grades, into the terminal.

[1536] The data entered by the learner is saved on the device.

[1537] Device:

[1538] The terminal collects the input data and sends it to the server.

[1539] The terminal is equipped with an application and a web interface to provide a user interface.

[1540] 2. Data Analysis

[1541] server:

[1542] Receives data sent from the device and stores it in a database.

[1543] Check your data for outliers and missing values ​​and correct them if necessary.

[1544] Learners' test scores and grade data are analyzed to evaluate their performance in each subject.

[1545] Based on the analysis results, the learner's strengths and weaknesses are identified and their academic ability is evaluated.

[1546] 3. Pass rate estimation and list generation

[1547] server:

[1548] Based on the results of the student's academic assessment, the chances of them being accepted into their preferred school are estimated.

[1549] Refer to the data and statistics of past successful applicants for the school of your choice.

[1550] Generate a list of preferred schools (first to third choice) and a list of backup schools based on the acceptance rate.

[1551] Send your list of preferred schools and backup schools to your device.

[1552] 4. Feedback and learning plan creation

[1553] Device:

[1554] The generated list of preferred schools and backup schools is displayed to the learner.

[1555] Support the learner in creating an individualized learning plan based on the list they have reviewed.

[1556] server:

[1557] Based on an analysis of grades for each subject, weak areas and specific challenges are identified.

[1558] Recommend specific study methods and materials for identified issues.

[1559] Recommended study materials and methods are sent to your device.

[1560] 5. Learning progress management and feedback

[1561] User (learner):

[1562] Daily study progress is entered into the device, including how much of each subject has been studied and the progress made.

[1563] Device:

[1564] The entered progress data is collected and sent to the server.

[1565] server:

[1566] Analyze your progress data to ensure your learning plan is on track.

[1567] Adjust the learning plan as needed and notify the learner.

[1568] Provide ongoing feedback to support effective learning.

[1569] Specific examples

[1570] User (learner):

[1571] Enter 80 points for math, 70 points for English, 60 points for science, and 90 points for Japanese into the terminal.

[1572] The terminal collects the data and sends it to the server.

[1573] server:

[1574] The grade data is analyzed and it is determined that mathematics and Japanese are strong subjects, while science and English are weak subjects.

[1575] Calculate the acceptance rate for your desired school and make a list of your first, second, and third choice schools.

[1576] Recommended study methods include using problem sets that focus on specific areas of science and strengthening English vocabulary.

[1577] Device:

[1578] The analysis results are displayed to the learner and recommended learning methods are provided.

[1579] The above series of processes realizes learning support that is optimized for each learner. As a concrete example, let us consider the following prompt sentence as input to the generative AI model.

[1580] Example prompt sentence:

[1581] "A student's test scores are: Math 80, English 70, Science 60, Japanese 90. In this case, please list the student's first, second, and third choice schools. Also, please suggest the best study methods for English and Science, which are the weaker subjects."

[1582] In this way, by utilizing generative AI models, it is possible to provide more accurate learning assistance.

[1583] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[1584] Step 1:

[1585] Users input test scores and grade data. Specifically, learners input their midterm and final exam scores and report card scores into a smartphone or PC device. The input data includes the scores for each subject. After input, the data is temporarily stored on the device.

[1586] Step 2:

[1587] The device sends the collected data to a server. The device is equipped with an application or web interface that formats the data entered by the user and sends it to the server. The data is encrypted before being sent.

[1588] Step 3:

[1589] The server receives the data and stores it in the database. The server checks the integrity of the data and corrects any outliers or missing values. For example, if a math score is over 100, it is treated as an outlier. After checking that the data is in the correct format, it is stored in the database.

[1590] Step 4:

[1591] The server analyzes the learner's test scores and performance data. It uses analytical algorithms to evaluate performance in each subject. Specifically, it calculates the mean and standard deviation of scores and identifies strengths and weaknesses in each subject. Algorithms used here include XGBoost and linear regression models.

[1592] Step 5:

[1593] The server estimates the pass rate for the student's desired school based on the analysis results. It compares the student's scores with past successful applicant data and statistical data to calculate the pass rate for the desired school. For example, using the XGBoost model, the pass rate can be estimated by inputting data for 80 points in math, 70 points in English, 60 points in science, and 90 points in Japanese.

[1594] Step 6:

[1595] The server generates a list of preferred schools and a list of backup schools according to the pass rate. Based on the calculated pass rate, lists of first-choice, second-choice, third-choice, etc. are created. A list of backup schools with relatively high pass rates is also generated at the same time.

[1596] Step 7:

[1597] The server sends the generated list to the terminal. After generating the list, the server sends it to the terminal. At this time, the data is encrypted again and sent. The data is formatted in the appropriate format so that it can be displayed correctly on the terminal.

[1598] Step 8:

[1599] The device displays the student's list of preferred schools and backup schools. The list is displayed for easy access by the student through the device's application or web interface. Specifically, the list is displayed in list format along with the acceptance rate for each preferred school.

[1600] Step 9:

[1601] The server analyzes the learner's weak areas and the challenges they need to overcome. Based on the results of the analysis, it identifies subjects and areas where students have particularly low scores and evaluates what learning methods are most effective.

[1602] Step 10:

[1603] The server then recommends learning materials and methods that address the identified issues. For example, it might recommend a workbook focused on a specific area of ​​science or an app to improve English vocabulary. This recommendation information is selected using an analytical algorithm.

[1604] Step 11:

[1605] The device will display recommended learning materials and methods to the learner, who can then review the recommended materials and methods and incorporate them into their own learning plans.

[1606] Step 12:

[1607] The user inputs their daily learning progress into the device. The learner inputs their daily learning content and progress and saves it on the device. The input data includes the subjects studied, the time spent, and the progress status.

[1608] Step 13:

[1609] The terminal sends the entered progress data to the server. The terminal formats the progress data entered by the learner and sends it to the server.

[1610] Step 14:

[1611] The server analyzes the progress data to check whether the learning plan is progressing as planned. Based on the progress data, the server evaluates whether the learner's plan is progressing properly and makes adjustments as necessary.

[1612] Step 15:

[1613] The server sends the results of the adjustments to the learning plan to the device. If the plan is not progressing as planned, a new learning plan will be proposed and sent to the device.

[1614] Step 16:

[1615] The device will then display the adjusted study plan to the learner. By presenting the new plan, the learner can study more efficiently.

[1616] The above processing steps enable learners to receive individually optimized learning support and maximize their learning outcomes. Specifically, by inputting the following prompt sentences into the generative AI model, highly accurate analysis and feedback can be obtained.

[1617] Example prompt sentence:

[1618] "A student's test scores are: Math 80, English 70, Science 60, Japanese 90. In this case, please list the student's first, second, and third choice schools. Also, please suggest the best study methods for English and Science, which are the weaker subjects."

[1619] Furthermore, an emotion engine that estimates the user's emotion may be further combined. That is, the identification processing unit 290 may estimate the user's emotion using the emotion identification model 59, and perform identification processing using the user's emotion.

[1620] This invention combines a system that uses a learner's test scores and report card grade data to generate a list of preferred and backup schools, and indicates necessary study and challenges to overcome, with an emotion engine that recognizes the user's emotions. The system is composed of a server, terminals, and users (students).

[1621] System Configuration

[1622] 1. Data Collection

[1623] User (student):

[1624] Students input their scores for each subject in midterm and final exams, as well as their report card grades, into the terminal using a terminal application or a web interface.

[1625] Device:

[1626] The terminal collects the entered data, formats it appropriately, and sends it to the server.

[1627] 2. Data Analysis

[1628] server:

[1629] The server receives the data sent from the terminal and stores it in a database.

[1630] Preprocessing such as outlier detection and missing value completion is performed on the received data.

[1631] Analyze the pre-processed data to evaluate the learner's academic ability, identifying scores, deviation values, strengths and weaknesses for each subject.

[1632] 3. Pass rate estimation and list generation

[1633] server:

[1634] Based on the results of the academic assessment, the system estimates the chances of passing the desired school. It also calculates the user's chances of passing by referencing past passing data and the school's passing criteria.

[1635] Based on the estimated pass rate, a list of preferred schools (first to third choice) and a list of backup schools are generated.

[1636] Send your list of preferred schools and backup schools to your device.

[1637] 4. Feedback and learning plan creation

[1638] Device:

[1639] The data received from the server is displayed to the user, who can then check the list of schools of choice and the results of the grade analysis.

[1640] Based on the results of the analysis of a learner's grades, we identify areas of weakness and challenges that need to be overcome, and then present specific study methods and recommended materials to address these challenges.

[1641] server:

[1642] Specific study methods and recommended study materials to overcome weak areas are selected and sent to the device.

[1643] 5. Emotional awareness and learning plan adjustment

[1644] Emotion Engine:

[1645] It recognizes emotions from the user's facial expressions, tone of voice, input content, etc., and identifies the user's current emotional state.

[1646] server:

[1647] The learning plan is adjusted based on the recognized emotional data, for example, adjusting the amount or difficulty of learning if the user is feeling stressed.

[1648] Depending on the recognized emotion, encouraging messages and appropriate feedback are generated and sent to the device.

[1649] 6. Learning progress management and feedback

[1650] User (student):

[1651] Daily study progress is entered into the device, including how much of each subject has been studied and the progress made.

[1652] Device:

[1653] The entered progress data is collected and sent to the server.

[1654] server:

[1655] Analyze progress data to ensure your learning plan is on track, adjust it if necessary, and generate a new plan.

[1656] The adjusted learning plan and feedback are sent to the device, where the user can confirm and continue learning.

[1657] Specific examples

[1658] Example 1: Test score analysis and feedback

[1659] User (student):

[1660] The student enters their scores into the terminal: 80 points for math, 70 points for English, 60 points for science, and 90 points for Japanese. The terminal collects the data and sends it to the server.

[1661] server:

[1662] The grade data is analyzed and it is determined that mathematics and Japanese are strong subjects, while science and English are weak subjects.

[1663] Calculate the acceptance rate for your desired school and make a list of your first, second, and third choice schools.

[1664] Recommended study methods include using problem sets that focus on specific areas of science and strengthening English vocabulary.

[1665] Device:

[1666] The analysis results are displayed to the learner and recommended learning methods are provided.

[1667] Emotion Engine:

[1668] The system recognizes whether the user is feeling anxious or stressed from their facial expressions and tone of voice while they are typing.

[1669] server:

[1670] Based on the recognized emotion data, the system generates encouraging messages and suggests adjustments to the amount of study. For example, it provides messages such as, "You seem to be good at math! Keep it up!"

[1671] Example 2: Managing learning progress

[1672] User (student):

[1673] The user enters their English study progress from the previous month into the device, which then collects the progress data and sends it to the server.

[1674] server:

[1675] Analyze progress data to determine if learning is not progressing as planned.

[1676] Adjust your English study plan and propose new ones.

[1677] Emotion Engine:

[1678] The emotion engine recognizes that the user is feeling stressed from their facial expressions and voice when entering their progress.

[1679] server:

[1680] Based on the recognized emotions, the system suggests educational materials that can be understood quickly and efficiently to reduce stress.

[1681] Device:

[1682] Provide users with tailored learning plans and feedback to support their learning.

[1683] summary

[1684] The system of the present invention allows learners to receive efficient and personalized learning support based on their own performance data and progress. Furthermore, by combining it with an emotion engine, appropriate feedback and adjustments to the learning plan are made according to the user's emotional state, enabling effective learning while reducing stress.

[1685] The processing flow will be explained below.

[1686] Step 1:

[1687] Students use the device to input their scores for each subject in midterm and final exams, as well as their report card grades. Specifically, they input their grades for each semester and their grades for each subject via the device's application or web interface.

[1688] Step 2:

[1689] The device collects test score and report card data entered by the user, which is then prepared and properly formatted for transmission to the server.

[1690] Step 3:

[1691] The terminal transmits the collected data to the server. This transmission is performed securely over a network.

[1692] Step 4:

[1693] The server receives the data sent from the device, stores it in a database, and uses it for subsequent analysis.

[1694] Step 5:

[1695] The server pre-processes the received data, which includes outlier detection and missing value imputation. Anomaly detection algorithms are applied to ensure data integrity and quality.

[1696] Step 6:

[1697] The server analyzes the preprocessed data and evaluates the user's academic ability. Specifically, it calculates a deviation score based on the scores for each subject and identifies strengths and weaknesses.

[1698] Step 7:

[1699] The server estimates the probability of passing the desired school based on the analysis results, comparing them with past successful applicant data and the school's passing criteria to calculate the user's chances of passing.

[1700] Step 8:

[1701] The server generates a list of preferred schools and a list of backup schools based on the estimated pass rate. The list includes first- to third-choice schools and recommended backup schools.

[1702] Step 9:

[1703] The server sends the generated list and analysis results to the device, formatting the data in a way that is easily accessible to the user.

[1704] Step 10:

[1705] The terminal displays the list of preferred schools and the list of backup schools sent from the server to the user, who can use this information to help formulate their own study plan.

[1706] Step 11:

[1707] The server identifies weak areas and issues that need to be overcome based on the results of the user's performance analysis, and selects specific study methods and recommended learning materials for the identified issues.

[1708] Step 12:

[1709] The server then sends the selected study methods and recommended learning materials to the device, allowing the user to study effectively.

[1710] Step 13:

[1711] The emotion engine recognizes emotions from the user's facial expressions, tone of voice, and input content to identify the user's current emotional state.

[1712] Step 14:

[1713] The server receives the emotion data recognized by the emotion engine and adjusts the study plan, for example, reducing the amount of study or lowering the difficulty level if the user is feeling stressed.

[1714] Step 15:

[1715] The server generates encouraging messages and appropriate feedback based on the recognized emotion data and sends them to the device, such as "You seem to be good at math! Keep it up!"

[1716] Step 16:

[1717] Users enter their daily study progress into the terminal, including how much they studied and what subjects they studied, as well as their progress.

[1718] Step 17:

[1719] The terminal collects the entered progress data and transmits it to the server.

[1720] Step 18:

[1721] The server analyzes the progress data to ensure the learning plan is on track, adjusts it as needed, and generates a new plan.

[1722] Step 19:

[1723] The server sends the adjusted learning plan and feedback to the device, which the user can then confirm and continue learning.

[1724] The above is a specific flow of processing in the system of the present invention. By providing individually optimized learning support while taking into consideration the user's emotions, learning efficiency is improved and stress is reduced.

[1725] Example 2

[1726] Next, a description will be given of Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the headset type terminal 314 will be referred to as a "terminal."

[1727] In conventional educational systems, learning plans are often created based on a learner's academic performance data, but they lack the ability to adjust to the learner's individual emotional state. This can lead to learners feeling stressed or anxious, which can hinder their ability to perform at their best and result in less than optimal learning outcomes. There is a need for a system that provides a comprehensive approach that takes into account not only academic performance data but also daily learning progress and emotional state.

[1728] The identification process by the identification processing unit 290 of the data processing device 12 in the second embodiment is realized by the following means. In this invention, the server includes means for collecting input academic performance data of the learner, means for analyzing the learner's academic ability based on the collected data, means for estimating the pass rate for the desired school based on the analysis results, means for generating a list of desired schools and a list of backup schools according to the estimated pass rate, means for displaying the generated lists, means for creating a study plan for the learner based on the display means, means for recognizing the learner's emotional state, and means for adjusting the study plan based on the recognized emotional state. This enables comprehensive learning support that takes into account the learner's emotional state.

[1729] "Academic performance data" refers to data including the scores obtained by a learner in each subject and the grades on their report cards.

[1730] "Academic ability" refers to the results of assessing a learner's scores in each subject and their overall learning ability.

[1731] "Analysis results" refers to the output of a learner's academic ability assessment based on the collected data.

[1732] "Preferred school" refers to the educational institution that a learner wishes to attend.

[1733] The "pass rate" is a value indicating the probability that a learner will pass the entrance examination to the school of their choice.

[1734] A "preferred school list" is a list of educational institutions that a learner wishes to attend, ranked in order.

[1735] A "safety school list" is a list of educational institutions that a student may consider attending if they are not accepted into their preferred school.

[1736] "Display means" refers to a device or method for displaying the generated list, analysis results, etc. to the learner.

[1737] A "study plan" refers to the specific learning content and schedule set out to help learners progress effectively in their studies.

[1738] "Emotional state" refers to the learner's current emotional state, including, for example, stress, anxiety, and motivation.

[1739] The present invention is a system that combines a learner's performance data and emotional state to provide an optimal study plan. This system is composed of a server, a terminal, and a user (learner).

[1740] server:

[1741] The server receives the grade data sent from the device and stores it in a database. It then analyzes the grade data to evaluate the learner's academic ability. Specifically, it performs preprocessing such as outlier detection and missing value imputation. Based on the preprocessed data, it calculates the deviation score for each subject, as well as the student's strong and weak subjects. Based on the analysis results, it estimates the student's chances of getting into their preferred school. Using this chance as a reference, it generates a list of first- to third-choice schools and a list of safety schools. The server also has the ability to recognize the learner's emotional state and reflect this data in the study plan. For example, if the learner is feeling stressed, it can reduce the amount of study or adjust the difficulty level.

[1742] Device:

[1743] The terminal provides an interface for users to input grade data and progress data. For example, learners use a terminal application or web interface to input their grades for each subject and their report card grades. The terminal then converts the received data into an appropriate format and sends it to the server. The terminal then displays the analysis results, preferred school list, study plan, and emotional feedback sent from the server to the user. A dashboard using a graphical user interface (GUI) is provided to make it easy for learners to check the data.

[1744] User (learner):

[1745] Users input their scores for each subject in midterm and final exams, as well as report card grades, through the device. They also input their daily learning progress into the device and send it to the server as appropriate. Learning progresses based on the learning plan and feedback received from the device. The device's camera and microphone are also used to recognize the user's emotional state, providing an appropriate learning method that matches their emotional state.

[1746] Examples:

[1747] For example, if a user inputs "80 points in math, 70 points in English, 60 points in science, and 90 points in Japanese" into the device, the device converts the data into JSON format and sends it to the server. The server analyzes the grade data and determines that math and Japanese are strong subjects, while science and English are weak subjects. The server calculates the pass rate and displays it as 70% for the first choice school, 50% for the second choice school, and 90% for the third choice school. Recommended study methods include using workbooks that focus on specific areas of science and strengthening English vocabulary. As the user inputs progress data into the device, the server analyzes the progress and adjusts the study plan.

[1748] Furthermore, the emotion engine recognizes that if the user frowns while typing, they are feeling anxious, and adjusts the amount of learning they are doing, sending encouraging messages such as, "You seem to be good at math! Keep it up!"

[1749] This system not only provides learners with optimal study plans based on their performance data, but also provides flexible feedback and study adjustments that are tailored to their emotional state at the time, enabling efficient and stress-free learning.

[1750] The flow of the identification process in the second embodiment will be described with reference to FIG.

[1751] Step 1:

[1752] User: The learner uses a terminal application or a web interface to input the scores for each subject in the midterm and final exams, as well as the grade data from the report card. For example, the learner enters "80 points for math, 70 points for English, 60 points for science, and 90 points for Japanese."

[1753] Input: Score and grade data for each subject entered by the user

[1754] Output: Performance data sent to the device

[1755] Step 2:

[1756] Terminal: The terminal collects the grade data entered by the user and converts it into an appropriate format. Specifically, it converts the input data into JSON format. For example, it formats it as follows: {"Subject": {"Math": 80, "English": 70, "Science": 60, "Japanese": 90}}.

[1757] Input: User-entered grade data

[1758] Output: Formatted data (JSON format)

[1759] Step 3:

[1760] Terminal: Sends the collected and formatted performance data to the server, for example, using HTTP requests.

[1761] Input: Formatted data (JSON format)

[1762] Output: Grade data sent to the server

[1763] Step 4:

[1764] Server: The server receives the performance data sent from the device and stores it in a database. When storing the data, it associates it with each user's ID.

[1765] Input: Performance data sent from the device

[1766] Output: Achievement data stored in the database

[1767] Step 5:

[1768] Server: Preprocesses the saved grade data. Performs outlier detection and missing value imputation to ensure data accuracy. An outlier, for example, would be a negative score for each subject, and corrects it to within the normal range.

[1769] Input: Achievement data stored in the database

[1770] Output: Preprocessed grade data

[1771] Step 6:

[1772] Server: Analyzes the pre-processed data and evaluates the user's academic ability. Specifically, it calculates the deviation score and strong and weak subjects based on the scores for each subject.

[1773] Input: Preprocessed grade data

[1774] Output: Academic ability analysis results (deviation score for each subject, strong and weak subjects)

[1775] Step 7:

[1776] Server: Based on the results of the academic ability analysis, estimate the probability of admission to the user's desired school. In this case, past admission data and school standards are used as reference.

[1777] Input: Academic ability analysis results

[1778] Output: Pass rate estimation result

[1779] Step 8:

[1780] Server: Based on the estimated pass rate, it generates a list of preferred schools and a list of backup schools and sends this to the terminal.

[1781] Input: Pass rate estimation result

[1782] Output: List of preferred schools, list of backup schools

[1783] Step 9:

[1784] Terminal: Displays the list of schools of choice sent from the server and the results of the academic ability analysis to the user. The user can check the analysis results and the list.

[1785] Input: Preferred school list sent from the server, academic ability analysis results

[1786] Output: Displayed list of preferred schools, academic ability analysis results

[1787] Step 10:

[1788] Server: Selects specific study methods and recommended learning materials to help learners overcome their weak areas and sends them to the device.

[1789] Input: Academic ability analysis results (weak subjects)

[1790] Output: Study methods and recommended materials

[1791] Step 11:

[1792] Device: Displays study methods and recommended learning materials to the user. The user creates a study plan based on the information provided.

[1793] Input: Study methods and recommended materials sent from the server

[1794] Output: Displayed study methods and recommended materials

[1795] Step 12:

[1796] Emotion engine: Recognizes emotions from the user's facial expressions, tone of voice, and input content to identify their current emotional state. For example, if the user frowns while typing, it determines that they are feeling anxious.

[1797] Input: User facial expressions, tone of voice, and input

[1798] Output: Perceived emotional state

[1799] Step 13:

[1800] Server: Adjusts the study plan based on the recognized emotion data. For example, if the user is feeling stressed, the server suggests adjusting the amount of study or difficulty.

[1801] Input: Perceived emotional state

[1802] Output: Adjusted lesson plan

[1803] Step 14:

[1804] Server: Generates encouraging messages and appropriate feedback based on the recognized emotions and sends them to the device. For example, it provides a message like, "You seem to be good at math! Keep it up!"

[1805] Input: Perceived emotional state

[1806] Output: Encouraging message, feedback

[1807] Step 15:

[1808] Device: Displays tailored study plans and encouraging messages to users, allowing them to receive appropriate study methods tailored to their emotional state.

[1809] Input: Tailored study plan and encouraging messages sent from the server

[1810] Output: A displayed lesson plan and encouraging messages

[1811] Step 16:

[1812] User: Enters daily learning progress into the device. For example, progress information such as "English: Study 3 hours a week, Science: Study 2 hours a week" is recorded.

[1813] Input: Daily learning progress

[1814] Output: Progress data sent to the device

[1815] Step 17:

[1816] Terminal: Sends the collected progress data to the server, for example, using HTTP requests.

[1817] Input: Collected progress data

[1818] Output: Progress data sent to the server

[1819] Step 18:

[1820] Server: Analyzes progress data and checks whether the lesson plan is on track. If it is behind schedule, adjusts the plan and generates a new lesson plan.

[1821] Input: Progress data

[1822] Output: Progress analysis results, adjusted learning plan

[1823] Step 19:

[1824] Server: Sends the adjusted learning plan and feedback to the device, allowing the user to receive an appropriate learning plan based on their current progress.

[1825] Input: Tailored learning plan, feedback

[1826] Output: Learning plan and feedback sent to the device

[1827] Step 20:

[1828] Device: The adjusted learning plan and feedback are displayed to the user to support their learning. The user can then review the plan and continue their learning.

[1829] Input: Learning plan and feedback sent from the server

[1830] Output: Displayed lesson plan, feedback

[1831] (Application example 2)

[1832] Next, a description will be given of Application Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the headset type terminal 314 will be referred to as a "terminal."

[1833] Modern factories require robots to improve the efficiency and optimization of their work, but there are limitations to systems that can accurately evaluate a robot's operating status and work efficiency and suggest improvement measures. Furthermore, there is a lack of functionality to recognize a robot's stress or illness using an emotion engine and propose appropriate countermeasures. Therefore, there is a need for a system that can improve the efficiency of robots and flexibly adjust work plans according to the robot's condition.

[1834] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 2 is realized by the following means.

[1835] In this invention, the server includes means for collecting input worker data, means for analyzing worker efficiency based on the collected data, means for estimating a work plan based on the analysis results, means for generating efficiency improvement measures in accordance with the estimated work plan, means for displaying the generated efficiency improvement measures, means for creating a work plan for the worker based on the display means, means for inputting the worker's daily work progress and collecting the work progress data, means for adjusting the work plan based on the collected progress data, and means for identifying the worker's weak areas and challenges to overcome based on the estimated work plan and providing specific work methods and tools to address the identified challenges. This enables improved robot work efficiency and flexible adjustment of the work plan in response to the robot's stress or illness.

[1836] "Workers" refers to factory robots and the personnel who operate and manage them.

[1837] "Work data" refers to data that includes information such as the operating status of factory robots, work progress, and error rates.

[1838] "Efficiency analysis" is the process of analyzing and evaluating the work efficiency of workers and robots based on collected work data.

[1839] A "work plan" is a plan that specifies the work content and procedures to be performed by workers and robots.

[1840] "Efficiency improvement measures" are proposals that include specific methods and actions to improve the work efficiency of workers and robots.

[1841] The "emotion engine" is a system that analyzes the state of workers and robots and recognizes emotions such as stress and illness.

[1842] A "work method" is a specific operational procedure or technique used by a worker or robot to perform a specific task.

[1843] "Tools" refers to the equipment and tools used by workers and robots when performing work.

[1844] System Configuration

[1845] The system that realizes this application example consists of three main elements: a server, a terminal, and a user (operator).

[1846] 1. Data Collection

[1847] User (worker)

[1848] During their daily work, workers input work data via devices such as tablets or smartphones, including specific work items, progress, and any problems that arise.

[1849] Terminal

[1850] The terminal collects the input work data, formats it appropriately, and sends it to the server. The terminal is also connected to peripheral devices such as a camera and microphone, which can be used to monitor the work status in real time.

[1851] 2. Data Analysis

[1852] server

[1853] The server receives the data sent from the terminal and stores it in a database. The received data undergoes preprocessing, such as outlier detection and missing value completion. The preprocessed data is then analyzed to evaluate the worker's work efficiency. Specifically, the progress and error rate of each work item are analyzed to identify the strengths and weaknesses of the work.

[1854] 3. Estimating and generating work plans

[1855] server

[1856] The server estimates the optimal work plan based on the results of the work efficiency evaluation. It calculates the worker's work plan by referencing past work data and efficiency standards. At this time, it also makes suggestions, including measures to improve efficiency. Furthermore, based on the estimation results, it suggests the optimal work method and tools that the worker should use.

[1857] 4. Suggestions and Feedback

[1858] Terminal

[1859] The data received from the server is displayed to the worker, who checks the estimated work plan and efficiency improvement measures and proceeds with the work accordingly.

[1860] 5. Managing and adjusting learning progress

[1861] User (worker)

[1862] Daily work progress is entered into the terminal, including how much progress has been made on each task and the progress status.

[1863] Terminal

[1864] The entered progress data is collected and sent to the server.

[1865] server

[1866] Analyze progress data to see if the work plan is progressing as planned. Adjust the work plan as needed and generate a new plan. Send the adjusted work plan and feedback to the device.

[1867] 6. Emotion recognition and work plan adjustment

[1868] Emotion Engine

[1869] It recognizes emotions from the worker's facial expressions, tone of voice, input content, etc., and identifies the worker's current emotional state.

[1870] server

[1871] The system adjusts the work plan based on the recognized emotion data. For example, if the worker is feeling stressed, it adjusts the workload or difficulty level. Depending on the recognized emotion, it generates encouraging messages or appropriate feedback and sends them to the device.

[1872] Specific examples

[1873] Specific examples including example prompts

[1874] Analyze the operating status of Area A and evaluate daily work efficiency and error rates. In addition, recognize emotions based on the robot's operating sounds and posture data, identify signs of stress, and propose appropriate improvement measures.

[1875] The above is an embodiment of the present invention. This system enables efficient and flexible generation of work plans and adjustments according to the emotional state of the worker.

[1876] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[1877] Step 1:

[1878] Data entry by the user (operator)

[1879] While working, workers input work data via devices such as tablets or smartphones, including specific work items, progress, and any problems that have occurred. The input data is temporarily stored on the device.

[1880] Input: Work items, progress, issues encountered

[1881] Output: raw data collected

[1882] Step 2:

[1883] Data collection and transmission by the device

[1884] The device collects the work data entered by the user, formats it appropriately, and transmits it to the server. The collected data, including real-time work status information obtained from the camera and microphone, is converted into a format that can be analyzed by the device.

[1885] Input: Raw data collected

[1886] Output: Formatted data

[1887] Step 3:

[1888] Data reception and preprocessing by the server

[1889] The server receives the data sent from the device and stores it in a database. It then performs preprocessing on the received data, such as outlier detection and missing value imputation, to improve the reliability of the data and make it suitable for subsequent analysis steps.

[1890] Input: Formatted data

[1891] Output: Preprocessed data

[1892] Step 4:

[1893] Data analysis by server

[1894] The server analyzes the preprocessed data and evaluates the worker's work efficiency. Specifically, it analyzes the progress and error rate of each work item and performs data calculations to identify the strengths and weaknesses of the work.

[1895] Input: Preprocessed data

[1896] Output: Efficiency analysis results

[1897] Step 5:

[1898] Server-based estimation and generation of work plans

[1899] The server estimates the optimal work plan based on the work efficiency evaluation results. It calculates the worker's work plan by referencing past work data and efficiency standards. At the same time, it generates and proposes efficiency improvement measures.

[1900] Input: Efficiency analysis results, past work data

[1901] Output: Estimated work plan, efficiency improvement measures

[1902] Step 6:

[1903] Device suggestions and feedback

[1904] The terminal displays the work plan and efficiency improvement measures received from the server to the worker. The worker checks these suggestions and proceeds with the work based on them. If necessary, the work plan can be adjusted.

[1905] Input: Estimated work plan, efficiency improvement measures

[1906] Output: Feedback and suggestions to the worker

[1907] Step 7:

[1908] Input of daily work progress by users (workers)

[1909] Workers input their daily work progress into the terminal, including how much progress has been made on each task and the progress status. The input data is temporarily saved on the terminal.

[1910] Input: Daily work progress

[1911] Output: Collected progress data

[1912] Step 8:

[1913] Progress data collection and transmission by the device

[1914] The terminal collects daily work progress data entered by the user, formats it appropriately, and transmits it to the server, where it is converted into a format suitable for subsequent analysis.

[1915] Input: Collected progress data

[1916] Output: Formatted progress data

[1917] Step 9:

[1918] Server analysis and adjustment of progress data

[1919] The server analyzes the formatted progress data to verify that the work plan is progressing as planned, adjusts the work plan as necessary, generates a new plan, and sends the adjusted work plan and feedback to the device.

[1920] Input: Formatted progress data

[1921] Output: Coordinated work plan, feedback

[1922] Step 10:

[1923] Emotion recognition by emotion engine

[1924] The emotion engine installed on the terminal or server recognizes emotions from the worker's facial expressions, tone of voice, input content, etc., and identifies the worker's current emotional state.

[1925] Input: Facial expression data, tone of voice, input content

[1926] Output: Emotion recognition result

[1927] Step 11:

[1928] Server adjusts work plan based on emotion data

[1929] The server adjusts the work plan based on the emotional data recognized by the emotion engine. If the user is feeling stressed, it adjusts the workload and difficulty, generates appropriate encouraging messages and feedback, and sends them to the device.

[1930] Input: Emotion recognition results

[1931] Output: Coordinated work plan, encouraging messages

[1932] Through the above processing steps, the system as a whole generates efficient and flexible work plans and makes adjustments according to the emotional state of the worker.

[1933] The specific processing unit 290 transmits the result of the specific processing to the headset type terminal 314. In the headset type terminal 314, the control unit 46A causes the speaker 240 and the display 343 to output the result of the specific processing. The microphone 238 acquires audio indicating a user input regarding the result of the specific processing. The control unit 46A transmits audio data indicating the user input acquired by the microphone 238 to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the audio data.

[1934] The data generation model 58 is a so-called generative AI (Artificial Intelligence). An example of the data generation model 58 is ChatGPT (Internet Search<URL: https: / / openai.com / blog / chatgpt> ), Gemini (Internet search <url: https: gemini.google.com ?hl="ja">) and other generation AIs. The data generation model 58 is obtained by performing deep learning on a neural network. A prompt including an instruction is input to the data generation model 58, and inference data such as voice data indicating voice, text data indicating text, and image data indicating an image is also input. The data generation model 58 performs inference on the input inference data in accordance with the instruction indicated by the prompt, and outputs the inference result in a data format such as voice data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[1935] In the above embodiment, an example was given in which the specific processing is performed by the data processing device 12, but the technology of the present disclosure is not limited to this, and the specific processing may be performed by the headset type terminal 314.

[1936] [Fourth embodiment]

[1937] FIG. 7 shows an example of the configuration of a data processing system 410 according to the fourth embodiment.

[1938] 7, a data processing system 410 includes a data processing device 12 and a robot 414. An example of the data processing device 12 is a server.

[1939] The data processing device 12 includes a computer 22, a database 24, and a communication I / F 26. The computer 22 is an example of a "computer" according to the technology of the present disclosure. The computer 22 includes a processor 28, a RAM 30, and a storage 32. The processor 28, the RAM 30, and the storage 32 are connected to a bus 34. The database 24 and the communication I / F 26 are also connected to the bus 34. The communication I / F 26 is connected to a network 54. Examples of the network 54 include a WAN (Wide Area Network) and / or a LAN (Local Area Network).

[1940] The robot 414 includes a computer 36, a microphone 238, a speaker 240, a camera 42, a communication I / F 44, and a control target 443. The computer 36 includes a processor 46, a RAM 48, and a storage 50. The processor 46, the RAM 48, and the storage 50 are connected to a bus 52. The microphone 238, the speaker 240, the camera 42, and the control target 443 are also connected to the bus 52.

[1941] The microphone 238 receives instructions and the like from the user 20 by receiving voice uttered by the user 20. The microphone 238 captures the voice uttered by the user 20, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio in accordance with instructions from the processor 46.

[1942] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an imaging element such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, and captures images of the surroundings of user 20 (for example, an imaging range defined by an angle of view equivalent to the field of vision of a typical healthy person).

[1943] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 are responsible for the exchange of various information between the processor 46 and the processor 28 via the network 54. The exchange of various information between the processor 46 and the processor 28 using the communication I / Fs 44 and 26 is carried out in a secure state.

[1944] The control object 443 includes a display device, LEDs in the eyes, and motors for driving the arms, hands, and feet. The posture and gestures of the robot 414 are controlled by controlling the motors of the arms, hands, and feet. Some of the emotions of the robot 414 can be expressed by controlling these motors. In addition, the facial expressions of the robot 414 can also be expressed by controlling the light emission state of the LEDs in the eyes of the robot 414.

[1945] Fig. 8 shows an example of the main functions of the data processing device 12 and the robot 414. As shown in Fig. 8, in the data processing device 12, a specific process is performed by the processor 28. A specific process program 56 is stored in the storage 32.

[1946] The specific processing program 56 is an example of a "program" according to the technology of the present disclosure. The processor 28 reads the specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific processing is realized by the processor 28 operating as a specific processing unit 290 in accordance with the specific processing program 56 executed on the RAM 30.

[1947] The storage 32 stores a data generation model 58 and an emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290.

[1948] In the robot 414, the processor 46 performs the reception output process. A reception output program 60 is stored in the storage 50. The processor 46 reads the reception output program 60 from the storage 50 and executes the read reception output program 60 on the RAM 48. The reception output process is realized by the processor 46 operating as the control unit 46A in accordance with the reception output program 60 executed on the RAM 48.

[1949] Next, a description will be given of the specific processing performed by the specific processing unit 290 of the data processing device 12. In the following description, the data processing device 12 will be referred to as a "server" and the robot 414 will be referred to as a "terminal."

[1950] This system uses students' test scores and report card performance data to generate a list of schools of choice and backup schools, and indicates necessary study and challenges to overcome. The system consists of a server, terminals, and users (students).

[1951] System Configuration

[1952] 1. Data Collection

[1953] User (student):

[1954] Students enter their midterm and final exam scores, as well as their report card grades, into the terminal.

[1955] The data entered by the learner is saved on the device.

[1956] Device:

[1957] The terminal collects the input data and sends it to the server.

[1958] The terminal is equipped with an application and a web interface to provide a user interface.

[1959] 2. Data Analysis

[1960] server:

[1961] Receives data sent from the device and stores it in a database.

[1962] Check your data for outliers and missing values ​​and correct them if necessary.

[1963] Learners' test scores and grade data are analyzed to evaluate their performance in each subject.

[1964] Based on the analysis results, the learner's strengths and weaknesses are identified and their academic ability is evaluated.

[1965] 3. Pass rate estimation and list generation

[1966] server:

[1967] Based on the results of the student's academic assessment, the chances of them being accepted into their preferred school are estimated.

[1968] Refer to the data and statistics of past successful applicants for the school of your choice.

[1969] Generate a list of preferred schools (first to third choice) and a list of backup schools based on the acceptance rate.

[1970] Send your list of preferred schools and backup schools to your device.

[1971] 4. Feedback and learning plan creation

[1972] Device:

[1973] The generated list of preferred schools and backup schools is displayed to the learner.

[1974] Support the learner in creating an individualized learning plan based on the list they have reviewed.

[1975] server:

[1976] Based on an analysis of grades for each subject, weak areas and specific challenges are identified.

[1977] Recommend specific study methods and materials for identified issues.

[1978] Recommended study materials and methods are sent to your device.

[1979] 5. Learning progress management and feedback

[1980] User (student):

[1981] Daily study progress is entered into the device, including how much of each subject has been studied and the progress made.

[1982] Device:

[1983] The entered progress data is collected and sent to the server.

[1984] server:

[1985] Analyze your progress data to ensure your learning plan is on track.

[1986] Adjust the learning plan as needed and notify the learner.

[1987] Provide ongoing feedback to support effective learning.

[1988] Specific examples

[1989] Example 1: Test score analysis and feedback

[1990] User (student):

[1991] Enter 80 points for math, 70 points for English, 60 points for science, and 90 points for Japanese into the terminal.

[1992] The terminal collects the data and sends it to the server.

[1993] server:

[1994] The grade data is analyzed and it is determined that mathematics and Japanese are strong subjects, while science and English are weak subjects.

[1995] Calculate the acceptance rate for your desired school and make a list of your first, second, and third choice schools.

[1996] Recommended study methods include using problem sets that focus on specific areas of science and strengthening English vocabulary.

[1997] Device:

[1998] The analysis results are displayed to the learner and recommended learning methods are provided.

[1999] Example 2: Managing learning progress

[2000] User (student):

[2001] Enter your English study progress from the previous month into the device.

[2002] The device collects progress data and sends it to the server.

[2003] server:

[2004] Analyze progress data to determine if learning is not progressing as planned.

[2005] Adjust your English study plan and propose new ones.

[2006] Device:

[2007] Display the adjusted learning plan to the learner and provide feedback.

[2008] The above is an embodiment of the system of the present invention, which makes it possible to provide learners with individually optimized study plans and support for further education.

[2009] The processing flow will be explained below.

[2010] Step 1:

[2011] Students use the device to input their scores for each subject in midterm and final exams, as well as their report card grades. Specifically, they input their grades for each semester and their grades for each subject via the device's application or web interface.

[2012] Step 2:

[2013] The device collects test score and report card data entered by the user, which is then properly formatted and prepared for transmission to the server.

[2014] Step 3:

[2015] The terminal transmits the collected data to the server. This transmission is performed securely over a network.

[2016] Step 4:

[2017] The server receives the data sent from the device, stores it in a database, and uses it for subsequent analysis.

[2018] Step 5:

[2019] The server pre-processes the received data, which includes outlier detection and missing value imputation. Anomaly detection algorithms are applied to ensure data integrity and quality.

[2020] Step 6:

[2021] The server analyzes the preprocessed data and evaluates the user's academic ability. Specifically, it calculates a deviation score based on the scores for each subject and identifies strengths and weaknesses.

[2022] Step 7:

[2023] The server estimates the probability of passing the desired school based on the analysis results, comparing them with past successful applicant data and the school's passing criteria to calculate the user's chances of passing.

[2024] Step 8:

[2025] The server generates a list of preferred schools and a list of backup schools based on the estimated pass rate. The list includes first- to third-choice schools and recommended backup schools.

[2026] Step 9:

[2027] The server sends the generated list and analysis results to the device, formatting the data in a way that is easily accessible to the user.

[2028] Step 10:

[2029] The terminal displays the list of preferred schools and the list of backup schools sent from the server to the user, who can use this information to help formulate their own study plan.

[2030] Step 11:

[2031] The server identifies weak areas and issues that need to be overcome based on the results of the user's performance analysis, and selects specific study methods and recommended learning materials for the identified issues.

[2032] Step 12:

[2033] The server then sends the selected study methods and recommended learning materials to the device, allowing the user to study effectively.

[2034] Step 13:

[2035] The user inputs their daily learning progress into the terminal, and the input progress data is collected by the terminal.

[2036] Step 14:

[2037] The device sends the collected progress data to a server, which enables real-time learning progress management.

[2038] Step 15:

[2039] The server analyzes the progress data to ensure the learning plan is on track, adjusts it as needed, and generates a new plan.

[2040] Step 16:

[2041] The server sends the adjusted learning plan and feedback to the device, which the user can then confirm and continue learning.

[2042] Example 1

[2043] Next, a description will be given of Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the robot 414 will be referred to as a "terminal."

[2044] In modern education, there is a demand for accurate assessment of each learner's academic ability and the provision of individualized learning plans based on that assessment. In particular, when selecting a school to attend, it is important to consider a learner's strengths and weaknesses and present effective learning methods. However, the current system does not adequately manage the creation of learning plans or learning progress, limiting the extent to which students can improve their academic ability. This makes it difficult to select a school to attend and create an effective learning plan, leading to problems such as reduced learning efficiency and motivation.

[2045] The specific processing by the specific processing unit 290 of the data processing device 12 in the first embodiment is realized by the following means.

[2046] In this invention, the server includes means for collecting input assessment data of learners, means for analyzing the learners' academic ability based on the collected data, means for estimating the pass rate for the desired school based on the analysis results, means for generating a list of educational institutions according to the pass rate estimated, means for displaying the generated list, means for creating a study plan for the learner based on the display means, and means for following up on the study plan. This allows for the evaluation of the learner's academic ability, selection of a school to attend, creation of an effective study plan, and progress management and feedback to be carried out in an integrated manner, thereby enabling the learner to improve their learning efficiency and achieve their goals.

[2047] "Inputted learner assessment data" refers to data such as test scores and report card grades entered by the learner.

[2048] "Means for analyzing academic ability" is a function that identifies a learner's strong and weak subjects based on collected evaluation data and evaluates the learner's overall academic ability.

[2049] "Means for estimating pass rates" is a function that statistically estimates the probability that a learner will be accepted into their desired school based on the results of academic ability analysis.

[2050] An "educational institution list" is a list of schools that a learner wishes to apply to, including their preferred school and backup schools.

[2051] The "means for displaying" is a function for providing the generated list of educational institutions to the learner and visually displaying it.

[2052] "Means for creating a study plan" is a function that allows learners to create a specific study plan to achieve their goals based on the displayed list of educational institutions.

[2053] "Means for following up on study plans" refers to a function for managing the progress of the study plans that have been created and adjusting the plans as necessary.

[2054] "Study progress data" refers to data such as the learning progress status and study time for each subject that is entered by the learner daily.

[2055] "Learning methods and materials" refers to the specific learning methods for a particular task and the instructions for the materials to be used.

[2056] This system uses student evaluation data to generate a list of schools of choice and backup schools, and creates and follows up on study plans. The system consists of a server, terminals, and users (student).

[2057] System Configuration

[2058] Data collection

[2059] User (learner):

[2060] The user enters into the terminal his or her test scores and report card grades for each subject, including, for example, math, English, science, and Japanese.

[2061] Device:

[2062] The terminal collects performance data entered by the user and sends it to the server. The terminal is equipped with an application or web interface and functions as a user interface. HTTP requests and JSON format data can be used for communication.

[2063] Data analysis

[2064] server:

[2065] The server receives the data sent from the device and stores it in a database system (e.g., MySQL or PostgreSQL). Next, it cleans the data and corrects outliers and missing values. It then uses a generative AI model (e.g., using Python's Pandas or Scikit-learn library) to analyze the learner's performance data and evaluate their performance in each subject.

[2066] Pass rate estimation and list generation

[2067] server:

[2068] Based on the analysis results, the system estimates the student's chances of getting into their preferred school. This estimation uses data on past successful applicants and statistical data. Next, a list of educational institutions (first choice, third choice, and backup schools) is generated based on the chances of getting into the school and sent to the device.

[2069] Feedback and learning plan creation

[2070] Device:

[2071] The device displays the generated list of preferred schools and backup schools to the user, and supports the user in creating an individualized study plan based on the lists they have reviewed.

[2072] server:

[2073] Based on the results of the analysis of grades, the system identifies areas where the learner is weak and specific challenges. Specific learning methods and learning materials are recommended for the identified challenges and sent to the device.

[2074] Learning progress management and feedback

[2075] User (learner):

[2076] Users enter their daily study progress into the device, for example, recording which subjects they studied and how many hours they spent studying.

[2077] Device:

[2078] The device collects the progress data entered and sends it to the server, which analyzes the progress data to check whether the learning plan is progressing as planned, adjusts the learning plan as necessary, and notifies the user.

[2079] Specific examples

[2080] Example 1: Test score analysis and feedback

[2081] User (learner):

[2082] Enter 80 points for math, 70 points for English, 60 points for science, and 90 points for Japanese into the terminal.

[2083] Device:

[2084] The terminal collects the data and sends it to the server.

[2085] server:

[2086] The server analyzes the grade data, evaluates students' strengths and weaknesses, calculates their chances of getting into their preferred schools, and generates a list of schools they can apply to. It also recommends using workbooks that focus on specific science subjects and improving English vocabulary.

[2087] Device:

[2088] The device displays the analysis results and recommended learning methods to the learner.

[2089] Example 2: Managing learning progress

[2090] User (learner):

[2091] Enter your English study progress from the previous month into the device.

[2092] Device:

[2093] The device collects progress data and sends it to the server.

[2094] server:

[2095] The server analyzes the progress data and determines if the student's learning is not going as planned. It adjusts the student's English learning plan and proposes a new plan.

[2096] Device:

[2097] The device displays the adjusted learning plan to the learner and provides feedback.

[2098] Prompt Sentence Examples

[2099] "Write a program where the user inputs grades for each subject, the system determines which subjects the user is good at and which subjects they are bad at, and generates a list of schools they want to apply to. Specifically, the system will analyze grade data for 80 points in math, 70 points in English, 60 points in science, and 90 points in Japanese, and generate a list of schools they want to apply to."

[2100] The above is an embodiment of the invention. This system makes it possible to provide learners with individually optimized learning plans and support for further education.

[2101] The flow of the identification process in the first embodiment will be described with reference to FIG.

[2102] Step 1:

[2103] The user (student) enters performance data:

[2104] Users enter their test scores and report card grades for each subject using a device application or a web interface. The data entered includes the grades for each subject (e.g., math 80 points, English 70 points, science 60 points, Japanese 90 points).

[2105] Input: Grade data for each subject

[2106] Output: Achievement data saved on the device

[2107] Step 2:

[2108] Device collects and transmits performance data:

[2109] The terminal temporarily stores the performance data entered by the user and sends it to the server. The data is encoded in JSON format and sent via an HTTP request.

[2110] Input: Achievement data saved on the device

[2111] Output: Achievement data sent to the server

[2112] Step 3:

[2113] The server receives and stores the performance data:

[2114] The server receives the grade data sent from the device and stores it in a database (e.g., MySQL or PostgreSQL). The received data includes grade information for each subject.

[2115] Input: Performance data sent from the device

[2116] Output: Achievement data stored in a database

[2117] Step 4:

[2118] The server parses the data:

[2119] The server retrieves the stored grade data and performs data cleaning, checking for outliers and missing values ​​and correcting them as necessary. It then uses a generative AI model (using, for example, Python's Pandas or Scikit-learn libraries) to evaluate performance in each subject and identify strong and weak subjects.

[2120] Input: Achievement data stored in the database

[2121] Output: Analysis results including strong and weak subjects

[2122] Step 5:

[2123] The server estimates the pass rate and generates a list:

[2124] Based on the analysis results, the server evaluates the student's academic ability and statistically estimates the student's chances of being accepted into their preferred school. This estimation uses data on past successful applicants and statistical data. It then generates a list of preferred schools and a list of backup schools.

[2125] Input: Analysis results including strong and weak subjects

[2126] Output: List of preferred schools and backup schools

[2127] Step 6:

[2128] The server sends the list to the device:

[2129] The generated list of preferred schools and alternative schools is sent to the device. The data is encoded in JSON format and sent via an HTTP request.

[2130] Input: List of preferred schools and backup schools

[2131] Output: List of preferred schools and backup schools sent to the terminal

[2132] Step 7:

[2133] The terminal displays the list to the user:

[2134] The terminal displays the received list of preferred schools and backup schools to the user, using an application or web page as the user interface.

[2135] Input: List of preferred schools and backup schools sent to the device

[2136] Output: A list of preferred and alternative schools displayed to the user

[2137] Step 8:

[2138] User enters learning progress data:

[2139] Users input their daily study progress into the device, for example, recording the study time and progress for each subject (e.g., studied English for 2 hours).

[2140] Input: Daily learning progress data

[2141] Output: Learning progress data saved on the device

[2142] Step 9:

[2143] Your device collects and transmits learning progress data:

[2144] The device collects learning progress data entered by the user and sends it to the server, where it is encoded in JSON format and sent via an HTTP request.

[2145] Input: Learning progress data stored on the device

[2146] Output: Learning progress data sent to the server

[2147] Step 10:

[2148] The server analyzes the progress data and provides feedback:

[2149] The server analyzes the received progress data, checks whether the learning plan is progressing as planned, adjusts the learning plan if necessary, creates a new learning plan, and notifies the user.

[2150] Input: Learning progress data sent to the server

[2151] Output: Feedback and adjusted learning plan provided to the user

[2152] (Application example 1)

[2153] Next, a description will be given of Application Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the robot 414 will be referred to as a "terminal."

[2154] Conventional educational support systems are limited to analyzing students' academic performance data and estimating their chances of getting into their preferred schools, and do not adequately create specific study plans or manage progress. Furthermore, they do not provide specific learning materials or methods to help students overcome their weaknesses, limiting the effectiveness of improving their learning efficiency. Furthermore, these functions needed to be integrated into an educational support application provided in a virtual store. The present invention aims to provide a system that solves these problems.

[2155] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 1 is realized by the following means.

[2156] In this invention, the server includes means for collecting input test scores and performance data of learners, means for analyzing the learner's academic ability based on the collected data, means for estimating the pass rate for the desired school based on the analysis results, means for generating a list of desired schools and a list of backup schools according to the estimated pass rate, means for displaying the generated lists, means for creating a study plan for the learner based on the display means, means for recommending learning materials and study methods to help the learner overcome weaknesses based on the study plan and list of desired schools, and means for collecting and analyzing the learner's progress with the recommended learning materials and study methods. This enables learning support and support for further education that are individually optimized for each learner.

[2157] A "learner" is someone who belongs to an educational institution and takes tests and assessments.

[2158] A "test score" is the score or marks a learner receives when taking an exam or assessment.

[2159] "Academic performance data" refers to information indicating a learner's academic performance as assessed in the form of a report card, a report, or the like.

[2160] "Means for analyzing academic ability" refers to methods or systems for analyzing learners' test scores and grade data and evaluating their academic ability in each subject and overall.

[2161] A "means for estimating pass rates" is a method or algorithm for calculating the probability of a student being accepted into a school of their choice based on their current academic ability data.

[2162] A "school of choice list" is a list of schools that a student wishes to attend, ranked based on their acceptance rate.

[2163] A "safety school list" is a list of schools that have a high chance of acceptance in case you are not accepted into your preferred school.

[2164] "Display means" refers to the method or device for visually presenting the generated school preference list and other information to the learner.

[2165] A "means for creating a study plan" is a method or system for constructing daily study content and schedules to help learners achieve their goals.

[2166] "Means for recommending learning materials and learning methods" are systems or algorithms that suggest appropriate learning materials and effective learning methods to address learners' weaknesses and challenges.

[2167] "Means for collecting and analyzing progress" refers to methods and systems for recording learners' daily learning activities and evaluating whether they are progressing as planned.

[2168] A "virtual store" is a virtual shop or platform that provides educational services and teaching materials via the Internet.

[2169] This system uses a student's test scores and report card grade data to generate a list of schools of choice and backup schools, and indicates necessary study and challenges to overcome. This system is composed of a server, a terminal (such as a smartphone or PC), and a user (a student).

[2170] System Configuration

[2171] 1. Data Collection

[2172] User (learner):

[2173] Students enter their midterm and final exam scores, as well as their report card grades, into the terminal.

[2174] The data entered by the learner is saved on the device.

[2175] Device:

[2176] The terminal collects the input data and sends it to the server.

[2177] The terminal is equipped with an application and a web interface to provide a user interface.

[2178] 2. Data Analysis

[2179] server:

[2180] Receives data sent from the device and stores it in a database.

[2181] Check your data for outliers and missing values ​​and correct them if necessary.

[2182] Learners' test scores and grade data are analyzed to evaluate their performance in each subject.

[2183] Based on the analysis results, the learner's strengths and weaknesses are identified and their academic ability is evaluated.

[2184] 3. Pass rate estimation and list generation

[2185] server:

[2186] Based on the results of the student's academic assessment, the chances of them being accepted into their preferred school are estimated.

[2187] Refer to the data and statistics of past successful applicants for the school of your choice.

[2188] Generate a list of preferred schools (first to third choice) and a list of backup schools based on the acceptance rate.

[2189] Send your list of preferred schools and backup schools to your device.

[2190] 4. Feedback and learning plan creation

[2191] Device:

[2192] The generated list of preferred schools and backup schools is displayed to the learner.

[2193] Support the learner in creating an individualized learning plan based on the list they have reviewed.

[2194] server:

[2195] Based on an analysis of grades for each subject, weak areas and specific challenges are identified.

[2196] Recommend specific study methods and materials for identified issues.

[2197] Recommended study materials and methods are sent to your device.

[2198] 5. Learning progress management and feedback

[2199] User (learner):

[2200] Daily study progress is entered into the device, including how much of each subject has been studied and the progress made.

[2201] Device:

[2202] The entered progress data is collected and sent to the server.

[2203] server:

[2204] Analyze your progress data to ensure your learning plan is on track.

[2205] Adjust the learning plan as needed and notify the learner.

[2206] Provide ongoing feedback to support effective learning.

[2207] Specific examples

[2208] User (learner):

[2209] Enter 80 points for math, 70 points for English, 60 points for science, and 90 points for Japanese into the terminal.

[2210] The terminal collects the data and sends it to the server.

[2211] server:

[2212] The grade data is analyzed and it is determined that mathematics and Japanese are strong subjects, while science and English are weak subjects.

[2213] Calculate the acceptance rate for your desired school and make a list of your first, second, and third choice schools.

[2214] Recommended study methods include using problem sets that focus on specific areas of science and strengthening English vocabulary.

[2215] Device:

[2216] The analysis results are displayed to the learner and recommended learning methods are provided.

[2217] The above series of processes realizes learning support that is optimized for each learner. As a concrete example, let us consider the following prompt sentence as input to the generative AI model.

[2218] Example prompt sentence:

[2219] "A student's test scores are: Math 80, English 70, Science 60, Japanese 90. In this case, please list the student's first, second, and third choice schools. Also, please suggest the best study methods for English and Science, which are the weaker subjects."

[2220] In this way, by utilizing generative AI models, it is possible to provide more accurate learning assistance.

[2221] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[2222] Step 1:

[2223] Users input test scores and grade data. Specifically, learners input their midterm and final exam scores and report card scores into a smartphone or PC device. The input data includes the scores for each subject. After input, the data is temporarily stored on the device.

[2224] Step 2:

[2225] The device sends the collected data to a server. The device is equipped with an application or web interface that formats the data entered by the user and sends it to the server. The data is encrypted before being sent.

[2226] Step 3:

[2227] The server receives the data and stores it in the database. The server checks the integrity of the data and corrects any outliers or missing values. For example, if a math score is over 100, it is treated as an outlier. After checking that the data is in the correct format, it is stored in the database.

[2228] Step 4:

[2229] The server analyzes the learner's test scores and performance data. It uses analytical algorithms to evaluate performance in each subject. Specifically, it calculates the mean and standard deviation of scores and identifies strengths and weaknesses in each subject. Algorithms used here include XGBoost and linear regression models.

[2230] Step 5:

[2231] The server estimates the pass rate for the student's desired school based on the analysis results. It compares the student's scores with past successful applicant data and statistical data to calculate the pass rate for the desired school. For example, using the XGBoost model, the pass rate can be estimated by inputting data for 80 points in math, 70 points in English, 60 points in science, and 90 points in Japanese.

[2232] Step 6:

[2233] The server generates a list of preferred schools and a list of backup schools according to the pass rate. Based on the calculated pass rate, lists of first-choice, second-choice, third-choice, etc. are created. A list of backup schools with relatively high pass rates is also generated at the same time.

[2234] Step 7:

[2235] The server sends the generated list to the terminal. After generating the list, the server sends it to the terminal. At this time, the data is encrypted again and sent. The data is formatted in the appropriate format so that it can be displayed correctly on the terminal.

[2236] Step 8:

[2237] The device displays the student's list of preferred schools and backup schools. The list is displayed for easy access by the student through the device's application or web interface. Specifically, the list is displayed in list format along with the acceptance rate for each preferred school.

[2238] Step 9:

[2239] The server analyzes the learner's weak areas and the challenges they need to overcome. Based on the results of the analysis, it identifies subjects and areas where students have particularly low scores and evaluates what learning methods are most effective.

[2240] Step 10:

[2241] The server then recommends learning materials and methods that address the identified issues. For example, it might recommend a workbook focused on a specific area of ​​science or an app to improve English vocabulary. This recommendation information is selected using an analytical algorithm.

[2242] Step 11:

[2243] The device will display recommended learning materials and methods to the learner, who can then review the recommended materials and methods and incorporate them into their own learning plans.

[2244] Step 12:

[2245] The user inputs their daily learning progress into the device. The learner inputs their daily learning content and progress and saves it on the device. The input data includes the subjects studied, the time spent, and the progress status.

[2246] Step 13:

[2247] The terminal sends the entered progress data to the server. The terminal formats the progress data entered by the learner and sends it to the server.

[2248] Step 14:

[2249] The server analyzes the progress data to check whether the learning plan is progressing as planned. Based on the progress data, the server evaluates whether the learner's plan is progressing properly and makes adjustments as necessary.

[2250] Step 15:

[2251] The server sends the results of the adjustments to the learning plan to the device. If the plan is not progressing as planned, a new learning plan will be proposed and sent to the device.

[2252] Step 16:

[2253] The device will then display the adjusted study plan to the learner. By presenting the new plan, the learner can study more efficiently.

[2254] The above processing steps enable learners to receive individually optimized learning support and maximize their learning outcomes. Specifically, by inputting the following prompt sentences into the generative AI model, highly accurate analysis and feedback can be obtained.

[2255] Example prompt sentence:

[2256] "A student's test scores are: Math 80, English 70, Science 60, Japanese 90. In this case, please list the student's first, second, and third choice schools. Also, please suggest the best study methods for English and Science, which are the weaker subjects."

[2257] Furthermore, an emotion engine that estimates the user's emotion may be further combined. That is, the identification processing unit 290 may estimate the user's emotion using the emotion identification model 59, and perform identification processing using the user's emotion.

[2258] This invention combines a system that uses a learner's test scores and report card grade data to generate a list of preferred and backup schools, and indicates necessary study and challenges to overcome, with an emotion engine that recognizes the user's emotions. The system is composed of a server, terminals, and users (students).

[2259] System Configuration

[2260] 1. Data Collection

[2261] User (student):

[2262] Students input their scores for each subject in midterm and final exams, as well as their report card grades, into the terminal using a terminal application or a web interface.

[2263] Device:

[2264] The terminal collects the entered data, formats it appropriately, and sends it to the server.

[2265] 2. Data Analysis

[2266] server:

[2267] The server receives the data sent from the terminal and stores it in a database.

[2268] Preprocessing such as outlier detection and missing value completion is performed on the received data.

[2269] Analyze the pre-processed data to evaluate the learner's academic ability, identifying scores, deviation values, strengths and weaknesses for each subject.

[2270] 3. Pass rate estimation and list generation

[2271] server:

[2272] Based on the results of the academic assessment, the system estimates the chances of passing the desired school. It also calculates the user's chances of passing by referencing past passing data and the school's passing criteria.

[2273] Based on the estimated pass rate, a list of preferred schools (first to third choice) and a list of backup schools are generated.

[2274] Send your list of preferred schools and backup schools to your device.

[2275] 4. Feedback and learning plan creation

[2276] Device:

[2277] The data received from the server is displayed to the user, who can then check the list of schools of choice and the results of the grade analysis.

[2278] Based on the results of the analysis of a learner's grades, we identify areas of weakness and challenges that need to be overcome, and then present specific study methods and recommended materials to address these challenges.

[2279] server:

[2280] Specific study methods and recommended study materials to overcome weak areas are selected and sent to the device.

[2281] 5. Emotional awareness and learning plan adjustment

[2282] Emotion Engine:

[2283] It recognizes emotions from the user's facial expressions, tone of voice, input content, etc., and identifies the user's current emotional state.

[2284] server:

[2285] The learning plan is adjusted based on the recognized emotional data, for example, adjusting the amount or difficulty of learning if the user is feeling stressed.

[2286] Depending on the recognized emotion, encouraging messages and appropriate feedback are generated and sent to the device.

[2287] 6. Learning progress management and feedback

[2288] User (student):

[2289] Daily study progress is entered into the device, including how much of each subject has been studied and the progress made.

[2290] Device:

[2291] The entered progress data is collected and sent to the server.

[2292] server:

[2293] Analyze progress data to ensure your learning plan is on track, adjust it if necessary, and generate a new plan.

[2294] The adjusted learning plan and feedback are sent to the device, where the user can confirm and continue learning.

[2295] Specific examples

[2296] Example 1: Test score analysis and feedback

[2297] User (student):

[2298] The student enters their scores into the terminal: 80 points for math, 70 points for English, 60 points for science, and 90 points for Japanese. The terminal collects the data and sends it to the server.

[2299] server:

[2300] The grade data is analyzed and it is determined that mathematics and Japanese are strong subjects, while science and English are weak subjects.

[2301] Calculate the acceptance rate for your desired school and make a list of your first, second, and third choice schools.

[2302] Recommended study methods include using problem sets that focus on specific areas of science and strengthening English vocabulary.

[2303] Device:

[2304] The analysis results are displayed to the learner and recommended learning methods are provided.

[2305] Emotion Engine:

[2306] The system recognizes whether the user is feeling anxious or stressed from their facial expressions and tone of voice while they are typing.

[2307] server:

[2308] Based on the recognized emotion data, the system generates encouraging messages and suggests adjustments to the amount of study. For example, it provides messages such as, "You seem to be good at math! Keep it up!"

[2309] Example 2: Managing learning progress

[2310] User (student):

[2311] The user enters their English study progress from the previous month into the device, which then collects the progress data and sends it to the server.

[2312] server:

[2313] Analyze progress data to determine if learning is not progressing as planned.

[2314] Adjust your English study plan and propose new ones.

[2315] Emotion Engine:

[2316] The emotion engine recognizes that the user is feeling stressed from their facial expressions and voice when entering their progress.

[2317] server:

[2318] Based on the recognized emotions, the system suggests educational materials that can be understood quickly and efficiently to reduce stress.

[2319] Device:

[2320] Provide users with tailored learning plans and feedback to support their learning.

[2321] summary

[2322] The system of the present invention allows learners to receive efficient and personalized learning support based on their own performance data and progress. Furthermore, by combining it with an emotion engine, appropriate feedback and adjustments to the learning plan are made according to the user's emotional state, enabling effective learning while reducing stress.

[2323] The processing flow will be explained below.

[2324] Step 1:

[2325] Students use the device to input their scores for each subject in midterm and final exams, as well as their report card grades. Specifically, they input their grades for each semester and their grades for each subject via the device's application or web interface.

[2326] Step 2:

[2327] The device collects test score and report card data entered by the user, which is then prepared and properly formatted for transmission to the server.

[2328] Step 3:

[2329] The terminal transmits the collected data to the server. This transmission is performed securely over a network.

[2330] Step 4:

[2331] The server receives the data sent from the device, stores it in a database, and uses it for subsequent analysis.

[2332] Step 5:

[2333] The server pre-processes the received data, which includes outlier detection and missing value imputation. Anomaly detection algorithms are applied to ensure data integrity and quality.

[2334] Step 6:

[2335] The server analyzes the preprocessed data and evaluates the user's academic ability. Specifically, it calculates a deviation score based on the scores for each subject and identifies strengths and weaknesses.

[2336] Step 7:

[2337] The server estimates the probability of passing the desired school based on the analysis results, comparing them with past successful applicant data and the school's passing criteria to calculate the user's chances of passing.

[2338] Step 8:

[2339] The server generates a list of preferred schools and a list of backup schools based on the estimated pass rate. The list includes first- to third-choice schools and recommended backup schools.

[2340] Step 9:

[2341] The server sends the generated list and analysis results to the device, formatting the data in a way that is easily accessible to the user.

[2342] Step 10:

[2343] The terminal displays the list of preferred schools and the list of backup schools sent from the server to the user, who can use this information to help formulate their own study plan.

[2344] Step 11:

[2345] The server identifies weak areas and issues that need to be overcome based on the results of the user's performance analysis, and selects specific study methods and recommended learning materials for the identified issues.

[2346] Step 12:

[2347] The server then sends the selected study methods and recommended learning materials to the device, allowing the user to study effectively.

[2348] Step 13:

[2349] The emotion engine recognizes emotions from the user's facial expressions, tone of voice, and input content to identify the user's current emotional state.

[2350] Step 14:

[2351] The server receives the emotion data recognized by the emotion engine and adjusts the study plan, for example, reducing the amount of study or lowering the difficulty level if the user is feeling stressed.

[2352] Step 15:

[2353] The server generates encouraging messages and appropriate feedback based on the recognized emotion data and sends them to the device, such as "You seem to be good at math! Keep it up!"

[2354] Step 16:

[2355] Users enter their daily study progress into the terminal, including how much they studied and what subjects they studied, as well as their progress.

[2356] Step 17:

[2357] The terminal collects the entered progress data and transmits it to the server.

[2358] Step 18:

[2359] The server analyzes the progress data to ensure the learning plan is on track, adjusts it as needed, and generates a new plan.

[2360] Step 19:

[2361] The server sends the adjusted learning plan and feedback to the device, which the user can then confirm and continue learning.

[2362] The above is a specific flow of processing in the system of the present invention. By providing individually optimized learning support while taking into consideration the user's emotions, learning efficiency is improved and stress is reduced.

[2363] Example 2

[2364] Next, a description will be given of Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the robot 414 will be referred to as a "terminal."

[2365] In conventional educational systems, learning plans are often created based on a learner's academic performance data, but they lack the ability to adjust to the learner's individual emotional state. This can lead to learners feeling stressed or anxious, which can hinder their ability to perform at their best and result in less than optimal learning outcomes. There is a need for a system that provides a comprehensive approach that takes into account not only academic performance data but also daily learning progress and emotional state.

[2366] The identification process by the identification processing unit 290 of the data processing device 12 in the second embodiment is realized by the following means. In this invention, the server includes means for collecting input academic performance data of the learner, means for analyzing the learner's academic ability based on the collected data, means for estimating the pass rate for the desired school based on the analysis results, means for generating a list of desired schools and a list of backup schools according to the estimated pass rate, means for displaying the generated lists, means for creating a study plan for the learner based on the display means, means for recognizing the learner's emotional state, and means for adjusting the study plan based on the recognized emotional state. This enables comprehensive learning support that takes into account the learner's emotional state.

[2367] "Academic performance data" refers to data including the scores obtained by a learner in each subject and the grades on their report cards.

[2368] "Academic ability" refers to the results of assessing a learner's scores in each subject and their overall learning ability.

[2369] "Analysis results" refers to the output of a learner's academic ability assessment based on the collected data.

[2370] "Preferred school" refers to the educational institution that a learner wishes to attend.

[2371] The "pass rate" is a value indicating the probability that a learner will pass the entrance examination to the school of their choice.

[2372] A "preferred school list" is a list of educational institutions that a learner wishes to attend, ranked in order.

[2373] A "safety school list" is a list of educational institutions that a student may consider attending if they are not accepted into their preferred school.

[2374] "Display means" refers to a device or method for displaying the generated list, analysis results, etc. to the learner.

[2375] A "study plan" refers to the specific learning content and schedule set out to help learners progress effectively in their studies.

[2376] "Emotional state" refers to the learner's current emotional state, including, for example, stress, anxiety, and motivation.

[2377] The present invention is a system that combines a learner's performance data and emotional state to provide an optimal study plan. This system is composed of a server, a terminal, and a user (learner).

[2378] server:

[2379] The server receives the grade data sent from the device and stores it in a database. It then analyzes the grade data to evaluate the learner's academic ability. Specifically, it performs preprocessing such as outlier detection and missing value imputation. Based on the preprocessed data, it calculates the deviation score for each subject, as well as the student's strong and weak subjects. Based on the analysis results, it estimates the student's chances of getting into their preferred school. Using this chance as a reference, it generates a list of first- to third-choice schools and a list of safety schools. The server also has the ability to recognize the learner's emotional state and reflect this data in the study plan. For example, if the learner is feeling stressed, it can reduce the amount of study or adjust the difficulty level.

[2380] Device:

[2381] The terminal provides an interface for users to input grade data and progress data. For example, learners use a terminal application or web interface to input their grades for each subject and their report card grades. The terminal then converts the received data into an appropriate format and sends it to the server. The terminal then displays the analysis results, preferred school list, study plan, and emotional feedback sent from the server to the user. A dashboard using a graphical user interface (GUI) is provided to make it easy for learners to check the data.

[2382] User (learner):

[2383] Users input their scores for each subject in midterm and final exams, as well as report card grades, through the device. They also input their daily learning progress into the device and send it to the server as appropriate. Learning progresses based on the learning plan and feedback received from the device. The device's camera and microphone are also used to recognize the user's emotional state, providing an appropriate learning method that matches their emotional state.

[2384] Examples:

[2385] For example, if a user inputs "80 points in math, 70 points in English, 60 points in science, and 90 points in Japanese" into the device, the device converts the data into JSON format and sends it to the server. The server analyzes the grade data and determines that math and Japanese are strong subjects, while science and English are weak subjects. The server calculates the pass rate and displays it as 70% for the first choice school, 50% for the second choice school, and 90% for the third choice school. Recommended study methods include using workbooks that focus on specific areas of science and strengthening English vocabulary. As the user inputs progress data into the device, the server analyzes the progress and adjusts the study plan.

[2386] Furthermore, the emotion engine recognizes that if the user frowns while typing, they are feeling anxious, and adjusts the amount of learning they are doing, sending encouraging messages such as, "You seem to be good at math! Keep it up!"

[2387] This system not only provides learners with optimal study plans based on their performance data, but also provides flexible feedback and study adjustments that are tailored to their emotional state at the time, enabling efficient and stress-free learning.

[2388] The flow of the identification process in the second embodiment will be described with reference to FIG.

[2389] Step 1:

[2390] User: The learner uses a terminal application or a web interface to input the scores for each subject in the midterm and final exams, as well as the grade data from the report card. For example, the learner enters "80 points for math, 70 points for English, 60 points for science, and 90 points for Japanese."

[2391] Input: Score and grade data for each subject entered by the user

[2392] Output: Performance data sent to the device

[2393] Step 2:

[2394] Terminal: The terminal collects the grade data entered by the user and converts it into an appropriate format. Specifically, it converts the input data into JSON format. For example, it formats it as follows: {"Subject": {"Math": 80, "English": 70, "Science": 60, "Japanese": 90}}.

[2395] Input: User-entered grade data

[2396] Output: Formatted data (JSON format)

[2397] Step 3:

[2398] Terminal: Sends the collected and formatted performance data to the server, for example, using HTTP requests.

[2399] Input: Formatted data (JSON format)

[2400] Output: Grade data sent to the server

[2401] Step 4:

[2402] Server: The server receives the performance data sent from the device and stores it in a database. When storing the data, it associates it with each user's ID.

[2403] Input: Performance data sent from the device

[2404] Output: Achievement data stored in the database

[2405] Step 5:

[2406] Server: Preprocesses the saved grade data. Performs outlier detection and missing value imputation to ensure data accuracy. An outlier, for example, would be a negative score for each subject, and corrects it to within the normal range.

[2407] Input: Achievement data stored in the database

[2408] Output: Preprocessed grade data

[2409] Step 6:

[2410] Server: Analyzes the pre-processed data and evaluates the user's academic ability. Specifically, it calculates the deviation score and strong and weak subjects based on the scores for each subject.

[2411] Input: Preprocessed grade data

[2412] Output: Academic ability analysis results (deviation score for each subject, strong and weak subjects)

[2413] Step 7:

[2414] Server: Based on the results of the academic ability analysis, estimate the probability of admission to the user's desired school. In this case, past admission data and school standards are used as reference.

[2415] Input: Academic ability analysis results

[2416] Output: Pass rate estimation result

[2417] Step 8:

[2418] Server: Based on the estimated pass rate, it generates a list of preferred schools and a list of backup schools and sends this to the terminal.

[2419] Input: Pass rate estimation result

[2420] Output: List of preferred schools, list of backup schools

[2421] Step 9:

[2422] Terminal: Displays the list of schools of choice sent from the server and the results of the academic ability analysis to the user. The user can check the analysis results and the list.

[2423] Input: Preferred school list sent from the server, academic ability analysis results

[2424] Output: Displayed list of preferred schools, academic ability analysis results

[2425] Step 10:

[2426] Server: Selects specific study methods and recommended learning materials to help learners overcome their weak areas and sends them to the device.

[2427] Input: Academic ability analysis results (weak subjects)

[2428] Output: Study methods and recommended materials

[2429] Step 11:

[2430] Device: Displays study methods and recommended learning materials to the user. The user creates a study plan based on the information provided.

[2431] Input: Study methods and recommended materials sent from ...

Claims

1. a means for collecting input learner test score and report card performance data; A means for analyzing the academic ability of learners based on the collected data; A means for estimating the probability of admission to the desired school based on the analysis results; A means for generating a list of preferred schools and a list of backup schools according to the estimated pass rate; means for displaying the generated list; and means for creating a study plan for the learner based on said display means.

2. 2. The system of claim 1, further comprising: means for inputting a learner's daily learning progress and collecting said learning progress data; and means for adjusting a learning plan based on said collected progress data.

3. The system according to claim 1, further comprising means for identifying the learner's weak areas and challenges to overcome based on the estimated pass rate, and providing specific study methods and learning materials corresponding to the identified challenges.

Images