System

Abstract

A system is provided.SOLUTION: A system comprising: means for collecting athletic performance and interest data from a student; means for pre-processing and validating the collected data; means for analyzing the student's aptitude based on the pre-processed data and selecting a job candidate; means for generating a recommendation report based on the analysis; means for presenting the generated report to the student, teacher, and parent and collecting feedback; and means for re-evaluating and improving the analysis algorithm based on the collected feedback.SELECTED DRAWING: Figure 1

Description

[Technical Field]

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

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

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

[0004] In the current compulsory education system, students often have difficulty envisioning their future dreams or careers. Opportunities to discover their aptitudes and interests are limited, especially from the upper grades of elementary school through junior high school, making it difficult for them to think concretely about their future career paths. Schools also have difficulty providing individual advice, resulting in a lack of career guidance tailored to each student. Furthermore, there is a lack of a system in place to effectively utilize feedback and continuously optimize the system. [Means for solving the problem]

[0005] The present invention solves the above problems by combining multiple means. First, it provides a means for collecting data on athletic performance and interests from students. Second, it provides a means for preprocessing and verifying the collected data. Third, it provides a means for analyzing students' aptitudes and selecting career candidates based on the preprocessed data. Fourth, it provides a means for generating a recommendation report based on the analysis results. Fifth, it provides a means for presenting the generated report to students, teachers, and parents and collecting feedback. Sixth, it provides a means for reevaluating and improving the analysis algorithm based on the collected feedback. This makes it easier for students to understand their own characteristics, and with specific support from teachers and parents, it becomes possible for them to concretely envision their future dreams.

[0006] "Athletic performance" refers to data used to evaluate a student's physical ability, and includes, for example, 100-meter sprint times and basketball game results.

[0007] "Interest data" is information that indicates a student's interest in academic subjects and activities, and refers to data such as favorite subjects and club activities collected in the form of a questionnaire.

[0008] "Preprocessing" refers to processes such as data validation, standardization, and encoding that are carried out before the collected data is analyzed.

[0009] "Verification" is the process of checking whether there are any errors in the collected data, for example, checking whether physical exercise performance is an abnormal value or whether all questionnaire responses have been recorded.

[0010] "Analysis" refers to the process of numerically and statistically evaluating students' characteristics and aptitudes based on collected and preprocessed data.

[0011] "Career candidates" refers to a list of occupations that are likely to match a student's aptitudes and interests based on the analysis.

[0012] A "recommendation report" refers to a report that, based on the analysis results, includes suitable career options for a particular student and a specific action plan for pursuing those careers.

[0013] "Presenting" refers to the act of visually displaying the generated recommendation report to students, teachers, and parents.

[0014] "Feedback" refers to the reactions, comments and opinions collected from students, teachers and parents who view the reports.

[0015] "Reevaluation" refers to the process of reviewing the analysis algorithm and the performance of the entire system based on the collected feedback and making appropriate improvements.

[0016] "Analysis algorithms" refer to mathematical methods for evaluating and analyzing aptitudes and characteristics based on student data, and include clustering and supervised learning. [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 is a system that helps students from the upper grades of elementary school to junior high school (hereinafter referred to as "students") to concretely visualize their future dreams and careers. The system aims to collect and analyze data on students' athletic performance and interests, and present appropriate career options.

[0039] Overall structure

[0040] The system consists of the following main components:

[0041] 1. Data collection terminal

[0042] 2. Data Validation and Preprocessing Server

[0043] 3. Data analysis server

[0044] 4. Report Generation Server

[0045] 5. Feedback collection terminal

[0046] 6. Algorithm Reevaluation Server

[0047] Program processing

[0048] Data collection

[0049] The device provides an interface for students to input information about their athletic achievements and interests. For example, an application can be provided to collect information such as their 100-meter sprint time in physical education class, or a questionnaire about their favorite subjects and extracurricular activities. The collected data is then sent to a server via the Internet.

[0050] Data Validation and Preprocessing

[0051] The server validates the received data and checks for input errors (for example, checking that the 100-meter sprint time is not physically impossible or that the questionnaire is completely filled out). The server then preprocesses the validated data (for example, standardizing numeric data and encoding categorical data into numbers).

[0052] Data analysis

[0053] The server analyzes each student's aptitude based on the preprocessed data, using clustering and supervised learning algorithms to classify them into clusters based on their interests and abilities, and then lists suitable career candidates based on the results.

[0054] Report Generation

[0055] The server generates a recommendation report for each student based on the data analysis results. This report includes a list of suitable careers for the student, along with the skills and related learning and activities required. For example, a student with strong athletic ability and good grades in mathematics may be recommended a career such as "sports data analyst," along with specific study methods and workshop participation recommendations.

[0056] Feedback collection

[0057] The terminal provides an interface for presenting the generated recommendation report to students, teachers, and parents. Users (students, teachers, and parents) can view the report through the terminal and enter their opinions and questions. For example, if a student is interested in "sports data analyst" and would like more detailed information about the job, they can send a question through the terminal.

[0058] Algorithm Reevaluation

[0059] The server collects feedback from the devices and reevaluates the performance of the analysis algorithm and the overall system. Based on this feedback, it creates and implements an improvement plan to optimize the content of the career candidate list and recommendation report. For example, if many students express interest in a particular career, it will provide more detailed information related to that career or add new related recommendations.

[0060] Specific examples

[0061] Example 1: Data collection

[0062] Using a dedicated app on a device, students enter their physical education records (for example, 100-meter sprint time) and interest questionnaires (favorite subjects, club activities, etc.) once a week.

[0063] The user (student) enters this information and the data is automatically sent to the server.

[0064] Example 2: Data validation and preprocessing

[0065] The server validates the received data to ensure there are no errors, for example, checking for anomalies in the 100-meter sprint time.

[0066] The server normalizes the data, for example encoding interest survey responses into numbers.

[0067] Example 3: Data analysis

[0068] The server generates an analysis result in which Student A is classified as "Athletic Ability Cluster: High" and "Mathematics Interest Cluster: Medium."

[0069] Example 4: Report Generation

[0070] The server recommends occupations such as "sports data analyst" or "sports instructor" to Student A. The report lists the necessary skills and learning recommendations.

[0071] Example 5: Feedback collection

[0072] The terminal presents the generated report to Student A, who then views the report and becomes interested in the "Sports Data Analyst."

[0073] Student A inputs a follow-up question through the terminal, for example, "How do I study the programming language required for this job?"

[0074] Example 6: Algorithm reevaluation

[0075] The server collects feedback from Student A and optimizes the analysis algorithm. This process continuously improves the entire system.

[0076] This system will enable students to gain a deeper understanding of their own aptitudes and to envision their future careers and dreams. It will also enable teachers and parents to provide specific support tailored to students' aptitudes.

[0077] The processing flow will be explained below.

[0078] Step 1:

[0079] The devices provide an interface for students to enter data about their athletic performance and interests, such as their weekly 100-meter sprint time or their favorite subjects and club activities, through a dedicated application.

[0080] Step 2:

[0081] The device sends the entered data to a server via the Internet, where it is temporarily stored and awaits processing for analysis.

[0082] Step 3:

[0083] The server validates the received data, detecting, for example, physically impossible 100-meter sprint times or incomplete survey responses, and verifies the accuracy of the data. Incorrect or incomplete data requires correction or re-entry.

[0084] Step 4:

[0085] The server preprocesses the validated data, specifically by standardizing numeric data and encoding categorical data. For example, it converts survey responses (favorite subject) into numerical values.

[0086] Step 5:

[0087] The server analyzes students' aptitudes based on the preprocessed data. It uses clustering algorithms and supervised learning algorithms to classify students' interests and abilities. For example, it divides students into clusters based on athletic ability and academic aptitude, and then selects career candidates based on each.

[0088] Step 6:

[0089] The server then generates a report for each student based on the analysis results. This report includes recommendations for multiple careers suitable for the student, along with the skills and related subjects required for those careers. For example, a student with strong athletic ability and good grades in math might be recommended a career such as "sports data analyst."

[0090] Step 7:

[0091] The terminal provides an interface for presenting the generated report to students, teachers, and parents. Users (students, teachers, and parents) can view and check the contents of the presented report. For example, this can be used to find out more information about a career that a student is interested in.

[0092] Step 8:

[0093] Users (students, teachers, and parents) can provide feedback on the report content through the terminal. For example, a student may be interested in the "Sports Data Analyst" section and enter additional questions or opinions about the topic.

[0094] Step 9:

[0095] The device sends the collected feedback to the server, where it is stored in a database for use in the re-evaluation process.

[0096] Step 10:

[0097] The server reevaluates and optimizes the analysis algorithm based on the feedback. For example, if a student's interests or trends change, or if many students show interest in a particular career, it will update the information and recommendations about that career. This reevaluation process improves the accuracy and effectiveness of the entire system.

[0098] Through these processing steps, the system supports students in choosing their future careers and enables educators to provide appropriate advice.

[0099] Example 1

[0100] 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."

[0101] In today's educational environment, students face the challenge of being unable to envision a specific future career based on their own interests and abilities. Therefore, there is a need for an effective support system to help students make appropriate career choices. However, traditional methods are problematic in that they are unable to flexibly accommodate students' diverse interests and abilities, and do not provide sufficient individualized advice.

[0102] 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.

[0103] In this invention, the server includes a means for collecting data on athletic performance and interests from students, a means for verifying and preprocessing the collected data, and a means for analyzing the aptitude of students based on the preprocessed data using a clustering algorithm or a supervised learning algorithm and selecting career candidates. This makes it possible to provide flexible and accurate career candidates based on each student's aptitude and interests, and to support career selection.

[0104] "Athletic performance" refers to data related to a student's physical ability, including, for example, 100-meter sprint times and physical fitness test results.

[0105] "Interests" refers to data about the areas and activities that students are interested in, such as their favorite subjects, club activities, and dreams for the future.

[0106] "Data Collection Means" refers to the interface for inputting and recording data from students regarding their athletic performance and interests and transmitting that data to the server.

[0107] "Data validation and pre-processing means" refers to a system for checking received data for errors and pre-processing the data, such as standardizing or encoding the data, if necessary.

[0108] "Clustering algorithm" refers to an algorithm for classifying students into groups with similar characteristics based on their athletic performance and interests.

[0109] "Supervised learning algorithms" refer to machine learning algorithms that use pre-labeled data to predict students' aptitudes and career prospects.

[0110] "Analysis means" refers to a system for assessing students' aptitude and selecting career candidates based on pre-processed data.

[0111] A "recommendation report" refers to a report generated based on the analysis results that lists suitable career options, required skills, and learning recommendations for each student.

[0112] "Feedback collection means" refers to an interface for collecting opinions and questions from users (students, educators, parents) regarding the generated reports.

[0113] "Algorithm re-evaluation and improvement measures" refers to a system for evaluating the performance of analysis algorithms and the overall system based on collected feedback and improving them as needed.

[0114] The present invention is a system for supporting students in choosing their future careers in an educational system. Specifically, the system collects and analyzes data on students' athletic performance and interests, and presents suitable career candidates. The system is composed of a data collection terminal, a data verification and preprocessing server, a data analysis server, a report generation server, a feedback collection terminal, and an algorithm reevaluation server.

[0115] Data collection

[0116] The devices provide an interface for students to input data about their athletic achievements and interests. For example, a dedicated application is provided, allowing students to input information about their 100-meter sprint time in gym class, their favorite subjects, and club activities. This data is then sent to a server via the Internet.

[0117] Data Validation and Preprocessing

[0118] The server validates the received data and checks for input errors (for example, checking that the 100-meter sprint time is not physically impossible or that the questionnaire is completely filled out). The server then preprocesses the validated data (for example, standardizing numeric data and encoding categorical data into numbers).

[0119] Data analysis

[0120] The server analyzes each student's aptitude based on the preprocessed data, using clustering and supervised learning algorithms to classify them into clusters based on their interests and abilities, and then lists suitable career candidates based on the results.

[0121] Report Generation

[0122] The server generates a recommendation report for each student based on the data analysis results. This report includes a list of suitable careers for the student, along with the skills and related learning and activities required. For example, a student with strong athletic ability and good math grades could be recommended a career such as "sports data analyst," along with specific study methods and workshop participation recommendations.

[0123] Feedback collection

[0124] The terminal provides an interface for presenting the generated recommendation report to students, educators, and parents. Users (students, educators, and parents) can view the report through the terminal and enter their opinions and questions. For example, if a student is interested in "sports data analyst" and wants more detailed information about the job, they can submit a question through the terminal.

[0125] Algorithm Reevaluation

[0126] The server collects feedback from the devices and reevaluates the performance of the analysis algorithm and the overall system. Based on this feedback, it creates and implements an improvement plan to optimize the content of the career candidate list and recommendation report. For example, if many students express interest in a particular career, it will provide more detailed information related to that career or add new related recommendations.

[0127] Specific examples

[0128] Example 1: Data collection

[0129] Using a dedicated app on a device, students enter their physical education records (for example, 100-meter sprint time) and interest questionnaires (favorite subjects, club activities, etc.) once a week.

[0130] The user (student) enters this information and the data is automatically sent to the server.

[0131] Example 2: Data validation and preprocessing

[0132] The server validates the received data to ensure there are no errors, for example, checking for anomalies in the 100-meter sprint time.

[0133] The server normalizes the data, for example encoding interest survey responses into numbers.

[0134] Example 3: Data analysis

[0135] The server generates an analysis result in which Student A is classified as "Athletic Ability Cluster: High" and "Mathematics Interest Cluster: Medium."

[0136] Example 4: Report Generation

[0137] The server recommends occupations such as "sports data analyst" or "sports instructor" to Student A. The report lists the necessary skills and learning recommendations.

[0138] Example 5: Feedback collection

[0139] The terminal presents the generated report to Student A, who then views the report and becomes interested in the "Sports Data Analyst."

[0140] Student A inputs a follow-up question through the terminal, for example, "How do I study the programming language required for this job?"

[0141] Example 6: Algorithm reevaluation

[0142] The server collects feedback from Student A and optimizes the analysis algorithm, and this process continuously improves the entire system.

[0143] Prompt Sentence Examples

[0144] By inputting the following prompt sentences into the generative AI model, an assistant function is provided to help the model specifically draw appropriate career candidates.

[0145] Example prompt:

[0146] "This student has good motor skills and an interest in mathematics. Please list suitable careers for him / her and recommend the necessary skills and related learning activities."

[0147] summary

[0148] This system will enable students to gain a deeper understanding of their own aptitudes and to concretely visualize their future careers and dreams, while also enabling educators and parents to provide specific support tailored to students' aptitudes.

[0149] The flow of the identification process in the first embodiment will be described with reference to FIG.

[0150] Step 1: Provide a data entry interface

[0151] The terminal provides an interface for students to input data about their athletic achievements and interests. Specifically, a form is displayed in which students can input information about their 100-meter sprint time, favorite subjects, and club activities via a dedicated application. The input data is information about the student's athletic achievements and interests. This data is received and sent to the server.

[0152] Step 2: Receiving and verifying data

[0153] The server receives the data sent from the device. It verifies the accuracy of the entered data, for example, checking that the 100-meter sprint time is not physically impossible or that a questionnaire is completely filled out. Incorrect or incomplete data generates an error message and sends it back to the device. The output of this step is the validated data.

[0154] Step 3: Data Preprocessing

[0155] The server preprocesses the validated data by standardizing numeric data and converting categorical data to numbers. For example, it might encode favorite subjects as "1: Math, 2: English, 3: Physical Education." This preprocessing generates standardized data that makes it easier for algorithms to understand the data. The input to this step is the validated data, and the output is the preprocessed data.

[0156] Step 4: Data analysis and clustering

[0157] The server analyzes each student's aptitude based on the preprocessed data. It uses clustering algorithms or supervised learning algorithms to classify students into clusters based on their characteristics. For example, it may classify students into a cluster with high athletic ability or a cluster with an interest in mathematics. The input of this step is the preprocessed data, and the output is the classification results of the clustered students.

[0158] Step 5: Selecting potential career candidates

[0159] The server selects suitable career candidates based on the clustered student data. It lists the careers associated with each cluster and recommends them to the student. In this step, a generative AI model is used to list careers that match the student's characteristics. For example, a student with high athletic ability and an interest in mathematics can be recommended a career such as "sports data analyst." The input to this step is the clustered classification results, and the output is a list of career candidates.

[0160] Step 6: Generate a recommendation report

[0161] The server generates a recommendation report for each student based on the career candidate list. This report includes recommended career candidates, the skills required for those careers, and recommendations for related learning and activities. The generated report is sent to the terminal. The input of this step is the career candidate list, and the output is the recommendation report.

[0162] Step 7: Gather feedback

[0163] The terminal provides an interface to present the generated recommendation report to students, educators, and parents. Users can view the report through the terminal and input their opinions or questions. For example, if a student wants more information about a "sports data analyst," he or she can submit a question through the terminal. The feedback is sent to the server. The input of this step is the recommendation report, and the output is the feedback information.

[0164] Step 8: Reevaluate and improve the algorithm

[0165] The server collects feedback sent from the devices and reevaluates the performance of the analysis algorithm and the entire system. Based on the collected feedback, it creates and implements an improvement plan to optimize the content of the career candidate list and recommendation report. For example, if many students express interest in "sports data analyst," it will strengthen the provision of information related to that career. The input of this step is feedback information, and the output is an optimized algorithm and an updated system.

[0166] By carrying out these specific processing steps in a detailed and orderly manner, it becomes possible to select a career and provide learning support based on each student's aptitude.

[0167] (Application example 1)

[0168] 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."

[0169] Currently, many students find it difficult to have a concrete image of their future dreams and careers. It is also difficult for teachers and parents to accurately grasp students' aptitudes and provide advice based on that. Furthermore, traditional career recommendation systems are based on static data analysis and lack the utilization of feedback and the delivery of educational and entertainment content. This prevents students from choosing a career that matches their aptitudes, making it difficult for them to set future goals.

[0170] 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.

[0171] In this invention, the server includes means for collecting data on athletic performance and interests from students, means for preprocessing and verifying the collected data, means for analyzing the aptitudes of students based on the preprocessed data and selecting career candidates, means for presenting generated reports to students, educators, and parents and collecting feedback, means for reevaluating and improving the analysis algorithm based on the collected feedback, and means for delivering educational and entertainment content related to the suggested careers. This allows students to understand career candidates based on their aptitudes and interests and to form a concrete image of them through the related content.

[0172] "Students" refers to children from the upper grades of elementary school to junior high school.

[0173] "Athletic performance" refers to the specific numerical data and evaluations recorded by students during physical education and club activities.

[0174] "Interest data" refers to survey results and information about students' favorite subjects, clubs, hobbies, and future interests.

[0175] A "clustering algorithm" is an analytical method for classifying data into multiple groups (clusters), and mainly uses the K-means method.

[0176] "Career suggestions" refer to specific occupations or career options suggested to students based on data analysis.

[0177] A "recommendation report" is a document that contains career options based on a student's aptitudes and interests, along with specific advice related to those careers.

[0178] "Feedback" refers to opinions, impressions, and questions provided by students, educators, and parents in response to the generated recommendation reports and proposals.

[0179] "Educational and entertainment content" refers to interactive materials such as videos, quizzes, and interviews that help students learn while having fun.

[0180] "Analysis algorithm" refers to a mathematical processing method for determining students' aptitude and selecting career candidates based on collected and pre-processed data.

[0181] MODE FOR CARRYING OUT THE INVENTION

[0182] This invention is a system for helping students concretely visualize their future dreams and careers. The system includes the steps of data collection, data preprocessing, data analysis, report generation, feedback collection, and content distribution.

[0183] Overall system configuration

[0184] The system consists of the following main components:

[0185] 1. Data collection terminal

[0186] 2. Data Validation and Preprocessing Server

[0187] 3. Data analysis server

[0188] 4. Report Generation Server

[0189] 5. Feedback collection terminal

[0190] 6. Algorithm Reevaluation Server

[0191] 7. Content Distribution Server

[0192] Technology used

[0193] Language: Python, JavaScript (registered trademark)

[0194] AI algorithms: clustering (K-means), supervised learning (SVM, Random Forest)

[0195] Database: Firebase

[0196] Front-end framework: React Native

[0197] Backend: Google® Cloud Functions

[0198] Content delivery: AWS (registered trademark) S3, CloudFront

[0199] Program processing

[0200] Data collection

[0201] Students enter information about their athletic achievements and interests through a smartphone application. For example, a questionnaire about their 100-meter sprint time in physical education class, their favorite subjects, and club activities is collected. This data is sent to Firebase via the Internet.

[0202] Examples:

[0203] Prompt: "What is your most recent 100-meter sprint time during gym class?"

[0204] Data Validation and Preprocessing

[0205] The server validates the received data and checks for input errors (for example, checking that the 100-meter sprint time is not physically impossible or that the questionnaire is completely filled out).The server then preprocesses the validated data, standardizing numeric data and encoding categorical data into numbers.

[0206] Data analysis

[0207] The data analysis server analyzes each student's aptitude based on the preprocessed data. The analysis mainly uses clustering algorithms (K-means) and supervised learning algorithms (SVM, Random Forest). This allows students to be classified into clusters based on their interests and abilities, and the results are used to create a list of suitable career candidates.

[0208] Examples:

[0209] Prompt: "Use a clustering algorithm to analyze the interests and abilities of all students and classify them into specific career clusters."

[0210] Report Generation

[0211] The report generation server generates a recommendation report for each student based on the data analysis results, which includes recommendations for suitable careers for the student, the necessary skills, and related learning and activities.

[0212] Feedback collection

[0213] The feedback collection terminal presents the generated recommendation report to students, educators, and parents. Users can view the report through the terminal and enter their opinions and questions. For example, if a student is interested in "sports data analyst" and wants more detailed information about the job, they can submit a question through the terminal.

[0214] Examples:

[0215] Prompt: "If you would like more information about the suggested jobs or have suggestions for improvement, please fill out the feedback form below."

[0216] Algorithm Reevaluation

[0217] The algorithm re-evaluation server collects feedback sent from the devices and re-evaluates the performance of the analysis algorithm and the entire system. Based on this feedback, it creates and implements an improvement plan to optimize the contents of the job candidate list and recommendation report.

[0218] Educational and entertainment content delivery

[0219] The content delivery server stores educational and entertainment content related to the proposed careers (e.g., videos, quizzes, interviews) in AWS S3 and uses CloudFront to deliver it to users at high speed.

[0220] Examples:

[0221] Prompt: "Watch educational videos related to sports data analysts."

[0222] This system allows students to understand potential careers based on their aptitudes and interests, and gives them a concrete image of what those careers could be through related content, allowing teachers and parents to provide specific support tailored to the students' aptitudes.

[0223] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[0224] System processing steps

[0225] Step 1: Data collection

[0226] The device provides an interface where students can input information about their athletic performance and interests. The input data is sent to Firebase. For example, a student can enter their 100-meter sprint time or favorite subject, and this data is immediately saved in the database. The input data (athletic performance, interest survey) is treated as output (data saved to Firebase) as is.

[0227] Step 2: Data validation and preprocessing

[0228] The server retrieves the data stored in Firebase and validates its contents. Specifically, it checks whether the 100-meter sprint time is within the physically possible range and whether all questions have been answered correctly. After confirming there are no errors, it then standardizes the numeric data and encodes the categorical data into numbers. It outputs the input data (student athletic performance and interest questionnaire) as validated data, which is then converted into preprocessed data.

[0229] Step 3: Data analysis

[0230] The data analysis server analyzes the preprocessed data using a clustering algorithm (K-means) and a supervised learning algorithm (SVM, Random Forest). This classifies students into clusters based on their interests and athletic performance, and lists corresponding career candidates. The input data (preprocessed data) is output as the analysis results (cluster classification and a list of career candidates).

[0231] Step 4: Generate a recommendation report

[0232] The report generation server generates a recommendation report containing suitable career candidates and details for each student based on the data analysis results. This report lists the recommended careers and the skills and learning methods required for those careers. For example, "For a student with high athletic ability and an interest in mathematics, we recommend a sports data analyst position and encourage learning related programming languages." The input data (analysis results) are output as a recommendation report.

[0233] Step 5: Gather feedback

[0234] The feedback collection terminal presents the generated recommendation report to students, educators, and parents. Users who view the report can enter their thoughts and questions in a feedback form. For example, if a student is interested in a "sports data analyst" and has a question about specific study methods, they can submit that question through the terminal. The input data (user feedback) is output as feedback.

[0235] Step 6: Reevaluate the algorithm

[0236] The algorithm re-evaluation server analyzes the collected feedback and re-evaluates the performance of the entire system. Based on this feedback, it makes improvements to optimize the analysis algorithm, career candidate list, and recommendation report content. For example, if many students express interest in a particular career, it adds detailed information and new recommendations related to that career. The input data (feedback) is output as an improved algorithm and career candidate list.

[0237] Step 7: Educational and Entertainment Content Distribution

[0238] The content delivery server provides educational and entertainment content (videos, quizzes, interviews, etc.) related to the recommended careers. For example, educational videos and interview videos about "sports data analyst" are stored in AWS S3 and delivered to users at high speed via CloudFront. The input data (career recommendations and related content) is output as delivery content.

[0239] This allows students to understand potential careers based on their aptitudes and interests, and form a concrete image of them through related content, while also enabling teachers and parents to provide specific support according to students' aptitudes.

[0240] 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.

[0241] This invention is a system to support students from the upper grades of elementary school to junior high school (hereinafter referred to as "students") in concretely envisioning their future dreams and careers. This system collects and analyzes data on students' athletic performance and interests, presents appropriate career options, and uses students' emotional data to improve the accuracy of the analysis.

[0242] Overall structure

[0243] The system consists of the following main components:

[0244] 1. Data collection terminal

[0245] 2. Data Validation and Preprocessing Server

[0246] 3. Data analysis server

[0247] 4. Report Generation Server

[0248] 5. Feedback collection terminal

[0249] 6. Algorithm Reevaluation Server

[0250] 7. Emotion Engine

[0251] Program processing

[0252] Data collection

[0253] The device provides an interface for students to input information about their athletic performance and interests. For example, a student can enter their weekly 100-meter sprint time or their favorite subjects and club activities through a dedicated application. At the same time, the device collects emotional data from the student's facial expressions and voice, which is also sent to the server.

[0254] Data Validation and Preprocessing

[0255] The server verifies the received data and checks for input errors. For example, it checks whether the 100-meter sprint time is physically impossible or whether the questionnaire is completely filled out. Incorrect or incomplete data requires correction or re-entry. At the same time, the emotion engine analyzes the collected emotion data and provides quantified emotion information to the server.

[0256] Data Preprocessing

[0257] The server preprocesses the validated data. Specifically, it standardizes numerical data and encodes categorical data. For example, it converts survey responses (favorite subject) into numerical values. At the same time, the server preprocesses sentiment data and integrates it with other data.

[0258] Data analysis

[0259] The server analyzes each student's aptitude based on the preprocessed data. It uses clustering and supervised learning algorithms to classify the student's interests and abilities. For example, students are divided into clusters based on athletic ability and academic aptitude, and career candidates are selected based on each. Emotional data is used as part of the analysis to reinforce interest levels.

[0260] Report Generation

[0261] The server generates a recommendation report for each student based on the data analysis results. This report includes multiple career options suitable for the student, along with recommendations for the skills and related subjects required. For example, a student with strong athletic ability and good math grades could be recommended a career such as "sports data analyst." At the same time, it utilizes emotional data to optimize the report content, taking into account the student's emotional interest in specific careers.

[0262] Feedback collection

[0263] The device provides an interface for presenting the generated report to students, teachers, and parents. Users (students, teachers, and parents) can view and confirm the contents of the presented report. For example, they can use it to find out more information about careers that students are interested in. At the same time, the device collects students' reactions and emotions using the emotion engine again and records them as feedback.

[0264] Feedback Reflected

[0265] Users (students, teachers, and parents) can provide feedback on the report content through the terminal. For example, a student may be interested in the "Sports Data Analyst" and enter additional questions or opinions about the report. At the same time, students' emotional data is also collected.

[0266] Algorithm Reevaluation

[0267] The server collects feedback and emotional data sent from the devices and reevaluates the performance of the analysis algorithm and the overall system. For example, if a student's emotional reaction to a particular occupation is positive, the system will be optimized to provide more detailed information about that occupation in the future, allowing it to provide more personalized advice to each individual student.

[0268] Specific examples

[0269] Example 1: Data collection

[0270] Using a dedicated app on a device, students enter their physical education records (for example, 100-meter sprint time) and interest questionnaires (favorite subjects, club activities, etc.) once a week.

[0271] At the same time, the device analyzes the students' facial expressions and voices using an emotion engine to collect emotional data.

[0272] Example 2: Data validation and preprocessing

[0273] The server validates the received data to ensure there are no errors, for example, checking for anomalies in the 100-meter sprint time.

[0274] The emotion engine analyzes the collected emotion data and provides the quantified results to the server.

[0275] Example 3: Data analysis

[0276] The server generates an analysis result in which Student A is classified as "Athletic Ability Cluster: High," "Mathematics Interest Cluster: Medium," and "Emotion Cluster: Positive."

[0277] Example 4: Report Generation

[0278] The server recommends occupations such as "sports data analyst" or "sports instructor" to Student A. The report lists the necessary skills and learning recommendations.

[0279] Based on the emotional data, we provide detailed information about the "sports data analyst" that Student A was particularly interested in.

[0280] Example 5: Feedback collection

[0281] The terminal presents the generated report to Student A, who then checks the report contents and becomes interested in the "Sports Data Analyst."

[0282] Student A's facial expressions and reactions are analyzed again by the emotion engine and saved as feedback data.

[0283] Example 6: Algorithm reevaluation

[0284] The server optimizes the analysis algorithm based on Student A's feedback and emotional data. This process will enable the server to provide more detailed and personalized recommendation reports in the future.

[0285] This system will enable students to gain a deeper understanding of their own characteristics and, taking into account their emotional reactions, to map out specific careers and dreams for the future, while also enabling teachers and parents to provide specific support tailored to students' aptitudes.

[0286] The processing flow will be explained below.

[0287] Step 1:

[0288] The device provides an interface for students to enter data about their athletic performance and interests. For example, using a dedicated application, students can enter their weekly 100-meter sprint time or their favorite subjects and club activities in a questionnaire. At the same time, the device uses an emotion engine to analyze the student's facial expressions and voice to collect emotional data.

[0289] Step 2:

[0290] The device transmits the collected athletic performance, interest questionnaire, and emotional data to a server via the Internet, where the data is temporarily stored and awaits further processing.

[0291] Step 3:

[0292] The server then verifies the received athletic performance and interest survey data, detecting, for example, physically impossible 100-meter sprint times or incomplete survey responses, and verifies the accuracy of the data. Any incorrect data is corrected or re-entered.

[0293] Step 4:

[0294] The emotion engine analyzes the collected emotion data and generates numerical emotion information (e.g., interest level or stress level), which is also sent to the server.

[0295] Step 5:

[0296] The server preprocesses the validated athletic performance and interest survey data by standardizing numeric data and encoding categorical data into numbers, e.g., by converting survey responses into consistent numeric values.

[0297] Step 6:

[0298] The server analyzes student aptitude based on the preprocessed data. Clustering and supervised learning algorithms are used to classify student interest and ability characteristics. Emotional data is also used as part of the analysis, taking into account the student's interest level and emotional tendencies.

[0299] Step 7:

[0300] The server generates a recommendation report for each student based on the analysis results, including recommendations for suitable careers, the skills required, and related subjects. Using emotional data, the report content is optimized to take into account the student's emotional interest in specific careers.

[0301] Step 8:

[0302] The terminal provides an interface for presenting the generated recommendation report to students, teachers, and parents. Users (students, teachers, and parents) can view the report through the terminal and check its contents.

[0303] Step 9:

[0304] Users (students, teachers, and parents) can provide feedback on the report content through the device. For example, a student can enter additional questions or opinions about a specific occupation. At the same time, the device analyzes the student's facial expressions and voice again using the emotion engine, collecting emotional data along with the feedback.

[0305] Step 10:

[0306] The device sends the collected feedback and emotion data to a server, where the feedback information is stored in a database and used for subsequent algorithm optimization processes.

[0307] Step 11:

[0308] The server reevaluates and optimizes the performance of the analysis algorithm and the entire system based on the collected feedback and sentiment data. For example, if many students show a high interest in a particular career, it will enrich the information related to that career or add new recommendations that incorporate the feedback.

[0309] This specific processing step allows students to receive career recommendations based on their aptitudes and interests, taking into account their emotional reactions, and also makes it easier for teachers and parents to provide appropriate advice to students.

[0310] Example 2

[0311] 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."

[0312] In recent years, the importance of supporting students in choosing their future careers has increased. However, simple aptitude tests and questionnaires alone have the problem of being unable to present career options that fully reflect students' interests and feelings. Furthermore, conventional systems do not adequately reflect feedback, making it difficult to respond to students' individual requests and changing interests. This presents a challenge, as students are unable to visualize a concrete future, making it difficult for educators and parents to provide appropriate guidance.

[0313] The specific processing by the specific processing unit 290 of the data processing device 12 in the second embodiment is realized by the following means.

[0314] In this invention, the server includes means for collecting data on athletic performance and interests from students, means for collecting and analyzing emotional data from students' facial expressions and voices, means for preprocessing and verifying the collected data, means for analyzing the students' aptitudes and selecting career candidates based on the preprocessed data, means for generating a recommendation report based on the analysis results, means for presenting the generated report to students, educators, and parents and collecting feedback, and means for reevaluating and improving the analysis algorithm based on the collected feedback. This makes it possible to present personalized career candidates that take students' emotions and feedback into consideration, allowing them to paint a more specific and appropriate picture of their future.

[0315] "Students" refers to students in the upper grades of elementary school to junior high school age groups.

[0316] "Athletic performance" refers to performance data such as times and scores recorded by students in physical education classes and sports activities.

[0317] "Interests" refers to information that shows a student's interests and preferences in their favorite subjects, club activities, hobbies, etc.

[0318] "Data collection" refers to the process of obtaining information from students about their athletic achievements and interests, including entering information through an application or interface.

[0319] "Emotional data" refers to information about emotions analyzed from students' facial expressions and voices, including data that quantifies emotional states such as joy, surprise, and interest.

[0320] "Data preprocessing" refers to processes such as standardization and encoding that prepare collected data into an analyzable format.

[0321] "Data verification" refers to the process of verifying that collected data is accurate and complete.

[0322] "Analytical algorithms" refer to mathematical methods and models used to classify students' aptitudes and select career candidates based on collected data.

[0323] A "clustering algorithm" refers to an analytical method for classifying data into multiple groups based on similarity.

[0324] A "recommendation report" is a document generated based on the analysis results that lists suitable career options, required skills, and related subject recommendations for students.

[0325] "Feedback" refers to the opinions and reactions provided by students, educators, and parents regarding the recommendation reports and system proposals.

[0326] "Algorithm re-evaluation" refers to the process of improving the performance and accuracy of analysis algorithms based on collected feedback.

[0327] This is a system that helps students from the upper grades of elementary school to junior high school (hereinafter referred to as "students") to concretely visualize their future dreams and careers. The system collects and analyzes data on students' athletic performance and interests, presents appropriate career options, and uses students' emotional data to improve the accuracy of the analysis.

[0328] Overall structure

[0329] The system consists of the following main components:

[0330] 1. Data collection terminal

[0331] 2. Data Validation and Preprocessing Server

[0332] 3. Data analysis server

[0333] 4. Report Generation Server

[0334] 5. Feedback collection terminal

[0335] 6. Algorithm Reevaluation Server

[0336] 7. Emotion Engine

[0337] Hardware and software used

[0338] Device: A smartphone, tablet, or computer running a dedicated application where students enter information.

[0339] Server: A central server for receiving, validating, analyzing, and generating reports on data, using generative AI models and clustering algorithms.

[0340] Emotion engine: Software that analyzes students' facial expressions and voices to generate emotional data.

[0341] Data collection

[0342] The device provides an interface for students to enter information about their athletic achievements and interests. For example, they may be asked to enter:

[0343] 100 meter sprint time once a week

[0344] Favorite subject

[0345] Club Activities

[0346] At the same time, the device collects the student's facial expressions and voice, and analyzes them using an emotion engine. For example, the device converts the student's facial expressions into numerical values ​​such as the degree of "happiness" or "interest," and sends the results to the server.

[0347] Data Validation and Preprocessing

[0348] The server validates the received data and checks for input errors. Any abnormal or incomplete data will be corrected or re-entered. For example, it checks to see if a 100-meter sprint time is a physically impossible value, such as "0 seconds" or "100 seconds."

[0349] The emotion data analyzed by the emotion engine is provided to the server as numerical information. The emotion data is provided in the following format, for example:

[0350] Delight level: 75

[0351] Surprise level: 30

[0352] These data are then combined with other input data and pre-processed for analysis: numerical data are standardized and categorical data are encoded.

[0353] Data analysis

[0354] The server analyzes each student's aptitude based on the preprocessed data. Clustering algorithms and supervised learning algorithms are used to classify the student's interests and abilities. For example, the server generates analysis results that classify Student A into "High athletic ability cluster," "Medium math interest cluster," and "Positive emotional cluster."

[0355] Report Generation

[0356] The server generates a recommendation report for each student based on the analysis results. This report lists suitable career candidates, the required skills, and recommendations for related subjects. For example, Student A may be recommended careers such as "sports data analyst" and "sports instructor," along with required skills (e.g., data analysis, communication) and recommended studies (e.g., statistics, information processing).

[0357] Feedback collection

[0358] The device provides an interface to present the generated report to students, educators, and parents. For example, if Student A is interested in "Sports Data Analyst," he or she can provide feedback such as "I'd like more detailed information." The student's reactions and emotions are also analyzed by the emotion engine and sent to the server.

[0359] Algorithm Reevaluation

[0360] The server collects feedback and emotional data sent from the devices and reevaluates the performance of the analysis algorithm and the overall system. For example, if students' emotional reactions to a particular occupation are positive, the system will be optimized to provide more detailed information about that occupation.

[0361] Specific examples

[0362] 1. Data collection: Student A uses a dedicated app to input "14.2 seconds for the 100-meter dash" and answer "Science is my favorite subject." At the same time, the student's facial expression is analyzed as "Delight level: 60" and sent to the server.

[0363] 2. Data validation and preprocessing: The server validates the received data and confirms that the 100-meter sprint time is correct as "14.2 seconds." The emotion engine converts the data into a numerical value, "Delight Level: 60," and provides it to the server.

[0364] 3. Data analysis: The server generates analysis results that classify Student A into "Athletic ability cluster: Medium," "Science interest cluster: High," and "Emotion cluster: Interested."

[0365] 4. Report Generation: The server generates a report recommending occupations such as "biologist" or "scientific researcher" to Student A. Required skills (e.g., laboratory techniques, data analysis) and recommended studies (e.g., biology, chemistry) are also listed.

[0366] 5. Feedback collection: The device presents the generated report to Student A, who provides feedback that he is “interested in scientific researchers.” The student’s facial expressions are analyzed again and sent to the server.

[0367] 6. Algorithm re-evaluation: The server will optimize the analysis algorithm based on Student A's feedback and emotional data, so that it can provide more detailed and personalized recommendation reports in the future.

[0368] This process allows students to envision specific careers and dreams, taking into account their own characteristics and emotional tendencies, and also allows educators and parents to efficiently provide support tailored to each student's aptitudes.

[0369] The flow of the identification process in the second embodiment will be described with reference to FIG.

[0370] The flow of this system's program processing

[0371] Step 1: Data collection

[0372] Device:

[0373] Input: Students use a dedicated application to input information about their athletic achievements (e.g., 100-meter sprint time) and interests (e.g., favorite subjects, club activities).

[0374] How it works: The application collects the student's facial expressions and voice and sends them to the emotion engine for analysis.

[0375] Output: The collected data (athletic performance, interest information, emotional data) is sent to the server.

[0376] Step 2: Data validation

[0377] server:

[0378] Input: Athletic performance, interest information, and emotional data sent from your device.

[0379] How it works: The server receives the data and checks whether the input values ​​are invalid or incorrect. For example, it checks whether the 100-meter sprint time is an abnormal value such as "0 seconds" or "100 seconds."

[0380] Output: Send the validated data to the preprocessing step. If the data is invalid, prompt the student to re-enter.

[0381] Step 3: Data Preprocessing

[0382] server:

[0383] Input: Verified athletic performance, interest information, and emotional data.

[0384] What it does: Normalize numerical data (e.g., convert 100-meter sprint times to standard scores), encode categorical data (e.g., convert favorite subjects to numbers), or integrate emotional data with other data.

[0385] Output: Send the preprocessed data to the analysis step.

[0386] Step 4: Data analysis

[0387] server:

[0388] Input: Preprocessed data.

[0389] How it works: Using clustering and supervised learning algorithms, we analyze the characteristics of students' interests and abilities, for example classifying them into motor skill clusters, high math interest clusters, and emotional clusters.

[0390] Output: Send the analysis results (classification of student aptitudes and interests) to the report generation step.

[0391] Step 5: Generate a report

[0392] server:

[0393] Input: Analysis results.

[0394] How it works: Based on the analysis results, a recommendation report is generated for the student, including suitable career options, required skills, and related subject recommendations. It also takes into account sentiment data and provides detailed information about careers that the student has expressed interest in.

[0395] Output: Send the generated recommendation report to the feedback collection terminal.

[0396] Step 6: Gather feedback

[0397] Device:

[0398] Input: The generated recommendation report.

[0399] What it does: Provides an interface to present reports to students, educators, and parents, and gathers feedback. Students can enter careers they're interested in, follow-up questions, etc.

[0400] Output: Send the collected feedback to the server.

[0401] Step 7: Reevaluate the algorithm

[0402] server:

[0403] Input: Feedback and emotion data.

[0404] How it works: Analyzes feedback and emotional data to optimize the analysis algorithm and system. For example, if a student's emotional reaction to a particular occupation is positive, the system will further enrich the information about that occupation.

[0405] Output: Prepare the data for further analysis and report generation using optimized analysis algorithms.

[0406] This system will enable personalized career suggestions that take into account students' feelings and feedback, allowing them to paint a more specific and appropriate picture of their future. It will also enable educators and parents to efficiently provide support that is tailored to students' aptitudes.

[0407] (Application example 2)

[0408] 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."

[0409] The present invention relates to a system that supports students in concretely envisioning their future dreams and careers, and aims to provide a system that can take into account not only athletic performance and interest data, but also emotional data. Conventional systems have had difficulty reflecting students' emotional interests, which has led to a problem of reduced accuracy in analyzing aptitude and selecting career candidates.

[0410] 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.

[0411] In this invention, the server includes a means for collecting data on athletic performance and interests from students, a means for preprocessing and verifying the collected data, and a means for analyzing the aptitude of students based on the preprocessed data and selecting career candidates, which enables emotional data to be integrated into the analysis result and optimize the recommendation report based on emotional interest levels.

[0412] "Students" refers to children from upper elementary school to junior high school.

[0413] "Athletic performance" refers to a student's physical education and athletic records and performance data.

[0414] "Interest data" refers to information such as the subjects and club activities that students are interested in.

[0415] "Data collection tools" refers to devices and software that provide an interface for collecting various data from students.

[0416] "Preprocessing" refers to the process of preparing collected data into a format that can be analyzed.

[0417] "Verification" refers to the process of checking and correcting errors or incompleteness in collected data.

[0418] "Data analysis" refers to the process of assessing students' aptitude based on collected and pre-processed data.

[0419] A "clustering algorithm" refers to a machine learning method for classifying data points into several groups (clusters).

[0420] "Career Candidates" refers to a list of occupations suggested to a student based on the results of the aptitude analysis.

[0421] "Recommendation Report" refers to a document or digital data that lists the results of a student's aptitude analysis and possible career options.

[0422] "Emotional Data" refers to emotional information obtained from a student's facial expressions, voice, and behavior.

[0423] An "emotion engine" refers to software or algorithms that analyze emotional data and generate quantified information.

[0424] "Feedback Collection Instrument" means any device or software used to present generated reports to students, educators, and parents and to collect their reactions and opinions.

[0425] "Analysis algorithm reevaluation" refers to the process of reviewing and improving the performance of data analysis algorithms based on collected feedback data.

[0426] "Optimization" refers to the process of improving the content and analytical algorithms of generated reports to make them more effective and efficient.

[0427] This invention is a system that helps students visualize their future dreams and careers by collecting and analyzing data on students' athletic performance, interests, and emotions, presenting appropriate career candidates, and reevaluating and improving the analysis algorithm based on feedback. The specific configuration and functions of this system are described below.

[0428] Overall structure

[0429] The system consists of the following main components:

[0430] 1. Data collection terminal

[0431] 2. Data Validation and Preprocessing Server

[0432] 3. Data analysis server

[0433] 4. Report Generation Server

[0434] 5. Feedback collection terminal

[0435] 6. Algorithm Reevaluation Server

[0436] 7. Emotion Engine

[0437] Program processing

[0438] Data collection

[0439] The device provides an interface for students to input information about their athletic performance and interests. For example, a student can enter their weekly 100-meter sprint time or their favorite subjects and club activities through a dedicated application. At the same time, the device collects emotional data from the student's facial expressions and voice, which is also sent to the server.

[0440] Data Validation and Preprocessing

[0441] The server verifies the received data and checks for input errors. For example, it checks whether the 100-meter sprint time is physically impossible or whether the questionnaire is completely filled out. Incorrect or incomplete data requires correction or re-entry. At the same time, the emotion engine analyzes the collected emotion data and provides quantified emotion information to the server.

[0442] Data analysis

[0443] The data analysis server analyzes each student's aptitude based on the preprocessed data. For example, it uses the k-means clustering algorithm to classify the student's athletic ability and interest characteristics. Emotional data is also used in the analysis to reinforce interest levels.

[0444] Report Generation

[0445] The report generation server generates a recommendation report for each student based on the data analysis results. This report includes multiple career options suitable for the student, along with recommendations for the skills and related subjects required for each. Using sentiment data, the report also includes detailed information about the careers that the student is particularly interested in.

[0446] Feedback collection

[0447] The feedback collection terminal provides an interface for presenting the generated reports to students, educators, and parents. Users can view and confirm the contents of the presented reports. For example, they can use the reports to find out more information about careers that students are interested in. At the same time, the terminal also collects students' facial expressions and reactions using the emotion engine and records them as feedback.

[0448] Algorithm Reevaluation

[0449] The server collects feedback and emotional data sent from the devices and reevaluates the performance of the analysis algorithm and the overall system. For example, if a student's emotional reaction to a particular occupation is positive, the system will be optimized to provide more detailed information about that occupation in the future, allowing it to provide more personalized advice to each individual student.

[0450] Hardware and software used

[0451] Hardware: Smartphones, server computers

[0452] Software: Python, Numpy, scikit-learn, dedicated applications

[0453] Adding specific examples

[0454] Example: Generate analysis results that classify Student A as "Athletic Ability Cluster: High," "Mathematics Interest Cluster: Medium," and "Emotion Cluster: Positive." The report recommends occupations such as "Sports Data Analyst" and "Sports Instructor," and lists the skills and learning recommendations related to those occupations. Detailed information about "Sports Data Analyst," in which Student A showed particular interest, is provided.

[0455] Prompt Sentence Examples

[0456] "Design data preprocessing and analysis algorithms for a system that collects students' athletic performance and interest data, classifies them using a clustering algorithm, and recommends suitable occupations. The generative AI model should include a procedure for compiling the clusters and recommended occupations into a report that is easy to understand for the student."

[0457] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[0458] Step 1:

[0459] Data collection

[0460] The device provides an interface for collecting data on athletic performance and interests from students. Specifically, students are asked to enter their 100-meter sprint times, favorite subjects, and club activities through a dedicated smartphone application once a week. The input data is stored in the device's internal memory. At the same time, the device also uses a camera and microphone to collect students' facial expressions and voice data, which is then saved as emotional data.

[0461] Input: Student athletic performance, interest survey data, facial expression and voice data

[0462] Output: Student data (athletic performance, interest data, emotional data)

[0463] Step 2:

[0464] Data Validation and Preprocessing

[0465] The server receives student data sent from the device and verifies it. During the verification process, it checks for physically impossible values ​​(e.g., a 100-meter sprint time of 0 seconds) and missing questionnaire entries. If the data is incomplete, the device is asked to re-enter it. The server then uses an emotion engine to quantify facial and voice data and convert it into an emotion score. It also standardizes and categorizes athletic performance and interest data.

[0466] Input: Student data (athletic performance, interest data, emotional data)

[0467] Output: Preprocessed data (standardized athletic performance, encoded interest data, emotion scores)

[0468] Step 3:

[0469] Data analysis

[0470] The data analysis server analyzes students' aptitudes based on the preprocessed data. During this process, a clustering algorithm (e.g., k-means) is used to cluster students based on their athletic ability, interests, and emotional characteristics. As a result of the clustering, students are classified into multiple aptitude clusters. At the same time, emotional data is integrated into the analysis results as the degree of interest.

[0471] Input: Preprocessed data (standardized motor performance, encoded interest data, emotion scores)

[0472] Output: Aptitude clusters (exercise clusters, interest clusters, emotion clusters)

[0473] Step 4:

[0474] Report Generation

[0475] The report generation server generates a recommendation report for each student based on the data analysis results. It selects career candidates for each cluster and provides detailed recommendations for the skills required and related subjects. It also uses emotional data to provide detailed information about careers that students are particularly interested in. The generated report is saved on the server.

[0476] Input: Aptitude cluster (exercise cluster, interest cluster, emotion cluster)

[0477] Output: Recommendation report (job candidates, required skills, learning recommendations)

[0478] Step 5:

[0479] Feedback collection

[0480] The feedback collection terminal presents the generated report to students, educators, and parents. Users can view the report contents and enter their opinions and questions about careers and study recommendations that students are interested in. The terminal also collects students' facial expressions and reactions, analyzes them using an emotion engine, and records them as feedback data.

[0481] Input: recommendation report, user responses (opinions, questions, facial expressions)

[0482] Output: Feedback data (user opinions, sentiment data)

[0483] Step 6:

[0484] Algorithm Reevaluation

[0485] The server collects and analyzes the feedback data sent from the devices and reevaluates the performance of the analysis algorithm. For example, if students have a high number of positive emotional reactions to a particular occupation, the system will optimize the algorithm to provide more detailed information about that occupation. This allows the system to provide more personalized advice to each student.

[0486] Input: Feedback data (user opinions, sentiment data)

[0487] Output: Improved analysis algorithm

[0488] 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.

[0489] 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.

[0490] 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.

[0491] [Second embodiment]

[0492] FIG. 3 shows an example of the configuration of a data processing system 210 according to the second embodiment.

[0493] 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.

[0494] 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).

[0495] 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.

[0496] 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.

[0497] 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).

[0498] 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.

[0499] 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.

[0500] 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.

[0501] 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.

[0502] In the smart glasses 214, the reception output process is performed by the processor 46. A reception output program 60 is stored in the storage 50. The processor 46 reads the reception output program 60 from the storage 50 and executes the read reception output program 60 on the RAM 48. The reception output process is realized by the processor 46 operating as the control unit 46A in accordance with the reception output program 60 executed on the RAM 48.

[0503] 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."

[0504] This is a system that helps students from the upper grades of elementary school to junior high school (hereinafter referred to as "students") to concretely visualize their future dreams and careers. The system aims to collect and analyze data on students' athletic performance and interests, and present appropriate career options.

[0505] Overall structure

[0506] The system consists of the following main components:

[0507] 1. Data collection terminal

[0508] 2. Data Validation and Preprocessing Server

[0509] 3. Data analysis server

[0510] 4. Report Generation Server

[0511] 5. Feedback collection terminal

[0512] 6. Algorithm Reevaluation Server

[0513] Program processing

[0514] Data collection

[0515] The device provides an interface for students to input information about their athletic achievements and interests. For example, an application can be provided to collect information such as their 100-meter sprint time in physical education class, or a questionnaire about their favorite subjects and extracurricular activities. The collected data is then sent to a server via the Internet.

[0516] Data Validation and Preprocessing

[0517] The server validates the received data and checks for input errors (for example, checking that the 100-meter sprint time is not physically impossible or that the questionnaire is completely filled out). The server then preprocesses the validated data (for example, standardizing numeric data and encoding categorical data into numbers).

[0518] Data analysis

[0519] The server analyzes each student's aptitude based on the preprocessed data, using clustering and supervised learning algorithms to classify them into clusters based on their interests and abilities, and then lists suitable career candidates based on the results.

[0520] Report Generation

[0521] The server generates a recommendation report for each student based on the data analysis results. This report includes a list of suitable careers for the student, along with the skills and related learning and activities required. For example, a student with strong athletic ability and good grades in mathematics may be recommended a career such as "sports data analyst," along with specific study methods and workshop participation recommendations.

[0522] Feedback collection

[0523] The terminal provides an interface for presenting the generated recommendation report to students, teachers, and parents. Users (students, teachers, and parents) can view the report through the terminal and enter their opinions and questions. For example, if a student is interested in "sports data analyst" and would like more detailed information about the job, they can send a question through the terminal.

[0524] Algorithm Reevaluation

[0525] The server collects feedback from the devices and reevaluates the performance of the analysis algorithm and the overall system. Based on this feedback, it creates and implements an improvement plan to optimize the content of the career candidate list and recommendation report. For example, if many students express interest in a particular career, it will provide more detailed information related to that career or add new related recommendations.

[0526] Specific examples

[0527] Example 1: Data collection

[0528] Using a dedicated app on a device, students enter their physical education records (for example, 100-meter sprint time) and interest questionnaires (favorite subjects, club activities, etc.) once a week.

[0529] The user (student) enters this information and the data is automatically sent to the server.

[0530] Example 2: Data validation and preprocessing

[0531] The server validates the received data to ensure there are no errors, for example, checking for anomalies in the 100-meter sprint time.

[0532] The server normalizes the data, for example encoding interest survey responses into numbers.

[0533] Example 3: Data analysis

[0534] The server generates an analysis result in which Student A is classified as "Athletic Ability Cluster: High" and "Mathematics Interest Cluster: Medium."

[0535] Example 4: Report Generation

[0536] The server recommends occupations such as "sports data analyst" or "sports instructor" to Student A. The report lists the necessary skills and learning recommendations.

[0537] Example 5: Feedback collection

[0538] The terminal presents the generated report to Student A, who then views the report and becomes interested in the "Sports Data Analyst."

[0539] Student A inputs a follow-up question through the terminal, for example, "How do I study the programming language required for this job?"

[0540] Example 6: Algorithm reevaluation

[0541] The server collects feedback from Student A and optimizes the analysis algorithm. This process continuously improves the entire system.

[0542] This system will enable students to gain a deeper understanding of their own aptitudes and to envision their future careers and dreams. It will also enable teachers and parents to provide specific support tailored to students' aptitudes.

[0543] The processing flow will be explained below.

[0544] Step 1:

[0545] The devices provide an interface for students to enter data about their athletic performance and interests, such as their weekly 100-meter sprint time or their favorite subjects and club activities, through a dedicated application.

[0546] Step 2:

[0547] The device sends the entered data to a server via the Internet, where it is temporarily stored and awaits processing for analysis.

[0548] Step 3:

[0549] The server validates the received data, detecting, for example, physically impossible 100-meter sprint times or incomplete survey responses, and verifies the accuracy of the data. Incorrect or incomplete data requires correction or re-entry.

[0550] Step 4:

[0551] The server preprocesses the validated data, specifically by standardizing numeric data and encoding categorical data. For example, it converts survey responses (favorite subject) into numerical values.

[0552] Step 5:

[0553] The server analyzes students' aptitudes based on the preprocessed data. It uses clustering algorithms and supervised learning algorithms to classify students' interests and abilities. For example, it divides students into clusters based on athletic ability and academic aptitude, and then selects career candidates based on each.

[0554] Step 6:

[0555] The server then generates a report for each student based on the analysis results. This report includes recommendations for multiple careers suitable for the student, along with the skills and related subjects required for those careers. For example, a student with strong athletic ability and good grades in math might be recommended a career such as "sports data analyst."

[0556] Step 7:

[0557] The terminal provides an interface for presenting the generated report to students, teachers, and parents. Users (students, teachers, and parents) can view and check the contents of the presented report. For example, this can be used to find out more information about a career that a student is interested in.

[0558] Step 8:

[0559] Users (students, teachers, and parents) can provide feedback on the report content through the terminal. For example, a student may be interested in the "Sports Data Analyst" section and enter additional questions or opinions about the topic.

[0560] Step 9:

[0561] The device sends the collected feedback to the server, where it is stored in a database for use in the re-evaluation process.

[0562] Step 10:

[0563] The server reevaluates and optimizes the analysis algorithm based on the feedback. For example, if a student's interests or trends change, or if many students show interest in a particular career, it will update the information and recommendations about that career. This reevaluation process improves the accuracy and effectiveness of the entire system.

[0564] Through these processing steps, the system supports students in choosing their future careers and enables educators to provide appropriate advice.

[0565] Example 1

[0566] 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."

[0567] In today's educational environment, students face the challenge of being unable to envision a specific future career based on their own interests and abilities. Therefore, there is a need for an effective support system to help students make appropriate career choices. However, traditional methods are problematic in that they are unable to flexibly accommodate students' diverse interests and abilities, and do not provide sufficient individualized advice.

[0568] 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.

[0569] In this invention, the server includes a means for collecting data on athletic performance and interests from students, a means for verifying and preprocessing the collected data, and a means for analyzing the aptitude of students based on the preprocessed data using a clustering algorithm or a supervised learning algorithm and selecting career candidates. This makes it possible to provide flexible and accurate career candidates based on each student's aptitude and interests, and to support career selection.

[0570] "Athletic performance" refers to data related to a student's physical ability, including, for example, 100-meter sprint times and physical fitness test results.

[0571] "Interests" refers to data about the areas and activities that students are interested in, such as their favorite subjects, club activities, and dreams for the future.

[0572] "Data Collection Means" refers to the interface for inputting and recording data from students regarding their athletic performance and interests and transmitting that data to the server.

[0573] "Data validation and pre-processing means" refers to a system for checking received data for errors and pre-processing the data, such as standardizing or encoding the data, if necessary.

[0574] "Clustering algorithm" refers to an algorithm for classifying students into groups with similar characteristics based on their athletic performance and interests.

[0575] "Supervised learning algorithms" refer to machine learning algorithms that use pre-labeled data to predict students' aptitudes and career prospects.

[0576] "Analysis means" refers to a system for assessing students' aptitude and selecting career candidates based on pre-processed data.

[0577] A "recommendation report" refers to a report generated based on the analysis results that lists suitable career options, required skills, and learning recommendations for each student.

[0578] "Feedback collection means" refers to an interface for collecting opinions and questions from users (students, educators, parents) regarding the generated reports.

[0579] "Algorithm re-evaluation and improvement measures" refers to a system for evaluating the performance of analysis algorithms and the overall system based on collected feedback and improving them as needed.

[0580] The present invention is a system for supporting students in choosing their future careers in an educational system. Specifically, the system collects and analyzes data on students' athletic performance and interests, and presents suitable career candidates. The system is composed of a data collection terminal, a data verification and preprocessing server, a data analysis server, a report generation server, a feedback collection terminal, and an algorithm reevaluation server.

[0581] Data collection

[0582] The devices provide an interface for students to input data about their athletic achievements and interests. For example, a dedicated application is provided, allowing students to input information about their 100-meter sprint time in gym class, their favorite subjects, and club activities. This data is then sent to a server via the Internet.

[0583] Data Validation and Preprocessing

[0584] The server validates the received data and checks for input errors (for example, checking that the 100-meter sprint time is not physically impossible or that the questionnaire is completely filled out). The server then preprocesses the validated data (for example, standardizing numeric data and encoding categorical data into numbers).

[0585] Data analysis

[0586] The server analyzes each student's aptitude based on the preprocessed data, using clustering and supervised learning algorithms to classify them into clusters based on their interests and abilities, and then lists suitable career candidates based on the results.

[0587] Report Generation

[0588] The server generates a recommendation report for each student based on the data analysis results. This report includes a list of suitable careers for the student, along with the skills and related learning and activities required. For example, a student with strong athletic ability and good math grades could be recommended a career such as "sports data analyst," along with specific study methods and workshop participation recommendations.

[0589] Feedback collection

[0590] The terminal provides an interface for presenting the generated recommendation report to students, educators, and parents. Users (students, educators, and parents) can view the report through the terminal and enter their opinions and questions. For example, if a student is interested in "sports data analyst" and wants more detailed information about the job, they can submit a question through the terminal.

[0591] Algorithm Reevaluation

[0592] The server collects feedback from the devices and reevaluates the performance of the analysis algorithm and the overall system. Based on this feedback, it creates and implements an improvement plan to optimize the content of the career candidate list and recommendation report. For example, if many students express interest in a particular career, it will provide more detailed information related to that career or add new related recommendations.

[0593] Specific examples

[0594] Example 1: Data collection

[0595] Using a dedicated app on a device, students enter their physical education records (for example, 100-meter sprint time) and interest questionnaires (favorite subjects, club activities, etc.) once a week.

[0596] The user (student) enters this information and the data is automatically sent to the server.

[0597] Example 2: Data validation and preprocessing

[0598] The server validates the received data to ensure there are no errors, for example, checking for anomalies in the 100-meter sprint time.

[0599] The server normalizes the data, for example encoding interest survey responses into numbers.

[0600] Example 3: Data analysis

[0601] The server generates an analysis result in which Student A is classified as "Athletic Ability Cluster: High" and "Mathematics Interest Cluster: Medium."

[0602] Example 4: Report Generation

[0603] The server recommends occupations such as "sports data analyst" or "sports instructor" to Student A. The report lists the necessary skills and learning recommendations.

[0604] Example 5: Feedback collection

[0605] The terminal presents the generated report to Student A, who then views the report and becomes interested in the "Sports Data Analyst."

[0606] Student A inputs a follow-up question through the terminal, for example, "How do I study the programming language required for this job?"

[0607] Example 6: Algorithm reevaluation

[0608] The server collects feedback from Student A and optimizes the analysis algorithm, and this process continuously improves the entire system.

[0609] Prompt Sentence Examples

[0610] By inputting the following prompt sentences into the generative AI model, an assistant function is provided to help the model specifically draw appropriate career candidates.

[0611] Example prompt:

[0612] "This student has good motor skills and an interest in mathematics. Please list suitable careers for him / her and recommend the necessary skills and related learning activities."

[0613] summary

[0614] This system will enable students to gain a deeper understanding of their own aptitudes and to concretely visualize their future careers and dreams, while also enabling educators and parents to provide specific support tailored to students' aptitudes.

[0615] The flow of the identification process in the first embodiment will be described with reference to FIG.

[0616] Step 1: Provide a data entry interface

[0617] The terminal provides an interface for students to input data about their athletic achievements and interests. Specifically, a form is displayed in which students can input information about their 100-meter sprint time, favorite subjects, and club activities via a dedicated application. The input data is information about the student's athletic achievements and interests. This data is received and sent to the server.

[0618] Step 2: Receiving and verifying data

[0619] The server receives the data sent from the device. It verifies the accuracy of the entered data, for example, checking that the 100-meter sprint time is not physically impossible or that a questionnaire is completely filled out. Incorrect or incomplete data generates an error message and sends it back to the device. The output of this step is the validated data.

[0620] Step 3: Data Preprocessing

[0621] The server preprocesses the validated data by standardizing numeric data and converting categorical data to numbers. For example, it might encode favorite subjects as "1: Math, 2: English, 3: Physical Education." This preprocessing generates standardized data that makes it easier for algorithms to understand the data. The input to this step is the validated data, and the output is the preprocessed data.

[0622] Step 4: Data analysis and clustering

[0623] The server analyzes each student's aptitude based on the preprocessed data. It uses clustering algorithms or supervised learning algorithms to classify students into clusters based on their characteristics. For example, it may classify students into a cluster with high athletic ability or a cluster with an interest in mathematics. The input of this step is the preprocessed data, and the output is the classification results of the clustered students.

[0624] Step 5: Selecting potential career candidates

[0625] The server selects suitable career candidates based on the clustered student data. It lists the careers associated with each cluster and recommends them to the student. In this step, a generative AI model is used to list careers that match the student's characteristics. For example, a student with high athletic ability and an interest in mathematics can be recommended a career such as "sports data analyst." The input to this step is the clustered classification results, and the output is a list of career candidates.

[0626] Step 6: Generate a recommendation report

[0627] The server generates a recommendation report for each student based on the career candidate list. This report includes recommended career candidates, the skills required for those careers, and recommendations for related learning and activities. The generated report is sent to the terminal. The input of this step is the career candidate list, and the output is the recommendation report.

[0628] Step 7: Gather feedback

[0629] The terminal provides an interface to present the generated recommendation report to students, educators, and parents. Users can view the report through the terminal and input their opinions or questions. For example, if a student wants more information about a "sports data analyst," he or she can submit a question through the terminal. The feedback is sent to the server. The input of this step is the recommendation report, and the output is the feedback information.

[0630] Step 8: Reevaluate and improve the algorithm

[0631] The server collects feedback sent from the devices and reevaluates the performance of the analysis algorithm and the entire system. Based on the collected feedback, it creates and implements an improvement plan to optimize the content of the career candidate list and recommendation report. For example, if many students express interest in "sports data analyst," it will strengthen the provision of information related to that career. The input of this step is feedback information, and the output is an optimized algorithm and an updated system.

[0632] By carrying out these specific processing steps in a detailed and orderly manner, it becomes possible to select a career and provide learning support based on each student's aptitude.

[0633] (Application example 1)

[0634] 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."

[0635] Currently, many students find it difficult to have a concrete image of their future dreams and careers. It is also difficult for teachers and parents to accurately grasp students' aptitudes and provide advice based on that. Furthermore, traditional career recommendation systems are based on static data analysis and lack the utilization of feedback and the delivery of educational and entertainment content. This prevents students from choosing a career that matches their aptitudes, making it difficult for them to set future goals.

[0636] 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.

[0637] In this invention, the server includes means for collecting data on athletic performance and interests from students, means for preprocessing and verifying the collected data, means for analyzing the aptitudes of students based on the preprocessed data and selecting career candidates, means for presenting generated reports to students, educators, and parents and collecting feedback, means for reevaluating and improving the analysis algorithm based on the collected feedback, and means for delivering educational and entertainment content related to the suggested careers. This allows students to understand career candidates based on their aptitudes and interests and to form a concrete image of them through the related content.

[0638] "Students" refers to children from the upper grades of elementary school to junior high school.

[0639] "Athletic performance" refers to the specific numerical data and evaluations recorded by students during physical education and club activities.

[0640] "Interest data" refers to survey results and information about students' favorite subjects, clubs, hobbies, and future interests.

[0641] A "clustering algorithm" is an analytical method for classifying data into multiple groups (clusters), and mainly uses the K-means method.

[0642] "Career suggestions" refer to specific occupations or career options suggested to students based on data analysis.

[0643] A "recommendation report" is a document that contains career options based on a student's aptitudes and interests, along with specific advice related to those careers.

[0644] "Feedback" refers to opinions, impressions, and questions provided by students, educators, and parents in response to the generated recommendation reports and proposals.

[0645] "Educational and entertainment content" refers to interactive materials such as videos, quizzes, and interviews that help students learn while having fun.

[0646] "Analysis algorithm" refers to a mathematical processing method for determining students' aptitude and selecting career candidates based on collected and pre-processed data.

[0647] MODE FOR CARRYING OUT THE INVENTION

[0648] This invention is a system for helping students concretely visualize their future dreams and careers. The system includes the steps of data collection, data preprocessing, data analysis, report generation, feedback collection, and content distribution.

[0649] Overall system configuration

[0650] The system consists of the following main components:

[0651] 1. Data collection terminal

[0652] 2. Data Validation and Preprocessing Server

[0653] 3. Data analysis server

[0654] 4. Report Generation Server

[0655] 5. Feedback collection terminal

[0656] 6. Algorithm Reevaluation Server

[0657] 7. Content Distribution Server

[0658] Technology used

[0659] Languages: Python, JavaScript

[0660] AI algorithms: clustering (K-means), supervised learning (SVM, Random Forest)

[0661] Database: Firebase

[0662] Front-end framework: React Native

[0663] Backend: Google Cloud Functions

[0664] Content delivery: AWS S3, CloudFront

[0665] Program processing

[0666] Data collection

[0667] Students enter information about their athletic achievements and interests through a smartphone application. For example, a questionnaire about their 100-meter sprint time in physical education class, their favorite subjects, and club activities is collected. This data is sent to Firebase via the Internet.

[0668] Examples:

[0669] Prompt: "What is your most recent 100-meter sprint time during gym class?"

[0670] Data Validation and Preprocessing

[0671] The server validates the received data and checks for input errors (for example, checking that the 100-meter sprint time is not physically impossible or that the questionnaire is completely filled out).The server then preprocesses the validated data, standardizing numeric data and encoding categorical data into numbers.

[0672] Data analysis

[0673] The data analysis server analyzes each student's aptitude based on the preprocessed data. The analysis mainly uses clustering algorithms (K-means) and supervised learning algorithms (SVM, Random Forest). This allows students to be classified into clusters based on their interests and abilities, and the results are used to create a list of suitable career candidates.

[0674] Examples:

[0675] Prompt: "Use a clustering algorithm to analyze the interests and abilities of all students and classify them into specific career clusters."

[0676] Report Generation

[0677] The report generation server generates a recommendation report for each student based on the data analysis results, which includes recommendations for suitable careers for the student, the necessary skills, and related learning and activities.

[0678] Feedback collection

[0679] The feedback collection terminal presents the generated recommendation report to students, educators, and parents. Users can view the report through the terminal and enter their opinions and questions. For example, if a student is interested in "sports data analyst" and wants more detailed information about the job, they can submit a question through the terminal.

[0680] Examples:

[0681] Prompt: "If you would like more information about the suggested jobs or have suggestions for improvement, please fill out the feedback form below."

[0682] Algorithm Reevaluation

[0683] The algorithm re-evaluation server collects feedback sent from the devices and re-evaluates the performance of the analysis algorithm and the entire system. Based on this feedback, it creates and implements an improvement plan to optimize the contents of the job candidate list and recommendation report.

[0684] Educational and entertainment content delivery

[0685] The content delivery server stores educational and entertainment content related to the proposed careers (e.g., videos, quizzes, interviews) in AWS S3 and uses CloudFront to deliver it to users at high speed.

[0686] Examples:

[0687] Prompt: "Watch educational videos related to sports data analysts."

[0688] This system allows students to understand potential careers based on their aptitudes and interests, and gives them a concrete image of what those careers could be through related content, allowing teachers and parents to provide specific support tailored to the students' aptitudes.

[0689] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[0690] System processing steps

[0691] Step 1: Data collection

[0692] The device provides an interface where students can input information about their athletic performance and interests. The input data is sent to Firebase. For example, a student can enter their 100-meter sprint time or favorite subject, and this data is immediately saved in the database. The input data (athletic performance, interest survey) is treated as output (data saved to Firebase) as is.

[0693] Step 2: Data validation and preprocessing

[0694] The server retrieves the data stored in Firebase and validates its contents. Specifically, it checks whether the 100-meter sprint time is within the physically possible range and whether all questions have been answered correctly. After confirming there are no errors, it then standardizes the numeric data and encodes the categorical data into numbers. It outputs the input data (student athletic performance and interest questionnaire) as validated data, which is then converted into preprocessed data.

[0695] Step 3: Data analysis

[0696] The data analysis server analyzes the preprocessed data using a clustering algorithm (K-means) and a supervised learning algorithm (SVM, Random Forest). This classifies students into clusters based on their interests and athletic performance, and lists corresponding career candidates. The input data (preprocessed data) is output as the analysis results (cluster classification and a list of career candidates).

[0697] Step 4: Generate a recommendation report

[0698] The report generation server generates a recommendation report containing suitable career candidates and details for each student based on the data analysis results. This report lists the recommended careers and the skills and learning methods required for those careers. For example, "For a student with high athletic ability and an interest in mathematics, we recommend a sports data analyst position and encourage learning related programming languages." The input data (analysis results) are output as a recommendation report.

[0699] Step 5: Gather feedback

[0700] The feedback collection terminal presents the generated recommendation report to students, educators, and parents. Users who view the report can enter their thoughts and questions in a feedback form. For example, if a student is interested in a "sports data analyst" and has a question about specific study methods, they can submit that question through the terminal. The input data (user feedback) is output as feedback.

[0701] Step 6: Reevaluate the algorithm

[0702] The algorithm re-evaluation server analyzes the collected feedback and re-evaluates the performance of the entire system. Based on this feedback, it makes improvements to optimize the analysis algorithm, career candidate list, and recommendation report content. For example, if many students express interest in a particular career, it adds detailed information and new recommendations related to that career. The input data (feedback) is output as an improved algorithm and career candidate list.

[0703] Step 7: Educational and Entertainment Content Distribution

[0704] The content delivery server provides educational and entertainment content (videos, quizzes, interviews, etc.) related to the recommended careers. For example, educational videos and interview videos about "sports data analyst" are stored in AWS S3 and delivered to users at high speed via CloudFront. The input data (career recommendations and related content) is output as delivery content.

[0705] This allows students to understand potential careers based on their aptitudes and interests, and form a concrete image of them through related content, while also enabling teachers and parents to provide specific support according to students' aptitudes.

[0706] 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.

[0707] This invention is a system to support students from the upper grades of elementary school to junior high school (hereinafter referred to as "students") in concretely envisioning their future dreams and careers. This system collects and analyzes data on students' athletic performance and interests, presents appropriate career options, and uses students' emotional data to improve the accuracy of the analysis.

[0708] Overall structure

[0709] The system consists of the following main components:

[0710] 1. Data collection terminal

[0711] 2. Data Validation and Preprocessing Server

[0712] 3. Data analysis server

[0713] 4. Report Generation Server

[0714] 5. Feedback collection terminal

[0715] 6. Algorithm Reevaluation Server

[0716] 7. Emotion Engine

[0717] Program processing

[0718] Data collection

[0719] The device provides an interface for students to input information about their athletic performance and interests. For example, a student can enter their weekly 100-meter sprint time or their favorite subjects and club activities through a dedicated application. At the same time, the device collects emotional data from the student's facial expressions and voice, which is also sent to the server.

[0720] Data Validation and Preprocessing

[0721] The server verifies the received data and checks for input errors. For example, it checks whether the 100-meter sprint time is physically impossible or whether the questionnaire is completely filled out. Incorrect or incomplete data requires correction or re-entry. At the same time, the emotion engine analyzes the collected emotion data and provides quantified emotion information to the server.

[0722] Data Preprocessing

[0723] The server preprocesses the validated data. Specifically, it standardizes numerical data and encodes categorical data. For example, it converts survey responses (favorite subject) into numerical values. At the same time, the server preprocesses sentiment data and integrates it with other data.

[0724] Data analysis

[0725] The server analyzes each student's aptitude based on the preprocessed data. It uses clustering and supervised learning algorithms to classify the student's interests and abilities. For example, students are divided into clusters based on athletic ability and academic aptitude, and career candidates are selected based on each. Emotional data is used as part of the analysis to reinforce interest levels.

[0726] Report Generation

[0727] The server generates a recommendation report for each student based on the data analysis results. This report includes multiple career options suitable for the student, along with recommendations for the skills and related subjects required. For example, a student with strong athletic ability and good math grades could be recommended a career such as "sports data analyst." At the same time, it utilizes emotional data to optimize the report content, taking into account the student's emotional interest in specific careers.

[0728] Feedback collection

[0729] The device provides an interface for presenting the generated report to students, teachers, and parents. Users (students, teachers, and parents) can view and confirm the contents of the presented report. For example, they can use it to find out more information about careers that students are interested in. At the same time, the device collects students' reactions and emotions using the emotion engine again and records them as feedback.

[0730] Feedback Reflected

[0731] Users (students, teachers, and parents) can provide feedback on the report content through the terminal. For example, a student may be interested in the "Sports Data Analyst" and enter additional questions or opinions about the report. At the same time, students' emotional data is also collected.

[0732] Algorithm Reevaluation

[0733] The server collects feedback and emotional data sent from the devices and reevaluates the performance of the analysis algorithm and the overall system. For example, if a student's emotional reaction to a particular occupation is positive, the system will be optimized to provide more detailed information about that occupation in the future, allowing it to provide more personalized advice to each individual student.

[0734] Specific examples

[0735] Example 1: Data collection

[0736] Using a dedicated app on a device, students enter their physical education records (for example, 100-meter sprint time) and interest questionnaires (favorite subjects, club activities, etc.) once a week.

[0737] At the same time, the device analyzes the students' facial expressions and voices using an emotion engine to collect emotional data.

[0738] Example 2: Data validation and preprocessing

[0739] The server validates the received data to ensure there are no errors, for example, checking for anomalies in the 100-meter sprint time.

[0740] The emotion engine analyzes the collected emotion data and provides the quantified results to the server.

[0741] Example 3: Data analysis

[0742] The server generates an analysis result in which Student A is classified as "Athletic Ability Cluster: High," "Mathematics Interest Cluster: Medium," and "Emotion Cluster: Positive."

[0743] Example 4: Report Generation

[0744] The server recommends occupations such as "sports data analyst" or "sports instructor" to Student A. The report lists the necessary skills and learning recommendations.

[0745] Based on the emotional data, we provide detailed information about the "sports data analyst" that Student A was particularly interested in.

[0746] Example 5: Feedback collection

[0747] The terminal presents the generated report to Student A, who then checks the report contents and becomes interested in the "Sports Data Analyst."

[0748] Student A's facial expressions and reactions are analyzed again by the emotion engine and saved as feedback data.

[0749] Example 6: Algorithm reevaluation

[0750] The server optimizes the analysis algorithm based on Student A's feedback and emotional data. This process will enable the server to provide more detailed and personalized recommendation reports in the future.

[0751] This system will enable students to gain a deeper understanding of their own characteristics and, taking into account their emotional reactions, to map out specific careers and dreams for the future, while also enabling teachers and parents to provide specific support tailored to students' aptitudes.

[0752] The processing flow will be explained below.

[0753] Step 1:

[0754] The device provides an interface for students to enter data about their athletic performance and interests. For example, using a dedicated application, students can enter their weekly 100-meter sprint time or their favorite subjects and club activities in a questionnaire. At the same time, the device uses an emotion engine to analyze the student's facial expressions and voice to collect emotional data.

[0755] Step 2:

[0756] The device transmits the collected athletic performance, interest questionnaire, and emotional data to a server via the Internet, where the data is temporarily stored and awaits further processing.

[0757] Step 3:

[0758] The server then verifies the received athletic performance and interest survey data, detecting, for example, physically impossible 100-meter sprint times or incomplete survey responses, and verifies the accuracy of the data. Any incorrect data is corrected or re-entered.

[0759] Step 4:

[0760] The emotion engine analyzes the collected emotion data and generates numerical emotion information (e.g., interest level or stress level), which is also sent to the server.

[0761] Step 5:

[0762] The server preprocesses the validated athletic performance and interest survey data by standardizing numeric data and encoding categorical data into numbers, e.g., by converting survey responses into consistent numeric values.

[0763] Step 6:

[0764] The server analyzes student aptitude based on the preprocessed data. Clustering and supervised learning algorithms are used to classify student interest and ability characteristics. Emotional data is also used as part of the analysis, taking into account the student's interest level and emotional tendencies.

[0765] Step 7:

[0766] The server generates a recommendation report for each student based on the analysis results, including recommendations for suitable careers, the skills required, and related subjects. Using emotional data, the report content is optimized to take into account the student's emotional interest in specific careers.

[0767] Step 8:

[0768] The terminal provides an interface for presenting the generated recommendation report to students, teachers, and parents. Users (students, teachers, and parents) can view the report through the terminal and check its contents.

[0769] Step 9:

[0770] Users (students, teachers, and parents) can provide feedback on the report content through the device. For example, a student can enter additional questions or opinions about a specific occupation. At the same time, the device analyzes the student's facial expressions and voice again using the emotion engine, collecting emotional data along with the feedback.

[0771] Step 10:

[0772] The device sends the collected feedback and emotion data to a server, where the feedback information is stored in a database and used for subsequent algorithm optimization processes.

[0773] Step 11:

[0774] The server reevaluates and optimizes the performance of the analysis algorithm and the entire system based on the collected feedback and sentiment data. For example, if many students show a high interest in a particular career, it will enrich the information related to that career or add new recommendations that incorporate the feedback.

[0775] This specific processing step allows students to receive career recommendations based on their aptitudes and interests, taking into account their emotional reactions, and also makes it easier for teachers and parents to provide appropriate advice to students.

[0776] Example 2

[0777] 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."

[0778] In recent years, the importance of supporting students in choosing their future careers has increased. However, simple aptitude tests and questionnaires alone have the problem of being unable to present career options that fully reflect students' interests and feelings. Furthermore, conventional systems do not adequately reflect feedback, making it difficult to respond to students' individual requests and changing interests. This presents a challenge, as students are unable to visualize a concrete future, making it difficult for educators and parents to provide appropriate guidance.

[0779] The specific processing by the specific processing unit 290 of the data processing device 12 in the second embodiment is realized by the following means.

[0780] In this invention, the server includes means for collecting data on athletic performance and interests from students, means for collecting and analyzing emotional data from students' facial expressions and voices, means for preprocessing and verifying the collected data, means for analyzing the students' aptitudes and selecting career candidates based on the preprocessed data, means for generating a recommendation report based on the analysis results, means for presenting the generated report to students, educators, and parents and collecting feedback, and means for reevaluating and improving the analysis algorithm based on the collected feedback. This makes it possible to present personalized career candidates that take students' emotions and feedback into consideration, allowing them to paint a more specific and appropriate picture of their future.

[0781] "Students" refers to students in the upper grades of elementary school to junior high school age groups.

[0782] "Athletic performance" refers to performance data such as times and scores recorded by students in physical education classes and sports activities.

[0783] "Interests" refers to information that shows a student's interests and preferences in their favorite subjects, club activities, hobbies, etc.

[0784] "Data collection" refers to the process of obtaining information from students about their athletic achievements and interests, including entering information through an application or interface.

[0785] "Emotional data" refers to information about emotions analyzed from students' facial expressions and voices, including data that quantifies emotional states such as joy, surprise, and interest.

[0786] "Data preprocessing" refers to processes such as standardization and encoding that prepare collected data into an analyzable format.

[0787] "Data verification" refers to the process of verifying that collected data is accurate and complete.

[0788] "Analytical algorithms" refer to mathematical methods and models used to classify students' aptitudes and select career candidates based on collected data.

[0789] A "clustering algorithm" refers to an analytical method for classifying data into multiple groups based on similarity.

[0790] A "recommendation report" is a document generated based on the analysis results that lists suitable career options, required skills, and related subject recommendations for students.

[0791] "Feedback" refers to the opinions and reactions provided by students, educators, and parents regarding the recommendation reports and system proposals.

[0792] "Algorithm re-evaluation" refers to the process of improving the performance and accuracy of analysis algorithms based on collected feedback.

[0793] This is a system that helps students from the upper grades of elementary school to junior high school (hereinafter referred to as "students") to concretely visualize their future dreams and careers. The system collects and analyzes data on students' athletic performance and interests, presents appropriate career options, and uses students' emotional data to improve the accuracy of the analysis.

[0794] Overall structure

[0795] The system consists of the following main components:

[0796] 1. Data collection terminal

[0797] 2. Data Validation and Preprocessing Server

[0798] 3. Data analysis server

[0799] 4. Report Generation Server

[0800] 5. Feedback collection terminal

[0801] 6. Algorithm Reevaluation Server

[0802] 7. Emotion Engine

[0803] Hardware and software used

[0804] Device: A smartphone, tablet, or computer running a dedicated application where students enter information.

[0805] Server: A central server for receiving, validating, analyzing, and generating reports on data, using generative AI models and clustering algorithms.

[0806] Emotion engine: Software that analyzes students' facial expressions and voices to generate emotional data.

[0807] Data collection

[0808] The device provides an interface for students to enter information about their athletic achievements and interests. For example, they may be asked to enter:

[0809] 100 meter sprint time once a week

[0810] Favorite subject

[0811] Club Activities

[0812] At the same time, the device collects the student's facial expressions and voice, and analyzes them using an emotion engine. For example, the device converts the student's facial expressions into numerical values ​​such as the degree of "happiness" or "interest," and sends the results to the server.

[0813] Data Validation and Preprocessing

[0814] The server validates the received data and checks for input errors. Any abnormal or incomplete data will be corrected or re-entered. For example, it checks to see if a 100-meter sprint time is a physically impossible value, such as "0 seconds" or "100 seconds."

[0815] The emotion data analyzed by the emotion engine is provided to the server as numerical information. The emotion data is provided in the following format, for example:

[0816] Delight level: 75

[0817] Surprise level: 30

[0818] These data are then combined with other input data and pre-processed for analysis: numerical data are standardized and categorical data are encoded.

[0819] Data analysis

[0820] The server analyzes each student's aptitude based on the preprocessed data. Clustering algorithms and supervised learning algorithms are used to classify the student's interests and abilities. For example, the server generates analysis results that classify Student A into "High athletic ability cluster," "Medium math interest cluster," and "Positive emotional cluster."

[0821] Report Generation

[0822] The server generates a recommendation report for each student based on the analysis results. This report lists suitable career candidates, the required skills, and recommendations for related subjects. For example, Student A may be recommended careers such as "sports data analyst" and "sports instructor," along with required skills (e.g., data analysis, communication) and recommended studies (e.g., statistics, information processing).

[0823] Feedback collection

[0824] The device provides an interface to present the generated report to students, educators, and parents. For example, if Student A is interested in "Sports Data Analyst," he or she can provide feedback such as "I'd like more detailed information." The student's reactions and emotions are also analyzed by the emotion engine and sent to the server.

[0825] Algorithm Reevaluation

[0826] The server collects feedback and emotional data sent from the devices and reevaluates the performance of the analysis algorithm and the overall system. For example, if students' emotional reactions to a particular occupation are positive, the system will be optimized to provide more detailed information about that occupation.

[0827] Specific examples

[0828] 1. Data collection: Student A uses a dedicated app to input "14.2 seconds for the 100-meter dash" and answer "Science is my favorite subject." At the same time, the student's facial expression is analyzed as "Delight level: 60" and sent to the server.

[0829] 2. Data validation and preprocessing: The server validates the received data and confirms that the 100-meter sprint time is correct as "14.2 seconds." The emotion engine converts the data into a numerical value, "Delight Level: 60," and provides it to the server.

[0830] 3. Data analysis: The server generates analysis results that classify Student A into "Athletic ability cluster: Medium," "Science interest cluster: High," and "Emotion cluster: Interested."

[0831] 4. Report Generation: The server generates a report recommending occupations such as "biologist" or "scientific researcher" to Student A. Required skills (e.g., laboratory techniques, data analysis) and recommended studies (e.g., biology, chemistry) are also listed.

[0832] 5. Feedback collection: The device presents the generated report to Student A, who provides feedback that he is “interested in scientific researchers.” The student’s facial expressions are analyzed again and sent to the server.

[0833] 6. Algorithm re-evaluation: The server will optimize the analysis algorithm based on Student A's feedback and emotional data, so that it can provide more detailed and personalized recommendation reports in the future.

[0834] This process allows students to envision specific careers and dreams, taking into account their own characteristics and emotional tendencies, and also allows educators and parents to efficiently provide support tailored to each student's aptitudes.

[0835] The flow of the identification process in the second embodiment will be described with reference to FIG.

[0836] The flow of this system's program processing

[0837] Step 1: Data collection

[0838] Device:

[0839] Input: Students use a dedicated application to input information about their athletic achievements (e.g., 100-meter sprint time) and interests (e.g., favorite subjects, club activities).

[0840] How it works: The application collects the student's facial expressions and voice and sends them to the emotion engine for analysis.

[0841] Output: The collected data (athletic performance, interest information, emotional data) is sent to the server.

[0842] Step 2: Data validation

[0843] server:

[0844] Input: Athletic performance, interest information, and emotional data sent from your device.

[0845] How it works: The server receives the data and checks whether the input values ​​are invalid or incorrect. For example, it checks whether the 100-meter sprint time is an abnormal value such as "0 seconds" or "100 seconds."

[0846] Output: Send the validated data to the preprocessing step. If the data is invalid, prompt the student to re-enter.

[0847] Step 3: Data Preprocessing

[0848] server:

[0849] Input: Verified athletic performance, interest information, and emotional data.

[0850] What it does: Normalize numerical data (e.g., convert 100-meter sprint times to standard scores), encode categorical data (e.g., convert favorite subjects to numbers), or integrate emotional data with other data.

[0851] Output: Send the preprocessed data to the analysis step.

[0852] Step 4: Data analysis

[0853] server:

[0854] Input: Preprocessed data.

[0855] How it works: Using clustering and supervised learning algorithms, we analyze the characteristics of students' interests and abilities, for example classifying them into motor skill clusters, high math interest clusters, and emotional clusters.

[0856] Output: Send the analysis results (classification of student aptitudes and interests) to the report generation step.

[0857] Step 5: Generate a report

[0858] server:

[0859] Input: Analysis results.

[0860] How it works: Based on the analysis results, a recommendation report is generated for the student, including suitable career options, required skills, and related subject recommendations. It also takes into account sentiment data and provides detailed information about careers that the student has expressed interest in.

[0861] Output: Send the generated recommendation report to the feedback collection terminal.

[0862] Step 6: Gather feedback

[0863] Device:

[0864] Input: The generated recommendation report.

[0865] What it does: Provides an interface to present reports to students, educators, and parents, and gathers feedback. Students can enter careers they're interested in, follow-up questions, etc.

[0866] Output: Send the collected feedback to the server.

[0867] Step 7: Reevaluate the algorithm

[0868] server:

[0869] Input: Feedback and emotion data.

[0870] How it works: Analyzes feedback and emotional data to optimize the analysis algorithm and system. For example, if a student's emotional reaction to a particular occupation is positive, the system will further enrich the information about that occupation.

[0871] Output: Prepare the data for further analysis and report generation using optimized analysis algorithms.

[0872] This system will enable personalized career suggestions that take into account students' feelings and feedback, allowing them to paint a more specific and appropriate picture of their future. It will also enable educators and parents to efficiently provide support that is tailored to students' aptitudes.

[0873] (Application example 2)

[0874] 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."

[0875] The present invention relates to a system that supports students in concretely envisioning their future dreams and careers, and aims to provide a system that can take into account not only athletic performance and interest data, but also emotional data. Conventional systems have had difficulty reflecting students' emotional interests, which has led to a problem of reduced accuracy in analyzing aptitude and selecting career candidates.

[0876] 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.

[0877] In this invention, the server includes a means for collecting data on athletic performance and interests from students, a means for preprocessing and verifying the collected data, and a means for analyzing the aptitude of students based on the preprocessed data and selecting career candidates, which enables emotional data to be integrated into the analysis result and optimize the recommendation report based on emotional interest levels.

[0878] "Students" refers to children from upper elementary school to junior high school.

[0879] "Athletic performance" refers to a student's physical education and athletic records and performance data.

[0880] "Interest data" refers to information such as the subjects and club activities that students are interested in.

[0881] "Data collection tools" refers to devices and software that provide an interface for collecting various data from students.

[0882] "Preprocessing" refers to the process of preparing collected data into a format that can be analyzed.

[0883] "Verification" refers to the process of checking and correcting errors or incompleteness in collected data.

[0884] "Data analysis" refers to the process of assessing students' aptitude based on collected and pre-processed data.

[0885] A "clustering algorithm" refers to a machine learning method for classifying data points into several groups (clusters).

[0886] "Career Candidates" refers to a list of occupations suggested to a student based on the results of the aptitude analysis.

[0887] "Recommendation Report" refers to a document or digital data that lists the results of a student's aptitude analysis and possible career options.

[0888] "Emotional Data" refers to emotional information obtained from a student's facial expressions, voice, and behavior.

[0889] An "emotion engine" refers to software or algorithms that analyze emotional data and generate quantified information.

[0890] "Feedback Collection Instrument" means any device or software used to present generated reports to students, educators, and parents and to collect their reactions and opinions.

[0891] "Analysis algorithm reevaluation" refers to the process of reviewing and improving the performance of data analysis algorithms based on collected feedback data.

[0892] "Optimization" refers to the process of improving the content and analytical algorithms of generated reports to make them more effective and efficient.

[0893] This invention is a system that helps students visualize their future dreams and careers by collecting and analyzing data on students' athletic performance, interests, and emotions, presenting appropriate career candidates, and reevaluating and improving the analysis algorithm based on feedback. The specific configuration and functions of this system are described below.

[0894] Overall structure

[0895] The system consists of the following main components:

[0896] 1. Data collection terminal

[0897] 2. Data Validation and Preprocessing Server

[0898] 3. Data analysis server

[0899] 4. Report Generation Server

[0900] 5. Feedback collection terminal

[0901] 6. Algorithm Reevaluation Server

[0902] 7. Emotion Engine

[0903] Program processing

[0904] Data collection

[0905] The device provides an interface for students to input information about their athletic performance and interests. For example, a student can enter their weekly 100-meter sprint time or their favorite subjects and club activities through a dedicated application. At the same time, the device collects emotional data from the student's facial expressions and voice, which is also sent to the server.

[0906] Data Validation and Preprocessing

[0907] The server verifies the received data and checks for input errors. For example, it checks whether the 100-meter sprint time is physically impossible or whether the questionnaire is completely filled out. Incorrect or incomplete data requires correction or re-entry. At the same time, the emotion engine analyzes the collected emotion data and provides quantified emotion information to the server.

[0908] Data analysis

[0909] The data analysis server analyzes each student's aptitude based on the preprocessed data. For example, it uses the k-means clustering algorithm to classify the student's athletic ability and interest characteristics. Emotional data is also used in the analysis to reinforce interest levels.

[0910] Report Generation

[0911] The report generation server generates a recommendation report for each student based on the data analysis results. This report includes multiple career options suitable for the student, along with recommendations for the skills and related subjects required for each. Using sentiment data, the report also includes detailed information about the careers that the student is particularly interested in.

[0912] Feedback collection

[0913] The feedback collection terminal provides an interface for presenting the generated reports to students, educators, and parents. Users can view and confirm the contents of the presented reports. For example, they can use the reports to find out more information about careers that students are interested in. At the same time, the terminal also collects students' facial expressions and reactions using the emotion engine and records them as feedback.

[0914] Algorithm Reevaluation

[0915] The server collects feedback and emotional data sent from the devices and reevaluates the performance of the analysis algorithm and the overall system. For example, if a student's emotional reaction to a particular occupation is positive, the system will be optimized to provide more detailed information about that occupation in the future, allowing it to provide more personalized advice to each individual student.

[0916] Hardware and software used

[0917] Hardware: Smartphones, server computers

[0918] Software: Python, Numpy, scikit-learn, dedicated applications

[0919] Adding specific examples

[0920] Example: Generate analysis results that classify Student A as "Athletic Ability Cluster: High," "Mathematics Interest Cluster: Medium," and "Emotion Cluster: Positive." The report recommends occupations such as "Sports Data Analyst" and "Sports Instructor," and lists the skills and learning recommendations related to those occupations. Detailed information about "Sports Data Analyst," in which Student A showed particular interest, is provided.

[0921] Prompt Sentence Examples

[0922] "Design data preprocessing and analysis algorithms for a system that collects students' athletic performance and interest data, classifies them using a clustering algorithm, and recommends suitable occupations. The generative AI model should include a procedure for compiling the clusters and recommended occupations into a report that is easy to understand for the student."

[0923] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[0924] Step 1:

[0925] Data collection

[0926] The device provides an interface for collecting data on athletic performance and interests from students. Specifically, students are asked to enter their 100-meter sprint times, favorite subjects, and club activities through a dedicated smartphone application once a week. The input data is stored in the device's internal memory. At the same time, the device also uses a camera and microphone to collect students' facial expressions and voice data, which is then saved as emotional data.

[0927] Input: Student athletic performance, interest survey data, facial expression and voice data

[0928] Output: Student data (athletic performance, interest data, emotional data)

[0929] Step 2:

[0930] Data Validation and Preprocessing

[0931] The server receives student data sent from the device and verifies it. During the verification process, it checks for physically impossible values ​​(e.g., a 100-meter sprint time of 0 seconds) and missing questionnaire entries. If the data is incomplete, the device is asked to re-enter it. The server then uses an emotion engine to quantify facial and voice data and convert it into an emotion score. It also standardizes and categorizes athletic performance and interest data.

[0932] Input: Student data (athletic performance, interest data, emotional data)

[0933] Output: Preprocessed data (standardized athletic performance, encoded interest data, emotion scores)

[0934] Step 3:

[0935] Data analysis

[0936] The data analysis server analyzes students' aptitudes based on the preprocessed data. During this process, a clustering algorithm (e.g., k-means) is used to cluster students based on their athletic ability, interests, and emotional characteristics. As a result of the clustering, students are classified into multiple aptitude clusters. At the same time, emotional data is integrated into the analysis results as the degree of interest.

[0937] Input: Preprocessed data (standardized motor performance, encoded interest data, emotion scores)

[0938] Output: Aptitude clusters (exercise clusters, interest clusters, emotion clusters)

[0939] Step 4:

[0940] Report Generation

[0941] The report generation server generates a recommendation report for each student based on the data analysis results. It selects career candidates for each cluster and provides detailed recommendations for the skills required and related subjects. It also uses emotional data to provide detailed information about careers that students are particularly interested in. The generated report is saved on the server.

[0942] Input: Aptitude cluster (exercise cluster, interest cluster, emotion cluster)

[0943] Output: Recommendation report (job candidates, required skills, learning recommendations)

[0944] Step 5:

[0945] Feedback collection

[0946] The feedback collection terminal presents the generated report to students, educators, and parents. Users can view the report contents and enter their opinions and questions about careers and study recommendations that students are interested in. The terminal also collects students' facial expressions and reactions, analyzes them using an emotion engine, and records them as feedback data.

[0947] Input: recommendation report, user responses (opinions, questions, facial expressions)

[0948] Output: Feedback data (user opinions, sentiment data)

[0949] Step 6:

[0950] Algorithm Reevaluation

[0951] The server collects and analyzes the feedback data sent from the devices and reevaluates the performance of the analysis algorithm. For example, if students have a high number of positive emotional reactions to a particular occupation, the system will optimize the algorithm to provide more detailed information about that occupation. This allows the system to provide more personalized advice to each student.

[0952] Input: Feedback data (user opinions, sentiment data)

[0953] Output: Improved analysis algorithm

[0954] 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.

[0955] 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.

[0956] 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.

[0957] [Third embodiment]

[0958] FIG. 5 shows an example of the configuration of a data processing system 310 according to the third embodiment.

[0959] 5, the data processing system 310 includes the data processing device 12 and a headset terminal 314. An example of the data processing device 12 is a server.

[0960] 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).

[0961] 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.

[0962] 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.

[0963] 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).

[0964] 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.

[0965] 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.

[0966] 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.

[0967] 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.

[0968] 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.

[0969] 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."

[0970] This is a system that helps students from the upper grades of elementary school to junior high school (hereinafter referred to as "students") to concretely visualize their future dreams and careers. The system aims to collect and analyze data on students' athletic performance and interests, and present appropriate career options.

[0971] Overall structure

[0972] The system consists of the following main components:

[0973] 1. Data collection terminal

[0974] 2. Data Validation and Preprocessing Server

[0975] 3. Data analysis server

[0976] 4. Report Generation Server

[0977] 5. Feedback collection terminal

[0978] 6. Algorithm Reevaluation Server

[0979] Program processing

[0980] Data collection

[0981] The device provides an interface for students to input information about their athletic achievements and interests. For example, an application can be provided to collect information such as their 100-meter sprint time in physical education class, or a questionnaire about their favorite subjects and extracurricular activities. The collected data is then sent to a server via the Internet.

[0982] Data Validation and Preprocessing

[0983] The server validates the received data and checks for input errors (for example, checking that the 100-meter sprint time is not physically impossible or that the questionnaire is completely filled out). The server then preprocesses the validated data (for example, standardizing numeric data and encoding categorical data into numbers).

[0984] Data analysis

[0985] The server analyzes each student's aptitude based on the preprocessed data, using clustering and supervised learning algorithms to classify them into clusters based on their interests and abilities, and then lists suitable career candidates based on the results.

[0986] Report Generation

[0987] The server generates a recommendation report for each student based on the data analysis results. This report includes a list of suitable careers for the student, along with the skills and related learning and activities required. For example, a student with strong athletic ability and good grades in mathematics may be recommended a career such as "sports data analyst," along with specific study methods and workshop participation recommendations.

[0988] Feedback collection

[0989] The terminal provides an interface for presenting the generated recommendation report to students, teachers, and parents. Users (students, teachers, and parents) can view the report through the terminal and enter their opinions and questions. For example, if a student is interested in "sports data analyst" and would like more detailed information about the job, they can send a question through the terminal.

[0990] Algorithm Reevaluation

[0991] The server collects feedback from the devices and reevaluates the performance of the analysis algorithm and the overall system. Based on this feedback, it creates and implements an improvement plan to optimize the content of the career candidate list and recommendation report. For example, if many students express interest in a particular career, it will provide more detailed information related to that career or add new related recommendations.

[0992] Specific examples

[0993] Example 1: Data collection

[0994] Using a dedicated app on a device, students enter their physical education records (for example, 100-meter sprint time) and interest questionnaires (favorite subjects, club activities, etc.) once a week.

[0995] The user (student) enters this information and the data is automatically sent to the server.

[0996] Example 2: Data validation and preprocessing

[0997] The server validates the received data to ensure there are no errors, for example, checking for anomalies in the 100-meter sprint time.

[0998] The server normalizes the data, for example encoding interest survey responses into numbers.

[0999] Example 3: Data analysis

[1000] The server generates an analysis result in which Student A is classified as "Athletic Ability Cluster: High" and "Mathematics Interest Cluster: Medium."

[1001] Example 4: Report Generation

[1002] The server recommends occupations such as "sports data analyst" or "sports instructor" to Student A. The report lists the necessary skills and learning recommendations.

[1003] Example 5: Feedback collection

[1004] The terminal presents the generated report to Student A, who then views the report and becomes interested in the "Sports Data Analyst."

[1005] Student A inputs a follow-up question through the terminal, for example, "How do I study the programming language required for this job?"

[1006] Example 6: Algorithm reevaluation

[1007] The server collects feedback from Student A and optimizes the analysis algorithm. This process continuously improves the entire system.

[1008] This system will enable students to gain a deeper understanding of their own aptitudes and to envision their future careers and dreams. It will also enable teachers and parents to provide specific support tailored to students' aptitudes.

[1009] The processing flow will be explained below.

[1010] Step 1:

[1011] The devices provide an interface for students to enter data about their athletic performance and interests, such as their weekly 100-meter sprint time or their favorite subjects and club activities, through a dedicated application.

[1012] Step 2:

[1013] The device sends the entered data to a server via the Internet, where it is temporarily stored and awaits processing for analysis.

[1014] Step 3:

[1015] The server validates the received data, detecting, for example, physically impossible 100-meter sprint times or incomplete survey responses, and verifies the accuracy of the data. Incorrect or incomplete data requires correction or re-entry.

[1016] Step 4:

[1017] The server preprocesses the validated data, specifically by standardizing numeric data and encoding categorical data. For example, it converts survey responses (favorite subject) into numerical values.

[1018] Step 5:

[1019] The server analyzes students' aptitudes based on the preprocessed data. It uses clustering algorithms and supervised learning algorithms to classify students' interests and abilities. For example, it divides students into clusters based on athletic ability and academic aptitude, and then selects career candidates based on each.

[1020] Step 6:

[1021] The server then generates a report for each student based on the analysis results. This report includes recommendations for multiple careers suitable for the student, along with the skills and related subjects required for those careers. For example, a student with strong athletic ability and good grades in math might be recommended a career such as "sports data analyst."

[1022] Step 7:

[1023] The terminal provides an interface for presenting the generated report to students, teachers, and parents. Users (students, teachers, and parents) can view and check the contents of the presented report. For example, this can be used to find out more information about a career that a student is interested in.

[1024] Step 8:

[1025] Users (students, teachers, and parents) can provide feedback on the report content through the terminal. For example, a student may be interested in the "Sports Data Analyst" section and enter additional questions or opinions about the topic.

[1026] Step 9:

[1027] The device sends the collected feedback to the server, where it is stored in a database for use in the re-evaluation process.

[1028] Step 10:

[1029] The server reevaluates and optimizes the analysis algorithm based on the feedback. For example, if a student's interests or trends change, or if many students show interest in a particular career, it will update the information and recommendations about that career. This reevaluation process improves the accuracy and effectiveness of the entire system.

[1030] Through these processing steps, the system supports students in choosing their future careers and enables educators to provide appropriate advice.

[1031] Example 1

[1032] 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."

[1033] In today's educational environment, students face the challenge of being unable to envision a specific future career based on their own interests and abilities. Therefore, there is a need for an effective support system to help students make appropriate career choices. However, traditional methods are problematic in that they are unable to flexibly accommodate students' diverse interests and abilities, and do not provide sufficient individualized advice.

[1034] 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.

[1035] In this invention, the server includes a means for collecting data on athletic performance and interests from students, a means for verifying and preprocessing the collected data, and a means for analyzing the aptitude of students based on the preprocessed data using a clustering algorithm or a supervised learning algorithm and selecting career candidates. This makes it possible to provide flexible and accurate career candidates based on each student's aptitude and interests, and to support career selection.

[1036] "Athletic performance" refers to data related to a student's physical ability, including, for example, 100-meter sprint times and physical fitness test results.

[1037] "Interests" refers to data about the areas and activities that students are interested in, such as their favorite subjects, club activities, and dreams for the future.

[1038] "Data Collection Means" refers to the interface for inputting and recording data from students regarding their athletic performance and interests and transmitting that data to the server.

[1039] "Data validation and pre-processing means" refers to a system for checking received data for errors and pre-processing the data, such as standardizing or encoding the data, if necessary.

[1040] "Clustering algorithm" refers to an algorithm for classifying students into groups with similar characteristics based on their athletic performance and interests.

[1041] "Supervised learning algorithms" refer to machine learning algorithms that use pre-labeled data to predict students' aptitudes and career prospects.

[1042] "Analysis means" refers to a system for assessing students' aptitude and selecting career candidates based on pre-processed data.

[1043] A "recommendation report" refers to a report generated based on the analysis results that lists suitable career options, required skills, and learning recommendations for each student.

[1044] "Feedback collection means" refers to an interface for collecting opinions and questions from users (students, educators, parents) regarding the generated reports.

[1045] "Algorithm re-evaluation and improvement measures" refers to a system for evaluating the performance of analysis algorithms and the overall system based on collected feedback and improving them as needed.

[1046] The present invention is a system for supporting students in choosing their future careers in an educational system. Specifically, the system collects and analyzes data on students' athletic performance and interests, and presents suitable career candidates. The system is composed of a data collection terminal, a data verification and preprocessing server, a data analysis server, a report generation server, a feedback collection terminal, and an algorithm reevaluation server.

[1047] Data collection

[1048] The devices provide an interface for students to input data about their athletic achievements and interests. For example, a dedicated application is provided, allowing students to input information about their 100-meter sprint time in gym class, their favorite subjects, and club activities. This data is then sent to a server via the Internet.

[1049] Data Validation and Preprocessing

[1050] The server validates the received data and checks for input errors (for example, checking that the 100-meter sprint time is not physically impossible or that the questionnaire is completely filled out). The server then preprocesses the validated data (for example, standardizing numeric data and encoding categorical data into numbers).

[1051] Data analysis

[1052] The server analyzes each student's aptitude based on the preprocessed data, using clustering and supervised learning algorithms to classify them into clusters based on their interests and abilities, and then lists suitable career candidates based on the results.

[1053] Report Generation

[1054] The server generates a recommendation report for each student based on the data analysis results. This report includes a list of suitable careers for the student, along with the skills and related learning and activities required. For example, a student with strong athletic ability and good math grades could be recommended a career such as "sports data analyst," along with specific study methods and workshop participation recommendations.

[1055] Feedback collection

[1056] The terminal provides an interface for presenting the generated recommendation report to students, educators, and parents. Users (students, educators, and parents) can view the report through the terminal and enter their opinions and questions. For example, if a student is interested in "sports data analyst" and wants more detailed information about the job, they can submit a question through the terminal.

[1057] Algorithm Reevaluation

[1058] The server collects feedback from the devices and reevaluates the performance of the analysis algorithm and the overall system. Based on this feedback, it creates and implements an improvement plan to optimize the content of the career candidate list and recommendation report. For example, if many students express interest in a particular career, it will provide more detailed information related to that career or add new related recommendations.

[1059] Specific examples

[1060] Example 1: Data collection

[1061] Using a dedicated app on a device, students enter their physical education records (for example, 100-meter sprint time) and interest questionnaires (favorite subjects, club activities, etc.) once a week.

[1062] The user (student) enters this information and the data is automatically sent to the server.

[1063] Example 2: Data validation and preprocessing

[1064] The server validates the received data to ensure there are no errors, for example, checking for anomalies in the 100-meter sprint time.

[1065] The server normalizes the data, for example encoding interest survey responses into numbers.

[1066] Example 3: Data analysis

[1067] The server generates an analysis result in which Student A is classified as "Athletic Ability Cluster: High" and "Mathematics Interest Cluster: Medium."

[1068] Example 4: Report Generation

[1069] The server recommends occupations such as "sports data analyst" or "sports instructor" to Student A. The report lists the necessary skills and learning recommendations.

[1070] Example 5: Feedback collection

[1071] The terminal presents the generated report to Student A, who then views the report and becomes interested in the "Sports Data Analyst."

[1072] Student A inputs a follow-up question through the terminal, for example, "How do I study the programming language required for this job?"

[1073] Example 6: Algorithm reevaluation

[1074] The server collects feedback from Student A and optimizes the analysis algorithm, and this process continuously improves the entire system.

[1075] Prompt Sentence Examples

[1076] By inputting the following prompt sentences into the generative AI model, an assistant function is provided to help the model specifically draw appropriate career candidates.

[1077] Example prompt:

[1078] "This student has good motor skills and an interest in mathematics. Please list suitable careers for him / her and recommend the necessary skills and related learning activities."

[1079] summary

[1080] This system will enable students to gain a deeper understanding of their own aptitudes and to concretely visualize their future careers and dreams, while also enabling educators and parents to provide specific support tailored to students' aptitudes.

[1081] The flow of the identification process in the first embodiment will be described with reference to FIG.

[1082] Step 1: Provide a data entry interface

[1083] The terminal provides an interface for students to input data about their athletic achievements and interests. Specifically, a form is displayed in which students can input information about their 100-meter sprint time, favorite subjects, and club activities via a dedicated application. The input data is information about the student's athletic achievements and interests. This data is received and sent to the server.

[1084] Step 2: Receiving and verifying data

[1085] The server receives the data sent from the device. It verifies the accuracy of the entered data, for example, checking that the 100-meter sprint time is not physically impossible or that a questionnaire is completely filled out. Incorrect or incomplete data generates an error message and sends it back to the device. The output of this step is the validated data.

[1086] Step 3: Data Preprocessing

[1087] The server preprocesses the validated data by standardizing numeric data and converting categorical data to numbers. For example, it might encode favorite subjects as "1: Math, 2: English, 3: Physical Education." This preprocessing generates standardized data that makes it easier for algorithms to understand the data. The input to this step is the validated data, and the output is the preprocessed data.

[1088] Step 4: Data analysis and clustering

[1089] The server analyzes each student's aptitude based on the preprocessed data. It uses clustering algorithms or supervised learning algorithms to classify students into clusters based on their characteristics. For example, it may classify students into a cluster with high athletic ability or a cluster with an interest in mathematics. The input of this step is the preprocessed data, and the output is the classification results of the clustered students.

[1090] Step 5: Selecting potential career candidates

[1091] The server selects suitable career candidates based on the clustered student data. It lists the careers associated with each cluster and recommends them to the student. In this step, a generative AI model is used to list careers that match the student's characteristics. For example, a student with high athletic ability and an interest in mathematics can be recommended a career such as "sports data analyst." The input to this step is the clustered classification results, and the output is a list of career candidates.

[1092] Step 6: Generate a recommendation report

[1093] The server generates a recommendation report for each student based on the career candidate list. This report includes recommended career candidates, the skills required for those careers, and recommendations for related learning and activities. The generated report is sent to the terminal. The input of this step is the career candidate list, and the output is the recommendation report.

[1094] Step 7: Gather feedback

[1095] The terminal provides an interface to present the generated recommendation report to students, educators, and parents. Users can view the report through the terminal and input their opinions or questions. For example, if a student wants more information about a "sports data analyst," he or she can submit a question through the terminal. The feedback is sent to the server. The input of this step is the recommendation report, and the output is the feedback information.

[1096] Step 8: Reevaluate and improve the algorithm

[1097] The server collects feedback sent from the devices and reevaluates the performance of the analysis algorithm and the entire system. Based on the collected feedback, it creates and implements an improvement plan to optimize the content of the career candidate list and recommendation report. For example, if many students express interest in "sports data analyst," it will strengthen the provision of information related to that career. The input of this step is feedback information, and the output is an optimized algorithm and an updated system.

[1098] By carrying out these specific processing steps in a detailed and orderly manner, it becomes possible to select a career and provide learning support based on each student's aptitude.

[1099] (Application example 1)

[1100] 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."

[1101] Currently, many students find it difficult to have a concrete image of their future dreams and careers. It is also difficult for teachers and parents to accurately grasp students' aptitudes and provide advice based on that. Furthermore, traditional career recommendation systems are based on static data analysis and lack the utilization of feedback and the delivery of educational and entertainment content. This prevents students from choosing a career that matches their aptitudes, making it difficult for them to set future goals.

[1102] 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.

[1103] In this invention, the server includes means for collecting data on athletic performance and interests from students, means for preprocessing and verifying the collected data, means for analyzing the aptitudes of students based on the preprocessed data and selecting career candidates, means for presenting generated reports to students, educators, and parents and collecting feedback, means for reevaluating and improving the analysis algorithm based on the collected feedback, and means for delivering educational and entertainment content related to the suggested careers. This allows students to understand career candidates based on their aptitudes and interests and to form a concrete image of them through the related content.

[1104] "Students" refers to children from the upper grades of elementary school to junior high school.

[1105] "Athletic performance" refers to the specific numerical data and evaluations recorded by students during physical education and club activities.

[1106] "Interest data" refers to survey results and information about students' favorite subjects, clubs, hobbies, and future interests.

[1107] A "clustering algorithm" is an analytical method for classifying data into multiple groups (clusters), and mainly uses the K-means method.

[1108] "Career suggestions" refer to specific occupations or career options suggested to students based on data analysis.

[1109] A "recommendation report" is a document that contains career options based on a student's aptitudes and interests, along with specific advice related to those careers.

[1110] "Feedback" refers to opinions, impressions, and questions provided by students, educators, and parents in response to the generated recommendation reports and proposals.

[1111] "Educational and entertainment content" refers to interactive materials such as videos, quizzes, and interviews that help students learn while having fun.

[1112] "Analysis algorithm" refers to a mathematical processing method for determining students' aptitude and selecting career candidates based on collected and pre-processed data.

[1113] MODE FOR CARRYING OUT THE INVENTION

[1114] This invention is a system for helping students concretely visualize their future dreams and careers. The system includes the steps of data collection, data preprocessing, data analysis, report generation, feedback collection, and content distribution.

[1115] Overall system configuration

[1116] The system consists of the following main components:

[1117] 1. Data collection terminal

[1118] 2. Data Validation and Preprocessing Server

[1119] 3. Data analysis server

[1120] 4. Report Generation Server

[1121] 5. Feedback collection terminal

[1122] 6. Algorithm Reevaluation Server

[1123] 7. Content Distribution Server

[1124] Technology used

[1125] Languages: Python, JavaScript

[1126] AI algorithms: clustering (K-means), supervised learning (SVM, Random Forest)

[1127] Database: Firebase

[1128] Front-end framework: React Native

[1129] Backend: Google Cloud Functions

[1130] Content delivery: AWS S3, CloudFront

[1131] Program processing

[1132] Data collection

[1133] Students enter information about their athletic achievements and interests through a smartphone application. For example, a questionnaire about their 100-meter sprint time in physical education class, their favorite subjects, and club activities is collected. This data is sent to Firebase via the Internet.

[1134] Examples:

[1135] Prompt: "What is your most recent 100-meter sprint time during gym class?"

[1136] Data Validation and Preprocessing

[1137] The server validates the received data and checks for input errors (for example, checking that the 100-meter sprint time is not physically impossible or that the questionnaire is completely filled out).The server then preprocesses the validated data, standardizing numeric data and encoding categorical data into numbers.

[1138] Data analysis

[1139] The data analysis server analyzes each student's aptitude based on the preprocessed data. The analysis mainly uses clustering algorithms (K-means) and supervised learning algorithms (SVM, Random Forest). This allows students to be classified into clusters based on their interests and abilities, and the results are used to create a list of suitable career candidates.

[1140] Examples:

[1141] Prompt: "Use a clustering algorithm to analyze the interests and abilities of all students and classify them into specific career clusters."

[1142] Report Generation

[1143] The report generation server generates a recommendation report for each student based on the data analysis results, which includes recommendations for suitable careers for the student, the necessary skills, and related learning and activities.

[1144] Feedback collection

[1145] The feedback collection terminal presents the generated recommendation report to students, educators, and parents. Users can view the report through the terminal and enter their opinions and questions. For example, if a student is interested in "sports data analyst" and wants more detailed information about the job, they can submit a question through the terminal.

[1146] Examples:

[1147] Prompt: "If you would like more information about the suggested jobs or have suggestions for improvement, please fill out the feedback form below."

[1148] Algorithm Reevaluation

[1149] The algorithm re-evaluation server collects feedback sent from the devices and re-evaluates the performance of the analysis algorithm and the entire system. Based on this feedback, it creates and implements an improvement plan to optimize the contents of the job candidate list and recommendation report.

[1150] Educational and entertainment content delivery

[1151] The content delivery server stores educational and entertainment content related to the proposed careers (e.g., videos, quizzes, interviews) in AWS S3 and uses CloudFront to deliver it to users at high speed.

[1152] Examples:

[1153] Prompt: "Watch educational videos related to sports data analysts."

[1154] This system allows students to understand potential careers based on their aptitudes and interests, and gives them a concrete image of what those careers could be through related content, allowing teachers and parents to provide specific support tailored to the students' aptitudes.

[1155] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[1156] System processing steps

[1157] Step 1: Data collection

[1158] The device provides an interface where students can input information about their athletic performance and interests. The input data is sent to Firebase. For example, a student can enter their 100-meter sprint time or favorite subject, and this data is immediately saved in the database. The input data (athletic performance, interest survey) is treated as output (data saved to Firebase) as is.

[1159] Step 2: Data validation and preprocessing

[1160] The server retrieves the data stored in Firebase and validates its contents. Specifically, it checks whether the 100-meter sprint time is within the physically possible range and whether all questions have been answered correctly. After confirming there are no errors, it then standardizes the numeric data and encodes the categorical data into numbers. It outputs the input data (student athletic performance and interest questionnaire) as validated data, which is then converted into preprocessed data.

[1161] Step 3: Data analysis

[1162] The data analysis server analyzes the preprocessed data using a clustering algorithm (K-means) and a supervised learning algorithm (SVM, Random Forest). This classifies students into clusters based on their interests and athletic performance, and lists corresponding career candidates. The input data (preprocessed data) is output as the analysis results (cluster classification and a list of career candidates).

[1163] Step 4: Generate a recommendation report

[1164] The report generation server generates a recommendation report containing suitable career candidates and details for each student based on the data analysis results. This report lists the recommended careers and the skills and learning methods required for those careers. For example, "For a student with high athletic ability and an interest in mathematics, we recommend a sports data analyst position and encourage learning related programming languages." The input data (analysis results) are output as a recommendation report.

[1165] Step 5: Gather feedback

[1166] The feedback collection terminal presents the generated recommendation report to students, educators, and parents. Users who view the report can enter their thoughts and questions in a feedback form. For example, if a student is interested in a "sports data analyst" and has a question about specific study methods, they can submit that question through the terminal. The input data (user feedback) is output as feedback.

[1167] Step 6: Reevaluate the algorithm

[1168] The algorithm re-evaluation server analyzes the collected feedback and re-evaluates the performance of the entire system. Based on this feedback, it makes improvements to optimize the analysis algorithm, career candidate list, and recommendation report content. For example, if many students express interest in a particular career, it adds detailed information and new recommendations related to that career. The input data (feedback) is output as an improved algorithm and career candidate list.

[1169] Step 7: Educational and Entertainment Content Distribution

[1170] The content delivery server provides educational and entertainment content (videos, quizzes, interviews, etc.) related to the recommended careers. For example, educational videos and interview videos about "sports data analyst" are stored in AWS S3 and delivered to users at high speed via CloudFront. The input data (career recommendations and related content) is output as delivery content.

[1171] This allows students to understand potential careers based on their aptitudes and interests, and form a concrete image of them through related content, while also enabling teachers and parents to provide specific support according to students' aptitudes.

[1172] 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.

[1173] This invention is a system to support students from the upper grades of elementary school to junior high school (hereinafter referred to as "students") in concretely envisioning their future dreams and careers. This system collects and analyzes data on students' athletic performance and interests, presents appropriate career options, and uses students' emotional data to improve the accuracy of the analysis.

[1174] Overall structure

[1175] The system consists of the following main components:

[1176] 1. Data collection terminal

[1177] 2. Data Validation and Preprocessing Server

[1178] 3. Data analysis server

[1179] 4. Report Generation Server

[1180] 5. Feedback collection terminal

[1181] 6. Algorithm Reevaluation Server

[1182] 7. Emotion Engine

[1183] Program processing

[1184] Data collection

[1185] The device provides an interface for students to input information about their athletic performance and interests. For example, a student can enter their weekly 100-meter sprint time or their favorite subjects and club activities through a dedicated application. At the same time, the device collects emotional data from the student's facial expressions and voice, which is also sent to the server.

[1186] Data Validation and Preprocessing

[1187] The server verifies the received data and checks for input errors. For example, it checks whether the 100-meter sprint time is physically impossible or whether the questionnaire is completely filled out. Incorrect or incomplete data requires correction or re-entry. At the same time, the emotion engine analyzes the collected emotion data and provides quantified emotion information to the server.

[1188] Data Preprocessing

[1189] The server preprocesses the validated data. Specifically, it standardizes numerical data and encodes categorical data. For example, it converts survey responses (favorite subject) into numerical values. At the same time, the server preprocesses sentiment data and integrates it with other data.

[1190] Data analysis

[1191] The server analyzes each student's aptitude based on the preprocessed data. It uses clustering and supervised learning algorithms to classify the student's interests and abilities. For example, students are divided into clusters based on athletic ability and academic aptitude, and career candidates are selected based on each. Emotional data is used as part of the analysis to reinforce interest levels.

[1192] Report Generation

[1193] The server generates a recommendation report for each student based on the data analysis results. This report includes multiple career options suitable for the student, along with recommendations for the skills and related subjects required. For example, a student with strong athletic ability and good math grades could be recommended a career such as "sports data analyst." At the same time, it utilizes emotional data to optimize the report content, taking into account the student's emotional interest in specific careers.

[1194] Feedback collection

[1195] The device provides an interface for presenting the generated report to students, teachers, and parents. Users (students, teachers, and parents) can view and confirm the contents of the presented report. For example, they can use it to find out more information about careers that students are interested in. At the same time, the device collects students' reactions and emotions using the emotion engine again and records them as feedback.

[1196] Feedback Reflected

[1197] Users (students, teachers, and parents) can provide feedback on the report content through the terminal. For example, a student may be interested in the "Sports Data Analyst" and enter additional questions or opinions about the report. At the same time, students' emotional data is also collected.

[1198] Algorithm Reevaluation

[1199] The server collects feedback and emotional data sent from the devices and reevaluates the performance of the analysis algorithm and the overall system. For example, if a student's emotional reaction to a particular occupation is positive, the system will be optimized to provide more detailed information about that occupation in the future, allowing it to provide more personalized advice to each individual student.

[1200] Specific examples

[1201] Example 1: Data collection

[1202] Using a dedicated app on a device, students enter their physical education records (for example, 100-meter sprint time) and interest questionnaires (favorite subjects, club activities, etc.) once a week.

[1203] At the same time, the device analyzes the students' facial expressions and voices using an emotion engine to collect emotional data.

[1204] Example 2: Data validation and preprocessing

[1205] The server validates the received data to ensure there are no errors, for example, checking for anomalies in the 100-meter sprint time.

[1206] The emotion engine analyzes the collected emotion data and provides the quantified results to the server.

[1207] Example 3: Data analysis

[1208] The server generates an analysis result in which Student A is classified as "Athletic Ability Cluster: High," "Mathematics Interest Cluster: Medium," and "Emotion Cluster: Positive."

[1209] Example 4: Report Generation

[1210] The server recommends occupations such as "sports data analyst" or "sports instructor" to Student A. The report lists the necessary skills and learning recommendations.

[1211] Based on the emotional data, we provide detailed information about the "sports data analyst" that Student A was particularly interested in.

[1212] Example 5: Feedback collection

[1213] The terminal presents the generated report to Student A, who then checks the report contents and becomes interested in the "Sports Data Analyst."

[1214] Student A's facial expressions and reactions are analyzed again by the emotion engine and saved as feedback data.

[1215] Example 6: Algorithm reevaluation

[1216] The server optimizes the analysis algorithm based on Student A's feedback and emotional data. This process will enable the server to provide more detailed and personalized recommendation reports in the future.

[1217] This system will enable students to gain a deeper understanding of their own characteristics and, taking into account their emotional reactions, to map out specific careers and dreams for the future, while also enabling teachers and parents to provide specific support tailored to students' aptitudes.

[1218] The processing flow will be explained below.

[1219] Step 1:

[1220] The device provides an interface for students to enter data about their athletic performance and interests. For example, using a dedicated application, students can enter their weekly 100-meter sprint time or their favorite subjects and club activities in a questionnaire. At the same time, the device uses an emotion engine to analyze the student's facial expressions and voice to collect emotional data.

[1221] Step 2:

[1222] The device transmits the collected athletic performance, interest questionnaire, and emotional data to a server via the Internet, where the data is temporarily stored and awaits further processing.

[1223] Step 3:

[1224] The server then verifies the received athletic performance and interest survey data, detecting, for example, physically impossible 100-meter sprint times or incomplete survey responses, and verifies the accuracy of the data. Any incorrect data is corrected or re-entered.

[1225] Step 4:

[1226] The emotion engine analyzes the collected emotion data and generates numerical emotion information (e.g., interest level or stress level), which is also sent to the server.

[1227] Step 5:

[1228] The server preprocesses the validated athletic performance and interest survey data by standardizing numeric data and encoding categorical data into numbers, e.g., by converting survey responses into consistent numeric values.

[1229] Step 6:

[1230] The server analyzes student aptitude based on the preprocessed data. Clustering and supervised learning algorithms are used to classify student interest and ability characteristics. Emotional data is also used as part of the analysis, taking into account the student's interest level and emotional tendencies.

[1231] Step 7:

[1232] The server generates a recommendation report for each student based on the analysis results, including recommendations for suitable careers, the skills required, and related subjects. Using emotional data, the report content is optimized to take into account the student's emotional interest in specific careers.

[1233] Step 8:

[1234] The terminal provides an interface for presenting the generated recommendation report to students, teachers, and parents. Users (students, teachers, and parents) can view the report through the terminal and check its contents.

[1235] Step 9:

[1236] Users (students, teachers, and parents) can provide feedback on the report content through the device. For example, a student can enter additional questions or opinions about a specific occupation. At the same time, the device analyzes the student's facial expressions and voice again using the emotion engine, collecting emotional data along with the feedback.

[1237] Step 10:

[1238] The device sends the collected feedback and emotion data to a server, where the feedback information is stored in a database and used for subsequent algorithm optimization processes.

[1239] Step 11:

[1240] The server reevaluates and optimizes the performance of the analysis algorithm and the entire system based on the collected feedback and sentiment data. For example, if many students show a high interest in a particular career, it will enrich the information related to that career or add new recommendations that incorporate the feedback.

[1241] This specific processing step allows students to receive career recommendations based on their aptitudes and interests, taking into account their emotional reactions, and also makes it easier for teachers and parents to provide appropriate advice to students.

[1242] Example 2

[1243] 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."

[1244] In recent years, the importance of supporting students in choosing their future careers has increased. However, simple aptitude tests and questionnaires alone have the problem of being unable to present career options that fully reflect students' interests and feelings. Furthermore, conventional systems do not adequately reflect feedback, making it difficult to respond to students' individual requests and changing interests. This presents a challenge, as students are unable to visualize a concrete future, making it difficult for educators and parents to provide appropriate guidance.

[1245] The specific processing by the specific processing unit 290 of the data processing device 12 in the second embodiment is realized by the following means.

[1246] In this invention, the server includes means for collecting data on athletic performance and interests from students, means for collecting and analyzing emotional data from students' facial expressions and voices, means for preprocessing and verifying the collected data, means for analyzing the students' aptitudes and selecting career candidates based on the preprocessed data, means for generating a recommendation report based on the analysis results, means for presenting the generated report to students, educators, and parents and collecting feedback, and means for reevaluating and improving the analysis algorithm based on the collected feedback. This makes it possible to present personalized career candidates that take students' emotions and feedback into consideration, allowing them to paint a more specific and appropriate picture of their future.

[1247] "Students" refers to students in the upper grades of elementary school to junior high school age groups.

[1248] "Athletic performance" refers to performance data such as times and scores recorded by students in physical education classes and sports activities.

[1249] "Interests" refers to information that shows a student's interests and preferences in their favorite subjects, club activities, hobbies, etc.

[1250] "Data collection" refers to the process of obtaining information from students about their athletic achievements and interests, including entering information through an application or interface.

[1251] "Emotional data" refers to information about emotions analyzed from students' facial expressions and voices, including data that quantifies emotional states such as joy, surprise, and interest.

[1252] "Data preprocessing" refers to processes such as standardization and encoding that prepare collected data into an analyzable format.

[1253] "Data verification" refers to the process of verifying that collected data is accurate and complete.

[1254] "Analytical algorithms" refer to mathematical methods and models used to classify students' aptitudes and select career candidates based on collected data.

[1255] A "clustering algorithm" refers to an analytical method for classifying data into multiple groups based on similarity.

[1256] A "recommendation report" is a document generated based on the analysis results that lists suitable career options, required skills, and related subject recommendations for students.

[1257] "Feedback" refers to the opinions and reactions provided by students, educators, and parents regarding the recommendation reports and system proposals.

[1258] "Algorithm re-evaluation" refers to the process of improving the performance and accuracy of analysis algorithms based on collected feedback.

[1259] This is a system that helps students from the upper grades of elementary school to junior high school (hereinafter referred to as "students") to concretely visualize their future dreams and careers. The system collects and analyzes data on students' athletic performance and interests, presents appropriate career options, and uses students' emotional data to improve the accuracy of the analysis.

[1260] Overall structure

[1261] The system consists of the following main components:

[1262] 1. Data collection terminal

[1263] 2. Data Validation and Preprocessing Server

[1264] 3. Data analysis server

[1265] 4. Report Generation Server

[1266] 5. Feedback collection terminal

[1267] 6. Algorithm Reevaluation Server

[1268] 7. Emotion Engine

[1269] Hardware and software used

[1270] Device: A smartphone, tablet, or computer running a dedicated application where students enter information.

[1271] Server: A central server for receiving, validating, analyzing, and generating reports on data, using generative AI models and clustering algorithms.

[1272] Emotion engine: Software that analyzes students' facial expressions and voices to generate emotional data.

[1273] Data collection

[1274] The device provides an interface for students to enter information about their athletic achievements and interests. For example, they may be asked to enter:

[1275] 100 meter sprint time once a week

[1276] Favorite subject

[1277] Club Activities

[1278] At the same time, the device collects the student's facial expressions and voice, and analyzes them using an emotion engine. For example, the device converts the student's facial expressions into numerical values ​​such as the degree of "happiness" or "interest," and sends the results to the server.

[1279] Data Validation and Preprocessing

[1280] The server validates the received data and checks for input errors. Any abnormal or incomplete data will be corrected or re-entered. For example, it checks to see if a 100-meter sprint time is a physically impossible value, such as "0 seconds" or "100 seconds."

[1281] The emotion data analyzed by the emotion engine is provided to the server as numerical information. The emotion data is provided in the following format, for example:

[1282] Delight level: 75

[1283] Surprise level: 30

[1284] These data are then combined with other input data and pre-processed for analysis: numerical data are standardized and categorical data are encoded.

[1285] Data analysis

[1286] The server analyzes each student's aptitude based on the preprocessed data. Clustering algorithms and supervised learning algorithms are used to classify the student's interests and abilities. For example, the server generates analysis results that classify Student A into "High athletic ability cluster," "Medium math interest cluster," and "Positive emotional cluster."

[1287] Report Generation

[1288] The server generates a recommendation report for each student based on the analysis results. This report lists suitable career candidates, the required skills, and recommendations for related subjects. For example, Student A may be recommended careers such as "sports data analyst" and "sports instructor," along with required skills (e.g., data analysis, communication) and recommended studies (e.g., statistics, information processing).

[1289] Feedback collection

[1290] The device provides an interface to present the generated report to students, educators, and parents. For example, if Student A is interested in "Sports Data Analyst," he or she can provide feedback such as "I'd like more detailed information." The student's reactions and emotions are also analyzed by the emotion engine and sent to the server.

[1291] Algorithm Reevaluation

[1292] The server collects feedback and emotional data sent from the devices and reevaluates the performance of the analysis algorithm and the overall system. For example, if students' emotional reactions to a particular occupation are positive, the system will be optimized to provide more detailed information about that occupation.

[1293] Specific examples

[1294] 1. Data collection: Student A uses a dedicated app to input "14.2 seconds for the 100-meter dash" and answer "Science is my favorite subject." At the same time, the student's facial expression is analyzed as "Delight level: 60" and sent to the server.

[1295] 2. Data validation and preprocessing: The server validates the received data and confirms that the 100-meter sprint time is correct as "14.2 seconds." The emotion engine converts the data into a numerical value, "Delight Level: 60," and provides it to the server.

[1296] 3. Data analysis: The server generates analysis results that classify Student A into "Athletic ability cluster: Medium," "Science interest cluster: High," and "Emotion cluster: Interested."

[1297] 4. Report Generation: The server generates a report recommending occupations such as "biologist" or "scientific researcher" to Student A. Required skills (e.g., laboratory techniques, data analysis) and recommended studies (e.g., biology, chemistry) are also listed.

[1298] 5. Feedback collection: The device presents the generated report to Student A, who provides feedback that he is “interested in scientific researchers.” The student’s facial expressions are analyzed again and sent to the server.

[1299] 6. Algorithm re-evaluation: The server will optimize the analysis algorithm based on Student A's feedback and emotional data, so that it can provide more detailed and personalized recommendation reports in the future.

[1300] This process allows students to envision specific careers and dreams, taking into account their own characteristics and emotional tendencies, and also allows educators and parents to efficiently provide support tailored to each student's aptitudes.

[1301] The flow of the identification process in the second embodiment will be described with reference to FIG.

[1302] The flow of this system's program processing

[1303] Step 1: Data collection

[1304] Device:

[1305] Input: Students use a dedicated application to input information about their athletic achievements (e.g., 100-meter sprint time) and interests (e.g., favorite subjects, club activities).

[1306] How it works: The application collects the student's facial expressions and voice and sends them to the emotion engine for analysis.

[1307] Output: The collected data (athletic performance, interest information, emotional data) is sent to the server.

[1308] Step 2: Data validation

[1309] server:

[1310] Input: Athletic performance, interest information, and emotional data sent from your device.

[1311] How it works: The server receives the data and checks whether the input values ​​are invalid or incorrect. For example, it checks whether the 100-meter sprint time is an abnormal value such as "0 seconds" or "100 seconds."

[1312] Output: Send the validated data to the preprocessing step. If the data is invalid, prompt the student to re-enter.

[1313] Step 3: Data Preprocessing

[1314] server:

[1315] Input: Verified athletic performance, interest information, and emotional data.

[1316] What it does: Normalize numerical data (e.g., convert 100-meter sprint times to standard scores), encode categorical data (e.g., convert favorite subjects to numbers), or integrate emotional data with other data.

[1317] Output: Send the preprocessed data to the analysis step.

[1318] Step 4: Data analysis

[1319] server:

[1320] Input: Preprocessed data.

[1321] How it works: Using clustering and supervised learning algorithms, we analyze the characteristics of students' interests and abilities, for example classifying them into motor skill clusters, high math interest clusters, and emotional clusters.

[1322] Output: Send the analysis results (classification of student aptitudes and interests) to the report generation step.

[1323] Step 5: Generate a report

[1324] server:

[1325] Input: Analysis results.

[1326] How it works: Based on the analysis results, a recommendation report is generated for the student, including suitable career options, required skills, and related subject recommendations. It also takes into account sentiment data and provides detailed information about careers that the student has expressed interest in.

[1327] Output: Send the generated recommendation report to the feedback collection terminal.

[1328] Step 6: Gather feedback

[1329] Device:

[1330] Input: The generated recommendation report.

[1331] What it does: Provides an interface to present reports to students, educators, and parents, and gathers feedback. Students can enter careers they're interested in, follow-up questions, etc.

[1332] Output: Send the collected feedback to the server.

[1333] Step 7: Reevaluate the algorithm

[1334] server:

[1335] Input: Feedback and emotion data.

[1336] How it works: Analyzes feedback and emotional data to optimize the analysis algorithm and system. For example, if a student's emotional reaction to a particular occupation is positive, the system will further enrich the information about that occupation.

[1337] Output: Prepare the data for further analysis and report generation using optimized analysis algorithms.

[1338] This system will enable personalized career suggestions that take into account students' feelings and feedback, allowing them to paint a more specific and appropriate picture of their future. It will also enable educators and parents to efficiently provide support that is tailored to students' aptitudes.

[1339] (Application example 2)

[1340] 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."

[1341] The present invention relates to a system that supports students in concretely envisioning their future dreams and careers, and aims to provide a system that can take into account not only athletic performance and interest data, but also emotional data. Conventional systems have had difficulty reflecting students' emotional interests, which has led to a problem of reduced accuracy in analyzing aptitude and selecting career candidates.

[1342] 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.

[1343] In this invention, the server includes a means for collecting data on athletic performance and interests from students, a means for preprocessing and verifying the collected data, and a means for analyzing the aptitude of students based on the preprocessed data and selecting career candidates, which enables emotional data to be integrated into the analysis result and optimize the recommendation report based on emotional interest levels.

[1344] "Students" refers to children from upper elementary school to junior high school.

[1345] "Athletic performance" refers to a student's physical education and athletic records and performance data.

[1346] "Interest data" refers to information such as the subjects and club activities that students are interested in.

[1347] "Data collection tools" refers to devices and software that provide an interface for collecting various data from students.

[1348] "Preprocessing" refers to the process of preparing collected data into a format that can be analyzed.

[1349] "Verification" refers to the process of checking and correcting errors or incompleteness in collected data.

[1350] "Data analysis" refers to the process of assessing students' aptitude based on collected and pre-processed data.

[1351] A "clustering algorithm" refers to a machine learning method for classifying data points into several groups (clusters).

[1352] "Career Candidates" refers to a list of occupations suggested to a student based on the results of the aptitude analysis.

[1353] "Recommendation Report" refers to a document or digital data that lists the results of a student's aptitude analysis and possible career options.

[1354] "Emotional Data" refers to emotional information obtained from a student's facial expressions, voice, and behavior.

[1355] An "emotion engine" refers to software or algorithms that analyze emotional data and generate quantified information.

[1356] "Feedback Collection Instrument" means any device or software used to present generated reports to students, educators, and parents and to collect their reactions and opinions.

[1357] "Analysis algorithm reevaluation" refers to the process of reviewing and improving the performance of data analysis algorithms based on collected feedback data.

[1358] "Optimization" refers to the process of improving the content and analytical algorithms of generated reports to make them more effective and efficient.

[1359] This invention is a system that helps students visualize their future dreams and careers by collecting and analyzing data on students' athletic performance, interests, and emotions, presenting appropriate career candidates, and reevaluating and improving the analysis algorithm based on feedback. The specific configuration and functions of this system are described below.

[1360] Overall structure

[1361] The system consists of the following main components:

[1362] 1. Data collection terminal

[1363] 2. Data Validation and Preprocessing Server

[1364] 3. Data analysis server

[1365] 4. Report Generation Server

[1366] 5. Feedback collection terminal

[1367] 6. Algorithm Reevaluation Server

[1368] 7. Emotion Engine

[1369] Program processing

[1370] Data collection

[1371] The device provides an interface for students to input information about their athletic performance and interests. For example, a student can enter their weekly 100-meter sprint time or their favorite subjects and club activities through a dedicated application. At the same time, the device collects emotional data from the student's facial expressions and voice, which is also sent to the server.

[1372] Data Validation and Preprocessing

[1373] The server verifies the received data and checks for input errors. For example, it checks whether the 100-meter sprint time is physically impossible or whether the questionnaire is completely filled out. Incorrect or incomplete data requires correction or re-entry. At the same time, the emotion engine analyzes the collected emotion data and provides quantified emotion information to the server.

[1374] Data analysis

[1375] The data analysis server analyzes each student's aptitude based on the preprocessed data. For example, it uses the k-means clustering algorithm to classify the student's athletic ability and interest characteristics. Emotional data is also used in the analysis to reinforce interest levels.

[1376] Report Generation

[1377] The report generation server generates a recommendation report for each student based on the data analysis results. This report includes multiple career options suitable for the student, along with recommendations for the skills and related subjects required for each. Using sentiment data, the report also includes detailed information about the careers that the student is particularly interested in.

[1378] Feedback collection

[1379] The feedback collection terminal provides an interface for presenting the generated reports to students, educators, and parents. Users can view and confirm the contents of the presented reports. For example, they can use the reports to find out more information about careers that students are interested in. At the same time, the terminal also collects students' facial expressions and reactions using the emotion engine and records them as feedback.

[1380] Algorithm Reevaluation

[1381] The server collects feedback and emotional data sent from the devices and reevaluates the performance of the analysis algorithm and the overall system. For example, if a student's emotional reaction to a particular occupation is positive, the system will be optimized to provide more detailed information about that occupation in the future, allowing it to provide more personalized advice to each individual student.

[1382] Hardware and software used

[1383] Hardware: Smartphones, server computers

[1384] Software: Python, Numpy, scikit-learn, dedicated applications

[1385] Adding specific examples

[1386] Example: Generate analysis results that classify Student A as "Athletic Ability Cluster: High," "Mathematics Interest Cluster: Medium," and "Emotion Cluster: Positive." The report recommends occupations such as "Sports Data Analyst" and "Sports Instructor," and lists the skills and learning recommendations related to those occupations. Detailed information about "Sports Data Analyst," in which Student A showed particular interest, is provided.

[1387] Prompt Sentence Examples

[1388] "Design data preprocessing and analysis algorithms for a system that collects students' athletic performance and interest data, classifies them using a clustering algorithm, and recommends suitable occupations. The generative AI model should include a procedure for compiling the clusters and recommended occupations into a report that is easy to understand for the student."

[1389] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[1390] Step 1:

[1391] Data collection

[1392] The device provides an interface for collecting data on athletic performance and interests from students. Specifically, students are asked to enter their 100-meter sprint times, favorite subjects, and club activities through a dedicated smartphone application once a week. The input data is stored in the device's internal memory. At the same time, the device also uses a camera and microphone to collect students' facial expressions and voice data, which is then saved as emotional data.

[1393] Input: Student athletic performance, interest survey data, facial expression and voice data

[1394] Output: Student data (athletic performance, interest data, emotional data)

[1395] Step 2:

[1396] Data Validation and Preprocessing

[1397] The server receives student data sent from the device and verifies it. During the verification process, it checks for physically impossible values ​​(e.g., a 100-meter sprint time of 0 seconds) and missing questionnaire entries. If the data is incomplete, the device is asked to re-enter it. The server then uses an emotion engine to quantify facial and voice data and convert it into an emotion score. It also standardizes and categorizes athletic performance and interest data.

[1398] Input: Student data (athletic performance, interest data, emotional data)

[1399] Output: Preprocessed data (standardized athletic performance, encoded interest data, emotion scores)

[1400] Step 3:

[1401] Data analysis

[1402] The data analysis server analyzes students' aptitudes based on the preprocessed data. During this process, a clustering algorithm (e.g., k-means) is used to cluster students based on their athletic ability, interests, and emotional characteristics. As a result of the clustering, students are classified into multiple aptitude clusters. At the same time, emotional data is integrated into the analysis results as the degree of interest.

[1403] Input: Preprocessed data (standardized motor performance, encoded interest data, emotion scores)

[1404] Output: Aptitude clusters (exercise clusters, interest clusters, emotion clusters)

[1405] Step 4:

[1406] Report Generation

[1407] The report generation server generates a recommendation report for each student based on the data analysis results. It selects career candidates for each cluster and provides detailed recommendations for the skills required and related subjects. It also uses emotional data to provide detailed information about careers that students are particularly interested in. The generated report is saved on the server.

[1408] Input: Aptitude cluster (exercise cluster, interest cluster, emotion cluster)

[1409] Output: Recommendation report (job candidates, required skills, learning recommendations)

[1410] Step 5:

[1411] Feedback collection

[1412] The feedback collection terminal presents the generated report to students, educators, and parents. Users can view the report contents and enter their opinions and questions about careers and study recommendations that students are interested in. The terminal also collects students' facial expressions and reactions, analyzes them using an emotion engine, and records them as feedback data.

[1413] Input: recommendation report, user responses (opinions, questions, facial expressions)

[1414] Output: Feedback data (user opinions, sentiment data)

[1415] Step 6:

[1416] Algorithm Reevaluation

[1417] The server collects and analyzes the feedback data sent from the devices and reevaluates the performance of the analysis algorithm. For example, if students have a high number of positive emotional reactions to a particular occupation, the system will optimize the algorithm to provide more detailed information about that occupation. This allows the system to provide more personalized advice to each student.

[1418] Input: Feedback data (user opinions, sentiment data)

[1419] Output: Improved analysis algorithm

[1420] 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.

[1421] 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.

[1422] 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.

[1423] [Fourth embodiment]

[1424] FIG. 7 shows an example of the configuration of a data processing system 410 according to the fourth embodiment.

[1425] 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.

[1426] 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).

[1427] 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.

[1428] 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.

[1429] 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).

[1430] 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.

[1431] 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.

[1432] 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.

[1433] 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.

[1434] 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.

[1435] 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.

[1436] 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."

[1437] This is a system that helps students from the upper grades of elementary school to junior high school (hereinafter referred to as "students") to concretely visualize their future dreams and careers. The system aims to collect and analyze data on students' athletic performance and interests, and present appropriate career options.

[1438] Overall structure

[1439] The system consists of the following main components:

[1440] 1. Data collection terminal

[1441] 2. Data Validation and Preprocessing Server

[1442] 3. Data analysis server

[1443] 4. Report Generation Server

[1444] 5. Feedback collection terminal

[1445] 6. Algorithm Reevaluation Server

[1446] Program processing

[1447] Data collection

[1448] The device provides an interface for students to input information about their athletic achievements and interests. For example, an application can be provided to collect information such as their 100-meter sprint time in physical education class, or a questionnaire about their favorite subjects and extracurricular activities. The collected data is then sent to a server via the Internet.

[1449] Data Validation and Preprocessing

[1450] The server validates the received data and checks for input errors (for example, checking that the 100-meter sprint time is not physically impossible or that the questionnaire is completely filled out). The server then preprocesses the validated data (for example, standardizing numeric data and encoding categorical data into numbers).

[1451] Data analysis

[1452] The server analyzes each student's aptitude based on the preprocessed data, using clustering and supervised learning algorithms to classify them into clusters based on their interests and abilities, and then lists suitable career candidates based on the results.

[1453] Report Generation

[1454] The server generates a recommendation report for each student based on the data analysis results. This report includes a list of suitable careers for the student, along with the skills and related learning and activities required. For example, a student with strong athletic ability and good grades in mathematics may be recommended a career such as "sports data analyst," along with specific study methods and workshop participation recommendations.

[1455] Feedback collection

[1456] The terminal provides an interface for presenting the generated recommendation report to students, teachers, and parents. Users (students, teachers, and parents) can view the report through the terminal and enter their opinions and questions. For example, if a student is interested in "sports data analyst" and would like more detailed information about the job, they can send a question through the terminal.

[1457] Algorithm Reevaluation

[1458] The server collects feedback from the devices and reevaluates the performance of the analysis algorithm and the overall system. Based on this feedback, it creates and implements an improvement plan to optimize the content of the career candidate list and recommendation report. For example, if many students express interest in a particular career, it will provide more detailed information related to that career or add new related recommendations.

[1459] Specific examples

[1460] Example 1: Data collection

[1461] Using a dedicated app on a device, students enter their physical education records (for example, 100-meter sprint time) and interest questionnaires (favorite subjects, club activities, etc.) once a week.

[1462] The user (student) enters this information and the data is automatically sent to the server.

[1463] Example 2: Data validation and preprocessing

[1464] The server validates the received data to ensure there are no errors, for example, checking for anomalies in the 100-meter sprint time.

[1465] The server normalizes the data, for example encoding interest survey responses into numbers.

[1466] Example 3: Data analysis

[1467] The server generates an analysis result in which Student A is classified as "Athletic Ability Cluster: High" and "Mathematics Interest Cluster: Medium."

[1468] Example 4: Report Generation

[1469] The server recommends occupations such as "sports data analyst" or "sports instructor" to Student A. The report lists the necessary skills and learning recommendations.

[1470] Example 5: Feedback collection

[1471] The terminal presents the generated report to Student A, who then views the report and becomes interested in the "Sports Data Analyst."

[1472] Student A inputs a follow-up question through the terminal, for example, "How do I study the programming language required for this job?"

[1473] Example 6: Algorithm reevaluation

[1474] The server collects feedback from Student A and optimizes the analysis algorithm. This process continuously improves the entire system.

[1475] This system will enable students to gain a deeper understanding of their own aptitudes and to envision their future careers and dreams. It will also enable teachers and parents to provide specific support tailored to students' aptitudes.

[1476] The processing flow will be explained below.

[1477] Step 1:

[1478] The devices provide an interface for students to enter data about their athletic performance and interests, such as their weekly 100-meter sprint time or their favorite subjects and club activities, through a dedicated application.

[1479] Step 2:

[1480] The device sends the entered data to a server via the Internet, where it is temporarily stored and awaits processing for analysis.

[1481] Step 3:

[1482] The server validates the received data, detecting, for example, physically impossible 100-meter sprint times or incomplete survey responses, and verifies the accuracy of the data. Incorrect or incomplete data requires correction or re-entry.

[1483] Step 4:

[1484] The server preprocesses the validated data, specifically by standardizing numeric data and encoding categorical data. For example, it converts survey responses (favorite subject) into numerical values.

[1485] Step 5:

[1486] The server analyzes students' aptitudes based on the preprocessed data. It uses clustering algorithms and supervised learning algorithms to classify students' interests and abilities. For example, it divides students into clusters based on athletic ability and academic aptitude, and then selects career candidates based on each.

[1487] Step 6:

[1488] The server then generates a report for each student based on the analysis results. This report includes recommendations for multiple careers suitable for the student, along with the skills and related subjects required for those careers. For example, a student with strong athletic ability and good grades in math might be recommended a career such as "sports data analyst."

[1489] Step 7:

[1490] The terminal provides an interface for presenting the generated report to students, teachers, and parents. Users (students, teachers, and parents) can view and check the contents of the presented report. For example, this can be used to find out more information about a career that a student is interested in.

[1491] Step 8:

[1492] Users (students, teachers, and parents) can provide feedback on the report content through the terminal. For example, a student may be interested in the "Sports Data Analyst" section and enter additional questions or opinions about the topic.

[1493] Step 9:

[1494] The device sends the collected feedback to the server, where it is stored in a database for use in the re-evaluation process.

[1495] Step 10:

[1496] The server reevaluates and optimizes the analysis algorithm based on the feedback. For example, if a student's interests or trends change, or if many students show interest in a particular career, it will update the information and recommendations about that career. This reevaluation process improves the accuracy and effectiveness of the entire system.

[1497] Through these processing steps, the system supports students in choosing their future careers and enables educators to provide appropriate advice.

[1498] Example 1

[1499] 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."

[1500] In today's educational environment, students face the challenge of being unable to envision a specific future career based on their own interests and abilities. Therefore, there is a need for an effective support system to help students make appropriate career choices. However, traditional methods are problematic in that they are unable to flexibly accommodate students' diverse interests and abilities, and do not provide sufficient individualized advice.

[1501] 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.

[1502] In this invention, the server includes a means for collecting data on athletic performance and interests from students, a means for verifying and preprocessing the collected data, and a means for analyzing the aptitude of students based on the preprocessed data using a clustering algorithm or a supervised learning algorithm and selecting career candidates. This makes it possible to provide flexible and accurate career candidates based on each student's aptitude and interests, and to support career selection.

[1503] "Athletic performance" refers to data related to a student's physical ability, including, for example, 100-meter sprint times and physical fitness test results.

[1504] "Interests" refers to data about the areas and activities that students are interested in, such as their favorite subjects, club activities, and dreams for the future.

[1505] "Data Collection Means" refers to the interface for inputting and recording data from students regarding their athletic performance and interests and transmitting that data to the server.

[1506] "Data validation and pre-processing means" refers to a system for checking received data for errors and pre-processing the data, such as standardizing or encoding the data, if necessary.

[1507] "Clustering algorithm" refers to an algorithm for classifying students into groups with similar characteristics based on their athletic performance and interests.

[1508] "Supervised learning algorithms" refer to machine learning algorithms that use pre-labeled data to predict students' aptitudes and career prospects.

[1509] "Analysis means" refers to a system for assessing students' aptitude and selecting career candidates based on pre-processed data.

[1510] A "recommendation report" refers to a report generated based on the analysis results that lists suitable career options, required skills, and learning recommendations for each student.

[1511] "Feedback collection means" refers to an interface for collecting opinions and questions from users (students, educators, parents) regarding the generated reports.

[1512] "Algorithm re-evaluation and improvement measures" refers to a system for evaluating the performance of analysis algorithms and the overall system based on collected feedback and improving them as needed.

[1513] The present invention is a system for supporting students in choosing their future careers in an educational system. Specifically, the system collects and analyzes data on students' athletic performance and interests, and presents suitable career candidates. The system is composed of a data collection terminal, a data verification and preprocessing server, a data analysis server, a report generation server, a feedback collection terminal, and an algorithm reevaluation server.

[1514] Data collection

[1515] The devices provide an interface for students to input data about their athletic achievements and interests. For example, a dedicated application is provided, allowing students to input information about their 100-meter sprint time in gym class, their favorite subjects, and club activities. This data is then sent to a server via the Internet.

[1516] Data Validation and Preprocessing

[1517] The server validates the received data and checks for input errors (for example, checking that the 100-meter sprint time is not physically impossible or that the questionnaire is completely filled out). The server then preprocesses the validated data (for example, standardizing numeric data and encoding categorical data into numbers).

[1518] Data analysis

[1519] The server analyzes each student's aptitude based on the preprocessed data, using clustering and supervised learning algorithms to classify them into clusters based on their interests and abilities, and then lists suitable career candidates based on the results.

[1520] Report Generation

[1521] The server generates a recommendation report for each student based on the data analysis results. This report includes a list of suitable careers for the student, along with the skills and related learning and activities required. For example, a student with strong athletic ability and good math grades could be recommended a career such as "sports data analyst," along with specific study methods and workshop participation recommendations.

[1522] Feedback collection

[1523] The terminal provides an interface for presenting the generated recommendation report to students, educators, and parents. Users (students, educators, and parents) can view the report through the terminal and enter their opinions and questions. For example, if a student is interested in "sports data analyst" and wants more detailed information about the job, they can submit a question through the terminal.

[1524] Algorithm Reevaluation

[1525] The server collects feedback from the devices and reevaluates the performance of the analysis algorithm and the overall system. Based on this feedback, it creates and implements an improvement plan to optimize the content of the career candidate list and recommendation report. For example, if many students express interest in a particular career, it will provide more detailed information related to that career or add new related recommendations.

[1526] Specific examples

[1527] Example 1: Data collection

[1528] Using a dedicated app on a device, students enter their physical education records (for example, 100-meter sprint time) and interest questionnaires (favorite subjects, club activities, etc.) once a week.

[1529] The user (student) enters this information and the data is automatically sent to the server.

[1530] Example 2: Data validation and preprocessing

[1531] The server validates the received data to ensure there are no errors, for example, checking for anomalies in the 100-meter sprint time.

[1532] The server normalizes the data, for example encoding interest survey responses into numbers.

[1533] Example 3: Data analysis

[1534] The server generates an analysis result in which Student A is classified as "Athletic Ability Cluster: High" and "Mathematics Interest Cluster: Medium."

[1535] Example 4: Report Generation

[1536] The server recommends occupations such as "sports data analyst" or "sports instructor" to Student A. The report lists the necessary skills and learning recommendations.

[1537] Example 5: Feedback collection

[1538] The terminal presents the generated report to Student A, who then views the report and becomes interested in the "Sports Data Analyst."

[1539] Student A inputs a follow-up question through the terminal, for example, "How do I study the programming language required for this job?"

[1540] Example 6: Algorithm reevaluation

[1541] The server collects feedback from Student A and optimizes the analysis algorithm, and this process continuously improves the entire system.

[1542] Prompt Sentence Examples

[1543] By inputting the following prompt sentences into the generative AI model, an assistant function is provided to help the model specifically draw appropriate career candidates.

[1544] Example prompt:

[1545] "This student has good motor skills and an interest in mathematics. Please list suitable careers for him / her and recommend the necessary skills and related learning activities."

[1546] summary

[1547] This system will enable students to gain a deeper understanding of their own aptitudes and to concretely visualize their future careers and dreams, while also enabling educators and parents to provide specific support tailored to students' aptitudes.

[1548] The flow of the identification process in the first embodiment will be described with reference to FIG.

[1549] Step 1: Provide a data entry interface

[1550] The terminal provides an interface for students to input data about their athletic achievements and interests. Specifically, a form is displayed in which students can input information about their 100-meter sprint time, favorite subjects, and club activities via a dedicated application. The input data is information about the student's athletic achievements and interests. This data is received and sent to the server.

[1551] Step 2: Receiving and verifying data

[1552] The server receives the data sent from the device. It verifies the accuracy of the entered data, for example, checking that the 100-meter sprint time is not physically impossible or that a questionnaire is completely filled out. Incorrect or incomplete data generates an error message and sends it back to the device. The output of this step is the validated data.

[1553] Step 3: Data Preprocessing

[1554] The server preprocesses the validated data by standardizing numeric data and converting categorical data to numbers. For example, it might encode favorite subjects as "1: Math, 2: English, 3: Physical Education." This preprocessing generates standardized data that makes it easier for algorithms to understand the data. The input to this step is the validated data, and the output is the preprocessed data.

[1555] Step 4: Data analysis and clustering

[1556] The server analyzes each student's aptitude based on the preprocessed data. It uses clustering algorithms or supervised learning algorithms to classify students into clusters based on their characteristics. For example, it may classify students into a cluster with high athletic ability or a cluster with an interest in mathematics. The input of this step is the preprocessed data, and the output is the classification results of the clustered students.

[1557] Step 5: Selecting potential career candidates

[1558] The server selects suitable career candidates based on the clustered student data. It lists the careers associated with each cluster and recommends them to the student. In this step, a generative AI model is used to list careers that match the student's characteristics. For example, a student with high athletic ability and an interest in mathematics can be recommended a career such as "sports data analyst." The input to this step is the clustered classification results, and the output is a list of career candidates.

[1559] Step 6: Generate a recommendation report

[1560] The server generates a recommendation report for each student based on the career candidate list. This report includes recommended career candidates, the skills required for those careers, and recommendations for related learning and activities. The generated report is sent to the terminal. The input of this step is the career candidate list, and the output is the recommendation report.

[1561] Step 7: Gather feedback

[1562] The terminal provides an interface to present the generated recommendation report to students, educators, and parents. Users can view the report through the terminal and input their opinions or questions. For example, if a student wants more information about a "sports data analyst," he or she can submit a question through the terminal. The feedback is sent to the server. The input of this step is the recommendation report, and the output is the feedback information.

[1563] Step 8: Reevaluate and improve the algorithm

[1564] The server collects feedback sent from the devices and reevaluates the performance of the analysis algorithm and the entire system. Based on the collected feedback, it creates and implements an improvement plan to optimize the content of the career candidate list and recommendation report. For example, if many students express interest in "sports data analyst," it will strengthen the provision of information related to that career. The input of this step is feedback information, and the output is an optimized algorithm and an updated system.

[1565] By carrying out these specific processing steps in a detailed and orderly manner, it becomes possible to select a career and provide learning support based on each student's aptitude.

[1566] (Application example 1)

[1567] 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."

[1568] Currently, many students find it difficult to have a concrete image of their future dreams and careers. It is also difficult for teachers and parents to accurately grasp students' aptitudes and provide advice based on that. Furthermore, traditional career recommendation systems are based on static data analysis and lack the utilization of feedback and the delivery of educational and entertainment content. This prevents students from choosing a career that matches their aptitudes, making it difficult for them to set future goals.

[1569] 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.

[1570] In this invention, the server includes means for collecting data on athletic performance and interests from students, means for preprocessing and verifying the collected data, means for analyzing the aptitudes of students based on the preprocessed data and selecting career candidates, means for presenting generated reports to students, educators, and parents and collecting feedback, means for reevaluating and improving the analysis algorithm based on the collected feedback, and means for delivering educational and entertainment content related to the suggested careers. This allows students to understand career candidates based on their aptitudes and interests and to form a concrete image of them through the related content.

[1571] "Students" refers to children from the upper grades of elementary school to junior high school.

[1572] "Athletic performance" refers to the specific numerical data and evaluations recorded by students during physical education and club activities.

[1573] "Interest data" refers to survey results and information about students' favorite subjects, clubs, hobbies, and future interests.

[1574] A "clustering algorithm" is an analytical method for classifying data into multiple groups (clusters), and mainly uses the K-means method.

[1575] "Career suggestions" refer to specific occupations or career options suggested to students based on data analysis.

[1576] A "recommendation report" is a document that contains career options based on a student's aptitudes and interests, along with specific advice related to those careers.

[1577] "Feedback" refers to opinions, impressions, and questions provided by students, educators, and parents in response to the generated recommendation reports and proposals.

[1578] "Educational and entertainment content" refers to interactive materials such as videos, quizzes, and interviews that help students learn while having fun.

[1579] "Analysis algorithm" refers to a mathematical processing method for determining students' aptitude and selecting career candidates based on collected and pre-processed data.

[1580] MODE FOR CARRYING OUT THE INVENTION

[1581] This invention is a system for helping students concretely visualize their future dreams and careers. The system includes the steps of data collection, data preprocessing, data analysis, report generation, feedback collection, and content distribution.

[1582] Overall system configuration

[1583] The system consists of the following main components:

[1584] 1. Data collection terminal

[1585] 2. Data Validation and Preprocessing Server

[1586] 3. Data analysis server

[1587] 4. Report Generation Server

[1588] 5. Feedback collection terminal

[1589] 6. Algorithm Reevaluation Server

[1590] 7. Content Distribution Server

[1591] Technology used

[1592] Languages: Python, JavaScript

[1593] AI algorithms: clustering (K-means), supervised learning (SVM, Random Forest)

[1594] Database: Firebase

[1595] Front-end framework: React Native

[1596] Backend: Google Cloud Functions

[1597] Content delivery: AWS S3, CloudFront

[1598] Program processing

[1599] Data collection

[1600] Students enter information about their athletic achievements and interests through a smartphone application. For example, a questionnaire about their 100-meter sprint time in physical education class, their favorite subjects, and club activities is collected. This data is sent to Firebase via the Internet.

[1601] Examples:

[1602] Prompt: "What is your most recent 100-meter sprint time during gym class?"

[1603] Data Validation and Preprocessing

[1604] The server validates the received data and checks for input errors (for example, checking that the 100-meter sprint time is not physically impossible or that the questionnaire is completely filled out).The server then preprocesses the validated data, standardizing numeric data and encoding categorical data into numbers.

[1605] Data analysis

[1606] The data analysis server analyzes each student's aptitude based on the preprocessed data. The analysis mainly uses clustering algorithms (K-means) and supervised learning algorithms (SVM, Random Forest). This allows students to be classified into clusters based on their interests and abilities, and the results are used to create a list of suitable career candidates.

[1607] Examples:

[1608] Prompt: "Use a clustering algorithm to analyze the interests and abilities of all students and classify them into specific career clusters."

[1609] Report Generation

[1610] The report generation server generates a recommendation report for each student based on the data analysis results, which includes recommendations for suitable careers for the student, the necessary skills, and related learning and activities.

[1611] Feedback collection

[1612] The feedback collection terminal presents the generated recommendation report to students, educators, and parents. Users can view the report through the terminal and enter their opinions and questions. For example, if a student is interested in "sports data analyst" and wants more detailed information about the job, they can submit a question through the terminal.

[1613] Examples:

[1614] Prompt: "If you would like more information about the suggested jobs or have suggestions for improvement, please fill out the feedback form below."

[1615] Algorithm Reevaluation

[1616] The algorithm re-evaluation server collects feedback sent from the devices and re-evaluates the performance of the analysis algorithm and the entire system. Based on this feedback, it creates and implements an improvement plan to optimize the contents of the job candidate list and recommendation report.

[1617] Educational and entertainment content delivery

[1618] The content delivery server stores educational and entertainment content related to the proposed careers (e.g., videos, quizzes, interviews) in AWS S3 and uses CloudFront to deliver it to users at high speed.

[1619] Examples:

[1620] Prompt: "Watch educational videos related to sports data analysts."

[1621] This system allows students to understand potential careers based on their aptitudes and interests, and gives them a concrete image of what those careers could be through related content, allowing teachers and parents to provide specific support tailored to the students' aptitudes.

[1622] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[1623] System processing steps

[1624] Step 1: Data collection

[1625] The device provides an interface where students can input information about their athletic performance and interests. The input data is sent to Firebase. For example, a student can enter their 100-meter sprint time or favorite subject, and this data is immediately saved in the database. The input data (athletic performance, interest survey) is treated as output (data saved to Firebase) as is.

[1626] Step 2: Data validation and preprocessing

[1627] The server retrieves the data stored in Firebase and validates its contents. Specifically, it checks whether the 100-meter sprint time is within the physically possible range and whether all questions have been answered correctly. After confirming there are no errors, it then standardizes the numeric data and encodes the categorical data into numbers. It outputs the input data (student athletic performance and interest questionnaire) as validated data, which is then converted into preprocessed data.

[1628] Step 3: Data analysis

[1629] The data analysis server analyzes the preprocessed data using a clustering algorithm (K-means) and a supervised learning algorithm (SVM, Random Forest). This classifies students into clusters based on their interests and athletic performance, and lists corresponding career candidates. The input data (preprocessed data) is output as the analysis results (cluster classification and a list of career candidates).

[1630] Step 4: Generate a recommendation report

[1631] The report generation server generates a recommendation report containing suitable career candidates and details for each student based on the data analysis results. This report lists the recommended careers and the skills and learning methods required for those careers. For example, "For a student with high athletic ability and an interest in mathematics, we recommend a sports data analyst position and encourage learning related programming languages." The input data (analysis results) are output as a recommendation report.

[1632] Step 5: Gather feedback

[1633] The feedback collection terminal presents the generated recommendation report to students, educators, and parents. Users who view the report can enter their thoughts and questions in a feedback form. For example, if a student is interested in a "sports data analyst" and has a question about specific study methods, they can submit that question through the terminal. The input data (user feedback) is output as feedback.

[1634] Step 6: Reevaluate the algorithm

[1635] The algorithm re-evaluation server analyzes the collected feedback and re-evaluates the performance of the entire system. Based on this feedback, it makes improvements to optimize the analysis algorithm, career candidate list, and recommendation report content. For example, if many students express interest in a particular career, it adds detailed information and new recommendations related to that career. The input data (feedback) is output as an improved algorithm and career candidate list.

[1636] Step 7: Educational and Entertainment Content Distribution

[1637] The content delivery server provides educational and entertainment content (videos, quizzes, interviews, etc.) related to the recommended careers. For example, educational videos and interview videos about "sports data analyst" are stored in AWS S3 and delivered to users at high speed via CloudFront. The input data (career recommendations and related content) is output as delivery content.

[1638] This allows students to understand potential careers based on their aptitudes and interests, and form a concrete image of them through related content, while also enabling teachers and parents to provide specific support according to students' aptitudes.

[1639] 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.

[1640] This invention is a system to support students from the upper grades of elementary school to junior high school (hereinafter referred to as "students") in concretely envisioning their future dreams and careers. This system collects and analyzes data on students' athletic performance and interests, presents appropriate career options, and uses students' emotional data to improve the accuracy of the analysis.

[1641] Overall structure

[1642] The system consists of the following main components:

[1643] 1. Data collection terminal

[1644] 2. Data Validation and Preprocessing Server

[1645] 3. Data analysis server

[1646] 4. Report Generation Server

[1647] 5. Feedback collection terminal

[1648] 6. Algorithm Reevaluation Server

[1649] 7. Emotion Engine

[1650] Program processing

[1651] Data collection

[1652] The device provides an interface for students to input information about their athletic performance and interests. For example, a student can enter their weekly 100-meter sprint time or their favorite subjects and club activities through a dedicated application. At the same time, the device collects emotional data from the student's facial expressions and voice, which is also sent to the server.

[1653] Data Validation and Preprocessing

[1654] The server verifies the received data and checks for input errors. For example, it checks whether the 100-meter sprint time is physically impossible or whether the questionnaire is completely filled out. Incorrect or incomplete data requires correction or re-entry. At the same time, the emotion engine analyzes the collected emotion data and provides quantified emotion information to the server.

[1655] Data Preprocessing

[1656] The server preprocesses the validated data. Specifically, it standardizes numerical data and encodes categorical data. For example, it converts survey responses (favorite subject) into numerical values. At the same time, the server preprocesses sentiment data and integrates it with other data.

[1657] Data analysis

[1658] The server analyzes each student's aptitude based on the preprocessed data. It uses clustering and supervised learning algorithms to classify the student's interests and abilities. For example, students are divided into clusters based on athletic ability and academic aptitude, and career candidates are selected based on each. Emotional data is used as part of the analysis to reinforce interest levels.

[1659] Report Generation

[1660] The server generates a recommendation report for each student based on the data analysis results. This report includes multiple career options suitable for the student, along with recommendations for the skills and related subjects required. For example, a student with strong athletic ability and good math grades could be recommended a career such as "sports data analyst." At the same time, it utilizes emotional data to optimize the report content, taking into account the student's emotional interest in specific careers.

[1661] Feedback collection

[1662] The device provides an interface for presenting the generated report to students, teachers, and parents. Users (students, teachers, and parents) can view and confirm the contents of the presented report. For example, they can use it to find out more information about careers that students are interested in. At the same time, the device collects students' reactions and emotions using the emotion engine again and records them as feedback.

[1663] Feedback Reflected

[1664] Users (students, teachers, and parents) can provide feedback on the report content through the terminal. For example, a student may be interested in the "Sports Data Analyst" and enter additional questions or opinions about the report. At the same time, students' emotional data is also collected.

[1665] Algorithm Reevaluation

[1666] The server collects feedback and emotional data sent from the devices and reevaluates the performance of the analysis algorithm and the overall system. For example, if a student's emotional reaction to a particular occupation is positive, the system will be optimized to provide more detailed information about that occupation in the future, allowing it to provide more personalized advice to each individual student.

[1667] Specific examples

[1668] Example 1: Data collection

[1669] Using a dedicated app on a device, students enter their physical education records (for example, 100-meter sprint time) and interest questionnaires (favorite subjects, club activities, etc.) once a week.

[1670] At the same time, the device analyzes the students' facial expressions and voices using an emotion engine to collect emotional data.

[1671] Example 2: Data validation and preprocessing

[1672] The server validates the received data to ensure there are no errors, for example, checking for anomalies in the 100-meter sprint time.

[1673] The emotion engine analyzes the collected emotion data and provides the quantified results to the server.

[1674] Example 3: Data analysis

[1675] The server generates an analysis result in which Student A is classified as "Athletic Ability Cluster: High," "Mathematics Interest Cluster: Medium," and "Emotion Cluster: Positive."

[1676] Example 4: Report Generation

[1677] The server recommends occupations such as "sports data analyst" or "sports instructor" to Student A. The report lists the necessary skills and learning recommendations.

[1678] Based on the emotional data, we provide detailed information about the "sports data analyst" that Student A was particularly interested in.

[1679] Example 5: Feedback collection

[1680] The terminal presents the generated report to Student A, who then checks the report contents and becomes interested in the "Sports Data Analyst."

[1681] Student A's facial expressions and reactions are analyzed again by the emotion engine and saved as feedback data.

[1682] Example 6: Algorithm reevaluation

[1683] The server optimizes the analysis algorithm based on Student A's feedback and emotional data. This process will enable the server to provide more detailed and personalized recommendation reports in the future.

[1684] This system will enable students to gain a deeper understanding of their own characteristics and, taking into account their emotional reactions, to map out specific careers and dreams for the future, while also enabling teachers and parents to provide specific support tailored to students' aptitudes.

[1685] The processing flow will be explained below.

[1686] Step 1:

[1687] The device provides an interface for students to enter data about their athletic performance and interests. For example, using a dedicated application, students can enter their weekly 100-meter sprint time or their favorite subjects and club activities in a questionnaire. At the same time, the device uses an emotion engine to analyze the student's facial expressions and voice to collect emotional data.

[1688] Step 2:

[1689] The device transmits the collected athletic performance, interest questionnaire, and emotional data to a server via the Internet, where the data is temporarily stored and awaits further processing.

[1690] Step 3:

[1691] The server then verifies the received athletic performance and interest survey data, detecting, for example, physically impossible 100-meter sprint times or incomplete survey responses, and verifies the accuracy of the data. Any incorrect data is corrected or re-entered.

[1692] Step 4:

[1693] The emotion engine analyzes the collected emotion data and generates numerical emotion information (e.g., interest level or stress level), which is also sent to the server.

[1694] Step 5:

[1695] The server preprocesses the validated athletic performance and interest survey data by standardizing numeric data and encoding categorical data into numbers, e.g., by converting survey responses into consistent numeric values.

[1696] Step 6:

[1697] The server analyzes student aptitude based on the preprocessed data. Clustering and supervised learning algorithms are used to classify student interest and ability characteristics. Emotional data is also used as part of the analysis, taking into account the student's interest level and emotional tendencies.

[1698] Step 7:

[1699] The server generates a recommendation report for each student based on the analysis results, including recommendations for suitable careers, the skills required, and related subjects. Using emotional data, the report content is optimized to take into account the student's emotional interest in specific careers.

[1700] Step 8:

[1701] The terminal provides an interface for presenting the generated recommendation report to students, teachers, and parents. Users (students, teachers, and parents) can view the report through the terminal and check its contents.

[1702] Step 9:

[1703] Users (students, teachers, and parents) can provide feedback on the report content through the device. For example, a student can enter additional questions or opinions about a specific occupation. At the same time, the device analyzes the student's facial expressions and voice again using the emotion engine, collecting emotional data along with the feedback.

[1704] Step 10:

[1705] The device sends the collected feedback and emotion data to a server, where the feedback information is stored in a database and used for subsequent algorithm optimization processes.

[1706] Step 11:

[1707] The server reevaluates and optimizes the performance of the analysis algorithm and the entire system based on the collected feedback and sentiment data. For example, if many students show a high interest in a particular career, it will enrich the information related to that career or add new recommendations that incorporate the feedback.

[1708] This specific processing step allows students to receive career recommendations based on their aptitudes and interests, taking into account their emotional reactions, and also makes it easier for teachers and parents to provide appropriate advice to students.

[1709] Example 2

[1710] 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."

[1711] In recent years, the importance of supporting students in choosing their future careers has increased. However, simple aptitude tests and questionnaires alone have the problem of being unable to present career options that fully reflect students' interests and feelings. Furthermore, conventional systems do not adequately reflect feedback, making it difficult to respond to students' individual requests and changing interests. This presents a challenge, as students are unable to visualize a concrete future, making it difficult for educators and parents to provide appropriate guidance.

[1712] The specific processing by the specific processing unit 290 of the data processing device 12 in the second embodiment is realized by the following means.

[1713] In this invention, the server includes means for collecting data on athletic performance and interests from students, means for collecting and analyzing emotional data from students' facial expressions and voices, means for preprocessing and verifying the collected data, means for analyzing the students' aptitudes and selecting career candidates based on the preprocessed data, means for generating a recommendation report based on the analysis results, means for presenting the generated report to students, educators, and parents and collecting feedback, and means for reevaluating and improving the analysis algorithm based on the collected feedback. This makes it possible to present personalized career candidates that take students' emotions and feedback into consideration, allowing them to paint a more specific and appropriate picture of their future.

[1714] "Students" refers to students in the upper grades of elementary school to junior high school age groups.

[1715] "Athletic performance" refers to performance data such as times and scores recorded by students in physical education classes and sports activities.

[1716] "Interests" refers to information that shows a student's interests and preferences in their favorite subjects, club activities, hobbies, etc.

[1717] "Data collection" refers to the process of obtaining information from students about their athletic achievements and interests, including entering information through an application or interface.

[1718] "Emotional data" refers to information about emotions analyzed from students' facial expressions and voices, including data that quantifies emotional states such as joy, surprise, and interest.

[1719] "Data preprocessing" refers to processes such as standardization and encoding that prepare collected data into an analyzable format.

[1720] "Data verification" refers to the process of verifying that collected data is accurate and complete.

[1721] "Analytical algorithms" refer to mathematical methods and models used to classify students' aptitudes and select career candidates based on collected data.

[1722] A "clustering algorithm" refers to an analytical method for classifying data into multiple groups based on similarity.

[1723] A "recommendation report" is a document generated based on the analysis results that lists suitable career options, required skills, and related subject recommendations for students.

[1724] "Feedback" refers to the opinions and reactions provided by students, educators, and parents regarding the recommendation reports and system proposals.

[1725] "Algorithm re-evaluation" refers to the process of improving the performance and accuracy of analysis algorithms based on collected feedback.

[1726] This is a system that helps students from the upper grades of elementary school to junior high school (hereinafter referred to as "students") to concretely visualize their future dreams and careers. The system collects and analyzes data on students' athletic performance and interests, presents appropriate career options, and uses students' emotional data to improve the accuracy of the analysis.

[1727] Overall structure

[1728] The system consists of the following main components:

[1729] 1. Data collection terminal

[1730] 2. Data Validation and Preprocessing Server

[1731] 3. Data analysis server

[1732] 4. Report Generation Server

[1733] 5. Feedback collection terminal

[1734] 6. Algorithm Reevaluation Server

[1735] 7. Emotion Engine

[1736] Hardware and software used

[1737] Device: A smartphone, tablet, or computer running a dedicated application where students enter information.

[1738] Server: A central server for receiving, validating, analyzing, and generating reports on data, using generative AI models and clustering algorithms.

[1739] Emotion engine: Software that analyzes students' facial expressions and voices to generate emotional data.

[1740] Data collection

[1741] The device provides an interface for students to enter information about their athletic achievements and interests. For example, they may be asked to enter:

[1742] 100 meter sprint time once a week

[1743] Favorite subject

[1744] Club Activities

[1745] At the same time, the device collects the student's facial expressions and voice, and analyzes them using an emotion engine. For example, the device converts the student's facial expressions into numerical values ​​such as the degree of "happiness" or "interest," and sends the results to the server.

[1746] Data Validation and Preprocessing

[1747] The server validates the received data and checks for input errors. Any abnormal or incomplete data will be corrected or re-entered. For example, it checks to see if a 100-meter sprint time is a physically impossible value, such as "0 seconds" or "100 seconds."

[1748] The emotion data analyzed by the emotion engine is provided to the server as numerical information. The emotion data is provided in the following format, for example:

[1749] Delight level: 75

[1750] Surprise level: 30

[1751] These data are then combined with other input data and pre-processed for analysis: numerical data are standardized and categorical data are encoded.

[1752] Data analysis

[1753] The server analyzes each student's aptitude based on the preprocessed data. Clustering algorithms and supervised learning algorithms are used to classify the student's interests and abilities. For example, the server generates analysis results that classify Student A into "High athletic ability cluster," "Medium math interest cluster," and "Positive emotional cluster."

[1754] Report Generation

[1755] The server generates a recommendation report for each student based on the analysis results. This report lists suitable career candidates, the required skills, and recommendations for related subjects. For example, Student A may be recommended careers such as "sports data analyst" and "sports instructor," along with required skills (e.g., data analysis, communication) and recommended studies (e.g., statistics, information processing).

[1756] Feedback collection

[1757] The device provides an interface to present the generated report to students, educators, and parents. For example, if Student A is interested in "Sports Data Analyst," he or she can provide feedback such as "I'd like more detailed information." The student's reactions and emotions are also analyzed by the emotion engine and sent to the server.

[1758] Algorithm Reevaluation

[1759] The server collects feedback and emotional data sent from the devices and reevaluates the performance of the analysis algorithm and the overall system. For example, if students' emotional reactions to a particular occupation are positive, the system will be optimized to provide more detailed information about that occupation.

[1760] Specific examples

[1761] 1. Data collection: Student A uses a dedicated app to input "14.2 seconds for the 100-meter dash" and answer "Science is my favorite subject." At the same time, the student's facial expression is analyzed as "Delight level: 60" and sent to the server.

[1762] 2. Data validation and preprocessing: The server validates the received data and confirms that the 100-meter sprint time is correct as "14.2 seconds." The emotion engine converts the data into a numerical value, "Delight Level: 60," and provides it to the server.

[1763] 3. Data analysis: The server generates analysis results that classify Student A into "Athletic ability cluster: Medium," "Science interest cluster: High," and "Emotion cluster: Interested."

[1764] 4. Report Generation: The server generates a report recommending occupations such as "biologist" or "scientific researcher" to Student A. Required skills (e.g., laboratory techniques, data analysis) and recommended studies (e.g., biology, chemistry) are also listed.

[1765] 5. Feedback collection: The device presents the generated report to Student A, who provides feedback that he is “interested in scientific researchers.” The student’s facial expressions are analyzed again and sent to the server.

[1766] 6. Algorithm re-evaluation: The server will optimize the analysis algorithm based on Student A's feedback and emotional data, so that it can provide more detailed and personalized recommendation reports in the future.

[1767] This process allows students to envision specific careers and dreams, taking into account their own characteristics and emotional tendencies, and also allows educators and parents to efficiently provide support tailored to each student's aptitudes.

[1768] The flow of the identification process in the second embodiment will be described with reference to FIG.

[1769] The flow of this system's program processing

[1770] Step 1: Data collection

[1771] Device:

[1772] Input: Students use a dedicated application to input information about their athletic achievements (e.g., 100-meter sprint time) and interests (e.g., favorite subjects, club activities).

[1773] How it works: The application collects the student's facial expressions and voice and sends them to the emotion engine for analysis.

[1774] Output: The collected data (athletic performance, interest information, emotional data) is sent to the server.

[1775] Step 2: Data validation

[1776] server:

[1777] Input: Athletic performance, interest information, and emotional data sent from your device.

[1778] How it works: The server receives the data and checks whether the input values ​​are invalid or incorrect. For example, it checks whether the 100-meter sprint time is an abnormal value such as "0 seconds" or "100 seconds."

[1779] Output: Send the validated data to the preprocessing step. If the data is invalid, prompt the student to re-enter.

[1780] Step 3: Data Preprocessing

[1781] server:

[1782] Input: Verified athletic performance, interest information, and emotional data.

[1783] What it does: Normalize numerical data (e.g., convert 100-meter sprint times to standard scores), encode categorical data (e.g., convert favorite subjects to numbers), or integrate emotional data with other data.

[1784] Output: Send the preprocessed data to the analysis step.

[1785] Step 4: Data analysis

[1786] server:

[1787] Input: Preprocessed data.

[1788] How it works: Using clustering and supervised learning algorithms, we analyze the characteristics of students' interests and abilities, for example classifying them into motor skill clusters, high math interest clusters, and emotional clusters.

[1789] Output: Send the analysis results (classification of student aptitudes and interests) to the report generation step.

[1790] Step 5: Generate a report

[1791] server:

[1792] Input: Analysis results.

[1793] How it works: Based on the analysis results, a recommendation report is generated for the student, including suitable career options, required skills, and related subject recommendations. It also takes into account sentiment data and provides detailed information about careers that the student has expressed interest in.

[1794] Output: Send the generated recommendation report to the feedback collection terminal.

[1795] Step 6: Gather feedback

[1796] Device:

[1797] Input: The generated recommendation report.

[1798] What it does: Provides an interface to present reports to students, educators, and parents, and gathers feedback. Students can enter careers they're interested in, follow-up questions, etc.

[1799] Output: Send the collected feedback to the server.

[1800] Step 7: Reevaluate the algorithm

[1801] server:

[1802] Input: Feedback and emotion data.

[1803] How it works: Analyzes feedback and emotional data to optimize the analysis algorithm and system. For example, if a student's emotional reaction to a particular occupation is positive, the system will further enrich the information about that occupation.

[1804] Output: Prepare the data for further analysis and report generation using optimized analysis algorithms.

[1805] This system will enable personalized career suggestions that take i...

Claims

1. a means of collecting data from students regarding athletic achievement and interests; a means of preprocessing and validating the collected data; A means for analyzing the aptitude of students based on the preprocessed data and selecting career candidates; A means for generating a recommendation report based on the analysis results; A means of presenting the generated reports to students, teachers, and parents and gathering feedback; a means to reevaluate and improve the analysis algorithms based on the collected feedback; A system including:

2. 10. The system of claim 1, further comprising means for analyzing data regarding student athletic performance and interests using a clustering algorithm.

3. The system of claim 1 further comprising means for using the feedback to optimize the content of the generated report.

Images