System

Abstract

A system is provided.SOLUTION: This system includes a means for collecting performance, evaluation and self-report data from a user as input, a means for analyzing the skill and target of the user on the basis of the collected data, a means for generating feedback to the user on the basis of an analysis result, and a means for providing the generated feedback to the user.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 modern society, individualized instruction and career counseling play an important role in educational institutions and workplaces. However, due to a shortage of teachers and career counselors, it is difficult to provide appropriate support tailored to the characteristics and needs of each user. In particular, efficient and effective individualized instruction is required for career counseling for working adults and career guidance for students. Conventional systems do not adequately analyze and provide feedback based on individual grades, evaluations, and self-reported data, resulting in a lack of appropriate support for users' skills and goals. [Means for solving the problem]

[0005] In order to solve the above-mentioned problems, the present invention provides the following means. A system is provided that includes means for collecting grades, evaluations, and self-reported data from users as input, means for analyzing the user's skills and goals based on the collected data, means for generating feedback for the user based on the analysis results, and means for providing the generated feedback to the user. This makes it possible to provide career counseling to working adults, assist with transfers and job changes, and support for exam and interview preparation. It also makes it possible to provide career guidance to students, solve the problem of teacher shortages, and provide comprehensive support for users in their studies and career choices.

[0006] "User" refers to an individual or corporation that uses the system.

[0007] "Performance" refers to academic or work performance as assessed by an educational institution or workplace.

[0008] "Evaluation" refers to a judgment of a user's skills or performance based on specific criteria.

[0009] "Self-reported data" refers to information provided by users themselves, such as skills, career goals, and interests.

[0010] "Means of collection" refers to the functions and methods for taking in data as input and storing it.

[0011] "Means for analysis" refers to the functions and methods for processing collected data and assessing the user's skills and goals.

[0012] "Feedback" refers to advice or suggestions generated based on the analysis results.

[0013] "Means for generating" refers to the functions and methods for generating feedback based on the results of data processing.

[0014] "Means for providing" refers to the functions and methods for notifying and displaying the generated feedback to the user.

[0015] "Career counseling" refers to providing advice on future career paths based on the user's work history and skills.

[0016] "Career guidance" refers to providing advice regarding future educational and career choices based on a user's academic performance and interests.

[0017] "Transfer" refers to a change in a user's job duties or a change in assignment.

[0018] "Changing jobs" refers to a user moving from their current workplace to another workplace.

[0019] "Exam prep" refers to providing advice on how a user can prepare or study for a particular exam.

[0020] "Interview preparation" refers to providing advice on how to prepare for a particular interview or interview techniques. [Brief explanation of the drawings]

[0021] [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

[0022] 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.

[0023] First, the terms used in the following description will be explained.

[0024] 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).

[0025] 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.

[0026] 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.

[0027] 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.

[0028] 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."

[0029] [First embodiment]

[0030] FIG. 1 shows an example of the configuration of a data processing system 10 according to the first embodiment.

[0031] 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.

[0032] 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).

[0033] 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.

[0034] 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.

[0035] 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.

[0036] 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.

[0037] FIG. 2 shows an example of the main functions of the data processing device 12 and the smart device 14.

[0038] 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.

[0039] 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.

[0040] 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.

[0041] 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."

[0042] The system of the present invention is composed of a series of steps that collects grades, evaluations, and self-reported data from users and then analyzes and provides feedback based on the collected data in order to provide individualized guidance and career counseling. Specific embodiments for implementing this system are described below.

[0043] Data collection

[0044] The server collects grades, assessments, and self-reported data that users enter through their devices, such as academic records, work experience, skill sets, and career goals, using web forms or dedicated applications.

[0045] Data analysis

[0046] The collected data is stored by the server and passed to the analytics module, which uses machine learning algorithms and statistical methods to identify patterns based on users' skills and goals. For example, data mining techniques are used to predict the degree to which a particular skill set contributes to career success. Cluster analysis is also used to identify groups of users with similar characteristics.

[0047] Feedback Generation

[0048] Based on the analysis results, the feedback module generates appropriate advice and recommendations for the user. For example, if a user is interested in project management, the system will recommend "taking an introductory project management course" or "aiming to obtain the PMP certification."

[0049] Providing Feedback

[0050] The generated feedback is sent from the server to the user's device. The user can check the feedback content in real time. For example, if a student user requests career counseling, the system will provide specific advice such as "Start studying using dedicated physics and chemistry problem sets."

[0051] Ongoing support

[0052] The system regularly monitors the user's progress and provides new feedback and advice as needed. Users can continually enter new achievements, skills, and career information into the system to receive up-to-date advice.

[0053] Specific examples

[0054] For example, if a working user wants career advice, the system works as follows:

[0055] 1. User data entry

[0056] Users enter their current job description, past work experience, skill set, and career goals.

[0057] The terminal transmits the input data to the server.

[0058] 2. Data Analysis

[0059] The server analyzes the user's information using machine learning algorithms.

[0060] As a result of the analysis, an appropriate career plan is developed based on the user's skills and career goals.

[0061] 3. Generating and Providing Feedback

[0062] The server generates feedback such as, "As a next step, take an introductory project management course and aim to obtain PMP certification."

[0063] The terminal notifies the user of the generated feedback and displays the details.

[0064] In this way, the system of the present invention can efficiently and effectively provide tutoring and career counseling in educational institutions and workplaces, and maximize users' skills and goals by providing real-time feedback based on their performance, assessments, and self-reported data.

[0065] The processing flow will be explained below.

[0066] Step 1:

[0067] Users log into the system using a terminal. New users create an account and log in after verifying their email.

[0068] Step 2:

[0069] Users enter performance, evaluation, and self-reported data into a form, such as current job description, past work experience, skill set, and career goals.

[0070] Step 3:

[0071] The terminal sends the entered data to the server, which checks the input data in real time and performs error checking.

[0072] Step 4:

[0073] The server stores the data received from the device in a database, which is used for further analysis.

[0074] Step 5:

[0075] The server collects the stored data and passes it to an analytics module, which includes grades, assessments, and self-reported data.

[0076] Step 6:

[0077] The analytics module uses machine learning algorithms to analyze users' skills and goals, for example using clustering algorithms to identify groups of users with similar career paths or aspirations.

[0078] Step 7:

[0079] The server passes the analysis results to the feedback module, which initiates the next step of generating feedback.

[0080] Step 8:

[0081] The feedback module generates appropriate feedback for the user based on the analysis results, for example, recommending that "As a next step, take an introductory project management course and aim to obtain PMP certification."

[0082] Step 9:

[0083] The server sends the generated feedback to the user's device, where the user can check the feedback content in real time.

[0084] Step 10:

[0085] Based on the feedback provided, the user can take the following actions: Initiate an action, such as enrolling in a recommended course.

[0086] Step 11:

[0087] The server periodically monitors the user's progress, collecting data to generate new feedback and advice, and updates the data as the user adds new achievements and skills.

[0088] Step 12:

[0089] The terminal notifies and displays regular assessments and new feedback to the user, allowing the user to receive the latest advice from the system.

[0090] Example 1

[0091] 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."

[0092] Conventional individualized tutoring and career counseling systems often lack real-time feedback based on users' grades, evaluations, and self-reported data, making it difficult to maximize users' skills and goals. Furthermore, they lack a mechanism for continuously providing appropriate advice and recommendations based on the user's progress. This makes it difficult to efficiently support users' growth.

[0093] 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.

[0094] In this invention, the server includes means for collecting data as input from the user, means for analyzing the user's information based on the collected data, means for generating feedback for the user based on the analysis results, means for providing the generated feedback to the user, and means for periodically monitoring the user's progress and providing new feedback and advice, thereby providing appropriate feedback in real time and making it possible to maximize the user's skills and goals.

[0095] "User" refers to an individual or organization that uses the system to input data and receive analysis and feedback.

[0096] "Data" refers to information such as a user's grades, ratings, self-reported data, skill sets, and career goals.

[0097] "Means of collection" refers to the process by which a user inputs data through a terminal and transmits it to a server.

[0098] "Means of analysis" refers to the process of analyzing collected data for patterns and trends using machine learning algorithms and statistical methods.

[0099] "Means of generating feedback" refers to the process of creating appropriate advice and recommendations for users based on the results of data analysis.

[0100] The "means for providing feedback" refers to a process for transmitting the generated feedback to the user's terminal and displaying it in real time.

[0101] "Monitoring" refers to the process of regularly checking the user's progress and providing new feedback or advice as needed.

[0102] "Career counseling" refers to a service that provides users with advice regarding career choices and career paths.

[0103] "Career guidance" refers to a service that provides advice to users on the career path they choose.

[0104] MODE FOR CARRYING OUT THE INVENTION

[0105] The system of the present invention is configured to provide individualized guidance and career counseling by collecting grades, evaluations, and self-reported data from users, and then analyzing and providing feedback based on the collected data. A specific embodiment of this system will be described.

[0106] Data collection

[0107] The server has a means for collecting grades, evaluations, and self-reported data entered by users through terminals. For example, users enter data such as academic achievements, work experience, skill sets, and career goals using a web form or a dedicated application. The terminal checks the format of this data and validates it based on certain rules.

[0108] Data transmission and storage

[0109] When a user enters data and presses the submit button, the terminal sends the data to the server using the HTTPS protocol. When the server receives the data, it first checks whether the data format and content are correct and then saves it in a database, such as MySQL or PostgreSQL.

[0110] Data analysis

[0111] The server passes the collected data to the analysis module, which analyzes the user data using machine learning algorithms and statistical methods implemented in programming languages ​​such as Python and R. Specifically, the module uses the Scikit-Learn library to perform data mining and clustering analysis to analyze how the user's skill set affects their career goals.

[0112] Feedback Generation

[0113] The server then uses the analysis results to activate a feedback module, which uses a generative AI model (such as GPT-3) to generate specific advice and recommendations. The generated feedback is customized for each user and formatted against a template.

[0114] Providing Feedback

[0115] The generated feedback is sent via the server to the user's device, where it is received and notified to the user in real time, displaying detailed information so that the user can immediately check the feedback and take action.

[0116] Ongoing support

[0117] The system also has the means to regularly monitor the user's progress and generate new feedback and advice as needed. Users can continually input new achievements, skills, and career information to receive up-to-date advice, thereby providing ongoing support for the user's development.

[0118] Specific examples

[0119] For example, if a working user wants career advice, the system works as follows:

[0120] 1. User data entry

[0121] Users enter their current job description, past work experience, skill set, and career goals.

[0122] The terminal transmits the input data to the server.

[0123] 2. Data Analysis

[0124] The server analyzes the user's information using machine learning algorithms.

[0125] As a result of the analysis, an appropriate career plan is developed based on the user's skills and career goals.

[0126] 3. Generating and Providing Feedback

[0127] The server generates feedback such as "As a next step, take an introductory course in project management and aim to obtain a qualification."

[0128] The terminal notifies the user of the generated feedback and displays the details.

[0129] Prompt Sentence Examples

[0130] "If users want to improve their programming skills, please recommend what learning resources they should use."

[0131] In this way, the system provides real-time feedback based on users' performance, assessments, and self-reported data to maximize their skills and goals, while providing ongoing support to support their long-term growth.

[0132] As a result, the system of the present invention can efficiently and effectively provide individualized instruction and career counseling in educational institutions and workplaces.

[0133] The flow of the identification process in the first embodiment will be described with reference to FIG.

[0134] Program processing flow

[0135] Step 1:

[0136] Entering User Data

[0137] Users use the terminal to enter their grades, evaluations, and self-reported data into web forms or dedicated applications. The terminal checks the format of the entered data and performs validation. For example, if a user enters "Work experience: 5 years, Education: College graduate, Skills: Python," the terminal checks whether the format is correct. If the format is correct, it proceeds to the next step.

[0138] Input: academic record, work history, skill set, career goals

[0139] Output: Format-checked and validated data

[0140] Step 2:

[0141] Data transmission and storage

[0142] After the user presses the send button, the device securely sends the data to the server using the HTTPS protocol. The server then double-checks the format and content of the received data and stores it in a database, for example, a MySQL database along with the user's ID.

[0143] Input: Format-checked and validated data

[0144] Output: Data stored in the database

[0145] Step 3:

[0146] Analyzing the data

[0147] The server retrieves the stored data from the database and passes it to the analysis module, which analyzes the data using machine learning algorithms implemented in Python or R. For example, it uses Scikit-Learn to perform clustering analysis and analyze the relationship between the user's skills and career goals. As a result of this analysis, appropriate feedback is generated based on the user's data.

[0148] Input: User data retrieved from the database

[0149] Output: User data analysis results

[0150] Step 4:

[0151] Generate feedback

[0152] Based on the results of the analysis module, the server uses a generative AI model (e.g., GPT-3) to generate specific feedback. This feedback is customized for each user and formatted using templates. For example, specific advice such as "As a next step, you should take an introductory project management course and aim to obtain a certification" is generated.

[0153] Input: User data analysis results

[0154] Output: Customized feedback

[0155] Step 5:

[0156] Providing Feedback

[0157] The server sends the generated feedback to the user's device, which notifies the user of the received feedback in real time and displays detailed information. The user can then click the "Start Now" button to directly access the suggested course.

[0158] Input:Customized Feedback

[0159] Output: Feedback provided to the user

[0160] Step 6:

[0161] Ongoing support

[0162] The system periodically monitors the user's progress and prompts them to enter new data and achievements. When new information is received from the user, it analyzes it again and generates and provides new feedback. This ensures that the user always receives the latest advice. For example, if a user acquires a new skill, they can enter that information to receive the latest career advice.

[0163] Input: User progress data, grade update data

[0164] Output: Updated feedback and ongoing advice

[0165] The above is a specific processing flow of the system of the present invention, which allows users to receive effective feedback and advice in real time based on their performance and goals.

[0166] (Application example 1)

[0167] 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."

[0168] In the past, when receiving individual guidance or career counseling, users had to conduct their own research and visit multiple counseling institutions, which was a time-consuming and labor-intensive process. Furthermore, because the feedback provided was general, it was difficult for each individual user to obtain the most appropriate advice. The present invention aims to solve these problems and provide a system that provides individual guidance and career counseling effectively and efficiently.

[0169] 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.

[0170] In this invention, the server includes means for collecting grades, evaluations, and self-reported data from users as input, means for analyzing the user's skills and goals based on the collected data, means for generating feedback for the user based on the analysis results, means for providing the generated feedback to the user, means for the user to input their career goals and skill sets in a virtual store and recommend appropriate products and services based thereon, means for analyzing the user's data using a machine learning algorithm and making appropriate recommendations, and means for presenting the recommendations to the user through a virtual reality device, thereby enabling users to effectively find the career path and skill-up courses, qualifications, and products that are best suited to them.

[0171] "User" refers to an individual who provides performance, assessment, and self-reported data and receives feedback from the system.

[0172] "Grades and evaluations" refers to the achievements the user has achieved in their studies or work, or evaluations from third parties.

[0173] "Self-reported data" refers to information that users voluntarily enter about their career goals, skill sets, work history, etc.

[0174] "Means of collection" refers to the method by which users enter grades, evaluations, and self-reported data into the system and obtain it.

[0175] "Means of analysis" refers to methods of analyzing a user's skills and goals based on collected data using machine learning algorithms and statistical methods.

[0176] "Means for generating feedback" refers to methods for generating next actions or recommendations for users based on the results of data analysis.

[0177] The "means for providing feedback" refers to a method for communicating the generated feedback to the user and displaying it on the browser or application screen.

[0178] "Virtual store" refers to a digital platform that offers and trades goods and services in a virtual environment.

[0179] "Career goals" refer to goals that a user wants to achieve in order to improve their work history or skills.

[0180] "Means for recommending products and services" refers to methods for recommending optimal products and services based on user input data.

[0181] A "machine learning algorithm" is a program that discovers patterns in data and makes predictions and classifications.

[0182] "Means for making recommendations" refers to a method for making suggestions to users based on the results of machine learning.

[0183] "Virtual reality device" refers to a headset or other device used to experience virtual reality.

[0184] "Presenting means" refers to the method by which information is displayed to the user using the virtual reality device.

[0185] The system for implementing this invention aims to collect performance, evaluations, and self-reported data from users, analyze the user's skills and goals based on that data, and provide appropriate feedback. Furthermore, particularly in virtual stores, the system has the function of recommending appropriate products and services based on the user's self-reported information.

[0186] First, the hardware you'll need includes:

[0187] Server (used for data processing and analysis)

[0188] User devices (smartphones, PCs, tablets, etc.)

[0189] Virtual reality devices (VR headsets)

[0190] The software then uses:

[0191] Python (programming language)

[0192] NumPy, Pandas (data processing libraries)

[0193] scikit-learn (machine learning library)

[0194] Data collection

[0195] The server collects grades, assessments, and self-reported data that users enter through their devices. Users enter information about their academic records, work history, skill sets, career goals, and more using dedicated applications and web forms.

[0196] Data analysis

[0197] The collected data is stored on a server and passed to an analytics module, which uses machine learning algorithms and statistical methods to identify patterns based on users' skills and goals. Clustering and regression analysis are used to predict specific skill sets and career success.

[0198] Feedback Generation

[0199] Based on the analysis results, the feedback module generates appropriate advice and recommendations for the user. For example, if a user is interested in project management, the system will recommend "taking an introductory project management course" or "aiming to obtain PMP certification."

[0200] Providing Feedback

[0201] The generated feedback is sent from the server to the user's device, where the user can check the feedback content in real time. For example, if a student user requests career counseling, the system will provide specific advice such as "Start studying using dedicated physics and chemistry problem sets."

[0202] Application in virtual stores

[0203] In the virtual store, users input their career goals and skill sets, and are recommended suitable products and courses based on that data. To do this, machine learning algorithms are used to analyze the user's input data and select the most suitable products and services. The recommendations are presented to the user through a virtual reality device.

[0204] Examples of specific prompts include:

[0205] "I currently work as a software engineer and my career goal is to become a project manager. My current skill set is Python, project management, and data analysis. What courses or certifications would you recommend as my next steps?"

[0206] This system allows users to effectively find the career path and skill-building courses, qualifications, and products that best suit them.

[0207] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[0208] Step 1:

[0209] Users enter their own grades, evaluations, and self-reported data through their terminals. They use dedicated applications or web forms to enter information such as academic achievements, work experience, skill sets, and career goals. This input data is collected and then sent to a server. The input data includes text and numerical data.

[0210] Step 2:

[0211] The server saves the collected input data and stores it in a database. This database stores each user's grades, evaluations, and self-reported data for later analysis. The database stores data in a table structure.

[0212] Step 3:

[0213] The server passes the stored data to an analytics module, which uses machine learning algorithms (e.g., KMeans and Linear Regression) to analyze the user's skills and goals. The inputs are the user's grades, ratings, and self-reported data stored in the database. The output identifies patterns in the user's career path and skill set.

[0214] Step 4:

[0215] The server's analysis module uses the patterns extracted from the data to generate appropriate advice and recommendations in the feedback module. For example, if a user is interested in project management, recommendations such as "take an introductory project management course" or "pursue PMP certification" are generated. The input is the analyzed data, and the output is the generated feedback.

[0216] Step 5:

[0217] The server sends the generated feedback to the user's device, allowing the user to check it in real time. The application on the device displays the received feedback in an easy-to-understand manner to the user. For example, in response to a user's career consultation, specific advice such as "Start studying using dedicated physics and chemistry problem sets" is displayed. The input is the generated feedback, and the output is a notification to the user.

[0218] Step 6:

[0219] Users enter their career goals and skill sets in a virtual store (VR environment). The user's data is entered through the VR headset and sent to the server. The input data includes text and numerical data.

[0220] Step 7:

[0221] The server's machine learning module analyzes user data collected in the virtual store and recommends appropriate products and services. Recommendations include educational courses, certification programs, and specialized books. The input is the data collected in the virtual store, and the output is the recommended products and services.

[0222] Step 8:

[0223] The server presents recommended products and services to the user through a virtual reality device. The user can then review the recommendations and select the appropriate product within the VR environment. The input is the recommended product or service, and the output is the display through the VR device. For example, specific recommendations such as "an introductory course in project management" or "subscription to specialized book XYZ" are presented.

[0224] Through the above processing steps, users can effectively find products and services that will help them find the career path and improve their skills that are best suited to them.

[0225] 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.

[0226] The system of the present invention collects grades, evaluations, and self-reported data from users to provide individualized guidance and career counseling, and combines this with an emotion engine that recognizes the user's emotions to provide highly accurate feedback. Specific embodiments for implementing this system are described below.

[0227] Data collection

[0228] The server collects grades, evaluations, and self-reported data entered by users through their devices. For example, users enter their academic records, work history, skill sets, career goals, etc., using web forms or dedicated applications. The emotion engine also works to recognize users' emotional states in real time during input and interactions.

[0229] Data analysis

[0230] The collected data is stored by the server and passed to the analysis module, which uses machine learning algorithms and statistical methods to identify patterns based on users' skills and goals. For example, data mining techniques are used to predict the degree to which a particular skill set contributes to career success. Cluster analysis is also used to identify user groups with similar characteristics. At the same time, user emotional data recognized by the emotion engine is also taken into account in the analysis.

[0231] Feedback Generation

[0232] Based on the analysis results, the feedback module generates advice and recommendations tailored to the user. For example, if the emotion engine detects that the user's stress level is high, it can suggest a flexible schedule for skill development. The feedback is tailored according to the user's emotional state.

[0233] Providing Feedback

[0234] The generated feedback is sent from the server to the user's device, where the user can check the feedback content in real time. For example, if a student user requests career counseling, the system will provide specific advice such as "Start studying by using dedicated physics and chemistry problem sets," while using emotionally appropriate expressions to attract the user's attention.

[0235] Emotion Engine

[0236] The emotion engine uses natural language processing and image analysis techniques to recognize emotions from user input data and interactions. For example, if a user uses a camera, it uses facial expression recognition technology to analyze the user's emotions. For text input, it infers emotions from the context. Emotion data is updated in real time and provided to the analysis module.

[0237] Ongoing support

[0238] The system periodically monitors the user's progress and provides new feedback and advice as needed. Users can continually input new performance, skill, and emotional information into the system to receive the most up-to-date advice.

[0239] Specific examples

[0240] For example, if a working user wants career advice, the system works as follows:

[0241] 1. User data entry

[0242] Users enter their current job description, past work experience, skill set, and career goals.

[0243] The device sends the input data to the server, and the emotion engine recognizes the user's stress level and motivation.

[0244] 2. Data Analysis

[0245] The server uses machine learning algorithms to analyze user information, while also taking into account emotional data.

[0246] As a result of the analysis, an appropriate career plan is developed based on the user's skills and career goals.

[0247] 3. Generating and Providing Feedback

[0248] The server generates feedback such as, "As a next step, take an introductory project management course and aim to obtain PMP certification." If the user's stress level is recognized by the emotion engine as high, the server will also take into consideration such as "proposing a flexible schedule."

[0249] The terminal notifies the user of the generated feedback and displays the details.

[0250] In this way, the system of the present invention can provide more precise support for individualized tutoring and career counseling in educational institutions and workplaces by combining the emotion engine. By analyzing emotion data in addition to the user's grades, evaluations, and self-reported data, the system can provide more personalized advice and maximize the user's skills and goals.

[0251] The processing flow will be explained below.

[0252] Step 1:

[0253] Users log into the system using a terminal. New users create an account and log in after verifying their email.

[0254] Step 2:

[0255] Users enter performance, evaluation, and self-reported data into a form, such as current job description, past work experience, skill set, and career goals.

[0256] Step 3:

[0257] The device sends the entered data to the server. The input is checked in real time and errors are checked. The emotion engine also recognizes the user's emotions and sends that data to the server.

[0258] Step 4:

[0259] The server stores the data received from the device in a database, which is used for further analysis.

[0260] Step 5:

[0261] The server collects the stored data and passes it to the analysis module. The data includes grades, ratings, and self-reported data, as well as emotional data recognized by the emotion engine.

[0262] Step 6:

[0263] The analytics module uses machine learning algorithms to analyze users' skills and goals. For example, it uses clustering algorithms to identify groups of users with similar career paths and aspirations. It also uses sentiment data to tailor appropriate feedback.

[0264] Step 7:

[0265] The server passes the analysis results to the feedback module, which initiates the next step of generating feedback.

[0266] Step 8:

[0267] The feedback module generates appropriate feedback for the user based on the analysis results. For example, it might recommend, "As a next step, take an introductory project management course and aim to obtain PMP certification." If the emotion engine recognizes that the user's stress level is high, it might additionally suggest, "Create a flexible schedule."

[0268] Step 9:

[0269] The server sends the generated feedback to the user's device, where the user can check the feedback content in real time.

[0270] Step 10:

[0271] Based on the provided feedback, the user may take further action, such as enrolling in a recommended course or trying relaxation techniques to reduce stress.

[0272] Step 11:

[0273] The server periodically monitors the user's progress, collecting data to generate new feedback and advice, and updates the data as the user adds new achievements, skills, and emotions.

[0274] Step 12:

[0275] The terminal notifies and displays regular assessments and new feedback to the user, allowing the user to receive the latest advice from the system.

[0276] Through these specific processing steps, the system of the present invention can provide more accurate support for individualized instruction and career counseling in educational institutions and workplaces by combining the emotion engine. Furthermore, by analyzing emotion data in addition to the user's grades, evaluations, and self-reported data, the system can provide more personalized advice and maximize the user's skills and goals.

[0277] Example 2

[0278] 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."

[0279] Conventional career counseling and guidance systems provide feedback based on users' grades, evaluations, and self-reported data, but because they do not take into account the user's emotional state, the feedback is uniform, making it difficult to provide optimal advice to each individual user.In addition, because the feedback provided does not adequately reflect fluctuations in stress and motivation, users are not sufficiently motivated to take appropriate action.

[0280] 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.

[0281] In this invention, the server includes means for collecting performance, evaluation, and self-reported data as input from users, means for recognizing emotions in real time from the user's input data and interactions, means for analyzing the user's skills and goals based on the collected data and emotional data, means for generating feedback for the user based on the analysis results and emotional data, and means for providing the generated feedback to the user. This makes it possible to comprehensively analyze a variety of data including the user's emotional state and provide personalized feedback optimized for each user.

[0282] "User" refers to an individual who utilizes the system to enter grades, assessments, and self-reported data and receive feedback.

[0283] "Server" refers to the central data processing device that processes and analyzes the data and sentiment data collected from users and generates and provides feedback.

[0284] "Grades" refers to the results of academic or professional evaluations entered by the user, and specific examples include academic grades and evaluation scores at work.

[0285] "Evaluation" refers to external measurements and judgments of a user's skills and abilities, and specifically includes feedback from superiors and the contents of transcripts.

[0286] "Self-reported data" refers to data that users enter into the system as information about themselves, such as their skill set, career goals, and past work history.

[0287] An "emotion engine" refers to a module or program that recognizes and analyzes the user's emotional state in real time from input data and interactions.

[0288] "Analysis Module" refers to a program or software that performs analysis of a user's skills and goals based on collected data and emotional data.

[0289] "Feedback Module" refers to a program or software for generating advice or recommendations to a user based on the results of the Analysis Module and sentiment data.

[0290] "Feedback" refers to advice, recommendations, specific guidelines for action, etc. provided to users, and is generated based on the analysis results.

[0291] "Personalized feedback" refers to feedback that is optimized based on a user's individual performance, ratings, self-reported data, and emotional state.

[0292] A "machine learning algorithm" is a mathematical or statistical method or program used for data analysis, and examples include regression analysis, classification, and clustering methods.

[0293] The system of this invention collects performance, evaluations, and self-reported data from users, analyzes the user's skills and goals based on the collected data, and generates and provides feedback. Furthermore, by incorporating an emotion engine that recognizes emotions in real time from the user's input data and interactions, more personalized feedback can be provided.

[0294] Data collection

[0295] The server collects grades, evaluations, and self-reported data entered by users through their devices. The data is collected by users entering it using web forms or dedicated applications. The system then activates an emotion engine to recognize the user's input data and their emotional state during interactions in real time. For example, the emotion engine uses facial expression recognition and natural language processing technologies to collect data.

[0296] Data analysis

[0297] The server stores the collected data in a database and passes it to the analysis module, which uses Python-based machine learning libraries (e.g., TensorFlow, Scikit-learn) to perform detailed analysis of the user's skills and goals. For example, it uses data mining techniques to predict the degree to which a particular skill set contributes to career success, and cluster analysis to identify user groups with similar characteristics. At the same time, it can also incorporate emotional data into the analysis to obtain results that reflect the user's emotional state.

[0298] Feedback Generation

[0299] Based on the analysis results, the feedback module generates appropriate advice and recommendations for the user. It uses a generative AI model (e.g., GPT-3) to generate expressions that match the user's emotional state. For example, a user with a high stress level might receive thoughtful feedback such as, "Take it easy and take it one step at a time."

[0300] Providing Feedback

[0301] The server sends the generated feedback to the user's device, where the user can check the provided feedback in real time. For example, if a student user is seeking career advice, the system will provide specific advice such as "Start studying using dedicated physics and chemistry problem sets," while also using emotional expressions to attract the user's attention.

[0302] Specific examples

[0303] For example, if a working user wants career advice, the system works as follows:

[0304] 1. Users enter their current job description, past work experience, skill set, and career goals.

[0305] 2. The device sends the input data to the server, and the emotion engine recognizes the user's stress level and motivation.

[0306] 3. The server analyzes the user's information using machine learning algorithms, while also taking into account emotional data.

[0307] 4. The server generates feedback such as, "As your next career step, take an introductory project management course and aim to obtain PMP certification." If the emotion engine recognizes that the stress level is high, it will also take into consideration the need to "suggest a flexible schedule."

[0308] 5. The device notifies the user of the generated feedback and displays its details.

[0309] In this way, by integrating an emotion engine, the system can provide highly personalized feedback according to the user's emotional state, optimally supporting the user's skills and goals.

[0310] The flow of the identification process in the second embodiment will be described with reference to FIG.

[0311] Step 1: User authentication

[0312] A user enters a username and password to log in to the system. The entered authentication information is sent from the terminal to the server. The server checks the authentication information against a database and returns the authentication result to the terminal. If the authentication is successful, the user can proceed to the next step.

[0313] Input: Username, Password

[0314] Output: Authentication success / failure result

[0315] Step 2: Enter self-reported data

[0316] Users enter their academic record, work history, skill set, and career goals through web forms or dedicated applications. The device collects the data, temporarily stores it, and then transmits it to the server.

[0317] Input: academic record, work history, skill set, career goals

[0318] Output: Collected self-reported data

[0319] Step 3: Obtaining emotion data

[0320] When users input data or interact with the device, the emotion engine works to collect real-time emotional data using cameras and natural language processing technology, which is then sent to a server along with self-reported data.

[0321] Input: facial expression recognition data, text input

[0322] Output: Collected emotion data

[0323] Step 4: Save Data

[0324] The server stores the collected self-reported data and emotion data in a database, with error handling to ensure data consistency and safety.

[0325] Input: Self-reported data, emotion data

[0326] Output: Save results to database

[0327] Step 5: Data analysis

[0328] The server passes the stored data to the analysis module, which analyzes the data using Python-based machine learning libraries (e.g., TensorFlow, Scikit-learn). Machine learning algorithms are applied to the collected data to identify patterns based on the user's skills and goals. Emotional data is also added to the analysis to obtain results that take into account the user's emotional state.

[0329] Input: Self-reported data, emotion data

[0330] Output: Analysis results (user skill patterns, goal setting, etc.)

[0331] Step 6: Feedback generation

[0332] The feedback module generates appropriate feedback for the user based on the analysis results and emotional data. It uses a generative AI model (e.g., GPT-3) to generate feedback that matches the user's emotional state. For example, a user with a high stress level can receive feedback that takes their emotions into consideration, such as, "Try not to push yourself too hard, but to take it one step at a time."

[0333] Input: Analysis results, emotion data

[0334] Output: Generated feedback

[0335] Step 7: Provide feedback

[0336] The server sends the generated feedback to the user's device. The user can check the provided feedback in real time. For example, not only is specific advice such as "Start studying using dedicated physics and chemistry problem sets," but encouraging words such as "Don't push yourself too hard, just progress little by little" are also displayed.

[0337] Input: Generated feedback

[0338] Output: Feedback display to the user

[0339] (Application example 2)

[0340] 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."

[0341] Conventional career counseling and career guidance systems only provide feedback based on a user's grades and skill sets, but are unable to provide personalized feedback that takes into account the user's emotional state. Furthermore, customer service support systems in brick-and-mortar stores have struggled to recognize customer emotions in real time and provide appropriate customer service. This can lead to reduced user and customer satisfaction and efficiency.

[0342] The specific processing by the specific processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means. In this invention, the server includes means for collecting performance, evaluation, and self-reported data from users as input, means for analyzing the user's skills and goals based on the collected data, means for generating feedback for the user based on the analysis results, means for providing the generated feedback to the user, means for recognizing the user's emotions in real time and adjusting the feedback content based on the emotional state, and means for periodically monitoring the user's progress and providing new feedback and advice. This enables personalized feedback and customer service that takes into account the emotions of users and customers.

[0343] The "means for collecting grades, evaluations, and self-reported data from users as input" refers to means for collecting grades, evaluations, and self-reported data collected by users via their terminals.

[0344] The "means for analyzing the skills and goals of a user based on collected data" refers to a means for analyzing the skills and goals of a user using collected data.

[0345] The "means for generating feedback to the user based on the analysis results" refers to means for generating appropriate feedback to the user based on the analyzed data.

[0346] The "means for providing the generated feedback to the user" refers to a means for notifying and providing the generated feedback to the user.

[0347] The "means for recognizing a user's emotions in real time and adjusting the feedback content based on the emotional state" refers to a means for recognizing a user's emotions in real time using an emotion engine and adjusting the feedback content based on the emotions.

[0348] "Means for regularly monitoring the user's progress and providing new feedback and advice" refers to means for regularly managing the user's progress and continuously providing new feedback and advice accordingly.

[0349] The "means for providing career counseling" is a means for providing appropriate advice and support for career-related counseling provided to users.

[0350] The "means for providing career guidance" is a means for providing appropriate advice and guidance regarding career paths to users.

[0351] "Means for providing customer service support" refers to a means for supporting customer service staff in physical stores in providing appropriate support based on customer emotions and data.

[0352] The "means for assisting with transfers and job changes" is a means for providing assistance and advice to users regarding transfers and job changes.

[0353] The "means of providing support for preparation for exams and interviews" are means for supporting the user in preparation for exams and interviews.

[0354] The "means for generating and providing an optimal proposal based on the emotional state and history data of a customer" is a means for generating and providing an optimal proposal based on the emotional state and history data of a customer.

[0355] System configuration

[0356] As an embodiment of the invention, this system consists of the following main components: The hardware includes a device used by the user, a camera for recognizing emotional states in real time, and a server running on the backend. The software includes various modules for data collection, analysis, feedback generation, and provision, implemented using libraries such as Python, OpenCV, Dlib, and Scikit-learn.

[0357] Data collection

[0358] The server collects grades, evaluations, and self-reported data provided by users through their devices. This data includes academic achievements, work history, skill sets, and career goals. During this process, an emotion engine also operates, recognizing users' emotional states in real time during input and interactions. The emotion engine uses natural language processing and image analysis techniques to analyze emotions from users' text input and facial expressions.

[0359] Data analysis

[0360] The collected data is stored on a server and passed to an analysis module, which uses machine learning algorithms and statistical methods to identify patterns based on users' skills and goals. For example, data mining techniques are used to predict the degree to which a particular skill set contributes to career success, and cluster analysis is used to identify user groups with similar characteristics. At the same time, user emotional data recognized by the emotion engine is also taken into account in the analysis.

[0361] Feedback generation and provision

[0362] Based on the analysis results, the feedback module generates advice and recommendations tailored to the user. For example, if the emotion engine detects that the user's stress level is high, it will suggest a flexible schedule. The generated feedback is then sent to the user's device via the server.

[0363] Emotion Engine

[0364] The emotion engine uses natural language processing and image analysis techniques to recognize emotions from user input data and interactions. When the user uses a camera, it uses facial expression recognition technology, and when the user inputs text, it infers emotions from the context of the words. Emotion data, updated in real time, is provided to the analysis module.

[0365] Ongoing support

[0366] The system regularly monitors the user's progress and provides new feedback and advice. Users can receive the latest advice by constantly inputting information about their achievements, skills, and emotions into the system. For example, if a working user requests career counseling, the system will recommend specific skills or qualifications to acquire, and will also provide flexible measures to address stress levels.

[0367] Examples and prompts

[0368] Specific examples

[0369] A salesperson at a physical store is wearing smart glasses. When a customer enters the store, the camera recognizes their face and an emotion engine determines their emotional state in real time. For example, if the emotional state is determined to be "happy," the smart glasses display feedback such as, "The customer is favorable, so it would be appropriate to introduce a new product."

[0370] Prompt Sentence Examples

[0371] "Customer emotional state: happy

[0372] Customer purchase history: a list of past purchases

[0373] Customer Feedback: Past Feedback Details

[0374] Use this as a starting point to suggest ways to present new products that will make customers want to buy right away."

[0375] In this way, the system of the present invention can provide more accurate support to users and customers in educational institutions, workplaces, and brick-and-mortar stores by combining it with an emotion engine.

[0376] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[0377] Step 1:

[0378] The server collects grades, evaluations, and self-reported data from users as input. Data collection occurs when users enter data through their devices (such as academic performance, work history, skill sets, and career goals) and send it to the server. An emotion engine also runs, analyzing the user's emotional state in real time as they enter their data. The user's emotional data is also sent to the server.

[0379] Step 2:

[0380] The server analyzes the user's skills and goals based on the collected data. The collected data is stored in a database and passed to the analysis module. The analysis module uses machine learning algorithms to identify patterns in the data. Data processing during this process includes data cleaning, feature extraction, and model application. This allows cluster analysis and data mining techniques to determine the importance of specific skill sets and classify users into groups.

[0381] Step 3:

[0382] The server uses an emotion engine to recognize the user's emotions in real time and provides the results to the analysis module. The emotion engine analyzes the user's text input and image data (e.g., facial expressions). Specifically, it performs emotion analysis based on natural language processing technology and facial expression recognition using image analysis technology. This provides the user's emotional state as numerical data, which is then incorporated into the analysis results.

[0383] Step 4:

[0384] A feedback module is generated based on the collected and analyzed data. The feedback module creates advice and recommendations tailored to the user. For example, if the user is determined to be under high stress, a flexible schedule suggestion that takes this into consideration is generated. Specifically, different forms of feedback text are generated depending on the user's emotional state.

[0385] Step 5:

[0386] The server then provides the generated feedback to the user. This feedback is sent to the user's device in real time, where the user can view suggestions and advice on their device screen. For example, specific feedback such as "Based on your current skill set, your next course should be an introductory project management course" is provided.

[0387] Step 6:

[0388] The server periodically monitors the user's progress and updates the database as new achievements and skills are entered. Based on the updated information, the server regenerates the latest feedback and advice. During this process, the server combines the new input data with existing data and re-analyzes it, ensuring that the most up-to-date advice is always provided.

[0389] Step 7:

[0390] In brick-and-mortar stores, customer service staff wear devices such as smart glasses to recognize the customer's emotional state in real time. An emotion engine uses video data acquired by a camera to operate, and if the result indicates that the customer is happy, specific customer service feedback, such as introductions to new products, is displayed on the device. This allows for optimal customer service for each customer.

[0391] 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.

[0392] 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.

[0393] 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.

[0394] [Second embodiment]

[0395] FIG. 3 shows an example of the configuration of a data processing system 210 according to the second embodiment.

[0396] 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.

[0397] 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).

[0398] 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.

[0399] 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.

[0400] 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).

[0401] 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.

[0402] 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.

[0403] 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.

[0404] 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.

[0405] 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.

[0406] 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."

[0407] The system of the present invention is composed of a series of steps that collects grades, evaluations, and self-reported data from users and then analyzes and provides feedback based on the collected data in order to provide individualized guidance and career counseling. Specific embodiments for implementing this system are described below.

[0408] Data collection

[0409] The server collects grades, assessments, and self-reported data that users enter through their devices, such as academic records, work experience, skill sets, and career goals, using web forms or dedicated applications.

[0410] Data analysis

[0411] The collected data is stored by the server and passed to the analytics module, which uses machine learning algorithms and statistical methods to identify patterns based on users' skills and goals. For example, data mining techniques are used to predict the degree to which a particular skill set contributes to career success. Cluster analysis is also used to identify groups of users with similar characteristics.

[0412] Feedback Generation

[0413] Based on the analysis results, the feedback module generates appropriate advice and recommendations for the user. For example, if a user is interested in project management, the system will recommend "taking an introductory project management course" or "aiming to obtain the PMP certification."

[0414] Providing Feedback

[0415] The generated feedback is sent from the server to the user's device. The user can check the feedback content in real time. For example, if a student user requests career counseling, the system will provide specific advice such as "Start studying using dedicated physics and chemistry problem sets."

[0416] Ongoing support

[0417] The system regularly monitors the user's progress and provides new feedback and advice as needed. Users can continually enter new achievements, skills, and career information into the system to receive up-to-date advice.

[0418] Specific examples

[0419] For example, if a working user wants career advice, the system works as follows:

[0420] 1. User data entry

[0421] Users enter their current job description, past work experience, skill set, and career goals.

[0422] The terminal transmits the input data to the server.

[0423] 2. Data Analysis

[0424] The server analyzes the user's information using machine learning algorithms.

[0425] As a result of the analysis, an appropriate career plan is developed based on the user's skills and career goals.

[0426] 3. Generating and Providing Feedback

[0427] The server generates feedback such as, "As a next step, take an introductory project management course and aim to obtain PMP certification."

[0428] The terminal notifies the user of the generated feedback and displays the details.

[0429] In this way, the system of the present invention can efficiently and effectively provide tutoring and career counseling in educational institutions and workplaces, and maximize users' skills and goals by providing real-time feedback based on their performance, assessments, and self-reported data.

[0430] The processing flow will be explained below.

[0431] Step 1:

[0432] Users log into the system using a terminal. New users create an account and log in after verifying their email.

[0433] Step 2:

[0434] Users enter performance, evaluation, and self-reported data into a form, such as current job description, past work experience, skill set, and career goals.

[0435] Step 3:

[0436] The terminal sends the entered data to the server, which checks the input data in real time and performs error checking.

[0437] Step 4:

[0438] The server stores the data received from the device in a database, which is used for further analysis.

[0439] Step 5:

[0440] The server collects the stored data and passes it to an analytics module, which includes grades, assessments, and self-reported data.

[0441] Step 6:

[0442] The analytics module uses machine learning algorithms to analyze users' skills and goals, for example using clustering algorithms to identify groups of users with similar career paths or aspirations.

[0443] Step 7:

[0444] The server passes the analysis results to the feedback module, which initiates the next step of generating feedback.

[0445] Step 8:

[0446] The feedback module generates appropriate feedback for the user based on the analysis results, for example, recommending that "As a next step, take an introductory project management course and aim to obtain PMP certification."

[0447] Step 9:

[0448] The server sends the generated feedback to the user's device, where the user can check the feedback content in real time.

[0449] Step 10:

[0450] Based on the feedback provided, the user can take the following actions: Initiate an action, such as enrolling in a recommended course.

[0451] Step 11:

[0452] The server periodically monitors the user's progress, collecting data to generate new feedback and advice, and updates the data as the user adds new achievements and skills.

[0453] Step 12:

[0454] The terminal notifies and displays regular assessments and new feedback to the user, allowing the user to receive the latest advice from the system.

[0455] Example 1

[0456] 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."

[0457] Conventional individualized tutoring and career counseling systems often lack real-time feedback based on users' grades, evaluations, and self-reported data, making it difficult to maximize users' skills and goals. Furthermore, they lack a mechanism for continuously providing appropriate advice and recommendations based on the user's progress. This makes it difficult to efficiently support users' growth.

[0458] 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.

[0459] In this invention, the server includes means for collecting data as input from the user, means for analyzing the user's information based on the collected data, means for generating feedback for the user based on the analysis results, means for providing the generated feedback to the user, and means for periodically monitoring the user's progress and providing new feedback and advice, thereby providing appropriate feedback in real time and making it possible to maximize the user's skills and goals.

[0460] "User" refers to an individual or organization that uses the system to input data and receive analysis and feedback.

[0461] "Data" refers to information such as a user's grades, ratings, self-reported data, skill sets, and career goals.

[0462] "Means of collection" refers to the process by which a user inputs data through a terminal and transmits it to a server.

[0463] "Means of analysis" refers to the process of analyzing collected data for patterns and trends using machine learning algorithms and statistical methods.

[0464] "Means of generating feedback" refers to the process of creating appropriate advice and recommendations for users based on the results of data analysis.

[0465] The "means for providing feedback" refers to a process for transmitting the generated feedback to the user's terminal and displaying it in real time.

[0466] "Monitoring" refers to the process of regularly checking the user's progress and providing new feedback or advice as needed.

[0467] "Career counseling" refers to a service that provides users with advice regarding career choices and career paths.

[0468] "Career guidance" refers to a service that provides advice to users on the career path they choose.

[0469] MODE FOR CARRYING OUT THE INVENTION

[0470] The system of the present invention is configured to provide individualized guidance and career counseling by collecting grades, evaluations, and self-reported data from users, and then analyzing and providing feedback based on the collected data. A specific embodiment of this system will be described.

[0471] Data collection

[0472] The server has a means for collecting grades, evaluations, and self-reported data entered by users through terminals. For example, users enter data such as academic achievements, work experience, skill sets, and career goals using a web form or a dedicated application. The terminal checks the format of this data and validates it based on certain rules.

[0473] Data transmission and storage

[0474] When a user enters data and presses the submit button, the terminal sends the data to the server using the HTTPS protocol. When the server receives the data, it first checks whether the data format and content are correct and then saves it in a database, such as MySQL or PostgreSQL.

[0475] Data analysis

[0476] The server passes the collected data to the analysis module, which analyzes the user data using machine learning algorithms and statistical methods implemented in programming languages ​​such as Python and R. Specifically, the module uses the Scikit-Learn library to perform data mining and clustering analysis to analyze how the user's skill set affects their career goals.

[0477] Feedback Generation

[0478] The server then uses the analysis results to activate a feedback module, which uses a generative AI model (such as GPT-3) to generate specific advice and recommendations. The generated feedback is customized for each user and formatted against a template.

[0479] Providing Feedback

[0480] The generated feedback is sent via the server to the user's device, where it is received and notified to the user in real time, displaying detailed information so that the user can immediately check the feedback and take action.

[0481] Ongoing support

[0482] The system also has the means to regularly monitor the user's progress and generate new feedback and advice as needed. Users can continually input new achievements, skills, and career information to receive up-to-date advice, thereby providing ongoing support for the user's development.

[0483] Specific examples

[0484] For example, if a working user wants career advice, the system works as follows:

[0485] 1. User data entry

[0486] Users enter their current job description, past work experience, skill set, and career goals.

[0487] The terminal transmits the input data to the server.

[0488] 2. Data Analysis

[0489] The server analyzes the user's information using machine learning algorithms.

[0490] As a result of the analysis, an appropriate career plan is developed based on the user's skills and career goals.

[0491] 3. Generating and Providing Feedback

[0492] The server generates feedback such as "As a next step, take an introductory course in project management and aim to obtain a qualification."

[0493] The terminal notifies the user of the generated feedback and displays the details.

[0494] Prompt Sentence Examples

[0495] "If users want to improve their programming skills, please recommend what learning resources they should use."

[0496] In this way, the system provides real-time feedback based on users' performance, assessments, and self-reported data to maximize their skills and goals, while providing ongoing support to support their long-term growth.

[0497] As a result, the system of the present invention can efficiently and effectively provide individualized instruction and career counseling in educational institutions and workplaces.

[0498] The flow of the identification process in the first embodiment will be described with reference to FIG.

[0499] Program processing flow

[0500] Step 1:

[0501] Entering User Data

[0502] Users use the terminal to enter their grades, evaluations, and self-reported data into web forms or dedicated applications. The terminal checks the format of the entered data and performs validation. For example, if a user enters "Work experience: 5 years, Education: College graduate, Skills: Python," the terminal checks whether the format is correct. If the format is correct, it proceeds to the next step.

[0503] Input: academic record, work history, skill set, career goals

[0504] Output: Format-checked and validated data

[0505] Step 2:

[0506] Data transmission and storage

[0507] After the user presses the send button, the device securely sends the data to the server using the HTTPS protocol. The server then double-checks the format and content of the received data and stores it in a database, for example, a MySQL database along with the user's ID.

[0508] Input: Format-checked and validated data

[0509] Output: Data stored in the database

[0510] Step 3:

[0511] Analyzing the data

[0512] The server retrieves the stored data from the database and passes it to the analysis module, which analyzes the data using machine learning algorithms implemented in Python or R. For example, it uses Scikit-Learn to perform clustering analysis and analyze the relationship between the user's skills and career goals. As a result of this analysis, appropriate feedback is generated based on the user's data.

[0513] Input: User data retrieved from the database

[0514] Output: User data analysis results

[0515] Step 4:

[0516] Generate feedback

[0517] Based on the results of the analysis module, the server uses a generative AI model (e.g., GPT-3) to generate specific feedback. This feedback is customized for each user and formatted using templates. For example, specific advice such as "As a next step, you should take an introductory project management course and aim to obtain a certification" is generated.

[0518] Input: User data analysis results

[0519] Output: Customized feedback

[0520] Step 5:

[0521] Providing Feedback

[0522] The server sends the generated feedback to the user's device, which notifies the user of the received feedback in real time and displays detailed information. The user can then click the "Start Now" button to directly access the suggested course.

[0523] Input:Customized Feedback

[0524] Output: Feedback provided to the user

[0525] Step 6:

[0526] Ongoing support

[0527] The system periodically monitors the user's progress and prompts them to enter new data and achievements. When new information is received from the user, it analyzes it again and generates and provides new feedback. This ensures that the user always receives the latest advice. For example, if a user acquires a new skill, they can enter that information to receive the latest career advice.

[0528] Input: User progress data, grade update data

[0529] Output: Updated feedback and ongoing advice

[0530] The above is a specific processing flow of the system of the present invention, which allows users to receive effective feedback and advice in real time based on their performance and goals.

[0531] (Application example 1)

[0532] 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."

[0533] In the past, when receiving individual guidance or career counseling, users had to conduct their own research and visit multiple counseling institutions, which was a time-consuming and labor-intensive process. Furthermore, because the feedback provided was general, it was difficult for each individual user to obtain the most appropriate advice. The present invention aims to solve these problems and provide a system that provides individual guidance and career counseling effectively and efficiently.

[0534] 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.

[0535] In this invention, the server includes means for collecting grades, evaluations, and self-reported data from users as input, means for analyzing the user's skills and goals based on the collected data, means for generating feedback for the user based on the analysis results, means for providing the generated feedback to the user, means for the user to input their career goals and skill sets in a virtual store and recommend appropriate products and services based thereon, means for analyzing the user's data using a machine learning algorithm and making appropriate recommendations, and means for presenting the recommendations to the user through a virtual reality device, thereby enabling users to effectively find the career path and skill-up courses, qualifications, and products that are best suited to them.

[0536] "User" refers to an individual who provides performance, assessment, and self-reported data and receives feedback from the system.

[0537] "Grades and evaluations" refers to the achievements the user has achieved in their studies or work, or evaluations from third parties.

[0538] "Self-reported data" refers to information that users voluntarily enter about their career goals, skill sets, work history, etc.

[0539] "Means of collection" refers to the method by which users enter grades, evaluations, and self-reported data into the system and obtain it.

[0540] "Means of analysis" refers to methods of analyzing a user's skills and goals based on collected data using machine learning algorithms and statistical methods.

[0541] "Means for generating feedback" refers to methods for generating next actions or recommendations for users based on the results of data analysis.

[0542] The "means for providing feedback" refers to a method for communicating the generated feedback to the user and displaying it on the browser or application screen.

[0543] "Virtual store" refers to a digital platform that offers and trades goods and services in a virtual environment.

[0544] "Career goals" refer to goals that a user wants to achieve in order to improve their work history or skills.

[0545] "Means for recommending products and services" refers to methods for recommending optimal products and services based on user input data.

[0546] A "machine learning algorithm" is a program that discovers patterns in data and makes predictions and classifications.

[0547] "Means for making recommendations" refers to a method for making suggestions to users based on the results of machine learning.

[0548] "Virtual reality device" refers to a headset or other device used to experience virtual reality.

[0549] "Presenting means" refers to the method by which information is displayed to the user using the virtual reality device.

[0550] The system for implementing this invention aims to collect performance, evaluations, and self-reported data from users, analyze the user's skills and goals based on that data, and provide appropriate feedback. Furthermore, particularly in virtual stores, the system has the function of recommending appropriate products and services based on the user's self-reported information.

[0551] First, the hardware you'll need includes:

[0552] Server (used for data processing and analysis)

[0553] User devices (smartphones, PCs, tablets, etc.)

[0554] Virtual reality devices (VR headsets)

[0555] The software then uses:

[0556] Python (programming language)

[0557] NumPy, Pandas (data processing libraries)

[0558] scikit-learn (machine learning library)

[0559] Data collection

[0560] The server collects grades, assessments, and self-reported data that users enter through their devices. Users enter information about their academic records, work history, skill sets, career goals, and more using dedicated applications and web forms.

[0561] Data analysis

[0562] The collected data is stored on a server and passed to an analytics module, which uses machine learning algorithms and statistical methods to identify patterns based on users' skills and goals. Clustering and regression analysis are used to predict specific skill sets and career success.

[0563] Feedback Generation

[0564] Based on the analysis results, the feedback module generates appropriate advice and recommendations for the user. For example, if a user is interested in project management, the system will recommend "taking an introductory project management course" or "aiming to obtain PMP certification."

[0565] Providing Feedback

[0566] The generated feedback is sent from the server to the user's device, where the user can check the feedback content in real time. For example, if a student user requests career counseling, the system will provide specific advice such as "Start studying using dedicated physics and chemistry problem sets."

[0567] Application in virtual stores

[0568] In the virtual store, users input their career goals and skill sets, and are recommended suitable products and courses based on that data. To do this, machine learning algorithms are used to analyze the user's input data and select the most suitable products and services. The recommendations are presented to the user through a virtual reality device.

[0569] Examples of specific prompts include:

[0570] "I currently work as a software engineer and my career goal is to become a project manager. My current skill set is Python, project management, and data analysis. What courses or certifications would you recommend as my next steps?"

[0571] This system allows users to effectively find the career path and skill-building courses, qualifications, and products that best suit them.

[0572] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[0573] Step 1:

[0574] Users enter their own grades, evaluations, and self-reported data through their terminals. They use dedicated applications or web forms to enter information such as academic achievements, work experience, skill sets, and career goals. This input data is collected and then sent to a server. The input data includes text and numerical data.

[0575] Step 2:

[0576] The server saves the collected input data and stores it in a database. This database stores each user's grades, evaluations, and self-reported data for later analysis. The database stores data in a table structure.

[0577] Step 3:

[0578] The server passes the stored data to an analytics module, which uses machine learning algorithms (e.g., KMeans and Linear Regression) to analyze the user's skills and goals. The inputs are the user's grades, ratings, and self-reported data stored in the database. The output identifies patterns in the user's career path and skill set.

[0579] Step 4:

[0580] The server's analysis module uses the patterns extracted from the data to generate appropriate advice and recommendations in the feedback module. For example, if a user is interested in project management, recommendations such as "take an introductory project management course" or "pursue PMP certification" are generated. The input is the analyzed data, and the output is the generated feedback.

[0581] Step 5:

[0582] The server sends the generated feedback to the user's device, allowing the user to check it in real time. The application on the device displays the received feedback in an easy-to-understand manner to the user. For example, in response to a user's career consultation, specific advice such as "Start studying using dedicated physics and chemistry problem sets" is displayed. The input is the generated feedback, and the output is a notification to the user.

[0583] Step 6:

[0584] Users enter their career goals and skill sets in a virtual store (VR environment). The user's data is entered through the VR headset and sent to the server. The input data includes text and numerical data.

[0585] Step 7:

[0586] The server's machine learning module analyzes user data collected in the virtual store and recommends appropriate products and services. Recommendations include educational courses, certification programs, and specialized books. The input is the data collected in the virtual store, and the output is the recommended products and services.

[0587] Step 8:

[0588] The server presents recommended products and services to the user through a virtual reality device. The user can then review the recommendations and select the appropriate product within the VR environment. The input is the recommended product or service, and the output is the display through the VR device. For example, specific recommendations such as "an introductory course in project management" or "subscription to specialized book XYZ" are presented.

[0589] Through the above processing steps, users can effectively find products and services that will help them find the career path and improve their skills that are best suited to them.

[0590] 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.

[0591] The system of the present invention collects grades, evaluations, and self-reported data from users to provide individualized guidance and career counseling, and combines this with an emotion engine that recognizes the user's emotions to provide highly accurate feedback. Specific embodiments for implementing this system are described below.

[0592] Data collection

[0593] The server collects grades, evaluations, and self-reported data entered by users through their devices. For example, users enter their academic records, work history, skill sets, career goals, etc., using web forms or dedicated applications. The emotion engine also works to recognize users' emotional states in real time during input and interactions.

[0594] Data analysis

[0595] The collected data is stored by the server and passed to the analysis module, which uses machine learning algorithms and statistical methods to identify patterns based on users' skills and goals. For example, data mining techniques are used to predict the degree to which a particular skill set contributes to career success. Cluster analysis is also used to identify user groups with similar characteristics. At the same time, user emotional data recognized by the emotion engine is also taken into account in the analysis.

[0596] Feedback Generation

[0597] Based on the analysis results, the feedback module generates advice and recommendations tailored to the user. For example, if the emotion engine detects that the user's stress level is high, it can suggest a flexible schedule for skill development. The feedback is tailored according to the user's emotional state.

[0598] Providing Feedback

[0599] The generated feedback is sent from the server to the user's device, where the user can check the feedback content in real time. For example, if a student user requests career counseling, the system will provide specific advice such as "Start studying by using dedicated physics and chemistry problem sets," while using emotionally appropriate expressions to attract the user's attention.

[0600] Emotion Engine

[0601] The emotion engine uses natural language processing and image analysis techniques to recognize emotions from user input data and interactions. For example, if a user uses a camera, it uses facial expression recognition technology to analyze the user's emotions. For text input, it infers emotions from the context. Emotion data is updated in real time and provided to the analysis module.

[0602] Ongoing support

[0603] The system periodically monitors the user's progress and provides new feedback and advice as needed. Users can continually input new performance, skill, and emotional information into the system to receive the most up-to-date advice.

[0604] Specific examples

[0605] For example, if a working user wants career advice, the system works as follows:

[0606] 1. User data entry

[0607] Users enter their current job description, past work experience, skill set, and career goals.

[0608] The device sends the input data to the server, and the emotion engine recognizes the user's stress level and motivation.

[0609] 2. Data Analysis

[0610] The server uses machine learning algorithms to analyze user information, while also taking into account emotional data.

[0611] As a result of the analysis, an appropriate career plan is developed based on the user's skills and career goals.

[0612] 3. Generating and Providing Feedback

[0613] The server generates feedback such as, "As a next step, take an introductory project management course and aim to obtain PMP certification." If the user's stress level is recognized by the emotion engine as high, the server will also take into consideration such as "proposing a flexible schedule."

[0614] The terminal notifies the user of the generated feedback and displays the details.

[0615] In this way, the system of the present invention can provide more precise support for individualized tutoring and career counseling in educational institutions and workplaces by combining the emotion engine. By analyzing emotion data in addition to the user's grades, evaluations, and self-reported data, the system can provide more personalized advice and maximize the user's skills and goals.

[0616] The processing flow will be explained below.

[0617] Step 1:

[0618] Users log into the system using a terminal. New users create an account and log in after verifying their email.

[0619] Step 2:

[0620] Users enter performance, evaluation, and self-reported data into a form, such as current job description, past work experience, skill set, and career goals.

[0621] Step 3:

[0622] The device sends the entered data to the server. The input is checked in real time and errors are checked. The emotion engine also recognizes the user's emotions and sends that data to the server.

[0623] Step 4:

[0624] The server stores the data received from the device in a database, which is used for further analysis.

[0625] Step 5:

[0626] The server collects the stored data and passes it to the analysis module. The data includes grades, ratings, and self-reported data, as well as emotional data recognized by the emotion engine.

[0627] Step 6:

[0628] The analytics module uses machine learning algorithms to analyze users' skills and goals. For example, it uses clustering algorithms to identify groups of users with similar career paths and aspirations. It also uses sentiment data to tailor appropriate feedback.

[0629] Step 7:

[0630] The server passes the analysis results to the feedback module, which initiates the next step of generating feedback.

[0631] Step 8:

[0632] The feedback module generates appropriate feedback for the user based on the analysis results. For example, it might recommend, "As a next step, take an introductory project management course and aim to obtain PMP certification." If the emotion engine recognizes that the user's stress level is high, it might additionally suggest, "Create a flexible schedule."

[0633] Step 9:

[0634] The server sends the generated feedback to the user's device, where the user can check the feedback content in real time.

[0635] Step 10:

[0636] Based on the provided feedback, the user may take further action, such as enrolling in a recommended course or trying relaxation techniques to reduce stress.

[0637] Step 11:

[0638] The server periodically monitors the user's progress, collecting data to generate new feedback and advice, and updates the data as the user adds new achievements, skills, and emotions.

[0639] Step 12:

[0640] The terminal notifies and displays regular assessments and new feedback to the user, allowing the user to receive the latest advice from the system.

[0641] Through these specific processing steps, the system of the present invention can provide more accurate support for individualized instruction and career counseling in educational institutions and workplaces by combining the emotion engine. Furthermore, by analyzing emotion data in addition to the user's grades, evaluations, and self-reported data, the system can provide more personalized advice and maximize the user's skills and goals.

[0642] Example 2

[0643] 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."

[0644] Conventional career counseling and guidance systems provide feedback based on users' grades, evaluations, and self-reported data, but because they do not take into account the user's emotional state, the feedback is uniform, making it difficult to provide optimal advice to each individual user.In addition, because the feedback provided does not adequately reflect fluctuations in stress and motivation, users are not sufficiently motivated to take appropriate action.

[0645] 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.

[0646] In this invention, the server includes means for collecting performance, evaluation, and self-reported data as input from users, means for recognizing emotions in real time from the user's input data and interactions, means for analyzing the user's skills and goals based on the collected data and emotional data, means for generating feedback for the user based on the analysis results and emotional data, and means for providing the generated feedback to the user. This makes it possible to comprehensively analyze a variety of data including the user's emotional state and provide personalized feedback optimized for each user.

[0647] "User" refers to an individual who utilizes the system to enter grades, assessments, and self-reported data and receive feedback.

[0648] "Server" refers to the central data processing device that processes and analyzes the data and sentiment data collected from users and generates and provides feedback.

[0649] "Grades" refers to the results of academic or professional evaluations entered by the user, and specific examples include academic grades and evaluation scores at work.

[0650] "Evaluation" refers to external measurements and judgments of a user's skills and abilities, and specifically includes feedback from superiors and the contents of transcripts.

[0651] "Self-reported data" refers to data that users enter into the system as information about themselves, such as their skill set, career goals, and past work history.

[0652] An "emotion engine" refers to a module or program that recognizes and analyzes the user's emotional state in real time from input data and interactions.

[0653] "Analysis Module" refers to a program or software that performs analysis of a user's skills and goals based on collected data and emotional data.

[0654] "Feedback Module" refers to a program or software for generating advice or recommendations to a user based on the results of the Analysis Module and sentiment data.

[0655] "Feedback" refers to advice, recommendations, specific guidelines for action, etc. provided to users, and is generated based on the analysis results.

[0656] "Personalized feedback" refers to feedback that is optimized based on a user's individual performance, ratings, self-reported data, and emotional state.

[0657] A "machine learning algorithm" is a mathematical or statistical method or program used for data analysis, and examples include regression analysis, classification, and clustering methods.

[0658] The system of this invention collects performance, evaluations, and self-reported data from users, analyzes the user's skills and goals based on the collected data, and generates and provides feedback. Furthermore, by incorporating an emotion engine that recognizes emotions in real time from the user's input data and interactions, more personalized feedback can be provided.

[0659] Data collection

[0660] The server collects grades, evaluations, and self-reported data entered by users through their devices. The data is collected by users entering it using web forms or dedicated applications. The system then activates an emotion engine to recognize the user's input data and their emotional state during interactions in real time. For example, the emotion engine uses facial expression recognition and natural language processing technologies to collect data.

[0661] Data analysis

[0662] The server stores the collected data in a database and passes it to the analysis module, which uses Python-based machine learning libraries (e.g., TensorFlow, Scikit-learn) to perform detailed analysis of the user's skills and goals. For example, it uses data mining techniques to predict the degree to which a particular skill set contributes to career success, and cluster analysis to identify user groups with similar characteristics. At the same time, it can also incorporate emotional data into the analysis to obtain results that reflect the user's emotional state.

[0663] Feedback Generation

[0664] Based on the analysis results, the feedback module generates appropriate advice and recommendations for the user. It uses a generative AI model (e.g., GPT-3) to generate expressions that match the user's emotional state. For example, a user with a high stress level might receive thoughtful feedback such as, "Take it easy and take it one step at a time."

[0665] Providing Feedback

[0666] The server sends the generated feedback to the user's device, where the user can check the provided feedback in real time. For example, if a student user is seeking career advice, the system will provide specific advice such as "Start studying using dedicated physics and chemistry problem sets," while also using emotional expressions to attract the user's attention.

[0667] Specific examples

[0668] For example, if a working user wants career advice, the system works as follows:

[0669] 1. Users enter their current job description, past work experience, skill set, and career goals.

[0670] 2. The device sends the input data to the server, and the emotion engine recognizes the user's stress level and motivation.

[0671] 3. The server analyzes the user's information using machine learning algorithms, while also taking into account emotional data.

[0672] 4. The server generates feedback such as, "As your next career step, take an introductory project management course and aim to obtain PMP certification." If the emotion engine recognizes that the stress level is high, it will also take into consideration the need to "suggest a flexible schedule."

[0673] 5. The device notifies the user of the generated feedback and displays its details.

[0674] In this way, by integrating an emotion engine, the system can provide highly personalized feedback according to the user's emotional state, optimally supporting the user's skills and goals.

[0675] The flow of the identification process in the second embodiment will be described with reference to FIG.

[0676] Step 1: User authentication

[0677] A user enters a username and password to log in to the system. The entered authentication information is sent from the terminal to the server. The server checks the authentication information against a database and returns the authentication result to the terminal. If the authentication is successful, the user can proceed to the next step.

[0678] Input: Username, Password

[0679] Output: Authentication success / failure result

[0680] Step 2: Enter self-reported data

[0681] Users enter their academic record, work history, skill set, and career goals through web forms or dedicated applications. The device collects the data, temporarily stores it, and then transmits it to the server.

[0682] Input: academic record, work history, skill set, career goals

[0683] Output: Collected self-reported data

[0684] Step 3: Obtaining emotion data

[0685] When users input data or interact with the device, the emotion engine works to collect real-time emotional data using cameras and natural language processing technology, which is then sent to a server along with self-reported data.

[0686] Input: facial expression recognition data, text input

[0687] Output: Collected emotion data

[0688] Step 4: Save Data

[0689] The server stores the collected self-reported data and emotion data in a database, with error handling to ensure data consistency and safety.

[0690] Input: Self-reported data, emotion data

[0691] Output: Save results to database

[0692] Step 5: Data analysis

[0693] The server passes the stored data to the analysis module, which analyzes the data using Python-based machine learning libraries (e.g., TensorFlow, Scikit-learn). Machine learning algorithms are applied to the collected data to identify patterns based on the user's skills and goals. Emotional data is also added to the analysis to obtain results that take into account the user's emotional state.

[0694] Input: Self-reported data, emotion data

[0695] Output: Analysis results (user skill patterns, goal setting, etc.)

[0696] Step 6: Feedback generation

[0697] The feedback module generates appropriate feedback for the user based on the analysis results and emotional data. It uses a generative AI model (e.g., GPT-3) to generate feedback that matches the user's emotional state. For example, a user with a high stress level can receive feedback that takes their emotions into consideration, such as, "Try not to push yourself too hard, but to take it one step at a time."

[0698] Input: Analysis results, emotion data

[0699] Output: Generated feedback

[0700] Step 7: Provide feedback

[0701] The server sends the generated feedback to the user's device. The user can check the provided feedback in real time. For example, not only is specific advice such as "Start studying using dedicated physics and chemistry problem sets," but encouraging words such as "Don't push yourself too hard, just progress little by little" are also displayed.

[0702] Input: Generated feedback

[0703] Output: Feedback display to the user

[0704] (Application example 2)

[0705] 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."

[0706] Conventional career counseling and career guidance systems only provide feedback based on a user's grades and skill sets, but are unable to provide personalized feedback that takes into account the user's emotional state. Furthermore, customer service support systems in brick-and-mortar stores have struggled to recognize customer emotions in real time and provide appropriate customer service. This can lead to reduced user and customer satisfaction and efficiency.

[0707] The specific processing by the specific processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means. In this invention, the server includes means for collecting performance, evaluation, and self-reported data from users as input, means for analyzing the user's skills and goals based on the collected data, means for generating feedback for the user based on the analysis results, means for providing the generated feedback to the user, means for recognizing the user's emotions in real time and adjusting the feedback content based on the emotional state, and means for periodically monitoring the user's progress and providing new feedback and advice. This enables personalized feedback and customer service that takes into account the emotions of users and customers.

[0708] The "means for collecting grades, evaluations, and self-reported data from users as input" refers to means for collecting grades, evaluations, and self-reported data collected by users via their terminals.

[0709] The "means for analyzing the skills and goals of a user based on collected data" refers to a means for analyzing the skills and goals of a user using collected data.

[0710] The "means for generating feedback to the user based on the analysis results" refers to means for generating appropriate feedback to the user based on the analyzed data.

[0711] The "means for providing the generated feedback to the user" refers to a means for notifying and providing the generated feedback to the user.

[0712] The "means for recognizing a user's emotions in real time and adjusting the feedback content based on the emotional state" refers to a means for recognizing a user's emotions in real time using an emotion engine and adjusting the feedback content based on the emotions.

[0713] "Means for regularly monitoring the user's progress and providing new feedback and advice" refers to means for regularly managing the user's progress and continuously providing new feedback and advice accordingly.

[0714] The "means for providing career counseling" is a means for providing appropriate advice and support for career-related counseling provided to users.

[0715] The "means for providing career guidance" is a means for providing appropriate advice and guidance regarding career paths to users.

[0716] "Means for providing customer service support" refers to a means for supporting customer service staff in physical stores in providing appropriate support based on customer emotions and data.

[0717] The "means for assisting with transfers and job changes" is a means for providing assistance and advice to users regarding transfers and job changes.

[0718] The "means of providing support for preparation for exams and interviews" are means for supporting the user in preparation for exams and interviews.

[0719] The "means for generating and providing an optimal proposal based on the emotional state and history data of a customer" is a means for generating and providing an optimal proposal based on the emotional state and history data of a customer.

[0720] System configuration

[0721] As an embodiment of the invention, this system consists of the following main components: The hardware includes a device used by the user, a camera for recognizing emotional states in real time, and a server running on the backend. The software includes various modules for data collection, analysis, feedback generation, and provision, implemented using libraries such as Python, OpenCV, Dlib, and Scikit-learn.

[0722] Data collection

[0723] The server collects grades, evaluations, and self-reported data provided by users through their devices. This data includes academic achievements, work history, skill sets, and career goals. During this process, an emotion engine also operates, recognizing users' emotional states in real time during input and interactions. The emotion engine uses natural language processing and image analysis techniques to analyze emotions from users' text input and facial expressions.

[0724] Data analysis

[0725] The collected data is stored on a server and passed to an analysis module, which uses machine learning algorithms and statistical methods to identify patterns based on users' skills and goals. For example, data mining techniques are used to predict the degree to which a particular skill set contributes to career success, and cluster analysis is used to identify user groups with similar characteristics. At the same time, user emotional data recognized by the emotion engine is also taken into account in the analysis.

[0726] Feedback generation and provision

[0727] Based on the analysis results, the feedback module generates advice and recommendations tailored to the user. For example, if the emotion engine detects that the user's stress level is high, it will suggest a flexible schedule. The generated feedback is then sent to the user's device via the server.

[0728] Emotion Engine

[0729] The emotion engine uses natural language processing and image analysis techniques to recognize emotions from user input data and interactions. When the user uses a camera, it uses facial expression recognition technology, and when the user inputs text, it infers emotions from the context of the words. Emotion data, updated in real time, is provided to the analysis module.

[0730] Ongoing support

[0731] The system regularly monitors the user's progress and provides new feedback and advice. Users can receive the latest advice by constantly inputting information about their achievements, skills, and emotions into the system. For example, if a working user requests career counseling, the system will recommend specific skills or qualifications to acquire, and will also provide flexible measures to address stress levels.

[0732] Examples and prompts

[0733] Specific examples

[0734] A salesperson at a physical store is wearing smart glasses. When a customer enters the store, the camera recognizes their face and an emotion engine determines their emotional state in real time. For example, if the emotional state is determined to be "happy," the smart glasses display feedback such as, "The customer is favorable, so it would be appropriate to introduce a new product."

[0735] Prompt Sentence Examples

[0736] "Customer emotional state: happy

[0737] Customer purchase history: a list of past purchases

[0738] Customer Feedback: Past Feedback Details

[0739] Use this as a starting point to suggest ways to present new products that will make customers want to buy right away."

[0740] In this way, the system of the present invention can provide more accurate support to users and customers in educational institutions, workplaces, and brick-and-mortar stores by combining it with an emotion engine.

[0741] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[0742] Step 1:

[0743] The server collects grades, evaluations, and self-reported data from users as input. Data collection occurs when users enter data through their devices (such as academic performance, work history, skill sets, and career goals) and send it to the server. An emotion engine also runs, analyzing the user's emotional state in real time as they enter their data. The user's emotional data is also sent to the server.

[0744] Step 2:

[0745] The server analyzes the user's skills and goals based on the collected data. The collected data is stored in a database and passed to the analysis module. The analysis module uses machine learning algorithms to identify patterns in the data. Data processing during this process includes data cleaning, feature extraction, and model application. This allows cluster analysis and data mining techniques to determine the importance of specific skill sets and classify users into groups.

[0746] Step 3:

[0747] The server uses an emotion engine to recognize the user's emotions in real time and provides the results to the analysis module. The emotion engine analyzes the user's text input and image data (e.g., facial expressions). Specifically, it performs emotion analysis based on natural language processing technology and facial expression recognition using image analysis technology. This provides the user's emotional state as numerical data, which is then incorporated into the analysis results.

[0748] Step 4:

[0749] A feedback module is generated based on the collected and analyzed data. The feedback module creates advice and recommendations tailored to the user. For example, if the user is determined to be under high stress, a flexible schedule suggestion that takes this into consideration is generated. Specifically, different forms of feedback text are generated depending on the user's emotional state.

[0750] Step 5:

[0751] The server then provides the generated feedback to the user. This feedback is sent to the user's device in real time, where the user can view suggestions and advice on their device screen. For example, specific feedback such as "Based on your current skill set, your next course should be an introductory project management course" is provided.

[0752] Step 6:

[0753] The server periodically monitors the user's progress and updates the database as new achievements and skills are entered. Based on the updated information, the server regenerates the latest feedback and advice. During this process, the server combines the new input data with existing data and re-analyzes it, ensuring that the most up-to-date advice is always provided.

[0754] Step 7:

[0755] In brick-and-mortar stores, customer service staff wear devices such as smart glasses to recognize the customer's emotional state in real time. An emotion engine uses video data acquired by a camera to operate, and if the result indicates that the customer is happy, specific customer service feedback, such as introductions to new products, is displayed on the device. This allows for optimal customer service for each customer.

[0756] 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.

[0757] 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.

[0758] 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.

[0759] [Third embodiment]

[0760] FIG. 5 shows an example of the configuration of a data processing system 310 according to the third embodiment.

[0761] 5, the data processing system 310 includes the data processing device 12 and a headset type terminal 314. An example of the data processing device 12 is a server.

[0762] 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).

[0763] 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.

[0764] 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.

[0765] 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).

[0766] 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.

[0767] 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.

[0768] 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.

[0769] 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.

[0770] 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.

[0771] 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."

[0772] The system of the present invention is composed of a series of steps that collects grades, evaluations, and self-reported data from users and then analyzes and provides feedback based on the collected data in order to provide individualized guidance and career counseling. Specific embodiments for implementing this system are described below.

[0773] Data collection

[0774] The server collects grades, assessments, and self-reported data that users enter through their devices, such as academic records, work experience, skill sets, and career goals, using web forms or dedicated applications.

[0775] Data analysis

[0776] The collected data is stored by the server and passed to the analytics module, which uses machine learning algorithms and statistical methods to identify patterns based on users' skills and goals. For example, data mining techniques are used to predict the degree to which a particular skill set contributes to career success. Cluster analysis is also used to identify groups of users with similar characteristics.

[0777] Feedback Generation

[0778] Based on the analysis results, the feedback module generates appropriate advice and recommendations for the user. For example, if a user is interested in project management, the system will recommend "taking an introductory project management course" or "aiming to obtain the PMP certification."

[0779] Providing Feedback

[0780] The generated feedback is sent from the server to the user's device. The user can check the feedback content in real time. For example, if a student user requests career counseling, the system will provide specific advice such as "Start studying using dedicated physics and chemistry problem sets."

[0781] Ongoing support

[0782] The system regularly monitors the user's progress and provides new feedback and advice as needed. Users can continually enter new achievements, skills, and career information into the system to receive up-to-date advice.

[0783] Specific examples

[0784] For example, if a working user wants career advice, the system works as follows:

[0785] 1. User data entry

[0786] Users enter their current job description, past work experience, skill set, and career goals.

[0787] The terminal transmits the input data to the server.

[0788] 2. Data Analysis

[0789] The server analyzes the user's information using machine learning algorithms.

[0790] As a result of the analysis, an appropriate career plan is developed based on the user's skills and career goals.

[0791] 3. Generating and Providing Feedback

[0792] The server generates feedback such as, "As a next step, take an introductory project management course and aim to obtain PMP certification."

[0793] The terminal notifies the user of the generated feedback and displays the details.

[0794] In this way, the system of the present invention can efficiently and effectively provide tutoring and career counseling in educational institutions and workplaces, and maximize users' skills and goals by providing real-time feedback based on their performance, assessments, and self-reported data.

[0795] The processing flow will be explained below.

[0796] Step 1:

[0797] Users log into the system using a terminal. New users create an account and log in after verifying their email.

[0798] Step 2:

[0799] Users enter performance, evaluation, and self-reported data into a form, such as current job description, past work experience, skill set, and career goals.

[0800] Step 3:

[0801] The terminal sends the entered data to the server, which checks the input data in real time and performs error checking.

[0802] Step 4:

[0803] The server stores the data received from the device in a database, which is used for further analysis.

[0804] Step 5:

[0805] The server collects the stored data and passes it to an analytics module, which includes grades, assessments, and self-reported data.

[0806] Step 6:

[0807] The analytics module uses machine learning algorithms to analyze users' skills and goals, for example using clustering algorithms to identify groups of users with similar career paths or aspirations.

[0808] Step 7:

[0809] The server passes the analysis results to the feedback module, which initiates the next step of generating feedback.

[0810] Step 8:

[0811] The feedback module generates appropriate feedback for the user based on the analysis results, for example, recommending that "As a next step, take an introductory project management course and aim to obtain PMP certification."

[0812] Step 9:

[0813] The server sends the generated feedback to the user's device, where the user can check the feedback content in real time.

[0814] Step 10:

[0815] Based on the feedback provided, the user can take the following actions: Initiate an action, such as enrolling in a recommended course.

[0816] Step 11:

[0817] The server periodically monitors the user's progress, collecting data to generate new feedback and advice, and updates the data as the user adds new achievements and skills.

[0818] Step 12:

[0819] The terminal notifies and displays regular assessments and new feedback to the user, allowing the user to receive the latest advice from the system.

[0820] Example 1

[0821] 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."

[0822] Conventional individualized tutoring and career counseling systems often lack real-time feedback based on users' grades, evaluations, and self-reported data, making it difficult to maximize users' skills and goals. Furthermore, they lack a mechanism for continuously providing appropriate advice and recommendations based on the user's progress. This makes it difficult to efficiently support users' growth.

[0823] 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.

[0824] In this invention, the server includes means for collecting data as input from the user, means for analyzing the user's information based on the collected data, means for generating feedback for the user based on the analysis results, means for providing the generated feedback to the user, and means for periodically monitoring the user's progress and providing new feedback and advice, thereby providing appropriate feedback in real time and making it possible to maximize the user's skills and goals.

[0825] "User" refers to an individual or organization that uses the system to input data and receive analysis and feedback.

[0826] "Data" refers to information such as a user's grades, ratings, self-reported data, skill sets, and career goals.

[0827] "Means of collection" refers to the process by which a user inputs data through a terminal and transmits it to a server.

[0828] "Means of analysis" refers to the process of analyzing collected data for patterns and trends using machine learning algorithms and statistical methods.

[0829] "Means of generating feedback" refers to the process of creating appropriate advice and recommendations for users based on the results of data analysis.

[0830] The "means for providing feedback" refers to a process for transmitting the generated feedback to the user's terminal and displaying it in real time.

[0831] "Monitoring" refers to the process of regularly checking the user's progress and providing new feedback or advice as needed.

[0832] "Career counseling" refers to a service that provides users with advice regarding career choices and career paths.

[0833] "Career guidance" refers to a service that provides advice to users on the career path they choose.

[0834] MODE FOR CARRYING OUT THE INVENTION

[0835] The system of the present invention is configured to provide individualized guidance and career counseling by collecting grades, evaluations, and self-reported data from users, and then analyzing and providing feedback based on the collected data. A specific embodiment of this system will be described.

[0836] Data collection

[0837] The server has a means for collecting grades, evaluations, and self-reported data entered by users through terminals. For example, users enter data such as academic achievements, work experience, skill sets, and career goals using a web form or a dedicated application. The terminal checks the format of this data and validates it based on certain rules.

[0838] Data transmission and storage

[0839] When a user enters data and presses the submit button, the terminal sends the data to the server using the HTTPS protocol. When the server receives the data, it first checks whether the data format and content are correct and then saves it in a database, such as MySQL or PostgreSQL.

[0840] Data analysis

[0841] The server passes the collected data to the analysis module, which analyzes the user data using machine learning algorithms and statistical methods implemented in programming languages ​​such as Python and R. Specifically, the module uses the Scikit-Learn library to perform data mining and clustering analysis to analyze how the user's skill set affects their career goals.

[0842] Feedback Generation

[0843] The server then uses the analysis results to activate a feedback module, which uses a generative AI model (such as GPT-3) to generate specific advice and recommendations. The generated feedback is customized for each user and formatted against a template.

[0844] Providing Feedback

[0845] The generated feedback is sent via the server to the user's device, where it is received and notified to the user in real time, displaying detailed information so that the user can immediately check the feedback and take action.

[0846] Ongoing support

[0847] The system also has the means to regularly monitor the user's progress and generate new feedback and advice as needed. Users can continually input new achievements, skills, and career information to receive up-to-date advice, thereby providing ongoing support for the user's development.

[0848] Specific examples

[0849] For example, if a working user wants career advice, the system works as follows:

[0850] 1. User data entry

[0851] Users enter their current job description, past work experience, skill set, and career goals.

[0852] The terminal transmits the input data to the server.

[0853] 2. Data Analysis

[0854] The server analyzes the user's information using machine learning algorithms.

[0855] As a result of the analysis, an appropriate career plan is developed based on the user's skills and career goals.

[0856] 3. Generating and Providing Feedback

[0857] The server generates feedback such as "As a next step, take an introductory course in project management and aim to obtain a qualification."

[0858] The terminal notifies the user of the generated feedback and displays the details.

[0859] Prompt Sentence Examples

[0860] "If users want to improve their programming skills, please recommend what learning resources they should use."

[0861] In this way, the system provides real-time feedback based on users' performance, assessments, and self-reported data to maximize their skills and goals, while providing ongoing support to support their long-term growth.

[0862] As a result, the system of the present invention can efficiently and effectively provide individualized instruction and career counseling in educational institutions and workplaces.

[0863] The flow of the identification process in the first embodiment will be described with reference to FIG.

[0864] Program processing flow

[0865] Step 1:

[0866] Entering User Data

[0867] Users use the terminal to enter their grades, evaluations, and self-reported data into web forms or dedicated applications. The terminal checks the format of the entered data and performs validation. For example, if a user enters "Work experience: 5 years, Education: College graduate, Skills: Python," the terminal checks whether the format is correct. If the format is correct, it proceeds to the next step.

[0868] Input: academic record, work history, skill set, career goals

[0869] Output: Format-checked and validated data

[0870] Step 2:

[0871] Data transmission and storage

[0872] After the user presses the send button, the device securely sends the data to the server using the HTTPS protocol. The server then double-checks the format and content of the received data and stores it in a database, for example, a MySQL database along with the user's ID.

[0873] Input: Format-checked and validated data

[0874] Output: Data stored in the database

[0875] Step 3:

[0876] Analyzing the data

[0877] The server retrieves the stored data from the database and passes it to the analysis module, which analyzes the data using machine learning algorithms implemented in Python or R. For example, it uses Scikit-Learn to perform clustering analysis and analyze the relationship between the user's skills and career goals. As a result of this analysis, appropriate feedback is generated based on the user's data.

[0878] Input: User data retrieved from the database

[0879] Output: User data analysis results

[0880] Step 4:

[0881] Generate feedback

[0882] Based on the results of the analysis module, the server uses a generative AI model (e.g., GPT-3) to generate specific feedback. This feedback is customized for each user and formatted using templates. For example, specific advice such as "As a next step, you should take an introductory project management course and aim to obtain a certification" is generated.

[0883] Input: User data analysis results

[0884] Output: Customized feedback

[0885] Step 5:

[0886] Providing Feedback

[0887] The server sends the generated feedback to the user's device, which notifies the user of the received feedback in real time and displays detailed information. The user can then click the "Start Now" button to directly access the suggested course.

[0888] Input:Customized Feedback

[0889] Output: Feedback provided to the user

[0890] Step 6:

[0891] Ongoing support

[0892] The system periodically monitors the user's progress and prompts them to enter new data and achievements. When new information is received from the user, it analyzes it again and generates and provides new feedback. This ensures that the user always receives the latest advice. For example, if a user acquires a new skill, they can enter that information to receive the latest career advice.

[0893] Input: User progress data, grade update data

[0894] Output: Updated feedback and ongoing advice

[0895] The above is a specific processing flow of the system of the present invention, which allows users to receive effective feedback and advice in real time based on their performance and goals.

[0896] (Application example 1)

[0897] 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."

[0898] In the past, when receiving individual guidance or career counseling, users had to conduct their own research and visit multiple counseling institutions, which was a time-consuming and labor-intensive process. Furthermore, because the feedback provided was general, it was difficult for each individual user to obtain the most appropriate advice. The present invention aims to solve these problems and provide a system that provides individual guidance and career counseling effectively and efficiently.

[0899] 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.

[0900] In this invention, the server includes means for collecting grades, evaluations, and self-reported data from users as input, means for analyzing the user's skills and goals based on the collected data, means for generating feedback for the user based on the analysis results, means for providing the generated feedback to the user, means for the user to input their career goals and skill sets in a virtual store and recommend appropriate products and services based thereon, means for analyzing the user's data using a machine learning algorithm and making appropriate recommendations, and means for presenting the recommendations to the user through a virtual reality device, thereby enabling users to effectively find the career path and skill-up courses, qualifications, and products that are best suited to them.

[0901] "User" refers to an individual who provides performance, assessment, and self-reported data and receives feedback from the system.

[0902] "Grades and evaluations" refers to the achievements the user has achieved in their studies or work, or evaluations from third parties.

[0903] "Self-reported data" refers to information that users voluntarily enter about their career goals, skill sets, work history, etc.

[0904] "Means of collection" refers to the method by which users enter grades, evaluations, and self-reported data into the system and obtain it.

[0905] "Means of analysis" refers to methods of analyzing a user's skills and goals based on collected data using machine learning algorithms and statistical methods.

[0906] "Means for generating feedback" refers to methods for generating next actions or recommendations for users based on the results of data analysis.

[0907] The "means for providing feedback" refers to a method for communicating the generated feedback to the user and displaying it on the browser or application screen.

[0908] "Virtual store" refers to a digital platform that offers and trades goods and services in a virtual environment.

[0909] "Career goals" refer to goals that a user wants to achieve in order to improve their work history or skills.

[0910] "Means for recommending products and services" refers to methods for recommending optimal products and services based on user input data.

[0911] A "machine learning algorithm" is a program that discovers patterns in data and makes predictions and classifications.

[0912] "Means for making recommendations" refers to a method for making suggestions to users based on the results of machine learning.

[0913] "Virtual reality device" refers to a headset or other device used to experience virtual reality.

[0914] "Presenting means" refers to the method by which information is displayed to the user using the virtual reality device.

[0915] The system for implementing this invention aims to collect performance, evaluations, and self-reported data from users, analyze the user's skills and goals based on that data, and provide appropriate feedback. Furthermore, particularly in virtual stores, the system has the function of recommending appropriate products and services based on the user's self-reported information.

[0916] First, the hardware you'll need includes:

[0917] Server (used for data processing and analysis)

[0918] User devices (smartphones, PCs, tablets, etc.)

[0919] Virtual reality devices (VR headsets)

[0920] The software then uses:

[0921] Python (programming language)

[0922] NumPy, Pandas (data processing libraries)

[0923] scikit-learn (machine learning library)

[0924] Data collection

[0925] The server collects grades, assessments, and self-reported data that users enter through their devices. Users enter information about their academic records, work history, skill sets, career goals, and more using dedicated applications and web forms.

[0926] Data analysis

[0927] The collected data is stored on a server and passed to an analytics module, which uses machine learning algorithms and statistical methods to identify patterns based on users' skills and goals. Clustering and regression analysis are used to predict specific skill sets and career success.

[0928] Feedback Generation

[0929] Based on the analysis results, the feedback module generates appropriate advice and recommendations for the user. For example, if a user is interested in project management, the system will recommend "taking an introductory project management course" or "aiming to obtain PMP certification."

[0930] Providing Feedback

[0931] The generated feedback is sent from the server to the user's device, where the user can check the feedback content in real time. For example, if a student user requests career counseling, the system will provide specific advice such as "Start studying using dedicated physics and chemistry problem sets."

[0932] Application in virtual stores

[0933] In the virtual store, users input their career goals and skill sets, and are recommended suitable products and courses based on that data. To do this, machine learning algorithms are used to analyze the user's input data and select the most suitable products and services. The recommendations are presented to the user through a virtual reality device.

[0934] Examples of specific prompts include:

[0935] "I currently work as a software engineer and my career goal is to become a project manager. My current skill set is Python, project management, and data analysis. What courses or certifications would you recommend as my next steps?"

[0936] This system allows users to effectively find the career path and skill-building courses, qualifications, and products that best suit them.

[0937] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[0938] Step 1:

[0939] Users enter their own grades, evaluations, and self-reported data through their terminals. They use dedicated applications or web forms to enter information such as academic achievements, work experience, skill sets, and career goals. This input data is collected and then sent to a server. The input data includes text and numerical data.

[0940] Step 2:

[0941] The server saves the collected input data and stores it in a database. This database stores each user's grades, evaluations, and self-reported data for later analysis. The database stores data in a table structure.

[0942] Step 3:

[0943] The server passes the stored data to an analytics module, which uses machine learning algorithms (e.g., KMeans and Linear Regression) to analyze the user's skills and goals. The inputs are the user's grades, ratings, and self-reported data stored in the database. The output identifies patterns in the user's career path and skill set.

[0944] Step 4:

[0945] The server's analysis module uses the patterns extracted from the data to generate appropriate advice and recommendations in the feedback module. For example, if a user is interested in project management, recommendations such as "take an introductory project management course" or "pursue PMP certification" are generated. The input is the analyzed data, and the output is the generated feedback.

[0946] Step 5:

[0947] The server sends the generated feedback to the user's device, allowing the user to check it in real time. The application on the device displays the received feedback in an easy-to-understand manner to the user. For example, in response to a user's career consultation, specific advice such as "Start studying using dedicated physics and chemistry problem sets" is displayed. The input is the generated feedback, and the output is a notification to the user.

[0948] Step 6:

[0949] Users enter their career goals and skill sets in a virtual store (VR environment). The user's data is entered through the VR headset and sent to the server. The input data includes text and numerical data.

[0950] Step 7:

[0951] The server's machine learning module analyzes user data collected in the virtual store and recommends appropriate products and services. Recommendations include educational courses, certification programs, and specialized books. The input is the data collected in the virtual store, and the output is the recommended products and services.

[0952] Step 8:

[0953] The server presents recommended products and services to the user through a virtual reality device. The user can then review the recommendations and select the appropriate product within the VR environment. The input is the recommended product or service, and the output is the display through the VR device. For example, specific recommendations such as "an introductory course in project management" or "subscription to specialized book XYZ" are presented.

[0954] Through the above processing steps, users can effectively find products and services that will help them find the career path and improve their skills that are best suited to them.

[0955] 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.

[0956] The system of the present invention collects grades, evaluations, and self-reported data from users to provide individualized guidance and career counseling, and combines this with an emotion engine that recognizes the user's emotions to provide highly accurate feedback. Specific embodiments for implementing this system are described below.

[0957] Data collection

[0958] The server collects grades, evaluations, and self-reported data entered by users through their devices. For example, users enter their academic records, work history, skill sets, career goals, etc., using web forms or dedicated applications. The emotion engine also works to recognize users' emotional states in real time during input and interactions.

[0959] Data analysis

[0960] The collected data is stored by the server and passed to the analysis module, which uses machine learning algorithms and statistical methods to identify patterns based on users' skills and goals. For example, data mining techniques are used to predict the degree to which a particular skill set contributes to career success. Cluster analysis is also used to identify user groups with similar characteristics. At the same time, user emotional data recognized by the emotion engine is also taken into account in the analysis.

[0961] Feedback Generation

[0962] Based on the analysis results, the feedback module generates advice and recommendations tailored to the user. For example, if the emotion engine detects that the user's stress level is high, it can suggest a flexible schedule for skill development. The feedback is tailored according to the user's emotional state.

[0963] Providing Feedback

[0964] The generated feedback is sent from the server to the user's device, where the user can check the feedback content in real time. For example, if a student user requests career counseling, the system will provide specific advice such as "Start studying by using dedicated physics and chemistry problem sets," while using emotionally appropriate expressions to attract the user's attention.

[0965] Emotion Engine

[0966] The emotion engine uses natural language processing and image analysis techniques to recognize emotions from user input data and interactions. For example, if a user uses a camera, it uses facial expression recognition technology to analyze the user's emotions. For text input, it infers emotions from the context. Emotion data is updated in real time and provided to the analysis module.

[0967] Ongoing support

[0968] The system periodically monitors the user's progress and provides new feedback and advice as needed. Users can continually input new performance, skill, and emotional information into the system to receive the most up-to-date advice.

[0969] Specific examples

[0970] For example, if a working user wants career advice, the system works as follows:

[0971] 1. User data entry

[0972] Users enter their current job description, past work experience, skill set, and career goals.

[0973] The device sends the input data to the server, and the emotion engine recognizes the user's stress level and motivation.

[0974] 2. Data Analysis

[0975] The server uses machine learning algorithms to analyze user information, while also taking into account emotional data.

[0976] As a result of the analysis, an appropriate career plan is developed based on the user's skills and career goals.

[0977] 3. Generating and Providing Feedback

[0978] The server generates feedback such as, "As a next step, take an introductory project management course and aim to obtain PMP certification." If the user's stress level is recognized by the emotion engine as high, the server will also take into consideration such as "proposing a flexible schedule."

[0979] The terminal notifies the user of the generated feedback and displays the details.

[0980] In this way, the system of the present invention can provide more precise support for individualized tutoring and career counseling in educational institutions and workplaces by combining the emotion engine. By analyzing emotion data in addition to the user's grades, evaluations, and self-reported data, the system can provide more personalized advice and maximize the user's skills and goals.

[0981] The processing flow will be explained below.

[0982] Step 1:

[0983] Users log into the system using a terminal. New users create an account and log in after verifying their email.

[0984] Step 2:

[0985] Users enter performance, evaluation, and self-reported data into a form, such as current job description, past work experience, skill set, and career goals.

[0986] Step 3:

[0987] The device sends the entered data to the server. The input is checked in real time and errors are checked. The emotion engine also recognizes the user's emotions and sends that data to the server.

[0988] Step 4:

[0989] The server stores the data received from the device in a database, which is used for further analysis.

[0990] Step 5:

[0991] The server collects the stored data and passes it to the analysis module. The data includes grades, ratings, and self-reported data, as well as emotional data recognized by the emotion engine.

[0992] Step 6:

[0993] The analytics module uses machine learning algorithms to analyze users' skills and goals. For example, it uses clustering algorithms to identify groups of users with similar career paths and aspirations. It also uses sentiment data to tailor appropriate feedback.

[0994] Step 7:

[0995] The server passes the analysis results to the feedback module, which initiates the next step of generating feedback.

[0996] Step 8:

[0997] The feedback module generates appropriate feedback for the user based on the analysis results. For example, it might recommend, "As a next step, take an introductory project management course and aim to obtain PMP certification." If the emotion engine recognizes that the user's stress level is high, it might additionally suggest, "Create a flexible schedule."

[0998] Step 9:

[0999] The server sends the generated feedback to the user's device, where the user can check the feedback content in real time.

[1000] Step 10:

[1001] Based on the provided feedback, the user may take further action, such as enrolling in a recommended course or trying relaxation techniques to reduce stress.

[1002] Step 11:

[1003] The server periodically monitors the user's progress, collecting data to generate new feedback and advice, and updates the data as the user adds new achievements, skills, and emotions.

[1004] Step 12:

[1005] The terminal notifies and displays regular assessments and new feedback to the user, allowing the user to receive the latest advice from the system.

[1006] Through these specific processing steps, the system of the present invention can provide more accurate support for individualized instruction and career counseling in educational institutions and workplaces by combining the emotion engine. Furthermore, by analyzing emotion data in addition to the user's grades, evaluations, and self-reported data, the system can provide more personalized advice and maximize the user's skills and goals.

[1007] Example 2

[1008] 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."

[1009] Conventional career counseling and guidance systems provide feedback based on users' grades, evaluations, and self-reported data, but because they do not take into account the user's emotional state, the feedback is uniform, making it difficult to provide optimal advice to each individual user.In addition, because the feedback provided does not adequately reflect fluctuations in stress and motivation, users are not sufficiently motivated to take appropriate action.

[1010] 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.

[1011] In this invention, the server includes means for collecting performance, evaluation, and self-reported data as input from users, means for recognizing emotions in real time from the user's input data and interactions, means for analyzing the user's skills and goals based on the collected data and emotional data, means for generating feedback for the user based on the analysis results and emotional data, and means for providing the generated feedback to the user. This makes it possible to comprehensively analyze a variety of data including the user's emotional state and provide personalized feedback optimized for each user.

[1012] "User" refers to an individual who utilizes the system to enter grades, assessments, and self-reported data and receive feedback.

[1013] "Server" refers to the central data processing device that processes and analyzes the data and sentiment data collected from users and generates and provides feedback.

[1014] "Grades" refers to the results of academic or professional evaluations entered by the user, and specific examples include academic grades and evaluation scores at work.

[1015] "Evaluation" refers to external measurements and judgments of a user's skills and abilities, and specifically includes feedback from superiors and the contents of transcripts.

[1016] "Self-reported data" refers to data that users enter into the system as information about themselves, such as their skill set, career goals, and past work history.

[1017] An "emotion engine" refers to a module or program that recognizes and analyzes the user's emotional state in real time from input data and interactions.

[1018] "Analysis Module" refers to a program or software that performs analysis of a user's skills and goals based on collected data and emotional data.

[1019] "Feedback Module" refers to a program or software for generating advice or recommendations to a user based on the results of the Analysis Module and sentiment data.

[1020] "Feedback" refers to advice, recommendations, specific guidelines for action, etc. provided to users, and is generated based on the analysis results.

[1021] "Personalized feedback" refers to feedback that is optimized based on a user's individual performance, ratings, self-reported data, and emotional state.

[1022] A "machine learning algorithm" is a mathematical or statistical method or program used for data analysis, and examples include regression analysis, classification, and clustering methods.

[1023] The system of this invention collects performance, evaluations, and self-reported data from users, analyzes the user's skills and goals based on the collected data, and generates and provides feedback. Furthermore, by incorporating an emotion engine that recognizes emotions in real time from the user's input data and interactions, more personalized feedback can be provided.

[1024] Data collection

[1025] The server collects grades, evaluations, and self-reported data entered by users through their devices. The data is collected by users entering it using web forms or dedicated applications. The system then activates an emotion engine to recognize the user's input data and their emotional state during interactions in real time. For example, the emotion engine uses facial expression recognition and natural language processing technologies to collect data.

[1026] Data analysis

[1027] The server stores the collected data in a database and passes it to the analysis module, which uses Python-based machine learning libraries (e.g., TensorFlow, Scikit-learn) to perform detailed analysis of the user's skills and goals. For example, it uses data mining techniques to predict the degree to which a particular skill set contributes to career success, and cluster analysis to identify user groups with similar characteristics. At the same time, it can also incorporate emotional data into the analysis to obtain results that reflect the user's emotional state.

[1028] Feedback Generation

[1029] Based on the analysis results, the feedback module generates appropriate advice and recommendations for the user. It uses a generative AI model (e.g., GPT-3) to generate expressions that match the user's emotional state. For example, a user with a high stress level might receive thoughtful feedback such as, "Take it easy and take it one step at a time."

[1030] Providing Feedback

[1031] The server sends the generated feedback to the user's device, where the user can check the provided feedback in real time. For example, if a student user is seeking career advice, the system will provide specific advice such as "Start studying using dedicated physics and chemistry problem sets," while also using emotional expressions to attract the user's attention.

[1032] Specific examples

[1033] For example, if a working user wants career advice, the system works as follows:

[1034] 1. Users enter their current job description, past work experience, skill set, and career goals.

[1035] 2. The device sends the input data to the server, and the emotion engine recognizes the user's stress level and motivation.

[1036] 3. The server analyzes the user's information using machine learning algorithms, while also taking into account emotional data.

[1037] 4. The server generates feedback such as, "As your next career step, take an introductory project management course and aim to obtain PMP certification." If the emotion engine recognizes that the stress level is high, it will also take into consideration the need to "suggest a flexible schedule."

[1038] 5. The device notifies the user of the generated feedback and displays its details.

[1039] In this way, by integrating an emotion engine, the system can provide highly personalized feedback according to the user's emotional state, optimally supporting the user's skills and goals.

[1040] The flow of the identification process in the second embodiment will be described with reference to FIG.

[1041] Step 1: User authentication

[1042] A user enters a username and password to log in to the system. The entered authentication information is sent from the terminal to the server. The server checks the authentication information against a database and returns the authentication result to the terminal. If the authentication is successful, the user can proceed to the next step.

[1043] Input: Username, Password

[1044] Output: Authentication success / failure result

[1045] Step 2: Enter self-reported data

[1046] Users enter their academic record, work history, skill set, and career goals through web forms or dedicated applications. The device collects the data, temporarily stores it, and then transmits it to the server.

[1047] Input: academic record, work history, skill set, career goals

[1048] Output: Collected self-reported data

[1049] Step 3: Obtaining emotion data

[1050] When users input data or interact with the device, the emotion engine works to collect real-time emotional data using cameras and natural language processing technology, which is then sent to a server along with self-reported data.

[1051] Input: facial expression recognition data, text input

[1052] Output: Collected emotion data

[1053] Step 4: Save Data

[1054] The server stores the collected self-reported data and emotion data in a database, with error handling to ensure data consistency and safety.

[1055] Input: Self-reported data, emotion data

[1056] Output: Save results to database

[1057] Step 5: Data analysis

[1058] The server passes the stored data to the analysis module, which analyzes the data using Python-based machine learning libraries (e.g., TensorFlow, Scikit-learn). Machine learning algorithms are applied to the collected data to identify patterns based on the user's skills and goals. Emotional data is also added to the analysis to obtain results that take into account the user's emotional state.

[1059] Input: Self-reported data, emotion data

[1060] Output: Analysis results (user skill patterns, goal setting, etc.)

[1061] Step 6: Feedback generation

[1062] The feedback module generates appropriate feedback for the user based on the analysis results and emotional data. It uses a generative AI model (e.g., GPT-3) to generate feedback that matches the user's emotional state. For example, a user with a high stress level can receive feedback that takes their emotions into consideration, such as, "Try not to push yourself too hard, but to take it one step at a time."

[1063] Input: Analysis results, emotion data

[1064] Output: Generated feedback

[1065] Step 7: Provide feedback

[1066] The server sends the generated feedback to the user's device. The user can check the provided feedback in real time. For example, not only is specific advice such as "Start studying using dedicated physics and chemistry problem sets," but encouraging words such as "Don't push yourself too hard, just progress little by little" are also displayed.

[1067] Input: Generated feedback

[1068] Output: Feedback display to the user

[1069] (Application example 2)

[1070] 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."

[1071] Conventional career counseling and career guidance systems only provide feedback based on a user's grades and skill sets, but are unable to provide personalized feedback that takes into account the user's emotional state. Furthermore, customer service support systems in brick-and-mortar stores have struggled to recognize customer emotions in real time and provide appropriate customer service. This can lead to reduced user and customer satisfaction and efficiency.

[1072] The specific processing by the specific processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means. In this invention, the server includes means for collecting performance, evaluation, and self-reported data from users as input, means for analyzing the user's skills and goals based on the collected data, means for generating feedback for the user based on the analysis results, means for providing the generated feedback to the user, means for recognizing the user's emotions in real time and adjusting the feedback content based on the emotional state, and means for periodically monitoring the user's progress and providing new feedback and advice. This enables personalized feedback and customer service that takes into account the emotions of users and customers.

[1073] The "means for collecting grades, evaluations, and self-reported data from users as input" refers to means for collecting grades, evaluations, and self-reported data collected by users via their terminals.

[1074] The "means for analyzing the skills and goals of a user based on collected data" refers to a means for analyzing the skills and goals of a user using collected data.

[1075] The "means for generating feedback to the user based on the analysis results" refers to means for generating appropriate feedback to the user based on the analyzed data.

[1076] The "means for providing the generated feedback to the user" refers to a means for notifying and providing the generated feedback to the user.

[1077] The "means for recognizing a user's emotions in real time and adjusting the feedback content based on the emotional state" refers to a means for recognizing a user's emotions in real time using an emotion engine and adjusting the feedback content based on the emotions.

[1078] "Means for regularly monitoring the user's progress and providing new feedback and advice" refers to means for regularly managing the user's progress and continuously providing new feedback and advice accordingly.

[1079] The "means for providing career counseling" is a means for providing appropriate advice and support for career-related counseling provided to users.

[1080] The "means for providing career guidance" is a means for providing appropriate advice and guidance regarding career paths to users.

[1081] "Means for providing customer service support" refers to a means for supporting customer service staff in physical stores in providing appropriate support based on customer emotions and data.

[1082] The "means for assisting with transfers and job changes" is a means for providing assistance and advice to users regarding transfers and job changes.

[1083] The "means of providing support for preparation for exams and interviews" are means for supporting the user in preparation for exams and interviews.

[1084] The "means for generating and providing an optimal proposal based on the emotional state and history data of a customer" is a means for generating and providing an optimal proposal based on the emotional state and history data of a customer.

[1085] System configuration

[1086] As an embodiment of the invention, this system consists of the following main components: The hardware includes a device used by the user, a camera for recognizing emotional states in real time, and a server running on the backend. The software includes various modules for data collection, analysis, feedback generation, and provision, implemented using libraries such as Python, OpenCV, Dlib, and Scikit-learn.

[1087] Data collection

[1088] The server collects grades, evaluations, and self-reported data provided by users through their devices. This data includes academic achievements, work history, skill sets, and career goals. During this process, an emotion engine also operates, recognizing users' emotional states in real time during input and interactions. The emotion engine uses natural language processing and image analysis techniques to analyze emotions from users' text input and facial expressions.

[1089] Data analysis

[1090] The collected data is stored on a server and passed to an analysis module, which uses machine learning algorithms and statistical methods to identify patterns based on users' skills and goals. For example, data mining techniques are used to predict the degree to which a particular skill set contributes to career success, and cluster analysis is used to identify user groups with similar characteristics. At the same time, user emotional data recognized by the emotion engine is also taken into account in the analysis.

[1091] Feedback generation and provision

[1092] Based on the analysis results, the feedback module generates advice and recommendations tailored to the user. For example, if the emotion engine detects that the user's stress level is high, it will suggest a flexible schedule. The generated feedback is then sent to the user's device via the server.

[1093] Emotion Engine

[1094] The emotion engine uses natural language processing and image analysis techniques to recognize emotions from user input data and interactions. When the user uses a camera, it uses facial expression recognition technology, and when the user inputs text, it infers emotions from the context of the words. Emotion data, updated in real time, is provided to the analysis module.

[1095] Ongoing support

[1096] The system regularly monitors the user's progress and provides new feedback and advice. Users can receive the latest advice by constantly inputting information about their achievements, skills, and emotions into the system. For example, if a working user requests career counseling, the system will recommend specific skills or qualifications to acquire, and will also provide flexible measures to address stress levels.

[1097] Examples and prompts

[1098] Specific examples

[1099] A salesperson at a physical store is wearing smart glasses. When a customer enters the store, the camera recognizes their face and an emotion engine determines their emotional state in real time. For example, if the emotional state is determined to be "happy," the smart glasses display feedback such as, "The customer is favorable, so it would be appropriate to introduce a new product."

[1100] Prompt Sentence Examples

[1101] "Customer emotional state: happy

[1102] Customer purchase history: a list of past purchases

[1103] Customer Feedback: Past Feedback Details

[1104] Use this as a starting point to suggest ways to present new products that will make customers want to buy right away."

[1105] In this way, the system of the present invention can provide more accurate support to users and customers in educational institutions, workplaces, and brick-and-mortar stores by combining it with an emotion engine.

[1106] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[1107] Step 1:

[1108] The server collects grades, evaluations, and self-reported data from users as input. Data collection occurs when users enter data through their devices (such as academic performance, work history, skill sets, and career goals) and send it to the server. An emotion engine also runs, analyzing the user's emotional state in real time as they enter their data. The user's emotional data is also sent to the server.

[1109] Step 2:

[1110] The server analyzes the user's skills and goals based on the collected data. The collected data is stored in a database and passed to the analysis module. The analysis module uses machine learning algorithms to identify patterns in the data. Data processing during this process includes data cleaning, feature extraction, and model application. This allows cluster analysis and data mining techniques to determine the importance of specific skill sets and classify users into groups.

[1111] Step 3:

[1112] The server uses an emotion engine to recognize the user's emotions in real time and provides the results to the analysis module. The emotion engine analyzes the user's text input and image data (e.g., facial expressions). Specifically, it performs emotion analysis based on natural language processing technology and facial expression recognition using image analysis technology. This provides the user's emotional state as numerical data, which is then incorporated into the analysis results.

[1113] Step 4:

[1114] A feedback module is generated based on the collected and analyzed data. The feedback module creates advice and recommendations tailored to the user. For example, if the user is determined to be under high stress, a flexible schedule suggestion that takes this into consideration is generated. Specifically, different forms of feedback text are generated depending on the user's emotional state.

[1115] Step 5:

[1116] The server then provides the generated feedback to the user. This feedback is sent to the user's device in real time, where the user can view suggestions and advice on their device screen. For example, specific feedback such as "Based on your current skill set, your next course should be an introductory project management course" is provided.

[1117] Step 6:

[1118] The server periodically monitors the user's progress and updates the database as new achievements and skills are entered. Based on the updated information, the server regenerates the latest feedback and advice. During this process, the server combines the new input data with existing data and re-analyzes it, ensuring that the most up-to-date advice is always provided.

[1119] Step 7:

[1120] In brick-and-mortar stores, customer service staff wear devices such as smart glasses to recognize the customer's emotional state in real time. An emotion engine uses video data acquired by a camera to operate, and if the result indicates that the customer is happy, specific customer service feedback, such as introductions to new products, is displayed on the device. This allows for optimal customer service for each customer.

[1121] 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.

[1122] 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.

[1123] 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.

[1124] [Fourth embodiment]

[1125] FIG. 7 shows an example of the configuration of a data processing system 410 according to the fourth embodiment.

[1126] 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.

[1127] 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).

[1128] 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.

[1129] 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.

[1130] 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).

[1131] 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.

[1132] 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.

[1133] 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.

[1134] 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.

[1135] 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.

[1136] 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.

[1137] 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."

[1138] The system of the present invention is composed of a series of steps that collects grades, evaluations, and self-reported data from users and then analyzes and provides feedback based on the collected data in order to provide individualized guidance and career counseling. Specific embodiments for implementing this system are described below.

[1139] Data collection

[1140] The server collects grades, assessments, and self-reported data that users enter through their devices, such as academic records, work experience, skill sets, and career goals, using web forms or dedicated applications.

[1141] Data analysis

[1142] The collected data is stored by the server and passed to the analytics module, which uses machine learning algorithms and statistical methods to identify patterns based on users' skills and goals. For example, data mining techniques are used to predict the degree to which a particular skill set contributes to career success. Cluster analysis is also used to identify groups of users with similar characteristics.

[1143] Feedback Generation

[1144] Based on the analysis results, the feedback module generates appropriate advice and recommendations for the user. For example, if a user is interested in project management, the system will recommend "taking an introductory project management course" or "aiming to obtain the PMP certification."

[1145] Providing Feedback

[1146] The generated feedback is sent from the server to the user's device. The user can check the feedback content in real time. For example, if a student user requests career counseling, the system will provide specific advice such as "Start studying using dedicated physics and chemistry problem sets."

[1147] Ongoing support

[1148] The system regularly monitors the user's progress and provides new feedback and advice as needed. Users can continually enter new achievements, skills, and career information into the system to receive up-to-date advice.

[1149] Specific examples

[1150] For example, if a working user wants career advice, the system works as follows:

[1151] 1. User data entry

[1152] Users enter their current job description, past work experience, skill set, and career goals.

[1153] The terminal transmits the input data to the server.

[1154] 2. Data Analysis

[1155] The server analyzes the user's information using machine learning algorithms.

[1156] As a result of the analysis, an appropriate career plan is developed based on the user's skills and career goals.

[1157] 3. Generating and Providing Feedback

[1158] The server generates feedback such as, "As a next step, take an introductory project management course and aim to obtain PMP certification."

[1159] The terminal notifies the user of the generated feedback and displays the details.

[1160] In this way, the system of the present invention can efficiently and effectively provide tutoring and career counseling in educational institutions and workplaces, and maximize users' skills and goals by providing real-time feedback based on their performance, assessments, and self-reported data.

[1161] The processing flow will be explained below.

[1162] Step 1:

[1163] Users log into the system using a terminal. New users create an account and log in after verifying their email.

[1164] Step 2:

[1165] Users enter performance, evaluation, and self-reported data into a form, such as current job description, past work experience, skill set, and career goals.

[1166] Step 3:

[1167] The terminal sends the entered data to the server, which checks the input data in real time and performs error checking.

[1168] Step 4:

[1169] The server stores the data received from the device in a database, which is used for further analysis.

[1170] Step 5:

[1171] The server collects the stored data and passes it to an analytics module, which includes grades, assessments, and self-reported data.

[1172] Step 6:

[1173] The analytics module uses machine learning algorithms to analyze users' skills and goals, for example using clustering algorithms to identify groups of users with similar career paths or aspirations.

[1174] Step 7:

[1175] The server passes the analysis results to the feedback module, which initiates the next step of generating feedback.

[1176] Step 8:

[1177] The feedback module generates appropriate feedback for the user based on the analysis results, for example, recommending that "As a next step, take an introductory project management course and aim to obtain PMP certification."

[1178] Step 9:

[1179] The server sends the generated feedback to the user's device, where the user can check the feedback content in real time.

[1180] Step 10:

[1181] Based on the feedback provided, the user can take the following actions: Initiate an action, such as enrolling in a recommended course.

[1182] Step 11:

[1183] The server periodically monitors the user's progress, collecting data to generate new feedback and advice, and updates the data as the user adds new achievements and skills.

[1184] Step 12:

[1185] The terminal notifies and displays regular assessments and new feedback to the user, allowing the user to receive the latest advice from the system.

[1186] Example 1

[1187] 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."

[1188] Conventional individualized tutoring and career counseling systems often lack real-time feedback based on users' grades, evaluations, and self-reported data, making it difficult to maximize users' skills and goals. Furthermore, they lack a mechanism for continuously providing appropriate advice and recommendations based on the user's progress. This makes it difficult to efficiently support users' growth.

[1189] 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.

[1190] In this invention, the server includes means for collecting data as input from the user, means for analyzing the user's information based on the collected data, means for generating feedback for the user based on the analysis results, means for providing the generated feedback to the user, and means for periodically monitoring the user's progress and providing new feedback and advice, thereby providing appropriate feedback in real time and making it possible to maximize the user's skills and goals.

[1191] "User" refers to an individual or organization that uses the system to input data and receive analysis and feedback.

[1192] "Data" refers to information such as a user's grades, ratings, self-reported data, skill sets, and career goals.

[1193] "Means of collection" refers to the process by which a user inputs data through a terminal and transmits it to a server.

[1194] "Means of analysis" refers to the process of analyzing collected data for patterns and trends using machine learning algorithms and statistical methods.

[1195] "Means of generating feedback" refers to the process of creating appropriate advice and recommendations for users based on the results of data analysis.

[1196] The "means for providing feedback" refers to a process for transmitting the generated feedback to the user's terminal and displaying it in real time.

[1197] "Monitoring" refers to the process of regularly checking the user's progress and providing new feedback or advice as needed.

[1198] "Career counseling" refers to a service that provides users with advice regarding career choices and career paths.

[1199] "Career guidance" refers to a service that provides advice to users on the career path they choose.

[1200] MODE FOR CARRYING OUT THE INVENTION

[1201] The system of the present invention is configured to provide individualized guidance and career counseling by collecting grades, evaluations, and self-reported data from users, and then analyzing and providing feedback based on the collected data. A specific embodiment of this system will be described.

[1202] Data collection

[1203] The server has a means for collecting grades, evaluations, and self-reported data entered by users through terminals. For example, users enter data such as academic achievements, work experience, skill sets, and career goals using a web form or a dedicated application. The terminal checks the format of this data and validates it based on certain rules.

[1204] Data transmission and storage

[1205] When a user enters data and presses the submit button, the terminal sends the data to the server using the HTTPS protocol. When the server receives the data, it first checks whether the data format and content are correct and then saves it in a database, such as MySQL or PostgreSQL.

[1206] Data analysis

[1207] The server passes the collected data to the analysis module, which analyzes the user data using machine learning algorithms and statistical methods implemented in programming languages ​​such as Python and R. Specifically, the module uses the Scikit-Learn library to perform data mining and clustering analysis to analyze how the user's skill set affects their career goals.

[1208] Feedback Generation

[1209] The server then uses the analysis results to activate a feedback module, which uses a generative AI model (such as GPT-3) to generate specific advice and recommendations. The generated feedback is customized for each user and formatted against a template.

[1210] Providing Feedback

[1211] The generated feedback is sent via the server to the user's device, where it is received and notified to the user in real time, displaying detailed information so that the user can immediately check the feedback and take action.

[1212] Ongoing support

[1213] The system also has the means to regularly monitor the user's progress and generate new feedback and advice as needed. Users can continually input new achievements, skills, and career information to receive up-to-date advice, thereby providing ongoing support for the user's development.

[1214] Specific examples

[1215] For example, if a working user wants career advice, the system works as follows:

[1216] 1. User data entry

[1217] Users enter their current job description, past work experience, skill set, and career goals.

[1218] The terminal transmits the input data to the server.

[1219] 2. Data Analysis

[1220] The server analyzes the user's information using machine learning algorithms.

[1221] As a result of the analysis, an appropriate career plan is developed based on the user's skills and career goals.

[1222] 3. Generating and Providing Feedback

[1223] The server generates feedback such as "As a next step, take an introductory course in project management and aim to obtain a qualification."

[1224] The terminal notifies the user of the generated feedback and displays the details.

[1225] Prompt Sentence Examples

[1226] "If users want to improve their programming skills, please recommend what learning resources they should use."

[1227] In this way, the system provides real-time feedback based on users' performance, assessments, and self-reported data to maximize their skills and goals, while providing ongoing support to support their long-term growth.

[1228] As a result, the system of the present invention can efficiently and effectively provide individualized instruction and career counseling in educational institutions and workplaces.

[1229] The flow of the identification process in the first embodiment will be described with reference to FIG.

[1230] Program processing flow

[1231] Step 1:

[1232] Entering User Data

[1233] Users use the terminal to enter their grades, evaluations, and self-reported data into web forms or dedicated applications. The terminal checks the format of the entered data and performs validation. For example, if a user enters "Work experience: 5 years, Education: College graduate, Skills: Python," the terminal checks whether the format is correct. If the format is correct, it proceeds to the next step.

[1234] Input: academic record, work history, skill set, career goals

[1235] Output: Format-checked and validated data

[1236] Step 2:

[1237] Data transmission and storage

[1238] After the user presses the send button, the device securely sends the data to the server using the HTTPS protocol. The server then double-checks the format and content of the received data and stores it in a database, for example, a MySQL database along with the user's ID.

[1239] Input: Format-checked and validated data

[1240] Output: Data stored in the database

[1241] Step 3:

[1242] Analyzing the data

[1243] The server retrieves the stored data from the database and passes it to the analysis module, which analyzes the data using machine learning algorithms implemented in Python or R. For example, it uses Scikit-Learn to perform clustering analysis and analyze the relationship between the user's skills and career goals. As a result of this analysis, appropriate feedback is generated based on the user's data.

[1244] Input: User data retrieved from the database

[1245] Output: User data analysis results

[1246] Step 4:

[1247] Generate feedback

[1248] Based on the results of the analysis module, the server uses a generative AI model (e.g., GPT-3) to generate specific feedback. This feedback is customized for each user and formatted using templates. For example, specific advice such as "As a next step, you should take an introductory project management course and aim to obtain a certification" is generated.

[1249] Input: User data analysis results

[1250] Output: Customized feedback

[1251] Step 5:

[1252] Providing Feedback

[1253] The server sends the generated feedback to the user's device, which notifies the user of the received feedback in real time and displays detailed information. The user can then click the "Start Now" button to directly access the suggested course.

[1254] Input:Customized Feedback

[1255] Output: Feedback provided to the user

[1256] Step 6:

[1257] Ongoing support

[1258] The system periodically monitors the user's progress and prompts them to enter new data and achievements. When new information is received from the user, it analyzes it again and generates and provides new feedback. This ensures that the user always receives the latest advice. For example, if a user acquires a new skill, they can enter that information to receive the latest career advice.

[1259] Input: User progress data, grade update data

[1260] Output: Updated feedback and ongoing advice

[1261] The above is a specific processing flow of the system of the present invention, which allows users to receive effective feedback and advice in real time based on their performance and goals.

[1262] (Application example 1)

[1263] 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."

[1264] In the past, when receiving individual guidance or career counseling, users had to conduct their own research and visit multiple counseling institutions, which was a time-consuming and labor-intensive process. Furthermore, because the feedback provided was general, it was difficult for each individual user to obtain the most appropriate advice. The present invention aims to solve these problems and provide a system that provides individual guidance and career counseling effectively and efficiently.

[1265] 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.

[1266] In this invention, the server includes means for collecting grades, evaluations, and self-reported data from users as input, means for analyzing the user's skills and goals based on the collected data, means for generating feedback for the user based on the analysis results, means for providing the generated feedback to the user, means for the user to input their career goals and skill sets in a virtual store and recommend appropriate products and services based thereon, means for analyzing the user's data using a machine learning algorithm and making appropriate recommendations, and means for presenting the recommendations to the user through a virtual reality device, thereby enabling users to effectively find the career path and skill-up courses, qualifications, and products that are best suited to them.

[1267] "User" refers to an individual who provides performance, assessment, and self-reported data and receives feedback from the system.

[1268] "Grades and evaluations" refers to the achievements the user has achieved in their studies or work, or evaluations from third parties.

[1269] "Self-reported data" refers to information that users voluntarily enter about their career goals, skill sets, work history, etc.

[1270] "Means of collection" refers to the method by which users enter grades, evaluations, and self-reported data into the system and obtain it.

[1271] "Means of analysis" refers to methods of analyzing a user's skills and goals based on collected data using machine learning algorithms and statistical methods.

[1272] "Means for generating feedback" refers to methods for generating next actions or recommendations for users based on the results of data analysis.

[1273] The "means for providing feedback" refers to a method for communicating the generated feedback to the user and displaying it on the browser or application screen.

[1274] "Virtual store" refers to a digital platform that offers and trades goods and services in a virtual environment.

[1275] "Career goals" refer to goals that a user wants to achieve in order to improve their work history or skills.

[1276] "Means for recommending products and services" refers to methods for recommending optimal products and services based on user input data.

[1277] A "machine learning algorithm" is a program that discovers patterns in data and makes predictions and classifications.

[1278] "Means for making recommendations" refers to a method for making suggestions to users based on the results of machine learning.

[1279] "Virtual reality device" refers to a headset or other device used to experience virtual reality.

[1280] "Presenting means" refers to the method by which information is displayed to the user using the virtual reality device.

[1281] The system for implementing this invention aims to collect performance, evaluations, and self-reported data from users, analyze the user's skills and goals based on that data, and provide appropriate feedback. Furthermore, particularly in virtual stores, the system has the function of recommending appropriate products and services based on the user's self-reported information.

[1282] First, the hardware you'll need includes:

[1283] Server (used for data processing and analysis)

[1284] User devices (smartphones, PCs, tablets, etc.)

[1285] Virtual reality devices (VR headsets)

[1286] The software then uses:

[1287] Python (programming language)

[1288] NumPy, Pandas (data processing libraries)

[1289] scikit-learn (machine learning library)

[1290] Data collection

[1291] The server collects grades, assessments, and self-reported data that users enter through their devices. Users enter information about their academic records, work history, skill sets, career goals, and more using dedicated applications and web forms.

[1292] Data analysis

[1293] The collected data is stored on a server and passed to an analytics module, which uses machine learning algorithms and statistical methods to identify patterns based on users' skills and goals. Clustering and regression analysis are used to predict specific skill sets and career success.

[1294] Feedback Generation

[1295] Based on the analysis results, the feedback module generates appropriate advice and recommendations for the user. For example, if a user is interested in project management, the system will recommend "taking an introductory project management course" or "aiming to obtain PMP certification."

[1296] Providing Feedback

[1297] The generated feedback is sent from the server to the user's device, where the user can check the feedback content in real time. For example, if a student user requests career counseling, the system will provide specific advice such as "Start studying using dedicated physics and chemistry problem sets."

[1298] Application in virtual stores

[1299] In the virtual store, users input their career goals and skill sets, and are recommended suitable products and courses based on that data. To do this, machine learning algorithms are used to analyze the user's input data and select the most suitable products and services. The recommendations are presented to the user through a virtual reality device.

[1300] Examples of specific prompts include:

[1301] "I currently work as a software engineer and my career goal is to become a project manager. My current skill set is Python, project management, and data analysis. What courses or certifications would you recommend as my next steps?"

[1302] This system allows users to effectively find the career path and skill-building courses, qualifications, and products that best suit them.

[1303] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[1304] Step 1:

[1305] Users enter their own grades, evaluations, and self-reported data through their terminals. They use dedicated applications or web forms to enter information such as academic achievements, work experience, skill sets, and career goals. This input data is collected and then sent to a server. The input data includes text and numerical data.

[1306] Step 2:

[1307] The server saves the collected input data and stores it in a database. This database stores each user's grades, evaluations, and self-reported data for later analysis. The database stores data in a table structure.

[1308] Step 3:

[1309] The server passes the stored data to an analytics module, which uses machine learning algorithms (e.g., KMeans and Linear Regression) to analyze the user's skills and goals. The inputs are the user's grades, ratings, and self-reported data stored in the database. The output identifies patterns in the user's career path and skill set.

[1310] Step 4:

[1311] The server's analysis module uses the patterns extracted from the data to generate appropriate advice and recommendations in the feedback module. For example, if a user is interested in project management, recommendations such as "take an introductory project management course" or "pursue PMP certification" are generated. The input is the analyzed data, and the output is the generated feedback.

[1312] Step 5:

[1313] The server sends the generated feedback to the user's device, allowing the user to check it in real time. The application on the device displays the received feedback in an easy-to-understand manner to the user. For example, in response to a user's career consultation, specific advice such as "Start studying using dedicated physics and chemistry problem sets" is displayed. The input is the generated feedback, and the output is a notification to the user.

[1314] Step 6:

[1315] Users enter their career goals and skill sets in a virtual store (VR environment). The user's data is entered through the VR headset and sent to the server. The input data includes text and numerical data.

[1316] Step 7:

[1317] The server's machine learning module analyzes user data collected in the virtual store and recommends appropriate products and services. Recommendations include educational courses, certification programs, and specialized books. The input is the data collected in the virtual store, and the output is the recommended products and services.

[1318] Step 8:

[1319] The server presents recommended products and services to the user through a virtual reality device. The user can then review the recommendations and select the appropriate product within the VR environment. The input is the recommended product or service, and the output is the display through the VR device. For example, specific recommendations such as "an introductory course in project management" or "subscription to specialized book XYZ" are presented.

[1320] Through the above processing steps, users can effectively find products and services that will help them find the career path and improve their skills that are best suited to them.

[1321] 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.

[1322] The system of the present invention collects grades, evaluations, and self-reported data from users to provide individualized guidance and career counseling, and combines this with an emotion engine that recognizes the user's emotions to provide highly accurate feedback. Specific embodiments for implementing this system are described below.

[1323] Data collection

[1324] The server collects grades, evaluations, and self-reported data entered by users through their devices. For example, users enter their academic records, work history, skill sets, career goals, etc., using web forms or dedicated applications. The emotion engine also works to recognize users' emotional states in real time during input and interactions.

[1325] Data analysis

[1326] The collected data is stored by the server and passed to the analysis module, which uses machine learning algorithms and statistical methods to identify patterns based on users' skills and goals. For example, data mining techniques are used to predict the degree to which a particular skill set contributes to career success. Cluster analysis is also used to identify user groups with similar characteristics. At the same time, user emotional data recognized by the emotion engine is also taken into account in the analysis.

[1327] Feedback Generation

[1328] Based on the analysis results, the feedback module generates advice and recommendations tailored to the user. For example, if the emotion engine detects that the user's stress level is high, it can suggest a flexible schedule for skill development. The feedback is tailored according to the user's emotional state.

[1329] Providing Feedback

[1330] The generated feedback is sent from the server to the user's device, where the user can check the feedback content in real time. For example, if a student user requests career counseling, the system will provide specific advice such as "Start studying by using dedicated physics and chemistry problem sets," while using emotionally appropriate expressions to attract the user's attention.

[1331] Emotion Engine

[1332] The emotion engine uses natural language processing and image analysis techniques to recognize emotions from user input data and interactions. For example, if a user uses a camera, it uses facial expression recognition technology to analyze the user's emotions. For text input, it infers emotions from the context. Emotion data is updated in real time and provided to the analysis module.

[1333] Ongoing support

[1334] The system periodically monitors the user's progress and provides new feedback and advice as needed. Users can continually input new performance, skill, and emotional information into the system to receive the most up-to-date advice.

[1335] Specific examples

[1336] For example, if a working user wants career advice, the system works as follows:

[1337] 1. User data entry

[1338] Users enter their current job description, past work experience, skill set, and career goals.

[1339] The device sends the input data to the server, and the emotion engine recognizes the user's stress level and motivation.

[1340] 2. Data Analysis

[1341] The server uses machine learning algorithms to analyze user information, while also taking into account emotional data.

[1342] As a result of the analysis, an appropriate career plan is developed based on the user's skills and career goals.

[1343] 3. Generating and Providing Feedback

[1344] The server generates feedback such as, "As a next step, take an introductory project management course and aim to obtain PMP certification." If the user's stress level is recognized by the emotion engine as high, the server will also take into consideration such as "proposing a flexible schedule."

[1345] The terminal notifies the user of the generated feedback and displays the details.

[1346] In this way, the system of the present invention can provide more precise support for individualized tutoring and career counseling in educational institutions and workplaces by combining the emotion engine. By analyzing emotion data in addition to the user's grades, evaluations, and self-reported data, the system can provide more personalized advice and maximize the user's skills and goals.

[1347] The processing flow will be explained below.

[1348] Step 1:

[1349] Users log into the system using a terminal. New users create an account and log in after verifying their email.

[1350] Step 2:

[1351] Users enter performance, evaluation, and self-reported data into a form, such as current job description, past work experience, skill set, and career goals.

[1352] Step 3:

[1353] The device sends the entered data to the server. The input is checked in real time and errors are checked. The emotion engine also recognizes the user's emotions and sends that data to the server.

[1354] Step 4:

[1355] The server stores the data received from the device in a database, which is used for further analysis.

[1356] Step 5:

[1357] The server collects the stored data and passes it to the analysis module. The data includes grades, ratings, and self-reported data, as well as emotional data recognized by the emotion engine.

[1358] Step 6:

[1359] The analytics module uses machine learning algorithms to analyze users' skills and goals. For example, it uses clustering algorithms to identify groups of users with similar career paths and aspirations. It also uses sentiment data to tailor appropriate feedback.

[1360] Step 7:

[1361] The server passes the analysis results to the feedback module, which initiates the next step of generating feedback.

[1362] Step 8:

[1363] The feedback module generates appropriate feedback for the user based on the analysis results. For example, it might recommend, "As a next step, take an introductory project management course and aim to obtain PMP certification." If the emotion engine recognizes that the user's stress level is high, it might additionally suggest, "Create a flexible schedule."

[1364] Step 9:

[1365] The server sends the generated feedback to the user's device, where the user can check the feedback content in real time.

[1366] Step 10:

[1367] Based on the provided feedback, the user may take further action, such as enrolling in a recommended course or trying relaxation techniques to reduce stress.

[1368] Step 11:

[1369] The server periodically monitors the user's progress, collecting data to generate new feedback and advice, and updates the data as the user adds new achievements, skills, and emotions.

[1370] Step 12:

[1371] The terminal notifies and displays regular assessments and new feedback to the user, allowing the user to receive the latest advice from the system.

[1372] Through these specific processing steps, the system of the present invention can provide more accurate support for individualized instruction and career counseling in educational institutions and workplaces by combining the emotion engine. Furthermore, by analyzing emotion data in addition to the user's grades, evaluations, and self-reported data, the system can provide more personalized advice and maximize the user's skills and goals.

[1373] Example 2

[1374] 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."

[1375] Conventional career counseling and guidance systems provide feedback based on users' grades, evaluations, and self-reported data, but because they do not take into account the user's emotional state, the feedback is uniform, making it difficult to provide optimal advice to each individual user.In addition, because the feedback provided does not adequately reflect fluctuations in stress and motivation, users are not sufficiently motivated to take appropriate action.

[1376] 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.

[1377] In this invention, the server includes means for collecting performance, evaluation, and self-reported data as input from users, means for recognizing emotions in real time from the user's input data and interactions, means for analyzing the user's skills and goals based on the collected data and emotional data, means for generating feedback for the user based on the analysis results and emotional data, and means for providing the generated feedback to the user. This makes it possible to comprehensively analyze a variety of data including the user's emotional state and provide personalized feedback optimized for each user.

[1378] "User" refers to an individual who utilizes the system to enter grades, assessments, and self-reported data and receive feedback.

[1379] "Server" refers to the central data processing device that processes and analyzes the data and sentiment data collected from users and generates and provides feedback.

[1380] "Grades" refers to the results of academic or professional evaluations entered by the user, and specific examples include academic grades and evaluation scores at work.

[1381] "Evaluation" refers to external measurements and judgments of a user's skills and abilities, and specifically includes feedback from superiors and the contents of transcripts.

[1382] "Self-reported data" refers to data that users enter into the system as information about themselves, such as their skill set, career goals, and past work history.

[1383] An "emotion engine" refers to a module or program that recognizes and analyzes the user's emotional state in real time from input data and interactions.

[1384] "Analysis Module" refers to a program or software that performs analysis of a user's skills and goals based on collected data and emotional data.

[1385] "Feedback Module" refers to a program or software for generating advice or recommendations to a user based on the results of the Analysis Module and sentiment data.

[1386] "Feedback" refers to advice, recommendations, specific guidelines for action, etc. provided to users, and is generated based on the analysis results.

[1387] "Personalized feedback" refers to feedback that is optimized based on a user's individual performance, ratings, self-reported data, and emotional state.

[1388] A "machine learning algorithm" is a mathematical or statistical method or program used for data analysis, and examples include regression analysis, classification, and clustering methods.

[1389] The system of this invention collects performance, evaluations, and self-reported data from users, analyzes the user's skills and goals based on the collected data, and generates and provides feedback. Furthermore, by incorporating an emotion engine that recognizes emotions in real time from the user's input data and interactions, more personalized feedback can be provided.

[1390] Data collection

[1391] The server collects grades, evaluations, and self-reported data entered by users through their devices. The data is collected by users entering it using web forms or dedicated applications. The system then activates an emotion engine to recognize the user's input data and their emotional state during interactions in real time. For example, the emotion engine uses facial expression recognition and natural language processing technologies to collect data.

[1392] Data analysis

[1393] The server stores the collected data in a database and passes it to the analysis module, which uses Python-based machine learning libraries (e.g., TensorFlow, Scikit-learn) to perform detailed analysis of the user's skills and goals. For example, it uses data mining techniques to predict the degree to which a particular skill set contributes to career success, and cluster analysis to identify user groups with similar characteristics. At the same time, it can also incorporate emotional data into the analysis to obtain results that reflect the user's emotional state.

[1394] Feedback Generation

[1395] Based on the analysis results, the feedback module generates appropriate advice and recommendations for the user. It uses a generative AI model (e.g., GPT-3) to generate expressions that match the user's emotional state. For example, a user with a high stress level might receive thoughtful feedback such as, "Take it easy and take it one step at a time."

[1396] Providing Feedback

[1397] The server sends the generated feedback to the user's device, where the user can check the provided feedback in real time. For example, if a student user is seeking career advice, the system will provide specific advice such as "Start studying using dedicated physics and chemistry problem sets," while also using emotional expressions to attract the user's attention.

[1398] Specific examples

[1399] For example, if a working user wants career advice, the system works as follows:

[1400] 1. Users enter their current job description, past work experience, skill set, and career goals.

[1401] 2. The device sends the input data to the server, and the emotion engine recognizes the user's stress level and motivation.

[1402] 3. The server analyzes the user's information using machine learning algorithms, while also taking into account emotional data.

[1403] 4. The server generates feedback such as, "As your next career step, take an introductory project management course and aim to obtain PMP certification." If the emotion engine recognizes that the stress level is high, it will also take into consideration the need to "suggest a flexible schedule."

[1404] 5. The device notifies the user of the generated feedback and displays its details.

[1405] In this way, by integrating an emotion engine, the system can provide highly personalized feedback according to the user's emotional state, optimally supporting the user's skills and goals.

[1406] The flow of the identification process in the second embodiment will be described with reference to FIG.

[1407] Step 1: User authentication

[1408] A user enters a username and password to log in to the system. The entered authentication information is sent from the terminal to the server. The server checks the authentication information against a database and returns the authentication result to the terminal. If the authentication is successful, the user can proceed to the next step.

[1409] Input: Username, Password

[1410] Output: Authentication success / failure result

[1411] Step 2: Enter self-reported data

[1412] Users enter their academic record, work history, skill set, and career goals through web forms or dedicated applications. The device collects the data, temporarily stores it, and then transmits it to the server.

[1413] Input: academic record, work history, skill set, career goals

[1414] Output: Collected self-reported data

[1415] Step 3: Obtaining emotion data

[1416] When users input data or interact with the device, the emotion engine works to collect real-time emotional data using cameras and natural language processing technology, which is then sent to a server along with self-reported data.

[1417] Input: facial expression recognition data, text input

[1418] Output: Collected emotion data

[1419] Step 4: Save Data

[1420] The server stores the collected self-reported data and emotion data in a database, with error handling to ensure data consistency and safety.

[1421] Input: Self-reported data, emotion data

[1422] Output: Save results to database

[1423] Step 5: Data analysis

[1424] The server passes the stored data to the analysis module, which analyzes the data using Python-based machine learning libraries (e.g., TensorFlow, Scikit-learn). Machine learning algorithms are applied to the collected data to identify patterns based on the user's skills and goals. Emotional data is also added to the analysis to obtain results that take into account the user's emotional state.

[1425] Input: Self-reported data, emotion data

[1426] Output: Analysis results (user skill patterns, goal setting, etc.)

[1427] Step 6: Feedback generation

[1428] The feedback module generates appropriate feedback for the user based on the analysis results and emotional data. It uses a generative AI model (e.g., GPT-3) to generate feedback that matches the user's emotional state. For example, a user with a high stress level can receive feedback that takes their emotions into consideration, such as, "Try not to push yourself too hard, but to take it one step at a time."

[1429] Input: Analysis results, emotion data

[1430] Output: Generated feedback

[1431] Step 7: Provide feedback

[1432] The server sends the generated feedback to the user's device. The user can check the provided feedback in real time. For example, not only is specific advice such as "Start studying using dedicated physics and chemistry problem sets," but encouraging words such as "Don't push yourself too hard, just progress little by little" are also displayed.

[1433] Input: Generated feedback

[1434] Output: Feedback display to the user

[1435] (Application example 2)

[1436] Next, a description will be given of Application Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the robot 414 will be referred to as a "terminal."

[1437] Conventional career counseling and career guidance systems only provide feedback based on a user's grades and skill sets, but are unable to provide personalized feedback that takes into account the user's emotional state. Furthermore, customer service support systems in brick-and-mortar stores have struggled to recognize customer emotions in real time and provide appropriate customer service. This can lead to reduced user and customer satisfaction and efficiency.

[1438] The specific processing by the specific processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means. In this invention, the server includes means for collecting performance, evaluation, and self-reported data from users as input, means for analyzing the user's skills and goals based on the collected data, means for generating feedback for the user based on the analysis results, means for providing the generated feedback to the user, means for recognizing the user's emotions in real time and adjusting the feedback content based on the emotional state, and means for periodically monitoring the user's progress and providing new feedback and advice. This enables personalized feedback and customer service that takes into account the emotions of users and customers.

[1439] The "means for collecting grades, evaluations, and self-reported data from users as input" refers to means for collecting grades, evaluations, and self-reported data collected by users via their terminals.

[1440] The "means for analyzing the skills and goals of a user based on collected data" refers to a means for analyzing the skills and goals of a user using collected data.

[1441] The "means for generating feedback to the user based on the analysis results" refers to means for generating appropriate feedback to the user based on the analyzed data.

[1442] The "means for providing the generated feedback to the user" refers to a means for notifying and providing the generated feedback to the user.

[1443] The "means for recognizing a user's emotions in real time and adjusting the feedback content based on the emotional state" refers to a means for recognizing a user's emotions in real time using an emotion engine and adjusting the feedback content based on the emotions.

[1444] "Means for regularly monitoring the user's progress and providing new feedback and advice" refers to means for regularly managing the user's progress and continuously providing new feedback and advice accordingly.

[1445] The "means for providing career counseling" is a means for providing appropriate advice and support for career-related counseling provided to users.

[1446] The "means for providing career guidance" is a means for providing appropriate advice and guidance regarding career paths to users.

[1447] "Means for providing customer service support" refers to a means for supporting customer service staff in physical stores in providing appropriate support based on customer emotions and data.

[1448] The "means for assisting with transfers and job changes" is a means for providing assistance and advice to users regarding transfers and job changes.

[1449] The "means of providing support for preparation for exams and interviews" are means for supporting the user in preparation for exams and interviews.

[1450] The "means for generating and providing an optimal proposal based on the emotional state and history data of a customer" is a means for generating and providing an optimal proposal based on the emotional state and history data of a customer.

[1451] System configuration

[1452] As an embodiment of the invention, this system consists of the following main components: The hardware includes a device used by the user, a camera for recognizing emotional states in real time, and a server running on the backend. The software includes various modules for data collection, analysis, feedback generation, and provision, implemented using libraries such as Python, OpenCV, Dlib, and Scikit-learn.

[1453] Data collection

[1454] The server collects grades, evaluations, and self-reported data provided by users through their devices. This data includes academic achievements, work history, skill sets, and career goals. During this process, an emotion engine also operates, recognizing users' emotional states in real time during input and interactions. The emotion engine uses natural language processing and image analysis techniques to analyze emotions from users' text input and facial expressions.

[1455] Data analysis

[1456] The collected data is stored on a server and passed to an analysis module, which uses machine learning algorithms and statistical methods to identify patterns based on users' skills and goals. For example, data mining techniques are used to predict the degree to which a particular skill set contributes to career success, and cluster analysis is used to identify user groups with similar characteristics. At the same time, user emotional data recognized by the emotion engine is also taken into account in the analysis.

[1457] Feedback generation and provision

[1458] Based on the analysis results, the feedback module generates advice and recommendations tailored to the user. For example, if the emotion engine detects that the user's stress level is high, it will suggest a flexible schedule. The generated feedback is then sent to the user's device via the server.

[1459] Emotion Engine

[1460] The emotion engine uses natural language processing and image analysis techniques to recognize emotions from user input data and interactions. When the user uses a camera, it uses facial expression recognition technology, and when the user inputs text, it infers emotions from the context of the words. Emotion data, updated in real time, is provided to the analysis module.

[1461] Ongoing support

[1462] The system regularly monitors the user's progress and provides new feedback and advice. Users can receive the latest advice by constantly inputting information about their achievements, skills, and emotions into the system. For example, if a working user requests career counseling, the system will recommend specific skills or qualifications to acquire, and will also provide flexible measures to address stress levels.

[1463] Examples and prompts

[1464] Specific examples

[1465] A salesperson at a physical store is wearing smart glasses. When a customer enters the store, the camera recognizes their face and an emotion engine determines their emotional state in real time. For example, if the emotional state is determined to be "happy," the smart glasses display feedback such as, "The customer is favorable, so it would be appropriate to introduce a new product."

[1466] Prompt Sentence Examples

[1467] "Customer emotional state: happy

[1468] Customer purchase history: a list of past purchases

[1469] Customer Feedback: Past Feedback Details

[1470] Use this as a starting point to suggest ways to present new products that will make customers want to buy right away."

[1471] In this way, the system of the present invention can provide more accurate support to users and customers in educational institutions, workplaces, and brick-and-mortar stores by combining it with an emotion engine.

[1472] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[1473] Step 1:

[1474] The server collects grades, evaluations, and self-reported data from users as input. Data collection occurs when users enter data through their devices (such as academic performance, work history, skill sets, and career goals) and send it to the server. An emotion engine also runs, analyzing the user's emotional state in real time as they enter their data. The user's emotional data is also sent to the server.

[1475] Step 2:

[1476] The server analyzes the user's skills and goals based on the collected data. The collected data is stored in a database and passed to the analysis module. The analysis module uses machine learning algorithms to identify patterns in the data. Data processing during this process includes data cleaning, feature extraction, and model application. This allows cluster analysis and data mining techniques to determine the importance of specific skill sets and classify users into groups.

[1477] Step 3:

[1478] The server uses an emotion engine to recognize the user's emotions in real time and provides the results to the analysis module. The emotion engine analyzes the user's text input and image data (e.g., facial expressions). Specifically, it performs emotion analysis based on natural language processing technology and facial expression recognition using image analysis technology. This provides the user's emotional state as numerical data, which is then incorporated into the analysis results.

[1479] Step 4:

[1480] A feedback module is generated based on the collected and analyzed data. The feedback module creates advice and recommendations tailored to the user. For example, if the user is determined to be under high stress, a flexible schedule suggestion that takes this into consideration is generated. Specifically, different forms of feedback text are generated depending on the user's emotional state.

[1481] Step 5:

[1482] The server then provides the generated feedback to the user. This feedback is sent to the user's device in real time, where the user can view suggestions and advice on their device screen. For example, specific feedback such as "Based on your current skill set, your next course should be an introductory project management course" is provided.

[1483] Step 6:

[1484] The server periodically monitors the user's progress and updates the database as new achievements and skills are entered. Based on the updated information, the server regenerates the latest feedback and advice. During this process, the server combines the new input data with existing data and re-analyzes it, ensuring that the most up-to-date advice is always provided.

[1485] Step 7:

[1486] In brick-and-mortar stores, customer service staff wear devices such as smart glasses to recognize the customer's emotional state in real time. An emotion engine uses video data acquired by a camera to operate, and if the result indicates that the customer is happy, specific customer service feedback, such as introductions to new products, is displayed on the device. This allows for optimal customer service for each customer.

[1487] The specific processing unit 290 transmits the result of the specific processing to the robot 414. In the robot 414, the control unit 46A causes the speaker 240 and the control target 443 to output the result of the specific processing. The microphone 238 acquires voice indicating a user input regarding the result of the specific processing. The control unit 46A transmits voice 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 voice data.

[1488] 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.

[1489] 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 robot 414.

[1490] The emotion identification model 59 as an emotion engine may determine the user's emotion according to a specific mapping. Specifically, the emotion identification model 59 may determine the user's emotion according to an emotion map (see FIG. 9), which is a specific mapping. Similarly, the emotion identification model 59 may determine the robot's emotion, and the identification processing unit 290 may perform identification processing using the robot's emotion.

[1491] FIG. 9 is a diagram illustrating an emotion map 400 on which multiple emotions are mapped. In the emotion map 400, emotions are arranged in concentric circles radiating from the center. Emotions closer to the center of the concentric circles are more primitive. Emotions representing states and actions arising from a state of mind are arranged on the outer edges of the concentric circles. The concept of emotion includes both affect and mental states. Emotions generally generated from reactions occurring in the brain are arranged on the left side of the concentric circles. Emotions generally induced by situational judgment are arranged on the right side of the concentric circles. Emotions generally generated from reactions occurring in the brain and induced by situational judgment are arranged on the upper and lower sides of the concentric circles. Furthermore, the emotion of "pleasure" is arranged on the upper side of the concentric circles, and the emotion of "discomfort" is arranged on the lower side. In this way, in the emotion map 400, multiple emotions are mapped based on the structure by which emotions are generated, and emotions that tend to occur simultaneously are mapped close to each other.

[1492] These emotions are distributed in the 3 o'clock direction on emotion map 400, and typically fluctuate between relief and anxiety. In the right half of emotion map 400, situational awareness dominates over internal sensations, resulting in a sense of calm.

[1493] The inside of emotion map 400 represents what is going on in the mind, and the outside of emotion map 400 represents behavior, so the further you go outside emotion map 400, the more visible the emotions become (the more they are expressed in behavior).

[1494] Human emotions are based on various balances, such as posture and blood sugar levels. When these balances deviate from the ideal, a state of discomfort is indicated, and when they approach the ideal, a state of pleasure is indicated. Emotions can also be created for robots, automobiles, and motorcycles, based on various balances, such as posture and remaining battery life. When these balances deviate from the ideal, a state of discomfort is indicated, and when they approach the ideal, a state of pleasure is indicated. An emotion map can be generated, for example, based on Dr. Mitsuyoshi's emotion map (Research on Voice Emotion Recognition and Emotional Brain Physiological Signal Analysis Systems, Tokushima University, Doctoral Dissertation: https: / / ci.nii.ac.jp / naid / 500000375379). The left half of the emotion map lists emotions belonging to the "reaction" domain, where sensation is dominant. The right half of the emotion map lists emotions belonging to the "situation" domain, where situational awareness is dominant.

[1495] The emotion map defines two emotions that promote learning. One is a negative emotion on the situation side, around the middle of "repentance" or "reflection." In other words, this occurs when the robot experiences negative emotions such as "I never want to feel this way again" or "I don't want to be scolded again." The other is a positive emotion on the response side, around "desire." In other words, this occurs when the robot experiences positive feelings such as "I want more" or "I want to know more."

[1496] The emotion identification model 59 inputs user input into a pre-trained neural network, obtains emotion values ​​indicating each emotion shown in the emotion map 400, and determines the user's emotion. This neural network is pre-trained based on multiple pieces of training data that are combinations of user input and emotion values ​​indicating each emotion shown in the emotion map 400. Furthermore, this neural network is trained so that emotions that are located close to each other have similar values, as in the emotion map 900 shown in FIG. 10. FIG. 10 shows an example in which multiple emotions, "relieved," "calm," and "reassuring," have similar emotion values.

[1497] The system according to the present disclosure has been described above mainly with respect to the functions of the data processing device 12, but the system according to the present disclosure is not necessarily implemented on a server. The system according to the present disclosure may be implemented as a general information processing system. The present disclosure may be implemented, for example, as a software program running on a personal computer or an application running on a smartphone, etc. The method according to the present disclosure may be provided to users in the form of SaaS (Software as a Service).

[1498] In the above embodiment, an example was given in which the specific processing is performed by one computer 22, but the technology of the present disclosure is not limited to this, and the specific processing may be distributed and performed by a plurality of computers including the computer 22. For example, the data generation model 58 may be provided in an external device of the data processing device 12, and data may be generated in the external device in accordance with input data.

[1499] In the above embodiment, an example in which the specific processing program 56 is stored in the storage 32 has been described, but the technology of the present disclosure is not limited to this. For example, the specific processing program 56 may be stored in a portable, computer-readable, non-transitory storage medium such as a USB (Universal Serial Bus) memory. The specific processing program 56 stored in the non-transitory storage medium is installed in the computer 22 of the data processing device 12. The processor 28 executes the specific processing in accordance with the specific processing program 56.

[1500] Alternatively, the specific processing program 56 may be stored in a storage device such as a server connected to the data processing device 12 via the network 54, and the specific processing program 56 may be downloaded and installed on the computer 22 in response to a request from the data processing device 12.

[1501] It is not necessary to store all of the specific processing program 56 in a storage device such as a server connected to the data processing device 12 via the network 54, or to store all of the specific processing program 56 in the storage 32; only a portion of the specific processing program 56 may be stored.

[1502] The hardware resource for executing a specific process can be any of the following processors: An example of a processor is a CPU, which is a general-purpose processor that functions as a hardware resource for executing a specific process by executing software, i.e., a program. Another example of a processor is a dedicated electrical circuit, such as an FPGA (Field-Programmable Gate Array), a PLD (Programmable Logic Device), or an ASIC (Application Specific Integrated Circuit), which is a processor with a circuit configuration designed specifically for executing a specific process. Each processor has built-in or connected memory, and each processor uses the memory to execute the specific process.

[1503] The hardware resource that executes the specific processing may be configured with one of these various processors, or may be configured with a combination of two or more processors of the same or different types (for example, a combination of multiple FPGAs, or a combination of a CPU and an FPGA). Also, the hardware resource that executes the specific processing may be a single processor.

[1504] As an example of a system configured with a single processor, first, one processor is configured by combining one or more CPUs and software, and this processor functions as a hardware resource that executes a specific process. Second, there is a system that uses a processor that realizes the functions of an entire system including multiple hardware resources that execute a specific process on a single IC chip, as typified by SoC (System-on-a-chip). In this way, a specific process is realized using one or more of the above-mentioned various processors as hardware resources.

[1505] Furthermore, the hardware structure of these various processors can be, more specifically, an electric circuit that combines circuit elements such as semiconductor devices. The specific processing described above is merely an example. Therefore, it goes without saying that unnecessary steps may be deleted, new steps may be added, or the processing order may be rearranged, without departing from the spirit of the invention.

[1506] The above-described description and illustrations are a detailed explanation of the parts related to the technology of the present disclosure and are merely an example of the technology of the present disclosure. For example, the above description of the configuration, functions, actions, and effects is an explanation of an example of the configuration, functions, actions, and effects of the parts related to the technology of the present disclosure. Therefore, it goes without saying that unnecessary parts may be deleted, new elements may be added, or replacements may be made to the above-described description and illustrations within the scope of the gist of the technology of the present disclosure. Furthermore, to avoid confusion and facilitate understanding of the parts related to the technology of the present disclosure, the above-described description and illustrations omit explanations of common technical knowledge that do not require particular explanation to enable the implementation of the technology of the present disclosure.

[1507] All publications, patent applications, and technical standards mentioned in this specification are herein incorporated by reference to the same extent as if each individual publication, patent application, or technical standard was specifically and individually indicated to be incorporated by reference.

[1508] The following is further disclosed regarding the above embodiment.

[1509] (Claim 1)

[1510] a means for collecting performance, assessment, and self-reported data as input from users;

[1511] A means of analyzing the user's skills and goals based on the collected data;

[1512] means for generating feedback to the user based on the analysis results;

[1513] means for providing the generated feedback to a user;

[1514] A system including:

[1515] (Claim 2)

[1516] a means of providing career counseling;

[1517] a means of providing career guidance;

[1518] The system of claim 1 further comprising:

[1519] (Claim 3)

[1520] A means of assisting with transfers and job changes,

[1521] We provide support for exam and interview preparation,

[1522] The system of claim 1 further comprising:

[1523] "Example 1"

[1524] (Claim 1)

[1525] means for collecting data as input from a user;

[1526] A means for analyzing user information based on the collected data;

[1527] means for generating feedback to the user based on the analysis results;

[1528] means for providing the generated feedback to a user;

[1529] A means to regularly monitor the user's progress and provide new feedback and advice;

[1530] A system including:

[1531] (Claim 2)

[1532] 10. The system of claim 1, which provides career counseling.

[1533] (Claim 3)

[1534] 10. The system of claim 1, which provides career guidance.

[1535] "Application Example 1"

[1536] (Claim 1)

[1537] a means for collecting performance, assessment, and self-reported data as input from users;

[1538] A means of analyzing the user's skills and goals based on the collected data;

[1539] means for generating feedback to the user based on the analysis results;

[1540] means for providing the generated feedback to a user;

[1541] A means for users to input their career goals and skill sets in a virtual store and have appropriate products and services recommended based on that information;

[1542] A means of analyzing user data using machine learning algorithms to make appropriate recommendations;

[1543] means for presenting the recommendations to the user through a virtual reality device;

[1544] A system including:

[1545] (Claim 2)

[1546] 10. The system of claim 1, which provides career counseling.

[1547] (Claim 3)

[1548] 10. The system of claim 1, which provides career guidance.

[1549] "Example 2: Combining Emotion Engines"

[1550] (Claim 1)

[1551] a means for collecting performance, assessment, and self-reported data as input from users;

[1552] A means of recognizing emotions in real time from user input data and interactions,

[1553] a means for analyzing the user's skills and goals based on the collected data and sentiment data;

[1554] means for generating feedback to the user based on the analysis results and the emotion data;

[1555] means for providing the generated feedback to a user;

[1556] A system including:

[1557] (Claim 2)

[1558] a means of providing career counseling;

[1559] a means of providing career guidance;

[1560] The system of claim 1 further comprising:

[1561] (Claim 3)

[1562] A means of assisting with transfers and job changes,

[1563] We provide support for exam and interview preparation,

[1564] The system of claim 1 further comprising:

[1565] "Application example 2 when combining emotion engines"

[1566] (Claim 1)

[1567] a means for collecting performance, assessment, and self-reported data as input from users;

[1568] A means of analyzing the user's skills and goals based on the collected data;

[1569] means for generating feedback to the user based on the analysis results;

[1570] means for providing the generated feedback to a user;

[1571] means for recognizing a user's emotions in real time and adjusting the feedback content based on the user's emotional state;

[1572] A means to regularly monitor the user's progress and provide new feedback and advice;

[1573] A system including:

[1574] (Claim 2)

[1575] a means of providing career counseling;

[1576] a means of providing career guidance;

[1577] a means of providing customer service assistance;

[1578] The system of claim 1 further comprising:

[1579] (Claim 3)

[1580] A means of assisting with transfers and job changes,

[1581] We provide support for exam and interview preparation,

[1582] A means for generating and providing optimal recommendations based on the customer's emotional state and historical data;

[1583] The system of claim 1 further comprising: [Explanation of symbols]

[1584] 10, 210, 310, 410 Data Processing Systems 12 Data Processing Device 14 Smart Devices 214 Smart Glasses 314 Headset-type terminal 414 Robot< / url:> < / url:> < / url:> < / url:>

Claims

1. a means for collecting performance, assessment, and self-reported data as input from users; A means of analyzing the user's skills and goals based on the collected data; means for generating feedback to the user based on the analysis results; means for providing the generated feedback to a user; A system including:

2. a means of providing career counseling; a means of providing career guidance; The system of claim 1 further comprising:

3. A means of assisting with transfers and job changes, We provide support for exam and interview preparation, The system of claim 1 further comprising:

Images