System

Abstract

A system is provided.SOLUTION: A system includes a means for inputting data such as a career orientation, experience, and skill of an individual from a terminal in order to analyze the career orientation of the individual, a means for transmitting the input data to a server, a means for analyzing the data received by the server, a means for generating optimal advice using AI generated based on an analysis result, a means for returning the generated advice to the terminal, and a means for displaying the returned advice on the terminal.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 today's work environment, individuals face challenges in finding their own career direction and identifying appropriate work methods and communication styles. This prevents many people from realizing their full potential and preventing them from building fulfilling careers. Another challenge is that typical career counseling provides uniform advice, rather than advice tailored to individual needs. [Means for solving the problem]

[0005] This invention provides a system that allows users to input data such as an individual's career aspirations, experience, and skills from a terminal and sends the data to a server. The server analyzes the received data and uses a generation AI to generate optimal advice based on the analysis results, returning the advice to the terminal. The terminal then displays the returned advice. This system provides optimal advice tailored to individual career aspirations and needs, helping individuals maximize their potential. Furthermore, by using machine learning algorithms and natural language processing for data analysis, it is possible to generate advice based on advanced analysis results. Furthermore, by storing the data entered by the user in a database and using that data as the basis for analysis, a system is realized that provides more accurate advice.

[0006] A "terminal" is a device operated by a user, which inputs data, transmits data to a server, and receives and displays data from a server.

[0007] The "server" is a computer system that analyzes the received data and generates advice using a generation AI.

[0008] "Generative AI" is an algorithm or model that uses artificial intelligence technology to generate advice on optimal work methods and communication styles based on analysis results.

[0009] "Data" refers to information entered by users, such as career aspirations, experience, and skills, which forms the basis for analysis and advice.

[0010] "Analysis" refers to the process of identifying the user's career aspirations, strengths, and areas for improvement based on the data received by the server.

[0011] "Advice" refers to specific suggestions and guidance that the generative AI creates based on the analysis results to help users develop their careers.

[0012] A "machine learning algorithm" is a mathematical technique for learning from large amounts of data and finding patterns and regularities.

[0013] "Natural language processing" refers to the technology that enables computers to understand and process human language.

[0014] A "database" is a system that systematically stores data collected from users and allows them to be referenced, searched, and analyzed later. [Brief explanation of the drawings]

[0015] [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

[0016] 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.

[0017] First, the terms used in the following description will be explained.

[0018] 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).

[0019] 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.

[0020] 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.

[0021] 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.

[0022] 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."

[0023] [First embodiment]

[0024] FIG. 1 shows an example of the configuration of a data processing system 10 according to the first embodiment.

[0025] 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.

[0026] 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).

[0027] 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.

[0028] 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.

[0029] 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.

[0030] 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.

[0031] FIG. 2 shows an example of the main functions of the data processing device 12 and the smart device 14.

[0032] 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.

[0033] 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.

[0034] 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.

[0035] 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."

[0036] In this invention, the following system and program are implemented to identify the career aspirations of each user and propose optimal work methods and communication styles.

[0037] First, a user uses a device to input data such as career information, skills, experience, and goals. This input data is done through a UI (user interface), such as a web form or a mobile app input form. The device then sends this input data to a server.

[0038] The server analyzes the received data using machine learning algorithms and natural language processing techniques to identify the user's career goals, strengths, and areas for improvement.

[0039] Once the analysis is complete, the server uses generative AI to generate optimal advice for the user, such as career path suggestions, training methods to improve skills, how to use tools to improve work efficiency, and effective communication methods.

[0040] The generated advice is returned from the server to the device, which receives it and displays it in a format that is easy for the user to understand, such as a visual display in the form of a dashboard or a report.

[0041] To give a specific example, suppose a user has a career goal of becoming a management consultant and has five years of experience as a marketing analyst. When the user enters this information on their device and sends it to the server, the server analyzes the user data and identifies strengths in marketing and analytical skills. Based on the analysis results, the generative AI generates specific advice such as obtaining an MBA, strengthening strategic thinking, and improving leadership skills. It also suggests effective ways to use project management tools and team communication.

[0042] In this way, the present invention provides specific, actionable career advice tailored to each user's needs, helping them to move efficiently and effectively towards their career goals.

[0043] The processing flow will be explained below.

[0044] Step 1:

[0045] The user inputs data such as career aspirations, experience, and skills through the terminal, which then temporarily stores the input data.

[0046] Step 2:

[0047] The terminal sends the input data to the server, for example, by using an HTTP POST request.

[0048] Step 3:

[0049] The server checks the data it receives, checking that the data is in the correct format and that all required information is included.

[0050] Step 4:

[0051] The server passes the received data to the analysis module, which analyzes the data using machine learning algorithms and natural language processing.

[0052] Step 5:

[0053] The analysis module identifies the user's career goals, strengths, and areas for improvement. For example, it analyzes the user's skill set and work history to extract strengths and weaknesses.

[0054] Step 6:

[0055] The server passes the analysis results to the generation AI, which then generates optimal advice for the user based on the analysis results.

[0056] Step 7:

[0057] Generative AI generates specific advice to provide to users, including career path suggestions and training methods to improve skills.

[0058] Step 8:

[0059] The server returns the generated advice to the device in JSON format.

[0060] Step 9:

[0061] The device receives the advice returned from the server and displays it in a format that is easy for the user to understand, such as a dashboard or report.

[0062] Step 10:

[0063] Users can review the displayed advice and use it as a reference for their future career development. They can also request more detailed information via their device.

[0064] Example 1

[0065] 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."

[0066] Conventional career advice systems have had difficulty generating optimal advice by fully analyzing each user's career aspirations, experience, skills, etc. Furthermore, the generated advice is often provided in a format that is difficult for users to understand, which has led to the problem of users being unable to receive advice that is actually useful.

[0067] 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.

[0068] In this invention, the server includes means for inputting data such as an individual's career aspirations, experience, and skills from a terminal, means for transmitting the input data to the server, means for the server to analyze the received data, means for generating optimal advice using a generation AI based on the analysis results, means for returning the generated advice to the terminal, and means for the terminal to display the returned advice in dashboard or report format. This allows the server to provide specific and actionable career advice tailored to the needs of each individual user, enabling the user to move efficiently and effectively toward their career goals.

[0069] "Career aspirations" refer to the hopes and goals that individuals have regarding the direction of their future careers and work.

[0070] "Experience" refers to an individual's track record and history based on the tasks, projects, and positions they have held in the past.

[0071] "Skills" refer to the abilities, knowledge, and techniques that an individual possesses to carry out specific tasks or tasks.

[0072] A "terminal" is a device through which a user inputs data and communicates with a server, and specifically includes a personal computer, a smartphone, etc.

[0073] A "server" is a computer system that analyzes the received data and generates and provides the necessary information and advice to users.

[0074] "Machine learning algorithms" refers to a collection of mathematical models that learn patterns from data and perform tasks such as prediction and classification automatically.

[0075] "Natural language processing technology" refers to technology that enables computers to understand, interpret, and generate human language.

[0076] "Generative AI" refers to technology that uses artificial intelligence models to generate new information and content.

[0077] "Dashboard format" refers to a graphical layout that displays important information in a visually easy-to-understand manner.

[0078] "Report format" refers to a format in which information and data are compiled in an orderly manner as a document.

[0079] This invention configures a system that collects data such as a user's career aspirations, experience, and skills, and provides optimal advice. Specific hardware requirements include a device (such as a PC or smartphone) for users to input data, and a server for processing and analyzing the data. Software requirements include a web form or mobile app as the user interface (UI), machine learning algorithms (e.g., scikit-learn) and natural language processing technology (e.g., spaCy) for data analysis, and a generative AI model (e.g., GPT-4) for generating advice.

[0080] First, a user uses a device to enter information about their career aspirations, including specific career goals, past experience, and skills. For example, a user might enter "I want to be a management consultant" or "I have five years of experience as a marketing analyst" into a form on the mobile app.

[0081] Next, the terminal sends the input data to the server in a data format such as JSON, using an HTTP POST request.

[0082] The server analyzes the received data to identify the user's career goals and skills. This analysis is performed using machine learning algorithms and natural language processing techniques. For example, scikit-learn is used to evaluate experience and skills, and spaCy is used to analyze text data.

[0083] The server then uses a generative AI model to generate optimal advice based on the analysis results. For example, it uses GPT-4 to generate specific career advice such as "obtain an MBA" or "strengthen strategic thinking."

[0084] The generated advice is sent back from the server to the device, which receives it and displays it in a format that is easy for the user to understand. For example, a mobile app could visually display the advice in a dashboard format and provide a message to the user, such as "It is recommended that you get an MBA."

[0085] As a concrete example, suppose a user has a career goal of becoming a management consultant and has five years of experience as a marketing analyst. When the user enters this information on their device and sends it to the server, the server analyzes the user data and identifies strengths in marketing and analytical skills. Based on the analysis results, the generative AI generates specific advice such as obtaining an MBA, strengthening strategic thinking, and improving leadership skills. It also suggests effective ways to use project management tools and team communication.

[0086] Examples of prompts include:

[0087] "I'm thinking about getting an MBA. Can you give me some advice on how to prepare and improve my related skills?"

[0088] "I have five years of experience as a marketing analyst. What skills do I need to become a management consultant?"

[0089] "What specific tools and methods can you use to improve team communication?"

[0090] The present invention allows users to receive specific, actionable career advice and effectively progress towards their career goals.

[0091] The flow of the identification process in the first embodiment will be described with reference to FIG.

[0092] Step 1:

[0093] User enters career information

[0094] The user uses the device to input information about their career (goals, experience, skills). Specifically, they enter information such as "I want to be a management consultant" or "I have five years of experience as a marketing analyst" into a form on the mobile app. The input data is in JSON format, and once the data has been entered, they press the "Submit" button.

[0095] Step 2:

[0096] The device sends the input data to the server

[0097] The device sends the data entered by the user to the server as an HTTP POST request. The input data is in JSON format, for example:

[0098] json

[0099] {

[0100] "career_goal": "Management Consultant",

[0101] "experience": "5 years as a marketing analyst"

[0102] }

[0103] The terminal transmits this data to the server over the network.

[0104] Step 3:

[0105] The server analyzes the data

[0106] The server analyzes the received JSON data using machine learning algorithms (such as scikit-learn) and natural language processing techniques (such as spaCy). The specific process is as follows:

[0107] The server receives the data and parses the JSON.

[0108] Using scikit-learn, we cluster users' experiences and skills and generate profiles.

[0109] Use spaCy to perform natural language processing on users' career goals.

[0110] Step 4:

[0111] The server generates the advice

[0112] Based on the analysis results, the server uses a generative AI model (such as GPT-4) to generate optimal advice. The generation process is as follows:

[0113] A prompt sentence is created using the user profile and goals obtained from the analysis.

[0114] For example, specific career advice such as "Get an MBA" or "Improve your strategic thinking" can be input as prompts into the generative AI.

[0115] The generative AI generates appropriate advice, and we get output like this example:

[0116] "An MBA is recommended for your career path as a management consultant, and training to strengthen your strategic thinking and leadership skills will be helpful."

[0117] Step 5:

[0118] The server sends the generated advice back to the device

[0119] The server reformats the generated advice in JSON format and sends it back to the device as an HTTP response. An example of generated advice might be returned as JSON like this:

[0120] json

[0121] {

[0122] "advice": "For your career path as a management consultant, an MBA is recommended. Training to strengthen your strategic thinking and leadership skills will also be beneficial."

[0123] }

[0124] The server transmits this data to the terminal via the network.

[0125] Step 6:

[0126] The device displays advice

[0127] The device parses the JSON data received from the server and displays visual advice to the user. The specific operations are as follows:

[0128] The device parses the received JSON and obtains the advice content.

[0129] The mobile app displays advice in the form of a dashboard, providing users with messages such as "Getting an MBA is recommended."

[0130] This allows users to receive specific and actionable career advice and move efficiently towards their career goals.

[0131] (Application example 1)

[0132] 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."

[0133] Conventional career orientation analysis systems have had the problem of lacking real-time support for improving individual workers' work efficiency and skills. In particular, in factory work environments, workers are unable to receive appropriate advice quickly, resulting in reduced work efficiency and delayed skill improvement. Furthermore, the user interface for data entry and advice reception is often complex and difficult to use. The objective of the present invention is to solve these problems and provide a more efficient and effective career support system.

[0134] 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.

[0135] In this invention, the server includes: means for inputting data such as an individual's career aspirations, experience, and skills from a terminal; means for transmitting the input data to the server; means for the server to analyze the received data; means for generating optimal advice using a generation AI based on the analysis results; means for returning the generated advice to the terminal; means for the terminal to display the returned advice; means for promoting improvement of the work situation and skill level based on the data input by the worker; and means for receiving user input via an interactive interface in the smart device and displaying advice for improving work efficiency in the factory in real time. This enables employees to receive optimal advice based on their own work situation in real time, thereby improving work efficiency and quickly improving their skills.

[0136] "Individual career aspirations" refer to the career direction, goals, and interests that individuals wish to achieve in the future.

[0137] The "server" is an information processing device that receives and analyzes data sent from personal devices and generates optimal advice using a generation AI.

[0138] "Generative AI" refers to artificial intelligence technology that automatically generates optimal advice and instructions based on input data.

[0139] A "terminal" is a device for inputting data and displaying analysis results and advice returned from the server, and includes smart glasses and smartphones.

[0140] "Work status" includes the state and progress of work being done in a factory or on-site, as well as the tools and methods being used.

[0141] "Skill level" refers to an individual's degree of technical ability or knowledge in a particular task or job.

[0142] An "interactive interface" refers to a user interface in which a user inputs and gives instructions in natural language, and the system responds flexibly accordingly.

[0143] This invention is a career support system for improving work efficiency in factories, which collects and analyzes data such as an individual's career aspirations, experience, and skills, and uses generative AI to provide optimal advice. Below, we will explain in detail the form in which this system is realized.

[0144] 1. System Configuration

[0145] The system includes the following main components:

[0146] Terminal: A device such as smart glasses or a smartphone where the user inputs data and receives and displays advice.

[0147] Server: An information processing device that receives, analyzes, and generates advice using AI.

[0148] Generative AI model: An artificial intelligence technology (e.g., GPT-4) that generates optimal advice based on data input by the user.

[0149] Database: A data storage system that stores user-entered data and serves as the basis for analysis.

[0150] NLP libraries: Libraries for natural language processing (e.g. spaCy).

[0151] Machine learning algorithms: Algorithms for extracting and analyzing data features (e.g., scikit-learn).

[0152] 2. Data entry and submission

[0153] Users input data such as their career aspirations, experience, skills, and work situation into the terminal. The conversational interface of the smart glasses allows input in natural language. For example, input as follows:

[0154] "Tell us about your work as a painter. What tools do you use, how many years of experience do you have, and what are your current concerns?"

[0155] This input data is sent to the server in real time.

[0156] 3. Data analysis and advice generation

[0157] The server analyzes the received data. To do this, it uses an NLP library (e.g., spaCy) to tokenize and summarize the text data, and then uses a machine learning algorithm (e.g., scikit-learn) to extract features from the data. For example, it identifies the work situation, areas of skill deficiency, and areas for improvement.

[0158] Based on the analysis results, a generative AI model (e.g., GPT-4) generates optimal advice for the user. Examples of prompts for the generative AI are as follows:

[0159] "User's work status: {Work status data}

[0160] User Skills: {Skills data}

[0161] User's problem: {Problem data}

[0162] Please suggest the best way to do this."

[0163] 4. Sending and Viewing Advice

[0164] The generated advice is sent from the server to the device, which visually displays this advice to the user in real time. For example, the following advice may be displayed on the display of smart glasses:

[0165] "When using painting tool A, keep it at a 45-degree angle for best efficiency. Also, consider introducing tool B."

[0166] 5. System Operation Example

[0167] Let's say a worker wants to improve his or her work efficiency as a "painter." The worker uses smart glasses to input information about the current work situation, the tools used, and any concerns. Based on this, the server analyzes the data, and the generative AI model generates optimal advice. As a result, the worker can learn efficient work methods and how to introduce new tools in real time, improving their work efficiency.

[0168] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[0169] Step 1:

[0170] The user uses the conversational interface of the smart glasses to input data such as their career aspirations, experience, skills, and work situation in natural language. This includes text input and voice input. For example, the user inputs data in response to prompts such as, "Tell me about your work situation as a painter. Please enter the tools you use, years of experience, and current concerns."

[0171] input:

[0172] User's career information (e.g., work situation, tools used, years of experience, current concerns)

[0173] output:

[0174] Entered carrier data

[0175] Step 2:

[0176] The device transmits the input data to the server in real time using a secure communication protocol to ensure data integrity and privacy.

[0177] input:

[0178] User's career data

[0179] output:

[0180] Carrier data sent to the server

[0181] Step 3:

[0182] The server analyzes the received data. First, it uses an NLP library (e.g., spaCy) to tokenize the text data and extract important keywords and phrases. Then, it uses a machine learning algorithm (e.g., scikit-learn) to analyze the data's features and evaluate the user's skill level and work status.

[0183] input:

[0184] Carrier data sent to the server

[0185] output:

[0186] Analyzed feature data (e.g., important keywords, skill level, work situation evaluation)

[0187] Step 4:

[0188] The server uses a generative AI model (e.g., GPT-4) based on the analysis results to generate optimal advice. The generative AI model uses the input feature data as prompts to automatically generate useful advice for the user.

[0189] Example of generated AI prompt:

[0190] "User's work status: {Work status data}

[0191] User Skills: {Skills data}

[0192] User's problem: {Problem data}

[0193] Please suggest the best way to do this."

[0194] input:

[0195] Analyzed feature data

[0196] output:

[0197] Generated Advice

[0198] Step 5:

[0199] The server sends the generated advice to the device in real time, using a secure communication protocol to ensure the data reaches the device reliably.

[0200] input:

[0201] Generated Advice

[0202] output:

[0203] Advice sent to device

[0204] Step 6:

[0205] The device visually displays the received advice. The advice is presented on the smart glasses display in a format that is easy for the user to understand. For example, specific advice such as "When using painting tool A, keeping it at a 45-degree angle will increase efficiency. Also, consider introducing tool B."

[0206] input:

[0207] Advice received

[0208] output:

[0209] Advice shown on the display

[0210] Through the above processing steps, the user can receive optimal advice in real time according to his / her own work situation, thereby improving work efficiency.

[0211] 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.

[0212] This invention is a system that analyzes the career aspirations of individual users and further combines an emotion engine to propose optimal work methods and communication styles. The present invention is specifically implemented as follows.

[0213] First, the user inputs data such as career aspirations, experience, and skills through the device. The device temporarily stores this input data and monitors the user's facial expressions and voice while they are inputting via an emotion engine. The emotion engine analyzes this data and generates emotion data for the user.

[0214] Next, the device sends the user data and emotion data to the server, for example, using an HTTP POST request. The server then checks the received data to ensure that the data format and all necessary information are included.

[0215] The server passes the received data to an analysis module, which uses machine learning algorithms and natural language processing techniques to identify the user's career goals, strengths, areas for improvement, and emotional information.

[0216] After completing the analysis, the server passes the results to the generation AI, which generates optimal advice for the user based on the analysis results and emotional data. This advice may include career path suggestions, training methods to improve skills, how to use tools to improve work efficiency, and effective communication methods. The generation AI then adapts the tone and content of the advice based on the user's emotions.

[0217] The generated advice is returned from the server to the terminal, which receives the advice and displays it in a format that is easy for the user to understand. For example, it could be displayed in a dashboard format or a report format.

[0218] To give a specific example, suppose a user has a career goal of becoming a management consultant and has five years of experience as a marketing analyst. The user enters this information on their device, and the emotion engine detects excitement or anxiety from the user's facial expressions while they are entering the information. The user data and emotion data are sent to the server, which analyzes the user's skill set and work history to identify their strengths and weaknesses. Based on the analysis results and emotion information, the generative AI generates specific advice. For example, it may suggest obtaining an MBA, strengthening strategic thinking, and improving leadership skills, as well as using project management tools and methods for team communication. If the user feels anxious, the AI ​​provides encouragement and specific action plans to alleviate their anxiety.

[0219] In this way, by combining emotion engines, a system is realized that provides specific and actionable career advice tailored to each user's needs, allowing users to move efficiently and effectively toward their career goals.

[0220] The processing flow will be explained below.

[0221] Step 1:

[0222] Users input data such as career aspirations, experience, and skills through the terminal, which then temporarily stores this data.

[0223] Step 2:

[0224] While the device is inputting, it uses an emotion engine to monitor the user's facial expressions and voice, for example, by using a camera and microphone to collect emotion data.

[0225] Step 3:

[0226] The emotion engine analyzes the collected facial expressions and voice data to recognize the user's emotions (e.g., excitement, joy, anxiety), and generate emotion data.

[0227] Step 4:

[0228] The device sends user data and emotion data to the server using a secure HTTP POST request.

[0229] Step 5:

[0230] The server checks the received data and checks whether the format and necessary information are included. If there is a shortage, it returns an error message to the terminal.

[0231] Step 6:

[0232] The server passes the received data to the analysis module, which analyzes the data using machine learning algorithms and natural language processing techniques.

[0233] Step 7:

[0234] The analysis module identifies the user's career goals, strengths, areas for improvement, and emotional information, for example, by analyzing the user's skill set and work history to extract strengths and weaknesses.

[0235] Step 8:

[0236] The server passes the analysis results to the generation AI, which then generates optimal advice based on the analysis results and emotional data.

[0237] Step 9:

[0238] Generative AI generates specific advice to provide to users, including career path suggestions and training methods to improve skills.

[0239] Step 10:

[0240] The generative AI adapts the tone and content of the advice depending on the user's emotions, for example including encouraging words for users who are feeling anxious.

[0241] Step 11:

[0242] The server returns the generated advice to the device in JSON format.

[0243] Step 12:

[0244] The device receives the advice returned from the server and displays it in a format that is easy for the user to understand, such as a dashboard or report.

[0245] Step 13:

[0246] Users can review the displayed advice and use it as a reference for their future career development. They can also request more detailed information via their device.

[0247] Example 2

[0248] 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."

[0249] Conventional career support systems rely solely on static data provided by users, making it difficult to provide advice that takes into account the emotions and subtle nuances of each individual user. Furthermore, they lacked a mechanism for monitoring emotional fluctuations and providing advice that is appropriate for each user, which limited the accuracy and reliability of the advice users received.

[0250] The identification process by the identification processing unit 290 of the data processing device 12 in the second embodiment is realized by the following means. In this invention, the server includes means for monitoring the user's facial expressions and voice via an emotion engine, means for the emotion engine to generate emotion data of the user, and means for analyzing the data received by the server using a machine learning algorithm and natural language processing technology. This enables real-time career advice that takes the user's emotions into consideration.

[0251] A "user" is an individual who uses the system to input information such as career aspirations, experience, and skills, and receives advice.

[0252] A "terminal" is an electronic device that allows users to input their personal information and collect facial expressions and voice data. Examples include personal computers and smartphones.

[0253] An "emotion engine" is software or hardware that generates user emotion data based on the user's facial expressions and voice data collected from the device.

[0254] "User data" refers to information regarding career aspirations, experience, skills, etc. that a user inputs via a terminal.

[0255] "Emotion data" refers to information about emotions obtained from the user's facial expressions and voice as analyzed by the emotion engine.

[0256] The "server" is a computer system that receives user data and emotion data and generates advice using an analysis module and a generation AI.

[0257] An "analysis module" is software that is placed in the server and analyzes received data using machine learning algorithms and natural language processing technology.

[0258] "Generative AI" is an artificial intelligence that generates optimal career advice for users based on the results extracted by the analysis module and emotional data.

[0259] An "HTTP POST request" is one of the communication protocols used to send data from a terminal to a server.

[0260] A "machine learning algorithm" is an algorithm that learns patterns from large amounts of data and makes predictions and classifications.

[0261] "Natural language processing technology" is a technology that allows computers to understand and process human language.

[0262] "Career advice" refers to career paths, ways to improve skills, measures to improve work efficiency, communication methods, etc. suggested by generative AI based on user data and emotional data.

[0263] MODE FOR CARRYING OUT THE INVENTION

[0264] This invention is a system that analyzes a user's career aspirations and suggests optimal work methods and communication styles. The system is configured by combining an emotion engine and is specifically implemented as follows.

[0265] First, the user inputs data such as career aspirations, experience, and skills through the device. The device temporarily stores this input data and transmits the user's facial expressions and voice in real time to the emotion engine, which then analyzes the facial and voice data to generate the user's emotion data.

[0266] Next, the device sends the user data and emotion data to the server. The HTTP POST request is used as the communication protocol for transmission. The server checks the format of the received data and whether all the necessary information is present. After checking the data format and whether all the information is present, the server passes the data to the analysis module.

[0267] The analysis module uses machine learning algorithms and natural language processing techniques to analyze the received data. The analysis module identifies the user's career goals, strengths, areas for improvement, and emotional information. Based on this analysis, the server passes the analysis results to the generation AI.

[0268] Based on the analysis results and emotional data, the generative AI generates optimal advice for users. This advice can include career path suggestions, training methods to improve skills, how to use tools to improve work efficiency, and effective communication methods. The generative AI adapts the tone and content of the advice depending on the user's emotions.

[0269] The generated advice is returned to the terminal via the server. The terminal receives this advice and presents it to the user in a visualized format, such as a dashboard or report, which makes it easier for the user to intuitively understand the advice.

[0270] As a concrete example, let's say a user has a career goal of becoming a management consultant and has five years of experience as a marketing analyst. The user enters this information on their device, and while they are entering it, the emotion engine detects excitement or anxiety from the user's facial expressions. The user data and emotion data are sent to the server, which analyzes it and analyzes the user's skill set and work history. Based on the analysis results and emotion information, the generation AI generates specific advice. For example, it suggests advice such as "obtaining an MBA," "strengthening strategic thinking," and "improving leadership skills," as well as "using project management tools" and "team communication methods." If the user feels anxious, the engine provides encouragement and advice including a specific action plan to alleviate their anxiety.

[0271] Example prompt sentence:

[0272] "I'd like to work as a management consultant. I have five years of experience as a marketing analyst. Can you give me some advice on how to improve my skills and career path?"

[0273] By feeding these prompts into a generative AI, users can get specific, customized advice, which will then make optimal suggestions based on their emotions and career data.

[0274] In this way, the combination of the emotion engine and the system provides specific, actionable career advice tailored to each user's needs, enabling users to move efficiently and effectively toward their career goals.

[0275] The flow of the identification process in the second embodiment will be described with reference to FIG.

[0276] Step 1:

[0277] The user enters information using the terminal.

[0278] The user enters data about their career aspirations, experience, and skills into an input form on the device. This inputs user data such as "career goals," "experience," and "skills" into the device. While the data is being input, the device also uses a camera and microphone to collect the user's facial expressions and voice in real time and sends this data to the emotion engine. This allows the device to record "facial expression data" and "voice data."

[0279] Step 2:

[0280] The device generates emotion data.

[0281] The emotion engine analyzes the facial expression and voice data sent from the device to generate the user's emotion data. This analysis is performed using an emotion recognition algorithm, specifically a machine learning model that identifies the user's facial expressions and voice patterns to identify emotions such as "excitement" or "anxiety." The output is "emotion data."

[0282] Step 3:

[0283] The terminal transmits user data and emotion data to the server.

[0284] The device structures the user data and emotion data and sends it to the server as a single data packet via an HTTP POST request. This data packet contains the user ID, career goals, experience, skills, and emotion data. The output is the data packet sent to the server.

[0285] Step 4:

[0286] The server accepts the data and performs format validation.

[0287] The server receives the HTTP POST request sent from the terminal and checks the format of the data packet. It checks that each data item is in the correct format and that all required information is present. Specifically, it performs "required field checks" and "format validation." The output is either "the data is valid" or an "error message."

[0288] Step 5:

[0289] The server passes the data to the analysis module.

[0290] The server passes the format-verified data packet to the analysis module, which analyzes the data using machine learning algorithms and natural language processing techniques. This analysis identifies the user's career goals, strengths, areas for improvement, and emotional information. The output is the "analysis results."

[0291] Step 6:

[0292] Generative AI generates advice.

[0293] The server sends the analysis results to the generation AI, which then generates optimal advice based on the analysis results and emotional data. The generation AI generates career path suggestions, ways to improve skills, how to use tools to improve work efficiency, effective communication methods, and more. At this time, it also adjusts the tone and content of the advice depending on the emotion. "Advice data" is generated as the output.

[0294] Step 7:

[0295] The server sends the advice to the terminal.

[0296] The generated advice data is returned to the device via the server. The server converts the advice data into JSON format and sends it to the device via an HTTP POST request. The output is the "advice data" sent to the device.

[0297] Step 8:

[0298] The device displays the advice.

[0299] The device receives the advice data sent from the server and displays it in a format that is easy for the user to understand. For example, this could be displayed in a dashboard or report format. Specifically, the device visualizes and displays advice such as "career path suggestions," "training methods to improve skills," "how to use tools to increase work efficiency," and "effective communication methods." This allows the user to create a specific action plan.

[0300] (Application example 2)

[0301] 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."

[0302] Conventional career advice systems are unable to take into account the user's emotional state, making it difficult to provide detailed advice based on the individual user's emotions and physical condition. Furthermore, because they are unable to provide real-time feedback, they are unable to provide practical advice that users can immediately implement. This has resulted in the challenge of being unable to effectively support users in achieving their career goals.

[0303] The specification process by the specification 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 analyzing the career aspirations, experience, skills, etc. input by the user, means for generating user emotion data and sending it to the server, and means for checking the received data format and the integrity of the information and passing it to the analysis module. This makes it possible to use the user emotion data for analysis and provide personalized advice in real time.

[0304] Term definition

[0305] "Career aspirations" refer to an individual's occupational and work interests, goals, and hopes and plans regarding a specific career path.

[0306] "Experience" refers to an individual's past work history and the knowledge and skills they acquired there, which influence their current abilities and career aspirations.

[0307] "Skills" is a general term for the techniques and abilities required to perform specific jobs or tasks.

[0308] A "terminal" is a device (e.g., a smartphone, a personal computer, smart glasses, etc.) that a user uses to manipulate input data and interact with the system.

[0309] An "emotion engine" is a software system that analyzes a user's facial expressions and voice to generate emotion data.

[0310] "Emotion data" is data that is generated by the emotion engine and indicates the user's emotional state.

[0311] A "server" is a remote computer system that receives data sent by a user, analyzes it, and generates and sends results back to the user.

[0312] An "analysis module" is a software component that performs data analysis within the server, and uses machine learning algorithms and natural language processing techniques.

[0313] "Generative AI" is an artificial intelligence technology that generates optimal advice based on the results of an analysis module.

[0314] "Advice" is guidance and suggestions generated based on the user's career aspirations and emotional data, and is intended to improve the user's working and communication methods.

[0315] "Real-time" is a concept that indicates that the time between data being generated and transmitted and being processed immediately, and the results being presented, is extremely short.

[0316] MODE FOR CARRYING OUT THE INVENTION

[0317] This invention is a system that analyzes the career aspirations of individual users and proposes optimal work methods and communication styles. This system provides more personalized advice by combining data entered by the user through a terminal with emotional data generated by an emotion engine.

[0318] First, the user uses the smart glasses to input data such as their career aspirations, experience, and skills. During this input, the smart glasses analyze the user's facial expressions and voice in real time through an emotion engine to generate emotion data. The emotion engine uses software specialized for emotion analysis (e.g., Microsoft Azure Emotion API).

[0319] Next, the device sends the user input data and generated emotion data to the server using an HTTP POST request, which then uses a data management system such as Apache Kafka to temporarily store the data and pass it to the analysis module.

[0320] The server's analysis module uses machine learning algorithms and natural language processing (NLP) to comprehensively analyze the user's career goals, strengths, areas for improvement, and emotional information. Specifically, the server checks the received data format and completeness of the information, and uses generative AI models such as GPT-4 to generate optimal advice for the user.

[0321] The generated advice is sent back to the device from the server. The device provides this advice to the user in real time, for example, on the display of smart glasses. The display format can be customized to make it easy for the user to understand, and a dashboard or report format can be selected.

[0322] As a specific example, let's say a worker inspecting products in a factory feels "fatigue." In this case, the smart glasses will detect fatigue through facial expression analysis and send the data to the server as emotional data. Based on the analysis results, the server will use a generative AI model to generate advice such as "We recommend you take a five-minute break," and display it on the smart glasses' display.

[0323] Examples of prompts to input to a generative AI model might include:

[0324] "When fatigue is detected from a worker's facial expression, how can we suggest a break? Generate specific advice and encouraging messages."

[0325] In this way, a system is realized that combines emotional data and career-oriented data to provide users with optimized advice in real time.

[0326] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[0327] Program processing flow

[0328] Step 1:

[0329] The user uses the smart glasses to input data such as their career aspirations, experience, and skills. The input data includes text-based career goals, work history, and skill sets. While inputting, the smart glasses use a camera and microphone to capture the user's facial expressions and voice in real time.

[0330] Input: Text data of user's career aspirations, experience, and skills, video data of facial expressions, and audio data

[0331] Output: User data temporarily stored in the smart glasses, as well as captured facial expression and voice data.

[0332] How it works: Users input their career aspirations and experience into the smart glasses, while the smart glasses' camera and microphone capture the user's facial expressions and voice in real time.

[0333] Step 2:

[0334] The device passes input data to an emotion engine that analyzes facial expressions and voice data. The emotion engine generates emotion data and uses services such as the Microsoft Azure Emotion API to identify emotions such as joy, anger, fear, and sadness.

[0335] Input: Captured facial expression video data, audio data

[0336] Output: Emotion data (e.g., 80% happiness, 10% anger, 10% sadness)

[0337] What it does: The emotion engine analyzes facial expressions and voice data to quantify the user's emotional state.

[0338] Step 3:

[0339] The device sends the user data and the generated emotion data to the server via an HTTP POST request.

[0340] Input: User data (career aspirations, experience, skills), emotional data

[0341] Output: Data sent to the server

[0342] Specific operation: The device temporarily stores user data and emotion data and sends them to the server.

[0343] Step 4:

[0344] The server checks the format and integrity of the received data and passes it to the analysis module. The data is temporarily stored using a data management system such as Apache Kafka.

[0345] Input: User data, emotion data

[0346] Output: Data passed to the analysis module

[0347] Specific operation: The server checks the data format, requests retransmission if there is incomplete data, and passes the complete data to the analysis module.

[0348] Step 5:

[0349] The analysis module uses machine learning algorithms and natural language processing (NLP) technology to comprehensively analyze the user's career goals, strengths, areas for improvement, and emotional information.

[0350] Input: Data passed to be analyzed (user data, emotion data)

[0351] Output: Analysis results (user's career goals, strengths, areas for improvement, emotional information)

[0352] What it does: The analysis module uses machine learning algorithms and NLP techniques to analyze user data and sentiment data.

[0353] Step 6:

[0354] Based on the analysis results, the server uses a generative AI model (e.g., GPT-4) to generate optimal advice for the user, with the tone and content adapted according to the user's emotional state.

[0355] Input: Analysis results (user's career goals, strengths, areas for improvement, emotional information)

[0356] Output: The generated advice

[0357] Specific operation: The server inputs prompts into the generative AI model and generates advice according to the user's emotional state. An example of a prompt is, "When fatigue is detected from a worker's facial expression, how should you suggest a break? Please generate specific advice and encouraging messages."

[0358] Step 7:

[0359] The server sends the generated advice back to the device, which then provides it to the user in real time.The advice is displayed on the smart glasses display.

[0360] Input: Generated advice

[0361] Output: Advice displayed to the user

[0362] Specific operation: The device displays the advice received from the server to the user in real time, supporting the user's actions.

[0363] 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.

[0364] 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.

[0365] 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.

[0366] [Second embodiment]

[0367] FIG. 3 shows an example of the configuration of a data processing system 210 according to the second embodiment.

[0368] 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.

[0369] 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).

[0370] 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.

[0371] 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.

[0372] 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).

[0373] 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.

[0374] 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.

[0375] 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.

[0376] 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.

[0377] 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.

[0378] 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."

[0379] In this invention, the following system and program are implemented to identify the career aspirations of each user and propose optimal work methods and communication styles.

[0380] First, a user uses a device to input data such as career information, skills, experience, and goals. This input data is done through a UI (user interface), such as a web form or a mobile app input form. The device then sends this input data to a server.

[0381] The server analyzes the received data using machine learning algorithms and natural language processing techniques to identify the user's career goals, strengths, and areas for improvement.

[0382] Once the analysis is complete, the server uses generative AI to generate optimal advice for the user, such as career path suggestions, training methods to improve skills, how to use tools to improve work efficiency, and effective communication methods.

[0383] The generated advice is returned from the server to the device, which receives it and displays it in a format that is easy for the user to understand, such as a visual display in the form of a dashboard or a report.

[0384] To give a specific example, suppose a user has a career goal of becoming a management consultant and has five years of experience as a marketing analyst. When the user enters this information on their device and sends it to the server, the server analyzes the user data and identifies strengths in marketing and analytical skills. Based on the analysis results, the generative AI generates specific advice such as obtaining an MBA, strengthening strategic thinking, and improving leadership skills. It also suggests effective ways to use project management tools and team communication.

[0385] In this way, the present invention provides specific, actionable career advice tailored to each user's needs, helping them to move efficiently and effectively towards their career goals.

[0386] The processing flow will be explained below.

[0387] Step 1:

[0388] The user inputs data such as career aspirations, experience, and skills through the terminal, which then temporarily stores the input data.

[0389] Step 2:

[0390] The terminal sends the input data to the server, for example, by using an HTTP POST request.

[0391] Step 3:

[0392] The server checks the data it receives, checking that the data is in the correct format and that all required information is included.

[0393] Step 4:

[0394] The server passes the received data to the analysis module, which analyzes the data using machine learning algorithms and natural language processing.

[0395] Step 5:

[0396] The analysis module identifies the user's career goals, strengths, and areas for improvement. For example, it analyzes the user's skill set and work history to extract strengths and weaknesses.

[0397] Step 6:

[0398] The server passes the analysis results to the generation AI, which then generates optimal advice for the user based on the analysis results.

[0399] Step 7:

[0400] Generative AI generates specific advice to provide to users, including career path suggestions and training methods to improve skills.

[0401] Step 8:

[0402] The server returns the generated advice to the device in JSON format.

[0403] Step 9:

[0404] The device receives the advice returned from the server and displays it in a format that is easy for the user to understand, such as a dashboard or report.

[0405] Step 10:

[0406] Users can review the displayed advice and use it as a reference for their future career development. They can also request more detailed information via their device.

[0407] Example 1

[0408] 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."

[0409] Conventional career advice systems have had difficulty generating optimal advice by fully analyzing each user's career aspirations, experience, skills, etc. Furthermore, the generated advice is often provided in a format that is difficult for users to understand, which has led to the problem of users being unable to receive advice that is actually useful.

[0410] 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.

[0411] In this invention, the server includes means for inputting data such as an individual's career aspirations, experience, and skills from a terminal, means for transmitting the input data to the server, means for the server to analyze the received data, means for generating optimal advice using a generation AI based on the analysis results, means for returning the generated advice to the terminal, and means for the terminal to display the returned advice in dashboard or report format. This allows the server to provide specific and actionable career advice tailored to the needs of each individual user, enabling the user to move efficiently and effectively toward their career goals.

[0412] "Career aspirations" refer to the hopes and goals that individuals have regarding the direction of their future careers and work.

[0413] "Experience" refers to an individual's track record and history based on the tasks, projects, and positions they have held in the past.

[0414] "Skills" refer to the abilities, knowledge, and techniques that an individual possesses to carry out specific tasks or tasks.

[0415] A "terminal" is a device through which a user inputs data and communicates with a server, and specifically includes a personal computer, a smartphone, etc.

[0416] A "server" is a computer system that analyzes the received data and generates and provides the necessary information and advice to users.

[0417] "Machine learning algorithms" refers to a collection of mathematical models that learn patterns from data and perform tasks such as prediction and classification automatically.

[0418] "Natural language processing technology" refers to technology that enables computers to understand, interpret, and generate human language.

[0419] "Generative AI" refers to technology that uses artificial intelligence models to generate new information and content.

[0420] "Dashboard format" refers to a graphical layout that displays important information in a visually easy-to-understand manner.

[0421] "Report format" refers to a format in which information and data are compiled in an orderly manner as a document.

[0422] This invention configures a system that collects data such as a user's career aspirations, experience, and skills, and provides optimal advice. Specific hardware requirements include a device (such as a PC or smartphone) for users to input data, and a server for processing and analyzing the data. Software requirements include a web form or mobile app as the user interface (UI), machine learning algorithms (e.g., scikit-learn) and natural language processing technology (e.g., spaCy) for data analysis, and a generative AI model (e.g., GPT-4) for generating advice.

[0423] First, a user uses a device to enter information about their career aspirations, including specific career goals, past experience, and skills. For example, a user might enter "I want to be a management consultant" or "I have five years of experience as a marketing analyst" into a form on the mobile app.

[0424] Next, the terminal sends the input data to the server in a data format such as JSON, using an HTTP POST request.

[0425] The server analyzes the received data to identify the user's career goals and skills. This analysis is performed using machine learning algorithms and natural language processing techniques. For example, scikit-learn is used to evaluate experience and skills, and spaCy is used to analyze text data.

[0426] The server then uses a generative AI model to generate optimal advice based on the analysis results. For example, it uses GPT-4 to generate specific career advice such as "obtain an MBA" or "strengthen strategic thinking."

[0427] The generated advice is sent back from the server to the device, which receives it and displays it in a format that is easy for the user to understand. For example, a mobile app could visually display the advice in a dashboard format and provide a message to the user, such as "It is recommended that you get an MBA."

[0428] As a concrete example, suppose a user has a career goal of becoming a management consultant and has five years of experience as a marketing analyst. When the user enters this information on their device and sends it to the server, the server analyzes the user data and identifies strengths in marketing and analytical skills. Based on the analysis results, the generative AI generates specific advice such as obtaining an MBA, strengthening strategic thinking, and improving leadership skills. It also suggests effective ways to use project management tools and team communication.

[0429] Examples of prompts include:

[0430] "I'm thinking about getting an MBA. Can you give me some advice on how to prepare and improve my related skills?"

[0431] "I have five years of experience as a marketing analyst. What skills do I need to become a management consultant?"

[0432] "What specific tools and methods can you use to improve team communication?"

[0433] The present invention allows users to receive specific, actionable career advice and effectively progress towards their career goals.

[0434] The flow of the identification process in the first embodiment will be described with reference to FIG.

[0435] Step 1:

[0436] User enters career information

[0437] The user uses the device to input information about their career (goals, experience, skills). Specifically, they enter information such as "I want to be a management consultant" or "I have five years of experience as a marketing analyst" into a form on the mobile app. The input data is in JSON format, and once the data has been entered, they press the "Submit" button.

[0438] Step 2:

[0439] The device sends the input data to the server

[0440] The device sends the data entered by the user to the server as an HTTP POST request. The input data is in JSON format, for example:

[0441] json

[0442] {

[0443] "career_goal": "Management Consultant",

[0444] "experience": "5 years as a marketing analyst"

[0445] }

[0446] The terminal transmits this data to the server over the network.

[0447] Step 3:

[0448] The server analyzes the data

[0449] The server analyzes the received JSON data using machine learning algorithms (such as scikit-learn) and natural language processing techniques (such as spaCy). The specific process is as follows:

[0450] The server receives the data and parses the JSON.

[0451] Using scikit-learn, we cluster users' experiences and skills and generate profiles.

[0452] Use spaCy to perform natural language processing on users' career goals.

[0453] Step 4:

[0454] The server generates the advice

[0455] Based on the analysis results, the server uses a generative AI model (such as GPT-4) to generate optimal advice. The generation process is as follows:

[0456] A prompt sentence is created using the user profile and goals obtained from the analysis.

[0457] For example, specific career advice such as "Get an MBA" or "Improve your strategic thinking" can be input as prompts into the generative AI.

[0458] The generative AI generates appropriate advice, and we get output like this example:

[0459] "An MBA is recommended for your career path as a management consultant, and training to strengthen your strategic thinking and leadership skills will be helpful."

[0460] Step 5:

[0461] The server sends the generated advice back to the device

[0462] The server reformats the generated advice in JSON format and sends it back to the device as an HTTP response. An example of generated advice might be returned as JSON like this:

[0463] json

[0464] {

[0465] "advice": "For your career path as a management consultant, an MBA is recommended. Training to strengthen your strategic thinking and leadership skills will also be beneficial."

[0466] }

[0467] The server transmits this data to the terminal via the network.

[0468] Step 6:

[0469] The device displays advice

[0470] The device parses the JSON data received from the server and displays visual advice to the user. The specific operations are as follows:

[0471] The device parses the received JSON and obtains the advice content.

[0472] The mobile app displays advice in the form of a dashboard, providing users with messages such as "Getting an MBA is recommended."

[0473] This allows users to receive specific and actionable career advice and move efficiently towards their career goals.

[0474] (Application example 1)

[0475] 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."

[0476] Conventional career orientation analysis systems have had the problem of lacking real-time support for improving individual workers' work efficiency and skills. In particular, in factory work environments, workers are unable to receive appropriate advice quickly, resulting in reduced work efficiency and delayed skill improvement. Furthermore, the user interface for data entry and advice reception is often complex and difficult to use. The objective of the present invention is to solve these problems and provide a more efficient and effective career support system.

[0477] 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.

[0478] In this invention, the server includes: means for inputting data such as an individual's career aspirations, experience, and skills from a terminal; means for transmitting the input data to the server; means for the server to analyze the received data; means for generating optimal advice using a generation AI based on the analysis results; means for returning the generated advice to the terminal; means for the terminal to display the returned advice; means for promoting improvement of the work situation and skill level based on the data input by the worker; and means for receiving user input via an interactive interface in the smart device and displaying advice for improving work efficiency in the factory in real time. This enables employees to receive optimal advice based on their own work situation in real time, thereby improving work efficiency and quickly improving their skills.

[0479] "Individual career aspirations" refer to the career direction, goals, and interests that individuals wish to achieve in the future.

[0480] The "server" is an information processing device that receives and analyzes data sent from personal devices and generates optimal advice using a generation AI.

[0481] "Generative AI" refers to artificial intelligence technology that automatically generates optimal advice and instructions based on input data.

[0482] A "terminal" is a device for inputting data and displaying analysis results and advice returned from the server, and includes smart glasses and smartphones.

[0483] "Work status" includes the state and progress of work being done in a factory or on-site, as well as the tools and methods being used.

[0484] "Skill level" refers to an individual's degree of technical ability or knowledge in a particular task or job.

[0485] An "interactive interface" refers to a user interface in which a user inputs and gives instructions in natural language, and the system responds flexibly accordingly.

[0486] This invention is a career support system for improving work efficiency in factories, which collects and analyzes data such as an individual's career aspirations, experience, and skills, and uses generative AI to provide optimal advice. Below, we will explain in detail the form in which this system is realized.

[0487] 1. System Configuration

[0488] The system includes the following main components:

[0489] Terminal: A device such as smart glasses or a smartphone where the user inputs data and receives and displays advice.

[0490] Server: An information processing device that receives, analyzes, and generates advice using AI.

[0491] Generative AI model: An artificial intelligence technology (e.g., GPT-4) that generates optimal advice based on data input by the user.

[0492] Database: A data storage system that stores user-entered data and serves as the basis for analysis.

[0493] NLP libraries: Libraries for natural language processing (e.g. spaCy).

[0494] Machine learning algorithms: Algorithms for extracting and analyzing data features (e.g., scikit-learn).

[0495] 2. Data entry and submission

[0496] Users input data such as their career aspirations, experience, skills, and work situation into the terminal. The conversational interface of the smart glasses allows input in natural language. For example, input as follows:

[0497] "Tell us about your work as a painter. What tools do you use, how many years of experience do you have, and what are your current concerns?"

[0498] This input data is sent to the server in real time.

[0499] 3. Data analysis and advice generation

[0500] The server analyzes the received data. To do this, it uses an NLP library (e.g., spaCy) to tokenize and summarize the text data, and then uses a machine learning algorithm (e.g., scikit-learn) to extract features from the data. For example, it identifies the work situation, areas of skill deficiency, and areas for improvement.

[0501] Based on the analysis results, a generative AI model (e.g., GPT-4) generates optimal advice for the user. Examples of prompts for the generative AI are as follows:

[0502] "User's work status: {Work status data}

[0503] User Skills: {Skills data}

[0504] User's problem: {Problem data}

[0505] Please suggest the best way to do this."

[0506] 4. Sending and Viewing Advice

[0507] The generated advice is sent from the server to the device, which visually displays this advice to the user in real time. For example, the following advice may be displayed on the display of smart glasses:

[0508] "When using painting tool A, keep it at a 45-degree angle for best efficiency. Also, consider introducing tool B."

[0509] 5. System Operation Example

[0510] Let's say a worker wants to improve his or her work efficiency as a "painter." The worker uses smart glasses to input information about the current work situation, the tools used, and any concerns. Based on this, the server analyzes the data, and the generative AI model generates optimal advice. As a result, the worker can learn efficient work methods and how to introduce new tools in real time, improving their work efficiency.

[0511] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[0512] Step 1:

[0513] The user uses the conversational interface of the smart glasses to input data such as their career aspirations, experience, skills, and work situation in natural language. This includes text input and voice input. For example, the user inputs data in response to prompts such as, "Tell me about your work situation as a painter. Please enter the tools you use, years of experience, and current concerns."

[0514] input:

[0515] User's career information (e.g., work situation, tools used, years of experience, current concerns)

[0516] output:

[0517] Entered carrier data

[0518] Step 2:

[0519] The device transmits the input data to the server in real time using a secure communication protocol to ensure data integrity and privacy.

[0520] input:

[0521] User's career data

[0522] output:

[0523] Carrier data sent to the server

[0524] Step 3:

[0525] The server analyzes the received data. First, it uses an NLP library (e.g., spaCy) to tokenize the text data and extract important keywords and phrases. Then, it uses a machine learning algorithm (e.g., scikit-learn) to analyze the data's features and evaluate the user's skill level and work status.

[0526] input:

[0527] Carrier data sent to the server

[0528] output:

[0529] Analyzed feature data (e.g., important keywords, skill level, work situation evaluation)

[0530] Step 4:

[0531] The server uses a generative AI model (e.g., GPT-4) based on the analysis results to generate optimal advice. The generative AI model uses the input feature data as prompts to automatically generate useful advice for the user.

[0532] Example of generated AI prompt:

[0533] "User's work status: {Work status data}

[0534] User Skills: {Skills data}

[0535] User's problem: {Problem data}

[0536] Please suggest the best way to do this."

[0537] input:

[0538] Analyzed feature data

[0539] output:

[0540] Generated Advice

[0541] Step 5:

[0542] The server sends the generated advice to the device in real time, using a secure communication protocol to ensure the data reaches the device reliably.

[0543] input:

[0544] Generated Advice

[0545] output:

[0546] Advice sent to device

[0547] Step 6:

[0548] The device visually displays the received advice. The advice is presented on the smart glasses display in a format that is easy for the user to understand. For example, specific advice such as "When using painting tool A, keeping it at a 45-degree angle will increase efficiency. Also, consider introducing tool B."

[0549] input:

[0550] Advice received

[0551] output:

[0552] Advice shown on the display

[0553] Through the above processing steps, the user can receive optimal advice in real time according to his / her own work situation, thereby improving work efficiency.

[0554] 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.

[0555] This invention is a system that analyzes the career aspirations of individual users and further combines an emotion engine to propose optimal work methods and communication styles. The present invention is specifically implemented as follows.

[0556] First, the user inputs data such as career aspirations, experience, and skills through the device. The device temporarily stores this input data and monitors the user's facial expressions and voice while they are inputting via an emotion engine. The emotion engine analyzes this data and generates emotion data for the user.

[0557] Next, the device sends the user data and emotion data to the server, for example, using an HTTP POST request. The server then checks the received data to ensure that the data format and all necessary information are included.

[0558] The server passes the received data to an analysis module, which uses machine learning algorithms and natural language processing techniques to identify the user's career goals, strengths, areas for improvement, and emotional information.

[0559] After completing the analysis, the server passes the results to the generation AI, which generates optimal advice for the user based on the analysis results and emotional data. This advice may include career path suggestions, training methods to improve skills, how to use tools to improve work efficiency, and effective communication methods. The generation AI then adapts the tone and content of the advice based on the user's emotions.

[0560] The generated advice is returned from the server to the terminal, which receives the advice and displays it in a format that is easy for the user to understand. For example, it could be displayed in a dashboard format or a report format.

[0561] To give a specific example, suppose a user has a career goal of becoming a management consultant and has five years of experience as a marketing analyst. The user enters this information on their device, and the emotion engine detects excitement or anxiety from the user's facial expressions while they are entering the information. The user data and emotion data are sent to the server, which analyzes the user's skill set and work history to identify their strengths and weaknesses. Based on the analysis results and emotion information, the generative AI generates specific advice. For example, it may suggest obtaining an MBA, strengthening strategic thinking, and improving leadership skills, as well as using project management tools and methods for team communication. If the user feels anxious, the AI ​​provides encouragement and specific action plans to alleviate their anxiety.

[0562] In this way, by combining emotion engines, a system is realized that provides specific and actionable career advice tailored to each user's needs, allowing users to move efficiently and effectively toward their career goals.

[0563] The processing flow will be explained below.

[0564] Step 1:

[0565] Users input data such as career aspirations, experience, and skills through the terminal, which then temporarily stores this data.

[0566] Step 2:

[0567] While the device is inputting, it uses an emotion engine to monitor the user's facial expressions and voice, for example, by using a camera and microphone to collect emotion data.

[0568] Step 3:

[0569] The emotion engine analyzes the collected facial expressions and voice data to recognize the user's emotions (e.g., excitement, joy, anxiety), and generate emotion data.

[0570] Step 4:

[0571] The device sends user data and emotion data to the server using a secure HTTP POST request.

[0572] Step 5:

[0573] The server checks the received data and checks whether the format and necessary information are included. If there is a shortage, it returns an error message to the terminal.

[0574] Step 6:

[0575] The server passes the received data to the analysis module, which analyzes the data using machine learning algorithms and natural language processing techniques.

[0576] Step 7:

[0577] The analysis module identifies the user's career goals, strengths, areas for improvement, and emotional information, for example, by analyzing the user's skill set and work history to extract strengths and weaknesses.

[0578] Step 8:

[0579] The server passes the analysis results to the generation AI, which then generates optimal advice based on the analysis results and emotional data.

[0580] Step 9:

[0581] Generative AI generates specific advice to provide to users, including career path suggestions and training methods to improve skills.

[0582] Step 10:

[0583] The generative AI adapts the tone and content of the advice depending on the user's emotions, for example including encouraging words for users who are feeling anxious.

[0584] Step 11:

[0585] The server returns the generated advice to the device in JSON format.

[0586] Step 12:

[0587] The device receives the advice returned from the server and displays it in a format that is easy for the user to understand, such as a dashboard or report.

[0588] Step 13:

[0589] Users can review the displayed advice and use it as a reference for their future career development. They can also request more detailed information via their device.

[0590] Example 2

[0591] 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."

[0592] Conventional career support systems rely solely on static data provided by users, making it difficult to provide advice that takes into account the emotions and subtle nuances of each individual user. Furthermore, they lacked a mechanism for monitoring emotional fluctuations and providing advice that is appropriate for each user, which limited the accuracy and reliability of the advice users received.

[0593] The identification process by the identification processing unit 290 of the data processing device 12 in the second embodiment is realized by the following means. In this invention, the server includes means for monitoring the user's facial expressions and voice via an emotion engine, means for the emotion engine to generate emotion data of the user, and means for analyzing the data received by the server using a machine learning algorithm and natural language processing technology. This enables real-time career advice that takes the user's emotions into consideration.

[0594] A "user" is an individual who uses the system to input information such as career aspirations, experience, and skills, and receives advice.

[0595] A "terminal" is an electronic device that allows users to input their personal information and collect facial expressions and voice data. Examples include personal computers and smartphones.

[0596] An "emotion engine" is software or hardware that generates user emotion data based on the user's facial expressions and voice data collected from the device.

[0597] "User data" refers to information regarding career aspirations, experience, skills, etc. that a user inputs via a terminal.

[0598] "Emotion data" refers to information about emotions obtained from the user's facial expressions and voice as analyzed by the emotion engine.

[0599] The "server" is a computer system that receives user data and emotion data and generates advice using an analysis module and a generation AI.

[0600] An "analysis module" is software that is placed in the server and analyzes received data using machine learning algorithms and natural language processing technology.

[0601] "Generative AI" is an artificial intelligence that generates optimal career advice for users based on the results extracted by the analysis module and emotional data.

[0602] An "HTTP POST request" is one of the communication protocols used to send data from a terminal to a server.

[0603] A "machine learning algorithm" is an algorithm that learns patterns from large amounts of data and makes predictions and classifications.

[0604] "Natural language processing technology" is a technology that allows computers to understand and process human language.

[0605] "Career advice" refers to career paths, ways to improve skills, measures to improve work efficiency, communication methods, etc. suggested by generative AI based on user data and emotional data.

[0606] MODE FOR CARRYING OUT THE INVENTION

[0607] This invention is a system that analyzes a user's career aspirations and suggests optimal work methods and communication styles. The system is configured by combining an emotion engine and is specifically implemented as follows.

[0608] First, the user inputs data such as career aspirations, experience, and skills through the device. The device temporarily stores this input data and transmits the user's facial expressions and voice in real time to the emotion engine, which then analyzes the facial and voice data to generate the user's emotion data.

[0609] Next, the device sends the user data and emotion data to the server. The HTTP POST request is used as the communication protocol for transmission. The server checks the format of the received data and whether all the necessary information is present. After checking the data format and whether all the information is present, the server passes the data to the analysis module.

[0610] The analysis module uses machine learning algorithms and natural language processing techniques to analyze the received data. The analysis module identifies the user's career goals, strengths, areas for improvement, and emotional information. Based on this analysis, the server passes the analysis results to the generation AI.

[0611] Based on the analysis results and emotional data, the generative AI generates optimal advice for users. This advice can include career path suggestions, training methods to improve skills, how to use tools to improve work efficiency, and effective communication methods. The generative AI adapts the tone and content of the advice depending on the user's emotions.

[0612] The generated advice is returned to the terminal via the server. The terminal receives this advice and presents it to the user in a visualized format, such as a dashboard or report, which makes it easier for the user to intuitively understand the advice.

[0613] As a concrete example, let's say a user has a career goal of becoming a management consultant and has five years of experience as a marketing analyst. The user enters this information on their device, and while they are entering it, the emotion engine detects excitement or anxiety from the user's facial expressions. The user data and emotion data are sent to the server, which analyzes it and analyzes the user's skill set and work history. Based on the analysis results and emotion information, the generation AI generates specific advice. For example, it suggests advice such as "obtaining an MBA," "strengthening strategic thinking," and "improving leadership skills," as well as "using project management tools" and "team communication methods." If the user feels anxious, the engine provides encouragement and advice including a specific action plan to alleviate their anxiety.

[0614] Example prompt sentence:

[0615] "I'd like to work as a management consultant. I have five years of experience as a marketing analyst. Can you give me some advice on how to improve my skills and career path?"

[0616] By feeding these prompts into a generative AI, users can get specific, customized advice, which will then make optimal suggestions based on their emotions and career data.

[0617] In this way, the combination of the emotion engine and the system provides specific, actionable career advice tailored to each user's needs, enabling users to move efficiently and effectively toward their career goals.

[0618] The flow of the identification process in the second embodiment will be described with reference to FIG.

[0619] Step 1:

[0620] The user enters information using the terminal.

[0621] The user enters data about their career aspirations, experience, and skills into an input form on the device. This inputs user data such as "career goals," "experience," and "skills" into the device. While the data is being input, the device also uses a camera and microphone to collect the user's facial expressions and voice in real time and sends this data to the emotion engine. This allows the device to record "facial expression data" and "voice data."

[0622] Step 2:

[0623] The device generates emotion data.

[0624] The emotion engine analyzes the facial expression and voice data sent from the device to generate the user's emotion data. This analysis is performed using an emotion recognition algorithm, specifically a machine learning model that identifies the user's facial expressions and voice patterns to identify emotions such as "excitement" or "anxiety." The output is "emotion data."

[0625] Step 3:

[0626] The terminal transmits user data and emotion data to the server.

[0627] The device structures the user data and emotion data and sends it to the server as a single data packet via an HTTP POST request. This data packet contains the user ID, career goals, experience, skills, and emotion data. The output is the data packet sent to the server.

[0628] Step 4:

[0629] The server accepts the data and performs format validation.

[0630] The server receives the HTTP POST request sent from the terminal and checks the format of the data packet. It checks that each data item is in the correct format and that all required information is present. Specifically, it performs "required field checks" and "format validation." The output is either "the data is valid" or an "error message."

[0631] Step 5:

[0632] The server passes the data to the analysis module.

[0633] The server passes the format-verified data packet to the analysis module, which analyzes the data using machine learning algorithms and natural language processing techniques. This analysis identifies the user's career goals, strengths, areas for improvement, and emotional information. The output is the "analysis results."

[0634] Step 6:

[0635] Generative AI generates advice.

[0636] The server sends the analysis results to the generation AI, which then generates optimal advice based on the analysis results and emotional data. The generation AI generates career path suggestions, ways to improve skills, how to use tools to improve work efficiency, effective communication methods, and more. At this time, it also adjusts the tone and content of the advice depending on the emotion. "Advice data" is generated as the output.

[0637] Step 7:

[0638] The server sends the advice to the terminal.

[0639] The generated advice data is returned to the device via the server. The server converts the advice data into JSON format and sends it to the device via an HTTP POST request. The output is the "advice data" sent to the device.

[0640] Step 8:

[0641] The device displays the advice.

[0642] The device receives the advice data sent from the server and displays it in a format that is easy for the user to understand. For example, this could be displayed in a dashboard or report format. Specifically, the device visualizes and displays advice such as "career path suggestions," "training methods to improve skills," "how to use tools to increase work efficiency," and "effective communication methods." This allows the user to create a specific action plan.

[0643] (Application example 2)

[0644] 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."

[0645] Conventional career advice systems are unable to take into account the user's emotional state, making it difficult to provide detailed advice based on the individual user's emotions and physical condition. Furthermore, because they are unable to provide real-time feedback, they are unable to provide practical advice that users can immediately implement. This has resulted in the challenge of being unable to effectively support users in achieving their career goals.

[0646] The specification process by the specification 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 analyzing the career aspirations, experience, skills, etc. input by the user, means for generating user emotion data and sending it to the server, and means for checking the received data format and the integrity of the information and passing it to the analysis module. This makes it possible to use the user emotion data for analysis and provide personalized advice in real time.

[0647] Term definition

[0648] "Career aspirations" refer to an individual's occupational and work interests, goals, and hopes and plans regarding a specific career path.

[0649] "Experience" refers to an individual's past work history and the knowledge and skills they acquired there, which influence their current abilities and career aspirations.

[0650] "Skills" is a general term for the techniques and abilities required to perform specific jobs or tasks.

[0651] A "terminal" is a device (e.g., a smartphone, a personal computer, smart glasses, etc.) that a user uses to manipulate input data and interact with the system.

[0652] An "emotion engine" is a software system that analyzes a user's facial expressions and voice to generate emotion data.

[0653] "Emotion data" is data that is generated by the emotion engine and indicates the user's emotional state.

[0654] A "server" is a remote computer system that receives data sent by a user, analyzes it, and generates and sends results back to the user.

[0655] An "analysis module" is a software component that performs data analysis within the server, and uses machine learning algorithms and natural language processing techniques.

[0656] "Generative AI" is an artificial intelligence technology that generates optimal advice based on the results of an analysis module.

[0657] "Advice" is guidance and suggestions generated based on the user's career aspirations and emotional data, and is intended to improve the user's working and communication methods.

[0658] "Real-time" is a concept that indicates that the time between data being generated and transmitted and being processed immediately, and the results being presented, is extremely short.

[0659] MODE FOR CARRYING OUT THE INVENTION

[0660] This invention is a system that analyzes the career aspirations of individual users and proposes optimal work methods and communication styles. This system provides more personalized advice by combining data entered by the user through a terminal with emotional data generated by an emotion engine.

[0661] First, the user uses the smart glasses to input data such as their career aspirations, experience, and skills. During this input, the smart glasses analyze the user's facial expressions and voice in real time through an emotion engine to generate emotion data. The emotion engine uses software specialized for emotion analysis (e.g., Microsoft Azure Emotion API).

[0662] Next, the device sends the user input data and generated emotion data to the server using an HTTP POST request, which then uses a data management system such as Apache Kafka to temporarily store the data and pass it to the analysis module.

[0663] The server's analysis module uses machine learning algorithms and natural language processing (NLP) to comprehensively analyze the user's career goals, strengths, areas for improvement, and emotional information. Specifically, the server checks the received data format and completeness of the information, and uses generative AI models such as GPT-4 to generate optimal advice for the user.

[0664] The generated advice is sent back to the device from the server. The device provides this advice to the user in real time, for example, on the display of smart glasses. The display format can be customized to make it easy for the user to understand, and a dashboard or report format can be selected.

[0665] As a specific example, let's say a worker inspecting products in a factory feels "fatigue." In this case, the smart glasses will detect fatigue through facial expression analysis and send the data to the server as emotional data. Based on the analysis results, the server will use a generative AI model to generate advice such as "We recommend you take a five-minute break," and display it on the smart glasses' display.

[0666] Examples of prompts to input to a generative AI model might include:

[0667] "When fatigue is detected from a worker's facial expression, how can we suggest a break? Generate specific advice and encouraging messages."

[0668] In this way, a system is realized that combines emotional data and career-oriented data to provide users with optimized advice in real time.

[0669] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[0670] Program processing flow

[0671] Step 1:

[0672] The user uses the smart glasses to input data such as their career aspirations, experience, and skills. The input data includes text-based career goals, work history, and skill sets. While inputting, the smart glasses use a camera and microphone to capture the user's facial expressions and voice in real time.

[0673] Input: Text data of user's career aspirations, experience, and skills, video data of facial expressions, and audio data

[0674] Output: User data temporarily stored in the smart glasses, as well as captured facial expression and voice data.

[0675] How it works: Users input their career aspirations and experience into the smart glasses, while the smart glasses' camera and microphone capture the user's facial expressions and voice in real time.

[0676] Step 2:

[0677] The device passes input data to an emotion engine that analyzes facial expressions and voice data. The emotion engine generates emotion data and uses services such as the Microsoft Azure Emotion API to identify emotions such as joy, anger, fear, and sadness.

[0678] Input: Captured facial expression video data, audio data

[0679] Output: Emotion data (e.g., 80% happiness, 10% anger, 10% sadness)

[0680] What it does: The emotion engine analyzes facial expressions and voice data to quantify the user's emotional state.

[0681] Step 3:

[0682] The device sends the user data and the generated emotion data to the server via an HTTP POST request.

[0683] Input: User data (career aspirations, experience, skills), emotional data

[0684] Output: Data sent to the server

[0685] Specific operation: The device temporarily stores user data and emotion data and sends them to the server.

[0686] Step 4:

[0687] The server checks the format and integrity of the received data and passes it to the analysis module. The data is temporarily stored using a data management system such as Apache Kafka.

[0688] Input: User data, emotion data

[0689] Output: Data passed to the analysis module

[0690] Specific operation: The server checks the data format, requests retransmission if there is incomplete data, and passes the complete data to the analysis module.

[0691] Step 5:

[0692] The analysis module uses machine learning algorithms and natural language processing (NLP) technology to comprehensively analyze the user's career goals, strengths, areas for improvement, and emotional information.

[0693] Input: Data passed to be analyzed (user data, emotion data)

[0694] Output: Analysis results (user's career goals, strengths, areas for improvement, emotional information)

[0695] What it does: The analysis module uses machine learning algorithms and NLP techniques to analyze user data and sentiment data.

[0696] Step 6:

[0697] Based on the analysis results, the server uses a generative AI model (e.g., GPT-4) to generate optimal advice for the user, with the tone and content adapted according to the user's emotional state.

[0698] Input: Analysis results (user's career goals, strengths, areas for improvement, emotional information)

[0699] Output: The generated advice

[0700] Specific operation: The server inputs prompts into the generative AI model and generates advice according to the user's emotional state. An example of a prompt is, "When fatigue is detected from a worker's facial expression, how should you suggest a break? Please generate specific advice and encouraging messages."

[0701] Step 7:

[0702] The server sends the generated advice back to the device, which then provides it to the user in real time.The advice is displayed on the smart glasses display.

[0703] Input: Generated advice

[0704] Output: Advice displayed to the user

[0705] Specific operation: The device displays the advice received from the server to the user in real time, supporting the user's actions.

[0706] 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.

[0707] 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.

[0708] 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.

[0709] [Third embodiment]

[0710] FIG. 5 shows an example of the configuration of a data processing system 310 according to the third embodiment.

[0711] 5, the data processing system 310 includes the data processing device 12 and a headset terminal 314. An example of the data processing device 12 is a server.

[0712] 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).

[0713] 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.

[0714] 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.

[0715] 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).

[0716] 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.

[0717] 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.

[0718] 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.

[0719] 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.

[0720] 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.

[0721] 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."

[0722] In this invention, the following system and program are implemented to identify the career aspirations of each user and propose optimal work methods and communication styles.

[0723] First, a user uses a device to input data such as career information, skills, experience, and goals. This input data is done through a UI (user interface), such as a web form or a mobile app input form. The device then sends this input data to a server.

[0724] The server analyzes the received data using machine learning algorithms and natural language processing techniques to identify the user's career goals, strengths, and areas for improvement.

[0725] Once the analysis is complete, the server uses generative AI to generate optimal advice for the user, such as career path suggestions, training methods to improve skills, how to use tools to improve work efficiency, and effective communication methods.

[0726] The generated advice is returned from the server to the device, which receives it and displays it in a format that is easy for the user to understand, such as a visual display in the form of a dashboard or a report.

[0727] To give a specific example, suppose a user has a career goal of becoming a management consultant and has five years of experience as a marketing analyst. When the user enters this information on their device and sends it to the server, the server analyzes the user data and identifies strengths in marketing and analytical skills. Based on the analysis results, the generative AI generates specific advice such as obtaining an MBA, strengthening strategic thinking, and improving leadership skills. It also suggests effective ways to use project management tools and team communication.

[0728] In this way, the present invention provides specific, actionable career advice tailored to each user's needs, helping them to move efficiently and effectively towards their career goals.

[0729] The processing flow will be explained below.

[0730] Step 1:

[0731] The user inputs data such as career aspirations, experience, and skills through the terminal, which then temporarily stores the input data.

[0732] Step 2:

[0733] The terminal sends the input data to the server, for example, by using an HTTP POST request.

[0734] Step 3:

[0735] The server checks the data it receives, checking that the data is in the correct format and that all required information is included.

[0736] Step 4:

[0737] The server passes the received data to the analysis module, which analyzes the data using machine learning algorithms and natural language processing.

[0738] Step 5:

[0739] The analysis module identifies the user's career goals, strengths, and areas for improvement. For example, it analyzes the user's skill set and work history to extract strengths and weaknesses.

[0740] Step 6:

[0741] The server passes the analysis results to the generation AI, which then generates optimal advice for the user based on the analysis results.

[0742] Step 7:

[0743] Generative AI generates specific advice to provide to users, including career path suggestions and training methods to improve skills.

[0744] Step 8:

[0745] The server returns the generated advice to the device in JSON format.

[0746] Step 9:

[0747] The device receives the advice returned from the server and displays it in a format that is easy for the user to understand, such as a dashboard or report.

[0748] Step 10:

[0749] Users can review the displayed advice and use it as a reference for their future career development. They can also request more detailed information via their device.

[0750] Example 1

[0751] 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."

[0752] Conventional career advice systems have had difficulty generating optimal advice by fully analyzing each user's career aspirations, experience, skills, etc. Furthermore, the generated advice is often provided in a format that is difficult for users to understand, which has led to the problem of users being unable to receive advice that is actually useful.

[0753] 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.

[0754] In this invention, the server includes means for inputting data such as an individual's career aspirations, experience, and skills from a terminal, means for transmitting the input data to the server, means for the server to analyze the received data, means for generating optimal advice using a generation AI based on the analysis results, means for returning the generated advice to the terminal, and means for the terminal to display the returned advice in dashboard or report format. This allows the server to provide specific and actionable career advice tailored to the needs of each individual user, enabling the user to move efficiently and effectively toward their career goals.

[0755] "Career aspirations" refer to the hopes and goals that individuals have regarding the direction of their future careers and work.

[0756] "Experience" refers to an individual's track record and history based on the tasks, projects, and positions they have held in the past.

[0757] "Skills" refer to the abilities, knowledge, and techniques that an individual possesses to carry out specific tasks or tasks.

[0758] A "terminal" is a device through which a user inputs data and communicates with a server, and specifically includes a personal computer, a smartphone, etc.

[0759] A "server" is a computer system that analyzes the received data and generates and provides the necessary information and advice to users.

[0760] "Machine learning algorithms" refers to a collection of mathematical models that learn patterns from data and perform tasks such as prediction and classification automatically.

[0761] "Natural language processing technology" refers to technology that enables computers to understand, interpret, and generate human language.

[0762] "Generative AI" refers to technology that uses artificial intelligence models to generate new information and content.

[0763] "Dashboard format" refers to a graphical layout that displays important information in a visually easy-to-understand manner.

[0764] "Report format" refers to a format in which information and data are compiled in an orderly manner as a document.

[0765] This invention configures a system that collects data such as a user's career aspirations, experience, and skills, and provides optimal advice. Specific hardware requirements include a device (such as a PC or smartphone) for users to input data, and a server for processing and analyzing the data. Software requirements include a web form or mobile app as the user interface (UI), machine learning algorithms (e.g., scikit-learn) and natural language processing technology (e.g., spaCy) for data analysis, and a generative AI model (e.g., GPT-4) for generating advice.

[0766] First, a user uses a device to enter information about their career aspirations, including specific career goals, past experience, and skills. For example, a user might enter "I want to be a management consultant" or "I have five years of experience as a marketing analyst" into a form on the mobile app.

[0767] Next, the terminal sends the input data to the server in a data format such as JSON, using an HTTP POST request.

[0768] The server analyzes the received data to identify the user's career goals and skills. This analysis is performed using machine learning algorithms and natural language processing techniques. For example, scikit-learn is used to evaluate experience and skills, and spaCy is used to analyze text data.

[0769] The server then uses a generative AI model to generate optimal advice based on the analysis results. For example, it uses GPT-4 to generate specific career advice such as "obtain an MBA" or "strengthen strategic thinking."

[0770] The generated advice is sent back from the server to the device, which receives it and displays it in a format that is easy for the user to understand. For example, a mobile app could visually display the advice in a dashboard format and provide a message to the user, such as "It is recommended that you get an MBA."

[0771] As a concrete example, suppose a user has a career goal of becoming a management consultant and has five years of experience as a marketing analyst. When the user enters this information on their device and sends it to the server, the server analyzes the user data and identifies strengths in marketing and analytical skills. Based on the analysis results, the generative AI generates specific advice such as obtaining an MBA, strengthening strategic thinking, and improving leadership skills. It also suggests effective ways to use project management tools and team communication.

[0772] Examples of prompts include:

[0773] "I'm thinking about getting an MBA. Can you give me some advice on how to prepare and improve my related skills?"

[0774] "I have five years of experience as a marketing analyst. What skills do I need to become a management consultant?"

[0775] "What specific tools and methods can you use to improve team communication?"

[0776] The present invention allows users to receive specific, actionable career advice and effectively progress towards their career goals.

[0777] The flow of the identification process in the first embodiment will be described with reference to FIG.

[0778] Step 1:

[0779] User enters career information

[0780] The user uses the device to input information about their career (goals, experience, skills). Specifically, they enter information such as "I want to be a management consultant" or "I have five years of experience as a marketing analyst" into a form on the mobile app. The input data is in JSON format, and once the data has been entered, they press the "Submit" button.

[0781] Step 2:

[0782] The device sends the input data to the server

[0783] The device sends the data entered by the user to the server as an HTTP POST request. The input data is in JSON format, for example:

[0784] json

[0785] {

[0786] "career_goal": "Management Consultant",

[0787] "experience": "5 years as a marketing analyst"

[0788] }

[0789] The terminal transmits this data to the server over the network.

[0790] Step 3:

[0791] The server analyzes the data

[0792] The server analyzes the received JSON data using machine learning algorithms (such as scikit-learn) and natural language processing techniques (such as spaCy). The specific process is as follows:

[0793] The server receives the data and parses the JSON.

[0794] Using scikit-learn, we cluster users' experiences and skills and generate profiles.

[0795] Use spaCy to perform natural language processing on users' career goals.

[0796] Step 4:

[0797] The server generates the advice

[0798] Based on the analysis results, the server uses a generative AI model (such as GPT-4) to generate optimal advice. The generation process is as follows:

[0799] A prompt sentence is created using the user profile and goals obtained from the analysis.

[0800] For example, specific career advice such as "Get an MBA" or "Improve your strategic thinking" can be input as prompts into the generative AI.

[0801] The generative AI generates appropriate advice, and we get output like this example:

[0802] "An MBA is recommended for your career path as a management consultant, and training to strengthen your strategic thinking and leadership skills will be helpful."

[0803] Step 5:

[0804] The server sends the generated advice back to the device

[0805] The server reformats the generated advice in JSON format and sends it back to the device as an HTTP response. An example of generated advice might be returned as JSON like this:

[0806] json

[0807] {

[0808] "advice": "For your career path as a management consultant, an MBA is recommended. Training to strengthen your strategic thinking and leadership skills will also be beneficial."

[0809] }

[0810] The server transmits this data to the terminal via the network.

[0811] Step 6:

[0812] The device displays advice

[0813] The device parses the JSON data received from the server and displays visual advice to the user. The specific operations are as follows:

[0814] The device parses the received JSON and obtains the advice content.

[0815] The mobile app displays advice in the form of a dashboard, providing users with messages such as "Getting an MBA is recommended."

[0816] This allows users to receive specific and actionable career advice and move efficiently towards their career goals.

[0817] (Application example 1)

[0818] 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."

[0819] Conventional career orientation analysis systems have had the problem of lacking real-time support for improving individual workers' work efficiency and skills. In particular, in factory work environments, workers are unable to receive appropriate advice quickly, resulting in reduced work efficiency and delayed skill improvement. Furthermore, the user interface for data entry and advice reception is often complex and difficult to use. The objective of the present invention is to solve these problems and provide a more efficient and effective career support system.

[0820] 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.

[0821] In this invention, the server includes: means for inputting data such as an individual's career aspirations, experience, and skills from a terminal; means for transmitting the input data to the server; means for the server to analyze the received data; means for generating optimal advice using a generation AI based on the analysis results; means for returning the generated advice to the terminal; means for the terminal to display the returned advice; means for promoting improvement of the work situation and skill level based on the data input by the worker; and means for receiving user input via an interactive interface in the smart device and displaying advice for improving work efficiency in the factory in real time. This enables employees to receive optimal advice based on their own work situation in real time, thereby improving work efficiency and quickly improving their skills.

[0822] "Individual career aspirations" refer to the career direction, goals, and interests that individuals wish to achieve in the future.

[0823] The "server" is an information processing device that receives and analyzes data sent from personal devices and generates optimal advice using a generation AI.

[0824] "Generative AI" refers to artificial intelligence technology that automatically generates optimal advice and instructions based on input data.

[0825] A "terminal" is a device for inputting data and displaying analysis results and advice returned from the server, and includes smart glasses and smartphones.

[0826] "Work status" includes the state and progress of work being done in a factory or on-site, as well as the tools and methods being used.

[0827] "Skill level" refers to an individual's degree of technical ability or knowledge in a particular task or job.

[0828] An "interactive interface" refers to a user interface in which a user inputs and gives instructions in natural language, and the system responds flexibly accordingly.

[0829] This invention is a career support system for improving work efficiency in factories, which collects and analyzes data such as an individual's career aspirations, experience, and skills, and uses generative AI to provide optimal advice. Below, we will explain in detail the form in which this system is realized.

[0830] 1. System Configuration

[0831] The system includes the following main components:

[0832] Terminal: A device such as smart glasses or a smartphone where the user inputs data and receives and displays advice.

[0833] Server: An information processing device that receives, analyzes, and generates advice using AI.

[0834] Generative AI model: An artificial intelligence technology (e.g., GPT-4) that generates optimal advice based on data input by the user.

[0835] Database: A data storage system that stores user-entered data and serves as the basis for analysis.

[0836] NLP libraries: Libraries for natural language processing (e.g. spaCy).

[0837] Machine learning algorithms: Algorithms for extracting and analyzing data features (e.g., scikit-learn).

[0838] 2. Data entry and submission

[0839] Users input data such as their career aspirations, experience, skills, and work situation into the terminal. The conversational interface of the smart glasses allows input in natural language. For example, input as follows:

[0840] "Tell us about your work as a painter. What tools do you use, how many years of experience do you have, and what are your current concerns?"

[0841] This input data is sent to the server in real time.

[0842] 3. Data analysis and advice generation

[0843] The server analyzes the received data. To do this, it uses an NLP library (e.g., spaCy) to tokenize and summarize the text data, and then uses a machine learning algorithm (e.g., scikit-learn) to extract features from the data. For example, it identifies the work situation, areas of skill deficiency, and areas for improvement.

[0844] Based on the analysis results, a generative AI model (e.g., GPT-4) generates optimal advice for the user. Examples of prompts for the generative AI are as follows:

[0845] "User's work status: {Work status data}

[0846] User Skills: {Skills data}

[0847] User's problem: {Problem data}

[0848] Please suggest the best way to do this."

[0849] 4. Sending and Viewing Advice

[0850] The generated advice is sent from the server to the device, which visually displays this advice to the user in real time. For example, the following advice may be displayed on the display of smart glasses:

[0851] "When using painting tool A, keep it at a 45-degree angle for best efficiency. Also, consider introducing tool B."

[0852] 5. System Operation Example

[0853] Let's say a worker wants to improve his or her work efficiency as a "painter." The worker uses smart glasses to input information about the current work situation, the tools used, and any concerns. Based on this, the server analyzes the data, and the generative AI model generates optimal advice. As a result, the worker can learn efficient work methods and how to introduce new tools in real time, improving their work efficiency.

[0854] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[0855] Step 1:

[0856] The user uses the conversational interface of the smart glasses to input data such as their career aspirations, experience, skills, and work situation in natural language. This includes text input and voice input. For example, the user inputs data in response to prompts such as, "Tell me about your work situation as a painter. Please enter the tools you use, years of experience, and current concerns."

[0857] input:

[0858] User's career information (e.g., work situation, tools used, years of experience, current concerns)

[0859] output:

[0860] Entered carrier data

[0861] Step 2:

[0862] The device transmits the input data to the server in real time using a secure communication protocol to ensure data integrity and privacy.

[0863] input:

[0864] User's career data

[0865] output:

[0866] Carrier data sent to the server

[0867] Step 3:

[0868] The server analyzes the received data. First, it uses an NLP library (e.g., spaCy) to tokenize the text data and extract important keywords and phrases. Then, it uses a machine learning algorithm (e.g., scikit-learn) to analyze the data's features and evaluate the user's skill level and work status.

[0869] input:

[0870] Carrier data sent to the server

[0871] output:

[0872] Analyzed feature data (e.g., important keywords, skill level, work situation evaluation)

[0873] Step 4:

[0874] The server uses a generative AI model (e.g., GPT-4) based on the analysis results to generate optimal advice. The generative AI model uses the input feature data as prompts to automatically generate useful advice for the user.

[0875] Example of generated AI prompt:

[0876] "User's work status: {Work status data}

[0877] User Skills: {Skills data}

[0878] User's problem: {Problem data}

[0879] Please suggest the best way to do this."

[0880] input:

[0881] Analyzed feature data

[0882] output:

[0883] Generated Advice

[0884] Step 5:

[0885] The server sends the generated advice to the device in real time, using a secure communication protocol to ensure the data reaches the device reliably.

[0886] input:

[0887] Generated Advice

[0888] output:

[0889] Advice sent to device

[0890] Step 6:

[0891] The device visually displays the received advice. The advice is presented on the smart glasses display in a format that is easy for the user to understand. For example, specific advice such as "When using painting tool A, keeping it at a 45-degree angle will increase efficiency. Also, consider introducing tool B."

[0892] input:

[0893] Advice received

[0894] output:

[0895] Advice shown on the display

[0896] Through the above processing steps, the user can receive optimal advice in real time according to his / her own work situation, thereby improving work efficiency.

[0897] 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.

[0898] This invention is a system that analyzes the career aspirations of individual users and further combines an emotion engine to propose optimal work methods and communication styles. The present invention is specifically implemented as follows.

[0899] First, the user inputs data such as career aspirations, experience, and skills through the device. The device temporarily stores this input data and monitors the user's facial expressions and voice while they are inputting via an emotion engine. The emotion engine analyzes this data and generates emotion data for the user.

[0900] Next, the device sends the user data and emotion data to the server, for example, using an HTTP POST request. The server then checks the received data to ensure that the data format and all necessary information are included.

[0901] The server passes the received data to an analysis module, which uses machine learning algorithms and natural language processing techniques to identify the user's career goals, strengths, areas for improvement, and emotional information.

[0902] After completing the analysis, the server passes the results to the generation AI, which generates optimal advice for the user based on the analysis results and emotional data. This advice may include career path suggestions, training methods to improve skills, how to use tools to improve work efficiency, and effective communication methods. The generation AI then adapts the tone and content of the advice based on the user's emotions.

[0903] The generated advice is returned from the server to the terminal, which receives the advice and displays it in a format that is easy for the user to understand. For example, it could be displayed in a dashboard format or a report format.

[0904] To give a specific example, suppose a user has a career goal of becoming a management consultant and has five years of experience as a marketing analyst. The user enters this information on their device, and the emotion engine detects excitement or anxiety from the user's facial expressions while they are entering the information. The user data and emotion data are sent to the server, which analyzes the user's skill set and work history to identify their strengths and weaknesses. Based on the analysis results and emotion information, the generative AI generates specific advice. For example, it may suggest obtaining an MBA, strengthening strategic thinking, and improving leadership skills, as well as using project management tools and methods for team communication. If the user feels anxious, the AI ​​provides encouragement and specific action plans to alleviate their anxiety.

[0905] In this way, by combining emotion engines, a system is realized that provides specific and actionable career advice tailored to each user's needs, allowing users to move efficiently and effectively toward their career goals.

[0906] The processing flow will be explained below.

[0907] Step 1:

[0908] Users input data such as career aspirations, experience, and skills through the terminal, which then temporarily stores this data.

[0909] Step 2:

[0910] While the device is inputting, it uses an emotion engine to monitor the user's facial expressions and voice, for example, by using a camera and microphone to collect emotion data.

[0911] Step 3:

[0912] The emotion engine analyzes the collected facial expressions and voice data to recognize the user's emotions (e.g., excitement, joy, anxiety), and generate emotion data.

[0913] Step 4:

[0914] The device sends user data and emotion data to the server using a secure HTTP POST request.

[0915] Step 5:

[0916] The server checks the received data and checks whether the format and necessary information are included. If there is a shortage, it returns an error message to the terminal.

[0917] Step 6:

[0918] The server passes the received data to the analysis module, which analyzes the data using machine learning algorithms and natural language processing techniques.

[0919] Step 7:

[0920] The analysis module identifies the user's career goals, strengths, areas for improvement, and emotional information, for example, by analyzing the user's skill set and work history to extract strengths and weaknesses.

[0921] Step 8:

[0922] The server passes the analysis results to the generation AI, which then generates optimal advice based on the analysis results and emotional data.

[0923] Step 9:

[0924] Generative AI generates specific advice to provide to users, including career path suggestions and training methods to improve skills.

[0925] Step 10:

[0926] The generative AI adapts the tone and content of the advice depending on the user's emotions, for example including encouraging words for users who are feeling anxious.

[0927] Step 11:

[0928] The server returns the generated advice to the device in JSON format.

[0929] Step 12:

[0930] The device receives the advice returned from the server and displays it in a format that is easy for the user to understand, such as a dashboard or report.

[0931] Step 13:

[0932] Users can review the displayed advice and use it as a reference for their future career development. They can also request more detailed information via their device.

[0933] Example 2

[0934] 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."

[0935] Conventional career support systems rely solely on static data provided by users, making it difficult to provide advice that takes into account the emotions and subtle nuances of each individual user. Furthermore, they lacked a mechanism for monitoring emotional fluctuations and providing advice that is appropriate for each user, which limited the accuracy and reliability of the advice users received.

[0936] The identification process by the identification processing unit 290 of the data processing device 12 in the second embodiment is realized by the following means. In this invention, the server includes means for monitoring the user's facial expressions and voice via an emotion engine, means for the emotion engine to generate emotion data of the user, and means for analyzing the data received by the server using a machine learning algorithm and natural language processing technology. This enables real-time career advice that takes the user's emotions into consideration.

[0937] A "user" is an individual who uses the system to input information such as career aspirations, experience, and skills, and receives advice.

[0938] A "terminal" is an electronic device that allows users to input their personal information and collect facial expressions and voice data. Examples include personal computers and smartphones.

[0939] An "emotion engine" is software or hardware that generates user emotion data based on the user's facial expressions and voice data collected from the device.

[0940] "User data" refers to information regarding career aspirations, experience, skills, etc. that a user inputs via a terminal.

[0941] "Emotion data" refers to information about emotions obtained from the user's facial expressions and voice as analyzed by the emotion engine.

[0942] The "server" is a computer system that receives user data and emotion data and generates advice using an analysis module and a generation AI.

[0943] An "analysis module" is software that is placed in the server and analyzes received data using machine learning algorithms and natural language processing technology.

[0944] "Generative AI" is an artificial intelligence that generates optimal career advice for users based on the results extracted by the analysis module and emotional data.

[0945] An "HTTP POST request" is one of the communication protocols used to send data from a terminal to a server.

[0946] A "machine learning algorithm" is an algorithm that learns patterns from large amounts of data and makes predictions and classifications.

[0947] "Natural language processing technology" is a technology that allows computers to understand and process human language.

[0948] "Career advice" refers to career paths, ways to improve skills, measures to improve work efficiency, communication methods, etc. suggested by generative AI based on user data and emotional data.

[0949] MODE FOR CARRYING OUT THE INVENTION

[0950] This invention is a system that analyzes a user's career aspirations and suggests optimal work methods and communication styles. The system is configured by combining an emotion engine and is specifically implemented as follows.

[0951] First, the user inputs data such as career aspirations, experience, and skills through the device. The device temporarily stores this input data and transmits the user's facial expressions and voice in real time to the emotion engine, which then analyzes the facial and voice data to generate the user's emotion data.

[0952] Next, the device sends the user data and emotion data to the server. The HTTP POST request is used as the communication protocol for transmission. The server checks the format of the received data and whether all the necessary information is present. After checking the data format and whether all the information is present, the server passes the data to the analysis module.

[0953] The analysis module uses machine learning algorithms and natural language processing techniques to analyze the received data. The analysis module identifies the user's career goals, strengths, areas for improvement, and emotional information. Based on this analysis, the server passes the analysis results to the generation AI.

[0954] Based on the analysis results and emotional data, the generative AI generates optimal advice for users. This advice can include career path suggestions, training methods to improve skills, how to use tools to improve work efficiency, and effective communication methods. The generative AI adapts the tone and content of the advice depending on the user's emotions.

[0955] The generated advice is returned to the terminal via the server. The terminal receives this advice and presents it to the user in a visualized format, such as a dashboard or report, which makes it easier for the user to intuitively understand the advice.

[0956] As a concrete example, let's say a user has a career goal of becoming a management consultant and has five years of experience as a marketing analyst. The user enters this information on their device, and while they are entering it, the emotion engine detects excitement or anxiety from the user's facial expressions. The user data and emotion data are sent to the server, which analyzes it and analyzes the user's skill set and work history. Based on the analysis results and emotion information, the generation AI generates specific advice. For example, it suggests advice such as "obtaining an MBA," "strengthening strategic thinking," and "improving leadership skills," as well as "using project management tools" and "team communication methods." If the user feels anxious, the engine provides encouragement and advice including a specific action plan to alleviate their anxiety.

[0957] Example prompt sentence:

[0958] "I'd like to work as a management consultant. I have five years of experience as a marketing analyst. Can you give me some advice on how to improve my skills and career path?"

[0959] By feeding these prompts into a generative AI, users can get specific, customized advice, which will then make optimal suggestions based on their emotions and career data.

[0960] In this way, the combination of the emotion engine and the system provides specific, actionable career advice tailored to each user's needs, enabling users to move efficiently and effectively toward their career goals.

[0961] The flow of the identification process in the second embodiment will be described with reference to FIG.

[0962] Step 1:

[0963] The user enters information using the terminal.

[0964] The user enters data about their career aspirations, experience, and skills into an input form on the device. This inputs user data such as "career goals," "experience," and "skills" into the device. While the data is being input, the device also uses a camera and microphone to collect the user's facial expressions and voice in real time and sends this data to the emotion engine. This allows the device to record "facial expression data" and "voice data."

[0965] Step 2:

[0966] The device generates emotion data.

[0967] The emotion engine analyzes the facial expression and voice data sent from the device to generate the user's emotion data. This analysis is performed using an emotion recognition algorithm, specifically a machine learning model that identifies the user's facial expressions and voice patterns to identify emotions such as "excitement" or "anxiety." The output is "emotion data."

[0968] Step 3:

[0969] The terminal transmits user data and emotion data to the server.

[0970] The device structures the user data and emotion data and sends it to the server as a single data packet via an HTTP POST request. This data packet contains the user ID, career goals, experience, skills, and emotion data. The output is the data packet sent to the server.

[0971] Step 4:

[0972] The server accepts the data and performs format validation.

[0973] The server receives the HTTP POST request sent from the terminal and checks the format of the data packet. It checks that each data item is in the correct format and that all required information is present. Specifically, it performs "required field checks" and "format validation." The output is either "the data is valid" or an "error message."

[0974] Step 5:

[0975] The server passes the data to the analysis module.

[0976] The server passes the format-verified data packet to the analysis module, which analyzes the data using machine learning algorithms and natural language processing techniques. This analysis identifies the user's career goals, strengths, areas for improvement, and emotional information. The output is the "analysis results."

[0977] Step 6:

[0978] Generative AI generates advice.

[0979] The server sends the analysis results to the generation AI, which then generates optimal advice based on the analysis results and emotional data. The generation AI generates career path suggestions, ways to improve skills, how to use tools to improve work efficiency, effective communication methods, and more. At this time, it also adjusts the tone and content of the advice depending on the emotion. "Advice data" is generated as the output.

[0980] Step 7:

[0981] The server sends the advice to the terminal.

[0982] The generated advice data is returned to the device via the server. The server converts the advice data into JSON format and sends it to the device via an HTTP POST request. The output is the "advice data" sent to the device.

[0983] Step 8:

[0984] The device displays the advice.

[0985] The device receives the advice data sent from the server and displays it in a format that is easy for the user to understand. For example, this could be displayed in a dashboard or report format. Specifically, the device visualizes and displays advice such as "career path suggestions," "training methods to improve skills," "how to use tools to increase work efficiency," and "effective communication methods." This allows the user to create a specific action plan.

[0986] (Application example 2)

[0987] 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."

[0988] Conventional career advice systems are unable to take into account the user's emotional state, making it difficult to provide detailed advice based on the individual user's emotions and physical condition. Furthermore, because they are unable to provide real-time feedback, they are unable to provide practical advice that users can immediately implement. This has resulted in the challenge of being unable to effectively support users in achieving their career goals.

[0989] The specification process by the specification 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 analyzing the career aspirations, experience, skills, etc. input by the user, means for generating user emotion data and sending it to the server, and means for checking the received data format and the integrity of the information and passing it to the analysis module. This makes it possible to use the user emotion data for analysis and provide personalized advice in real time.

[0990] Term definition

[0991] "Career aspirations" refer to an individual's occupational and work interests, goals, and hopes and plans regarding a specific career path.

[0992] "Experience" refers to an individual's past work history and the knowledge and skills they acquired there, which influence their current abilities and career aspirations.

[0993] "Skills" is a general term for the techniques and abilities required to perform specific jobs or tasks.

[0994] A "terminal" is a device (e.g., a smartphone, a personal computer, smart glasses, etc.) that a user uses to manipulate input data and interact with the system.

[0995] An "emotion engine" is a software system that analyzes a user's facial expressions and voice to generate emotion data.

[0996] "Emotion data" is data that is generated by the emotion engine and indicates the user's emotional state.

[0997] A "server" is a remote computer system that receives data sent by a user, analyzes it, and generates and sends results back to the user.

[0998] An "analysis module" is a software component that performs data analysis within the server, and uses machine learning algorithms and natural language processing techniques.

[0999] "Generative AI" is an artificial intelligence technology that generates optimal advice based on the results of an analysis module.

[1000] "Advice" is guidance and suggestions generated based on the user's career aspirations and emotional data, and is intended to improve the user's working and communication methods.

[1001] "Real-time" is a concept that indicates that the time between data being generated and transmitted and being processed immediately, and the results being presented, is extremely short.

[1002] MODE FOR CARRYING OUT THE INVENTION

[1003] This invention is a system that analyzes the career aspirations of individual users and proposes optimal work methods and communication styles. This system provides more personalized advice by combining data entered by the user through a terminal with emotional data generated by an emotion engine.

[1004] First, the user uses the smart glasses to input data such as their career aspirations, experience, and skills. During this input, the smart glasses analyze the user's facial expressions and voice in real time through an emotion engine to generate emotion data. The emotion engine uses software specialized for emotion analysis (e.g., Microsoft Azure Emotion API).

[1005] Next, the device sends the user input data and generated emotion data to the server using an HTTP POST request, which then uses a data management system such as Apache Kafka to temporarily store the data and pass it to the analysis module.

[1006] The server's analysis module uses machine learning algorithms and natural language processing (NLP) to comprehensively analyze the user's career goals, strengths, areas for improvement, and emotional information. Specifically, the server checks the received data format and completeness of the information, and uses generative AI models such as GPT-4 to generate optimal advice for the user.

[1007] The generated advice is sent back to the device from the server. The device provides this advice to the user in real time, for example, on the display of smart glasses. The display format can be customized to make it easy for the user to understand, and a dashboard or report format can be selected.

[1008] As a specific example, let's say a worker inspecting products in a factory feels "fatigue." In this case, the smart glasses will detect fatigue through facial expression analysis and send the data to the server as emotional data. Based on the analysis results, the server will use a generative AI model to generate advice such as "We recommend you take a five-minute break," and display it on the smart glasses' display.

[1009] Examples of prompts to input to a generative AI model might include:

[1010] "When fatigue is detected from a worker's facial expression, how can we suggest a break? Generate specific advice and encouraging messages."

[1011] In this way, a system is realized that combines emotional data and career-oriented data to provide users with optimized advice in real time.

[1012] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[1013] Program processing flow

[1014] Step 1:

[1015] The user uses the smart glasses to input data such as their career aspirations, experience, and skills. The input data includes text-based career goals, work history, and skill sets. While inputting, the smart glasses use a camera and microphone to capture the user's facial expressions and voice in real time.

[1016] Input: Text data of user's career aspirations, experience, and skills, video data of facial expressions, and audio data

[1017] Output: User data temporarily stored in the smart glasses, as well as captured facial expression and voice data.

[1018] How it works: Users input their career aspirations and experience into the smart glasses, while the smart glasses' camera and microphone capture the user's facial expressions and voice in real time.

[1019] Step 2:

[1020] The device passes input data to an emotion engine that analyzes facial expressions and voice data. The emotion engine generates emotion data and uses services such as the Microsoft Azure Emotion API to identify emotions such as joy, anger, fear, and sadness.

[1021] Input: Captured facial expression video data, audio data

[1022] Output: Emotion data (e.g., 80% happiness, 10% anger, 10% sadness)

[1023] What it does: The emotion engine analyzes facial expressions and voice data to quantify the user's emotional state.

[1024] Step 3:

[1025] The device sends the user data and the generated emotion data to the server via an HTTP POST request.

[1026] Input: User data (career aspirations, experience, skills), emotional data

[1027] Output: Data sent to the server

[1028] Specific operation: The device temporarily stores user data and emotion data and sends them to the server.

[1029] Step 4:

[1030] The server checks the format and integrity of the received data and passes it to the analysis module. The data is temporarily stored using a data management system such as Apache Kafka.

[1031] Input: User data, emotion data

[1032] Output: Data passed to the analysis module

[1033] Specific operation: The server checks the data format, requests retransmission if there is incomplete data, and passes the complete data to the analysis module.

[1034] Step 5:

[1035] The analysis module uses machine learning algorithms and natural language processing (NLP) technology to comprehensively analyze the user's career goals, strengths, areas for improvement, and emotional information.

[1036] Input: Data passed to be analyzed (user data, emotion data)

[1037] Output: Analysis results (user's career goals, strengths, areas for improvement, emotional information)

[1038] What it does: The analysis module uses machine learning algorithms and NLP techniques to analyze user data and sentiment data.

[1039] Step 6:

[1040] Based on the analysis results, the server uses a generative AI model (e.g., GPT-4) to generate optimal advice for the user, with the tone and content adapted according to the user's emotional state.

[1041] Input: Analysis results (user's career goals, strengths, areas for improvement, emotional information)

[1042] Output: The generated advice

[1043] Specific operation: The server inputs prompts into the generative AI model and generates advice according to the user's emotional state. An example of a prompt is, "When fatigue is detected from a worker's facial expression, how should you suggest a break? Please generate specific advice and encouraging messages."

[1044] Step 7:

[1045] The server sends the generated advice back to the device, which then provides it to the user in real time.The advice is displayed on the smart glasses display.

[1046] Input: Generated advice

[1047] Output: Advice displayed to the user

[1048] Specific operation: The device displays the advice received from the server to the user in real time, supporting the user's actions.

[1049] 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.

[1050] 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.

[1051] 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.

[1052] [Fourth embodiment]

[1053] FIG. 7 shows an example of the configuration of a data processing system 410 according to the fourth embodiment.

[1054] 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.

[1055] 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).

[1056] 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.

[1057] 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.

[1058] 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).

[1059] 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.

[1060] 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.

[1061] 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.

[1062] 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.

[1063] 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.

[1064] 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.

[1065] 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."

[1066] In this invention, the following system and program are implemented to identify the career aspirations of each user and propose optimal work methods and communication styles.

[1067] First, a user uses a device to input data such as career information, skills, experience, and goals. This input data is done through a UI (user interface), such as a web form or a mobile app input form. The device then sends this input data to a server.

[1068] The server analyzes the received data using machine learning algorithms and natural language processing techniques to identify the user's career goals, strengths, and areas for improvement.

[1069] Once the analysis is complete, the server uses generative AI to generate optimal advice for the user, such as career path suggestions, training methods to improve skills, how to use tools to improve work efficiency, and effective communication methods.

[1070] The generated advice is returned from the server to the device, which receives it and displays it in a format that is easy for the user to understand, such as a visual display in the form of a dashboard or a report.

[1071] To give a specific example, suppose a user has a career goal of becoming a management consultant and has five years of experience as a marketing analyst. When the user enters this information on their device and sends it to the server, the server analyzes the user data and identifies strengths in marketing and analytical skills. Based on the analysis results, the generative AI generates specific advice such as obtaining an MBA, strengthening strategic thinking, and improving leadership skills. It also suggests effective ways to use project management tools and team communication.

[1072] In this way, the present invention provides specific, actionable career advice tailored to each user's needs, helping them to move efficiently and effectively towards their career goals.

[1073] The processing flow will be explained below.

[1074] Step 1:

[1075] The user inputs data such as career aspirations, experience, and skills through the terminal, which then temporarily stores the input data.

[1076] Step 2:

[1077] The terminal sends the input data to the server, for example, by using an HTTP POST request.

[1078] Step 3:

[1079] The server checks the data it receives, checking that the data is in the correct format and that all required information is included.

[1080] Step 4:

[1081] The server passes the received data to the analysis module, which analyzes the data using machine learning algorithms and natural language processing.

[1082] Step 5:

[1083] The analysis module identifies the user's career goals, strengths, and areas for improvement. For example, it analyzes the user's skill set and work history to extract strengths and weaknesses.

[1084] Step 6:

[1085] The server passes the analysis results to the generation AI, which then generates optimal advice for the user based on the analysis results.

[1086] Step 7:

[1087] Generative AI generates specific advice to provide to users, including career path suggestions and training methods to improve skills.

[1088] Step 8:

[1089] The server returns the generated advice to the device in JSON format.

[1090] Step 9:

[1091] The device receives the advice returned from the server and displays it in a format that is easy for the user to understand, such as a dashboard or report.

[1092] Step 10:

[1093] Users can review the displayed advice and use it as a reference for their future career development. They can also request more detailed information via their device.

[1094] Example 1

[1095] 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."

[1096] Conventional career advice systems have had difficulty generating optimal advice by fully analyzing each user's career aspirations, experience, skills, etc. Furthermore, the generated advice is often provided in a format that is difficult for users to understand, which has led to the problem of users being unable to receive advice that is actually useful.

[1097] 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.

[1098] In this invention, the server includes means for inputting data such as an individual's career aspirations, experience, and skills from a terminal, means for transmitting the input data to the server, means for the server to analyze the received data, means for generating optimal advice using a generation AI based on the analysis results, means for returning the generated advice to the terminal, and means for the terminal to display the returned advice in dashboard or report format. This allows the server to provide specific and actionable career advice tailored to the needs of each individual user, enabling the user to move efficiently and effectively toward their career goals.

[1099] "Career aspirations" refer to the hopes and goals that individuals have regarding the direction of their future careers and work.

[1100] "Experience" refers to an individual's track record and history based on the tasks, projects, and positions they have held in the past.

[1101] "Skills" refer to the abilities, knowledge, and techniques that an individual possesses to carry out specific tasks or tasks.

[1102] A "terminal" is a device through which a user inputs data and communicates with a server, and specifically includes a personal computer, a smartphone, etc.

[1103] A "server" is a computer system that analyzes the received data and generates and provides the necessary information and advice to users.

[1104] "Machine learning algorithms" refers to a collection of mathematical models that learn patterns from data and perform tasks such as prediction and classification automatically.

[1105] "Natural language processing technology" refers to technology that enables computers to understand, interpret, and generate human language.

[1106] "Generative AI" refers to technology that uses artificial intelligence models to generate new information and content.

[1107] "Dashboard format" refers to a graphical layout that displays important information in a visually easy-to-understand manner.

[1108] "Report format" refers to a format in which information and data are compiled in an orderly manner as a document.

[1109] This invention configures a system that collects data such as a user's career aspirations, experience, and skills, and provides optimal advice. Specific hardware requirements include a device (such as a PC or smartphone) for users to input data, and a server for processing and analyzing the data. Software requirements include a web form or mobile app as the user interface (UI), machine learning algorithms (e.g., scikit-learn) and natural language processing technology (e.g., spaCy) for data analysis, and a generative AI model (e.g., GPT-4) for generating advice.

[1110] First, a user uses a device to enter information about their career aspirations, including specific career goals, past experience, and skills. For example, a user might enter "I want to be a management consultant" or "I have five years of experience as a marketing analyst" into a form on the mobile app.

[1111] Next, the terminal sends the input data to the server in a data format such as JSON, using an HTTP POST request.

[1112] The server analyzes the received data to identify the user's career goals and skills. This analysis is performed using machine learning algorithms and natural language processing techniques. For example, scikit-learn is used to evaluate experience and skills, and spaCy is used to analyze text data.

[1113] The server then uses a generative AI model to generate optimal advice based on the analysis results. For example, it uses GPT-4 to generate specific career advice such as "obtain an MBA" or "strengthen strategic thinking."

[1114] The generated advice is sent back from the server to the device, which receives it and displays it in a format that is easy for the user to understand. For example, a mobile app could visually display the advice in a dashboard format and provide a message to the user, such as "It is recommended that you get an MBA."

[1115] As a concrete example, suppose a user has a career goal of becoming a management consultant and has five years of experience as a marketing analyst. When the user enters this information on their device and sends it to the server, the server analyzes the user data and identifies strengths in marketing and analytical skills. Based on the analysis results, the generative AI generates specific advice such as obtaining an MBA, strengthening strategic thinking, and improving leadership skills. It also suggests effective ways to use project management tools and team communication.

[1116] Examples of prompts include:

[1117] "I'm thinking about getting an MBA. Can you give me some advice on how to prepare and improve my related skills?"

[1118] "I have five years of experience as a marketing analyst. What skills do I need to become a management consultant?"

[1119] "What specific tools and methods can you use to improve team communication?"

[1120] The present invention allows users to receive specific, actionable career advice and effectively progress towards their career goals.

[1121] The flow of the identification process in the first embodiment will be described with reference to FIG.

[1122] Step 1:

[1123] User enters career information

[1124] The user uses the device to input information about their career (goals, experience, skills). Specifically, they enter information such as "I want to be a management consultant" or "I have five years of experience as a marketing analyst" into a form on the mobile app. The input data is in JSON format, and once the data has been entered, they press the "Submit" button.

[1125] Step 2:

[1126] The device sends the input data to the server

[1127] The device sends the data entered by the user to the server as an HTTP POST request. The input data is in JSON format, for example:

[1128] json

[1129] {

[1130] "career_goal": "Management Consultant",

[1131] "experience": "5 years as a marketing analyst"

[1132] }

[1133] The terminal transmits this data to the server over the network.

[1134] Step 3:

[1135] The server analyzes the data

[1136] The server analyzes the received JSON data using machine learning algorithms (such as scikit-learn) and natural language processing techniques (such as spaCy). The specific process is as follows:

[1137] The server receives the data and parses the JSON.

[1138] Using scikit-learn, we cluster users' experiences and skills and generate profiles.

[1139] Use spaCy to perform natural language processing on users' career goals.

[1140] Step 4:

[1141] The server generates the advice

[1142] Based on the analysis results, the server uses a generative AI model (such as GPT-4) to generate optimal advice. The generation process is as follows:

[1143] A prompt sentence is created using the user profile and goals obtained from the analysis.

[1144] For example, specific career advice such as "Get an MBA" or "Improve your strategic thinking" can be input as prompts into the generative AI.

[1145] The generative AI generates appropriate advice, and we get output like this example:

[1146] "An MBA is recommended for your career path as a management consultant, and training to strengthen your strategic thinking and leadership skills will be helpful."

[1147] Step 5:

[1148] The server sends the generated advice back to the device

[1149] The server reformats the generated advice in JSON format and sends it back to the device as an HTTP response. An example of generated advice might be returned as JSON like this:

[1150] json

[1151] {

[1152] "advice": "For your career path as a management consultant, an MBA is recommended. Training to strengthen your strategic thinking and leadership skills will also be beneficial."

[1153] }

[1154] The server transmits this data to the terminal via the network.

[1155] Step 6:

[1156] The device displays advice

[1157] The device parses the JSON data received from the server and displays visual advice to the user. The specific operations are as follows:

[1158] The device parses the received JSON and obtains the advice content.

[1159] The mobile app displays advice in the form of a dashboard, providing users with messages such as "Getting an MBA is recommended."

[1160] This allows users to receive specific and actionable career advice and move efficiently towards their career goals.

[1161] (Application example 1)

[1162] 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."

[1163] Conventional career orientation analysis systems have had the problem of lacking real-time support for improving individual workers' work efficiency and skills. In particular, in factory work environments, workers are unable to receive appropriate advice quickly, resulting in reduced work efficiency and delayed skill improvement. Furthermore, the user interface for data entry and advice reception is often complex and difficult to use. The objective of the present invention is to solve these problems and provide a more efficient and effective career support system.

[1164] 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.

[1165] In this invention, the server includes: means for inputting data such as an individual's career aspirations, experience, and skills from a terminal; means for transmitting the input data to the server; means for the server to analyze the received data; means for generating optimal advice using a generation AI based on the analysis results; means for returning the generated advice to the terminal; means for the terminal to display the returned advice; means for promoting improvement of the work situation and skill level based on the data input by the worker; and means for receiving user input via an interactive interface in the smart device and displaying advice for improving work efficiency in the factory in real time. This enables employees to receive optimal advice based on their own work situation in real time, thereby improving work efficiency and quickly improving their skills.

[1166] "Individual career aspirations" refer to the career direction, goals, and interests that individuals wish to achieve in the future.

[1167] The "server" is an information processing device that receives and analyzes data sent from personal devices and generates optimal advice using a generation AI.

[1168] "Generative AI" refers to artificial intelligence technology that automatically generates optimal advice and instructions based on input data.

[1169] A "terminal" is a device for inputting data and displaying analysis results and advice returned from the server, and includes smart glasses and smartphones.

[1170] "Work status" includes the state and progress of work being done in a factory or on-site, as well as the tools and methods being used.

[1171] "Skill level" refers to an individual's degree of technical ability or knowledge in a particular task or job.

[1172] An "interactive interface" refers to a user interface in which a user inputs and gives instructions in natural language, and the system responds flexibly accordingly.

[1173] This invention is a career support system for improving work efficiency in factories, which collects and analyzes data such as an individual's career aspirations, experience, and skills, and uses generative AI to provide optimal advice. Below, we will explain in detail the form in which this system is realized.

[1174] 1. System Configuration

[1175] The system includes the following main components:

[1176] Terminal: A device such as smart glasses or a smartphone where the user inputs data and receives and displays advice.

[1177] Server: An information processing device that receives, analyzes, and generates advice using AI.

[1178] Generative AI model: An artificial intelligence technology (e.g., GPT-4) that generates optimal advice based on data input by the user.

[1179] Database: A data storage system that stores user-entered data and serves as the basis for analysis.

[1180] NLP libraries: Libraries for natural language processing (e.g. spaCy).

[1181] Machine learning algorithms: Algorithms for extracting and analyzing data features (e.g., scikit-learn).

[1182] 2. Data entry and submission

[1183] Users input data such as their career aspirations, experience, skills, and work situation into the terminal. The conversational interface of the smart glasses allows input in natural language. For example, input as follows:

[1184] "Tell us about your work as a painter. What tools do you use, how many years of experience do you have, and what are your current concerns?"

[1185] This input data is sent to the server in real time.

[1186] 3. Data analysis and advice generation

[1187] The server analyzes the received data. To do this, it uses an NLP library (e.g., spaCy) to tokenize and summarize the text data, and then uses a machine learning algorithm (e.g., scikit-learn) to extract features from the data. For example, it identifies the work situation, areas of skill deficiency, and areas for improvement.

[1188] Based on the analysis results, a generative AI model (e.g., GPT-4) generates optimal advice for the user. Examples of prompts for the generative AI are as follows:

[1189] "User's work status: {Work status data}

[1190] User Skills: {Skills data}

[1191] User's problem: {Problem data}

[1192] Please suggest the best way to do this."

[1193] 4. Sending and Viewing Advice

[1194] The generated advice is sent from the server to the device, which visually displays this advice to the user in real time. For example, the following advice may be displayed on the display of smart glasses:

[1195] "When using painting tool A, keep it at a 45-degree angle for best efficiency. Also, consider introducing tool B."

[1196] 5. System Operation Example

[1197] Let's say a worker wants to improve his or her work efficiency as a "painter." The worker uses smart glasses to input information about the current work situation, the tools used, and any concerns. Based on this, the server analyzes the data, and the generative AI model generates optimal advice. As a result, the worker can learn efficient work methods and how to introduce new tools in real time, improving their work efficiency.

[1198] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[1199] Step 1:

[1200] The user uses the conversational interface of the smart glasses to input data such as their career aspirations, experience, skills, and work situation in natural language. This includes text input and voice input. For example, the user inputs data in response to prompts such as, "Tell me about your work situation as a painter. Please enter the tools you use, years of experience, and current concerns."

[1201] input:

[1202] User's career information (e.g., work situation, tools used, years of experience, current concerns)

[1203] output:

[1204] Entered carrier data

[1205] Step 2:

[1206] The device transmits the input data to the server in real time using a secure communication protocol to ensure data integrity and privacy.

[1207] input:

[1208] User's career data

[1209] output:

[1210] Carrier data sent to the server

[1211] Step 3:

[1212] The server analyzes the received data. First, it uses an NLP library (e.g., spaCy) to tokenize the text data and extract important keywords and phrases. Then, it uses a machine learning algorithm (e.g., scikit-learn) to analyze the data's features and evaluate the user's skill level and work status.

[1213] input:

[1214] Carrier data sent to the server

[1215] output:

[1216] Analyzed feature data (e.g., important keywords, skill level, work situation evaluation)

[1217] Step 4:

[1218] The server uses a generative AI model (e.g., GPT-4) based on the analysis results to generate optimal advice. The generative AI model uses the input feature data as prompts to automatically generate useful advice for the user.

[1219] Example of generated AI prompt:

[1220] "User's work status: {Work status data}

[1221] User Skills: {Skills data}

[1222] User's problem: {Problem data}

[1223] Please suggest the best way to do this."

[1224] input:

[1225] Analyzed feature data

[1226] output:

[1227] Generated Advice

[1228] Step 5:

[1229] The server sends the generated advice to the device in real time, using a secure communication protocol to ensure the data reaches the device reliably.

[1230] input:

[1231] Generated Advice

[1232] output:

[1233] Advice sent to device

[1234] Step 6:

[1235] The device visually displays the received advice. The advice is presented on the smart glasses display in a format that is easy for the user to understand. For example, specific advice such as "When using painting tool A, keeping it at a 45-degree angle will increase efficiency. Also, consider introducing tool B."

[1236] input:

[1237] Advice received

[1238] output:

[1239] Advice shown on the display

[1240] Through the above processing steps, the user can receive optimal advice in real time according to his / her own work situation, thereby improving work efficiency.

[1241] 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.

[1242] This invention is a system that analyzes the career aspirations of individual users and further combines an emotion engine to propose optimal work methods and communication styles. The present invention is specifically implemented as follows.

[1243] First, the user inputs data such as career aspirations, experience, and skills through the device. The device temporarily stores this input data and monitors the user's facial expressions and voice while they are inputting via an emotion engine. The emotion engine analyzes this data and generates emotion data for the user.

[1244] Next, the device sends the user data and emotion data to the server, for example, using an HTTP POST request. The server then checks the received data to ensure that the data format and all necessary information are included.

[1245] The server passes the received data to an analysis module, which uses machine learning algorithms and natural language processing techniques to identify the user's career goals, strengths, areas for improvement, and emotional information.

[1246] After completing the analysis, the server passes the results to the generation AI, which generates optimal advice for the user based on the analysis results and emotional data. This advice may include career path suggestions, training methods to improve skills, how to use tools to improve work efficiency, and effective communication methods. The generation AI then adapts the tone and content of the advice based on the user's emotions.

[1247] The generated advice is returned from the server to the terminal, which receives the advice and displays it in a format that is easy for the user to understand. For example, it could be displayed in a dashboard format or a report format.

[1248] To give a specific example, suppose a user has a career goal of becoming a management consultant and has five years of experience as a marketing analyst. The user enters this information on their device, and the emotion engine detects excitement or anxiety from the user's facial expressions while they are entering the information. The user data and emotion data are sent to the server, which analyzes the user's skill set and work history to identify their strengths and weaknesses. Based on the analysis results and emotion information, the generative AI generates specific advice. For example, it may suggest obtaining an MBA, strengthening strategic thinking, and improving leadership skills, as well as using project management tools and methods for team communication. If the user feels anxious, the AI ​​provides encouragement and specific action plans to alleviate their anxiety.

[1249] In this way, by combining emotion engines, a system is realized that provides specific and actionable career advice tailored to each user's needs, allowing users to move efficiently and effectively toward their career goals.

[1250] The processing flow will be explained below.

[1251] Step 1:

[1252] Users input data such as career aspirations, experience, and skills through the terminal, which then temporarily stores this data.

[1253] Step 2:

[1254] While the device is inputting, it uses an emotion engine to monitor the user's facial expressions and voice, for example, by using a camera and microphone to collect emotion data.

[1255] Step 3:

[1256] The emotion engine analyzes the collected facial expressions and voice data to recognize the user's emotions (e.g., excitement, joy, anxiety), and generate emotion data.

[1257] Step 4:

[1258] The device sends user data and emotion data to the server using a secure HTTP POST request.

[1259] Step 5:

[1260] The server checks the received data and checks whether the format and necessary information are included. If there is a shortage, it returns an error message to the terminal.

[1261] Step 6:

[1262] The server passes the received data to the analysis module, which analyzes the data using machine learning algorithms and natural language processing techniques.

[1263] Step 7:

[1264] The analysis module identifies the user's career goals, strengths, areas for improvement, and emotional information, for example, by analyzing the user's skill set and work history to extract strengths and weaknesses.

[1265] Step 8:

[1266] The server passes the analysis results to the generation AI, which then generates optimal advice based on the analysis results and emotional data.

[1267] Step 9:

[1268] Generative AI generates specific advice to provide to users, including career path suggestions and training methods to improve skills.

[1269] Step 10:

[1270] The generative AI adapts the tone and content of the advice depending on the user's emotions, for example including encouraging words for users who are feeling anxious.

[1271] Step 11:

[1272] The server returns the generated advice to the device in JSON format.

[1273] Step 12:

[1274] The device receives the advice returned from the server and displays it in a format that is easy for the user to understand, such as a dashboard or report.

[1275] Step 13:

[1276] Users can review the displayed advice and use it as a reference for their future career development. They can also request more detailed information via their device.

[1277] Example 2

[1278] 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."

[1279] Conventional career support systems rely solely on static data provided by users, making it difficult to provide advice that takes into account the emotions and subtle nuances of each individual user. Furthermore, they lacked a mechanism for monitoring emotional fluctuations and providing advice that is appropriate for each user, which limited the accuracy and reliability of the advice users received.

[1280] The identification process by the identification processing unit 290 of the data processing device 12 in the second embodiment is realized by the following means. In this invention, the server includes means for monitoring the user's facial expressions and voice via an emotion engine, means for the emotion engine to generate emotion data of the user, and means for analyzing the data received by the server using a machine learning algorithm and natural language processing technology. This enables real-time career advice that takes the user's emotions into consideration.

[1281] A "user" is an individual who uses the system to input information such as career aspirations, experience, and skills, and receives advice.

[1282] A "terminal" is an electronic device that allows users to input their personal information and collect facial expressions and voice data. Examples include personal computers and smartphones.

[1283] An "emotion engine" is software or hardware that generates user emotion data based on the user's facial expressions and voice data collected from the device.

[1284] "User data" refers to information regarding career aspirations, experience, skills, etc. that a user inputs via a terminal.

[1285] "Emotion data" refers to information about emotions obtained from the user's facial expressions and voice as analyzed by the emotion engine.

[1286] The "server" is a computer system that receives user data and emotion data and generates advice using an analysis module and a generation AI.

[1287] An "analysis module" is software that is placed in the server and analyzes received data using machine learning algorithms and natural language processing technology.

[1288] "Generative AI" is an artificial intelligence that generates optimal career advice for users based on the results extracted by the analysis module and emotional data.

[1289] An "HTTP POST request" is one of the communication protocols used to send data from a terminal to a server.

[1290] A "machine learning algorithm" is an algorithm that learns patterns from large amounts of data and makes predictions and classifications.

[1291] "Natural language processing technology" is a technology that allows computers to understand and process human language.

[1292] "Career advice" refers to career paths, ways to improve skills, measures to improve work efficiency, communication methods, etc. suggested by generative AI based on user data and emotional data.

[1293] MODE FOR CARRYING OUT THE INVENTION

[1294] This invention is a system that analyzes a user's career aspirations and suggests optimal work methods and communication styles. The system is configured by combining an emotion engine and is specifically implemented as follows.

[1295] First, the user inputs data such as career aspirations, experience, and skills through the device. The device temporarily stores this input data and transmits the user's facial expressions and voice in real time to the emotion engine, which then analyzes the facial and voice data to generate the user's emotion data.

[1296] Next, the device sends the user data and emotion data to the server. The HTTP POST request is used as the communication protocol for transmission. The server checks the format of the received data and whether all the necessary information is present. After checking the data format and whether all the information is present, the server passes the data to the analysis module.

[1297] The analysis module uses machine learning algorithms and natural language processing techniques to analyze the received data. The analysis module identifies the user's career goals, strengths, areas for improvement, and emotional information. Based on this analysis, the server passes the analysis results to the generation AI.

[1298] Based on the analysis results and emotional data, the generative AI generates optimal advice for users. This advice can include career path suggestions, training methods to improve skills, how to use tools to improve work efficiency, and effective communication methods. The generative AI adapts the tone and content of the advice depending on the user's emotions.

[1299] The generated advice is returned to the terminal via the server. The terminal receives this advice and presents it to the user in a visualized format, such as a dashboard or report, which makes it easier for the user to intuitively understand the advice.

[1300] As a concrete example, let's say a user has a career goal of becoming a management consultant and has five years of experience as a marketing analyst. The user enters this information on their device, and while they are entering it, the emotion engine detects excitement or anxiety from the user's facial expressions. The user data and emotion data are sent to the server, which analyzes it and analyzes the user's skill set and work history. Based on the analysis results and emotion information, the generation AI generates specific advice. For example, it suggests advice such as "obtaining an MBA," "strengthening strategic thinking," and "improving leadership skills," as well as "using project management tools" and "team communication methods." If the user feels anxious, the engine provides encouragement and advice including a specific action plan to alleviate their anxiety.

[1301] Example prompt sentence:

[1302] "I'd like to work as a management consultant. I have five years of experience as a marketing analyst. Can you give me some advice on how to improve my skills and career path?"

[1303] By feeding these prompts into a generative AI, users can get specific, customized advice, which will then make optimal suggestions based on their emotions and career data.

[1304] In this way, the combination of the emotion engine and the system provides specific, actionable career advice tailored to each user's needs, enabling users to move efficiently and effectively toward their career goals.

[1305] The flow of the identification process in the second embodiment will be described with reference to FIG.

[1306] Step 1:

[1307] The user enters information using the terminal.

[1308] The user enters data about their career aspirations, experience, and skills into an input form on the device. This inputs user data such as "career goals," "experience," and "skills" into the device. While the data is being input, the device also uses a camera and microphone to collect the user's facial expressions and voice in real time and sends this data to the emotion engine. This allows the device to record "facial expression data" and "voice data."

[1309] Step 2:

[1310] The device generates emotion data.

[1311] The emotion engine analyzes the facial expression and voice data sent from the device to generate the user's emotion data. This analysis is performed using an emotion recognition algorithm, specifically a machine learning model that identifies the user's facial expressions and voice patterns to identify emotions such as "excitement" or "anxiety." The output is "emotion data."

[1312] Step 3:

[1313] The terminal transmits user data and emotion data to the server.

[1314] The device structures the user data and emotion data and sends it to the server as a single data packet via an HTTP POST request. This data packet contains the user ID, career goals, experience, skills, and emotion data. The output is the data packet sent to the server.

[1315] Step 4:

[1316] The server accepts the data and performs format validation.

[1317] The server receives the HTTP POST request sent from the terminal and checks the format of the data packet. It checks that each data item is in the correct format and that all required information is present. Specifically, it performs "required field checks" and "format validation." The output is either "the data is valid" or an "error message."

[1318] Step 5:

[1319] The server passes the data to the analysis module.

[1320] The server passes the format-verified data packet to the analysis module, which analyzes the data using machine learning algorithms and natural language processing techniques. This analysis identifies the user's career goals, strengths, areas for improvement, and emotional information. The output is the "analysis results."

[1321] Step 6:

[1322] Generative AI generates advice.

[1323] The server sends the analysis results to the generation AI, which then generates optimal advice based on the analysis results and emotional data. The generation AI generates career path suggestions, ways to improve skills, how to use tools to improve work efficiency, effective communication methods, and more. At this time, it also adjusts the tone and content of the advice depending on the emotion. "Advice data" is generated as the output.

[1324] Step 7:

[1325] The server sends the advice to the terminal.

[1326] The generated advice data is returned to the device via the server. The server converts the advice data into JSON format and sends it to the device via an HTTP POST request. The output is the "advice data" sent to the device.

[1327] Step 8:

[1328] The device displays the advice.

[1329] The device receives the advice data sent from the server and displays it in a format that is easy for the user to understand. For example, this could be displayed in a dashboard or report format. Specifically, the device visualizes and displays advice such as "career path suggestions," "training methods to improve skills," "how to use tools to increase work efficiency," and "effective communication methods." This allows the user to create a specific action plan.

[1330] (Application example 2)

[1331] 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."

[1332] Conventional career advice systems are unable to take into account the user's emotional state, making it difficult to provide detailed advice based on the individual user's emotions and physical condition. Furthermore, because they are unable to provide real-time feedback, they are unable to provide practical advice that users can immediately implement. This has resulted in the challenge of being unable to effectively support users in achieving their career goals.

[1333] The specification process by the specification 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 analyzing the career aspirations, experience, skills, etc. input by the user, means for generating user emotion data and sending it to the server, and means for checking the received data format and the integrity of the information and passing it to the analysis module. This makes it possible to use the user emotion data for analysis and provide personalized advice in real time.

[1334] Term definition

[1335] "Career aspirations" refer to an individual's occupational and work interests, goals, and hopes and plans regarding a specific career path.

[1336] "Experience" refers to an individual's past work history and the knowledge and skills they acquired there, which influence their current abilities and career aspirations.

[1337] "Skills" is a general term for the techniques and abilities required to perform specific jobs or tasks.

[1338] A "terminal" is a device (e.g., a smartphone, a personal computer, smart glasses, etc.) that a user uses to manipulate input data and interact with the system.

[1339] An "emotion engine" is a software system that analyzes a user's facial expressions and voice to generate emotion data.

[1340] "Emotion data" is data that is generated by the emotion engine and indicates the user's emotional state.

[1341] A "server" is a remote computer system that receives data sent by a user, analyzes it, and generates and sends results back to the user.

[1342] An "analysis module" is a software component that performs data analysis within the server, and uses machine learning algorithms and natural language processing techniques.

[1343] "Generative AI" is an artificial intelligence technology that generates optimal advice based on the results of an analysis module.

[1344] "Advice" is guidance and suggestions generated based on the user's career aspirations and emotional data, and is intended to improve the user's working and communication methods.

[1345] "Real-time" is a concept that indicates that the time between data being generated and transmitted and being processed immediately, and the results being presented, is extremely short.

[1346] MODE FOR CARRYING OUT THE INVENTION

[1347] This invention is a system that analyzes the career aspirations of individual users and proposes optimal work methods and communication styles. This system provides more personalized advice by combining data entered by the user through a terminal with emotional data generated by an emotion engine.

[1348] First, the user uses the smart glasses to input data such as their career aspirations, experience, and skills. During this input, the smart glasses analyze the user's facial expressions and voice in real time through an emotion engine to generate emotion data. The emotion engine uses software specialized for emotion analysis (e.g., Microsoft Azure Emotion API).

[1349] Next, the device sends the user input data and generated emotion data to the server using an HTTP POST request, which then uses a data management system such as Apache Kafka to temporarily store the data and pass it to the analysis module.

[1350] The server's analysis module uses machine learning algorithms and natural language processing (NLP) to comprehensively analyze the user's career goals, strengths, areas for improvement, and emotional information. Specifically, the server checks the received data format and completeness of the information, and uses generative AI models such as GPT-4 to generate optimal advice for the user.

[1351] The generated advice is sent back to the device from the server. The device provides this advice to the user in real time, for example, on the display of smart glasses. The display format can be customized to make it easy for the user to understand, and a dashboard or report format can be selected.

[1352] As a specific example, let's say a worker inspecting products in a factory feels "fatigue." In this case, the smart glasses will detect fatigue through facial expression analysis and send the data to the server as emotional data. Based on the analysis results, the server will use a generative AI model to generate advice such as "We recommend you take a five-minute break," and display it on the smart glasses' display.

[1353] Examples of prompts to input to a generative AI model might include:

[1354] "When fatigue is detected from a worker's facial expression, how can we suggest a break? Generate specific advice and encouraging messages."

[1355] In this way, a system is realized that combines emotional data and career-oriented data to provide users with optimized advice in real time.

[1356] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[1357] Program processing flow

[1358] Step 1:

[1359] The user uses the smart glasses to input data such as their career aspirations, experience, and skills. The input data includes text-based career goals, work history, and skill sets. While inputting, the smart glasses use a camera and microphone to capture the user's facial expressions and voice in real time.

[1360] Input: Text data of user's career aspirations, experience, and skills, video data of facial expressions, and audio data

[1361] Output: User data temporarily stored in the smart glasses, as well as captured facial expression and voice data.

[1362] How it works: Users input their career aspirations and experience into the smart glasses, while the smart glasses' camera and microphone capture the user's facial expressions and voice in real time.

[1363] Step 2:

[1364] The device passes input data to an emotion engine that analyzes facial expressions and voice data. The emotion engine generates emotion data and uses services such as the Microsoft Azure Emotion API to identify emotions such as joy, anger, fear, and sadness.

[1365] Input: Captured facial expression video data, audio data

[1366] Output: Emotion data (e.g., 80% happiness, 10% anger, 10% sadness)

[1367] What it does: The emotion engine analyzes facial expressions and voice data to quantify the user's emotional state.

[1368] Step 3:

[1369] The device sends the user data and the generated emotion data to the server via an HTTP POST request.

[1370] Input: User data (career aspirations, experience, skills), emotional data

[1371] Output: Data sent to the server

[1372] Specific operation: The device temporarily stores user data and emotion data and sends them to the server.

[1373] Step 4:

[1374] The server checks the format and integrity of the received data and passes it to the analysis module. The data is temporarily stored using a data management system such as Apache Kafka.

[1375] Input: User data, emotion data

[1376] Output: Data passed to the analysis module

[1377] Specific operation: The server checks the data format, requests retransmission if there is incomplete data, and passes the complete data to the analysis module.

[1378] Step 5:

[1379] The analysis module uses machine learning algorithms and natural language processing (NLP) technology to comprehensively analyze the user's career goals, strengths, areas for improvement, and emotional information.

[1380] Input: Data passed to be analyzed (user data, emotion data)

[1381] Output: Analysis results (user's career goals, strengths, areas for improvement, emotional information)

[1382] What it does: The analysis module uses machine learning algorithms and NLP techniques to analyze user data and sentiment data.

[1383] Step 6:

[1384] Based on the analysis results, the server uses a generative AI model (e.g., GPT-4) to generate optimal advice for the user, with the tone and content adapted according to the user's emotional state.

[1385] Input: Analysis results (user's career goals, strengths, areas for improvement, emotional information)

[1386] Output: The generated advice

[1387] Specific operation: The server inputs prompts into the generative AI model and generates advice according to the user's emotional state. An example of a prompt is, "When fatigue is detected from a worker's facial expression, how should you suggest a break? Please generate specific advice and encouraging messages."

[1388] Step 7:

[1389] The server sends the generated advice back to the device, which then provides it to the user in real time.The advice is displayed on the smart glasses display.

[1390] Input: Generated advice

[1391] Output: Advice displayed to the user

[1392] Specific operation: The device displays the advice received from the server to the user in real time, supporting the user's actions.

[1393] 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.

[1394] 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.

[1395] 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.

[1396] 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.

[1397] FIG. 9 illustrates 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 behaviors 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.

[1398] 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.

[1399] 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).

[1400] 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.

[1401] 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."

[1402] 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.

[1403] 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).

[1404] 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.

[1405] 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.

[1406] 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.

[1407] 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.

[1408] 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.

[1409] 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.

[1410] 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.

[1411] 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.

[1412] 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.

[1413] 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.

[1414] The following is further disclosed regarding the above embodiment.

[1415] (Claim 1)

[1416] To analyze an individual's career aspirations,

[1417] A means to input data such as individual career aspirations, experience, and skills from a terminal,

[1418] means for transmitting the input data to a server;

[1419] means for analyzing the data received by the server;

[1420] A means to generate optimal advice using AI based on the analysis results, and

[1421] a means for returning the generated advice to the terminal;

[1422] a means for the terminal to display the returned advice;

[1423] A system including:

[1424] (Claim 2)

[1425] 2. The system of claim 1, wherein the server uses machine learning algorithms and natural language processing when analyzing the data.

[1426] (Claim 3)

[1427] 2. The system according to claim 1, wherein the data entered by the user is stored in a database and the data is used as the basis for analysis.

[1428] "Example 1"

[1429] (Claim 1)

[1430] To analyze an individual's career aspirations,

[1431] A means to input data such as individual career aspirations, experience, and skills from a terminal,

[1432] means for transmitting the input data to a server;

[1433] means for analyzing the data received by the server;

[1434] A means to generate optimal advice using AI based on the analysis results, and

[1435] a means for returning the generated advice to the terminal;

[1436] A means for the device to display the returned advice in a dashboard or report format;

[1437] A system including:

[1438] (Claim 2)

[1439] 2. The system according to claim 1, wherein the server uses machine learning algorithms and natural language processing techniques when analyzing the data.

[1440] (Claim 3)

[1441] 2. The system according to claim 1, wherein the data entered by the user is stored in a database and the data is used as the basis for analysis.

[1442] "Application Example 1"

[1443] (Claim 1)

[1444] To analyze an individual's career aspirations,

[1445] A means to input data such as individual career aspirations, experience, and skills from a terminal,

[1446] means for transmitting the input data to a server;

[1447] means for analyzing the data received by the server;

[1448] A means to generate optimal advice using AI based on the analysis results, and

[1449] a means for returning the generated advice to the terminal;

[1450] a means for the terminal to display the returned advice;

[1451] Based on the data entered by the worker,

[1452] measures to promote improvements in work conditions and skill levels;

[1453] receiving user input through an interactive interface on the smart device;

[1454] A means to display real-time advice on improving work efficiency within the factory,

[1455] A system including:

[1456] (Claim 2)

[1457] The system according to claim 1, wherein the server uses machine learning algorithms and natural language processing to generate work efficiency advice in real time when analyzing the data.

[1458] (Claim 3)

[1459] The system according to claim 1, wherein data entered through a smart device is stored in a database, and the data is used as the basis for analysis to provide work efficiency advice specific to each user.

[1460] "Example 2: Combining Emotion Engines"

[1461] (Claim 1)

[1462] To analyze users' career aspirations,

[1463] A means for users to input data such as their career aspirations, experience, and skills from a terminal;

[1464] A means for temporarily storing input data and monitoring the user's facial expressions and voice during input via an emotion engine;

[1465] A means for generating emotion data of a user by an emotion engine;

[1466] A means for the terminal to transmit user data and emotion data to a server;

[1467] A means to check the data format of the data received by the server and whether the necessary information is included.

[1468] A means for passing the data received by the server to an analysis module and analyzing it using machine learning algorithms and natural language processing techniques;

[1469] A means for passing the analysis results to the generation AI, which then generates optimal advice based on the analysis results and emotion data;

[1470] a means for returning the generated advice to the terminal;

[1471] a means for the terminal to display the returned advice;

[1472] A system including:

[1473] (Claim 2)

[1474] 2. The system according to claim 1, wherein the server uses machine learning algorithms and natural language processing techniques when analyzing the data.

[1475] (Claim 3)

[1476] 2. The system according to claim 1, wherein the data entered by the user is stored in a database and the data is used as the basis for analysis.

[1477] "Application example 2 when combining emotion engines"

[1478] (Claim 1)

[1479] In order to analyze each user's career aspirations and propose optimal work methods and communication styles,

[1480] A means for each user to input their career aspirations, experience, skills, etc. from a terminal;

[1481] The device temporarily stores the input data and detects facial expressions and voice via an emotion engine to analyze the user's emotions during input.

[1482] a means for the terminal to generate emotion data and transmit the user data and the emotion data to a server;

[1483] A means for the server to verify the format and integrity of the received data and pass it on to an analysis module;

[1484] The analysis module analyzes the data to identify the user's career goals, strengths, areas for improvement, and emotional information;

[1485] A means to generate optimal advice using AI based on the analysis results, and

[1486] A means for returning the generated advice from the server to the terminal;

[1487] means for the device to display the returned advice in real time and present it to the user in an easily understandable format;

[1488] A system including:

[1489] (Claim 2)

[1490] 2. The system according to claim 1, wherein the server uses machine learning algorithms and natural language processing techniques when analyzing the data.

[1491] (Claim 3)

[1492] 2. The system according to claim 1, wherein the data and emotion data input by the user are stored in a database and the data is used as the basis for analysis. [Explanation of symbols]

[1493] 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. To analyze an individual's career aspirations, A means to input data such as individual career aspirations, experience, and skills from a terminal, means for transmitting the input data to a server; means for analyzing the data received by the server; A means to generate optimal advice using AI based on the analysis results, and a means for returning the generated advice to the terminal; a means for the terminal to display the returned advice; A system including:

2. The system according to claim 1 , wherein the server uses machine learning algorithms and natural language processing when analyzing the data.

3. 2. The system according to claim 1, wherein the data input by the user is stored in a database and the data is used as the basis for analysis.

Images