System

Abstract

To provide an efficient and effective system for collecting and analyzing various data of employees, and generating and presenting individually optimized career paths.SOLUTION: The system includes a data acquiring means, a means for acquiring the profile information, the past project history, the evaluation data, and the skill set of the employee, an interface means for inputting the career desire and the target of the employee, a means for learning the generated AI model based on the acquired data, a means for generating the advice for the optimum career path and skill development for each employee by using the generated AI, a means for presenting the generated career path and advice to the employee, a means for inputting the feedback to the presented career path and advice by the employee, and a means for analyzing the collected feedback and re-learning the generated AI model.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] Companies today place great importance on employee career development. However, optimally designing and supporting each employee's individual career path requires the collection and analysis of a wide variety of data, which is an extremely tedious process. Furthermore, conventional methods often fail to adequately address the needs of individual employees and end up providing a uniform career path. This can result in a decline in employee motivation and performance. Therefore, there is a need for an efficient and effective system that can collect and analyze a wide variety of employee data and generate and present individually optimized career paths. [Means for solving the problem]

[0005] The present invention solves the above-mentioned problems by providing a system that includes: means for acquiring employee profile information, past project history, evaluation data, and skill sets; an interface for inputting employee career aspirations and goals; means for training a generative AI model based on the acquired data; means for generating optimal career paths and skill development advice for each employee using the trained generative AI; means for presenting the generated career paths and advice to employees; means for employees to input feedback on the presented career paths and advice; and means for analyzing the collected feedback and re-training the generative AI model. This makes it possible to efficiently generate and present optimal career paths for each employee. Furthermore, by incorporating feedback and improving the accuracy of the AI ​​model, it is possible to achieve continuously optimized career development support.

[0006] The "data acquisition means" is a device or program that has the function of collecting employee profile information, past project history, evaluation data, skill sets, etc. from a database.

[0007] A "generative AI model" is a model that uses machine learning and artificial intelligence technology to generate career development patterns and skill development advice for employees based on collected data.

[0008] "Interface means" refers to the device or software features that employees use to enter their career aspirations and goals and view the generated career paths and advice.

[0009] A "career path" is a specific route or plan that shows the optimal career progression plan based on an employee's skills and aspirations.

[0010] "Feedback tools" are functions that allow employees to provide their thoughts and evaluations on the career paths and advice presented to them, and are tools for collecting and analyzing that feedback.

[0011] "Retraining means" is a function that retrains the generative AI model based on collected feedback to improve its accuracy and applicability. [Brief explanation of the drawings]

[0012] [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

[0013] 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.

[0014] First, the terms used in the following description will be explained.

[0015] 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).

[0016] 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.

[0017] 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.

[0018] 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.

[0019] 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."

[0020] [First embodiment]

[0021] FIG. 1 shows an example of the configuration of a data processing system 10 according to the first embodiment.

[0022] 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.

[0023] 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).

[0024] 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.

[0025] 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.

[0026] 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.

[0027] 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.

[0028] FIG. 2 shows an example of the main functions of the data processing device 12 and the smart device 14.

[0029] 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.

[0030] 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.

[0031] 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.

[0032] 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."

[0033] This invention is a system for supporting employee career development, which links generative AI with employee-related data to efficiently and effectively propose career paths. Specifically, the server, terminals, and users work together to provide career development support optimized for each employee.

[0034] System configuration and operation

[0035] The server retrieves employee profile information, past project history, evaluation data, and skill sets from the database, thereby collecting data on the employee's current and past performance.

[0036] The terminal provides an interface for employees to input their career aspirations and goals. Users (employees) can use the terminal to input their intentions and goals into the system.

[0037] The server trains a generative AI model based on the collected data. This training process involves cleansing the data and pre-processing it to convert it into a format suitable for the AI ​​model, enabling it to generate highly accurate career paths.

[0038] Using trained generation AI, the server generates advice for optimal career paths and skill development for each employee. For example, it may suggest that "Employee A should take training to improve his project management skills over the next three months. It is also recommended that he try for a new project manager position in the future."

[0039] The terminal provides an interface that presents the generated career path and advice to the employee, allowing the user (employee) to confirm a specific career development plan.

[0040] Users (employees) can enter their feedback on the career paths and advice presented to them through their terminals. An example of the feedback they can enter is, "Project management training is appropriate, but I would like to gain more experience before taking on the new project manager position."

[0041] The server analyzes the collected feedback and performs re-training to further improve the accuracy of the generative AI model, thereby providing continuously optimized career paths.

[0042] Specific examples

[0043] Characters:

[0044] User: Employee A

[0045] server

[0046] Terminal

[0047] 1. Data Acquisition:

[0048] The server retrieves employee A's profile information (age, job title, years of service), past project history (project name, role, results), evaluation data (supervisor evaluation, feedback from colleagues), and skill set (programming languages, management skills) from the database.

[0049] 2. Enter your career aspirations and goals:

[0050] The terminal provides an interface for employee A to input his / her career aspirations and goals. The user (employee A) inputs "I want to improve my project management skills."

[0051] 3. Career path generation and presentation:

[0052] The server uses generative AI to generate a career path that reads, "Take training to improve your project management skills over the next three months and try for a new project manager position."

[0053] The terminal presents this career path to employee A.

[0054] 4. Gather and incorporate feedback:

[0055] The user (Employee A) enters feedback such as, "The training is suitable, but I would like to gain more experience before trying for a managerial position."

[0056] The server analyzes this feedback and performs re-training to improve the accuracy of the generative AI model.

[0057] This will create a system that provides employee A with the optimal career path and effectively supports individual career development.

[0058] The processing flow will be explained below.

[0059] Step 1:

[0060] The server retrieves employee profile information, past project history, evaluation data, and skill sets from the company's database.

[0061] Step 2:

[0062] The terminal provides an interface for employees to input their career aspirations and goals. Users (employees) use the terminal to input their career aspirations and goals.

[0063] Step 3:

[0064] The server cleanses the acquired data and performs preprocessing to fill in any invalid data or missing values, thereby preparing the data in a format suitable for training the AI ​​model.

[0065] Step 4:

[0066] The server uses the preprocessed data to create a training dataset and trains the generative AI model. Training is the process of extracting career development trends and patterns based on employee profile data.

[0067] Step 5:

[0068] The server uses the trained generative AI model to generate advice for optimal career paths and skill development for each employee. For example, it may generate a suggestion such as, "Employee A is recommended to take training to improve his project management skills over the next three months."

[0069] Step 6:

[0070] The terminal provides an interface for presenting the generated career path and advice to the employee, who then confirms the presented career path and advice.

[0071] Step 7:

[0072] Users (employees) can input their feedback on career paths and advice through terminals. For example, they can input feedback such as, "The training is good, but the project manager position is too early."

[0073] Step 8:

[0074] The server stores the collected feedback in a database and performs analysis to evaluate the performance of the generative AI model and identify areas for improvement.

[0075] Step 9:

[0076] The server retrains the generative AI model based on the feedback, further improving the accuracy of career paths and advice.

[0077] Step 10:

[0078] The terminal again presents the improved career path and advice to the employee, who can then review the new suggestions and provide feedback again.

[0079] By repeating the above steps, career development support optimized for each employee can be continuously provided.

[0080] Example 1

[0081] 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."

[0082] Employee career development is an important issue for companies, but it is extremely difficult to create an optimized career path for each employee and provide support tailored to their individual skills and goals. Furthermore, there is a lack of systems that efficiently incorporate feedback from employees and continuously optimize their career paths. The present invention aims to solve these problems and provide an efficient and effective system for promoting employee career development.

[0083] 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.

[0084] In this invention, the server includes a data acquisition means, a means for acquiring employee profile information, past project history, evaluation data, and skill sets, an interface means for inputting employee career aspirations and goals, a means for training a generative AI model based on the acquired data, a means for generating optimal career paths and advice for skill development for each employee using the trained generative AI, a means for presenting the generated career paths and advice to employees, a means for employees to input feedback on the presented career paths and advice, and a means for analyzing the collected feedback and re-training the generative AI model. This makes it possible to provide career paths optimized for each employee and continuously improve accuracy.

[0085] The "data acquisition means" is a means by which the server acquires data such as employee profile information, past project history, evaluation data, and skill sets from the database.

[0086] "Interface means" refers to input fields, forms, or other means on a terminal through which employees input their career aspirations and goals.

[0087] A "generative AI model" is an artificial intelligence model that predicts and generates optimal career paths for each employee based on large-scale data sets.

[0088] A "career path generation method" is a method that uses a trained generative AI model to generate optimal career paths and advice for skill development for each employee.

[0089] The "presentation means" refers to a means for presenting the generated career path and advice to employees, specifically, a screen display function of a terminal.

[0090] The "feedback input means" is a means for employees to input their opinions and requests regarding the career paths and advice presented to them.

[0091] The "relearning means" is a means for analyzing collected feedback and conducting re-learning to improve the accuracy of the generative AI model.

[0092] This invention is a system for supporting employee career development, which proposes career paths efficiently and effectively by linking generative AI with employee-related data. Specifically, the system realizes career development support optimized for each employee by having the server, terminals, and users function in cooperation with each other.

[0093] System configuration and operation

[0094] The server has functions such as a data acquisition means, a means for learning and relearning the generated AI model, a means for generating a career path, and a means for presenting the career path.

[0095] Data Acquisition Method

[0096] The server has a means to retrieve information from the database, such as employee profile information (age, job title, years of service), past project history (project name, role, results), evaluation data (supervisor evaluation, feedback from colleagues), skill set (programming language, management ability), etc. For example, the server uses SQL queries to retrieve the required information from the database.

[0097] Generative AI models and learning methods

[0098] The server trains a generative AI model based on the collected data. In this training process, data cleansing (e.g., removing duplicate data and filling in missing data) and preprocessing (standardizing and normalizing data) are performed, and then the data is input into an AI model (e.g., BERT or GPT-3 (registered trademark)) for training.

[0099] Career path generation method

[0100] Using trained generation AI, the server generates optimal career paths and advice for skill development for each employee. For example, for Employee A, a specific career path would be generated such as, "It is recommended that you take training to improve your project management skills over the next three months. It is recommended that you try for a new project manager position in the future."

[0101] Presentation means

[0102] The career paths and advice generated by the server are presented to employees via their terminals. The terminals receive the information from the server and display it on their screens, allowing employees to check specific career development plans.

[0103] Feedback input and re-learning methods

[0104] Employees (users) enter feedback on the presented career paths and advice through their terminals. For example, they may say, "The training is appropriate, but I would like to gain more experience before taking on a managerial position." The server analyzes this feedback and performs re-training to improve the accuracy of the generative AI model. This re-training gives the system the ability to continuously provide optimized career paths.

[0105] Specific examples

[0106] Characters:

[0107] User: Employee A

[0108] server

[0109] Terminal

[0110] 1. Data Acquisition

[0111] The server retrieves data such as employee A's profile information, past project history, evaluation data, and skill set from the database.

[0112] 2. Enter your career aspirations and goals

[0113] The terminal provides an interface for Employee A to input his / her career aspirations and goals. Employee A inputs, "I want to improve my project management skills."

[0114] 3. Creating and presenting career paths

[0115] The server uses generative AI to generate career paths such as "Take training to improve your project management skills over the next three months and try for a new project manager position."

[0116] The terminal presents this career path to employee A.

[0117] 4. Gather and incorporate feedback

[0118] The user (Employee A) enters feedback into the terminal, saying, "The training is appropriate, but I would like to gain more experience before trying for a managerial position."

[0119] The server analyzes this feedback and performs re-training to improve the accuracy of the generative AI model.

[0120] Prompt Sentence Examples

[0121] "Generate a suitable career path for Employee A based on their profile information and project history."

[0122] The flow of the identification process in the first embodiment will be described with reference to FIG.

[0123] Step 1:

[0124] Data Acquisition

[0125] The server retrieves data from the database, such as employee profile information, past project history, evaluation data, and skill sets.

[0126] Input: Employee ID and database credentials

[0127] Data processing: The process of issuing an SQL query to retrieve the relevant employee data.

[0128] Output: A dataset containing information about each employee

[0129] Specific behavior: Executes an SQL query such as SELECT FROM employee_data WHERE employee_id = 'A123'.

[0130] Step 2:

[0131] Enter your career aspirations and goals

[0132] The terminal provides an interface for employees to input their career aspirations and goals.

[0133] Input: Employee's career aspirations and goals (e.g., "I want to improve my project management skills")

[0134] Data processing: Convert the input hopes and goals into a specific format and send it to the server

[0135] Output: Preferences and goals sent to the server

[0136] Specific operation: The employee enters their request into the input field on the terminal and presses the send button.

[0137] Step 3:

[0138] Training generative AI models

[0139] The server trains a generative AI model based on the collected data.

[0140] Inputs: Employee profile information, past project history, evaluation data, skill sets

[0141] Data processing: Perform preprocessing such as data cleansing (removal of duplicate data, filling in missing data), standardization and normalization of data

[0142] Output: A trained generative AI model

[0143] What it does: Cleanses data and converts it into a format suitable for AI models to run the learning process.

[0144] Step 4:

[0145] Career path creation

[0146] The server uses trained generative AI to generate the optimal career path for each employee.

[0147] Input: trained generative AI model, employee data

[0148] Data Computing: Generative AI models generate career paths using employee data as input

[0149] Output: Generated career path and advice (e.g., "It is recommended that you take training to improve your project management skills in the next three months")

[0150] How it works: Employee data is fed into a generative AI model to generate career paths.

[0151] Step 5:

[0152] Providing career paths

[0153] The terminal then presents the generated career path and advice to the employee.

[0154] Input: Career path data sent from the server

[0155] Data processing: Converts career path data into a display format and displays it on the terminal screen

[0156] Output: Screen display to employees (e.g., specific career development plans are displayed)

[0157] Specific operation: Display career path on the device screen.

[0158] Step 6:

[0159] Collecting feedback

[0160] The user inputs feedback on the presented career path and advice via the terminal.

[0161] Input: Employee feedback (e.g., "The training was appropriate, but I would like to gain more experience before taking on a managerial position.")

[0162] Data processing: The feedback content is converted into a specific format and sent to the server.

[0163] Output: Feedback data sent to the server

[0164] Specific actions: Enter feedback into the input field on the device and press the send button.

[0165] Step 7:

[0166] Reflecting feedback

[0167] The server analyzes the collected feedback and retrains the generative AI model.

[0168] Input: Employee feedback data

[0169] Data computation: Analyze the feedback data and provide it as new data points to the generative AI model for retraining.

[0170] Output: An updated generative AI model

[0171] Specific operation: A re-learning process is performed based on feedback data to improve the accuracy of the generative AI model.

[0172] (Application example 1)

[0173] 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."

[0174] Existing career development support systems suggest career paths based on employee profile information and evaluation data, but this alone makes it difficult to provide specific advice optimized for each employee. Furthermore, the means by which employees can provide feedback are limited, making continuous optimization difficult and preventing effective linkage to actual work and skill development in the workplace. Furthermore, the lack of an interface that can be used immediately in the workplace tends to reduce employees' motivation and involvement in their career development.

[0175] 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.

[0176] In this invention, the server includes means for acquiring employee profile information, past project history, evaluation data, and skill sets, interface means for inputting employee career aspirations and goals, and means for training a generative AI model based on the acquired data. This allows the generative AI model to be trained based on the acquired data, and the trained generative AI can be used to generate optimal career paths and advice for skill development for each employee, which can then be presented via a touchscreen or voice recognition system. By analyzing feedback collected using the feedback input means and retraining the generative AI model, this system can provide continuously optimized career paths and efficiently support employees' career development.

[0177] A "data acquisition means" is a device or system for collecting and managing information about employees.

[0178] "Profile information" refers to basic information such as an employee's age, position, and years of service.

[0179] "Past project history" is data that records the names, roles, results, etc. of projects that employees have participated in.

[0180] "Evaluation data" is information that includes the results of evaluations of an employee's work by their superiors and colleagues.

[0181] A "skill set" refers to the list of skills and abilities that an employee possesses.

[0182] An "interface means" is a device or system through which employees input their career aspirations and goals.

[0183] A "generative AI model" is a model that uses artificial intelligence technology to generate advice for optimal career paths and skill development based on employee data.

[0184] A "career path" is a path that shows employees the steps they should aim for and the goals they should achieve.

[0185] A "touch screen" is a type of display device that can be operated by directly touching the screen.

[0186] A "speech recognition system" is a device or system that analyzes and converts spoken input into text or commands.

[0187] "Feedback" refers to the opinions and suggestions that employees provide regarding the career path or advice presented to them.

[0188] "Retraining" is the process of incorporating new data, such as collected feedback, into a generative AI model.

[0189] System configuration and operation

[0190] This invention is a system for supporting employee career development through factory robots. Specifically, a server, factory robots, and employees (users) work together to provide optimized career development support.

[0191] Hardware Configuration

[0192] Server: Manages databases and trains generative AI models.

[0193] Factory robots: Equipped with touchscreens and voice recognition systems, they act as an interface with employees. Examples include FANUC robotic arms and devices with touchscreens.

[0194] Employees (users): Use the system to enter their career aspirations and goals.

[0195] Software Configuration

[0196] Generative AI model: An AI model built using TENSORFLOW (registered trademark) and Keras. It learns from employee data and generates advice on optimal career paths and skill development.

[0197] Database management system: MySQL (registered trademark) is used to manage employee profile information, past project history, evaluation data, and skill sets.

[0198] Speech Recognition System: Uses Google® Cloud Speech-to-Text to convert employee voice input into text.

[0199] Programming language: Python is used for data processing and implementing AI models.

[0200] Explanation of program processing

[0201] The server retrieves employee profile information, past project history, evaluation data, and skill sets from the database, thereby gathering data on the employee's current and past performance.

[0202] The factory robots provide an interface for employees to input their career aspirations and goals, which are then sent to a server via a touchscreen or voice recognition system.

[0203] The server trains a generative AI model based on the collected data, cleansing the data and performing preprocessing to convert it into a format suitable for the AI ​​model, thereby enabling the generation of highly accurate career paths.

[0204] Using trained generation AI, the server generates advice for optimal career paths and skill development for each employee. For example, it might suggest, "Employee A is recommended to take training to improve his project management skills over the next three months. It would also be advisable for him to try for a new project manager position in the future."

[0205] The factory robot will then present the generated career paths and advice to employees, who can then view specific career development plans via a touchscreen or voice assistant.

[0206] Employees can use the factory robot to provide feedback on the career paths and advice presented to them, such as, "Project management training is appropriate, but I would like to gain more experience before taking on the new project manager position."

[0207] The server analyzes the collected feedback and retrains the generative AI model, allowing it to provide continuously optimized career paths.

[0208] Specific examples

[0209] Characters:

[0210] Employee A

[0211] server

[0212] Factory Robots

[0213] 1. Data Acquisition:

[0214] The server retrieves employee A's profile information (age, job title, years of service), past project history (project name, role, results), evaluation data (supervisor evaluation, feedback from colleagues), and skill set (programming languages, management skills) from the database.

[0215] 2. Enter your career aspirations and goals:

[0216] The factory robot provides an interface for Employee A to input his / her career aspirations and goals. Employee A inputs, "I want to improve my project management skills."

[0217] 3. Career path generation and presentation:

[0218] The server uses generative AI to generate a career path that reads, "Take training to improve your project management skills over the next three months and try for a new project manager position."

[0219] The factory robot presents this career path to employee A.

[0220] 4. Gather and incorporate feedback:

[0221] Employee A provides feedback saying, "The training is suitable, but I would like to gain more experience before taking on a managerial position."

[0222] The server analyzes this feedback and performs re-training to improve the accuracy of the generative AI model.

[0223] Example prompt sentence:

[0224] INSERT INTO employee_data (name, age, role, skills, past_projects, evaluations) VALUES ('Employee A', 34, 'Line Manager', 'Production Management, Quality Control', 'Project X, Project Y', 'Supervisor rating: 4.5, Peer rating: 4.0')

[0225] This system makes it possible to provide employee A with the optimal career path and effectively support his or her individual career development.

[0226] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[0227] Step 1:

[0228] The server retrieves employee profile information, past project history, evaluation data, and skill sets from the database. Based on this input data, an initial dataset regarding the employee's current status and past performance is created. Specifically, MySQL is used to retrieve the necessary information from the database using SQL queries, and the information is converted into a data frame using Python's pandas library.

[0229] Step 2:

[0230] The terminal (factory robot) provides an interface for employees to input their career aspirations and goals. Specifically, it accepts input from employees (e.g., "I want to improve my project management skills") using a touchscreen or voice recognition system. This input data is sent to the server via an HTTP request.

[0231] Step 3:

[0232] The server receives employee input data and integrates it with previously collected profile information and evaluation data. It trains a generative AI model based on this integrated dataset. It cleans the data and performs preprocessing to convert it into a format suitable for the AI ​​model. It trains the AI ​​model using TensorFlow or Keras.

[0233] Step 4:

[0234] Using trained generative AI, the server generates optimal career paths and advice for skill development for each employee. Specifically, the server inputs the employee's integrated data into the AI ​​model to generate career path candidates. The generated career path is output as a specific action plan (e.g., "We recommend that you take training to improve your project management skills in the next three months").

[0235] Step 5:

[0236] The terminal (factory robot) presents the generated career path and advice to the employee. Specifically, it displays the generated career path and advice visually or audibly via a touch screen or voice assistant, and the employee confirms the results.

[0237] Step 6:

[0238] The user (employee) enters feedback on the presented career path and advice through a terminal (factory robot). Specifically, the user enters feedback (e.g., "The training is suitable, but I would like to gain more experience before attempting a managerial position") using a touch screen or voice recognition system. This feedback data is then sent back to the server via an HTTP request.

[0239] Step 7:

[0240] The server analyzes the collected feedback and retrains the generative AI model. Specifically, the feedback data is added to the dataset, the data is cleansed, and the AI ​​model is retrained. The generative AI model, with improved accuracy through retraining, is used to generate the next career path, making it possible to provide continuously optimized career paths.

[0241] 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.

[0242] This invention is a system for supporting employee career development, which links generative AI with employee-related data and combines it with an emotion engine that recognizes user emotions to efficiently and effectively propose career paths. Specifically, by having the server, terminals, and users cooperate with each other, it realizes career development support that is optimized for each employee.

[0243] System configuration and operation

[0244] The server retrieves employee profile information, past project history, evaluation data, and skill sets from the company's database, thereby gathering data on the employee's current and past performance.

[0245] The terminal provides an interface for employees to input their career aspirations and goals, and collects this information input by the user (employee).

[0246] The server cleanses the collected data and performs preprocessing to fill in any invalid or missing values, preparing the data in a format suitable for training AI models.

[0247] The server uses the preprocessed data to create a training dataset and trains the generative AI model, which extracts career development trends and patterns based on employee profile data.

[0248] Using the trained generative AI, the server generates advice for optimal career paths and skill development for each employee. For example, a recommendation might be generated such as, "Employee A should take training to improve his project management skills over the next three months."

[0249] The terminal presents the generated career path and advice to the employee, and the user (employee) confirms the presented information.

[0250] Users (employees) can input their feedback on career paths and advice via a terminal. For example, they can input feedback such as, "The training is good, but it's too early for you to take a management position."

[0251] The server analyzes the collected feedback and performs re-training to improve the accuracy of the generative AI model, which further improves the accuracy of career paths and advice.

[0252] Introducing the Emotion Engine

[0253] Furthermore, the present invention incorporates an emotion engine that recognizes the user's emotions. The emotion engine operates as follows:

[0254] The server collects facial expression and voice data via the terminal when employees enter their career aspirations and goals, and when they confirm their career path and advice.

[0255] The emotion engine analyzes this data to recognize the user's emotional state, for example, determining whether an employee is stressed or happy.

[0256] The server adjusts the content and tone of career paths and advice based on the emotional state derived from the emotion engine, potentially offering more relaxed goals to stressed employees and more challenging goals to satisfied employees.

[0257] Users (employees) will feel more satisfied with their career path by receiving advice that is more in line with their own emotions.

[0258] Specific examples

[0259] Characters:

[0260] User: Employee A

[0261] server

[0262] Terminal

[0263] 1. Data Acquisition:

[0264] The server retrieves employee A's profile information (age, job title, years of service), past project history (project name, role, results), evaluation data (supervisor evaluation, feedback from colleagues), and skill set (programming languages, management skills) from the database.

[0265] 2. Enter your career aspirations and goals:

[0266] The terminal provides an interface for employee A to input their career aspirations and goals. The user (employee A) inputs, "I want to improve my project management skills." The emotion engine reads the emotions of employee A from their facial expressions at this time.

[0267] 3. Career path generation and presentation:

[0268] The server uses generative AI to generate a career path such as "Take training to improve your project management skills in the next three months and try for a new project manager position." It adjusts the advice to an appropriate tone, taking into account Employee A's emotional state.

[0269] The terminal presents this career path to employee A.

[0270] 4. Gather and incorporate feedback:

[0271] The user (Employee A) enters feedback such as, "The training is suitable, but I would like to gain more experience before taking on the managerial position." The user's feelings at this time are also recorded.

[0272] The server analyzes the feedback and emotional data and retrains the generative AI model.

[0273] This will create a system that provides the optimal career path for employee A and effectively supports individual career development. The introduction of an emotion engine will enable advanced career support that takes into account the emotions of employees.

[0274] The processing flow will be explained below.

[0275] Step 1:

[0276] The server retrieves employee profile information, past project history, evaluation data, and skill sets from the company's database.

[0277] Step 2:

[0278] The terminal provides an interface for employees to input their career aspirations and goals. Users (employees) use the terminal to input their career aspirations and goals.

[0279] Step 3:

[0280] The server cleanses the collected data and performs preprocessing to fill in any invalid or missing values, preparing the data in a format suitable for training AI models.

[0281] Step 4:

[0282] The server uses the preprocessed data to create a training dataset and trains the generative AI model. Training is the process of extracting career development trends and patterns based on employee profile data.

[0283] Step 5:

[0284] When an employee inputs their career aspirations and goals, the server acquires facial expression and voice data and analyzes them using an emotion engine, thereby recognizing the user's emotional state.

[0285] Step 6:

[0286] The server uses a trained generative AI model to generate optimal career paths and advice for skill development for each employee. The generated career paths and advice are adjusted taking into account the user's emotional state. For example, a recommendation might be generated such as, "Employee A is recommended to take training to improve his project management skills over the next three months."

[0287] Step 7:

[0288] The terminal provides an interface for presenting the generated career path and advice to the employee, who then confirms the presented career path and advice.

[0289] Step 8:

[0290] Users (employees) can input their feedback on career paths and advice through a terminal. For example, they can input feedback such as, "The training was good, but it's too early for you to move into a management position." Their emotional state at this time is also recorded.

[0291] Step 9:

[0292] The server analyzes the collected feedback and emotional data and performs retraining to improve the accuracy of the generative AI model, which further improves the accuracy of career paths and advice.

[0293] Step 10:

[0294] The terminal again presents the improved career path and advice to the employee, who can then review the new suggestions and provide feedback again.

[0295] By repeating the above steps, the emotional engine can be utilized to provide ongoing career development support that is optimized for each employee.

[0296] Example 2

[0297] 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."

[0298] Conventional career development support systems mainly make suggestions based on quantitative employee data, making it difficult to reflect employees' emotions and motivation. Furthermore, the generated career paths and advice are often unrealistic, limiting their ability to provide optimal support to individual employees. This can result in insufficient contribution to employee satisfaction and career advancement.

[0299] The specific processing by the specific processing unit 290 of the data processing device 12 in the second embodiment is realized by the following means.

[0300] In this invention, the server includes means for acquiring employee profile information, past project history, evaluation data, and skill sets, an interface means for inputting employee career aspirations and goals, means for acquiring user facial expression and voice data, means for cleansing the acquired data and complementing invalid data and missing values, means for training a generative AI model based on the cleansed data, means for inputting prompt sentences to the generative AI model and generating advice for career paths and skill development, means for adjusting and presenting the content of the career paths and advice generated by the generative AI model, means for employees to input feedback on the career paths and advice, and means for analyzing the collected feedback and emotion data and re-training the generative AI model. This makes it possible to provide career paths and advice optimized for each employee, reflecting the emotions and career aspirations of the employees.

[0301] "Data acquisition means" refers to means for collecting employee profile information, past project history, evaluation data, and skill sets from the company's database.

[0302] "Employee profile information" refers to basic personal information such as an employee's age, position, and years of service.

[0303] "Past project history" is data including the names, roles, and results of projects in which an employee has participated.

[0304] "Evaluation data" refers to data used to evaluate an employee's performance, including feedback from superiors and colleagues.

[0305] A "skill set" is data that specifically indicates the skills, qualifications, and special talents possessed by an employee.

[0306] "Interface means" refers to a user interface that allows employees to input their career aspirations and goals.

[0307] "Means for acquiring facial expressions and voice data" refers to means for acquiring facial expressions and voice data using a camera or microphone while an employee is using the interface.

[0308] "Data cleansing methods" are methods for organizing collected data, eliminating invalid data, and filling in missing values.

[0309] A "means for training a generative AI model" is a means for training an AI algorithm using cleansed data to train a model.

[0310] "Means for inputting prompt sentences and generating advice" refers to means for providing specific input sentences to a generative AI model and generating advice for career paths and skill development based on those sentences.

[0311] "Means for adjusting and presenting advice content" refers to a means for adjusting the advice generated by the generative AI model based on the employee's emotional data and presenting it to the employee.

[0312] "Means for inputting feedback" refers to a user interface that allows employees to input feedback on career paths and advice.

[0313] "Means for analyzing feedback and emotional data and retraining the generative AI model" refers to means for analyzing collected feedback and emotional data and retraining the generative AI model based on that data.

[0314] System program processing

[0315] This invention is a system for supporting employees' career development. The system mainly involves the cooperation of a server, terminals, and users to realize career development support optimized for each employee.

[0316] Data Acquisition

[0317] The server retrieves employee profile information, past project history, evaluation data, and skill sets from the company database using a database query such as SQL. For example, the server executes a query like this: SELECT FROM EmployeeProfile WHERE EmployeeID = 'A123';

[0318] Enter your career aspirations and goals

[0319] The device provides an interface for users (employees) to input their career aspirations and goals. This interface can be implemented as a web form or a mobile app, and displays text boxes and options for entering the required information.

[0320] The device also captures facial and voice data as users enter their career aspirations and goals using a camera and microphone. For example, the device captures facial and voice data in real time while a user types, "I want to improve my project management skills."

[0321] Data Preprocessing

[0322] The server cleanses the collected employee data and fills in any invalid data or missing values. For this, you can use the Python pandas library. For example, the server fills in missing values ​​as follows: df.fillna(method='ffill')

[0323] Training generative AI models

[0324] The server uses the preprocessed data to create a training dataset and train a generative AI model using a generative AI framework (e.g., GPT-3 or GPT-4 (registered trademark)). The server can run the command: openai.TrainModel(data='training_data.csv')

[0325] Career path creation

[0326] The server uses trained generative AI to generate optimal career paths and advice on skill development for each employee. A specific prompt is input to the generative AI model. For example, this prompt might be something like, "What career path would you suggest for employee A?"

[0327] The generated career path is adjusted taking into account the emotional state captured by the emotion engine. For example, the server may adjust the career path based on the output of the generative AI model, such as "Employee A is feeling stressed, so the training should be short-term."

[0328] Providing career paths

[0329] The device presents the generated career path and skill development advice to the employee, which is displayed as a user interface and includes information such as specific goals and training plans.

[0330] Collecting feedback

[0331] Users (employees) can input their feedback on career paths and advice through a terminal. Text boxes and options are provided for this input. Facial expressions and voices are also recorded when inputting feedback.

[0332] Re-learning and accuracy improvement

[0333] The server analyzes the collected feedback and emotion data and retrains the generative AI model. This involves adding new data and training the AI ​​model again. For example, the server adds new feedback data and retrains it as follows: openai.TrainModel(data='updated_feedback_data.csv')

[0334] This makes it possible to reflect employees' career aspirations and feelings and provide career paths and advice that are optimized for each individual employee.

[0335] The flow of the identification process in the second embodiment will be described with reference to FIG.

[0336] System program processing flow

[0337] Step 1:

[0338] Data Acquisition

[0339] The server retrieves employee profile information, past project history, evaluation data, and skill sets from the company database. The server executes SQL queries to gather the required data. For example, the server might use a query like this: SELECT FROM EmployeeProfile WHERE EmployeeID = 'A123';

[0340] Input: Company database

[0341] Output: Employee profile information, project history, evaluation data, skill set

[0342] Step 2:

[0343] Enter your career aspirations and goals

[0344] The terminal provides an interface for users (employees) to input their career aspirations and goals. The terminal displays UI components of web forms or mobile apps to prompt users to enter the required information.

[0345] Specific behavior: Displaying text boxes and drop-down menus.

[0346] Input: User's career aspirations and goals

[0347] Output: User's career preference data

[0348] Step 3:

[0349] Acquiring facial and voice data

[0350] The device captures facial and voice data as the user enters their career aspirations and goals. The device uses a camera and microphone to capture the data.

[0351] Input: User's facial expression, voice

[0352] Output: User's facial expression data, voice data

[0353] Step 4:

[0354] Data Preprocessing

[0355] The server cleanses the collected data and imputes invalid data and missing values. For this, it uses the Python pandas library. For example, the server imputes missing values ​​as follows: df.fillna(method='ffill')

[0356] Input: Employee profile information, project history, evaluation data, skill set, career aspirations, facial expression data, voice data

[0357] Output: A cleansed dataset

[0358] Step 5:

[0359] Training generative AI models

[0360] The server uses the preprocessed data to create a training dataset and trains a generative AI model. The model is trained using a generative AI framework (e.g., GPT-3 or GPT-4). The server executes the command: openai.TrainModel(data='training_data.csv')

[0361] Input: Cleansed dataset

[0362] Output: A trained generative AI model

[0363] Step 6:

[0364] Career path creation

[0365] The server uses trained generative AI to generate optimal career paths and skill development advice for each employee. A specific prompt is given to the generative AI model to generate career path suggestions. For example, the prompt could be, "What career path would you suggest for employee A?"

[0366] Input: trained generative AI model, prompt

[0367] Output: Generated career paths and skill development advice

[0368] Step 7:

[0369] Providing and adjusting advice

[0370] The server adjusts the advice generated by the generative AI model based on the employee's emotional data and presents it to the employee via their device, softening difficult suggestions and emphasizing easy goals.

[0371] Input: Generated career paths, skill advice, sentiment data

[0372] Output: Tailored career paths, skills advice

[0373] Step 8:

[0374] Collecting feedback

[0375] The user (employee) inputs feedback on career paths and advice and sends it to the server via the terminal. The terminal also collects facial expressions and voice data.

[0376] Specific actions: Providing an input form and using the camera and microphone.

[0377] Input: Employee feedback, facial expressions, and voice data

[0378] Output: Feedback data, additional facial and voice data

[0379] Step 9:

[0380] Re-learning and accuracy improvement

[0381] The server analyzes the collected feedback and new emotion data and retrains the generative AI model based on it. This involves creating a new dataset and retraining the model. For example, the server adds new feedback data and retrains it as follows: openai.TrainModel(data='updated_feedback_data.csv')

[0382] Input: Feedback data, new facial and voice data

[0383] Output: Improved generative AI model

[0384] Following these steps will enable us to provide career paths and skills advice that are optimized for each individual employee.

[0385] (Application example 2)

[0386] 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."

[0387] Conventional career development support systems make suggestions based on employee profile information and past data, but they are unable to take into account employees' emotions and psychological state. As a result, the suggested career paths and advice may not be appropriate for employees, resulting in low satisfaction and effectiveness. Furthermore, in workplaces such as factories, there was a lack of a way to collect performance data on robots and employees in real time and propose appropriate training or role changes.

[0388] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 2 is realized by the following means.

[0389] In this invention, the server includes a data acquisition unit, a unit for acquiring employee profile information, past project history, evaluation data, and skill sets, an emotion engine for recognizing emotions, a unit for acquiring and analyzing emotional data from employees at the time of input or feedback using the emotion engine, a unit for adjusting the content and tone of career paths and advice based on the employee's emotional state, and a unit for generating optimal career paths and advice for skill development using artificial intelligence. This makes it possible to propose optimal career paths based on each employee's emotional state. Furthermore, particularly in factory settings, it is possible to collect performance data from robots and employees in real time and propose appropriate training programs and role changes.

[0390] "Data acquisition means" refers to the means for collecting necessary data such as employee profile information, past project history, evaluation data, skill sets, and emotional data.

[0391] "Profile information" refers to basic information about each employee, including age, position, years of service, etc.

[0392] A "generative AI model" is an artificial intelligence model that learns patterns based on collected employee data and generates advice for optimal career paths and skill development.

[0393] The "Emotion Engine" is a technology that acquires and analyzes the emotional data expressed by employees when entering data or providing feedback, and recognizes their emotional state.

[0394] "Feedback" refers to the reactions and opinions employees provide to the career paths and advice presented, and is used to retrain the system.

[0395] A "career path" indicates the optimal career path and direction for an employee.

[0396] A "skill set" is a collection of specialized skills and knowledge that an employee possesses, and is a list of skills necessary to perform their job.

[0397] The "interface means" is a user interface that allows employees to input their career aspirations, goals, and feedback.

[0398] This invention is a system for efficiently and effectively supporting employee career development. In particular, it aims to provide advice on optimal career paths and skill development based on performance data of employees and robots in a factory work environment. The specific configuration and operation of the system are described below.

[0399] System configuration and operation

[0400] server:

[0401] The server retrieves employee profile information, past project history, evaluation data, and skill sets from the company's database, thereby gathering data on the employee's current and past performance.

[0402] The server performs pre-processing to cleanse the collected data and fill in any invalid or missing values, preparing the data in a format suitable for training the generative AI model.

[0403] The server uses the preprocessed data to create a training dataset and trains the generative AI model, which extracts career development trends and patterns based on employee profile data.

[0404] Using the trained generative AI, the server generates advice for optimal career paths and skill development for each employee. For example, a recommendation might be generated such as, "Employee A should take training to improve his project management skills over the next three months."

[0405] Emotion Engine:

[0406] The server collects facial expression and voice data via the terminal when employees enter their career aspirations and goals, and when they confirm their career path and advice.

[0407] The emotion engine analyzes this data to recognize the employee's emotional state, for example, determining whether they are stressed or happy.

[0408] The server adjusts the content and tone of career paths and advice based on the emotional state derived from the emotion engine, potentially offering more relaxed goals to stressed employees and more challenging goals to satisfied employees.

[0409] Device:

[0410] The terminal provides an interface for employees to input their career aspirations and goals. The user (employee) inputs, "I want to improve my project management skills." The emotion engine reads the employee's emotions from their facial expressions.

[0411] The terminal presents the generated career path and advice to the employee, and the user (employee) confirms the presented information.

[0412] Users (employees) can input their feedback on career paths and advice via a terminal. For example, they can input feedback such as, "The training is good, but it's too early for you to take a management position."

[0413] Gathering feedback and relearning:

[0414] The server analyzes the collected feedback and retrains the generative AI model, further improving the accuracy of career paths and advice.

[0415] Hardware and software used

[0416] Data collection and processing uses hardware such as computers, IoT sensors, cameras, and microphones.

[0417] The software used is Python, TensorFlow, OpenCV, etc., to analyze data and build generative AI models.

[0418] Specific examples

[0419] For example, factory employee A inputs that he / she wants to improve his / her sewing machine operation skills. The generative AI model will suggest "We recommend online training on sewing machine operation in the next month," and if the emotion engine confirms that A is satisfied, it can make an additional suggestion such as "To further improve your skills, participate in actual product prototyping." An example of a prompt sentence is "We recommend training to improve sewing machine operation skills. We suggest that you participate in product prototyping as the next step."

[0420] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[0421] Step 1:

[0422] The server retrieves employee profile information, past project history, evaluation data, and skill sets from the company database. This input data includes basic employee information, project results, evaluations from superiors and colleagues, acquired skills, etc. By collecting this data, detailed information about employees' current and past performance can be obtained.

[0423] Step 2:

[0424] The server performs preprocessing to cleanse the collected data and fill in any invalid or missing values. This is done using Python libraries (e.g., Pandas, NumPy, etc.) to fill in missing values ​​and maintain data integrity. This preprocessing prepares the data in a format suitable for training generative AI models.

[0425] Step 3:

[0426] The server uses the preprocessed data to create a training dataset and trains the generative AI model. This process uses deep learning libraries such as TensorFlow and Keras to extract career development trends and patterns based on employee profile data. The input data is the preprocessed employee data, and the output is a trained generative AI model.

[0427] Step 4:

[0428] The server uses trained generative AI to generate optimal career paths and advice for skill development for each employee. Specifically, it generates a prompt for employee A such as, "We recommend training to improve your project management skills over the next three months." This input data is the trained generative AI, and the output is specific career paths and advice.

[0429] Step 5:

[0430] The server and terminals work together to provide an interface for employees to input their career aspirations and goals. The user (employee) inputs their career aspirations and goals, and the emotion engine acquires facial expression and voice data at that time. The user's emotions are recognized based on this data. The input data is the user's input information and emotional data, and the output is the recognized emotional state.

[0431] Step 6:

[0432] The terminal presents the generated career path and advice to the employee, who then confirms the information. The emotion engine recognizes the user's emotional state and adjusts the career path and advice. The input data are the generated career path and advice, as well as emotional data, and the output is the adjusted career path and advice.

[0433] Step 7:

[0434] Users (employees) input their feedback on career paths and advice via a terminal. For example, they might say, "The training is good, but I'd like to gain more experience before taking on a management position." This input data is feedback information, and emotional data is also recorded.

[0435] Step 8:

[0436] The server analyzes the collected feedback and retrains the generative AI model. In this process, the feedback data and emotion data are analyzed and retrained to improve the accuracy of the generative AI model. The input data is the feedback data and emotion data, and the output is an updated generative AI model. This further improves the accuracy of career paths and advice.

[0437] 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.

[0438] The data generation model 58 is a so-called generative AI (Artificial Intelligence). An example of the data generation model 58 is ChatGPT (registered trademark) (Internet search engine).<URL: https: / / openai.com / blog / chatgpt> ), Gemini (registered trademark) (Internet search <url: https: gemini.google.com ?hl="ja">) and other generation AIs. The data generation model 58 is obtained by performing deep learning on a neural network. A prompt including an instruction is input to the data generation model 58, and inference data such as voice data indicating voice, text data indicating text, and image data indicating an image is also input. The data generation model 58 performs inference on the input inference data in accordance with the instruction indicated by the prompt, and outputs the inference result in a data format such as voice data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[0439] 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.

[0440] [Second embodiment]

[0441] FIG. 3 shows an example of the configuration of a data processing system 210 according to the second embodiment.

[0442] 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.

[0443] 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).

[0444] 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.

[0445] 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.

[0446] 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).

[0447] 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.

[0448] 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.

[0449] 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.

[0450] 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.

[0451] 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.

[0452] 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."

[0453] This invention is a system for supporting employee career development, which links generative AI with employee-related data to efficiently and effectively propose career paths. Specifically, the server, terminals, and users work together to provide career development support optimized for each employee.

[0454] System configuration and operation

[0455] The server retrieves employee profile information, past project history, evaluation data, and skill sets from the database, thereby collecting data on the employee's current and past performance.

[0456] The terminal provides an interface for employees to input their career aspirations and goals. Users (employees) can use the terminal to input their intentions and goals into the system.

[0457] The server trains a generative AI model based on the collected data. This training process involves cleansing the data and pre-processing it to convert it into a format suitable for the AI ​​model, enabling it to generate highly accurate career paths.

[0458] Using trained generation AI, the server generates advice for optimal career paths and skill development for each employee. For example, it may suggest that "Employee A should take training to improve his project management skills over the next three months. It is also recommended that he try for a new project manager position in the future."

[0459] The terminal provides an interface that presents the generated career path and advice to the employee, allowing the user (employee) to confirm a specific career development plan.

[0460] Users (employees) can enter their feedback on the career paths and advice presented to them through their terminals. An example of the feedback they can enter is, "Project management training is appropriate, but I would like to gain more experience before taking on the new project manager position."

[0461] The server analyzes the collected feedback and performs re-training to further improve the accuracy of the generative AI model, thereby providing continuously optimized career paths.

[0462] Specific examples

[0463] Characters:

[0464] User: Employee A

[0465] server

[0466] Terminal

[0467] 1. Data Acquisition:

[0468] The server retrieves employee A's profile information (age, job title, years of service), past project history (project name, role, results), evaluation data (supervisor evaluation, feedback from colleagues), and skill set (programming languages, management skills) from the database.

[0469] 2. Enter your career aspirations and goals:

[0470] The terminal provides an interface for employee A to input his / her career aspirations and goals. The user (employee A) inputs "I want to improve my project management skills."

[0471] 3. Career path generation and presentation:

[0472] The server uses generative AI to generate a career path that reads, "Take training to improve your project management skills over the next three months and try for a new project manager position."

[0473] The terminal presents this career path to employee A.

[0474] 4. Gather and incorporate feedback:

[0475] The user (Employee A) enters feedback such as, "The training is suitable, but I would like to gain more experience before trying for a managerial position."

[0476] The server analyzes this feedback and performs re-training to improve the accuracy of the generative AI model.

[0477] This will create a system that provides employee A with the optimal career path and effectively supports individual career development.

[0478] The processing flow will be explained below.

[0479] Step 1:

[0480] The server retrieves employee profile information, past project history, evaluation data, and skill sets from the company's database.

[0481] Step 2:

[0482] The terminal provides an interface for employees to input their career aspirations and goals. Users (employees) use the terminal to input their career aspirations and goals.

[0483] Step 3:

[0484] The server cleanses the acquired data and performs preprocessing to fill in any invalid data or missing values, thereby preparing the data in a format suitable for training the AI ​​model.

[0485] Step 4:

[0486] The server uses the preprocessed data to create a training dataset and trains the generative AI model. Training is the process of extracting career development trends and patterns based on employee profile data.

[0487] Step 5:

[0488] The server uses the trained generative AI model to generate advice for optimal career paths and skill development for each employee. For example, it may generate a suggestion such as, "Employee A is recommended to take training to improve his project management skills over the next three months."

[0489] Step 6:

[0490] The terminal provides an interface for presenting the generated career path and advice to the employee, who then confirms the presented career path and advice.

[0491] Step 7:

[0492] Users (employees) can input their feedback on career paths and advice through terminals. For example, they can input feedback such as, "The training is good, but the project manager position is too early."

[0493] Step 8:

[0494] The server stores the collected feedback in a database and performs analysis to evaluate the performance of the generative AI model and identify areas for improvement.

[0495] Step 9:

[0496] The server retrains the generative AI model based on the feedback, further improving the accuracy of career paths and advice.

[0497] Step 10:

[0498] The terminal again presents the improved career path and advice to the employee, who can then review the new suggestions and provide feedback again.

[0499] By repeating the above steps, career development support optimized for each employee can be continuously provided.

[0500] Example 1

[0501] 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."

[0502] Employee career development is an important issue for companies, but it is extremely difficult to create an optimized career path for each employee and provide support tailored to their individual skills and goals. Furthermore, there is a lack of systems that efficiently incorporate feedback from employees and continuously optimize their career paths. The present invention aims to solve these problems and provide an efficient and effective system for promoting employee career development.

[0503] 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.

[0504] In this invention, the server includes a data acquisition means, a means for acquiring employee profile information, past project history, evaluation data, and skill sets, an interface means for inputting employee career aspirations and goals, a means for training a generative AI model based on the acquired data, a means for generating optimal career paths and advice for skill development for each employee using the trained generative AI, a means for presenting the generated career paths and advice to employees, a means for employees to input feedback on the presented career paths and advice, and a means for analyzing the collected feedback and re-training the generative AI model. This makes it possible to provide career paths optimized for each employee and continuously improve accuracy.

[0505] The "data acquisition means" is a means by which the server acquires data such as employee profile information, past project history, evaluation data, and skill sets from the database.

[0506] "Interface means" refers to input fields, forms, or other means on a terminal through which employees input their career aspirations and goals.

[0507] A "generative AI model" is an artificial intelligence model that predicts and generates optimal career paths for each employee based on large-scale data sets.

[0508] A "career path generation method" is a method that uses a trained generative AI model to generate optimal career paths and advice for skill development for each employee.

[0509] The "presentation means" refers to a means for presenting the generated career path and advice to employees, specifically, a screen display function of a terminal.

[0510] The "feedback input means" is a means for employees to input their opinions and requests regarding the career paths and advice presented to them.

[0511] The "relearning means" is a means for analyzing collected feedback and conducting re-learning to improve the accuracy of the generative AI model.

[0512] This invention is a system for supporting employee career development, which proposes career paths efficiently and effectively by linking generative AI with employee-related data. Specifically, the system realizes career development support optimized for each employee by having the server, terminals, and users function in cooperation with each other.

[0513] System configuration and operation

[0514] The server has functions such as a data acquisition means, a means for learning and relearning the generated AI model, a means for generating a career path, and a means for presenting the career path.

[0515] Data Acquisition Method

[0516] The server has a means to retrieve information from the database, such as employee profile information (age, job title, years of service), past project history (project name, role, results), evaluation data (supervisor evaluation, feedback from colleagues), skill set (programming language, management ability), etc. For example, the server uses SQL queries to retrieve the required information from the database.

[0517] Generative AI models and learning methods

[0518] The server trains a generative AI model based on the collected data. In this training process, data cleansing (e.g., removing duplicate data, filling in missing data) and preprocessing (standardizing and normalizing data) are performed, and then the data is input into an AI model (e.g., BERT or GPT-3) for training.

[0519] Career path generation method

[0520] Using trained generation AI, the server generates optimal career paths and advice for skill development for each employee. For example, for Employee A, a specific career path would be generated such as, "It is recommended that you take training to improve your project management skills over the next three months. It is recommended that you try for a new project manager position in the future."

[0521] Presentation means

[0522] The career paths and advice generated by the server are presented to employees via their terminals. The terminals receive the information from the server and display it on their screens, allowing employees to check specific career development plans.

[0523] Feedback input and re-learning methods

[0524] Employees (users) enter feedback on the presented career paths and advice through their terminals. For example, they may say, "The training is appropriate, but I would like to gain more experience before taking on a managerial position." The server analyzes this feedback and performs re-training to improve the accuracy of the generative AI model. This re-training gives the system the ability to continuously provide optimized career paths.

[0525] Specific examples

[0526] Characters:

[0527] User: Employee A

[0528] server

[0529] Terminal

[0530] 1. Data Acquisition

[0531] The server retrieves data such as employee A's profile information, past project history, evaluation data, and skill set from the database.

[0532] 2. Enter your career aspirations and goals

[0533] The terminal provides an interface for Employee A to input his / her career aspirations and goals. Employee A inputs, "I want to improve my project management skills."

[0534] 3. Creating and presenting career paths

[0535] The server uses generative AI to generate career paths such as "Take training to improve your project management skills over the next three months and try for a new project manager position."

[0536] The terminal presents this career path to employee A.

[0537] 4. Gather and incorporate feedback

[0538] The user (Employee A) enters feedback into the terminal, saying, "The training is appropriate, but I would like to gain more experience before trying for a managerial position."

[0539] The server analyzes this feedback and performs re-training to improve the accuracy of the generative AI model.

[0540] Prompt Sentence Examples

[0541] "Generate a suitable career path for Employee A based on their profile information and project history."

[0542] The flow of the identification process in the first embodiment will be described with reference to FIG.

[0543] Step 1:

[0544] Data Acquisition

[0545] The server retrieves data from the database, such as employee profile information, past project history, evaluation data, and skill sets.

[0546] Input: Employee ID and database credentials

[0547] Data processing: The process of issuing an SQL query to retrieve the relevant employee data.

[0548] Output: A dataset containing information about each employee

[0549] Specific behavior: Executes an SQL query such as SELECT FROM employee_data WHERE employee_id = 'A123'.

[0550] Step 2:

[0551] Enter your career aspirations and goals

[0552] The terminal provides an interface for employees to input their career aspirations and goals.

[0553] Input: Employee's career aspirations and goals (e.g., "I want to improve my project management skills")

[0554] Data processing: Convert the input hopes and goals into a specific format and send it to the server

[0555] Output: Preferences and goals sent to the server

[0556] Specific operation: The employee enters their request into the input field on the terminal and presses the send button.

[0557] Step 3:

[0558] Training generative AI models

[0559] The server trains a generative AI model based on the collected data.

[0560] Inputs: Employee profile information, past project history, evaluation data, skill sets

[0561] Data processing: Perform preprocessing such as data cleansing (removal of duplicate data, filling in missing data), standardization and normalization of data

[0562] Output: A trained generative AI model

[0563] What it does: Cleanses data and converts it into a format suitable for AI models to run the learning process.

[0564] Step 4:

[0565] Career path creation

[0566] The server uses trained generative AI to generate the optimal career path for each employee.

[0567] Input: trained generative AI model, employee data

[0568] Data Computing: Generative AI models generate career paths using employee data as input

[0569] Output: Generated career path and advice (e.g., "It is recommended that you take training to improve your project management skills in the next three months")

[0570] How it works: Employee data is fed into a generative AI model to generate career paths.

[0571] Step 5:

[0572] Providing career paths

[0573] The terminal then presents the generated career path and advice to the employee.

[0574] Input: Career path data sent from the server

[0575] Data processing: Converts career path data into a display format and displays it on the terminal screen

[0576] Output: Screen display to employees (e.g., specific career development plans are displayed)

[0577] Specific operation: Display career path on the device screen.

[0578] Step 6:

[0579] Collecting feedback

[0580] The user inputs feedback on the presented career path and advice via the terminal.

[0581] Input: Employee feedback (e.g., "The training was appropriate, but I would like to gain more experience before taking on a managerial position.")

[0582] Data processing: The feedback content is converted into a specific format and sent to the server.

[0583] Output: Feedback data sent to the server

[0584] Specific actions: Enter feedback into the input field on the device and press the send button.

[0585] Step 7:

[0586] Reflecting feedback

[0587] The server analyzes the collected feedback and retrains the generative AI model.

[0588] Input: Employee feedback data

[0589] Data computation: Analyze the feedback data and provide it as new data points to the generative AI model for retraining.

[0590] Output: An updated generative AI model

[0591] Specific operation: A re-learning process is performed based on feedback data to improve the accuracy of the generative AI model.

[0592] (Application example 1)

[0593] 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."

[0594] Existing career development support systems suggest career paths based on employee profile information and evaluation data, but this alone makes it difficult to provide specific advice optimized for each employee. Furthermore, the means by which employees can provide feedback are limited, making continuous optimization difficult and preventing effective linkage to actual work and skill development in the workplace. Furthermore, the lack of an interface that can be used immediately in the workplace tends to reduce employees' motivation and involvement in their career development.

[0595] 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.

[0596] In this invention, the server includes means for acquiring employee profile information, past project history, evaluation data, and skill sets, interface means for inputting employee career aspirations and goals, and means for training a generative AI model based on the acquired data. This allows the generative AI model to be trained based on the acquired data, and the trained generative AI can be used to generate optimal career paths and advice for skill development for each employee, which can then be presented via a touchscreen or voice recognition system. By analyzing feedback collected using the feedback input means and retraining the generative AI model, this system can provide continuously optimized career paths and efficiently support employees' career development.

[0597] A "data acquisition means" is a device or system for collecting and managing information about employees.

[0598] "Profile information" refers to basic information such as an employee's age, position, and years of service.

[0599] "Past project history" is data that records the names, roles, results, etc. of projects that employees have participated in.

[0600] "Evaluation data" is information that includes the results of evaluations of an employee's work by their superiors and colleagues.

[0601] A "skill set" refers to the list of skills and abilities that an employee possesses.

[0602] An "interface means" is a device or system through which employees input their career aspirations and goals.

[0603] A "generative AI model" is a model that uses artificial intelligence technology to generate advice for optimal career paths and skill development based on employee data.

[0604] A "career path" is a path that shows employees the steps they should aim for and the goals they should achieve.

[0605] A "touch screen" is a type of display device that can be operated by directly touching the screen.

[0606] A "speech recognition system" is a device or system that analyzes and converts spoken input into text or commands.

[0607] "Feedback" refers to the opinions and suggestions that employees provide regarding the career path or advice presented to them.

[0608] "Retraining" is the process of incorporating new data, such as collected feedback, into a generative AI model.

[0609] System configuration and operation

[0610] This invention is a system for supporting employee career development through factory robots. Specifically, a server, factory robots, and employees (users) work together to provide optimized career development support.

[0611] Hardware Configuration

[0612] Server: Manages databases and trains generative AI models.

[0613] Factory robots: Equipped with touchscreens and voice recognition systems, they act as an interface with employees. Examples include FANUC robotic arms and devices with touchscreens.

[0614] Employees (users): Use the system to enter their career aspirations and goals.

[0615] Software Configuration

[0616] Generative AI model: Built using TensorFlow and Keras, this AI model learns from employee data and generates advice on optimal career paths and skill development.

[0617] Database management system: MySQL is used to manage employee profile information, past project history, evaluation data, and skill sets.

[0618] Speech Recognition System: Uses Google Cloud Speech-to-Text to convert employee voice input into text.

[0619] Programming language: Python is used for data processing and implementing AI models.

[0620] Explanation of program processing

[0621] The server retrieves employee profile information, past project history, evaluation data, and skill sets from the database, thereby gathering data on the employee's current and past performance.

[0622] The factory robots provide an interface for employees to input their career aspirations and goals, which are then sent to a server via a touchscreen or voice recognition system.

[0623] The server trains a generative AI model based on the collected data, cleansing the data and performing preprocessing to convert it into a format suitable for the AI ​​model, thereby enabling the generation of highly accurate career paths.

[0624] Using trained generation AI, the server generates advice for optimal career paths and skill development for each employee. For example, it might suggest, "Employee A is recommended to take training to improve his project management skills over the next three months. It would also be advisable for him to try for a new project manager position in the future."

[0625] The factory robot will then present the generated career paths and advice to employees, who can then view specific career development plans via a touchscreen or voice assistant.

[0626] Employees can use the factory robot to provide feedback on the career paths and advice presented to them, such as, "Project management training is appropriate, but I would like to gain more experience before taking on the new project manager position."

[0627] The server analyzes the collected feedback and retrains the generative AI model, allowing it to provide continuously optimized career paths.

[0628] Specific examples

[0629] Characters:

[0630] Employee A

[0631] server

[0632] Factory Robots

[0633] 1. Data Acquisition:

[0634] The server retrieves employee A's profile information (age, job title, years of service), past project history (project name, role, results), evaluation data (supervisor evaluation, feedback from colleagues), and skill set (programming languages, management skills) from the database.

[0635] 2. Enter your career aspirations and goals:

[0636] The factory robot provides an interface for Employee A to input his / her career aspirations and goals. Employee A inputs, "I want to improve my project management skills."

[0637] 3. Career path generation and presentation:

[0638] The server uses generative AI to generate a career path that reads, "Take training to improve your project management skills over the next three months and try for a new project manager position."

[0639] The factory robot presents this career path to employee A.

[0640] 4. Gather and incorporate feedback:

[0641] Employee A provides feedback saying, "The training is suitable, but I would like to gain more experience before taking on a managerial position."

[0642] The server analyzes this feedback and performs re-training to improve the accuracy of the generative AI model.

[0643] Example prompt sentence:

[0644] INSERT INTO employee_data (name, age, role, skills, past_projects, evaluations) VALUES ('Employee A', 34, 'Line Manager', 'Production Management, Quality Control', 'Project X, Project Y', 'Supervisor rating: 4.5, Peer rating: 4.0')

[0645] This system makes it possible to provide employee A with the optimal career path and effectively support his or her individual career development.

[0646] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[0647] Step 1:

[0648] The server retrieves employee profile information, past project history, evaluation data, and skill sets from the database. Based on this input data, an initial dataset regarding the employee's current status and past performance is created. Specifically, MySQL is used to retrieve the necessary information from the database using SQL queries, and the information is converted into a data frame using Python's pandas library.

[0649] Step 2:

[0650] The terminal (factory robot) provides an interface for employees to input their career aspirations and goals. Specifically, it accepts input from employees (e.g., "I want to improve my project management skills") using a touchscreen or voice recognition system. This input data is sent to the server via an HTTP request.

[0651] Step 3:

[0652] The server receives employee input data and integrates it with previously collected profile information and evaluation data. It trains a generative AI model based on this integrated dataset. It cleans the data and performs preprocessing to convert it into a format suitable for the AI ​​model. It trains the AI ​​model using TensorFlow or Keras.

[0653] Step 4:

[0654] Using trained generative AI, the server generates optimal career paths and advice for skill development for each employee. Specifically, the server inputs the employee's integrated data into the AI ​​model to generate career path candidates. The generated career path is output as a specific action plan (e.g., "We recommend that you take training to improve your project management skills in the next three months").

[0655] Step 5:

[0656] The terminal (factory robot) presents the generated career path and advice to the employee. Specifically, it displays the generated career path and advice visually or audibly via a touch screen or voice assistant, and the employee confirms the results.

[0657] Step 6:

[0658] The user (employee) enters feedback on the presented career path and advice through a terminal (factory robot). Specifically, the user enters feedback (e.g., "The training is suitable, but I would like to gain more experience before attempting a managerial position") using a touch screen or voice recognition system. This feedback data is then sent back to the server via an HTTP request.

[0659] Step 7:

[0660] The server analyzes the collected feedback and retrains the generative AI model. Specifically, the feedback data is added to the dataset, the data is cleansed, and the AI ​​model is retrained. The generative AI model, with improved accuracy through retraining, is used to generate the next career path, making it possible to provide continuously optimized career paths.

[0661] 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.

[0662] This invention is a system for supporting employee career development, which links generative AI with employee-related data and combines it with an emotion engine that recognizes user emotions to efficiently and effectively propose career paths. Specifically, by having the server, terminals, and users cooperate with each other, it realizes career development support that is optimized for each employee.

[0663] System configuration and operation

[0664] The server retrieves employee profile information, past project history, evaluation data, and skill sets from the company's database, thereby gathering data on the employee's current and past performance.

[0665] The terminal provides an interface for employees to input their career aspirations and goals, and collects this information input by the user (employee).

[0666] The server cleanses the collected data and performs preprocessing to fill in any invalid or missing values, preparing the data in a format suitable for training AI models.

[0667] The server uses the preprocessed data to create a training dataset and trains the generative AI model, which extracts career development trends and patterns based on employee profile data.

[0668] Using the trained generative AI, the server generates advice for optimal career paths and skill development for each employee. For example, a recommendation might be generated such as, "Employee A should take training to improve his project management skills over the next three months."

[0669] The terminal presents the generated career path and advice to the employee, and the user (employee) confirms the presented information.

[0670] Users (employees) can input their feedback on career paths and advice via a terminal. For example, they can input feedback such as, "The training is good, but it's too early for you to take a management position."

[0671] The server analyzes the collected feedback and performs re-training to improve the accuracy of the generative AI model, which further improves the accuracy of career paths and advice.

[0672] Introducing the Emotion Engine

[0673] Furthermore, the present invention incorporates an emotion engine that recognizes the user's emotions. The emotion engine operates as follows:

[0674] The server collects facial expression and voice data via the terminal when employees enter their career aspirations and goals, and when they confirm their career path and advice.

[0675] The emotion engine analyzes this data to recognize the user's emotional state, for example, determining whether an employee is stressed or happy.

[0676] The server adjusts the content and tone of career paths and advice based on the emotional state derived from the emotion engine, potentially offering more relaxed goals to stressed employees and more challenging goals to satisfied employees.

[0677] Users (employees) will feel more satisfied with their career path by receiving advice that is more in line with their own emotions.

[0678] Specific examples

[0679] Characters:

[0680] User: Employee A

[0681] server

[0682] Terminal

[0683] 1. Data Acquisition:

[0684] The server retrieves employee A's profile information (age, job title, years of service), past project history (project name, role, results), evaluation data (supervisor evaluation, feedback from colleagues), and skill set (programming languages, management skills) from the database.

[0685] 2. Enter your career aspirations and goals:

[0686] The terminal provides an interface for employee A to input their career aspirations and goals. The user (employee A) inputs, "I want to improve my project management skills." The emotion engine reads the emotions of employee A from their facial expressions at this time.

[0687] 3. Career path generation and presentation:

[0688] The server uses generative AI to generate a career path such as "Take training to improve your project management skills in the next three months and try for a new project manager position." It adjusts the advice to an appropriate tone, taking into account Employee A's emotional state.

[0689] The terminal presents this career path to employee A.

[0690] 4. Gather and incorporate feedback:

[0691] The user (Employee A) enters feedback such as, "The training is suitable, but I would like to gain more experience before taking on the managerial position." The user's feelings at this time are also recorded.

[0692] The server analyzes the feedback and emotional data and retrains the generative AI model.

[0693] This will create a system that provides the optimal career path for employee A and effectively supports individual career development. The introduction of an emotion engine will enable advanced career support that takes into account the emotions of employees.

[0694] The processing flow will be explained below.

[0695] Step 1:

[0696] The server retrieves employee profile information, past project history, evaluation data, and skill sets from the company's database.

[0697] Step 2:

[0698] The terminal provides an interface for employees to input their career aspirations and goals. Users (employees) use the terminal to input their career aspirations and goals.

[0699] Step 3:

[0700] The server cleanses the collected data and performs preprocessing to fill in any invalid or missing values, preparing the data in a format suitable for training AI models.

[0701] Step 4:

[0702] The server uses the preprocessed data to create a training dataset and trains the generative AI model. Training is the process of extracting career development trends and patterns based on employee profile data.

[0703] Step 5:

[0704] When an employee inputs their career aspirations and goals, the server acquires facial expression and voice data and analyzes them using an emotion engine, thereby recognizing the user's emotional state.

[0705] Step 6:

[0706] The server uses a trained generative AI model to generate optimal career paths and advice for skill development for each employee. The generated career paths and advice are adjusted taking into account the user's emotional state. For example, a recommendation might be generated such as, "Employee A is recommended to take training to improve his project management skills over the next three months."

[0707] Step 7:

[0708] The terminal provides an interface for presenting the generated career path and advice to the employee, who then confirms the presented career path and advice.

[0709] Step 8:

[0710] Users (employees) can input their feedback on career paths and advice through a terminal. For example, they can input feedback such as, "The training was good, but it's too early for you to move into a management position." Their emotional state at this time is also recorded.

[0711] Step 9:

[0712] The server analyzes the collected feedback and emotional data and performs retraining to improve the accuracy of the generative AI model, which further improves the accuracy of career paths and advice.

[0713] Step 10:

[0714] The terminal again presents the improved career path and advice to the employee, who can then review the new suggestions and provide feedback again.

[0715] By repeating the above steps, the emotional engine can be utilized to provide ongoing career development support that is optimized for each employee.

[0716] Example 2

[0717] 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."

[0718] Conventional career development support systems mainly make suggestions based on quantitative employee data, making it difficult to reflect employees' emotions and motivation. Furthermore, the generated career paths and advice are often unrealistic, limiting their ability to provide optimal support to individual employees. This can result in insufficient contribution to employee satisfaction and career advancement.

[0719] The specific processing by the specific processing unit 290 of the data processing device 12 in the second embodiment is realized by the following means.

[0720] In this invention, the server includes means for acquiring employee profile information, past project history, evaluation data, and skill sets, an interface means for inputting employee career aspirations and goals, means for acquiring user facial expression and voice data, means for cleansing the acquired data and complementing invalid data and missing values, means for training a generative AI model based on the cleansed data, means for inputting prompt sentences to the generative AI model and generating advice for career paths and skill development, means for adjusting and presenting the content of the career paths and advice generated by the generative AI model, means for employees to input feedback on the career paths and advice, and means for analyzing the collected feedback and emotion data and re-training the generative AI model. This makes it possible to provide career paths and advice optimized for each employee, reflecting the emotions and career aspirations of the employees.

[0721] "Data acquisition means" refers to means for collecting employee profile information, past project history, evaluation data, and skill sets from the company's database.

[0722] "Employee profile information" refers to basic personal information such as an employee's age, position, and years of service.

[0723] "Past project history" is data including the names, roles, and results of projects in which an employee has participated.

[0724] "Evaluation data" refers to data used to evaluate an employee's performance, including feedback from superiors and colleagues.

[0725] A "skill set" is data that specifically indicates the skills, qualifications, and special talents possessed by an employee.

[0726] "Interface means" refers to a user interface that allows employees to input their career aspirations and goals.

[0727] "Means for acquiring facial expressions and voice data" refers to means for acquiring facial expressions and voice data using a camera or microphone while an employee is using the interface.

[0728] "Data cleansing methods" are methods for organizing collected data, eliminating invalid data, and filling in missing values.

[0729] A "means for training a generative AI model" is a means for training an AI algorithm using cleansed data to train a model.

[0730] "Means for inputting prompt sentences and generating advice" refers to means for providing specific input sentences to a generative AI model and generating advice for career paths and skill development based on those sentences.

[0731] "Means for adjusting and presenting advice content" refers to a means for adjusting the advice generated by the generative AI model based on the employee's emotional data and presenting it to the employee.

[0732] "Means for inputting feedback" refers to a user interface that allows employees to input feedback on career paths and advice.

[0733] "Means for analyzing feedback and emotional data and retraining the generative AI model" refers to means for analyzing collected feedback and emotional data and retraining the generative AI model based on that data.

[0734] System program processing

[0735] This invention is a system for supporting employees' career development. The system mainly involves the cooperation of a server, terminals, and users to realize career development support optimized for each employee.

[0736] Data Acquisition

[0737] The server retrieves employee profile information, past project history, evaluation data, and skill sets from the company database using a database query such as SQL. For example, the server executes a query like this: SELECT FROM EmployeeProfile WHERE EmployeeID = 'A123';

[0738] Enter your career aspirations and goals

[0739] The device provides an interface for users (employees) to input their career aspirations and goals. This interface can be implemented as a web form or a mobile app, and displays text boxes and options for entering the required information.

[0740] The device also captures facial and voice data as users enter their career aspirations and goals using a camera and microphone. For example, the device captures facial and voice data in real time while a user types, "I want to improve my project management skills."

[0741] Data Preprocessing

[0742] The server cleanses the collected employee data and fills in any invalid data or missing values. For this, you can use the Python pandas library. For example, the server fills in missing values ​​as follows: df.fillna(method='ffill')

[0743] Training generative AI models

[0744] The server uses the preprocessed data to create a training dataset and trains a generative AI model using a generative AI framework (e.g., GPT-3 or GPT-4). The server can run the command: openai.TrainModel(data='training_data.csv')

[0745] Career path creation

[0746] The server uses trained generative AI to generate optimal career paths and advice on skill development for each employee. A specific prompt is input to the generative AI model. For example, this prompt might be something like, "What career path would you suggest for employee A?"

[0747] The generated career path is adjusted taking into account the emotional state captured by the emotion engine. For example, the server may adjust the career path based on the output of the generative AI model, such as "Employee A is feeling stressed, so the training should be short-term."

[0748] Providing career paths

[0749] The device presents the generated career path and skill development advice to the employee, which is displayed as a user interface and includes information such as specific goals and training plans.

[0750] Collecting feedback

[0751] Users (employees) can input their feedback on career paths and advice through a terminal. Text boxes and options are provided for this input. Facial expressions and voices are also recorded when inputting feedback.

[0752] Re-learning and accuracy improvement

[0753] The server analyzes the collected feedback and emotion data and retrains the generative AI model. This involves adding new data and training the AI ​​model again. For example, the server adds new feedback data and retrains it as follows: openai.TrainModel(data='updated_feedback_data.csv')

[0754] This makes it possible to reflect employees' career aspirations and feelings and provide career paths and advice that are optimized for each individual employee.

[0755] The flow of the identification process in the second embodiment will be described with reference to FIG.

[0756] System program processing flow

[0757] Step 1:

[0758] Data Acquisition

[0759] The server retrieves employee profile information, past project history, evaluation data, and skill sets from the company database. The server executes SQL queries to gather the required data. For example, the server might use a query like this: SELECT FROM EmployeeProfile WHERE EmployeeID = 'A123';

[0760] Input: Company database

[0761] Output: Employee profile information, project history, evaluation data, skill set

[0762] Step 2:

[0763] Enter your career aspirations and goals

[0764] The terminal provides an interface for users (employees) to input their career aspirations and goals. The terminal displays UI components of web forms or mobile apps to prompt users to enter the required information.

[0765] Specific behavior: Displaying text boxes and drop-down menus.

[0766] Input: User's career aspirations and goals

[0767] Output: User's career preference data

[0768] Step 3:

[0769] Acquiring facial and voice data

[0770] The device captures facial and voice data as the user enters their career aspirations and goals. The device uses a camera and microphone to capture the data.

[0771] Input: User's facial expression, voice

[0772] Output: User's facial expression data, voice data

[0773] Step 4:

[0774] Data Preprocessing

[0775] The server cleanses the collected data and imputes invalid data and missing values. For this, it uses the Python pandas library. For example, the server imputes missing values ​​as follows: df.fillna(method='ffill')

[0776] Input: Employee profile information, project history, evaluation data, skill set, career aspirations, facial expression data, voice data

[0777] Output: A cleansed dataset

[0778] Step 5:

[0779] Training generative AI models

[0780] The server uses the preprocessed data to create a training dataset and trains a generative AI model. The model is trained using a generative AI framework (e.g., GPT-3 or GPT-4). The server executes the command: openai.TrainModel(data='training_data.csv')

[0781] Input: Cleansed dataset

[0782] Output: A trained generative AI model

[0783] Step 6:

[0784] Career path creation

[0785] The server uses trained generative AI to generate optimal career paths and skill development advice for each employee. A specific prompt is given to the generative AI model to generate career path suggestions. For example, the prompt could be, "What career path would you suggest for employee A?"

[0786] Input: trained generative AI model, prompt

[0787] Output: Generated career paths and skill development advice

[0788] Step 7:

[0789] Providing and adjusting advice

[0790] The server adjusts the advice generated by the generative AI model based on the employee's emotional data and presents it to the employee via their device, softening difficult suggestions and emphasizing easy goals.

[0791] Input: Generated career paths, skill advice, sentiment data

[0792] Output: Tailored career paths, skills advice

[0793] Step 8:

[0794] Collecting feedback

[0795] The user (employee) inputs feedback on career paths and advice and sends it to the server via the terminal. The terminal also collects facial expressions and voice data.

[0796] Specific actions: Providing an input form and using the camera and microphone.

[0797] Input: Employee feedback, facial expressions, and voice data

[0798] Output: Feedback data, additional facial and voice data

[0799] Step 9:

[0800] Re-learning and accuracy improvement

[0801] The server analyzes the collected feedback and new emotion data and retrains the generative AI model based on it. This involves creating a new dataset and retraining the model. For example, the server adds new feedback data and retrains it as follows: openai.TrainModel(data='updated_feedback_data.csv')

[0802] Input: Feedback data, new facial and voice data

[0803] Output: Improved generative AI model

[0804] Following these steps will enable us to provide career paths and skills advice that are optimized for each individual employee.

[0805] (Application example 2)

[0806] 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."

[0807] Conventional career development support systems make suggestions based on employee profile information and past data, but they are unable to take into account employees' emotions and psychological state. As a result, the suggested career paths and advice may not be appropriate for employees, resulting in low satisfaction and effectiveness. Furthermore, in workplaces such as factories, there was a lack of a way to collect performance data on robots and employees in real time and propose appropriate training or role changes.

[0808] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 2 is realized by the following means.

[0809] In this invention, the server includes a data acquisition unit, a unit for acquiring employee profile information, past project history, evaluation data, and skill sets, an emotion engine for recognizing emotions, a unit for acquiring and analyzing emotional data from employees at the time of input or feedback using the emotion engine, a unit for adjusting the content and tone of career paths and advice based on the employee's emotional state, and a unit for generating optimal career paths and advice for skill development using artificial intelligence. This makes it possible to propose optimal career paths based on each employee's emotional state. Furthermore, particularly in factory settings, it is possible to collect performance data from robots and employees in real time and propose appropriate training programs and role changes.

[0810] "Data acquisition means" refers to the means for collecting necessary data such as employee profile information, past project history, evaluation data, skill sets, and emotional data.

[0811] "Profile information" refers to basic information about each employee, including age, position, years of service, etc.

[0812] A "generative AI model" is an artificial intelligence model that learns patterns based on collected employee data and generates advice for optimal career paths and skill development.

[0813] The "Emotion Engine" is a technology that acquires and analyzes the emotional data expressed by employees when entering data or providing feedback, and recognizes their emotional state.

[0814] "Feedback" refers to the reactions and opinions employees provide to the career paths and advice presented, and is used to retrain the system.

[0815] A "career path" indicates the optimal career path and direction for an employee.

[0816] A "skill set" is a collection of specialized skills and knowledge that an employee possesses, and is a list of skills necessary to perform their job.

[0817] The "interface means" is a user interface that allows employees to input their career aspirations, goals, and feedback.

[0818] This invention is a system for efficiently and effectively supporting employee career development. In particular, it aims to provide advice on optimal career paths and skill development based on performance data of employees and robots in a factory work environment. The specific configuration and operation of the system are described below.

[0819] System configuration and operation

[0820] server:

[0821] The server retrieves employee profile information, past project history, evaluation data, and skill sets from the company's database, thereby gathering data on the employee's current and past performance.

[0822] The server performs pre-processing to cleanse the collected data and fill in any invalid or missing values, preparing the data in a format suitable for training the generative AI model.

[0823] The server uses the preprocessed data to create a training dataset and trains the generative AI model, which extracts career development trends and patterns based on employee profile data.

[0824] Using the trained generative AI, the server generates advice for optimal career paths and skill development for each employee. For example, a recommendation might be generated such as, "Employee A should take training to improve his project management skills over the next three months."

[0825] Emotion Engine:

[0826] The server collects facial expression and voice data via the terminal when employees enter their career aspirations and goals, and when they confirm their career path and advice.

[0827] The emotion engine analyzes this data to recognize the employee's emotional state, for example, determining whether they are stressed or happy.

[0828] The server adjusts the content and tone of career paths and advice based on the emotional state derived from the emotion engine, potentially offering more relaxed goals to stressed employees and more challenging goals to satisfied employees.

[0829] Device:

[0830] The terminal provides an interface for employees to input their career aspirations and goals. The user (employee) inputs, "I want to improve my project management skills." The emotion engine reads the employee's emotions from their facial expressions.

[0831] The terminal presents the generated career path and advice to the employee, and the user (employee) confirms the presented information.

[0832] Users (employees) can input their feedback on career paths and advice via a terminal. For example, they can input feedback such as, "The training is good, but it's too early for you to take a management position."

[0833] Gathering feedback and relearning:

[0834] The server analyzes the collected feedback and retrains the generative AI model, further improving the accuracy of career paths and advice.

[0835] Hardware and software used

[0836] Data collection and processing uses hardware such as computers, IoT sensors, cameras, and microphones.

[0837] The software used is Python, TensorFlow, OpenCV, etc., to analyze data and build generative AI models.

[0838] Specific examples

[0839] For example, factory employee A inputs that he / she wants to improve his / her sewing machine operation skills. The generative AI model will suggest "We recommend online training on sewing machine operation in the next month," and if the emotion engine confirms that A is satisfied, it can make an additional suggestion such as "To further improve your skills, participate in actual product prototyping." An example of a prompt sentence is "We recommend training to improve sewing machine operation skills. We suggest that you participate in product prototyping as the next step."

[0840] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[0841] Step 1:

[0842] The server retrieves employee profile information, past project history, evaluation data, and skill sets from the company database. This input data includes basic employee information, project results, evaluations from superiors and colleagues, acquired skills, etc. By collecting this data, detailed information about employees' current and past performance can be obtained.

[0843] Step 2:

[0844] The server performs preprocessing to cleanse the collected data and fill in any invalid or missing values. This is done using Python libraries (e.g., Pandas, NumPy, etc.) to fill in missing values ​​and maintain data integrity. This preprocessing prepares the data in a format suitable for training generative AI models.

[0845] Step 3:

[0846] The server uses the preprocessed data to create a training dataset and trains the generative AI model. This process uses deep learning libraries such as TensorFlow and Keras to extract career development trends and patterns based on employee profile data. The input data is the preprocessed employee data, and the output is a trained generative AI model.

[0847] Step 4:

[0848] The server uses trained generative AI to generate optimal career paths and advice for skill development for each employee. Specifically, it generates a prompt for employee A such as, "We recommend training to improve your project management skills over the next three months." This input data is the trained generative AI, and the output is specific career paths and advice.

[0849] Step 5:

[0850] The server and terminals work together to provide an interface for employees to input their career aspirations and goals. The user (employee) inputs their career aspirations and goals, and the emotion engine acquires facial expression and voice data at that time. The user's emotions are recognized based on this data. The input data is the user's input information and emotional data, and the output is the recognized emotional state.

[0851] Step 6:

[0852] The terminal presents the generated career path and advice to the employee, who then confirms the information. The emotion engine recognizes the user's emotional state and adjusts the career path and advice. The input data are the generated career path and advice, as well as emotional data, and the output is the adjusted career path and advice.

[0853] Step 7:

[0854] Users (employees) input their feedback on career paths and advice via a terminal. For example, they might say, "The training is good, but I'd like to gain more experience before taking on a management position." This input data is feedback information, and emotional data is also recorded.

[0855] Step 8:

[0856] The server analyzes the collected feedback and retrains the generative AI model. In this process, the feedback data and emotion data are analyzed and retrained to improve the accuracy of the generative AI model. The input data is the feedback data and emotion data, and the output is an updated generative AI model. This further improves the accuracy of career paths and advice.

[0857] 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.

[0858] 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.

[0859] 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.

[0860] [Third embodiment]

[0861] FIG. 5 shows an example of the configuration of a data processing system 310 according to the third embodiment.

[0862] 5, the data processing system 310 includes the data processing device 12 and a headset type terminal 314. An example of the data processing device 12 is a server.

[0863] 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).

[0864] 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.

[0865] 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.

[0866] 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).

[0867] 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.

[0868] 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.

[0869] 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.

[0870] 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.

[0871] 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.

[0872] 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."

[0873] This invention is a system for supporting employee career development, which links generative AI with employee-related data to efficiently and effectively propose career paths. Specifically, the server, terminals, and users work together to provide career development support optimized for each employee.

[0874] System configuration and operation

[0875] The server retrieves employee profile information, past project history, evaluation data, and skill sets from the database, thereby collecting data on the employee's current and past performance.

[0876] The terminal provides an interface for employees to input their career aspirations and goals. Users (employees) can use the terminal to input their intentions and goals into the system.

[0877] The server trains a generative AI model based on the collected data. This training process involves cleansing the data and pre-processing it to convert it into a format suitable for the AI ​​model, enabling it to generate highly accurate career paths.

[0878] Using trained generation AI, the server generates advice for optimal career paths and skill development for each employee. For example, it may suggest that "Employee A should take training to improve his project management skills over the next three months. It is also recommended that he try for a new project manager position in the future."

[0879] The terminal provides an interface that presents the generated career path and advice to the employee, allowing the user (employee) to confirm a specific career development plan.

[0880] Users (employees) can enter their feedback on the career paths and advice presented to them through their terminals. An example of the feedback they can enter is, "Project management training is appropriate, but I would like to gain more experience before taking on the new project manager position."

[0881] The server analyzes the collected feedback and performs re-training to further improve the accuracy of the generative AI model, thereby providing continuously optimized career paths.

[0882] Specific examples

[0883] Characters:

[0884] User: Employee A

[0885] server

[0886] Terminal

[0887] 1. Data Acquisition:

[0888] The server retrieves employee A's profile information (age, job title, years of service), past project history (project name, role, results), evaluation data (supervisor evaluation, feedback from colleagues), and skill set (programming languages, management skills) from the database.

[0889] 2. Enter your career aspirations and goals:

[0890] The terminal provides an interface for employee A to input his / her career aspirations and goals. The user (employee A) inputs "I want to improve my project management skills."

[0891] 3. Career path generation and presentation:

[0892] The server uses generative AI to generate a career path that reads, "Take training to improve your project management skills over the next three months and try for a new project manager position."

[0893] The terminal presents this career path to employee A.

[0894] 4. Gather and incorporate feedback:

[0895] The user (Employee A) enters feedback such as, "The training is suitable, but I would like to gain more experience before trying for a managerial position."

[0896] The server analyzes this feedback and performs re-training to improve the accuracy of the generative AI model.

[0897] This will create a system that provides employee A with the optimal career path and effectively supports individual career development.

[0898] The processing flow will be explained below.

[0899] Step 1:

[0900] The server retrieves employee profile information, past project history, evaluation data, and skill sets from the company's database.

[0901] Step 2:

[0902] The terminal provides an interface for employees to input their career aspirations and goals. Users (employees) use the terminal to input their career aspirations and goals.

[0903] Step 3:

[0904] The server cleanses the acquired data and performs preprocessing to fill in any invalid data or missing values, thereby preparing the data in a format suitable for training the AI ​​model.

[0905] Step 4:

[0906] The server uses the preprocessed data to create a training dataset and trains the generative AI model. Training is the process of extracting career development trends and patterns based on employee profile data.

[0907] Step 5:

[0908] The server uses the trained generative AI model to generate advice for optimal career paths and skill development for each employee. For example, it may generate a suggestion such as, "Employee A is recommended to take training to improve his project management skills over the next three months."

[0909] Step 6:

[0910] The terminal provides an interface for presenting the generated career path and advice to the employee, who then confirms the presented career path and advice.

[0911] Step 7:

[0912] Users (employees) can input their feedback on career paths and advice through terminals. For example, they can input feedback such as, "The training is good, but the project manager position is too early."

[0913] Step 8:

[0914] The server stores the collected feedback in a database and performs analysis to evaluate the performance of the generative AI model and identify areas for improvement.

[0915] Step 9:

[0916] The server retrains the generative AI model based on the feedback, further improving the accuracy of career paths and advice.

[0917] Step 10:

[0918] The terminal again presents the improved career path and advice to the employee, who can then review the new suggestions and provide feedback again.

[0919] By repeating the above steps, career development support optimized for each employee can be continuously provided.

[0920] Example 1

[0921] 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."

[0922] Employee career development is an important issue for companies, but it is extremely difficult to create an optimized career path for each employee and provide support tailored to their individual skills and goals. Furthermore, there is a lack of systems that efficiently incorporate feedback from employees and continuously optimize their career paths. The present invention aims to solve these problems and provide an efficient and effective system for promoting employee career development.

[0923] 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.

[0924] In this invention, the server includes a data acquisition means, a means for acquiring employee profile information, past project history, evaluation data, and skill sets, an interface means for inputting employee career aspirations and goals, a means for training a generative AI model based on the acquired data, a means for generating optimal career paths and advice for skill development for each employee using the trained generative AI, a means for presenting the generated career paths and advice to employees, a means for employees to input feedback on the presented career paths and advice, and a means for analyzing the collected feedback and re-training the generative AI model. This makes it possible to provide career paths optimized for each employee and continuously improve accuracy.

[0925] The "data acquisition means" is a means by which the server acquires data such as employee profile information, past project history, evaluation data, and skill sets from the database.

[0926] "Interface means" refers to input fields, forms, or other means on a terminal through which employees input their career aspirations and goals.

[0927] A "generative AI model" is an artificial intelligence model that predicts and generates optimal career paths for each employee based on large-scale data sets.

[0928] A "career path generation method" is a method that uses a trained generative AI model to generate optimal career paths and advice for skill development for each employee.

[0929] The "presentation means" refers to a means for presenting the generated career path and advice to employees, specifically, a screen display function of a terminal.

[0930] The "feedback input means" is a means for employees to input their opinions and requests regarding the career paths and advice presented to them.

[0931] The "relearning means" is a means for analyzing collected feedback and conducting re-learning to improve the accuracy of the generative AI model.

[0932] This invention is a system for supporting employee career development, which proposes career paths efficiently and effectively by linking generative AI with employee-related data. Specifically, the system realizes career development support optimized for each employee by having the server, terminals, and users function in cooperation with each other.

[0933] System configuration and operation

[0934] The server has functions such as a data acquisition means, a means for learning and relearning the generated AI model, a means for generating a career path, and a means for presenting the career path.

[0935] Data Acquisition Method

[0936] The server has a means to retrieve information from the database, such as employee profile information (age, job title, years of service), past project history (project name, role, results), evaluation data (supervisor evaluation, feedback from colleagues), skill set (programming language, management ability), etc. For example, the server uses SQL queries to retrieve the required information from the database.

[0937] Generative AI models and learning methods

[0938] The server trains a generative AI model based on the collected data. In this training process, data cleansing (e.g., removing duplicate data, filling in missing data) and preprocessing (standardizing and normalizing data) are performed, and then the data is input into an AI model (e.g., BERT or GPT-3) for training.

[0939] Career path generation method

[0940] Using trained generation AI, the server generates optimal career paths and advice for skill development for each employee. For example, for Employee A, a specific career path would be generated such as, "It is recommended that you take training to improve your project management skills over the next three months. It is recommended that you try for a new project manager position in the future."

[0941] Presentation means

[0942] The career paths and advice generated by the server are presented to employees via their terminals. The terminals receive the information from the server and display it on their screens, allowing employees to check specific career development plans.

[0943] Feedback input and re-learning methods

[0944] Employees (users) enter feedback on the presented career paths and advice through their terminals. For example, they may say, "The training is appropriate, but I would like to gain more experience before taking on a managerial position." The server analyzes this feedback and performs re-training to improve the accuracy of the generative AI model. This re-training gives the system the ability to continuously provide optimized career paths.

[0945] Specific examples

[0946] Characters:

[0947] User: Employee A

[0948] server

[0949] Terminal

[0950] 1. Data Acquisition

[0951] The server retrieves data such as employee A's profile information, past project history, evaluation data, and skill set from the database.

[0952] 2. Enter your career aspirations and goals

[0953] The terminal provides an interface for Employee A to input his / her career aspirations and goals. Employee A inputs, "I want to improve my project management skills."

[0954] 3. Creating and presenting career paths

[0955] The server uses generative AI to generate career paths such as "Take training to improve your project management skills over the next three months and try for a new project manager position."

[0956] The terminal presents this career path to employee A.

[0957] 4. Gather and incorporate feedback

[0958] The user (Employee A) enters feedback into the terminal, saying, "The training is appropriate, but I would like to gain more experience before trying for a managerial position."

[0959] The server analyzes this feedback and performs re-training to improve the accuracy of the generative AI model.

[0960] Prompt Sentence Examples

[0961] "Generate a suitable career path for Employee A based on their profile information and project history."

[0962] The flow of the identification process in the first embodiment will be described with reference to FIG.

[0963] Step 1:

[0964] Data Acquisition

[0965] The server retrieves data from the database, such as employee profile information, past project history, evaluation data, and skill sets.

[0966] Input: Employee ID and database credentials

[0967] Data processing: The process of issuing an SQL query to retrieve the relevant employee data.

[0968] Output: A dataset containing information about each employee

[0969] Specific behavior: Executes an SQL query such as SELECT FROM employee_data WHERE employee_id = 'A123'.

[0970] Step 2:

[0971] Enter your career aspirations and goals

[0972] The terminal provides an interface for employees to input their career aspirations and goals.

[0973] Input: Employee's career aspirations and goals (e.g., "I want to improve my project management skills")

[0974] Data processing: Convert the input hopes and goals into a specific format and send it to the server

[0975] Output: Preferences and goals sent to the server

[0976] Specific operation: The employee enters their request into the input field on the terminal and presses the send button.

[0977] Step 3:

[0978] Training generative AI models

[0979] The server trains a generative AI model based on the collected data.

[0980] Inputs: Employee profile information, past project history, evaluation data, skill sets

[0981] Data processing: Perform preprocessing such as data cleansing (removal of duplicate data, filling in missing data), standardization and normalization of data

[0982] Output: A trained generative AI model

[0983] What it does: Cleanses data and converts it into a format suitable for AI models to run the learning process.

[0984] Step 4:

[0985] Career path creation

[0986] The server uses trained generative AI to generate the optimal career path for each employee.

[0987] Input: trained generative AI model, employee data

[0988] Data Computing: Generative AI models generate career paths using employee data as input

[0989] Output: Generated career path and advice (e.g., "It is recommended that you take training to improve your project management skills in the next three months")

[0990] How it works: Employee data is fed into a generative AI model to generate career paths.

[0991] Step 5:

[0992] Providing career paths

[0993] The terminal then presents the generated career path and advice to the employee.

[0994] Input: Career path data sent from the server

[0995] Data processing: Converts career path data into a display format and displays it on the terminal screen

[0996] Output: Screen display to employees (e.g., specific career development plans are displayed)

[0997] Specific operation: Display career path on the device screen.

[0998] Step 6:

[0999] Collecting feedback

[1000] The user inputs feedback on the presented career path and advice via the terminal.

[1001] Input: Employee feedback (e.g., "The training was appropriate, but I would like to gain more experience before taking on a managerial position.")

[1002] Data processing: The feedback content is converted into a specific format and sent to the server.

[1003] Output: Feedback data sent to the server

[1004] Specific actions: Enter feedback into the input field on the device and press the send button.

[1005] Step 7:

[1006] Reflecting feedback

[1007] The server analyzes the collected feedback and retrains the generative AI model.

[1008] Input: Employee feedback data

[1009] Data computation: Analyze the feedback data and provide it as new data points to the generative AI model for retraining.

[1010] Output: An updated generative AI model

[1011] Specific operation: A re-learning process is performed based on feedback data to improve the accuracy of the generative AI model.

[1012] (Application example 1)

[1013] 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."

[1014] Existing career development support systems suggest career paths based on employee profile information and evaluation data, but this alone makes it difficult to provide specific advice optimized for each employee. Furthermore, the means by which employees can provide feedback are limited, making continuous optimization difficult and preventing effective linkage to actual work and skill development in the workplace. Furthermore, the lack of an interface that can be used immediately in the workplace tends to reduce employees' motivation and involvement in their career development.

[1015] 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.

[1016] In this invention, the server includes means for acquiring employee profile information, past project history, evaluation data, and skill sets, interface means for inputting employee career aspirations and goals, and means for training a generative AI model based on the acquired data. This allows the generative AI model to be trained based on the acquired data, and the trained generative AI can be used to generate optimal career paths and advice for skill development for each employee, which can then be presented via a touchscreen or voice recognition system. By analyzing feedback collected using the feedback input means and retraining the generative AI model, this system can provide continuously optimized career paths and efficiently support employees' career development.

[1017] A "data acquisition means" is a device or system for collecting and managing information about employees.

[1018] "Profile information" refers to basic information such as an employee's age, position, and years of service.

[1019] "Past project history" is data that records the names, roles, results, etc. of projects that employees have participated in.

[1020] "Evaluation data" is information that includes the results of evaluations of an employee's work by their superiors and colleagues.

[1021] A "skill set" refers to the list of skills and abilities that an employee possesses.

[1022] An "interface means" is a device or system through which employees input their career aspirations and goals.

[1023] A "generative AI model" is a model that uses artificial intelligence technology to generate advice for optimal career paths and skill development based on employee data.

[1024] A "career path" is a path that shows employees the steps they should aim for and the goals they should achieve.

[1025] A "touch screen" is a type of display device that can be operated by directly touching the screen.

[1026] A "speech recognition system" is a device or system that analyzes and converts spoken input into text or commands.

[1027] "Feedback" refers to the opinions and suggestions that employees provide regarding the career path or advice presented to them.

[1028] "Retraining" is the process of incorporating new data, such as collected feedback, into a generative AI model.

[1029] System configuration and operation

[1030] This invention is a system for supporting employee career development through factory robots. Specifically, a server, factory robots, and employees (users) work together to provide optimized career development support.

[1031] Hardware Configuration

[1032] Server: Manages databases and trains generative AI models.

[1033] Factory robots: Equipped with touchscreens and voice recognition systems, they act as an interface with employees. Examples include FANUC robotic arms and devices with touchscreens.

[1034] Employees (users): Use the system to enter their career aspirations and goals.

[1035] Software Configuration

[1036] Generative AI model: Built using TensorFlow and Keras, this AI model learns from employee data and generates advice on optimal career paths and skill development.

[1037] Database management system: MySQL is used to manage employee profile information, past project history, evaluation data, and skill sets.

[1038] Speech Recognition System: Uses Google Cloud Speech-to-Text to convert employee voice input into text.

[1039] Programming language: Python is used for data processing and implementing AI models.

[1040] Explanation of program processing

[1041] The server retrieves employee profile information, past project history, evaluation data, and skill sets from the database, thereby gathering data on the employee's current and past performance.

[1042] The factory robots provide an interface for employees to input their career aspirations and goals, which are then sent to a server via a touchscreen or voice recognition system.

[1043] The server trains a generative AI model based on the collected data, cleansing the data and performing preprocessing to convert it into a format suitable for the AI ​​model, thereby enabling the generation of highly accurate career paths.

[1044] Using trained generation AI, the server generates advice for optimal career paths and skill development for each employee. For example, it might suggest, "Employee A is recommended to take training to improve his project management skills over the next three months. It would also be advisable for him to try for a new project manager position in the future."

[1045] The factory robot will then present the generated career paths and advice to employees, who can then view specific career development plans via a touchscreen or voice assistant.

[1046] Employees can use the factory robot to provide feedback on the career paths and advice presented to them, such as, "Project management training is appropriate, but I would like to gain more experience before taking on the new project manager position."

[1047] The server analyzes the collected feedback and retrains the generative AI model, allowing it to provide continuously optimized career paths.

[1048] Specific examples

[1049] Characters:

[1050] Employee A

[1051] server

[1052] Factory Robots

[1053] 1. Data Acquisition:

[1054] The server retrieves employee A's profile information (age, job title, years of service), past project history (project name, role, results), evaluation data (supervisor evaluation, feedback from colleagues), and skill set (programming languages, management skills) from the database.

[1055] 2. Enter your career aspirations and goals:

[1056] The factory robot provides an interface for Employee A to input his / her career aspirations and goals. Employee A inputs, "I want to improve my project management skills."

[1057] 3. Career path generation and presentation:

[1058] The server uses generative AI to generate a career path that reads, "Take training to improve your project management skills over the next three months and try for a new project manager position."

[1059] The factory robot presents this career path to employee A.

[1060] 4. Gather and incorporate feedback:

[1061] Employee A provides feedback saying, "The training is suitable, but I would like to gain more experience before taking on a managerial position."

[1062] The server analyzes this feedback and performs re-training to improve the accuracy of the generative AI model.

[1063] Example prompt sentence:

[1064] INSERT INTO employee_data (name, age, role, skills, past_projects, evaluations) VALUES ('Employee A', 34, 'Line Manager', 'Production Management, Quality Control', 'Project X, Project Y', 'Supervisor rating: 4.5, Peer rating: 4.0')

[1065] This system makes it possible to provide employee A with the optimal career path and effectively support his or her individual career development.

[1066] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[1067] Step 1:

[1068] The server retrieves employee profile information, past project history, evaluation data, and skill sets from the database. Based on this input data, an initial dataset regarding the employee's current status and past performance is created. Specifically, MySQL is used to retrieve the necessary information from the database using SQL queries, and the information is converted into a data frame using Python's pandas library.

[1069] Step 2:

[1070] The terminal (factory robot) provides an interface for employees to input their career aspirations and goals. Specifically, it accepts input from employees (e.g., "I want to improve my project management skills") using a touchscreen or voice recognition system. This input data is sent to the server via an HTTP request.

[1071] Step 3:

[1072] The server receives employee input data and integrates it with previously collected profile information and evaluation data. It trains a generative AI model based on this integrated dataset. It cleans the data and performs preprocessing to convert it into a format suitable for the AI ​​model. It trains the AI ​​model using TensorFlow or Keras.

[1073] Step 4:

[1074] Using trained generative AI, the server generates optimal career paths and advice for skill development for each employee. Specifically, the server inputs the employee's integrated data into the AI ​​model to generate career path candidates. The generated career path is output as a specific action plan (e.g., "We recommend that you take training to improve your project management skills in the next three months").

[1075] Step 5:

[1076] The terminal (factory robot) presents the generated career path and advice to the employee. Specifically, it displays the generated career path and advice visually or audibly via a touch screen or voice assistant, and the employee confirms the results.

[1077] Step 6:

[1078] The user (employee) enters feedback on the presented career path and advice through a terminal (factory robot). Specifically, the user enters feedback (e.g., "The training is suitable, but I would like to gain more experience before attempting a managerial position") using a touch screen or voice recognition system. This feedback data is then sent back to the server via an HTTP request.

[1079] Step 7:

[1080] The server analyzes the collected feedback and retrains the generative AI model. Specifically, the feedback data is added to the dataset, the data is cleansed, and the AI ​​model is retrained. The generative AI model, with improved accuracy through retraining, is used to generate the next career path, making it possible to provide continuously optimized career paths.

[1081] 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.

[1082] This invention is a system for supporting employee career development, which links generative AI with employee-related data and combines it with an emotion engine that recognizes user emotions to efficiently and effectively propose career paths. Specifically, by having the server, terminals, and users cooperate with each other, it realizes career development support that is optimized for each employee.

[1083] System configuration and operation

[1084] The server retrieves employee profile information, past project history, evaluation data, and skill sets from the company's database, thereby gathering data on the employee's current and past performance.

[1085] The terminal provides an interface for employees to input their career aspirations and goals, and collects this information input by the user (employee).

[1086] The server cleanses the collected data and performs preprocessing to fill in any invalid or missing values, preparing the data in a format suitable for training AI models.

[1087] The server uses the preprocessed data to create a training dataset and trains the generative AI model, which extracts career development trends and patterns based on employee profile data.

[1088] Using the trained generative AI, the server generates advice for optimal career paths and skill development for each employee. For example, a recommendation might be generated such as, "Employee A should take training to improve his project management skills over the next three months."

[1089] The terminal presents the generated career path and advice to the employee, and the user (employee) confirms the presented information.

[1090] Users (employees) can input their feedback on career paths and advice via a terminal. For example, they can input feedback such as, "The training is good, but it's too early for you to take a management position."

[1091] The server analyzes the collected feedback and performs re-training to improve the accuracy of the generative AI model, which further improves the accuracy of career paths and advice.

[1092] Introducing the Emotion Engine

[1093] Furthermore, the present invention incorporates an emotion engine that recognizes the user's emotions. The emotion engine operates as follows:

[1094] The server collects facial expression and voice data via the terminal when employees enter their career aspirations and goals, and when they confirm their career path and advice.

[1095] The emotion engine analyzes this data to recognize the user's emotional state, for example, determining whether an employee is stressed or happy.

[1096] The server adjusts the content and tone of career paths and advice based on the emotional state derived from the emotion engine, potentially offering more relaxed goals to stressed employees and more challenging goals to satisfied employees.

[1097] Users (employees) will feel more satisfied with their career path by receiving advice that is more in line with their own emotions.

[1098] Specific examples

[1099] Characters:

[1100] User: Employee A

[1101] server

[1102] Terminal

[1103] 1. Data Acquisition:

[1104] The server retrieves employee A's profile information (age, job title, years of service), past project history (project name, role, results), evaluation data (supervisor evaluation, feedback from colleagues), and skill set (programming languages, management skills) from the database.

[1105] 2. Enter your career aspirations and goals:

[1106] The terminal provides an interface for employee A to input their career aspirations and goals. The user (employee A) inputs, "I want to improve my project management skills." The emotion engine reads the emotions of employee A from their facial expressions at this time.

[1107] 3. Career path generation and presentation:

[1108] The server uses generative AI to generate a career path such as "Take training to improve your project management skills in the next three months and try for a new project manager position." It adjusts the advice to an appropriate tone, taking into account Employee A's emotional state.

[1109] The terminal presents this career path to employee A.

[1110] 4. Gather and incorporate feedback:

[1111] The user (Employee A) enters feedback such as, "The training is suitable, but I would like to gain more experience before taking on the managerial position." The user's feelings at this time are also recorded.

[1112] The server analyzes the feedback and emotional data and retrains the generative AI model.

[1113] This will create a system that provides the optimal career path for employee A and effectively supports individual career development. The introduction of an emotion engine will enable advanced career support that takes into account the emotions of employees.

[1114] The processing flow will be explained below.

[1115] Step 1:

[1116] The server retrieves employee profile information, past project history, evaluation data, and skill sets from the company's database.

[1117] Step 2:

[1118] The terminal provides an interface for employees to input their career aspirations and goals. Users (employees) use the terminal to input their career aspirations and goals.

[1119] Step 3:

[1120] The server cleanses the collected data and performs preprocessing to fill in any invalid or missing values, preparing the data in a format suitable for training AI models.

[1121] Step 4:

[1122] The server uses the preprocessed data to create a training dataset and trains the generative AI model. Training is the process of extracting career development trends and patterns based on employee profile data.

[1123] Step 5:

[1124] When an employee inputs their career aspirations and goals, the server acquires facial expression and voice data and analyzes them using an emotion engine, thereby recognizing the user's emotional state.

[1125] Step 6:

[1126] The server uses a trained generative AI model to generate optimal career paths and advice for skill development for each employee. The generated career paths and advice are adjusted taking into account the user's emotional state. For example, a recommendation might be generated such as, "Employee A is recommended to take training to improve his project management skills over the next three months."

[1127] Step 7:

[1128] The terminal provides an interface for presenting the generated career path and advice to the employee, who then confirms the presented career path and advice.

[1129] Step 8:

[1130] Users (employees) can input their feedback on career paths and advice through a terminal. For example, they can input feedback such as, "The training was good, but it's too early for you to move into a management position." Their emotional state at this time is also recorded.

[1131] Step 9:

[1132] The server analyzes the collected feedback and emotional data and performs retraining to improve the accuracy of the generative AI model, which further improves the accuracy of career paths and advice.

[1133] Step 10:

[1134] The terminal again presents the improved career path and advice to the employee, who can then review the new suggestions and provide feedback again.

[1135] By repeating the above steps, the emotional engine can be utilized to provide ongoing career development support that is optimized for each employee.

[1136] Example 2

[1137] 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."

[1138] Conventional career development support systems mainly make suggestions based on quantitative employee data, making it difficult to reflect employees' emotions and motivation. Furthermore, the generated career paths and advice are often unrealistic, limiting their ability to provide optimal support to individual employees. This can result in insufficient contribution to employee satisfaction and career advancement.

[1139] The specific processing by the specific processing unit 290 of the data processing device 12 in the second embodiment is realized by the following means.

[1140] In this invention, the server includes means for acquiring employee profile information, past project history, evaluation data, and skill sets, an interface means for inputting employee career aspirations and goals, means for acquiring user facial expression and voice data, means for cleansing the acquired data and complementing invalid data and missing values, means for training a generative AI model based on the cleansed data, means for inputting prompt sentences to the generative AI model and generating advice for career paths and skill development, means for adjusting and presenting the content of the career paths and advice generated by the generative AI model, means for employees to input feedback on the career paths and advice, and means for analyzing the collected feedback and emotion data and re-training the generative AI model. This makes it possible to provide career paths and advice optimized for each employee, reflecting the emotions and career aspirations of the employees.

[1141] "Data acquisition means" refers to means for collecting employee profile information, past project history, evaluation data, and skill sets from the company's database.

[1142] "Employee profile information" refers to basic personal information such as an employee's age, position, and years of service.

[1143] "Past project history" is data including the names, roles, and results of projects in which an employee has participated.

[1144] "Evaluation data" refers to data used to evaluate an employee's performance, including feedback from superiors and colleagues.

[1145] A "skill set" is data that specifically indicates the skills, qualifications, and special talents possessed by an employee.

[1146] "Interface means" refers to a user interface that allows employees to input their career aspirations and goals.

[1147] "Means for acquiring facial expressions and voice data" refers to means for acquiring facial expressions and voice data using a camera or microphone while an employee is using the interface.

[1148] "Data cleansing methods" are methods for organizing collected data, eliminating invalid data, and filling in missing values.

[1149] A "means for training a generative AI model" is a means for training an AI algorithm using cleansed data to train a model.

[1150] "Means for inputting prompt sentences and generating advice" refers to means for providing specific input sentences to a generative AI model and generating advice for career paths and skill development based on those sentences.

[1151] "Means for adjusting and presenting advice content" refers to a means for adjusting the advice generated by the generative AI model based on the employee's emotional data and presenting it to the employee.

[1152] "Means for inputting feedback" refers to a user interface that allows employees to input feedback on career paths and advice.

[1153] "Means for analyzing feedback and emotional data and retraining the generative AI model" refers to means for analyzing collected feedback and emotional data and retraining the generative AI model based on that data.

[1154] System program processing

[1155] This invention is a system for supporting employees' career development. The system mainly involves the cooperation of a server, terminals, and users to realize career development support optimized for each employee.

[1156] Data Acquisition

[1157] The server retrieves employee profile information, past project history, evaluation data, and skill sets from the company database using a database query such as SQL. For example, the server executes a query like this: SELECT FROM EmployeeProfile WHERE EmployeeID = 'A123';

[1158] Enter your career aspirations and goals

[1159] The device provides an interface for users (employees) to input their career aspirations and goals. This interface can be implemented as a web form or a mobile app, and displays text boxes and options for entering the required information.

[1160] The device also captures facial and voice data as users enter their career aspirations and goals using a camera and microphone. For example, the device captures facial and voice data in real time while a user types, "I want to improve my project management skills."

[1161] Data Preprocessing

[1162] The server cleanses the collected employee data and fills in any invalid data or missing values. For this, you can use the Python pandas library. For example, the server fills in missing values ​​as follows: df.fillna(method='ffill')

[1163] Training generative AI models

[1164] The server uses the preprocessed data to create a training dataset and trains a generative AI model using a generative AI framework (e.g., GPT-3 or GPT-4). The server can run the command: openai.TrainModel(data='training_data.csv')

[1165] Career path creation

[1166] The server uses trained generative AI to generate optimal career paths and advice on skill development for each employee. A specific prompt is input to the generative AI model. For example, this prompt might be something like, "What career path would you suggest for employee A?"

[1167] The generated career path is adjusted taking into account the emotional state captured by the emotion engine. For example, the server may adjust the career path based on the output of the generative AI model, such as "Employee A is feeling stressed, so the training should be short-term."

[1168] Providing career paths

[1169] The device presents the generated career path and skill development advice to the employee, which is displayed as a user interface and includes information such as specific goals and training plans.

[1170] Collecting feedback

[1171] Users (employees) can input their feedback on career paths and advice through a terminal. Text boxes and options are provided for this input. Facial expressions and voices are also recorded when inputting feedback.

[1172] Re-learning and accuracy improvement

[1173] The server analyzes the collected feedback and emotion data and retrains the generative AI model. This involves adding new data and training the AI ​​model again. For example, the server adds new feedback data and retrains it as follows: openai.TrainModel(data='updated_feedback_data.csv')

[1174] This makes it possible to reflect employees' career aspirations and feelings and provide career paths and advice that are optimized for each individual employee.

[1175] The flow of the identification process in the second embodiment will be described with reference to FIG.

[1176] System program processing flow

[1177] Step 1:

[1178] Data Acquisition

[1179] The server retrieves employee profile information, past project history, evaluation data, and skill sets from the company database. The server executes SQL queries to gather the required data. For example, the server might use a query like this: SELECT FROM EmployeeProfile WHERE EmployeeID = 'A123';

[1180] Input: Company database

[1181] Output: Employee profile information, project history, evaluation data, skill set

[1182] Step 2:

[1183] Enter your career aspirations and goals

[1184] The terminal provides an interface for users (employees) to input their career aspirations and goals. The terminal displays UI components of web forms or mobile apps to prompt users to enter the required information.

[1185] Specific behavior: Displaying text boxes and drop-down menus.

[1186] Input: User's career aspirations and goals

[1187] Output: User's career preference data

[1188] Step 3:

[1189] Acquiring facial and voice data

[1190] The device captures facial and voice data as the user enters their career aspirations and goals. The device uses a camera and microphone to capture the data.

[1191] Input: User's facial expression, voice

[1192] Output: User's facial expression data, voice data

[1193] Step 4:

[1194] Data Preprocessing

[1195] The server cleanses the collected data and imputes invalid data and missing values. For this, it uses the Python pandas library. For example, the server imputes missing values ​​as follows: df.fillna(method='ffill')

[1196] Input: Employee profile information, project history, evaluation data, skill set, career aspirations, facial expression data, voice data

[1197] Output: A cleansed dataset

[1198] Step 5:

[1199] Training generative AI models

[1200] The server uses the preprocessed data to create a training dataset and trains a generative AI model. The model is trained using a generative AI framework (e.g., GPT-3 or GPT-4). The server executes the command: openai.TrainModel(data='training_data.csv')

[1201] Input: Cleansed dataset

[1202] Output: A trained generative AI model

[1203] Step 6:

[1204] Career path creation

[1205] The server uses trained generative AI to generate optimal career paths and skill development advice for each employee. A specific prompt is given to the generative AI model to generate career path suggestions. For example, the prompt could be, "What career path would you suggest for employee A?"

[1206] Input: trained generative AI model, prompt

[1207] Output: Generated career paths and skill development advice

[1208] Step 7:

[1209] Providing and adjusting advice

[1210] The server adjusts the advice generated by the generative AI model based on the employee's emotional data and presents it to the employee via their device, softening difficult suggestions and emphasizing easy goals.

[1211] Input: Generated career paths, skill advice, sentiment data

[1212] Output: Tailored career paths, skills advice

[1213] Step 8:

[1214] Collecting feedback

[1215] The user (employee) inputs feedback on career paths and advice and sends it to the server via the terminal. The terminal also collects facial expressions and voice data.

[1216] Specific actions: Providing an input form and using the camera and microphone.

[1217] Input: Employee feedback, facial expressions, and voice data

[1218] Output: Feedback data, additional facial and voice data

[1219] Step 9:

[1220] Re-learning and accuracy improvement

[1221] The server analyzes the collected feedback and new emotion data and retrains the generative AI model based on it. This involves creating a new dataset and retraining the model. For example, the server adds new feedback data and retrains it as follows: openai.TrainModel(data='updated_feedback_data.csv')

[1222] Input: Feedback data, new facial and voice data

[1223] Output: Improved generative AI model

[1224] Following these steps will enable us to provide career paths and skills advice that are optimized for each individual employee.

[1225] (Application example 2)

[1226] 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."

[1227] Conventional career development support systems make suggestions based on employee profile information and past data, but they are unable to take into account employees' emotions and psychological state. As a result, the suggested career paths and advice may not be appropriate for employees, resulting in low satisfaction and effectiveness. Furthermore, in workplaces such as factories, there was a lack of a way to collect performance data on robots and employees in real time and propose appropriate training or role changes.

[1228] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 2 is realized by the following means.

[1229] In this invention, the server includes a data acquisition unit, a unit for acquiring employee profile information, past project history, evaluation data, and skill sets, an emotion engine for recognizing emotions, a unit for acquiring and analyzing emotional data from employees at the time of input or feedback using the emotion engine, a unit for adjusting the content and tone of career paths and advice based on the employee's emotional state, and a unit for generating optimal career paths and advice for skill development using artificial intelligence. This makes it possible to propose optimal career paths based on each employee's emotional state. Furthermore, particularly in factory settings, it is possible to collect performance data from robots and employees in real time and propose appropriate training programs and role changes.

[1230] "Data acquisition means" refers to the means for collecting necessary data such as employee profile information, past project history, evaluation data, skill sets, and emotional data.

[1231] "Profile information" refers to basic information about each employee, including age, position, years of service, etc.

[1232] A "generative AI model" is an artificial intelligence model that learns patterns based on collected employee data and generates advice for optimal career paths and skill development.

[1233] The "Emotion Engine" is a technology that acquires and analyzes the emotional data expressed by employees when entering data or providing feedback, and recognizes their emotional state.

[1234] "Feedback" refers to the reactions and opinions employees provide to the career paths and advice presented, and is used to retrain the system.

[1235] A "career path" indicates the optimal career path and direction for an employee.

[1236] A "skill set" is a collection of specialized skills and knowledge that an employee possesses, and is a list of skills necessary to perform their job.

[1237] The "interface means" is a user interface that allows employees to input their career aspirations, goals, and feedback.

[1238] This invention is a system for efficiently and effectively supporting employee career development. In particular, it aims to provide advice on optimal career paths and skill development based on performance data of employees and robots in a factory work environment. The specific configuration and operation of the system are described below.

[1239] System configuration and operation

[1240] server:

[1241] The server retrieves employee profile information, past project history, evaluation data, and skill sets from the company's database, thereby gathering data on the employee's current and past performance.

[1242] The server performs pre-processing to cleanse the collected data and fill in any invalid or missing values, preparing the data in a format suitable for training the generative AI model.

[1243] The server uses the preprocessed data to create a training dataset and trains the generative AI model, which extracts career development trends and patterns based on employee profile data.

[1244] Using the trained generative AI, the server generates advice for optimal career paths and skill development for each employee. For example, a recommendation might be generated such as, "Employee A should take training to improve his project management skills over the next three months."

[1245] Emotion Engine:

[1246] The server collects facial expression and voice data via the terminal when employees enter their career aspirations and goals, and when they confirm their career path and advice.

[1247] The emotion engine analyzes this data to recognize the employee's emotional state, for example, determining whether they are stressed or happy.

[1248] The server adjusts the content and tone of career paths and advice based on the emotional state derived from the emotion engine, potentially offering more relaxed goals to stressed employees and more challenging goals to satisfied employees.

[1249] Device:

[1250] The terminal provides an interface for employees to input their career aspirations and goals. The user (employee) inputs, "I want to improve my project management skills." The emotion engine reads the employee's emotions from their facial expressions.

[1251] The terminal presents the generated career path and advice to the employee, and the user (employee) confirms the presented information.

[1252] Users (employees) can input their feedback on career paths and advice via a terminal. For example, they can input feedback such as, "The training is good, but it's too early for you to take a management position."

[1253] Gathering feedback and relearning:

[1254] The server analyzes the collected feedback and retrains the generative AI model, further improving the accuracy of career paths and advice.

[1255] Hardware and software used

[1256] Data collection and processing uses hardware such as computers, IoT sensors, cameras, and microphones.

[1257] The software used is Python, TensorFlow, OpenCV, etc., to analyze data and build generative AI models.

[1258] Specific examples

[1259] For example, factory employee A inputs that he / she wants to improve his / her sewing machine operation skills. The generative AI model will suggest "We recommend online training on sewing machine operation in the next month," and if the emotion engine confirms that A is satisfied, it can make an additional suggestion such as "To further improve your skills, participate in actual product prototyping." An example of a prompt sentence is "We recommend training to improve sewing machine operation skills. We suggest that you participate in product prototyping as the next step."

[1260] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[1261] Step 1:

[1262] The server retrieves employee profile information, past project history, evaluation data, and skill sets from the company database. This input data includes basic employee information, project results, evaluations from superiors and colleagues, acquired skills, etc. By collecting this data, detailed information about employees' current and past performance can be obtained.

[1263] Step 2:

[1264] The server performs preprocessing to cleanse the collected data and fill in any invalid or missing values. This is done using Python libraries (e.g., Pandas, NumPy, etc.) to fill in missing values ​​and maintain data integrity. This preprocessing prepares the data in a format suitable for training generative AI models.

[1265] Step 3:

[1266] The server uses the preprocessed data to create a training dataset and trains the generative AI model. This process uses deep learning libraries such as TensorFlow and Keras to extract career development trends and patterns based on employee profile data. The input data is the preprocessed employee data, and the output is a trained generative AI model.

[1267] Step 4:

[1268] The server uses trained generative AI to generate optimal career paths and advice for skill development for each employee. Specifically, it generates a prompt for employee A such as, "We recommend training to improve your project management skills over the next three months." This input data is the trained generative AI, and the output is specific career paths and advice.

[1269] Step 5:

[1270] The server and terminals work together to provide an interface for employees to input their career aspirations and goals. The user (employee) inputs their career aspirations and goals, and the emotion engine acquires facial expression and voice data at that time. The user's emotions are recognized based on this data. The input data is the user's input information and emotional data, and the output is the recognized emotional state.

[1271] Step 6:

[1272] The terminal presents the generated career path and advice to the employee, who then confirms the information. The emotion engine recognizes the user's emotional state and adjusts the career path and advice. The input data are the generated career path and advice, as well as emotional data, and the output is the adjusted career path and advice.

[1273] Step 7:

[1274] Users (employees) input their feedback on career paths and advice via a terminal. For example, they might say, "The training is good, but I'd like to gain more experience before taking on a management position." This input data is feedback information, and emotional data is also recorded.

[1275] Step 8:

[1276] The server analyzes the collected feedback and retrains the generative AI model. In this process, the feedback data and emotion data are analyzed and retrained to improve the accuracy of the generative AI model. The input data is the feedback data and emotion data, and the output is an updated generative AI model. This further improves the accuracy of career paths and advice.

[1277] 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.

[1278] 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.

[1279] 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.

[1280] [Fourth embodiment]

[1281] FIG. 7 shows an example of the configuration of a data processing system 410 according to the fourth embodiment.

[1282] 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.

[1283] 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).

[1284] 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.

[1285] 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.

[1286] 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).

[1287] 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.

[1288] 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.

[1289] 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.

[1290] 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.

[1291] 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.

[1292] 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.

[1293] 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."

[1294] This invention is a system for supporting employee career development, which links generative AI with employee-related data to efficiently and effectively propose career paths. Specifically, the server, terminals, and users work together to provide career development support optimized for each employee.

[1295] System configuration and operation

[1296] The server retrieves employee profile information, past project history, evaluation data, and skill sets from the database, thereby collecting data on the employee's current and past performance.

[1297] The terminal provides an interface for employees to input their career aspirations and goals. Users (employees) can use the terminal to input their intentions and goals into the system.

[1298] The server trains a generative AI model based on the collected data. This training process involves cleansing the data and pre-processing it to convert it into a format suitable for the AI ​​model, enabling it to generate highly accurate career paths.

[1299] Using trained generation AI, the server generates advice for optimal career paths and skill development for each employee. For example, it may suggest that "Employee A should take training to improve his project management skills over the next three months. It is also recommended that he try for a new project manager position in the future."

[1300] The terminal provides an interface that presents the generated career path and advice to the employee, allowing the user (employee) to confirm a specific career development plan.

[1301] Users (employees) can enter their feedback on the career paths and advice presented to them through their terminals. An example of the feedback they can enter is, "Project management training is appropriate, but I would like to gain more experience before taking on the new project manager position."

[1302] The server analyzes the collected feedback and performs re-training to further improve the accuracy of the generative AI model, thereby providing continuously optimized career paths.

[1303] Specific examples

[1304] Characters:

[1305] User: Employee A

[1306] server

[1307] Terminal

[1308] 1. Data Acquisition:

[1309] The server retrieves employee A's profile information (age, job title, years of service), past project history (project name, role, results), evaluation data (supervisor evaluation, feedback from colleagues), and skill set (programming languages, management skills) from the database.

[1310] 2. Enter your career aspirations and goals:

[1311] The terminal provides an interface for employee A to input his / her career aspirations and goals. The user (employee A) inputs "I want to improve my project management skills."

[1312] 3. Career path generation and presentation:

[1313] The server uses generative AI to generate a career path that reads, "Take training to improve your project management skills over the next three months and try for a new project manager position."

[1314] The terminal presents this career path to employee A.

[1315] 4. Gather and incorporate feedback:

[1316] The user (Employee A) enters feedback such as, "The training is suitable, but I would like to gain more experience before trying for a managerial position."

[1317] The server analyzes this feedback and performs re-training to improve the accuracy of the generative AI model.

[1318] This will create a system that provides employee A with the optimal career path and effectively supports individual career development.

[1319] The processing flow will be explained below.

[1320] Step 1:

[1321] The server retrieves employee profile information, past project history, evaluation data, and skill sets from the company's database.

[1322] Step 2:

[1323] The terminal provides an interface for employees to input their career aspirations and goals. Users (employees) use the terminal to input their career aspirations and goals.

[1324] Step 3:

[1325] The server cleanses the acquired data and performs preprocessing to fill in any invalid data or missing values, thereby preparing the data in a format suitable for training the AI ​​model.

[1326] Step 4:

[1327] The server uses the preprocessed data to create a training dataset and trains the generative AI model. Training is the process of extracting career development trends and patterns based on employee profile data.

[1328] Step 5:

[1329] The server uses the trained generative AI model to generate advice for optimal career paths and skill development for each employee. For example, it may generate a suggestion such as, "Employee A is recommended to take training to improve his project management skills over the next three months."

[1330] Step 6:

[1331] The terminal provides an interface for presenting the generated career path and advice to the employee, who then confirms the presented career path and advice.

[1332] Step 7:

[1333] Users (employees) can input their feedback on career paths and advice through terminals. For example, they can input feedback such as, "The training is good, but the project manager position is too early."

[1334] Step 8:

[1335] The server stores the collected feedback in a database and performs analysis to evaluate the performance of the generative AI model and identify areas for improvement.

[1336] Step 9:

[1337] The server retrains the generative AI model based on the feedback, further improving the accuracy of career paths and advice.

[1338] Step 10:

[1339] The terminal again presents the improved career path and advice to the employee, who can then review the new suggestions and provide feedback again.

[1340] By repeating the above steps, career development support optimized for each employee can be continuously provided.

[1341] Example 1

[1342] 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."

[1343] Employee career development is an important issue for companies, but it is extremely difficult to create an optimized career path for each employee and provide support tailored to their individual skills and goals. Furthermore, there is a lack of systems that efficiently incorporate feedback from employees and continuously optimize their career paths. The present invention aims to solve these problems and provide an efficient and effective system for promoting employee career development.

[1344] 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.

[1345] In this invention, the server includes a data acquisition means, a means for acquiring employee profile information, past project history, evaluation data, and skill sets, an interface means for inputting employee career aspirations and goals, a means for training a generative AI model based on the acquired data, a means for generating optimal career paths and advice for skill development for each employee using the trained generative AI, a means for presenting the generated career paths and advice to employees, a means for employees to input feedback on the presented career paths and advice, and a means for analyzing the collected feedback and re-training the generative AI model. This makes it possible to provide career paths optimized for each employee and continuously improve accuracy.

[1346] The "data acquisition means" is a means by which the server acquires data such as employee profile information, past project history, evaluation data, and skill sets from the database.

[1347] "Interface means" refers to input fields, forms, or other means on a terminal through which employees input their career aspirations and goals.

[1348] A "generative AI model" is an artificial intelligence model that predicts and generates optimal career paths for each employee based on large-scale data sets.

[1349] A "career path generation method" is a method that uses a trained generative AI model to generate optimal career paths and advice for skill development for each employee.

[1350] The "presentation means" refers to a means for presenting the generated career path and advice to employees, specifically, a screen display function of a terminal.

[1351] The "feedback input means" is a means for employees to input their opinions and requests regarding the career paths and advice presented to them.

[1352] The "relearning means" is a means for analyzing collected feedback and conducting re-learning to improve the accuracy of the generative AI model.

[1353] This invention is a system for supporting employee career development, which proposes career paths efficiently and effectively by linking generative AI with employee-related data. Specifically, the system realizes career development support optimized for each employee by having the server, terminals, and users function in cooperation with each other.

[1354] System configuration and operation

[1355] The server has functions such as a data acquisition means, a means for learning and relearning the generated AI model, a means for generating a career path, and a means for presenting the career path.

[1356] Data Acquisition Method

[1357] The server has a means to retrieve information from the database, such as employee profile information (age, job title, years of service), past project history (project name, role, results), evaluation data (supervisor evaluation, feedback from colleagues), skill set (programming language, management ability), etc. For example, the server uses SQL queries to retrieve the required information from the database.

[1358] Generative AI models and learning methods

[1359] The server trains a generative AI model based on the collected data. In this training process, data cleansing (e.g., removing duplicate data, filling in missing data) and preprocessing (standardizing and normalizing data) are performed, and then the data is input into an AI model (e.g., BERT or GPT-3) for training.

[1360] Career path generation method

[1361] Using trained generation AI, the server generates optimal career paths and advice for skill development for each employee. For example, for Employee A, a specific career path would be generated such as, "It is recommended that you take training to improve your project management skills over the next three months. It is recommended that you try for a new project manager position in the future."

[1362] Presentation means

[1363] The career paths and advice generated by the server are presented to employees via their terminals. The terminals receive the information from the server and display it on their screens, allowing employees to check specific career development plans.

[1364] Feedback input and re-learning methods

[1365] Employees (users) enter feedback on the presented career paths and advice through their terminals. For example, they may say, "The training is appropriate, but I would like to gain more experience before taking on a managerial position." The server analyzes this feedback and performs re-training to improve the accuracy of the generative AI model. This re-training gives the system the ability to continuously provide optimized career paths.

[1366] Specific examples

[1367] Characters:

[1368] User: Employee A

[1369] server

[1370] Terminal

[1371] 1. Data Acquisition

[1372] The server retrieves data such as employee A's profile information, past project history, evaluation data, and skill set from the database.

[1373] 2. Enter your career aspirations and goals

[1374] The terminal provides an interface for Employee A to input his / her career aspirations and goals. Employee A inputs, "I want to improve my project management skills."

[1375] 3. Creating and presenting career paths

[1376] The server uses generative AI to generate career paths such as "Take training to improve your project management skills over the next three months and try for a new project manager position."

[1377] The terminal presents this career path to employee A.

[1378] 4. Gather and incorporate feedback

[1379] The user (Employee A) enters feedback into the terminal, saying, "The training is appropriate, but I would like to gain more experience before trying for a managerial position."

[1380] The server analyzes this feedback and performs re-training to improve the accuracy of the generative AI model.

[1381] Prompt Sentence Examples

[1382] "Generate a suitable career path for Employee A based on their profile information and project history."

[1383] The flow of the identification process in the first embodiment will be described with reference to FIG.

[1384] Step 1:

[1385] Data Acquisition

[1386] The server retrieves data from the database, such as employee profile information, past project history, evaluation data, and skill sets.

[1387] Input: Employee ID and database credentials

[1388] Data processing: The process of issuing an SQL query to retrieve the relevant employee data.

[1389] Output: A dataset containing information about each employee

[1390] Specific behavior: Executes an SQL query such as SELECT FROM employee_data WHERE employee_id = 'A123'.

[1391] Step 2:

[1392] Enter your career aspirations and goals

[1393] The terminal provides an interface for employees to input their career aspirations and goals.

[1394] Input: Employee's career aspirations and goals (e.g., "I want to improve my project management skills")

[1395] Data processing: Convert the input hopes and goals into a specific format and send it to the server

[1396] Output: Preferences and goals sent to the server

[1397] Specific operation: The employee enters their request into the input field on the terminal and presses the send button.

[1398] Step 3:

[1399] Training generative AI models

[1400] The server trains a generative AI model based on the collected data.

[1401] Inputs: Employee profile information, past project history, evaluation data, skill sets

[1402] Data processing: Perform preprocessing such as data cleansing (removal of duplicate data, filling in missing data), standardization and normalization of data

[1403] Output: A trained generative AI model

[1404] What it does: Cleanses data and converts it into a format suitable for AI models to run the learning process.

[1405] Step 4:

[1406] Career path creation

[1407] The server uses trained generative AI to generate the optimal career path for each employee.

[1408] Input: trained generative AI model, employee data

[1409] Data Computing: Generative AI models generate career paths using employee data as input

[1410] Output: Generated career path and advice (e.g., "It is recommended that you take training to improve your project management skills in the next three months")

[1411] How it works: Employee data is fed into a generative AI model to generate career paths.

[1412] Step 5:

[1413] Providing career paths

[1414] The terminal then presents the generated career path and advice to the employee.

[1415] Input: Career path data sent from the server

[1416] Data processing: Converts career path data into a display format and displays it on the terminal screen

[1417] Output: Screen display to employees (e.g., specific career development plans are displayed)

[1418] Specific operation: Display career path on the device screen.

[1419] Step 6:

[1420] Collecting feedback

[1421] The user inputs feedback on the presented career path and advice via the terminal.

[1422] Input: Employee feedback (e.g., "The training was appropriate, but I would like to gain more experience before taking on a managerial position.")

[1423] Data processing: The feedback content is converted into a specific format and sent to the server.

[1424] Output: Feedback data sent to the server

[1425] Specific actions: Enter feedback into the input field on the device and press the send button.

[1426] Step 7:

[1427] Reflecting feedback

[1428] The server analyzes the collected feedback and retrains the generative AI model.

[1429] Input: Employee feedback data

[1430] Data computation: Analyze the feedback data and provide it as new data points to the generative AI model for retraining.

[1431] Output: An updated generative AI model

[1432] Specific operation: A re-learning process is performed based on feedback data to improve the accuracy of the generative AI model.

[1433] (Application example 1)

[1434] 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."

[1435] Existing career development support systems suggest career paths based on employee profile information and evaluation data, but this alone makes it difficult to provide specific advice optimized for each employee. Furthermore, the means by which employees can provide feedback are limited, making continuous optimization difficult and preventing effective linkage to actual work and skill development in the workplace. Furthermore, the lack of an interface that can be used immediately in the workplace tends to reduce employees' motivation and involvement in their career development.

[1436] 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.

[1437] In this invention, the server includes means for acquiring employee profile information, past project history, evaluation data, and skill sets, interface means for inputting employee career aspirations and goals, and means for training a generative AI model based on the acquired data. This allows the generative AI model to be trained based on the acquired data, and the trained generative AI can be used to generate optimal career paths and advice for skill development for each employee, which can then be presented via a touchscreen or voice recognition system. By analyzing feedback collected using the feedback input means and retraining the generative AI model, this system can provide continuously optimized career paths and efficiently support employees' career development.

[1438] A "data acquisition means" is a device or system for collecting and managing information about employees.

[1439] "Profile information" refers to basic information such as an employee's age, position, and years of service.

[1440] "Past project history" is data that records the names, roles, results, etc. of projects that employees have participated in.

[1441] "Evaluation data" is information that includes the results of evaluations of an employee's work by their superiors and colleagues.

[1442] A "skill set" refers to the list of skills and abilities that an employee possesses.

[1443] An "interface means" is a device or system through which employees input their career aspirations and goals.

[1444] A "generative AI model" is a model that uses artificial intelligence technology to generate advice for optimal career paths and skill development based on employee data.

[1445] A "career path" is a path that shows employees the steps they should aim for and the goals they should achieve.

[1446] A "touch screen" is a type of display device that can be operated by directly touching the screen.

[1447] A "speech recognition system" is a device or system that analyzes and converts spoken input into text or commands.

[1448] "Feedback" refers to the opinions and suggestions that employees provide regarding the career path or advice presented to them.

[1449] "Retraining" is the process of incorporating new data, such as collected feedback, into a generative AI model.

[1450] System configuration and operation

[1451] This invention is a system for supporting employee career development through factory robots. Specifically, a server, factory robots, and employees (users) work together to provide optimized career development support.

[1452] Hardware Configuration

[1453] Server: Manages databases and trains generative AI models.

[1454] Factory robots: Equipped with touchscreens and voice recognition systems, they act as an interface with employees. Examples include FANUC robotic arms and devices with touchscreens.

[1455] Employees (users): Use the system to enter their career aspirations and goals.

[1456] Software Configuration

[1457] Generative AI model: Built using TensorFlow and Keras, this AI model learns from employee data and generates advice on optimal career paths and skill development.

[1458] Database management system: MySQL is used to manage employee profile information, past project history, evaluation data, and skill sets.

[1459] Speech Recognition System: Uses Google Cloud Speech-to-Text to convert employee voice input into text.

[1460] Programming language: Python is used for data processing and implementing AI models.

[1461] Explanation of program processing

[1462] The server retrieves employee profile information, past project history, evaluation data, and skill sets from the database, thereby gathering data on the employee's current and past performance.

[1463] The factory robots provide an interface for employees to input their career aspirations and goals, which are then sent to a server via a touchscreen or voice recognition system.

[1464] The server trains a generative AI model based on the collected data, cleansing the data and performing preprocessing to convert it into a format suitable for the AI ​​model, thereby enabling the generation of highly accurate career paths.

[1465] Using trained generation AI, the server generates advice for optimal career paths and skill development for each employee. For example, it might suggest, "Employee A is recommended to take training to improve his project management skills over the next three months. It would also be advisable for him to try for a new project manager position in the future."

[1466] The factory robot will then present the generated career paths and advice to employees, who can then view specific career development plans via a touchscreen or voice assistant.

[1467] Employees can use the factory robot to provide feedback on the career paths and advice presented to them, such as, "Project management training is appropriate, but I would like to gain more experience before taking on the new project manager position."

[1468] The server analyzes the collected feedback and retrains the generative AI model, allowing it to provide continuously optimized career paths.

[1469] Specific examples

[1470] Characters:

[1471] Employee A

[1472] server

[1473] Factory Robots

[1474] 1. Data Acquisition:

[1475] The server retrieves employee A's profile information (age, job title, years of service), past project history (project name, role, results), evaluation data (supervisor evaluation, feedback from colleagues), and skill set (programming languages, management skills) from the database.

[1476] 2. Enter your career aspirations and goals:

[1477] The factory robot provides an interface for Employee A to input his / her career aspirations and goals. Employee A inputs, "I want to improve my project management skills."

[1478] 3. Career path generation and presentation:

[1479] The server uses generative AI to generate a career path that reads, "Take training to improve your project management skills over the next three months and try for a new project manager position."

[1480] The factory robot presents this career path to employee A.

[1481] 4. Gather and incorporate feedback:

[1482] Employee A provides feedback saying, "The training is suitable, but I would like to gain more experience before taking on a managerial position."

[1483] The server analyzes this feedback and performs re-training to improve the accuracy of the generative AI model.

[1484] Example prompt sentence:

[1485] INSERT INTO employee_data (name, age, role, skills, past_projects, evaluations) VALUES ('Employee A', 34, 'Line Manager', 'Production Management, Quality Control', 'Project X, Project Y', 'Supervisor rating: 4.5, Peer rating: 4.0')

[1486] This system makes it possible to provide employee A with the optimal career path and effectively support his or her individual career development.

[1487] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[1488] Step 1:

[1489] The server retrieves employee profile information, past project history, evaluation data, and skill sets from the database. Based on this input data, an initial dataset regarding the employee's current status and past performance is created. Specifically, MySQL is used to retrieve the necessary information from the database using SQL queries, and the information is converted into a data frame using Python's pandas library.

[1490] Step 2:

[1491] The terminal (factory robot) provides an interface for employees to input their career aspirations and goals. Specifically, it accepts input from employees (e.g., "I want to improve my project management skills") using a touchscreen or voice recognition system. This input data is sent to the server via an HTTP request.

[1492] Step 3:

[1493] The server receives employee input data and integrates it with previously collected profile information and evaluation data. It trains a generative AI model based on this integrated dataset. It cleans the data and performs preprocessing to convert it into a format suitable for the AI ​​model. It trains the AI ​​model using TensorFlow or Keras.

[1494] Step 4:

[1495] Using trained generative AI, the server generates optimal career paths and advice for skill development for each employee. Specifically, the server inputs the employee's integrated data into the AI ​​model to generate career path candidates. The generated career path is output as a specific action plan (e.g., "We recommend that you take training to improve your project management skills in the next three months").

[1496] Step 5:

[1497] The terminal (factory robot) presents the generated career path and advice to the employee. Specifically, it displays the generated career path and advice visually or audibly via a touch screen or voice assistant, and the employee confirms the results.

[1498] Step 6:

[1499] The user (employee) enters feedback on the presented career path and advice through a terminal (factory robot). Specifically, the user enters feedback (e.g., "The training is suitable, but I would like to gain more experience before attempting a managerial position") using a touch screen or voice recognition system. This feedback data is then sent back to the server via an HTTP request.

[1500] Step 7:

[1501] The server analyzes the collected feedback and retrains the generative AI model. Specifically, the feedback data is added to the dataset, the data is cleansed, and the AI ​​model is retrained. The generative AI model, with improved accuracy through retraining, is used to generate the next career path, making it possible to provide continuously optimized career paths.

[1502] 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.

[1503] This invention is a system for supporting employee career development, which links generative AI with employee-related data and combines it with an emotion engine that recognizes user emotions to efficiently and effectively propose career paths. Specifically, by having the server, terminals, and users cooperate with each other, it realizes career development support that is optimized for each employee.

[1504] System configuration and operation

[1505] The server retrieves employee profile information, past project history, evaluation data, and skill sets from the company's database, thereby gathering data on the employee's current and past performance.

[1506] The terminal provides an interface for employees to input their career aspirations and goals, and collects this information input by the user (employee).

[1507] The server cleanses the collected data and performs preprocessing to fill in any invalid or missing values, preparing the data in a format suitable for training AI models.

[1508] The server uses the preprocessed data to create a training dataset and trains the generative AI model, which extracts career development trends and patterns based on employee profile data.

[1509] Using the trained generative AI, the server generates advice for optimal career paths and skill development for each employee. For example, a recommendation might be generated such as, "Employee A should take training to improve his project management skills over the next three months."

[1510] The terminal presents the generated career path and advice to the employee, and the user (employee) confirms the presented information.

[1511] Users (employees) can input their feedback on career paths and advice via a terminal. For example, they can input feedback such as, "The training is good, but it's too early for you to take a management position."

[1512] The server analyzes the collected feedback and performs re-training to improve the accuracy of the generative AI model, which further improves the accuracy of career paths and advice.

[1513] Introducing the Emotion Engine

[1514] Furthermore, the present invention incorporates an emotion engine that recognizes the user's emotions. The emotion engine operates as follows:

[1515] The server collects facial expression and voice data via the terminal when employees enter their career aspirations and goals, and when they confirm their career path and advice.

[1516] The emotion engine analyzes this data to recognize the user's emotional state, for example, determining whether an employee is stressed or happy.

[1517] The server adjusts the content and tone of career paths and advice based on the emotional state derived from the emotion engine, potentially offering more relaxed goals to stressed employees and more challenging goals to satisfied employees.

[1518] Users (employees) will feel more satisfied with their career path by receiving advice that is more in line with their own emotions.

[1519] Specific examples

[1520] Characters:

[1521] User: Employee A

[1522] server

[1523] Terminal

[1524] 1. Data Acquisition:

[1525] The server retrieves employee A's profile information (age, job title, years of service), past project history (project name, role, results), evaluation data (supervisor evaluation, feedback from colleagues), and skill set (programming languages, management skills) from the database.

[1526] 2. Enter your career aspirations and goals:

[1527] The terminal provides an interface for employee A to input their career aspirations and goals. The user (employee A) inputs, "I want to improve my project management skills." The emotion engine reads the emotions of employee A from their facial expressions at this time.

[1528] 3. Career path generation and presentation:

[1529] The server uses generative AI to generate a career path such as "Take training to improve your project management skills in the next three months and try for a new project manager position." It adjusts the advice to an appropriate tone, taking into account Employee A's emotional state.

[1530] The terminal presents this career path to employee A.

[1531] 4. Gather and incorporate feedback:

[1532] The user (Employee A) enters feedback such as, "The training is suitable, but I would like to gain more experience before taking on the managerial position." The user's feelings at this time are also recorded.

[1533] The server analyzes the feedback and emotional data and retrains the generative AI model.

[1534] This will create a system that provides the optimal career path for employee A and effectively supports individual career development. The introduction of an emotion engine will enable advanced career support that takes into account the emotions of employees.

[1535] The processing flow will be explained below.

[1536] Step 1:

[1537] The server retrieves employee profile information, past project history, evaluation data, and skill sets from the company's database.

[1538] Step 2:

[1539] The terminal provides an interface for employees to input their career aspirations and goals. Users (employees) use the terminal to input their career aspirations and goals.

[1540] Step 3:

[1541] The server cleanses the collected data and performs preprocessing to fill in any invalid or missing values, preparing the data in a format suitable for training AI models.

[1542] Step 4:

[1543] The server uses the preprocessed data to create a training dataset and trains the generative AI model. Training is the process of extracting career development trends and patterns based on employee profile data.

[1544] Step 5:

[1545] When an employee inputs their career aspirations and goals, the server acquires facial expression and voice data and analyzes them using an emotion engine, thereby recognizing the user's emotional state.

[1546] Step 6:

[1547] The server uses a trained generative AI model to generate optimal career paths and advice for skill development for each employee. The generated career paths and advice are adjusted taking into account the user's emotional state. For example, a recommendation might be generated such as, "Employee A is recommended to take training to improve his project management skills over the next three months."

[1548] Step 7:

[1549] The terminal provides an interface for presenting the generated career path and advice to the employee, who then confirms the presented career path and advice.

[1550] Step 8:

[1551] Users (employees) can input their feedback on career paths and advice through a terminal. For example, they can input feedback such as, "The training was good, but it's too early for you to move into a management position." Their emotional state at this time is also recorded.

[1552] Step 9:

[1553] The server analyzes the collected feedback and emotional data and performs retraining to improve the accuracy of the generative AI model, which further improves the accuracy of career paths and advice.

[1554] Step 10:

[1555] The terminal again presents the improved career path and advice to the employee, who can then review the new suggestions and provide feedback again.

[1556] By repeating the above steps, the emotional engine can be utilized to provide ongoing career development support that is optimized for each employee.

[1557] Example 2

[1558] 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."

[1559] Conventional career development support systems mainly make suggestions based on quantitative employee data, making it difficult to reflect employees' emotions and motivation. Furthermore, the generated career paths and advice are often unrealistic, limiting their ability to provide optimal support to individual employees. This can result in insufficient contribution to employee satisfaction and career advancement.

[1560] The specific processing by the specific processing unit 290 of the data processing device 12 in the second embodiment is realized by the following means.

[1561] In this invention, the server includes means for acquiring employee profile information, past project history, evaluation data, and skill sets, an interface means for inputting employee career aspirations and goals, means for acquiring user facial expression and voice data, means for cleansing the acquired data and complementing invalid data and missing values, means for training a generative AI model based on the cleansed data, means for inputting prompt sentences to the generative AI model and generating advice for career paths and skill development, means for adjusting and presenting the content of the career paths and advice generated by the generative AI model, means for employees to input feedback on the career paths and advice, and means for analyzing the collected feedback and emotion data and re-training the generative AI model. This makes it possible to provide career paths and advice optimized for each employee, reflecting the emotions and career aspirations of the employees.

[1562] "Data acquisition means" refers to means for collecting employee profile information, past project history, evaluation data, and skill sets from the company's database.

[1563] "Employee profile information" refers to basic personal information such as an employee's age, position, and years of service.

[1564] "Past project history" is data including the names, roles, and results of projects in which an employee has participated.

[1565] "Evaluation data" refers to data used to evaluate an employee's performance, including feedback from superiors and colleagues.

[1566] A "skill set" is data that specifically indicates the skills, qualifications, and special talents possessed by an employee.

[1567] "Interface means" refers to a user interface that allows employees to input their career aspirations and goals.

[1568] "Means for acquiring facial expressions and voice data" refers to means for acquiring facial expressions and voice data using a camera or microphone while an employee is using the interface.

[1569] "Data cleansing methods" are methods for organizing collected data, eliminating invalid data, and filling in missing values.

[1570] A "means for training a generative AI model" is a means for training an AI algorithm using cleansed data to train a model.

[1571] "Means for inputting prompt sentences and generating advice" refers to means for providing specific input sentences to a generative AI model and generating advice for career paths and skill development based on those sentences.

[1572] "Means for adjusting and presenting advice content" refers to a means for adjusting the advice generated by the generative AI model based on the employee's emotional data and presenting it to the employee.

[1573] "Means for inputting feedback" refers to a user interface that allows employees to input feedback on career paths and advice.

[1574] "Means for analyzing feedback and emotional data and retraining the generative AI model" refers to means for analyzing collected feedback and emotional data and retraining the generative AI model based on that data.

[1575] System program processing

[1576] This invention is a system for supporting employees' career development. The system mainly involves the cooperation of a server, terminals, and users to realize career development support optimized for each employee.

[1577] Data Acquisition

[1578] The server retrieves employee profile information, past project history, evaluation data, and skill sets from the company database using a database query such as SQL. For example, the server executes a query like this: SELECT FROM EmployeeProfile WHERE EmployeeID = 'A123';

[1579] Enter your career aspirations and goals

[1580] The device provides an interface for users (employees) to input their career aspirations and goals. This interface can be implemented as a web form or a mobile app, and displays text boxes and options for entering the required information.

[1581] The device also captures facial and voice data as users enter their career aspirations and goals using a camera and microphone. For example, the device captures facial and voice data in real time while a user types, "I want to improve my project management skills."

[1582] Data Preprocessing

[1583] The server cleanses the collected employee data and fills in any invalid data or missing values. For this, you can use the Python pandas library. For example, the server fills in missing values ​​as follows: df.fillna(method='ffill')

[1584] Training generative AI models

[1585] The server uses the preprocessed data to create a training dataset and trains a generative AI model using a generative AI framework (e.g., GPT-3 or GPT-4). The server can run the command: openai.TrainModel(data='training_data.csv')

[1586] Career path creation

[1587] The server uses trained generative AI to generate optimal career paths and advice on skill development for each employee. A specific prompt is input to the generative AI model. For example, this prompt might be something like, "What career path would you suggest for employee A?"

[1588] The generated career path is adjusted taking into account the emotional state captured by the emotion engine. For example, the server may adjust the career path based on the output of the generative AI model, such as "Employee A is feeling stressed, so the training should be short-term."

[1589] Providing career paths

[1590] The device presents the generated career path and skill development advice to the employee, which is displayed as a user interface and includes information such as specific goals and training plans.

[1591] Collecting feedback

[1592] Users (employees) can input their feedback on career paths and advice through a terminal. Text boxes and options are provided for this input. Facial expressions and voices are also recorded when inputting feedback.

[1593] Re-learning and accuracy improvement

[1594] The server analyzes the collected feedback and emotion data and retrains the generative AI model. This involves adding new data and training the AI ​​model again. For example, the server adds new feedback data and retrains it as follows: openai.TrainModel(data='updated_feedback_data.csv')

[1595] This makes it possible to reflect employees' career aspirations and feelings and provide career paths and advice that are optimized for each individual employee.

[1596] The flow of the identification process in the second embodiment will be described with reference to FIG.

[1597] System program processing flow

[1598] Step 1:

[1599] Data Acquisition

[1600] The server retrieves employee profile information, past project history, evaluation data, and skill sets from the company database. The server executes SQL queries to gather the required data. For example, the server might use a query like this: SELECT FROM EmployeeProfile WHERE EmployeeID = 'A123';

[1601] Input: Company database

[1602] Output: Employee profile information, project history, evaluation data, skill set

[1603] Step 2:

[1604] Enter your career aspirations and goals

[1605] The terminal provides an interface for users (employees) to input their career aspirations and goals. The terminal displays UI components of web forms or mobile apps to prompt users to enter the required information.

[1606] Specific behavior: Displaying text boxes and drop-down menus.

[1607] Input: User's career aspirations and goals

[1608] Output: User's career preference data

[1609] Step 3:

[1610] Acquiring facial and voice data

[1611] The device captures facial and voice data as the user enters their career aspirations and goals. The device uses a camera and microphone to capture the data.

[1612] Input: User's facial expression, voice

[1613] Output: User's facial expression data, voice data

[1614] Step 4:

[1615] Data Preprocessing

[1616] The server cleanses the collected data and imputes invalid data and missing values. For this, it uses the Python pandas library. For example, the server imputes missing values ​​as follows: df.fillna(method='ffill')

[1617] Input: Employee profile information, project history, evaluation data, skill set, career aspirations, facial expression data, voice data

[1618] Output: A cleansed dataset

[1619] Step 5:

[1620] Training generative AI models

[1621] The server uses the preprocessed data to create a training dataset and trains a generative AI model. The model is trained using a generative AI framework (e.g., GPT-3 or GPT-4). The server executes the command: openai.TrainModel(data='training_data.csv')

[1622] Input: Cleansed dataset

[1623] Output: A trained generative AI model

[1624] Step 6:

[1625] Career path creation

[1626] The server uses trained generative AI to generate optimal career paths and skill development advice for each employee. A specific prompt is given to the generative AI model to generate career path suggestions. For example, the prompt could be, "What career path would you suggest for employee A?"

[1627] Input: trained generative AI model, prompt

[1628] Output: Generated career paths and skill development advice

[1629] Step 7:

[1630] Providing and adjusting advice

[1631] The server adjusts the advice generated by the generative AI model based on the employee's emotional data and presents it to the employee via their device, softening difficult suggestions and emphasizing easy goals.

[1632] Input: Generated career paths, skill advice, sentiment data

[1633] Output: Tailored career paths, skills advice

[1634] Step 8:

[1635] Collecting feedback

[1636] The user (employee) inputs feedback on career paths and advice and sends it to the server via the terminal. The terminal also collects facial expressions and voice data.

[1637] Specific actions: Providing an input form and using the camera and microphone.

[1638] Input: Employee feedback, facial expressions, and voice data

[1639] Output: Feedback data, additional facial and voice data

[1640] Step 9:

[1641] Re-learning and accuracy improvement

[1642] The server analyzes the collected feedback and new emotion data and retrains the generative AI model based on it. This involves creating a new dataset and retraining the model. For example, the server adds new feedback data and retrains it as follows: openai.TrainModel(data='updated_feedback_data.csv')

[1643] Input: Feedback data, new facial and voice data

[1644] Output: Improved generative AI model

[1645] Following these steps will enable us to provide career paths and skills advice that are optimized for each individual employee.

[1646] (Application example 2)

[1647] 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."

[1648] Conventional career development support systems make suggestions based on employee profile information and past data, but they are unable to take into account employees' emotions and psychological state. As a result, the suggested career paths and advice may not be appropriate for employees, resulting in low satisfaction and effectiveness. Furthermore, in workplaces such as factories, there was a lack of a way to collect performance data on robots and employees in real time and propose appropriate training or role changes.

[1649] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 2 is realized by the following means.

[1650] In this invention, the server includes a data acquisition unit, a unit for acquiring employee profile information, past project history, evaluation data, and skill sets, an emotion engine for recognizing emotions, a unit for acquiring and analyzing emotional data from employees at the time of input or feedback using the emotion engine, a unit for adjusting the content and tone of career paths and advice based on the employee's emotional state, and a unit for generating optimal career paths and advice for skill development using artificial intelligence. This makes it possible to propose optimal career paths based on each employee's emotional state. Furthermore, particularly in factory settings, it is possible to collect performance data from robots and employees in real time and propose appropriate training programs and role changes.

[1651] "Data acquisition means" refers to the means for collecting necessary data such as employee profile information, past project history, evaluation data, skill sets, and emotional data.

[1652] "Profile information" refers to basic information about each employee, including age, position, years of service, etc.

[1653] A "generative AI model" is an artificial intelligence model that learns patterns based on collected employee data and generates advice for optimal career paths and skill development.

[1654] The "Emotion Engine" is a technology that acquires and analyzes the emotional data expressed by employees when entering data or providing feedback, and recognizes their emotional state.

[1655] "Feedback" refers to the reactions and opinions employees provide to the career paths and advice presented, and is used to retrain the system.

[1656] A "career path" indicates the optimal career path and direction for an employee.

[1657] A "skill set" is a collection of specialized skills and knowledge that an employee possesses, and is a list of skills necessary to perform their job.

[1658] The "interface means" is a user interface that allows employees to input their career aspirations, goals, and feedback.

[1659] This invention is a system for efficiently and effectively supporting employee career development. In particular, it aims to provide advice on optimal career paths and skill development based on performance data of employees and robots in a factory work environment. The specific configuration and operation of the system are described below.

[1660] System configuration and operation

[1661] server:

[1662] The server retrieves employee profile information, past project history, evaluation data, and skill sets from the company's database, thereby gathering data on the employee's current and past performance.

[1663] The server performs pre-processing to cleanse the collected data and fill in any invalid or missing values, preparing the data in a format suitable for training the generative AI model.

[1664] The server uses the preprocessed data to create a training dataset and trains the generative AI model, which extracts career development trends and patterns based on employee profile data.

[1665] Using the trained generative AI, the server generates advice for optimal career paths and skill development for each employee. For example, a recommendation might be generated such as, "Employee A should take training to improve his project management skills over the next three months."

[1666] Emotion Engine:

[1667] The server collects facial expression and voice data via the terminal when employees enter their career aspirations and goals, and when they confirm their career path and advice.

[1668] The emotion engine analyzes this data to recognize the employee's emotional state, for example, determining whether they are stressed or happy.

[1669] The server adjusts the content and tone of career paths and advice based on the emotional state derived from the emotion engine, potentially offering more relaxed goals to stressed employees and more challenging goals to satisfied employees.

[1670] Device:

[1671] The terminal provides an interface for employees to input their career aspirations and goals. The user (employee) inputs, "I want to improve my project management skills." The emotion engine reads the employee's emotions from their facial expressions.

[1672] The terminal presents the generated career path and advice to the employee, and the user (employee) confirms the presented information.

[1673] Users (employees) can input their feedback on career paths and advice via a terminal. For example, they can input feedback such as, "The training is good, but it's too early for you to take a management position."

[1674] Gathering feedback and relearning:

[1675] The server analyzes the collected feedback and retrains the generative AI model, further improving the accuracy of career paths and advice.

[1676] Hardware and software used

[1677] Data collection and processing uses hardware such as computers, IoT sensors, cameras, and microphones.

[1678] The software used is Python, TensorFlow, OpenCV, etc., to analyze data and build generative AI models.

[1679] Specific examples

[1680] For example, factory employee A inputs that he / she wants to improve his / her sewing machine operation skills. The generative AI model will suggest "We recommend online training on sewing machine operation in the next month," and if the emotion engine confirms that A is satisfied, it can make an additional suggestion such as "To further improve your skills, participate in actual product prototyping." An example of a prompt sentence is "We recommend training to improve sewing machine operation skills. We suggest that you participate in product prototyping as the next step."

[1681] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[1682] Step 1:

[1683] The server retrieves employee profile information, past project history, evaluation data, and skill sets from the company database. This input data includes basic employee information, project results, evaluations from superiors and colleagues, acquired skills, etc. By collecting this data, detailed information about employees' current and past performance can be obtained.

[1684] Step 2:

[1685] The server performs preprocessing to cleanse the collected data and fill in any invalid or missing values. This is done using Python libraries (e.g., Pandas, NumPy, etc.) to fill in missing values ​​and maintain data integrity. This preprocessing prepares the data in a format suitable for training generative AI models.

[1686] Step 3:

[1687] The server uses the preprocessed data to create a training dataset and trains the generative AI model. This process uses deep learning libraries such as TensorFlow and Keras to extract career development trends and patterns based on employee profile data. The input data is the preprocessed employee data, and the output is a trained generative AI model.

[1688] Step 4:

[1689] The server uses trained generative AI to generate optimal career paths and advice for skill development for each employee. Specifically, it generates a prompt for employee A such as, "We recommend training to improve your project management skills over the next three months." This input data is the trained generative AI, and the output is specific career paths and advice.

[1690] Step 5:

[1691] The server and terminals work together to provide an interface for employees to input their career aspirations and goals. The user (employee) inputs their career aspirations and goals, and the emotion engine acquires facial expression and voice data at that time. The user's emotions are recognized based on this data. The input data is the user's input information and emotional data, and the output is the recognized emotional state.

[1692] Step 6:

[1693] The terminal presents the generated career path and advice to the employee, who then confirms the information. The emotion engine recognizes the user's emotional state and adjusts the career path and advice. The input data are the generated career path and advice, as well as emotional data, and the output is the adjusted career path and advice.

[1694] Step 7:

[1695] Users (employees) input their feedback on career paths and advice via a terminal. For example, they might say, "The training is good, but I'd like to gain more experience before taking on a management position." This input data is feedback information, and emotional data is also recorded.

[1696] Step 8:

[1697] The server analyzes the collected feedback and retrains the generative AI model. In this process, the feedback data and emotion data are analyzed and retrained to improve the accuracy of the generative AI model. The input data is the feedback data and emotion data, and the output is an updated generative AI model. This further improves the accuracy of career paths and advice.

[1698] 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.

[1699] 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.

[1700] 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.

[1701] 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.

[1702] FIG. 9 is a diagram illustrating an emotion map 400 on which multiple emotions are mapped. In the emotion map 400, emotions are arranged in concentric circles radiating from the center. Emotions closer to the center of the concentric circles are more primitive. Emotions representing states and actions arising from a state of mind are arranged on the outer edges of the concentric circles. The concept of emotion includes both affect and mental states. Emotions generally generated from reactions occurring in the brain are arranged on the left side of the concentric circles. Emotions generally induced by situational judgment are arranged on the right side of the concentric circles. Emotions generally generated from reactions occurring in the brain and induced by situational judgment are arranged on the upper and lower sides of the concentric circles. Furthermore, the emotion of "pleasure" is arranged on the upper side of the concentric circles, and the emotion of "discomfort" is arranged on the lower side. In this way, in the emotion map 400, multiple emotions are mapped based on the structure by which emotions are generated, and emotions that tend to occur simultaneously are mapped close to each other.

[1703] 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.

[1704] 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).

[1705] 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.

[1706] 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."

[1707] 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.

[1708] 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).

[1709] 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.

[1710] 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.

[1711] 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.

[1712] 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.

[1713] 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.

[1714] 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.

[1715] 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.

[1716] 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.

[1717] 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.

[1718] 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.

[1719] The following is further disclosed regarding the above embodiment.

[1720] (Claim 1)

[1721] A data acquisition means;

[1722] A means to obtain employee profile information, past project history, evaluation data, and skill sets;

[1723] An interface for inputting employees' career aspirations and goals,

[1724] A means of training a generative AI model based on the acquired data; and

[1725] A means to generate optimal career paths and skill development advice for each employee using trained generative AI,

[1726] A means to present the generated career paths and advice to employees,

[1727] A way for employees to provide feedback on the career paths and advice presented to them;

[1728] A means for analyzing the collected feedback and retraining the generative AI model; and

[1729] A system including:

[1730] (Claim 2)

[1731] The system of claim 1, characterized in that the generative AI model extracts trends and patterns related to career development based on employee data.

[1732] (Claim 3)

[1733] The system of claim 1, characterized in that the dataset used to train the generative AI model includes individual employee profile data and corresponding examples of successful career development.

[1734] "Example 1"

[1735] (Claim 1)

[1736] A data acquisition means;

[1737] A means to capture employee profile information, past project history, evaluation data, and skill sets;

[1738] An interface for inputting employees' career aspirations and goals;

[1739] A means of training a generative AI model based on the acquired data; and

[1740] A means to generate optimal career paths and skill development advice for each employee using trained generative AI, and

[1741] A means to present the generated career paths and advice to employees;

[1742] A means for employees to provide feedback on the career paths and advice presented to them;

[1743] A means for analyzing the collected feedback and retraining the generative AI model; and

[1744] A system including:

[1745] (Claim 2)

[1746] The system of claim 1, wherein the generative AI model extracts trends and patterns related to career development based on employee data.

[1747] (Claim 3)

[1748] The system of claim 1, characterized in that the dataset used to train the generative AI model includes individual employee profile data and corresponding examples of successful career development.

[1749] "Application Example 1"

[1750] (Claim 1)

[1751] A data acquisition means;

[1752] A means to obtain employee profile information, past project history, evaluation data, and skill sets;

[1753] An interface for inputting employees' career aspirations and goals,

[1754] A means of training a generative AI model based on the acquired data; and

[1755] A means to generate optimal career paths and skill development advice for each employee using trained generative AI,

[1756] a means of presenting career paths and advice generated via a touchscreen or voice recognition system;

[1757] A way for employees to provide feedback on the career paths and advice presented to them;

[1758] A means for analyzing the collected feedback and retraining the generative AI model; and

[1759] A system including:

[1760] (Claim 2)

[1761] The system of claim 1, characterized in that the generative AI model extracts trends and patterns related to career development based on employee data.

[1762] (Claim 3)

[1763] The system of claim 1, characterized in that the dataset used to train the generative AI model includes individual employee profile data and corresponding examples of successful career development.

[1764] "Example 2: Combining Emotion Engines"

[1765] (Claim 1)

[1766] A data acquisition means;

[1767] A means to obtain employee profile information, past project history, evaluation data, and skill sets;

[1768] An interface for inputting employees' career aspirations and goals,

[1769] A means for acquiring facial expression and voice data of a user;

[1770] A means to cleanse the acquired data and fill in invalid data and missing values,

[1771] A means of training a generative AI model based on the cleansed data; and

[1772] A means to input prompts into the generative AI model to generate advice for career paths and skill development;

[1773] A means to adjust and present the career paths and advice generated by the generative AI model;

[1774] A way for employees to input feedback on career paths and advice;

[1775] A means to analyze the collected feedback and emotion data and retrain the generative AI model;

[1776] A system including:

[1777] (Claim 2)

[1778] The system of claim 1, characterized in that the generative AI model extracts trends and patterns related to career development based on employee data and reflects data from the emotion engine.

[1779] (Claim 3)

[1780] The system of claim 1, characterized in that the dataset used to train the generative AI model includes profile data and emotional data for individual employees, as well as corresponding examples of successful career development.

[1781] "Application example 2 when combining emotion engines"

[1782] (Claim 1)

[1783] A data acquisition means;

[1784] A means to obtain employee profile information, past project history, evaluation data, and skill sets;

[1785] An interface for inputting employees' career aspirations and goals,

[1786] A means of training a generative AI model based on the acquired data; and

[1787] A means to generate optimal career paths and skill development advice for each employee using trained generative AI,

[1788] A means to present the generated career paths and advice to employees,

[1789] A way for employees to provide feedback on the career paths and advice presented to them;

[1790] A means for analyzing the collected feedback and retraining the generative AI model; and

[1791] An emotion engine that recognizes emotions,

[1792] A means for acquiring and analyzing emotional data at the time of employee input or feedback using an emotion engine;

[1793] a way to tailor the content and tone of career paths and advice based on emotional states;

[1794] A system including:

[1795] (Claim 2)

[1796] The system of claim 1, wherein the generative AI model extracts trends and patterns related to career development based on employee data and further fine-tunes the feedback using an emotion engine.

[1797] (Claim 3)

[1798] The system described in claim 1, characterized in that the dataset used to train the generative AI model includes successful career development examples corresponding to individual employee profile data, and further uses emotional data. [Explanation of symbols]

[1799] 10, 210, 310, 410 Data Processing Systems 12 Data Processing Device 14 Smart Devices 214 Smart Glasses 314 Headset-type terminal 414 Robot< / url:> < / url:> < / url:> < / url:>

Claims

1. A data acquisition means; A means to obtain employee profile information, past project history, evaluation data, and skill sets; An interface for inputting employees' career aspirations and goals, A means of training a generative AI model based on the acquired data; and A means to generate optimal career paths and skill development advice for each employee using trained generative AI, A means to present the generated career paths and advice to employees, A way for employees to provide feedback on the career paths and advice presented to them; A means for analyzing the collected feedback and retraining the generative AI model; and A system including:

2. The system of claim 1, wherein the generative AI model extracts trends and patterns related to career development based on employee data.

3. The system of claim 1, wherein the dataset used to train the generative AI model includes individual employee profile data and corresponding examples of successful career development.

Images