System

Abstract

A system is provided.SOLUTION: A system comprising: means for inputting data regarding skill sets, work experience, and interests / orientations of individual employees; data storage means for storing the data; generation means for analyzing the stored data and generating customized career plans and skill development recommendations based on industry trends; providing means for providing the generated recommendations to the employees; and feedback collection means for collecting feedback on the recommendations and improving the generation means.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 face a lack of support for employee career development and skill improvement, making it difficult for employees to find optimal growth opportunities. Furthermore, it is difficult to provide customized career advice to each employee, and information is scattered, preventing effective career planning. With the spread of remote work, demand for virtual support is increasing, but current systems are unable to adequately meet this demand. Therefore, there is a need for methods to improve employee motivation and achieve effective career development. [Means for solving the problem]

[0005] To solve the above problems, the present invention provides the following means. First, a means is provided for individual employees to input data regarding their skill sets, work history, interests, and inclinations. Next, a data storage means is provided for storing this data. Next, a generation means is provided for analyzing the stored data and generating customized career plans and skill improvement proposals based on industry trends. Furthermore, a provision means is provided for providing the generated proposals to employees. Finally, a feedback collection means is provided for collecting feedback on the proposals and improving the generation means.

[0006] This method allows employees to receive career advice tailored to their needs, and the company as a whole can effectively support their career development. Furthermore, by analyzing the data using natural language processing models, more accurate suggestions can be made. Furthermore, the suggestions are provided simultaneously to employees and the HR department or managers, strengthening the support system across the company.

[0007] "Employee Data" refers to the collection of information entered by individual employees about their skill sets, work history, and interests.

[0008] "Data Storage Means" means any means for temporarily or permanently retaining information, including databases and storage devices for storing employee data.

[0009] "Generation Means" means means, including, for example, natural language processing models and machine learning algorithms, for analyzing stored employee data and generating customized career plans and skill development recommendations.

[0010] "Delivery means" refers to means for providing the generated career plans and skill improvement proposals to employees, including, for example, a user interface and a notification system.

[0011] "Feedback collection means" refers to means for collecting feedback from employees on suggestions and using that feedback to improve the production means, including, for example, survey forms and feedback tools.

[0012] A "natural language processing model" refers to a computational model for understanding and analyzing input text data. For example, a language model using artificial intelligence falls into this category.

[0013] "Customized career planning" refers to an individually optimized career path or plan that takes into account each employee's individual skill set, work history, and interests and aspirations.

[0014] "Skill improvement suggestions" refers to information that suggests specific methods or training programs for employees to acquire new skills.

[0015] "Industry Trends" refers to information that describes current trends and demands within a particular industry, including, for example, data on technological advancements and market changes.

[0016] The "human resources department" refers to the department within a company that is responsible for employee management and career development. [Brief explanation of the drawings]

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

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

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

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

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

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

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

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

[0025] [First embodiment]

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

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

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

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

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

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

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

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

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

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

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

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

[0038] This invention provides a virtual career mentor system that utilizes generative AI to support the career development and skill improvement of corporate employees. This system supports effective career development for employees by generating and providing customized career plans and skill improvement proposals that take into account the skills, work history, and interests and inclinations of each employee.

[0039] System Configuration

[0040] 1. User data input method

[0041] Users enter information about their skill sets, work history, interests and aspirations through a company's portal site.

[0042] 2. Data storage method

[0043] The terminal transmits the data entered by the user to the server;

[0044] The server stores the received data in a database.

[0045] 3. Generation means

[0046] The server retrieves the stored data and analyzes it using a natural language processing model.

[0047] The server takes into account industry trends and the latest trends to generate customized career plans and skill improvement proposals.

[0048] 4. Means of provision

[0049] The server provides the generated career plans and offers to the user.

[0050] The server also provides the same information to the human resources department and administrators, establishing a support system across the entire company.

[0051] 5. Feedback Collection Methods

[0052] Users review the proposals and provide feedback on their satisfaction and feasibility.

[0053] The device sends the feedback to the server,

[0054] The server receives the feedback, stores it in a database, and uses it to improve the model to improve the accuracy of future proposals.

[0055] Explanation of program processing

[0056] User data input means

[0057] Users access a company's portal site and log in. They enter their skill set (e.g., Java programming, database administration), work experience (e.g., three years of software engineering experience), and interests (e.g., cloud computing).

[0058] Data storage means

[0059] The terminal transmits the user's input data to the server, which stores the data in a database, which serves as the basis for analysis by the generating means.

[0060] generation means

[0061] The server retrieves user data from the database and analyzes it using a natural language processing model (e.g., generative AI), accurately capturing the user's skill set, interests, and aspirations, and generating customized career plans and skill improvement proposals that reflect industry trends and the latest developments.

[0062] Providing means

[0063] The server provides the generated career plans and proposals to the user, and also provides the same information to the human resources department and managers to enhance support for employees in implementing the proposals.

[0064] Feedback collection methods

[0065] The user implements the provided career plans and skill improvement suggestions and provides feedback on the results. The device sends the feedback to the server, which receives it and stores it in a database. The stored feedback is used to improve the model in the future, helping to increase the accuracy of the suggestions.

[0066] Specific examples

[0067] For example, if a user is interested in data science, has Python skills, and has two years of experience as a marketing analyst, the user enters this information into the portal site, where the server stores the data and analyzes it using a natural language processing model as a generation tool.

[0068] Based on the analysis, the server generates the following suggestions:

[0069] 1. Recommended skills: Machine learning, data mining

[0070] 2. Training programs: Online courses (e.g., Coursera's machine learning course)

[0071] 3. Career Path: From Data Analyst to Data Scientist

[0072] These suggestions are notified to the user by the server and are also shared with the human resources department and managers. When the user acts on the suggestions and provides feedback on the results, the server collects the feedback and uses it to improve the accuracy of future suggestions. In this way, the system effectively supports employees' career development.

[0073] The above is an embodiment of the present invention. This invention allows employees to obtain career plans and skill improvement measures that are optimal for them, and enables companies to effectively support the career development of their employees.

[0074] The processing flow will be explained below.

[0075] Step 1:

[0076] Users log into a company's portal site and enter information about their skill set, work history, and interests.

[0077] Step 2:

[0078] The terminal transmits the data entered by the user to the server.

[0079] Step 3:

[0080] The server stores the received data in a database.

[0081] Step 4:

[0082] The server retrieves user data from the database, checks for missing data or outliers, and performs preprocessing (e.g., data normalization, consistency check) as needed.

[0083] Step 5:

[0084] The server uses natural language processing models to analyze users' skill sets, work history, and interests, and also consults external data sources on industry trends and current trends.

[0085] Step 6:

[0086] Based on the analysis results, the server generates optimal career plans and suggestions for skill improvement for the user, including recommended skill sets, appropriate training programs, and career paths.

[0087] Step 7:

[0088] The server sends the generated career plan and proposal to the user's terminal, and also sends the same information to the human resources department and managers.

[0089] Step 8:

[0090] Users review the career plans and skill development suggestions provided and provide feedback.

[0091] Step 9:

[0092] The terminal transmits the user's feedback to the server.

[0093] Step 10:

[0094] The server receives the feedback and stores it in a database, which is used to improve the model in the generator.

[0095] Step 11:

[0096] The server analyzes user feedback to refine its natural language processing model, which improves the quality of future suggestions.

[0097] Example 1

[0098] 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."

[0099] For a company's employees to effectively advance their career development and skill improvement, they need customized career plans and skill improvement proposals tailored to each individual employee. However, with conventional systems, it was difficult to effectively generate and provide such customized proposals to employees. There were also insufficient means to collect feedback from employees and improve the system. This made it impossible to efficiently support employee career development.

[0100] 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.

[0101] In this invention, the server includes: a means for inputting data regarding each employee's skill set, work history, and interests and inclinations; a data storage means for storing the data; a generation means for analyzing the stored data and generating customized career plans and skill improvement proposals based on industry trends; a provision means for providing the generated proposals to the employee; a feedback collection means for collecting feedback on the proposals and improving the generation means; and a step in which the generation means acquires the user's input data and analyzes it using a natural language processing model, and a step in which the generation means generates customized career plans and skill improvement proposals tailored to the user's skills, interests, and inclinations based on the analysis results. This makes it possible to effectively generate and provide career plans and skill improvement proposals that are optimal for each employee. This system efficiently supports employee career development and promotes the growth of the entire company.

[0102] A "skill set" is the collection of specific skills and knowledge possessed by an individual employee.

[0103] "Work history" refers to the job and work history that an employee has had up to now.

[0104] "Interests and inclinations" refer to areas in which employees are interested and their hopes and inclinations regarding their future careers.

[0105] A "means for entering data" is an interface or system through which a user enters their information.

[0106] "Data storage means" refers to a storage system or database for storing data entered by a user.

[0107] The "generation means" is a mechanism that analyzes user data and generates customized career plans and proposals for improving skills.

[0108] A "natural language processing model" is an artificial intelligence model that analyzes text data, understands its meaning, and generates responses.

[0109] "Provision means" refers to a mechanism for providing the generated career plans and proposals to users and other related parties.

[0110] The "feedback collection means" is a mechanism for collecting reactions and results to suggestions received from users and using them to improve the system.

[0111] A "generative AI model" is an artificial intelligence model that uses machine learning and deep learning to analyze data and generate responses.

[0112] A "prompt" is text that you enter into a generative AI model to elicit a specific response.

[0113] The "analysis step" is the process of acquiring user data and analyzing it using a natural language processing model.

[0114] A "customized career plan" is a career development guideline that is specifically created based on the characteristics of each individual employee.

[0115] "Skills Upgrading Suggestions" are recommended training or learning programs to enhance your current skill set.

[0116] The present invention provides a virtual career mentor system that utilizes a generative AI model to support the career development and skill improvement of company employees. An embodiment of the present invention will be described in detail below.

[0117] This system mainly consists of five main parts: user data input means, data storage means, generation means, provision means, and feedback collection means.

[0118] First, the user accesses the company's portal site and logs in by entering their ID and password on the login screen. After logging in, the user enters information about their skill set, work history, and interests and aspirations. Specifically, the user enters "Python" and "database management" as skill sets, "three years of software engineering experience" as work history, and "cloud computing" as interests and aspirations.

[0119] The device then sends the entered data to a server. The hardware used for this is a regular personal computer or smartphone, and the communication protocol is HTTPS. The server then stores the received data in a database. This database uses an SQL or NoSQL data storage system.

[0120] The server retrieves the stored data periodically or whenever new data is added. It then analyzes the data using a generative AI model. This natural language processing model uses the latest machine learning algorithms to generate customized career plans and skill development suggestions based on the user's input data. Specific examples of prompts include:

[0121] User Information

[0122] Skill set: Python, Excel

[0123] Work Experience: 2 years of experience as a marketing analyst

[0124] Interests: Data Science

[0125] Proposals to generate

[0126] Training programs to help you improve your skills

[0127] Recommended Career Path

[0128] Latest trends based on industry trends

[0129] The server provides the generated career plans and proposals to the user, who can then review the proposals on the portal site. At the same time, this information is also provided to the human resources department and managers, providing them with enhanced support when implementing the proposals.

[0130] Finally, the user implements the provided career planning and skill improvement suggestions and provides feedback on the results. Feedback content may include, for example, impressions of online courses taken or progress on acquiring new skills. The device sends this feedback to the server, which stores it in a database. This feedback data is used to improve the generative AI model and help improve the accuracy of future suggestions.

[0131] As a concrete example, if a user is interested in data science, has Python skills, and two years of experience as a marketing analyst, the server can analyze the data and generate suggestions like this:

[0132] 1. Recommended skills: Machine learning, data mining

[0133] 2. Training programs: Online courses (e.g., Coursera's machine learning course)

[0134] 3. Career Path: From Data Analyst to Data Scientist

[0135] These suggestions are notified to the user by the server and are also shared with the human resources department and managers. When the user acts on the suggestions and provides feedback on the results, the server collects the feedback and uses it to improve the accuracy of future suggestions. In this way, the system effectively supports employees' career development.

[0136] The flow of the identification process in the first embodiment will be described with reference to FIG.

[0137] Step 1:

[0138] A user accesses a company's portal site and logs in. First, the user enters their ID and password for authentication. Next, they move to a data entry form on the site and enter their skill set (e.g., "Python," "database management"), work experience (e.g., "3 years of software engineering experience"), and interests and aspirations (e.g., "cloud computing"). This input data becomes the basis for subsequent processing.

[0139] Input: User-entered information about skill sets, work history, interests, and aspirations.

[0140] Output: The input data is stored on the device.

[0141] Step 2:

[0142] The device sends the user's input data to the server. Specifically, the input data is sent using the HTTPS protocol. At this time, the sent data includes the user's skill set, work history, and interests and inclinations. The sent data is then analyzed and stored on the server.

[0143] Input: Data entered by the user into the terminal.

[0144] Output: Data sent from the device to the server.

[0145] Step 3:

[0146] The server stores the received data in a database. This storage process uses a storage system (e.g., SQL database, NoSQL database). Once the data has been saved, a confirmation message is sent back to the device.

[0147] Input: Data sent from the terminal.

[0148] Output: The data stored in the database, and a confirmation message.

[0149] Step 4:

[0150] The server retrieves the stored data periodically or when new data is added, and analyzes it using a generative AI model. This analysis uses a natural language processing model. The input prompts for the generative AI model are as follows:

[0151] User Information

[0152] Skill set: Python, Excel

[0153] Work Experience: 2 years of experience as a marketing analyst

[0154] Interests: Data Science

[0155] Proposals to generate

[0156] Training programs to help you improve your skills

[0157] Recommended Career Path

[0158] Latest trends based on industry trends

[0159] Based on these prompts, the generative AI model generates customized career plans and skill development suggestions that match the user's skills, interests, and aspirations.

[0160] Input: User data stored in a database, prompts to the generative AI model.

[0161] Output: Career plan and skill improvement suggestions generated from the generative AI model.

[0162] Step 5:

[0163] The server provides the generated career plans and proposals to users, who can then view the proposals on a portal site. The same information is also provided to the human resources department and managers. This process strengthens the support system for employees when implementing the proposals.

[0164] Input: Career plans and recommendations generated from a generative AI model.

[0165] Output: Career plans and proposals provided to users, HR departments and managers.

[0166] Step 6:

[0167] Users implement the provided career planning and skill improvement suggestions and provide feedback on the results, such as their impressions of an online course they took or their progress in acquiring new skills. The device then sends this feedback to the server, which stores it in a database. The collected feedback data is used to improve the generative AI model and help refine future suggestions.

[0168] Input: Feedback data from users.

[0169] Output: Feedback data sent to the server and stored in the database.

[0170] In this way, the overall processing steps of the present system are linked, making it possible to continuously support employees' career development.

[0171] (Application example 1)

[0172] 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."

[0173] In modern factories, robots handle many work tasks, but improving the robots' performance and skills still relies on manual adjustment and management. This management method is inefficient and makes it difficult to optimize robot utilization. Furthermore, it is difficult to provide learning plans to reduce robot errors and improve work efficiency. This hinders improvements in work efficiency and productivity throughout the factory.

[0174] 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.

[0175] In this invention, the server includes means for inputting work task data and performance data of each robot, data storage means for storing the data, generation means for analyzing the stored data and generating customized learning plans and proposals for improving work efficiency based on the work efficiency of the factory, provision means for providing the generated proposals to the robot, and feedback collection means for collecting feedback on the proposals and improving the generation means. This automates the performance improvement and skill development of robots, making it possible to improve the work efficiency and productivity of the entire factory.

[0176] "Individual robot" refers to a piece of automated equipment designed to perform a specific work task within a factory.

[0177] "Work task data" refers to data including specific information about each task performed by a robot, such as the work content, procedures, and usage time.

[0178] "Performance data" refers to data that indicates the results and efficiency of work tasks performed by a robot, and includes, for example, the time it takes to complete a task, the error rate, and the availability rate.

[0179] "Data storage means" refers to a device or system for storing work task data and performance data transmitted from a robot.

[0180] "Generation means" refers to a device or system that generates suggestions for improving the efficiency and skills of a robot based on stored data.

[0181] "Providing means" refers to a device or system for notifying the robot and the administrator of the generated learning plan and suggestions for improving work efficiency.

[0182] "Feedback collection means" refers to a device or system for collecting results and reactions after the robot implements the provided suggestions.

[0183] The system of the present invention automates the improvement of the efficiency and skill of robots operating in factories. The specific implementation procedure is shown below.

[0184] <System Program>

[0185] This system is configured using the following hardware and software.

[0186] 1. Hardware:

[0187] Robots (industrial and collaborative robots): handle individual work tasks and collect performance data.

[0188] Built-in sensors: Collect real-time robot behavior and performance data.

[0189] Management server: Stores data, analyzes it, and generates proposals.

[0190] 2. Software:

[0191] Database system (e.g. MySQL, PostgreSQL): Stores robot work task data and performance data.

[0192] Generative AI models (e.g., GPT-3, BERT): Analyze robot data and generate customized learning plans and suggestions.

[0193] Robot control software (e.g. ROS): manages the robot's movements and executes the proposed plan.

[0194] Using the above hardware and software, the system operates as follows.

[0195] <System Operation>

[0196] 1. Data entry method

[0197] While the robot is performing a task, it uses built-in sensors to collect task data (e.g., part type, assembly time) and performance data (e.g., error rate, task time) in real time. This data is then sent to the management server via the terminal.

[0198] 2. Data storage method

[0199] The management server stores the received work task data and performance data in a database, thereby accumulating historical data on the robot.

[0200] 3. Generation means

[0201] The management server retrieves the robot's stored data from the database and analyzes it using the generative AI model. Based on the analysis results, it generates optimal learning plans and suggestions for improving operational efficiency for each robot. Examples include "learning new motion sequences to reduce error rates" and "proposing procedures to optimize work speed."

[0202] 4. Means of provision

[0203] The management server notifies the robot and the administrator of the generated learning plan and suggestions. The robot performs the task according to the proposed plan, and the administrator monitors and manages the robot's operation.

[0204] 5. Feedback Collection Methods

[0205] The robot performs the task based on the provided plan, and then collects and sends the resulting performance data and error feedback. The management server stores this in a database and uses this feedback data when generating the next proposal.

[0206] <Example>

[0207] For example, if a welding robot frequently makes errors in past data, the generative AI model will analyze the cause of the error and create a "learning plan to improve welding accuracy at a specific angle." This learning plan can then be applied to the welding robot to reduce errors.

[0208] <Example of prompt sentence for generative AI model>

[0209] "Analyze the welding robot's operation data from the past six months to identify the frequency and causes of errors, and generate a learning plan based on that."

[0210] In this way, this system allows robots in factories to constantly learn the latest, most efficient work procedures, which is expected to improve overall work efficiency.

[0211] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[0212] Step 1:

[0213] While the robot is performing a work task, it uses built-in sensors to collect work task data and performance data in real time.

[0214] Input: Sensor data about the robot's movements.

[0215] Data processing / data calculation: Formats data collected by built-in sensors and converts it into performance indicators such as error rates and task completion times.

[0216] Output: Collected work task and performance data.

[0217] Step 2:

[0218] The terminal transmits the collected data to the management server.

[0219] Input: Work task and performance data from the robot.

[0220] Data processing / data calculation: Encode the data for transmission to the management server using the appropriate communication protocol.

[0221] Output: The encoded data.

[0222] Step 3:

[0223] The server stores the received data in a database.

[0224] Input: The encoded data sent from the terminal.

[0225] Data processing / data operation: Decode the data and insert it into the database using an SQL query.

[0226] Output: Work task and performance data stored in a database.

[0227] Step 4:

[0228] The server retrieves the stored data from the database for analysis and inputs it into the generative AI model.

[0229] Input: Work task data and performance data in a database.

[0230] Data processing / data calculation: Use SQL queries to retrieve the necessary data from the database and convert it into a format suitable for the generative AI model.

[0231] Output: Analyzed data that is fed into a generative AI model.

[0232] Step 5:

[0233] The server inputs the analytical data into a generative AI model to generate a customized learning plan and suggestions for improving work efficiency.

[0234] Input: The data that is fed into the generative AI model.

[0235] Data processing / data calculation: Analyze data using a generative AI model to generate optimal learning plans and suggestions for improving work efficiency.

[0236] Output: Study plan and suggestions for improving work efficiency.

[0237] Step 6:

[0238] The server provides the generated learning plans and suggestions to the robot and the administrator.

[0239] Input: Study plans and suggestions for improving work efficiency.

[0240] Data processing / data calculation: Convert the proposal into the appropriate format and send it to the robot's control system and the administrator's monitoring system.

[0241] Output: Learning plans and suggestions provided to the robot and administrator.

[0242] Step 7:

[0243] The robot performs the task based on the provided learning plan and suggestions, and then collects the results again using its built-in sensors.

[0244] Input: Study plans and suggestions for improving work efficiency.

[0245] Data processing / data calculation: Adjust the robot's movement sequence based on suggestions and record new performance data collected by the built-in sensors.

[0246] Output: New performance data.

[0247] Step 8:

[0248] The terminals send the collected new performance data to the management server, which stores it in a database.

[0249] Input: New performance data.

[0250] Data processing / data calculation: Encode the data, send it using a protocol to send it to the management server, decode the received data, and save it back in the database.

[0251] Output: Feedback data stored in a database.

[0252] 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.

[0253] This invention provides a virtual career mentor system that combines generative AI and an emotion engine to support the career development and skill improvement of corporate employees. By considering each employee's skills, work history, and interests and inclinations, and by analyzing the user's emotions, the system generates and provides customized career plans and skill improvement proposals, thereby supporting effective career development for employees.

[0254] System Configuration

[0255] 1. User data input method

[0256] Users enter information about their skill sets, work history, and interests through a company portal site.

[0257] 2. Data storage method

[0258] The terminal transmits the data entered by the user to the server.

[0259] The server stores the received data in a database.

[0260] 3. Generation means

[0261] The server retrieves user data from the database, checks for missing data or outliers, and performs preprocessing (e.g., data normalization, consistency check) as needed.

[0262] The server uses natural language processing models to analyze the user's skill set, work history, and interests.

[0263] The server takes into account industry trends and the latest trends to generate customized career plans and skill improvement proposals.

[0264] 4. Emotion Engine

[0265] The server uses an emotion engine to analyze the user's emotion data (e.g., text input, voice, facial expressions).

[0266] The server reflects the analysis results of the emotion data in the generated career plan and skill improvement proposals.

[0267] 5. Means of provision

[0268] The server provides the generated career plans and proposals to the user, and also provides the same information to human resources and management.

[0269] 6. Feedback Collection Methods

[0270] Users review the proposals and provide feedback on their satisfaction and feasibility.

[0271] The terminal sends the feedback to the server.

[0272] The server receives and stores the feedback in a database, which is used to improve the models in the generator and emotion engine.

[0273] Explanation of program processing

[0274] User data input means

[0275] Users log in to a company's portal site and enter their skill set (e.g., Java programming, database administration), work experience (e.g., three years of software engineering experience), and interests (e.g., cloud computing).

[0276] Data storage means

[0277] The terminal sends the user's input data to the server, which then stores the data in a database for later processing.

[0278] generation means

[0279] The server retrieves user data from the database and analyzes it using a natural language processing model. This analysis accurately captures the user's skill set, interests, and inclinations, and generates customized career plans and skill improvement proposals that reflect industry trends and the latest trends.

[0280] Emotion Engine

[0281] The server uses an emotion engine to analyze the user's emotional data. For example, it analyzes the text, voice, or facial expression data entered by the user to understand the user's current emotional state. The results of this analysis are reflected in the generated career plan and skill improvement proposals. This allows the proposals to match the user's emotional state and become more personalized.

[0282] Providing means

[0283] The server provides the generated career plans and proposals to the user, and also provides the same information to the human resources department and managers, establishing a support system throughout the company.

[0284] Feedback collection methods

[0285] The user implements the provided career plan and skill improvement suggestions and provides feedback on the results. The device sends the feedback to the server, which receives it and stores it in a database. The stored feedback is used to improve the models in the emotion engine and generation means, thereby improving the quality of future suggestions.

[0286] Specific examples

[0287] For example, if a user is interested in data science, has Python skills, and has two years of experience as a marketing analyst, they can enter this information into the portal site, where the server stores the data and analyzes it using natural language processing models and sentiment engines.

[0288] Based on the analysis, the server generates the following suggestions:

[0289] 1. Recommended skills: Machine learning, data mining

[0290] 2. Training programs: Online courses (e.g., Coursera's machine learning course)

[0291] 3. Career Path: From Data Analyst to Data Scientist

[0292] These suggestions are notified to the user by the server and are also shared with the human resources department and managers. When the user acts on the suggestions and provides feedback, the server collects the feedback and uses it to improve the accuracy of future suggestions. In addition, the emotion engine performs emotional analysis of the feedback to provide more effective suggestions.

[0293] The above is an embodiment of the present invention. This invention allows employees to obtain career plans and skill improvement measures that are optimal for them, and enables companies to effectively support the career development of their employees.

[0294] The processing flow will be explained below.

[0295] Step 1:

[0296] Users log in to the company's portal site and enter their skill set (e.g., Python programming, data analysis), work experience (e.g., two years of experience as a data analyst), and interests (e.g., data science).

[0297] Step 2:

[0298] The terminal transmits data entered by the user, including the skill set, work history, and interests and preferences, to the server.

[0299] Step 3:

[0300] The server stores the received data in a database, which is used for subsequent analysis.

[0301] Step 4:

[0302] The server retrieves user data from the database, checks for missing values ​​and outliers, preprocesses the data as needed (e.g., normalizes data, checks for consistency), and prepares it for analysis.

[0303] Step 5:

[0304] The server uses natural language processing models to analyze a user's skill set, work history, and interests, and also references external data sources on industry trends and current trends, to generate customized career plans and skill development suggestions.

[0305] Step 6:

[0306] The server uses an emotion engine to analyze emotions based on the user's text input, voice, or facial expression data. For example, if the user is feeling anxious, the server considers reassuring suggestions.

[0307] Step 7:

[0308] The server then reflects the results of the emotion analysis in the generated career plans and skill improvement proposals, resulting in customized proposals that take emotion into consideration.

[0309] Step 8:

[0310] The server provides the completed career plan and proposal to the user's terminal, and also notifies the human resources department and manager of the same information to provide support.

[0311] Step 9:

[0312] Users review and implement the provided career plans and skill improvement suggestions, and then provide feedback on the satisfaction and feasibility of the suggestions.

[0313] Step 10:

[0314] The device sends user feedback to the server, which evaluates the effectiveness of the suggestions and uses it for future improvements.

[0315] Step 11:

[0316] The server receives the feedback, stores it in a database, and analyzes it to improve the accuracy of the natural language processing model and emotion engine, making future suggestions more effective and personalized.

[0317] In this way, the system comprehensively supports employees' career development and makes suggestions that take into consideration the user's feelings, thereby achieving higher satisfaction and effectiveness.

[0318] Example 2

[0319] 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."

[0320] In modern companies, employee career development and skill improvement are extremely important issues. However, it is difficult to provide customized career plans that take into account the needs and interests of individual employees. Furthermore, suggestions that ignore the employee's emotional state are often ineffective. Therefore, there is a need for a system that can comprehensively analyze employee information and emotions and provide optimal career plans and skill improvement suggestions.

[0321] The identification processing by the identification processing unit 290 of the data processing device 12 in Example 2 is realized by the following means. In this invention, the server includes: means for inputting data on each employee's skill set, work history, and interests and inclinations; data storage means for storing the data; means for preprocessing the stored data, filling in missing values, and normalizing the data; means for analyzing the preprocessed data and generating customized career plans and skill improvement proposals based on industry trends; an emotion engine for analyzing user emotion data and reflecting the results in the generated proposals; means for providing the generated proposals to the employee and also to the human resources department and manager; and means for collecting feedback on the proposals and improving the generation means. This enables the generation of customized proposals to effectively support employees' career development and skill improvement.

[0322] A "skill set" refers to the collection of skills and expertise that an individual employee possesses.

[0323] "Work history" refers to the history of the work, jobs, and roles an employee has performed to date.

[0324] "Interests and orientations" refer to the interests and goals that individual employees have regarding their work.

[0325] "Data storage means" means any device or method that securely stores data collected from employees and makes it available for subsequent processing.

[0326] "Preprocessing" refers to tasks such as filling in missing values ​​and normalizing data that are carried out before data analysis.

[0327] A "natural language processing model" refers to the algorithms and techniques that enable computers to understand and analyze human language.

[0328] An "emotion engine" refers to a technology that analyzes a user's text, voice, and facial expression data to understand their emotional state and utilize the results.

[0329] "Generation means" refers to a device or method that analyzes the stored data and generates customized career plans and skill improvement suggestions based on industry trends.

[0330] The "provision means" refers to a device or method for providing the generated proposal to the user, the human resources department, and the manager.

[0331] The term "feedback collection means" refers to a device or method that collects opinions and evaluations provided by users regarding the provided suggestions and uses them to improve the system.

[0332] This invention provides a virtual career mentoring system that combines a generative AI model and an emotion engine to support the career development and skill improvement of corporate employees. The system generates and provides customized career plans and skill improvement proposals by considering each employee's skills, work history, and interests and inclinations, and by analyzing the user's emotions.

[0333] The system components are:

[0334] User data input means

[0335] Data storage means

[0336] Pretreatment means

[0337] generation means

[0338] Emotion Engine

[0339] Providing means

[0340] Feedback collection methods

[0341] User data input means

[0342] Users log in to the company's portal site and enter their skill set (e.g., Java programming, database management), work experience (e.g., three years of software engineering experience), and interests (e.g., cloud computing). The entered data is registered in the system.

[0343] Data storage means

[0344] The terminal sends the data entered by the user to the server, which stores the received data in a database for subsequent processing.

[0345] Pretreatment means

[0346] The server retrieves user data from the database and performs preprocessing, including filling in missing values ​​and normalizing the data. For example, if there is a missing year, it is filled in with the average value and data scaling is performed.

[0347] generation means

[0348] The server uses natural language processing (NLP) models to perform detailed analysis of the user's skill set, work history, and interests and inclinations. As a result of the analysis, it accurately identifies the user's characteristics and generates a customized career plan and skill improvement proposals based on industry trends and the latest trends. For example, a user with "Python programming" skills could be recommended machine learning skills.

[0349] Emotion Engine

[0350] The server uses an emotion engine to analyze the user's emotional data (e.g., text, voice, facial expressions). For example, if a user enters, "I've been feeling unmotivated at work lately," the emotion engine will classify that state as "stress." This information is taken into account and reflected in the generated career plans and skill improvement suggestions. Specifically, relaxation methods for stress reduction can be added to the suggestions.

[0351] Providing means

[0352] The server notifies the user of the generated career plan and skill improvement proposals via a dashboard on the portal site or by email. The same information is also provided to the human resources department and managers, creating a support system across the company.

[0353] Feedback collection methods

[0354] The user provides feedback on the provided career plan and skill improvement suggestions. The feedback includes the effectiveness of the suggestions and the level of satisfaction. The device sends this feedback to the server, which stores the received feedback in a database. The stored feedback is used to improve the generation method and emotion engine model. This allows the system to improve the accuracy of future suggestions.

[0355] Specific examples

[0356] For example, let's say a user is interested in data science, has Python skills, and has two years of experience as a marketing analyst. When the user enters this information into the portal, their device sends the data to the server, where it is stored in a database. The server then performs analysis using natural language processing models and sentiment engines to generate suggestions such as:

[0357] 1. Recommended skills: Machine learning, data mining

[0358] 2. Training programs: Online courses (e.g., Coursera's machine learning course)

[0359] 3. Career Path: From Data Analyst to Data Scientist

[0360] These suggestions are notified to the user by the server and are also shared with the human resources department and managers. When the user acts on the suggestions and provides the results as feedback, the server collects this information and uses it to improve the accuracy of future suggestions. The emotion engine also analyzes the emotions in the feedback to provide even more effective suggestions.

[0361] Prompt Sentence Examples

[0362] "Analyze user-entered data and propose a customized career plan."

[0363] "Generate skill improvement suggestions that take into account user sentiment data."

[0364] The above is an embodiment of the present invention. This invention allows employees to obtain career plans and skill improvement measures that are optimal for them, and also enables companies to effectively support the career development of their employees.

[0365] The flow of the identification process in the second embodiment will be described with reference to FIG.

[0366] Step 1: User data input

[0367] A user logs in to a company's portal site. The user enters their skill set (e.g., Java programming, database administration), work experience (e.g., three years of software engineering experience), and interests (e.g., cloud computing). The entered data is temporarily stored on the device. This is the input data in step 1. The specific actions in this step are to enter data into a text form and click the submit button.

[0368] Step 2: Data transmission and storage

[0369] The terminal sends the data entered by the user to the server. During this transmission process, the data is encrypted and transmitted using a secure communication protocol (e.g., HTTPS). The server receives the received data and stores it in a database. This is the output data of step 2. The specific operations in this step are data encryption, transmission, and recording in the database.

[0370] Step 3: Preprocessing the data

[0371] The server retrieves the stored user data from the database. This retrieved data is the input data for Step 3. The server preprocesses the data. Specifically, it imputes missing values, checks consistency, and normalizes the data. For example, it imputes missing values ​​with the mean and standard-scales the numeric data. This preprocessed data is the output data for Step 3.

[0372] Step 4: Data analysis and proposal generation

[0373] The server uses the preprocessed data to run a natural language processing (NLP) model to perform a detailed analysis of the user's skill set, work history, interests, and inclinations. This is the input data for step 4. It also collects industry trends and the latest trends from the internet and analyzes them against the user's data. A generative AI model is used to generate a customized career plan and suggestions for skill improvement. This is the output data for step 4. The specific operations in this step are NLP analysis, data matching, and generation of a career plan and suggestions.

[0374] Step 5: Sentiment Data Analysis

[0375] The server obtains the user's input text, voice, and facial expression data. This is the input data for step 5. The emotion engine analyzes this data to understand the user's emotional state. For example, if the user inputs "high stress," the emotion engine identifies this state as "stress." The results of this analysis are reflected in career plans and suggestions for skill improvement. This is the output data for step 5. The specific operations in this step are emotion analysis and feedback of the results.

[0376] Step 6: Provide a proposal

[0377] The server notifies the user of the generated career plan and skill improvement suggestions. This is the input data of step 6. This notification is sent via the portal site dashboard, email, etc. The same information is also provided to the HR department and administrators. This is the output data of step 6. The specific actions in this step are the generation and distribution of notifications.

[0378] Step 7: Gather feedback

[0379] The user provides feedback on the provided career plan and skill improvement suggestions. This is the input data for step 7. The feedback includes the effectiveness of the suggestions and the level of satisfaction. The device sends this feedback to the server. The server receives the feedback and stores it in a database. The stored feedback is used to improve the generation means and emotion engine models. This is the output data for step 7. The specific operations in this step are collecting and storing feedback and improving the model.

[0380] (Application example 2)

[0381] 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."

[0382] While there are many systems that effectively support employee career development and skill improvement, they lack the ability to provide personalized suggestions that take into account employees' emotional state. This can lead to situations where employees are unmotivated or stressed by the suggestions. Furthermore, there are limited means to collect feedback and improve the quality of suggestions, making continuous improvement difficult. Another problem is that they are unable to provide information simultaneously to not only employees but also the HR department and managers, enabling efficient career support throughout the organization.

[0383] 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.

[0384] In this invention, the server includes: a means for inputting data regarding each employee's skill set, work history, and interests and inclinations; a data storage means for storing the data; a generation means for analyzing the stored data and generating customized career plans and skill improvement proposals based on industry trends; a provision means for providing the generated proposals to the employee; a feedback collection means for collecting feedback on the proposals and improving the generation means; and an emotion analysis means for analyzing the input emotional data and reflecting the results in the proposals. This allows for personalized career plans and skill improvement proposals that take employees' emotional states into account, thereby increasing employee motivation and enabling efficient career support throughout the organization. Furthermore, the collected feedback can be used to continuously improve the system and improve the quality of proposals.

[0385] A "skill set" is the collection of skills and knowledge that an employee possesses.

[0386] "Work history" refers to the history of jobs and positions that an employee has held up to now.

[0387] "Interests and orientations" refer to the areas in which employees are interested and their orientation toward the future.

[0388] "Data storage means" refers to a device or system that stores data entered by employees.

[0389] The "generation means" is a device or system that analyzes the stored data and generates customized career plans and skill improvement proposals.

[0390] The "means for providing" refers to a device or system that presents the generated career plans and skill improvement proposals to employees.

[0391] A "feedback collection tool" is a device or system that collects information by allowing employees to input their opinions and satisfaction with the suggestions provided.

[0392] An "emotion analysis means" is a device or system that analyzes emotions from employee input data and reflects the results in proposals.

[0393] A "natural language processing model" is a machine learning model for analyzing employee and industry data, and has the ability to understand and analyze natural language.

[0394] This invention relates to a virtual career mentor system for supporting employees' career development and skill improvement. This system collects data on employees' skill sets, work history, interests, and inclinations, and also analyzes their emotions to provide optimal career plans for each employee. Specifically, it has the following configuration:

[0395] 1. User data input method

[0396] Users (employees) use smartphones or web portals to input information about their skill sets, work history, interests, and aspirations. This input data is used to inform detailed career development for employees.

[0397] 2. Data storage method

[0398] The device sends the data entered by the user to a cloud server, which then stores the data in a database, such as AWS's DynamoDB.

[0399] 3. Generation means

[0400] The server retrieves the stored data and analyzes it using a natural language processing model, such as OpenAI's GPT-4, to generate customized career plans and skill development suggestions based on the user's skill set, work history, interests, and aspirations.

[0401] 4. Emotion analysis method

[0402] The server analyzes the collected emotional data (voice, text, facial expressions, etc.) from the user using an emotion analysis engine such as Azure's Emotion API to determine the user's emotional state. This allows the server to reflect the emotional data in the generated career plans and skill improvement proposals, providing more personalized proposals.

[0403] 5. Means of provision

[0404] The server provides the generated career plan and proposal to the user, and also notifies the human resources department and managers of the information, thereby establishing a support system throughout the company.

[0405] 6. Feedback Collection Methods

[0406] Users can provide feedback on the provided career plans and skill improvement suggestions. This feedback is sent to a cloud server and stored in a database. The collected feedback is used to improve the models of the generator and sentiment analyzer.

[0407] Specific examples

[0408] For example, let's say an employee has an interest in data science, Python skills, and two years of experience as a marketing analyst. When the employee enters this information into a smartphone app, the server stores the information in a database and performs analysis. Using OpenAI's GPT-4, the analysis generates the following suggestions:

[0409] 1. Recommended skills: Machine learning, data mining

[0410] 2. Training programs: Online courses (e.g., an introductory course on machine learning)

[0411] 3. Career Path: From Data Analyst to Data Scientist

[0412] At this time, emotion analysis is performed based on the voice data entered by the employee, and if the result is that "the employee is highly motivated and has a strong interest in machine learning," this result can be reflected to "assess true interest and enthusiasm in career plans and strengthen the content of advice."

[0413] Prompt Sentence Examples

[0414] (Input information)

[0415] Skill Set: Python programming, data analysis

[0416] ·Work Experience: 2 years of experience as a marketing analyst

[0417] Interests: Data science, machine learning

[0418] (emotion data)

[0419] Users are highly motivated and have a strong interest in machine learning

[0420] The above is an embodiment of the present invention. This system allows employees to obtain career plans and skill improvement measures that are best suited to them, and enables companies to effectively support the career development of their employees.

[0421] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[0422] Step 1:

[0423] A user inputs information about their skill set, work history, and interests and aspirations via a smartphone or web portal. The information entered by the user is sent from the device to the server. Specifically, it is assumed that the user inputs "Skill set: Python programming, data analysis," "Work history: 2 years of experience as a marketing analyst," and "Interests and aspirations: data science, machine learning."

[0424] Input: User's skill set, work history, interests and preferences

[0425] Output: User data sent to the server

[0426] Step 2:

[0427] The device sends the input data from the user to a cloud server, which then stores it in a database using AWS's DynamoDB or similar.

[0428] Input: User data sent to the server

[0429] Output: User data stored in the database

[0430] Step 3:

[0431] The server retrieves the stored user data and analyzes it using a natural language processing model (e.g., OpenAI's GPT-4). It then generates a customized career plan and skill improvement suggestions based on the user's skill set, work history, interests, and aspirations. Specifically, it may suggest "recommended skills: machine learning, data mining," "training program: online courses," and "career path: from data analyst to data scientist."

[0432] Input: User data retrieved from the database

[0433] Output: Generated career plans and skill improvement suggestions

[0434] Step 4:

[0435] The user provides emotional data to the server through voice or text input, such as "I am highly motivated and have a strong interest in machine learning."

[0436] Input: User's voice data, text data

[0437] Output: Emotion data sent to the server

[0438] Step 5:

[0439] The server uses Azure's Emotion API to analyze the emotional data and evaluate the user's emotional state. The results of this evaluation are reflected in the generated career plan and skill improvement proposals. For example, adjustments may be made such as "proposing a more difficult course because the user is highly motivated."

[0440] Input: Emotion data sent to the server

[0441] Output: Parsed emotional state

[0442] Step 6:

[0443] The server provides the generated career plan and proposals to the user and simultaneously notifies the human resources department and managers, and displays them via a smartphone app or web portal.

[0444] Input: Generated career plans and skill improvement suggestions, analyzed emotional states

[0445] Output: Customization suggestions provided to the user and HR department

[0446] Step 7:

[0447] Users can provide feedback on the provided career plans and proposals through a smartphone app or web portal, which is then sent to a cloud server and stored in a database.

[0448] Input: User feedback

[0449] Output: Feedback stored in a database

[0450] Step 8:

[0451] The server analyzes the collected feedback and refines the models of the generator and sentiment analyzer to improve the quality of future suggestions, which will enable suggestions that better reflect the user's needs and emotions.

[0452] Input: Feedback stored in the database

[0453] Output: Improved generative and sentiment analysis models

[0454] 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.

[0455] 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.

[0456] 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.

[0457] [Second embodiment]

[0458] FIG. 3 shows an example of the configuration of a data processing system 210 according to the second embodiment.

[0459] 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.

[0460] 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).

[0461] 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.

[0462] 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.

[0463] 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).

[0464] 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.

[0465] 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.

[0466] 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.

[0467] 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.

[0468] 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.

[0469] 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."

[0470] This invention provides a virtual career mentor system that utilizes generative AI to support the career development and skill improvement of corporate employees. This system supports effective career development for employees by generating and providing customized career plans and skill improvement proposals that take into account the skills, work history, and interests and inclinations of each employee.

[0471] System Configuration

[0472] 1. User data input method

[0473] Users enter information about their skill sets, work history, interests and aspirations through a company's portal site.

[0474] 2. Data storage method

[0475] The terminal transmits the data entered by the user to the server;

[0476] The server stores the received data in a database.

[0477] 3. Generation means

[0478] The server retrieves the stored data and analyzes it using a natural language processing model.

[0479] The server takes into account industry trends and the latest trends to generate customized career plans and skill improvement proposals.

[0480] 4. Means of provision

[0481] The server provides the generated career plans and offers to the user.

[0482] The server also provides the same information to the human resources department and administrators, establishing a support system across the entire company.

[0483] 5. Feedback Collection Methods

[0484] Users review the proposals and provide feedback on their satisfaction and feasibility.

[0485] The device sends the feedback to the server,

[0486] The server receives the feedback, stores it in a database, and uses it to improve the model to improve the accuracy of future proposals.

[0487] Explanation of program processing

[0488] User data input means

[0489] Users access a company's portal site and log in. They enter their skill set (e.g., Java programming, database administration), work experience (e.g., three years of software engineering experience), and interests (e.g., cloud computing).

[0490] Data storage means

[0491] The terminal transmits the user's input data to the server, which stores the data in a database, which serves as the basis for analysis by the generating means.

[0492] generation means

[0493] The server retrieves user data from the database and analyzes it using a natural language processing model (e.g., generative AI), accurately capturing the user's skill set, interests, and aspirations, and generating customized career plans and skill improvement proposals that reflect industry trends and the latest developments.

[0494] Providing means

[0495] The server provides the generated career plans and proposals to the user, and also provides the same information to the human resources department and managers to enhance support for employees in implementing the proposals.

[0496] Feedback collection methods

[0497] The user implements the provided career plans and skill improvement suggestions and provides feedback on the results. The device sends the feedback to the server, which receives it and stores it in a database. The stored feedback is used to improve the model in the future, helping to increase the accuracy of the suggestions.

[0498] Specific examples

[0499] For example, if a user is interested in data science, has Python skills, and has two years of experience as a marketing analyst, the user enters this information into the portal site, where the server stores the data and analyzes it using a natural language processing model as a generation tool.

[0500] Based on the analysis, the server generates the following suggestions:

[0501] 1. Recommended skills: Machine learning, data mining

[0502] 2. Training programs: Online courses (e.g., Coursera's machine learning course)

[0503] 3. Career Path: From Data Analyst to Data Scientist

[0504] These suggestions are notified to the user by the server and are also shared with the human resources department and managers. When the user acts on the suggestions and provides feedback on the results, the server collects the feedback and uses it to improve the accuracy of future suggestions. In this way, the system effectively supports employees' career development.

[0505] The above is an embodiment of the present invention. This invention allows employees to obtain career plans and skill improvement measures that are optimal for them, and enables companies to effectively support the career development of their employees.

[0506] The processing flow will be explained below.

[0507] Step 1:

[0508] Users log into a company's portal site and enter information about their skill set, work history, and interests.

[0509] Step 2:

[0510] The terminal transmits the data entered by the user to the server.

[0511] Step 3:

[0512] The server stores the received data in a database.

[0513] Step 4:

[0514] The server retrieves user data from the database, checks for missing data or outliers, and performs preprocessing (e.g., data normalization, consistency check) as needed.

[0515] Step 5:

[0516] The server uses natural language processing models to analyze users' skill sets, work history, and interests, and also consults external data sources on industry trends and current trends.

[0517] Step 6:

[0518] Based on the analysis results, the server generates optimal career plans and suggestions for skill improvement for the user, including recommended skill sets, appropriate training programs, and career paths.

[0519] Step 7:

[0520] The server sends the generated career plan and proposal to the user's terminal, and also sends the same information to the human resources department and managers.

[0521] Step 8:

[0522] Users review the career plans and skill development suggestions provided and provide feedback.

[0523] Step 9:

[0524] The terminal transmits the user's feedback to the server.

[0525] Step 10:

[0526] The server receives the feedback and stores it in a database, which is used to improve the model in the generator.

[0527] Step 11:

[0528] The server analyzes user feedback to refine its natural language processing model, which improves the quality of future suggestions.

[0529] Example 1

[0530] 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."

[0531] For a company's employees to effectively advance their career development and skill improvement, they need customized career plans and skill improvement proposals tailored to each individual employee. However, with conventional systems, it was difficult to effectively generate and provide such customized proposals to employees. There were also insufficient means to collect feedback from employees and improve the system. This made it impossible to efficiently support employee career development.

[0532] 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.

[0533] In this invention, the server includes: a means for inputting data regarding each employee's skill set, work history, and interests and inclinations; a data storage means for storing the data; a generation means for analyzing the stored data and generating customized career plans and skill improvement proposals based on industry trends; a provision means for providing the generated proposals to the employee; a feedback collection means for collecting feedback on the proposals and improving the generation means; and a step in which the generation means acquires the user's input data and analyzes it using a natural language processing model, and a step in which the generation means generates customized career plans and skill improvement proposals tailored to the user's skills, interests, and inclinations based on the analysis results. This makes it possible to effectively generate and provide career plans and skill improvement proposals that are optimal for each employee. This system efficiently supports employee career development and promotes the growth of the entire company.

[0534] A "skill set" is the collection of specific skills and knowledge possessed by an individual employee.

[0535] "Work history" refers to the job and work history that an employee has had up to now.

[0536] "Interests and inclinations" refer to areas in which employees are interested and their hopes and inclinations regarding their future careers.

[0537] A "means for entering data" is an interface or system through which a user enters their information.

[0538] "Data storage means" refers to a storage system or database for storing data entered by a user.

[0539] The "generation means" is a mechanism that analyzes user data and generates customized career plans and proposals for improving skills.

[0540] A "natural language processing model" is an artificial intelligence model that analyzes text data, understands its meaning, and generates responses.

[0541] "Provision means" refers to a mechanism for providing the generated career plans and proposals to users and other related parties.

[0542] The "feedback collection means" is a mechanism for collecting reactions and results to suggestions received from users and using them to improve the system.

[0543] A "generative AI model" is an artificial intelligence model that uses machine learning and deep learning to analyze data and generate responses.

[0544] A "prompt" is text that you enter into a generative AI model to elicit a specific response.

[0545] The "analysis step" is the process of acquiring user data and analyzing it using a natural language processing model.

[0546] A "customized career plan" is a career development guideline that is specifically created based on the characteristics of each individual employee.

[0547] "Skills Upgrading Suggestions" are recommended training or learning programs to enhance your current skill set.

[0548] The present invention provides a virtual career mentor system that utilizes a generative AI model to support the career development and skill improvement of company employees. An embodiment of the present invention will be described in detail below.

[0549] This system mainly consists of five main parts: user data input means, data storage means, generation means, provision means, and feedback collection means.

[0550] First, the user accesses the company's portal site and logs in by entering their ID and password on the login screen. After logging in, the user enters information about their skill set, work history, and interests and aspirations. Specifically, the user enters "Python" and "database management" as skill sets, "three years of software engineering experience" as work history, and "cloud computing" as interests and aspirations.

[0551] The device then sends the entered data to a server. The hardware used for this is a regular personal computer or smartphone, and the communication protocol is HTTPS. The server then stores the received data in a database. This database uses an SQL or NoSQL data storage system.

[0552] The server retrieves the stored data periodically or whenever new data is added. It then analyzes the data using a generative AI model. This natural language processing model uses the latest machine learning algorithms to generate customized career plans and skill development suggestions based on the user's input data. Specific examples of prompts include:

[0553] User Information

[0554] Skill set: Python, Excel

[0555] Work Experience: 2 years of experience as a marketing analyst

[0556] Interests: Data Science

[0557] Proposals to generate

[0558] Training programs to help you improve your skills

[0559] Recommended Career Path

[0560] Latest trends based on industry trends

[0561] The server provides the generated career plans and proposals to the user, who can then review the proposals on the portal site. At the same time, this information is also provided to the human resources department and managers, providing them with enhanced support when implementing the proposals.

[0562] Finally, the user implements the provided career planning and skill improvement suggestions and provides feedback on the results. Feedback content may include, for example, impressions of online courses taken or progress on acquiring new skills. The device sends this feedback to the server, which stores it in a database. This feedback data is used to improve the generative AI model and help improve the accuracy of future suggestions.

[0563] As a concrete example, if a user is interested in data science, has Python skills, and two years of experience as a marketing analyst, the server can analyze the data and generate suggestions like this:

[0564] 1. Recommended skills: Machine learning, data mining

[0565] 2. Training programs: Online courses (e.g., Coursera's machine learning course)

[0566] 3. Career Path: From Data Analyst to Data Scientist

[0567] These suggestions are notified to the user by the server and are also shared with the human resources department and managers. When the user acts on the suggestions and provides feedback on the results, the server collects the feedback and uses it to improve the accuracy of future suggestions. In this way, the system effectively supports employees' career development.

[0568] The flow of the identification process in the first embodiment will be described with reference to FIG.

[0569] Step 1:

[0570] A user accesses a company's portal site and logs in. First, the user enters their ID and password for authentication. Next, they move to a data entry form on the site and enter their skill set (e.g., "Python," "database management"), work experience (e.g., "3 years of software engineering experience"), and interests and aspirations (e.g., "cloud computing"). This input data becomes the basis for subsequent processing.

[0571] Input: User-entered information about skill sets, work history, interests, and aspirations.

[0572] Output: The input data is stored on the device.

[0573] Step 2:

[0574] The device sends the user's input data to the server. Specifically, the input data is sent using the HTTPS protocol. At this time, the sent data includes the user's skill set, work history, and interests and inclinations. The sent data is then analyzed and stored on the server.

[0575] Input: Data entered by the user into the terminal.

[0576] Output: Data sent from the device to the server.

[0577] Step 3:

[0578] The server stores the received data in a database. This storage process uses a storage system (e.g., SQL database, NoSQL database). Once the data has been saved, a confirmation message is sent back to the device.

[0579] Input: Data sent from the terminal.

[0580] Output: The data stored in the database, and a confirmation message.

[0581] Step 4:

[0582] The server retrieves the stored data periodically or when new data is added, and analyzes it using a generative AI model. This analysis uses a natural language processing model. The input prompts for the generative AI model are as follows:

[0583] User Information

[0584] Skill set: Python, Excel

[0585] Work Experience: 2 years of experience as a marketing analyst

[0586] Interests: Data Science

[0587] Proposals to generate

[0588] Training programs to help you improve your skills

[0589] Recommended Career Path

[0590] Latest trends based on industry trends

[0591] Based on these prompts, the generative AI model generates customized career plans and skill development suggestions that match the user's skills, interests, and aspirations.

[0592] Input: User data stored in a database, prompts to the generative AI model.

[0593] Output: Career plan and skill improvement suggestions generated from the generative AI model.

[0594] Step 5:

[0595] The server provides the generated career plans and proposals to users, who can then view the proposals on a portal site. The same information is also provided to the human resources department and managers. This process strengthens the support system for employees when implementing the proposals.

[0596] Input: Career plans and recommendations generated from a generative AI model.

[0597] Output: Career plans and proposals provided to users, HR departments and managers.

[0598] Step 6:

[0599] Users implement the provided career planning and skill improvement suggestions and provide feedback on the results, such as their impressions of an online course they took or their progress in acquiring new skills. The device then sends this feedback to the server, which stores it in a database. The collected feedback data is used to improve the generative AI model and help refine future suggestions.

[0600] Input: Feedback data from users.

[0601] Output: Feedback data sent to the server and stored in the database.

[0602] In this way, the overall processing steps of the present system are linked, making it possible to continuously support employees' career development.

[0603] (Application example 1)

[0604] 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."

[0605] In modern factories, robots handle many work tasks, but improving the robots' performance and skills still relies on manual adjustment and management. This management method is inefficient and makes it difficult to optimize robot utilization. Furthermore, it is difficult to provide learning plans to reduce robot errors and improve work efficiency. This hinders improvements in work efficiency and productivity throughout the factory.

[0606] 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.

[0607] In this invention, the server includes means for inputting work task data and performance data of each robot, data storage means for storing the data, generation means for analyzing the stored data and generating customized learning plans and proposals for improving work efficiency based on the work efficiency of the factory, provision means for providing the generated proposals to the robot, and feedback collection means for collecting feedback on the proposals and improving the generation means. This automates the performance improvement and skill development of robots, making it possible to improve the work efficiency and productivity of the entire factory.

[0608] "Individual robot" refers to a piece of automated equipment designed to perform a specific work task within a factory.

[0609] "Work task data" refers to data including specific information about each task performed by a robot, such as the work content, procedures, and usage time.

[0610] "Performance data" refers to data that indicates the results and efficiency of work tasks performed by a robot, and includes, for example, the time it takes to complete a task, the error rate, and the availability rate.

[0611] "Data storage means" refers to a device or system for storing work task data and performance data transmitted from a robot.

[0612] "Generation means" refers to a device or system that generates suggestions for improving the efficiency and skills of a robot based on stored data.

[0613] "Providing means" refers to a device or system for notifying the robot and the administrator of the generated learning plan and suggestions for improving work efficiency.

[0614] "Feedback collection means" refers to a device or system for collecting results and reactions after the robot implements the provided suggestions.

[0615] The system of the present invention automates the improvement of the efficiency and skill of robots operating in factories. The specific implementation procedure is shown below.

[0616] <System Program>

[0617] This system is configured using the following hardware and software.

[0618] 1. Hardware:

[0619] Robots (industrial and collaborative robots): handle individual work tasks and collect performance data.

[0620] Built-in sensors: Collect real-time robot behavior and performance data.

[0621] Management server: Stores data, analyzes it, and generates proposals.

[0622] 2. Software:

[0623] Database system (e.g. MySQL, PostgreSQL): Stores robot work task data and performance data.

[0624] Generative AI models (e.g., GPT-3, BERT): Analyze robot data and generate customized learning plans and suggestions.

[0625] Robot control software (e.g. ROS): manages the robot's movements and executes the proposed plan.

[0626] Using the above hardware and software, the system operates as follows.

[0627] <System Operation>

[0628] 1. Data entry method

[0629] While the robot is performing a task, it uses built-in sensors to collect task data (e.g., part type, assembly time) and performance data (e.g., error rate, task time) in real time. This data is then sent to the management server via the terminal.

[0630] 2. Data storage method

[0631] The management server stores the received work task data and performance data in a database, thereby accumulating historical data on the robot.

[0632] 3. Generation means

[0633] The management server retrieves the robot's stored data from the database and analyzes it using the generative AI model. Based on the analysis results, it generates optimal learning plans and suggestions for improving operational efficiency for each robot. Examples include "learning new motion sequences to reduce error rates" and "proposing procedures to optimize work speed."

[0634] 4. Means of provision

[0635] The management server notifies the robot and the administrator of the generated learning plan and suggestions. The robot performs the task according to the proposed plan, and the administrator monitors and manages the robot's operation.

[0636] 5. Feedback Collection Methods

[0637] The robot performs the task based on the provided plan, and then collects and sends the resulting performance data and error feedback. The management server stores this in a database and uses this feedback data when generating the next proposal.

[0638] <Example>

[0639] For example, if a welding robot frequently makes errors in past data, the generative AI model will analyze the cause of the error and create a "learning plan to improve welding accuracy at a specific angle." This learning plan can then be applied to the welding robot to reduce errors.

[0640] <Example of prompt sentence for generative AI model>

[0641] "Analyze the welding robot's operation data from the past six months to identify the frequency and causes of errors, and generate a learning plan based on that."

[0642] In this way, this system allows robots in factories to constantly learn the latest, most efficient work procedures, which is expected to improve overall work efficiency.

[0643] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[0644] Step 1:

[0645] While the robot is performing a work task, it uses built-in sensors to collect work task data and performance data in real time.

[0646] Input: Sensor data about the robot's movements.

[0647] Data processing / data calculation: Formats data collected by built-in sensors and converts it into performance indicators such as error rates and task completion times.

[0648] Output: Collected work task and performance data.

[0649] Step 2:

[0650] The terminal transmits the collected data to the management server.

[0651] Input: Work task and performance data from the robot.

[0652] Data processing / data calculation: Encode the data for transmission to the management server using the appropriate communication protocol.

[0653] Output: The encoded data.

[0654] Step 3:

[0655] The server stores the received data in a database.

[0656] Input: The encoded data sent from the terminal.

[0657] Data processing / data operation: Decode the data and insert it into the database using an SQL query.

[0658] Output: Work task and performance data stored in a database.

[0659] Step 4:

[0660] The server retrieves the stored data from the database for analysis and inputs it into the generative AI model.

[0661] Input: Work task data and performance data in a database.

[0662] Data processing / data calculation: Use SQL queries to retrieve the necessary data from the database and convert it into a format suitable for the generative AI model.

[0663] Output: Analyzed data that is fed into a generative AI model.

[0664] Step 5:

[0665] The server inputs the analytical data into a generative AI model to generate a customized learning plan and suggestions for improving work efficiency.

[0666] Input: The data that is fed into the generative AI model.

[0667] Data processing / data calculation: Analyze data using a generative AI model to generate optimal learning plans and suggestions for improving work efficiency.

[0668] Output: Study plan and suggestions for improving work efficiency.

[0669] Step 6:

[0670] The server provides the generated learning plans and suggestions to the robot and the administrator.

[0671] Input: Study plans and suggestions for improving work efficiency.

[0672] Data processing / data calculation: Convert the proposal into the appropriate format and send it to the robot's control system and the administrator's monitoring system.

[0673] Output: Learning plans and suggestions provided to the robot and administrator.

[0674] Step 7:

[0675] The robot performs the task based on the provided learning plan and suggestions, and then collects the results again using its built-in sensors.

[0676] Input: Study plans and suggestions for improving work efficiency.

[0677] Data processing / data calculation: Adjust the robot's movement sequence based on suggestions and record new performance data collected by the built-in sensors.

[0678] Output: New performance data.

[0679] Step 8:

[0680] The terminals send the collected new performance data to the management server, which stores it in a database.

[0681] Input: New performance data.

[0682] Data processing / data calculation: Encode the data, send it using a protocol to send it to the management server, decode the received data, and save it back in the database.

[0683] Output: Feedback data stored in a database.

[0684] 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.

[0685] This invention provides a virtual career mentor system that combines generative AI and an emotion engine to support the career development and skill improvement of corporate employees. By considering each employee's skills, work history, and interests and inclinations, and by analyzing the user's emotions, the system generates and provides customized career plans and skill improvement proposals, thereby supporting effective career development for employees.

[0686] System Configuration

[0687] 1. User data input method

[0688] Users enter information about their skill sets, work history, and interests through a company portal site.

[0689] 2. Data storage method

[0690] The terminal transmits the data entered by the user to the server.

[0691] The server stores the received data in a database.

[0692] 3. Generation means

[0693] The server retrieves user data from the database, checks for missing data or outliers, and performs preprocessing (e.g., data normalization, consistency check) as needed.

[0694] The server uses natural language processing models to analyze the user's skill set, work history, and interests.

[0695] The server takes into account industry trends and the latest trends to generate customized career plans and skill improvement proposals.

[0696] 4. Emotion Engine

[0697] The server uses an emotion engine to analyze the user's emotion data (e.g., text input, voice, facial expressions).

[0698] The server reflects the analysis results of the emotion data in the generated career plan and skill improvement proposals.

[0699] 5. Means of provision

[0700] The server provides the generated career plans and proposals to the user, and also provides the same information to human resources and management.

[0701] 6. Feedback Collection Methods

[0702] Users review the proposals and provide feedback on their satisfaction and feasibility.

[0703] The terminal sends the feedback to the server.

[0704] The server receives and stores the feedback in a database, which is used to improve the models in the generator and emotion engine.

[0705] Explanation of program processing

[0706] User data input means

[0707] Users log in to a company's portal site and enter their skill set (e.g., Java programming, database administration), work experience (e.g., three years of software engineering experience), and interests (e.g., cloud computing).

[0708] Data storage means

[0709] The terminal sends the user's input data to the server, which then stores the data in a database for later processing.

[0710] generation means

[0711] The server retrieves user data from the database and analyzes it using a natural language processing model. This analysis accurately captures the user's skill set, interests, and inclinations, and generates customized career plans and skill improvement proposals that reflect industry trends and the latest trends.

[0712] Emotion Engine

[0713] The server uses an emotion engine to analyze the user's emotional data. For example, it analyzes the text, voice, or facial expression data entered by the user to understand the user's current emotional state. The results of this analysis are reflected in the generated career plan and skill improvement proposals. This allows the proposals to match the user's emotional state and become more personalized.

[0714] Providing means

[0715] The server provides the generated career plans and proposals to the user, and also provides the same information to the human resources department and managers, establishing a support system throughout the company.

[0716] Feedback collection methods

[0717] The user implements the provided career plan and skill improvement suggestions and provides feedback on the results. The device sends the feedback to the server, which receives it and stores it in a database. The stored feedback is used to improve the models in the emotion engine and generation means, thereby improving the quality of future suggestions.

[0718] Specific examples

[0719] For example, if a user is interested in data science, has Python skills, and has two years of experience as a marketing analyst, they can enter this information into the portal site, where the server stores the data and analyzes it using natural language processing models and sentiment engines.

[0720] Based on the analysis, the server generates the following suggestions:

[0721] 1. Recommended skills: Machine learning, data mining

[0722] 2. Training programs: Online courses (e.g., Coursera's machine learning course)

[0723] 3. Career Path: From Data Analyst to Data Scientist

[0724] These suggestions are notified to the user by the server and are also shared with the human resources department and managers. When the user acts on the suggestions and provides feedback, the server collects the feedback and uses it to improve the accuracy of future suggestions. In addition, the emotion engine performs emotional analysis of the feedback to provide more effective suggestions.

[0725] The above is an embodiment of the present invention. This invention allows employees to obtain career plans and skill improvement measures that are optimal for them, and enables companies to effectively support the career development of their employees.

[0726] The processing flow will be explained below.

[0727] Step 1:

[0728] Users log in to the company's portal site and enter their skill set (e.g., Python programming, data analysis), work experience (e.g., two years of experience as a data analyst), and interests (e.g., data science).

[0729] Step 2:

[0730] The terminal transmits data entered by the user, including the skill set, work history, and interests and preferences, to the server.

[0731] Step 3:

[0732] The server stores the received data in a database, which is used for subsequent analysis.

[0733] Step 4:

[0734] The server retrieves user data from the database, checks for missing values ​​and outliers, preprocesses the data as needed (e.g., normalizes data, checks for consistency), and prepares it for analysis.

[0735] Step 5:

[0736] The server uses natural language processing models to analyze a user's skill set, work history, and interests, and also references external data sources on industry trends and current trends, to generate customized career plans and skill development suggestions.

[0737] Step 6:

[0738] The server uses an emotion engine to analyze emotions based on the user's text input, voice, or facial expression data. For example, if the user is feeling anxious, the server considers reassuring suggestions.

[0739] Step 7:

[0740] The server then reflects the results of the emotion analysis in the generated career plans and skill improvement proposals, resulting in customized proposals that take emotion into consideration.

[0741] Step 8:

[0742] The server provides the completed career plan and proposal to the user's terminal, and also notifies the human resources department and manager of the same information to provide support.

[0743] Step 9:

[0744] Users review and implement the provided career plans and skill improvement suggestions, and then provide feedback on the satisfaction and feasibility of the suggestions.

[0745] Step 10:

[0746] The device sends user feedback to the server, which evaluates the effectiveness of the suggestions and uses it for future improvements.

[0747] Step 11:

[0748] The server receives the feedback, stores it in a database, and analyzes it to improve the accuracy of the natural language processing model and emotion engine, making future suggestions more effective and personalized.

[0749] In this way, the system comprehensively supports employees' career development and makes suggestions that take into consideration the user's feelings, thereby achieving higher satisfaction and effectiveness.

[0750] Example 2

[0751] 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."

[0752] In modern companies, employee career development and skill improvement are extremely important issues. However, it is difficult to provide customized career plans that take into account the needs and interests of individual employees. Furthermore, suggestions that ignore the employee's emotional state are often ineffective. Therefore, there is a need for a system that can comprehensively analyze employee information and emotions and provide optimal career plans and skill improvement suggestions.

[0753] The identification processing by the identification processing unit 290 of the data processing device 12 in Example 2 is realized by the following means. In this invention, the server includes: means for inputting data on each employee's skill set, work history, and interests and inclinations; data storage means for storing the data; means for preprocessing the stored data, filling in missing values, and normalizing the data; means for analyzing the preprocessed data and generating customized career plans and skill improvement proposals based on industry trends; an emotion engine for analyzing user emotion data and reflecting the results in the generated proposals; means for providing the generated proposals to the employee and also to the human resources department and manager; and means for collecting feedback on the proposals and improving the generation means. This enables the generation of customized proposals to effectively support employees' career development and skill improvement.

[0754] A "skill set" refers to the collection of skills and expertise that an individual employee possesses.

[0755] "Work history" refers to the history of the work, jobs, and roles an employee has performed to date.

[0756] "Interests and orientations" refer to the interests and goals that individual employees have regarding their work.

[0757] "Data storage means" means any device or method that securely stores data collected from employees and makes it available for subsequent processing.

[0758] "Preprocessing" refers to tasks such as filling in missing values ​​and normalizing data that are carried out before data analysis.

[0759] A "natural language processing model" refers to the algorithms and techniques that enable computers to understand and analyze human language.

[0760] An "emotion engine" refers to a technology that analyzes a user's text, voice, and facial expression data to understand their emotional state and utilize the results.

[0761] "Generation means" refers to a device or method that analyzes the stored data and generates customized career plans and skill improvement suggestions based on industry trends.

[0762] The "provision means" refers to a device or method for providing the generated proposal to the user, the human resources department, and the manager.

[0763] The term "feedback collection means" refers to a device or method that collects opinions and evaluations provided by users regarding the provided suggestions and uses them to improve the system.

[0764] This invention provides a virtual career mentoring system that combines a generative AI model and an emotion engine to support the career development and skill improvement of corporate employees. The system generates and provides customized career plans and skill improvement proposals by considering each employee's skills, work history, and interests and inclinations, and by analyzing the user's emotions.

[0765] The system components are:

[0766] User data input means

[0767] Data storage means

[0768] Pretreatment means

[0769] generation means

[0770] Emotion Engine

[0771] Providing means

[0772] Feedback collection methods

[0773] User data input means

[0774] Users log in to the company's portal site and enter their skill set (e.g., Java programming, database management), work experience (e.g., three years of software engineering experience), and interests (e.g., cloud computing). The entered data is registered in the system.

[0775] Data storage means

[0776] The terminal sends the data entered by the user to the server, which stores the received data in a database for subsequent processing.

[0777] Pretreatment means

[0778] The server retrieves user data from the database and performs preprocessing, including filling in missing values ​​and normalizing the data. For example, if there is a missing year, it is filled in with the average value and data scaling is performed.

[0779] generation means

[0780] The server uses natural language processing (NLP) models to perform detailed analysis of the user's skill set, work history, and interests and inclinations. As a result of the analysis, it accurately identifies the user's characteristics and generates a customized career plan and skill improvement proposals based on industry trends and the latest trends. For example, a user with "Python programming" skills could be recommended machine learning skills.

[0781] Emotion Engine

[0782] The server uses an emotion engine to analyze the user's emotional data (e.g., text, voice, facial expressions). For example, if a user enters, "I've been feeling unmotivated at work lately," the emotion engine will classify that state as "stress." This information is taken into account and reflected in the generated career plans and skill improvement suggestions. Specifically, relaxation methods for stress reduction can be added to the suggestions.

[0783] Providing means

[0784] The server notifies the user of the generated career plan and skill improvement proposals via a dashboard on the portal site or by email. The same information is also provided to the human resources department and managers, creating a support system across the company.

[0785] Feedback collection methods

[0786] The user provides feedback on the provided career plan and skill improvement suggestions. The feedback includes the effectiveness of the suggestions and the level of satisfaction. The device sends this feedback to the server, which stores the received feedback in a database. The stored feedback is used to improve the generation method and emotion engine model. This allows the system to improve the accuracy of future suggestions.

[0787] Specific examples

[0788] For example, let's say a user is interested in data science, has Python skills, and has two years of experience as a marketing analyst. When the user enters this information into the portal, their device sends the data to the server, where it is stored in a database. The server then performs analysis using natural language processing models and sentiment engines to generate suggestions such as:

[0789] 1. Recommended skills: Machine learning, data mining

[0790] 2. Training programs: Online courses (e.g., Coursera's machine learning course)

[0791] 3. Career Path: From Data Analyst to Data Scientist

[0792] These suggestions are notified to the user by the server and are also shared with the human resources department and managers. When the user acts on the suggestions and provides the results as feedback, the server collects this information and uses it to improve the accuracy of future suggestions. The emotion engine also analyzes the emotions in the feedback to provide even more effective suggestions.

[0793] Prompt Sentence Examples

[0794] "Analyze user-entered data and propose a customized career plan."

[0795] "Generate skill improvement suggestions that take into account user sentiment data."

[0796] The above is an embodiment of the present invention. This invention allows employees to obtain career plans and skill improvement measures that are optimal for them, and also enables companies to effectively support the career development of their employees.

[0797] The flow of the identification process in the second embodiment will be described with reference to FIG.

[0798] Step 1: User data input

[0799] A user logs in to a company's portal site. The user enters their skill set (e.g., Java programming, database administration), work experience (e.g., three years of software engineering experience), and interests (e.g., cloud computing). The entered data is temporarily stored on the device. This is the input data in step 1. The specific actions in this step are to enter data into a text form and click the submit button.

[0800] Step 2: Data transmission and storage

[0801] The terminal sends the data entered by the user to the server. During this transmission process, the data is encrypted and transmitted using a secure communication protocol (e.g., HTTPS). The server receives the received data and stores it in a database. This is the output data of step 2. The specific operations in this step are data encryption, transmission, and recording in the database.

[0802] Step 3: Preprocessing the data

[0803] The server retrieves the stored user data from the database. This retrieved data is the input data for Step 3. The server preprocesses the data. Specifically, it imputes missing values, checks consistency, and normalizes the data. For example, it imputes missing values ​​with the mean and standard-scales the numeric data. This preprocessed data is the output data for Step 3.

[0804] Step 4: Data analysis and proposal generation

[0805] The server uses the preprocessed data to run a natural language processing (NLP) model to perform a detailed analysis of the user's skill set, work history, interests, and inclinations. This is the input data for step 4. It also collects industry trends and the latest trends from the internet and analyzes them against the user's data. A generative AI model is used to generate a customized career plan and suggestions for skill improvement. This is the output data for step 4. The specific operations in this step are NLP analysis, data matching, and generation of a career plan and suggestions.

[0806] Step 5: Sentiment Data Analysis

[0807] The server obtains the user's input text, voice, and facial expression data. This is the input data for step 5. The emotion engine analyzes this data to understand the user's emotional state. For example, if the user inputs "high stress," the emotion engine identifies this state as "stress." The results of this analysis are reflected in career plans and suggestions for skill improvement. This is the output data for step 5. The specific operations in this step are emotion analysis and feedback of the results.

[0808] Step 6: Provide a proposal

[0809] The server notifies the user of the generated career plan and skill improvement suggestions. This is the input data of step 6. This notification is sent via the portal site dashboard, email, etc. The same information is also provided to the HR department and administrators. This is the output data of step 6. The specific actions in this step are the generation and distribution of notifications.

[0810] Step 7: Gather feedback

[0811] The user provides feedback on the provided career plan and skill improvement suggestions. This is the input data for step 7. The feedback includes the effectiveness of the suggestions and the level of satisfaction. The device sends this feedback to the server. The server receives the feedback and stores it in a database. The stored feedback is used to improve the generation means and emotion engine models. This is the output data for step 7. The specific operations in this step are collecting and storing feedback and improving the model.

[0812] (Application example 2)

[0813] 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."

[0814] While there are many systems that effectively support employee career development and skill improvement, they lack the ability to provide personalized suggestions that take into account employees' emotional state. This can lead to situations where employees are unmotivated or stressed by the suggestions. Furthermore, there are limited means to collect feedback and improve the quality of suggestions, making continuous improvement difficult. Another problem is that they are unable to provide information simultaneously to not only employees but also the HR department and managers, enabling efficient career support throughout the organization.

[0815] 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.

[0816] In this invention, the server includes: a means for inputting data regarding each employee's skill set, work history, and interests and inclinations; a data storage means for storing the data; a generation means for analyzing the stored data and generating customized career plans and skill improvement proposals based on industry trends; a provision means for providing the generated proposals to the employee; a feedback collection means for collecting feedback on the proposals and improving the generation means; and an emotion analysis means for analyzing the input emotional data and reflecting the results in the proposals. This allows for personalized career plans and skill improvement proposals that take employees' emotional states into account, thereby increasing employee motivation and enabling efficient career support throughout the organization. Furthermore, the collected feedback can be used to continuously improve the system and improve the quality of proposals.

[0817] A "skill set" is the collection of skills and knowledge that an employee possesses.

[0818] "Work history" refers to the history of jobs and positions that an employee has held up to now.

[0819] "Interests and orientations" refer to the areas in which employees are interested and their orientation toward the future.

[0820] "Data storage means" refers to a device or system that stores data entered by employees.

[0821] The "generation means" is a device or system that analyzes the stored data and generates customized career plans and skill improvement proposals.

[0822] The "means for providing" refers to a device or system that presents the generated career plans and skill improvement proposals to employees.

[0823] A "feedback collection tool" is a device or system that collects information by allowing employees to input their opinions and satisfaction with the suggestions provided.

[0824] An "emotion analysis means" is a device or system that analyzes emotions from employee input data and reflects the results in proposals.

[0825] A "natural language processing model" is a machine learning model for analyzing employee and industry data, and has the ability to understand and analyze natural language.

[0826] This invention relates to a virtual career mentor system for supporting employees' career development and skill improvement. This system collects data on employees' skill sets, work history, interests, and inclinations, and also analyzes their emotions to provide optimal career plans for each employee. Specifically, it has the following configuration:

[0827] 1. User data input method

[0828] Users (employees) use smartphones or web portals to input information about their skill sets, work history, interests, and aspirations. This input data is used to inform detailed career development for employees.

[0829] 2. Data storage method

[0830] The device sends the data entered by the user to a cloud server, which then stores the data in a database, such as AWS's DynamoDB.

[0831] 3. Generation means

[0832] The server retrieves the stored data and analyzes it using a natural language processing model, such as OpenAI's GPT-4, to generate customized career plans and skill development suggestions based on the user's skill set, work history, interests, and aspirations.

[0833] 4. Emotion analysis method

[0834] The server analyzes the collected emotional data (voice, text, facial expressions, etc.) from the user using an emotion analysis engine such as Azure's Emotion API to determine the user's emotional state. This allows the server to reflect the emotional data in the generated career plans and skill improvement proposals, providing more personalized proposals.

[0835] 5. Means of provision

[0836] The server provides the generated career plan and proposal to the user, and also notifies the human resources department and managers of the information, thereby establishing a support system throughout the company.

[0837] 6. Feedback Collection Methods

[0838] Users can provide feedback on the provided career plans and skill improvement suggestions. This feedback is sent to a cloud server and stored in a database. The collected feedback is used to improve the models of the generator and sentiment analyzer.

[0839] Specific examples

[0840] For example, let's say an employee has an interest in data science, Python skills, and two years of experience as a marketing analyst. When the employee enters this information into a smartphone app, the server stores the information in a database and performs analysis. Using OpenAI's GPT-4, the analysis generates the following suggestions:

[0841] 1. Recommended skills: Machine learning, data mining

[0842] 2. Training programs: Online courses (e.g., an introductory course on machine learning)

[0843] 3. Career Path: From Data Analyst to Data Scientist

[0844] At this time, emotion analysis is performed based on the voice data entered by the employee, and if the result is that "the employee is highly motivated and has a strong interest in machine learning," this result can be reflected to "assess true interest and enthusiasm in career plans and strengthen the content of advice."

[0845] Prompt Sentence Examples

[0846] (Input information)

[0847] Skill Set: Python programming, data analysis

[0848] ·Work Experience: 2 years of experience as a marketing analyst

[0849] Interests: Data science, machine learning

[0850] (emotion data)

[0851] Users are highly motivated and have a strong interest in machine learning

[0852] The above is an embodiment of the present invention. This system allows employees to obtain career plans and skill improvement measures that are best suited to them, and enables companies to effectively support the career development of their employees.

[0853] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[0854] Step 1:

[0855] A user inputs information about their skill set, work history, and interests and aspirations via a smartphone or web portal. The information entered by the user is sent from the device to the server. Specifically, it is assumed that the user inputs "Skill set: Python programming, data analysis," "Work history: 2 years of experience as a marketing analyst," and "Interests and aspirations: data science, machine learning."

[0856] Input: User's skill set, work history, interests and preferences

[0857] Output: User data sent to the server

[0858] Step 2:

[0859] The device sends the input data from the user to a cloud server, which then stores it in a database using AWS's DynamoDB or similar.

[0860] Input: User data sent to the server

[0861] Output: User data stored in the database

[0862] Step 3:

[0863] The server retrieves the stored user data and analyzes it using a natural language processing model (e.g., OpenAI's GPT-4). It then generates a customized career plan and skill improvement suggestions based on the user's skill set, work history, interests, and aspirations. Specifically, it may suggest "recommended skills: machine learning, data mining," "training program: online courses," and "career path: from data analyst to data scientist."

[0864] Input: User data retrieved from the database

[0865] Output: Generated career plans and skill improvement suggestions

[0866] Step 4:

[0867] The user provides emotional data to the server through voice or text input, such as "I am highly motivated and have a strong interest in machine learning."

[0868] Input: User's voice data, text data

[0869] Output: Emotion data sent to the server

[0870] Step 5:

[0871] The server uses Azure's Emotion API to analyze the emotional data and evaluate the user's emotional state. The results of this evaluation are reflected in the generated career plan and skill improvement proposals. For example, adjustments may be made such as "proposing a more difficult course because the user is highly motivated."

[0872] Input: Emotion data sent to the server

[0873] Output: Parsed emotional state

[0874] Step 6:

[0875] The server provides the generated career plan and proposals to the user and simultaneously notifies the human resources department and managers, and displays them via a smartphone app or web portal.

[0876] Input: Generated career plans and skill improvement suggestions, analyzed emotional states

[0877] Output: Customization suggestions provided to the user and HR department

[0878] Step 7:

[0879] Users can provide feedback on the provided career plans and proposals through a smartphone app or web portal, which is then sent to a cloud server and stored in a database.

[0880] Input: User feedback

[0881] Output: Feedback stored in a database

[0882] Step 8:

[0883] The server analyzes the collected feedback and refines the models of the generator and sentiment analyzer to improve the quality of future suggestions, which will enable suggestions that better reflect the user's needs and emotions.

[0884] Input: Feedback stored in the database

[0885] Output: Improved generative and sentiment analysis models

[0886] 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.

[0887] 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.

[0888] 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.

[0889] [Third embodiment]

[0890] FIG. 5 shows an example of the configuration of a data processing system 310 according to the third embodiment.

[0891] 5, the data processing system 310 includes the data processing device 12 and a headset terminal 314. An example of the data processing device 12 is a server.

[0892] 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).

[0893] 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.

[0894] 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.

[0895] 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).

[0896] 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.

[0897] 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.

[0898] 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.

[0899] 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.

[0900] 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.

[0901] 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."

[0902] This invention provides a virtual career mentor system that utilizes generative AI to support the career development and skill improvement of corporate employees. This system supports effective career development for employees by generating and providing customized career plans and skill improvement proposals that take into account the skills, work history, and interests and inclinations of each employee.

[0903] System Configuration

[0904] 1. User data input method

[0905] Users enter information about their skill sets, work history, interests and aspirations through a company's portal site.

[0906] 2. Data storage method

[0907] The terminal transmits the data entered by the user to the server;

[0908] The server stores the received data in a database.

[0909] 3. Generation means

[0910] The server retrieves the stored data and analyzes it using a natural language processing model.

[0911] The server takes into account industry trends and the latest trends to generate customized career plans and skill improvement proposals.

[0912] 4. Means of provision

[0913] The server provides the generated career plans and offers to the user.

[0914] The server also provides the same information to the human resources department and administrators, establishing a support system across the entire company.

[0915] 5. Feedback Collection Methods

[0916] Users review the proposals and provide feedback on their satisfaction and feasibility.

[0917] The device sends the feedback to the server,

[0918] The server receives the feedback, stores it in a database, and uses it to improve the model to improve the accuracy of future proposals.

[0919] Explanation of program processing

[0920] User data input means

[0921] Users access a company's portal site and log in. They enter their skill set (e.g., Java programming, database administration), work experience (e.g., three years of software engineering experience), and interests (e.g., cloud computing).

[0922] Data storage means

[0923] The terminal transmits the user's input data to the server, which stores the data in a database, which serves as the basis for analysis by the generating means.

[0924] generation means

[0925] The server retrieves user data from the database and analyzes it using a natural language processing model (e.g., generative AI), accurately capturing the user's skill set, interests, and aspirations, and generating customized career plans and skill improvement proposals that reflect industry trends and the latest developments.

[0926] Providing means

[0927] The server provides the generated career plans and proposals to the user, and also provides the same information to the human resources department and managers to enhance support for employees in implementing the proposals.

[0928] Feedback collection methods

[0929] The user implements the provided career plans and skill improvement suggestions and provides feedback on the results. The device sends the feedback to the server, which receives it and stores it in a database. The stored feedback is used to improve the model in the future, helping to increase the accuracy of the suggestions.

[0930] Specific examples

[0931] For example, if a user is interested in data science, has Python skills, and has two years of experience as a marketing analyst, the user enters this information into the portal site, where the server stores the data and analyzes it using a natural language processing model as a generation tool.

[0932] Based on the analysis, the server generates the following suggestions:

[0933] 1. Recommended skills: Machine learning, data mining

[0934] 2. Training programs: Online courses (e.g., Coursera's machine learning course)

[0935] 3. Career Path: From Data Analyst to Data Scientist

[0936] These suggestions are notified to the user by the server and are also shared with the human resources department and managers. When the user acts on the suggestions and provides feedback on the results, the server collects the feedback and uses it to improve the accuracy of future suggestions. In this way, the system effectively supports employees' career development.

[0937] The above is an embodiment of the present invention. This invention allows employees to obtain career plans and skill improvement measures that are optimal for them, and enables companies to effectively support the career development of their employees.

[0938] The processing flow will be explained below.

[0939] Step 1:

[0940] Users log into a company's portal site and enter information about their skill set, work history, and interests.

[0941] Step 2:

[0942] The terminal transmits the data entered by the user to the server.

[0943] Step 3:

[0944] The server stores the received data in a database.

[0945] Step 4:

[0946] The server retrieves user data from the database, checks for missing data or outliers, and performs preprocessing (e.g., data normalization, consistency check) as needed.

[0947] Step 5:

[0948] The server uses natural language processing models to analyze users' skill sets, work history, and interests, and also consults external data sources on industry trends and current trends.

[0949] Step 6:

[0950] Based on the analysis results, the server generates optimal career plans and suggestions for skill improvement for the user, including recommended skill sets, appropriate training programs, and career paths.

[0951] Step 7:

[0952] The server sends the generated career plan and proposal to the user's terminal, and also sends the same information to the human resources department and managers.

[0953] Step 8:

[0954] Users review the career plans and skill development suggestions provided and provide feedback.

[0955] Step 9:

[0956] The terminal transmits the user's feedback to the server.

[0957] Step 10:

[0958] The server receives the feedback and stores it in a database, which is used to improve the model in the generator.

[0959] Step 11:

[0960] The server analyzes user feedback to refine its natural language processing model, which improves the quality of future suggestions.

[0961] Example 1

[0962] 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."

[0963] For a company's employees to effectively advance their career development and skill improvement, they need customized career plans and skill improvement proposals tailored to each individual employee. However, with conventional systems, it was difficult to effectively generate and provide such customized proposals to employees. There were also insufficient means to collect feedback from employees and improve the system. This made it impossible to efficiently support employee career development.

[0964] 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.

[0965] In this invention, the server includes: a means for inputting data regarding each employee's skill set, work history, and interests and inclinations; a data storage means for storing the data; a generation means for analyzing the stored data and generating customized career plans and skill improvement proposals based on industry trends; a provision means for providing the generated proposals to the employee; a feedback collection means for collecting feedback on the proposals and improving the generation means; and a step in which the generation means acquires the user's input data and analyzes it using a natural language processing model, and a step in which the generation means generates customized career plans and skill improvement proposals tailored to the user's skills, interests, and inclinations based on the analysis results. This makes it possible to effectively generate and provide career plans and skill improvement proposals that are optimal for each employee. This system efficiently supports employee career development and promotes the growth of the entire company.

[0966] A "skill set" is the collection of specific skills and knowledge possessed by an individual employee.

[0967] "Work history" refers to the job and work history that an employee has had up to now.

[0968] "Interests and inclinations" refer to areas in which employees are interested and their hopes and inclinations regarding their future careers.

[0969] A "means for entering data" is an interface or system through which a user enters their information.

[0970] "Data storage means" refers to a storage system or database for storing data entered by a user.

[0971] The "generation means" is a mechanism that analyzes user data and generates customized career plans and proposals for improving skills.

[0972] A "natural language processing model" is an artificial intelligence model that analyzes text data, understands its meaning, and generates responses.

[0973] "Provision means" refers to a mechanism for providing the generated career plans and proposals to users and other related parties.

[0974] The "feedback collection means" is a mechanism for collecting reactions and results to suggestions received from users and using them to improve the system.

[0975] A "generative AI model" is an artificial intelligence model that uses machine learning and deep learning to analyze data and generate responses.

[0976] A "prompt" is text that you enter into a generative AI model to elicit a specific response.

[0977] The "analysis step" is the process of acquiring user data and analyzing it using a natural language processing model.

[0978] A "customized career plan" is a career development guideline that is specifically created based on the characteristics of each individual employee.

[0979] "Skills Upgrading Suggestions" are recommended training or learning programs to enhance your current skill set.

[0980] The present invention provides a virtual career mentor system that utilizes a generative AI model to support the career development and skill improvement of company employees. An embodiment of the present invention will be described in detail below.

[0981] This system mainly consists of five main parts: user data input means, data storage means, generation means, provision means, and feedback collection means.

[0982] First, the user accesses the company's portal site and logs in by entering their ID and password on the login screen. After logging in, the user enters information about their skill set, work history, and interests and aspirations. Specifically, the user enters "Python" and "database management" as skill sets, "three years of software engineering experience" as work history, and "cloud computing" as interests and aspirations.

[0983] The device then sends the entered data to a server. The hardware used for this is a regular personal computer or smartphone, and the communication protocol is HTTPS. The server then stores the received data in a database. This database uses an SQL or NoSQL data storage system.

[0984] The server retrieves the stored data periodically or whenever new data is added. It then analyzes the data using a generative AI model. This natural language processing model uses the latest machine learning algorithms to generate customized career plans and skill development suggestions based on the user's input data. Specific examples of prompts include:

[0985] User Information

[0986] Skill set: Python, Excel

[0987] Work Experience: 2 years of experience as a marketing analyst

[0988] Interests: Data Science

[0989] Proposals to generate

[0990] Training programs to help you improve your skills

[0991] Recommended Career Path

[0992] Latest trends based on industry trends

[0993] The server provides the generated career plans and proposals to the user, who can then review the proposals on the portal site. At the same time, this information is also provided to the human resources department and managers, providing them with enhanced support when implementing the proposals.

[0994] Finally, the user implements the provided career planning and skill improvement suggestions and provides feedback on the results. Feedback content may include, for example, impressions of online courses taken or progress on acquiring new skills. The device sends this feedback to the server, which stores it in a database. This feedback data is used to improve the generative AI model and help improve the accuracy of future suggestions.

[0995] As a concrete example, if a user is interested in data science, has Python skills, and two years of experience as a marketing analyst, the server can analyze the data and generate suggestions like this:

[0996] 1. Recommended skills: Machine learning, data mining

[0997] 2. Training programs: Online courses (e.g., Coursera's machine learning course)

[0998] 3. Career Path: From Data Analyst to Data Scientist

[0999] These suggestions are notified to the user by the server and are also shared with the human resources department and managers. When the user acts on the suggestions and provides feedback on the results, the server collects the feedback and uses it to improve the accuracy of future suggestions. In this way, the system effectively supports employees' career development.

[1000] The flow of the identification process in the first embodiment will be described with reference to FIG.

[1001] Step 1:

[1002] A user accesses a company's portal site and logs in. First, the user enters their ID and password for authentication. Next, they move to a data entry form on the site and enter their skill set (e.g., "Python," "database management"), work experience (e.g., "3 years of software engineering experience"), and interests and aspirations (e.g., "cloud computing"). This input data becomes the basis for subsequent processing.

[1003] Input: User-entered information about skill sets, work history, interests, and aspirations.

[1004] Output: The input data is stored on the device.

[1005] Step 2:

[1006] The device sends the user's input data to the server. Specifically, the input data is sent using the HTTPS protocol. At this time, the sent data includes the user's skill set, work history, and interests and inclinations. The sent data is then analyzed and stored on the server.

[1007] Input: Data entered by the user into the terminal.

[1008] Output: Data sent from the device to the server.

[1009] Step 3:

[1010] The server stores the received data in a database. This storage process uses a storage system (e.g., SQL database, NoSQL database). Once the data has been saved, a confirmation message is sent back to the device.

[1011] Input: Data sent from the terminal.

[1012] Output: The data stored in the database, and a confirmation message.

[1013] Step 4:

[1014] The server retrieves the stored data periodically or when new data is added, and analyzes it using a generative AI model. This analysis uses a natural language processing model. The input prompts for the generative AI model are as follows:

[1015] User Information

[1016] Skill set: Python, Excel

[1017] Work Experience: 2 years of experience as a marketing analyst

[1018] Interests: Data Science

[1019] Proposals to generate

[1020] Training programs to help you improve your skills

[1021] Recommended Career Path

[1022] Latest trends based on industry trends

[1023] Based on these prompts, the generative AI model generates customized career plans and skill development suggestions that match the user's skills, interests, and aspirations.

[1024] Input: User data stored in a database, prompts to the generative AI model.

[1025] Output: Career plan and skill improvement suggestions generated from the generative AI model.

[1026] Step 5:

[1027] The server provides the generated career plans and proposals to users, who can then view the proposals on a portal site. The same information is also provided to the human resources department and managers. This process strengthens the support system for employees when implementing the proposals.

[1028] Input: Career plans and recommendations generated from a generative AI model.

[1029] Output: Career plans and proposals provided to users, HR departments and managers.

[1030] Step 6:

[1031] Users implement the provided career planning and skill improvement suggestions and provide feedback on the results, such as their impressions of an online course they took or their progress in acquiring new skills. The device then sends this feedback to the server, which stores it in a database. The collected feedback data is used to improve the generative AI model and help refine future suggestions.

[1032] Input: Feedback data from users.

[1033] Output: Feedback data sent to the server and stored in the database.

[1034] In this way, the overall processing steps of the present system are linked, making it possible to continuously support employees' career development.

[1035] (Application example 1)

[1036] 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."

[1037] In modern factories, robots handle many work tasks, but improving the robots' performance and skills still relies on manual adjustment and management. This management method is inefficient and makes it difficult to optimize robot utilization. Furthermore, it is difficult to provide learning plans to reduce robot errors and improve work efficiency. This hinders improvements in work efficiency and productivity throughout the factory.

[1038] 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.

[1039] In this invention, the server includes means for inputting work task data and performance data of each robot, data storage means for storing the data, generation means for analyzing the stored data and generating customized learning plans and proposals for improving work efficiency based on the work efficiency of the factory, provision means for providing the generated proposals to the robot, and feedback collection means for collecting feedback on the proposals and improving the generation means. This automates the performance improvement and skill development of robots, making it possible to improve the work efficiency and productivity of the entire factory.

[1040] "Individual robot" refers to a piece of automated equipment designed to perform a specific work task within a factory.

[1041] "Work task data" refers to data including specific information about each task performed by a robot, such as the work content, procedures, and usage time.

[1042] "Performance data" refers to data that indicates the results and efficiency of work tasks performed by a robot, and includes, for example, the time it takes to complete a task, the error rate, and the availability rate.

[1043] "Data storage means" refers to a device or system for storing work task data and performance data transmitted from a robot.

[1044] "Generation means" refers to a device or system that generates suggestions for improving the efficiency and skills of a robot based on stored data.

[1045] "Providing means" refers to a device or system for notifying the robot and the administrator of the generated learning plan and suggestions for improving work efficiency.

[1046] "Feedback collection means" refers to a device or system for collecting results and reactions after the robot implements the provided suggestions.

[1047] The system of the present invention automates the improvement of the efficiency and skill of robots operating in factories. The specific implementation procedure is shown below.

[1048] <System Program>

[1049] This system is configured using the following hardware and software.

[1050] 1. Hardware:

[1051] Robots (industrial and collaborative robots): handle individual work tasks and collect performance data.

[1052] Built-in sensors: Collect real-time robot behavior and performance data.

[1053] Management server: Stores data, analyzes it, and generates proposals.

[1054] 2. Software:

[1055] Database system (e.g. MySQL, PostgreSQL): Stores robot work task data and performance data.

[1056] Generative AI models (e.g., GPT-3, BERT): Analyze robot data and generate customized learning plans and suggestions.

[1057] Robot control software (e.g. ROS): manages the robot's movements and executes the proposed plan.

[1058] Using the above hardware and software, the system operates as follows.

[1059] <System Operation>

[1060] 1. Data entry method

[1061] While the robot is performing a task, it uses built-in sensors to collect task data (e.g., part type, assembly time) and performance data (e.g., error rate, task time) in real time. This data is then sent to the management server via the terminal.

[1062] 2. Data storage method

[1063] The management server stores the received work task data and performance data in a database, thereby accumulating historical data on the robot.

[1064] 3. Generation means

[1065] The management server retrieves the robot's stored data from the database and analyzes it using the generative AI model. Based on the analysis results, it generates optimal learning plans and suggestions for improving operational efficiency for each robot. Examples include "learning new motion sequences to reduce error rates" and "proposing procedures to optimize work speed."

[1066] 4. Means of provision

[1067] The management server notifies the robot and the administrator of the generated learning plan and suggestions. The robot performs the task according to the proposed plan, and the administrator monitors and manages the robot's operation.

[1068] 5. Feedback Collection Methods

[1069] The robot performs the task based on the provided plan, and then collects and sends the resulting performance data and error feedback. The management server stores this in a database and uses this feedback data when generating the next proposal.

[1070] <Example>

[1071] For example, if a welding robot frequently makes errors in past data, the generative AI model will analyze the cause of the error and create a "learning plan to improve welding accuracy at a specific angle." This learning plan can then be applied to the welding robot to reduce errors.

[1072] <Example of prompt sentence for generative AI model>

[1073] "Analyze the welding robot's operation data from the past six months to identify the frequency and causes of errors, and generate a learning plan based on that."

[1074] In this way, this system allows robots in factories to constantly learn the latest, most efficient work procedures, which is expected to improve overall work efficiency.

[1075] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[1076] Step 1:

[1077] While the robot is performing a work task, it uses built-in sensors to collect work task data and performance data in real time.

[1078] Input: Sensor data about the robot's movements.

[1079] Data processing / data calculation: Formats data collected by built-in sensors and converts it into performance indicators such as error rates and task completion times.

[1080] Output: Collected work task and performance data.

[1081] Step 2:

[1082] The terminal transmits the collected data to the management server.

[1083] Input: Work task and performance data from the robot.

[1084] Data processing / data calculation: Encode the data for transmission to the management server using the appropriate communication protocol.

[1085] Output: The encoded data.

[1086] Step 3:

[1087] The server stores the received data in a database.

[1088] Input: The encoded data sent from the terminal.

[1089] Data processing / data operation: Decode the data and insert it into the database using an SQL query.

[1090] Output: Work task and performance data stored in a database.

[1091] Step 4:

[1092] The server retrieves the stored data from the database for analysis and inputs it into the generative AI model.

[1093] Input: Work task data and performance data in a database.

[1094] Data processing / data calculation: Use SQL queries to retrieve the necessary data from the database and convert it into a format suitable for the generative AI model.

[1095] Output: Analyzed data that is fed into a generative AI model.

[1096] Step 5:

[1097] The server inputs the analytical data into a generative AI model to generate a customized learning plan and suggestions for improving work efficiency.

[1098] Input: The data that is fed into the generative AI model.

[1099] Data processing / data calculation: Analyze data using a generative AI model to generate optimal learning plans and suggestions for improving work efficiency.

[1100] Output: Study plan and suggestions for improving work efficiency.

[1101] Step 6:

[1102] The server provides the generated learning plans and suggestions to the robot and the administrator.

[1103] Input: Study plans and suggestions for improving work efficiency.

[1104] Data processing / data calculation: Convert the proposal into the appropriate format and send it to the robot's control system and the administrator's monitoring system.

[1105] Output: Learning plans and suggestions provided to the robot and administrator.

[1106] Step 7:

[1107] The robot performs the task based on the provided learning plan and suggestions, and then collects the results again using its built-in sensors.

[1108] Input: Study plans and suggestions for improving work efficiency.

[1109] Data processing / data calculation: Adjust the robot's movement sequence based on suggestions and record new performance data collected by the built-in sensors.

[1110] Output: New performance data.

[1111] Step 8:

[1112] The terminals send the collected new performance data to the management server, which stores it in a database.

[1113] Input: New performance data.

[1114] Data processing / data calculation: Encode the data, send it using a protocol to send it to the management server, decode the received data, and save it back in the database.

[1115] Output: Feedback data stored in a database.

[1116] 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.

[1117] This invention provides a virtual career mentor system that combines generative AI and an emotion engine to support the career development and skill improvement of corporate employees. By considering each employee's skills, work history, and interests and inclinations, and by analyzing the user's emotions, the system generates and provides customized career plans and skill improvement proposals, thereby supporting effective career development for employees.

[1118] System Configuration

[1119] 1. User data input method

[1120] Users enter information about their skill sets, work history, and interests through a company portal site.

[1121] 2. Data storage method

[1122] The terminal transmits the data entered by the user to the server.

[1123] The server stores the received data in a database.

[1124] 3. Generation means

[1125] The server retrieves user data from the database, checks for missing data or outliers, and performs preprocessing (e.g., data normalization, consistency check) as needed.

[1126] The server uses natural language processing models to analyze the user's skill set, work history, and interests.

[1127] The server takes into account industry trends and the latest trends to generate customized career plans and skill improvement proposals.

[1128] 4. Emotion Engine

[1129] The server uses an emotion engine to analyze the user's emotion data (e.g., text input, voice, facial expressions).

[1130] The server reflects the analysis results of the emotion data in the generated career plan and skill improvement proposals.

[1131] 5. Means of provision

[1132] The server provides the generated career plans and proposals to the user, and also provides the same information to human resources and management.

[1133] 6. Feedback Collection Methods

[1134] Users review the proposals and provide feedback on their satisfaction and feasibility.

[1135] The terminal sends the feedback to the server.

[1136] The server receives and stores the feedback in a database, which is used to improve the models in the generator and emotion engine.

[1137] Explanation of program processing

[1138] User data input means

[1139] Users log in to a company's portal site and enter their skill set (e.g., Java programming, database administration), work experience (e.g., three years of software engineering experience), and interests (e.g., cloud computing).

[1140] Data storage means

[1141] The terminal sends the user's input data to the server, which then stores the data in a database for later processing.

[1142] generation means

[1143] The server retrieves user data from the database and analyzes it using a natural language processing model. This analysis accurately captures the user's skill set, interests, and inclinations, and generates customized career plans and skill improvement proposals that reflect industry trends and the latest trends.

[1144] Emotion Engine

[1145] The server uses an emotion engine to analyze the user's emotional data. For example, it analyzes the text, voice, or facial expression data entered by the user to understand the user's current emotional state. The results of this analysis are reflected in the generated career plan and skill improvement proposals. This allows the proposals to match the user's emotional state and become more personalized.

[1146] Providing means

[1147] The server provides the generated career plans and proposals to the user, and also provides the same information to the human resources department and managers, establishing a support system throughout the company.

[1148] Feedback collection methods

[1149] The user implements the provided career plan and skill improvement suggestions and provides feedback on the results. The device sends the feedback to the server, which receives it and stores it in a database. The stored feedback is used to improve the models in the emotion engine and generation means, thereby improving the quality of future suggestions.

[1150] Specific examples

[1151] For example, if a user is interested in data science, has Python skills, and has two years of experience as a marketing analyst, they can enter this information into the portal site, where the server stores the data and analyzes it using natural language processing models and sentiment engines.

[1152] Based on the analysis, the server generates the following suggestions:

[1153] 1. Recommended skills: Machine learning, data mining

[1154] 2. Training programs: Online courses (e.g., Coursera's machine learning course)

[1155] 3. Career Path: From Data Analyst to Data Scientist

[1156] These suggestions are notified to the user by the server and are also shared with the human resources department and managers. When the user acts on the suggestions and provides feedback, the server collects the feedback and uses it to improve the accuracy of future suggestions. In addition, the emotion engine performs emotional analysis of the feedback to provide more effective suggestions.

[1157] The above is an embodiment of the present invention. This invention allows employees to obtain career plans and skill improvement measures that are optimal for them, and enables companies to effectively support the career development of their employees.

[1158] The processing flow will be explained below.

[1159] Step 1:

[1160] Users log in to the company's portal site and enter their skill set (e.g., Python programming, data analysis), work experience (e.g., two years of experience as a data analyst), and interests (e.g., data science).

[1161] Step 2:

[1162] The terminal transmits data entered by the user, including the skill set, work history, and interests and preferences, to the server.

[1163] Step 3:

[1164] The server stores the received data in a database, which is used for subsequent analysis.

[1165] Step 4:

[1166] The server retrieves user data from the database, checks for missing values ​​and outliers, preprocesses the data as needed (e.g., normalizes data, checks for consistency), and prepares it for analysis.

[1167] Step 5:

[1168] The server uses natural language processing models to analyze a user's skill set, work history, and interests, and also references external data sources on industry trends and current trends, to generate customized career plans and skill development suggestions.

[1169] Step 6:

[1170] The server uses an emotion engine to analyze emotions based on the user's text input, voice, or facial expression data. For example, if the user is feeling anxious, the server considers reassuring suggestions.

[1171] Step 7:

[1172] The server then reflects the results of the emotion analysis in the generated career plans and skill improvement proposals, resulting in customized proposals that take emotion into consideration.

[1173] Step 8:

[1174] The server provides the completed career plan and proposal to the user's terminal, and also notifies the human resources department and manager of the same information to provide support.

[1175] Step 9:

[1176] Users review and implement the provided career plans and skill improvement suggestions, and then provide feedback on the satisfaction and feasibility of the suggestions.

[1177] Step 10:

[1178] The device sends user feedback to the server, which evaluates the effectiveness of the suggestions and uses it for future improvements.

[1179] Step 11:

[1180] The server receives the feedback, stores it in a database, and analyzes it to improve the accuracy of the natural language processing model and emotion engine, making future suggestions more effective and personalized.

[1181] In this way, the system comprehensively supports employees' career development and makes suggestions that take into consideration the user's feelings, thereby achieving higher satisfaction and effectiveness.

[1182] Example 2

[1183] 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."

[1184] In modern companies, employee career development and skill improvement are extremely important issues. However, it is difficult to provide customized career plans that take into account the needs and interests of individual employees. Furthermore, suggestions that ignore the employee's emotional state are often ineffective. Therefore, there is a need for a system that can comprehensively analyze employee information and emotions and provide optimal career plans and skill improvement suggestions.

[1185] The identification processing by the identification processing unit 290 of the data processing device 12 in Example 2 is realized by the following means. In this invention, the server includes: means for inputting data on each employee's skill set, work history, and interests and inclinations; data storage means for storing the data; means for preprocessing the stored data, filling in missing values, and normalizing the data; means for analyzing the preprocessed data and generating customized career plans and skill improvement proposals based on industry trends; an emotion engine for analyzing user emotion data and reflecting the results in the generated proposals; means for providing the generated proposals to the employee and also to the human resources department and manager; and means for collecting feedback on the proposals and improving the generation means. This enables the generation of customized proposals to effectively support employees' career development and skill improvement.

[1186] A "skill set" refers to the collection of skills and expertise that an individual employee possesses.

[1187] "Work history" refers to the history of the work, jobs, and roles an employee has performed to date.

[1188] "Interests and orientations" refer to the interests and goals that individual employees have regarding their work.

[1189] "Data storage means" means any device or method that securely stores data collected from employees and makes it available for subsequent processing.

[1190] "Preprocessing" refers to tasks such as filling in missing values ​​and normalizing data that are carried out before data analysis.

[1191] A "natural language processing model" refers to the algorithms and techniques that enable computers to understand and analyze human language.

[1192] An "emotion engine" refers to a technology that analyzes a user's text, voice, and facial expression data to understand their emotional state and utilize the results.

[1193] "Generation means" refers to a device or method that analyzes the stored data and generates customized career plans and skill improvement suggestions based on industry trends.

[1194] The "provision means" refers to a device or method for providing the generated proposal to the user, the human resources department, and the manager.

[1195] The term "feedback collection means" refers to a device or method that collects opinions and evaluations provided by users regarding the provided suggestions and uses them to improve the system.

[1196] This invention provides a virtual career mentoring system that combines a generative AI model and an emotion engine to support the career development and skill improvement of corporate employees. The system generates and provides customized career plans and skill improvement proposals by considering each employee's skills, work history, and interests and inclinations, and by analyzing the user's emotions.

[1197] The system components are:

[1198] User data input means

[1199] Data storage means

[1200] Pretreatment means

[1201] generation means

[1202] Emotion Engine

[1203] Providing means

[1204] Feedback collection methods

[1205] User data input means

[1206] Users log in to the company's portal site and enter their skill set (e.g., Java programming, database management), work experience (e.g., three years of software engineering experience), and interests (e.g., cloud computing). The entered data is registered in the system.

[1207] Data storage means

[1208] The terminal sends the data entered by the user to the server, which stores the received data in a database for subsequent processing.

[1209] Pretreatment means

[1210] The server retrieves user data from the database and performs preprocessing, including filling in missing values ​​and normalizing the data. For example, if there is a missing year, it is filled in with the average value and data scaling is performed.

[1211] generation means

[1212] The server uses natural language processing (NLP) models to perform detailed analysis of the user's skill set, work history, and interests and inclinations. As a result of the analysis, it accurately identifies the user's characteristics and generates a customized career plan and skill improvement proposals based on industry trends and the latest trends. For example, a user with "Python programming" skills could be recommended machine learning skills.

[1213] Emotion Engine

[1214] The server uses an emotion engine to analyze the user's emotional data (e.g., text, voice, facial expressions). For example, if a user enters, "I've been feeling unmotivated at work lately," the emotion engine will classify that state as "stress." This information is taken into account and reflected in the generated career plans and skill improvement suggestions. Specifically, relaxation methods for stress reduction can be added to the suggestions.

[1215] Providing means

[1216] The server notifies the user of the generated career plan and skill improvement proposals via a dashboard on the portal site or by email. The same information is also provided to the human resources department and managers, creating a support system across the company.

[1217] Feedback collection methods

[1218] The user provides feedback on the provided career plan and skill improvement suggestions. The feedback includes the effectiveness of the suggestions and the level of satisfaction. The device sends this feedback to the server, which stores the received feedback in a database. The stored feedback is used to improve the generation method and emotion engine model. This allows the system to improve the accuracy of future suggestions.

[1219] Specific examples

[1220] For example, let's say a user is interested in data science, has Python skills, and has two years of experience as a marketing analyst. When the user enters this information into the portal, their device sends the data to the server, where it is stored in a database. The server then performs analysis using natural language processing models and sentiment engines to generate suggestions such as:

[1221] 1. Recommended skills: Machine learning, data mining

[1222] 2. Training programs: Online courses (e.g., Coursera's machine learning course)

[1223] 3. Career Path: From Data Analyst to Data Scientist

[1224] These suggestions are notified to the user by the server and are also shared with the human resources department and managers. When the user acts on the suggestions and provides the results as feedback, the server collects this information and uses it to improve the accuracy of future suggestions. The emotion engine also analyzes the emotions in the feedback to provide even more effective suggestions.

[1225] Prompt Sentence Examples

[1226] "Analyze user-entered data and propose a customized career plan."

[1227] "Generate skill improvement suggestions that take into account user sentiment data."

[1228] The above is an embodiment of the present invention. This invention allows employees to obtain career plans and skill improvement measures that are optimal for them, and also enables companies to effectively support the career development of their employees.

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

[1230] Step 1: User data input

[1231] A user logs in to a company's portal site. The user enters their skill set (e.g., Java programming, database administration), work experience (e.g., three years of software engineering experience), and interests (e.g., cloud computing). The entered data is temporarily stored on the device. This is the input data in step 1. The specific actions in this step are to enter data into a text form and click the submit button.

[1232] Step 2: Data transmission and storage

[1233] The terminal sends the data entered by the user to the server. During this transmission process, the data is encrypted and transmitted using a secure communication protocol (e.g., HTTPS). The server receives the received data and stores it in a database. This is the output data of step 2. The specific operations in this step are data encryption, transmission, and recording in the database.

[1234] Step 3: Preprocessing the data

[1235] The server retrieves the stored user data from the database. This retrieved data is the input data for Step 3. The server preprocesses the data. Specifically, it imputes missing values, checks consistency, and normalizes the data. For example, it imputes missing values ​​with the mean and standard-scales the numeric data. This preprocessed data is the output data for Step 3.

[1236] Step 4: Data analysis and proposal generation

[1237] The server uses the preprocessed data to run a natural language processing (NLP) model to perform a detailed analysis of the user's skill set, work history, interests, and inclinations. This is the input data for step 4. It also collects industry trends and the latest trends from the internet and analyzes them against the user's data. A generative AI model is used to generate a customized career plan and suggestions for skill improvement. This is the output data for step 4. The specific operations in this step are NLP analysis, data matching, and generation of a career plan and suggestions.

[1238] Step 5: Sentiment Data Analysis

[1239] The server obtains the user's input text, voice, and facial expression data. This is the input data for step 5. The emotion engine analyzes this data to understand the user's emotional state. For example, if the user inputs "high stress," the emotion engine identifies this state as "stress." The results of this analysis are reflected in career plans and suggestions for skill improvement. This is the output data for step 5. The specific operations in this step are emotion analysis and feedback of the results.

[1240] Step 6: Provide a proposal

[1241] The server notifies the user of the generated career plan and skill improvement suggestions. This is the input data of step 6. This notification is sent via the portal site dashboard, email, etc. The same information is also provided to the HR department and administrators. This is the output data of step 6. The specific actions in this step are the generation and distribution of notifications.

[1242] Step 7: Gather feedback

[1243] The user provides feedback on the provided career plan and skill improvement suggestions. This is the input data for step 7. The feedback includes the effectiveness of the suggestions and the level of satisfaction. The device sends this feedback to the server. The server receives the feedback and stores it in a database. The stored feedback is used to improve the generation means and emotion engine models. This is the output data for step 7. The specific operations in this step are collecting and storing feedback and improving the model.

[1244] (Application example 2)

[1245] 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."

[1246] While there are many systems that effectively support employee career development and skill improvement, they lack the ability to provide personalized suggestions that take into account employees' emotional state. This can lead to situations where employees are unmotivated or stressed by the suggestions. Furthermore, there are limited means to collect feedback and improve the quality of suggestions, making continuous improvement difficult. Another problem is that they are unable to provide information simultaneously to not only employees but also the HR department and managers, enabling efficient career support throughout the organization.

[1247] 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.

[1248] In this invention, the server includes: a means for inputting data regarding each employee's skill set, work history, and interests and inclinations; a data storage means for storing the data; a generation means for analyzing the stored data and generating customized career plans and skill improvement proposals based on industry trends; a provision means for providing the generated proposals to the employee; a feedback collection means for collecting feedback on the proposals and improving the generation means; and an emotion analysis means for analyzing the input emotional data and reflecting the results in the proposals. This allows for personalized career plans and skill improvement proposals that take employees' emotional states into account, thereby increasing employee motivation and enabling efficient career support throughout the organization. Furthermore, the collected feedback can be used to continuously improve the system and improve the quality of proposals.

[1249] A "skill set" is the collection of skills and knowledge that an employee possesses.

[1250] "Work history" refers to the history of jobs and positions that an employee has held up to now.

[1251] "Interests and orientations" refer to the areas in which employees are interested and their orientation toward the future.

[1252] "Data storage means" refers to a device or system that stores data entered by employees.

[1253] The "generation means" is a device or system that analyzes the stored data and generates customized career plans and skill improvement proposals.

[1254] The "means for providing" refers to a device or system that presents the generated career plans and skill improvement proposals to employees.

[1255] A "feedback collection tool" is a device or system that collects information by allowing employees to input their opinions and satisfaction with the suggestions provided.

[1256] An "emotion analysis means" is a device or system that analyzes emotions from employee input data and reflects the results in proposals.

[1257] A "natural language processing model" is a machine learning model for analyzing employee and industry data, and has the ability to understand and analyze natural language.

[1258] This invention relates to a virtual career mentor system for supporting employees' career development and skill improvement. This system collects data on employees' skill sets, work history, interests, and inclinations, and also analyzes their emotions to provide optimal career plans for each employee. Specifically, it has the following configuration:

[1259] 1. User data input method

[1260] Users (employees) use smartphones or web portals to input information about their skill sets, work history, interests, and aspirations. This input data is used to inform detailed career development for employees.

[1261] 2. Data storage method

[1262] The device sends the data entered by the user to a cloud server, which then stores the data in a database, such as AWS's DynamoDB.

[1263] 3. Generation means

[1264] The server retrieves the stored data and analyzes it using a natural language processing model, such as OpenAI's GPT-4, to generate customized career plans and skill development suggestions based on the user's skill set, work history, interests, and aspirations.

[1265] 4. Emotion analysis method

[1266] The server analyzes the collected emotional data (voice, text, facial expressions, etc.) from the user using an emotion analysis engine such as Azure's Emotion API to determine the user's emotional state. This allows the server to reflect the emotional data in the generated career plans and skill improvement proposals, providing more personalized proposals.

[1267] 5. Means of provision

[1268] The server provides the generated career plan and proposal to the user, and also notifies the human resources department and managers of the information, thereby establishing a support system throughout the company.

[1269] 6. Feedback Collection Methods

[1270] Users can provide feedback on the provided career plans and skill improvement suggestions. This feedback is sent to a cloud server and stored in a database. The collected feedback is used to improve the models of the generator and sentiment analyzer.

[1271] Specific examples

[1272] For example, let's say an employee has an interest in data science, Python skills, and two years of experience as a marketing analyst. When the employee enters this information into a smartphone app, the server stores the information in a database and performs analysis. Using OpenAI's GPT-4, the analysis generates the following suggestions:

[1273] 1. Recommended skills: Machine learning, data mining

[1274] 2. Training programs: Online courses (e.g., an introductory course on machine learning)

[1275] 3. Career Path: From Data Analyst to Data Scientist

[1276] At this time, emotion analysis is performed based on the voice data entered by the employee, and if the result is that "the employee is highly motivated and has a strong interest in machine learning," this result can be reflected to "assess true interest and enthusiasm in career plans and strengthen the content of advice."

[1277] Prompt Sentence Examples

[1278] (Input information)

[1279] Skill Set: Python programming, data analysis

[1280] ·Work Experience: 2 years of experience as a marketing analyst

[1281] Interests: Data science, machine learning

[1282] (emotion data)

[1283] Users are highly motivated and have a strong interest in machine learning

[1284] The above is an embodiment of the present invention. This system allows employees to obtain career plans and skill improvement measures that are best suited to them, and enables companies to effectively support the career development of their employees.

[1285] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[1286] Step 1:

[1287] A user inputs information about their skill set, work history, and interests and aspirations via a smartphone or web portal. The information entered by the user is sent from the device to the server. Specifically, it is assumed that the user inputs "Skill set: Python programming, data analysis," "Work history: 2 years of experience as a marketing analyst," and "Interests and aspirations: data science, machine learning."

[1288] Input: User's skill set, work history, interests and preferences

[1289] Output: User data sent to the server

[1290] Step 2:

[1291] The device sends the input data from the user to a cloud server, which then stores it in a database using AWS's DynamoDB or similar.

[1292] Input: User data sent to the server

[1293] Output: User data stored in the database

[1294] Step 3:

[1295] The server retrieves the stored user data and analyzes it using a natural language processing model (e.g., OpenAI's GPT-4). It then generates a customized career plan and skill improvement suggestions based on the user's skill set, work history, interests, and aspirations. Specifically, it may suggest "recommended skills: machine learning, data mining," "training program: online courses," and "career path: from data analyst to data scientist."

[1296] Input: User data retrieved from the database

[1297] Output: Generated career plans and skill improvement suggestions

[1298] Step 4:

[1299] The user provides emotional data to the server through voice or text input, such as "I am highly motivated and have a strong interest in machine learning."

[1300] Input: User's voice data, text data

[1301] Output: Emotion data sent to the server

[1302] Step 5:

[1303] The server uses Azure's Emotion API to analyze the emotional data and evaluate the user's emotional state. The results of this evaluation are reflected in the generated career plan and skill improvement proposals. For example, adjustments may be made such as "proposing a more difficult course because the user is highly motivated."

[1304] Input: Emotion data sent to the server

[1305] Output: Parsed emotional state

[1306] Step 6:

[1307] The server provides the generated career plan and proposals to the user and simultaneously notifies the human resources department and managers, and displays them via a smartphone app or web portal.

[1308] Input: Generated career plans and skill improvement suggestions, analyzed emotional states

[1309] Output: Customization suggestions provided to the user and HR department

[1310] Step 7:

[1311] Users can provide feedback on the provided career plans and proposals through a smartphone app or web portal, which is then sent to a cloud server and stored in a database.

[1312] Input: User feedback

[1313] Output: Feedback stored in a database

[1314] Step 8:

[1315] The server analyzes the collected feedback and refines the models of the generator and sentiment analyzer to improve the quality of future suggestions, which will enable suggestions that better reflect the user's needs and emotions.

[1316] Input: Feedback stored in the database

[1317] Output: Improved generative and sentiment analysis models

[1318] 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.

[1319] 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.

[1320] 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.

[1321] [Fourth embodiment]

[1322] FIG. 7 shows an example of the configuration of a data processing system 410 according to the fourth embodiment.

[1323] 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.

[1324] 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).

[1325] 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.

[1326] 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.

[1327] 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).

[1328] 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.

[1329] 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.

[1330] 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.

[1331] 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.

[1332] 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.

[1333] 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.

[1334] 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."

[1335] This invention provides a virtual career mentor system that utilizes generative AI to support the career development and skill improvement of corporate employees. This system supports effective career development for employees by generating and providing customized career plans and skill improvement proposals that take into account the skills, work history, and interests and inclinations of each employee.

[1336] System Configuration

[1337] 1. User data input method

[1338] Users enter information about their skill sets, work history, interests and aspirations through a company's portal site.

[1339] 2. Data storage method

[1340] The terminal transmits the data entered by the user to the server;

[1341] The server stores the received data in a database.

[1342] 3. Generation means

[1343] The server retrieves the stored data and analyzes it using a natural language processing model.

[1344] The server takes into account industry trends and the latest trends to generate customized career plans and skill improvement proposals.

[1345] 4. Means of provision

[1346] The server provides the generated career plans and offers to the user.

[1347] The server also provides the same information to the human resources department and administrators, establishing a support system across the entire company.

[1348] 5. Feedback Collection Methods

[1349] Users review the proposals and provide feedback on their satisfaction and feasibility.

[1350] The device sends the feedback to the server,

[1351] The server receives the feedback, stores it in a database, and uses it to improve the model to improve the accuracy of future proposals.

[1352] Explanation of program processing

[1353] User data input means

[1354] Users access a company's portal site and log in. They enter their skill set (e.g., Java programming, database administration), work experience (e.g., three years of software engineering experience), and interests (e.g., cloud computing).

[1355] Data storage means

[1356] The terminal transmits the user's input data to the server, which stores the data in a database, which serves as the basis for analysis by the generating means.

[1357] generation means

[1358] The server retrieves user data from the database and analyzes it using a natural language processing model (e.g., generative AI), accurately capturing the user's skill set, interests, and aspirations, and generating customized career plans and skill improvement proposals that reflect industry trends and the latest developments.

[1359] Providing means

[1360] The server provides the generated career plans and proposals to the user, and also provides the same information to the human resources department and managers to enhance support for employees in implementing the proposals.

[1361] Feedback collection methods

[1362] The user implements the provided career plans and skill improvement suggestions and provides feedback on the results. The device sends the feedback to the server, which receives it and stores it in a database. The stored feedback is used to improve the model in the future, helping to increase the accuracy of the suggestions.

[1363] Specific examples

[1364] For example, if a user is interested in data science, has Python skills, and has two years of experience as a marketing analyst, the user enters this information into the portal site, where the server stores the data and analyzes it using a natural language processing model as a generation tool.

[1365] Based on the analysis, the server generates the following suggestions:

[1366] 1. Recommended skills: Machine learning, data mining

[1367] 2. Training programs: Online courses (e.g., Coursera's machine learning course)

[1368] 3. Career Path: From Data Analyst to Data Scientist

[1369] These suggestions are notified to the user by the server and are also shared with the human resources department and managers. When the user acts on the suggestions and provides feedback on the results, the server collects the feedback and uses it to improve the accuracy of future suggestions. In this way, the system effectively supports employees' career development.

[1370] The above is an embodiment of the present invention. This invention allows employees to obtain career plans and skill improvement measures that are optimal for them, and enables companies to effectively support the career development of their employees.

[1371] The processing flow will be explained below.

[1372] Step 1:

[1373] Users log into a company's portal site and enter information about their skill set, work history, and interests.

[1374] Step 2:

[1375] The terminal transmits the data entered by the user to the server.

[1376] Step 3:

[1377] The server stores the received data in a database.

[1378] Step 4:

[1379] The server retrieves user data from the database, checks for missing data or outliers, and performs preprocessing (e.g., data normalization, consistency check) as needed.

[1380] Step 5:

[1381] The server uses natural language processing models to analyze users' skill sets, work history, and interests, and also consults external data sources on industry trends and current trends.

[1382] Step 6:

[1383] Based on the analysis results, the server generates optimal career plans and suggestions for skill improvement for the user, including recommended skill sets, appropriate training programs, and career paths.

[1384] Step 7:

[1385] The server sends the generated career plan and proposal to the user's terminal, and also sends the same information to the human resources department and managers.

[1386] Step 8:

[1387] Users review the career plans and skill development suggestions provided and provide feedback.

[1388] Step 9:

[1389] The terminal transmits the user's feedback to the server.

[1390] Step 10:

[1391] The server receives the feedback and stores it in a database, which is used to improve the model in the generator.

[1392] Step 11:

[1393] The server analyzes user feedback to refine its natural language processing model, which improves the quality of future suggestions.

[1394] Example 1

[1395] 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."

[1396] For a company's employees to effectively advance their career development and skill improvement, they need customized career plans and skill improvement proposals tailored to each individual employee. However, with conventional systems, it was difficult to effectively generate and provide such customized proposals to employees. There were also insufficient means to collect feedback from employees and improve the system. This made it impossible to efficiently support employee career development.

[1397] 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.

[1398] In this invention, the server includes: a means for inputting data regarding each employee's skill set, work history, and interests and inclinations; a data storage means for storing the data; a generation means for analyzing the stored data and generating customized career plans and skill improvement proposals based on industry trends; a provision means for providing the generated proposals to the employee; a feedback collection means for collecting feedback on the proposals and improving the generation means; and a step in which the generation means acquires the user's input data and analyzes it using a natural language processing model, and a step in which the generation means generates customized career plans and skill improvement proposals tailored to the user's skills, interests, and inclinations based on the analysis results. This makes it possible to effectively generate and provide career plans and skill improvement proposals that are optimal for each employee. This system efficiently supports employee career development and promotes the growth of the entire company.

[1399] A "skill set" is the collection of specific skills and knowledge possessed by an individual employee.

[1400] "Work history" refers to the job and work history that an employee has had up to now.

[1401] "Interests and inclinations" refer to areas in which employees are interested and their hopes and inclinations regarding their future careers.

[1402] A "means for entering data" is an interface or system through which a user enters their information.

[1403] "Data storage means" refers to a storage system or database for storing data entered by a user.

[1404] The "generation means" is a mechanism that analyzes user data and generates customized career plans and proposals for improving skills.

[1405] A "natural language processing model" is an artificial intelligence model that analyzes text data, understands its meaning, and generates responses.

[1406] "Provision means" refers to a mechanism for providing the generated career plans and proposals to users and other related parties.

[1407] The "feedback collection means" is a mechanism for collecting reactions and results to suggestions received from users and using them to improve the system.

[1408] A "generative AI model" is an artificial intelligence model that uses machine learning and deep learning to analyze data and generate responses.

[1409] A "prompt" is text that you enter into a generative AI model to elicit a specific response.

[1410] The "analysis step" is the process of acquiring user data and analyzing it using a natural language processing model.

[1411] A "customized career plan" is a career development guideline that is specifically created based on the characteristics of each individual employee.

[1412] "Skills Upgrading Suggestions" are recommended training or learning programs to enhance your current skill set.

[1413] The present invention provides a virtual career mentor system that utilizes a generative AI model to support the career development and skill improvement of company employees. An embodiment of the present invention will be described in detail below.

[1414] This system mainly consists of five main parts: user data input means, data storage means, generation means, provision means, and feedback collection means.

[1415] First, the user accesses the company's portal site and logs in by entering their ID and password on the login screen. After logging in, the user enters information about their skill set, work history, and interests and aspirations. Specifically, the user enters "Python" and "database management" as skill sets, "three years of software engineering experience" as work history, and "cloud computing" as interests and aspirations.

[1416] The device then sends the entered data to a server. The hardware used for this is a regular personal computer or smartphone, and the communication protocol is HTTPS. The server then stores the received data in a database. This database uses an SQL or NoSQL data storage system.

[1417] The server retrieves the stored data periodically or whenever new data is added. It then analyzes the data using a generative AI model. This natural language processing model uses the latest machine learning algorithms to generate customized career plans and skill development suggestions based on the user's input data. Specific examples of prompts include:

[1418] User Information

[1419] Skill set: Python, Excel

[1420] Work Experience: 2 years of experience as a marketing analyst

[1421] Interests: Data Science

[1422] Proposals to generate

[1423] Training programs to help you improve your skills

[1424] Recommended Career Path

[1425] Latest trends based on industry trends

[1426] The server provides the generated career plans and proposals to the user, who can then review the proposals on the portal site. At the same time, this information is also provided to the human resources department and managers, providing them with enhanced support when implementing the proposals.

[1427] Finally, the user implements the provided career planning and skill improvement suggestions and provides feedback on the results. Feedback content may include, for example, impressions of online courses taken or progress on acquiring new skills. The device sends this feedback to the server, which stores it in a database. This feedback data is used to improve the generative AI model and help improve the accuracy of future suggestions.

[1428] As a concrete example, if a user is interested in data science, has Python skills, and two years of experience as a marketing analyst, the server can analyze the data and generate suggestions like this:

[1429] 1. Recommended skills: Machine learning, data mining

[1430] 2. Training programs: Online courses (e.g., Coursera's machine learning course)

[1431] 3. Career Path: From Data Analyst to Data Scientist

[1432] These suggestions are notified to the user by the server and are also shared with the human resources department and managers. When the user acts on the suggestions and provides feedback on the results, the server collects the feedback and uses it to improve the accuracy of future suggestions. In this way, the system effectively supports employees' career development.

[1433] The flow of the identification process in the first embodiment will be described with reference to FIG.

[1434] Step 1:

[1435] A user accesses a company's portal site and logs in. First, the user enters their ID and password for authentication. Next, they move to a data entry form on the site and enter their skill set (e.g., "Python," "database management"), work experience (e.g., "3 years of software engineering experience"), and interests and aspirations (e.g., "cloud computing"). This input data becomes the basis for subsequent processing.

[1436] Input: User-entered information about skill sets, work history, interests, and aspirations.

[1437] Output: The input data is stored on the device.

[1438] Step 2:

[1439] The device sends the user's input data to the server. Specifically, the input data is sent using the HTTPS protocol. At this time, the sent data includes the user's skill set, work history, and interests and inclinations. The sent data is then analyzed and stored on the server.

[1440] Input: Data entered by the user into the terminal.

[1441] Output: Data sent from the device to the server.

[1442] Step 3:

[1443] The server stores the received data in a database. This storage process uses a storage system (e.g., SQL database, NoSQL database). Once the data has been saved, a confirmation message is sent back to the device.

[1444] Input: Data sent from the terminal.

[1445] Output: The data stored in the database, and a confirmation message.

[1446] Step 4:

[1447] The server retrieves the stored data periodically or when new data is added, and analyzes it using a generative AI model. This analysis uses a natural language processing model. The input prompts for the generative AI model are as follows:

[1448] User Information

[1449] Skill set: Python, Excel

[1450] Work Experience: 2 years of experience as a marketing analyst

[1451] Interests: Data Science

[1452] Proposals to generate

[1453] Training programs to help you improve your skills

[1454] Recommended Career Path

[1455] Latest trends based on industry trends

[1456] Based on these prompts, the generative AI model generates customized career plans and skill development suggestions that match the user's skills, interests, and aspirations.

[1457] Input: User data stored in a database, prompts to the generative AI model.

[1458] Output: Career plan and skill improvement suggestions generated from the generative AI model.

[1459] Step 5:

[1460] The server provides the generated career plans and proposals to users, who can then view the proposals on a portal site. The same information is also provided to the human resources department and managers. This process strengthens the support system for employees when implementing the proposals.

[1461] Input: Career plans and recommendations generated from a generative AI model.

[1462] Output: Career plans and proposals provided to users, HR departments and managers.

[1463] Step 6:

[1464] Users implement the provided career planning and skill improvement suggestions and provide feedback on the results, such as their impressions of an online course they took or their progress in acquiring new skills. The device then sends this feedback to the server, which stores it in a database. The collected feedback data is used to improve the generative AI model and help refine future suggestions.

[1465] Input: Feedback data from users.

[1466] Output: Feedback data sent to the server and stored in the database.

[1467] In this way, the overall processing steps of the present system are linked, making it possible to continuously support employees' career development.

[1468] (Application example 1)

[1469] 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."

[1470] In modern factories, robots handle many work tasks, but improving the robots' performance and skills still relies on manual adjustment and management. This management method is inefficient and makes it difficult to optimize robot utilization. Furthermore, it is difficult to provide learning plans to reduce robot errors and improve work efficiency. This hinders improvements in work efficiency and productivity throughout the factory.

[1471] 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.

[1472] In this invention, the server includes means for inputting work task data and performance data of each robot, data storage means for storing the data, generation means for analyzing the stored data and generating customized learning plans and proposals for improving work efficiency based on the work efficiency of the factory, provision means for providing the generated proposals to the robot, and feedback collection means for collecting feedback on the proposals and improving the generation means. This automates the performance improvement and skill development of robots, making it possible to improve the work efficiency and productivity of the entire factory.

[1473] "Individual robot" refers to a piece of automated equipment designed to perform a specific work task within a factory.

[1474] "Work task data" refers to data including specific information about each task performed by a robot, such as the work content, procedures, and usage time.

[1475] "Performance data" refers to data that indicates the results and efficiency of work tasks performed by a robot, and includes, for example, the time it takes to complete a task, the error rate, and the availability rate.

[1476] "Data storage means" refers to a device or system for storing work task data and performance data transmitted from a robot.

[1477] "Generation means" refers to a device or system that generates suggestions for improving the efficiency and skills of a robot based on stored data.

[1478] "Providing means" refers to a device or system for notifying the robot and the administrator of the generated learning plan and suggestions for improving work efficiency.

[1479] "Feedback collection means" refers to a device or system for collecting results and reactions after the robot implements the provided suggestions.

[1480] The system of the present invention automates the improvement of the efficiency and skill of robots operating in factories. The specific implementation procedure is shown below.

[1481] <System Program>

[1482] This system is configured using the following hardware and software.

[1483] 1. Hardware:

[1484] Robots (industrial and collaborative robots): handle individual work tasks and collect performance data.

[1485] Built-in sensors: Collect real-time robot behavior and performance data.

[1486] Management server: Stores data, analyzes it, and generates proposals.

[1487] 2. Software:

[1488] Database system (e.g. MySQL, PostgreSQL): Stores robot work task data and performance data.

[1489] Generative AI models (e.g., GPT-3, BERT): Analyze robot data and generate customized learning plans and suggestions.

[1490] Robot control software (e.g. ROS): manages the robot's movements and executes the proposed plan.

[1491] Using the above hardware and software, the system operates as follows.

[1492] <System Operation>

[1493] 1. Data entry method

[1494] While the robot is performing a task, it uses built-in sensors to collect task data (e.g., part type, assembly time) and performance data (e.g., error rate, task time) in real time. This data is then sent to the management server via the terminal.

[1495] 2. Data storage method

[1496] The management server stores the received work task data and performance data in a database, thereby accumulating historical data on the robot.

[1497] 3. Generation means

[1498] The management server retrieves the robot's stored data from the database and analyzes it using the generative AI model. Based on the analysis results, it generates optimal learning plans and suggestions for improving operational efficiency for each robot. Examples include "learning new motion sequences to reduce error rates" and "proposing procedures to optimize work speed."

[1499] 4. Means of provision

[1500] The management server notifies the robot and the administrator of the generated learning plan and suggestions. The robot performs the task according to the proposed plan, and the administrator monitors and manages the robot's operation.

[1501] 5. Feedback Collection Methods

[1502] The robot performs the task based on the provided plan, and then collects and sends the resulting performance data and error feedback. The management server stores this in a database and uses this feedback data when generating the next proposal.

[1503] <Example>

[1504] For example, if a welding robot frequently makes errors in past data, the generative AI model will analyze the cause of the error and create a "learning plan to improve welding accuracy at a specific angle." This learning plan can then be applied to the welding robot to reduce errors.

[1505] <Example of prompt sentence for generative AI model>

[1506] "Analyze the welding robot's operation data from the past six months to identify the frequency and causes of errors, and generate a learning plan based on that."

[1507] In this way, this system allows robots in factories to constantly learn the latest, most efficient work procedures, which is expected to improve overall work efficiency.

[1508] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[1509] Step 1:

[1510] While the robot is performing a work task, it uses built-in sensors to collect work task data and performance data in real time.

[1511] Input: Sensor data about the robot's movements.

[1512] Data processing / data calculation: Formats data collected by built-in sensors and converts it into performance indicators such as error rates and task completion times.

[1513] Output: Collected work task and performance data.

[1514] Step 2:

[1515] The terminal transmits the collected data to the management server.

[1516] Input: Work task and performance data from the robot.

[1517] Data processing / data calculation: Encode the data for transmission to the management server using the appropriate communication protocol.

[1518] Output: The encoded data.

[1519] Step 3:

[1520] The server stores the received data in a database.

[1521] Input: The encoded data sent from the terminal.

[1522] Data processing / data operation: Decode the data and insert it into the database using an SQL query.

[1523] Output: Work task and performance data stored in a database.

[1524] Step 4:

[1525] The server retrieves the stored data from the database for analysis and inputs it into the generative AI model.

[1526] Input: Work task data and performance data in a database.

[1527] Data processing / data calculation: Use SQL queries to retrieve the necessary data from the database and convert it into a format suitable for the generative AI model.

[1528] Output: Analyzed data that is fed into a generative AI model.

[1529] Step 5:

[1530] The server inputs the analytical data into a generative AI model to generate a customized learning plan and suggestions for improving work efficiency.

[1531] Input: The data that is fed into the generative AI model.

[1532] Data processing / data calculation: Analyze data using a generative AI model to generate optimal learning plans and suggestions for improving work efficiency.

[1533] Output: Study plan and suggestions for improving work efficiency.

[1534] Step 6:

[1535] The server provides the generated learning plans and suggestions to the robot and the administrator.

[1536] Input: Study plans and suggestions for improving work efficiency.

[1537] Data processing / data calculation: Convert the proposal into the appropriate format and send it to the robot's control system and the administrator's monitoring system.

[1538] Output: Learning plans and suggestions provided to the robot and administrator.

[1539] Step 7:

[1540] The robot performs the task based on the provided learning plan and suggestions, and then collects the results again using its built-in sensors.

[1541] Input: Study plans and suggestions for improving work efficiency.

[1542] Data processing / data calculation: Adjust the robot's movement sequence based on suggestions and record new performance data collected by the built-in sensors.

[1543] Output: New performance data.

[1544] Step 8:

[1545] The terminals send the collected new performance data to the management server, which stores it in a database.

[1546] Input: New performance data.

[1547] Data processing / data calculation: Encode the data, send it using a protocol to send it to the management server, decode the received data, and save it back in the database.

[1548] Output: Feedback data stored in a database.

[1549] 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.

[1550] This invention provides a virtual career mentor system that combines generative AI and an emotion engine to support the career development and skill improvement of corporate employees. By considering each employee's skills, work history, and interests and inclinations, and by analyzing the user's emotions, the system generates and provides customized career plans and skill improvement proposals, thereby supporting effective career development for employees.

[1551] System Configuration

[1552] 1. User data input method

[1553] Users enter information about their skill sets, work history, and interests through a company portal site.

[1554] 2. Data storage method

[1555] The terminal transmits the data entered by the user to the server.

[1556] The server stores the received data in a database.

[1557] 3. Generation means

[1558] The server retrieves user data from the database, checks for missing data or outliers, and performs preprocessing (e.g., data normalization, consistency check) as needed.

[1559] The server uses natural language processing models to analyze the user's skill set, work history, and interests.

[1560] The server takes into account industry trends and the latest trends to generate customized career plans and skill improvement proposals.

[1561] 4. Emotion Engine

[1562] The server uses an emotion engine to analyze the user's emotion data (e.g., text input, voice, facial expressions).

[1563] The server reflects the analysis results of the emotion data in the generated career plan and skill improvement proposals.

[1564] 5. Means of provision

[1565] The server provides the generated career plans and proposals to the user, and also provides the same information to human resources and management.

[1566] 6. Feedback Collection Methods

[1567] Users review the proposals and provide feedback on their satisfaction and feasibility.

[1568] The terminal sends the feedback to the server.

[1569] The server receives and stores the feedback in a database, which is used to improve the models in the generator and emotion engine.

[1570] Explanation of program processing

[1571] User data input means

[1572] Users log in to a company's portal site and enter their skill set (e.g., Java programming, database administration), work experience (e.g., three years of software engineering experience), and interests (e.g., cloud computing).

[1573] Data storage means

[1574] The terminal sends the user's input data to the server, which then stores the data in a database for later processing.

[1575] generation means

[1576] The server retrieves user data from the database and analyzes it using a natural language processing model. This analysis accurately captures the user's skill set, interests, and inclinations, and generates customized career plans and skill improvement proposals that reflect industry trends and the latest trends.

[1577] Emotion Engine

[1578] The server uses an emotion engine to analyze the user's emotional data. For example, it analyzes the text, voice, or facial expression data entered by the user to understand the user's current emotional state. The results of this analysis are reflected in the generated career plan and skill improvement proposals. This allows the proposals to match the user's emotional state and become more personalized.

[1579] Providing means

[1580] The server provides the generated career plans and proposals to the user, and also provides the same information to the human resources department and managers, establishing a support system throughout the company.

[1581] Feedback collection methods

[1582] The user implements the provided career plan and skill improvement suggestions and provides feedback on the results. The device sends the feedback to the server, which receives it and stores it in a database. The stored feedback is used to improve the models in the emotion engine and generation means, thereby improving the quality of future suggestions.

[1583] Specific examples

[1584] For example, if a user is interested in data science, has Python skills, and has two years of experience as a marketing analyst, they can enter this information into the portal site, where the server stores the data and analyzes it using natural language processing models and sentiment engines.

[1585] Based on the analysis, the server generates the following suggestions:

[1586] 1. Recommended skills: Machine learning, data mining

[1587] 2. Training programs: Online courses (e.g., Coursera's machine learning course)

[1588] 3. Career Path: From Data Analyst to Data Scientist

[1589] These suggestions are notified to the user by the server and are also shared with the human resources department and managers. When the user acts on the suggestions and provides feedback, the server collects the feedback and uses it to improve the accuracy of future suggestions. In addition, the emotion engine performs emotional analysis of the feedback to provide more effective suggestions.

[1590] The above is an embodiment of the present invention. This invention allows employees to obtain career plans and skill improvement measures that are optimal for them, and enables companies to effectively support the career development of their employees.

[1591] The processing flow will be explained below.

[1592] Step 1:

[1593] Users log in to the company's portal site and enter their skill set (e.g., Python programming, data analysis), work experience (e.g., two years of experience as a data analyst), and interests (e.g., data science).

[1594] Step 2:

[1595] The terminal transmits data entered by the user, including the skill set, work history, and interests and preferences, to the server.

[1596] Step 3:

[1597] The server stores the received data in a database, which is used for subsequent analysis.

[1598] Step 4:

[1599] The server retrieves user data from the database, checks for missing values ​​and outliers, preprocesses the data as needed (e.g., normalizes data, checks for consistency), and prepares it for analysis.

[1600] Step 5:

[1601] The server uses natural language processing models to analyze a user's skill set, work history, and interests, and also references external data sources on industry trends and current trends, to generate customized career plans and skill development suggestions.

[1602] Step 6:

[1603] The server uses an emotion engine to analyze emotions based on the user's text input, voice, or facial expression data. For example, if the user is feeling anxious, the server considers reassuring suggestions.

[1604] Step 7:

[1605] The server then reflects the results of the emotion analysis in the generated career plans and skill improvement proposals, resulting in customized proposals that take emotion into consideration.

[1606] Step 8:

[1607] The server provides the completed career plan and proposal to the user's terminal, and also notifies the human resources department and manager of the same information to provide support.

[1608] Step 9:

[1609] Users review and implement the provided career plans and skill improvement suggestions, and then provide feedback on the satisfaction and feasibility of the suggestions.

[1610] Step 10:

[1611] The device sends user feedback to the server, which evaluates the effectiveness of the suggestions and uses it for future improvements.

[1612] Step 11:

[1613] The server receives the feedback, stores it in a database, and analyzes it to improve the accuracy of the natural language processing model and emotion engine, making future suggestions more effective and personalized.

[1614] In this way, the system comprehensively supports employees' career development and makes suggestions that take into consideration the user's feelings, thereby achieving higher satisfaction and effectiveness.

[1615] Example 2

[1616] 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."

[1617] In modern companies, employee career development and skill improvement are extremely important issues. However, it is difficult to provide customized career plans that take into account the needs and interests of individual employees. Furthermore, suggestions that ignore the employee's emotional state are often ineffective. Therefore, there is a need for a system that can comprehensively analyze employee information and emotions and provide optimal career plans and skill improvement suggestions.

[1618] The identification processing by the identification processing unit 290 of the data processing device 12 in Example 2 is realized by the following means. In this invention, the server includes: means for inputting data on each employee's skill set, work history, and interests and inclinations; data storage means for storing the data; means for preprocessing the stored data, filling in missing values, and normalizing the data; means for analyzing the preprocessed data and generating customized career plans and skill improvement proposals based on industry trends; an emotion engine for analyzing user emotion data and reflecting the results in the generated proposals; means for providing the generated proposals to the employee and also to the human resources department and manager; and means for collecting feedback on the proposals and improving the generation means. This enables the generation of customized proposals to effectively support employees' career development and skill improvement.

[1619] A "skill set" refers to the collection of skills and expertise that an individual employee possesses.

[1620] "Work history" refers to the history of the work, jobs, and roles an employee has performed to date.

[1621] "Interests and orientations" refer to the interests and goals that individual employees have regarding their work.

[1622] "Data storage means" means any device or method that securely stores data collected from employees and makes it available for subsequent processing.

[1623] "Preprocessing" refers to tasks such as filling in missing values ​​and normalizing data that are carried out before data analysis.

[1624] A "natural language processing model" refers to the algorithms and techniques that enable computers to understand and analyze human language.

[1625] An "emotion engine" refers to a technology that analyzes a user's text, voice, and facial expression data to understand their emotional state and utilize the results.

[1626] "Generation means" refers to a device or method that analyzes the stored data and generates customized career plans and skill improvement suggestions based on industry trends.

[1627] The "provision means" refers to a device or method for providing the generated proposal to the user, the human resources department, and the manager.

[1628] The term "feedback collection means" refers to a device or method that collects opinions and evaluations provided by users regarding the provided suggestions and uses them to improve the system.

[1629] This invention provides a virtual career mentoring system that combines a generative AI model and an emotion engine to support the career development and skill improvement of corporate employees. The system generates and provides customized career plans and skill improvement proposals by considering each employee's skills, work history, and interests and inclinations, and by analyzing the user's emotions.

[1630] The system components are:

[1631] User data input means

[1632] Data storage means

[1633] Pretreatment means

[1634] generation means

[1635] Emotion Engine

[1636] Providing means

[1637] Feedback collection methods

[1638] User data input means

[1639] Users log in to the company's portal site and enter their skill set (e.g., Java programming, database management), work experience (e.g., three years of software engineering experience), and interests (e.g., cloud computing). The entered data is registered in the system.

[1640] Data storage means

[1641] The terminal sends the data entered by the user to the server, which stores the received data in a database for subsequent processing.

[1642] Pretreatment means

[1643] The server retrieves user data from the database and performs preprocessing, including filling in missing values ​​and normalizing the data. For example, if there is a missing year, it is filled in with the average value and data scaling is performed.

[1644] generation means

[1645] The server uses natural language processing (NLP) models to perform detailed analysis of the user's skill set, work history, and interests and inclinations. As a result of the analysis, it accurately identifies the user's characteristics and generates a customized career plan and skill improvement proposals based on industry trends and the latest trends. For example, a user with "Python programming" skills could be recommended machine learning skills.

[1646] Emotion Engine

[1647] The server uses an emotion engine to analyze the user's emotional data (e.g., text, voice, facial expressions). For example, if a user enters, "I've been feeling unmotivated at work lately," the emotion engine will classify that state as "stress." This information is taken into account and reflected in the generated career plans and skill improvement suggestions. Specifically, relaxation methods for stress reduction can be added to the suggestions.

[1648] Providing means

[1649] The server notifies the user of the generated career plan and skill improvement proposals via a dashboard on the portal site or by email. The same information is also provided to the human resources department and managers, creating a support system across the company.

[1650] Feedback collection methods

[1651] The user provides feedback on the provided career plan and skill improvement suggestions. The feedback includes the effectiveness of the suggestions and the level of satisfaction. The device sends this feedback to the server, which stores the received feedback in a database. The stored feedback is used to improve the generation method and emotion engine model. This allows the system to improve the accuracy of future suggestions.

[1652] Specific examples

[1653] For example, let's say a user is interested in data science, has Python skills, and has two years of experience as a marketing analyst. When the user enters this information into the portal, their device sends the data to the server, where it is stored in a database. The server then performs analysis using natural language processing models and sentiment engines to generate suggestions such as:

[1654] 1. Recommended skills: Machine learning, data mining

[1655] 2. Training programs: Online courses (e.g., Coursera's machine learning course)

[1656] 3. Career Path: From Data Analyst to Data Scientist

[1657] These suggestions are notified to the user by the server and are also shared with the human resources department and managers. When the user acts on the suggestions and provides the results as feedback, the server collects this information and uses it to improve the accuracy of future suggestions. The emotion engine also analyzes the emotions in the feedback to provide even more effective suggestions.

[1658] Prompt Sentence Examples

[1659] "Analyze user-entered data and propose a customized career plan."

[1660] "Generate skill improvement suggestions that take into account user sentiment data."

[1661] The above is an embodiment of the present invention. This invention allows employees to obtain career plans and skill improvement measures that are optimal for them, and also enables companies to effectively support the career development of their employees.

[1662] The flow of the identification process in the second embodiment will be described with reference to FIG.

[1663] Step 1: User data input

[1664] A user logs in to a company's portal site. The user enters their skill set (e.g., Java programming, database administration), work experience (e.g., three years of software engineering experience), and interests (e.g., cloud computing). The entered data is temporarily stored on the device. This is the input data in step 1. The specific actions in this step are to enter data into a text form and click the submit button.

[1665] Step 2: Data transmission and storage

[1666] The terminal sends the data entered by the user to the server. During this transmission process, the data is encrypted and transmitted using a secure communication protocol (e.g., HTTPS). The server receives the received data and stores it in a database. This is the output data of step 2. The specific operations in this step are data encryption, transmission, and recording in the database.

[1667] Step 3: Preprocessing the data

[1668] The server retrieves the stored user data from the database. This retrieved data is the input data for Step 3. The server preprocesses the data. Specifically, it imputes missing values, checks consistency, and normalizes the data. For example, it imputes missing values ​​with the mean and standard-scales the numeric data. This preprocessed data is the output data for Step 3.

[1669] Step 4: Data analysis and proposal generation

[1670] The server uses the preprocessed data to run a natural language processing (NLP) model to perform a detailed analysis of the user's skill set, work history, interests, and inclinations. This is the input data for step 4. It also collects industry trends and the latest trends from the internet and analyzes them against the user's data. A generative AI model is used to generate a customized career plan and suggestions for skill improvement. This is the output data for step 4. The specific operations in this step are NLP analysis, data matching, and generation of a career plan and suggestions.

[1671] Step 5: Sentiment Data Analysis

[1672] The server obtains the user's input text, voice, and facial expression data. This is the input data for step 5. The emotion engine analyzes this data to understand the user's emotional state. For example, if the user inputs "high stress," the emotion engine identifies this state as "stress." The results of this analysis are reflected in career plans and suggestions for skill improvement. This is the output data for step 5. The specific operations in this step are emotion analysis and feedback of the results.

[1673] Step 6: Provide a proposal

[1674] The server notifies the user of the generated career plan and skill improvement suggestions. This is the input data of step 6. This notification is sent via the portal site dashboard, email, etc. The same information is also provided to the HR department and administrators. This is the output data of step 6. The specific actions in this step are the generation and distribution of notifications.

[1675] Step 7: Gather feedback

[1676] The user provides feedback on the provided career plan and skill improvement suggestions. This is the input data for step 7. The feedback includes the effectiveness of the suggestions and the level of satisfaction. The device sends this feedback to the server. The server receives the feedback and stores it in a database. The stored feedback is used to improve the generation means and emotion engine models. This is the output data for step 7. The specific operations in this step are collecting and storing feedback and improving the model.

[1677] (Application example 2)

[1678] 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."

[1679] While there are many systems that effectively support employee career development and skill improvement, they lack the ability to provide personalized suggestions that take into account employees' emotional state. This can lead to situations where employees are unmotivated or stressed by the suggestions. Furthermore, there are limited means to collect feedback and improve the quality of suggestions, making continuous improvement difficult. Another problem is that they are unable to provide information simultaneously to not only employees but also the HR department and managers, enabling efficient career support throughout the organization.

[1680] 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.

[1681] In this invention, the server includes: a means for inputting data regarding each employee's skill set, work history, and interests and inclinations; a data storage means for storing the data; a generation means for analyzing the stored data and generating customized career plans and skill improvement proposals based on industry trends; a provision means for providing the generated proposals to the employee; a feedback collection means for collecting feedback on the proposals and improving the generation means; and an emotion analysis means for analyzing the input emotional data and reflecting the results in the proposals. This allows for personalized career plans and skill improvement proposals that take employees' emotional states into account, thereby increasing employee motivation and enabling efficient career support throughout the organization. Furthermore, the collected feedback can be used to continuously improve the system and improve the quality of proposals.

[1682] A "skill set" is the collection of skills and knowledge that an employee possesses.

[1683] "Work history" refers to the history of jobs and positions that an employee has held up to now.

[1684] "Interests and orientations" refer to the areas in which employees are interested and their orientation toward the future.

[1685] "Data storage means" refers to a device or system that stores data entered by employees.

[1686] The "generation means" is a device or system that analyzes the stored data and generates customized career plans and skill improvement proposals.

[1687] The "means for providing" refers to a device or system that presents the generated career plans and skill improvement proposals to employees.

[1688] A "feedback collection tool" is a device or system that collects information by allowing employees to input their opinions and satisfaction with the suggestions provided.

[1689] An "emotion analysis means" is a device or system that analyzes emotions from employee input data and reflects the results in proposals.

[1690] A "natural language processing model" is a machine learning model for analyzing employee and industry data, and has the ability to understand and analyze natural language.

[1691] This invention relates to a virtual career mentor system for supporting employees' career development and skill improvement. This system collects data on employees' skill sets, work history, interests, and inclinations, and also analyzes their emotions to provide optimal career plans for each employee. Specifically, it has the following configuration:

[1692] 1. User data input method

[1693] Users (employees) use smartphones or web portals to input information about their skill sets, work history, interests, and aspirations. This input data is used to inform detailed career development for employees.

[1694] 2. Data storage method

[1695] The device sends the data entered by the user to a cloud server, which then stores the data in a database, such as AWS's DynamoDB.

[1696] 3. Generation means

[1697] The server retrieves the stored data and analyzes it using a natural language processing model, such as OpenAI's GPT-4, to generate customized career plans and skill development suggestions based on the user's skill set, work history, interests, and aspirations.

[1698] 4. Emotion analysis method

[1699] The server analyzes the collected emotional data (voice, text, facial expressions, etc.) from the user using an emotion analysis engine such as Azure's Emotion API to determine the user's emotional state. This allows the server to reflect the emotional data in the generated career plans and skill improvement proposals, providing more personalized proposals.

[1700] 5. Means of provision

[1701] The server provides the generated career plan and proposal to the user, and also notifies the human resources department and managers of the information, thereby establishing a support system throughout the company.

[1702] 6. Feedback Collection Methods

[1703] Users can provide feedback on the provided career plans and skill improvement suggestions. This feedback is sent to a cloud server and stored in a database. The collected feedback is used to improve the models of the generator and sentiment analyzer.

[1704] Specific examples

[1705] For example, let's say an employee has an interest in data science, Python skills, and two years of experience as a marketing analyst. When the employee enters this information into a smartphone app, the server stores the information in a database and performs analysis. Using OpenAI's GPT-4, the analysis generates the following suggestions:

[1706] 1. Recommended skills: Machine learning, data mining

[1707] 2. Training programs: Online courses (e.g., an introductory course on machine learning)

[1708] 3. Career Path: From Data Analyst to Data Scientist

[1709] At this time, emotion analysis is performed based on the voice data entered by the employee, and if the result is that "the employee is highly motivated and has a strong interest in machine learning," this result can be reflected to "assess true interest and enthusiasm in career plans and strengthen the content of advice."

[1710] Prompt Sentence Examples

[1711] (Input information)

[1712] Skill Set: Python programming, data analysis

[1713] ·Work Experience: 2 years of experience as a marketing analyst

[1714] Interests: Data science, machine learning

[1715] (emotion data)

[1716] Users are highly motivated and have a strong interest in machine learning

[1717] The above is an embodiment of the present invention. This system allows employees to obtain career plans and skill improvement measures that are best suited to them, and enables companies to effectively support the career development of their employees.

[1718] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[1719] Step 1:

[1720] A user inputs information about their skill set, work history, and interests and aspirations via a smartphone or web portal. The information entered by the user is sent from the device to the server. Specifically, it is assumed that the user inputs "Skill set: Python programming, data analysis," "Work history: 2 years of experience as a marketing analyst," and "Interests and aspirations: data science, machine learning."

[1721] Input: User's skill set, work history, interests and preferences

[1722] Output: User data sent to the server

[1723] Step 2:

[1724] The device sends the input data from the user to a cloud server, which then stores it in a database using AWS's DynamoDB or similar.

[1725] Input: User data sent to the server

[1726] Output: User data stored in the database

[1727] Step 3:

[1728] The server retrieves the stored user data and analyzes it using a natural language processing model (e.g., OpenAI's GPT-4). It then generates a customized career plan and skill improvement suggestions based on the user's skill set, work history, interests, and aspirations. Specifically, it may suggest "recommended skills: machine learning, data mining," "training program: online courses," and "career path: from data analyst to data scientist."

[1729] Input: User data retrieved from the database

[1730] Output: Generated career plans and skill improvement suggestions

[1731] Step 4:

[1732] The user provides emotional data to the server through voice or text input, such as "I am highly motivated and have a strong interest in machine learning."

[1733] Input: User's voice data, text data

[1734] Output: Emotion data sent to the server

[1735] Step 5:

[1736] The server uses Azure's Emotion API to analyze the emotional data and evaluate the user's emotional state. The results of this evaluation are reflected in the generated career plan and skill improvement proposals. For example, adjustments may be made such as "proposing a more difficult course because the user is highly motivated."

[1737] Input: Emotion data sent to the server

[1738] Output: Parsed emotional state

[1739] Step 6:

[1740] The server provides the generated career plan and proposals to the user and simultaneously notifies the human resources department and managers, and displays them via a smartphone app or web portal.

[1741] Input: Generated career plans and skill improvement suggestions, analyzed emotional states

[1742] Output: Customization suggestions provided to the user and HR department

[1743] Step 7:

[1744] Users can provide feedback on the provided career plans and proposals through a smartphone app or web portal, which is then sent to a cloud server and stored in a database.

[1745] Input: User feedback

[1746] Output: Feedback stored in a database

[1747] Step 8:

[1748] The server analyzes the collected feedback and refines the models of the generator and sentiment analyzer to improve the quality of future suggestions, which will enable suggestions that better reflect the user's needs and emotions.

[1749] Input: Feedback stored in the database

[1750] Output: Improved generative and sentiment analysis models

[1751] 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.

[1752] 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.

[1753] 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.

[1754] 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.

[1755] FIG. 9 illustrates an emotion map 400 on which multiple emotions are mapped. In the emotion map 400, emotions are arranged in concentric circles radiating from the center. Emotions closer to the center of the concentric circles are more primitive. Emotions representing states and behaviors arising from a state of mind are arranged on the outer edges of the concentric circles. The concept of emotion includes both affect and mental states. Emotions generally generated from reactions occurring in the brain are arranged on the left side of the concentric circles. Emotions generally induced by situational judgment are arranged on the right side of the concentric circles. Emotions generally generated from reactions occurring in the brain and induced by situational judgment are arranged on the upper and lower sides of the concentric circles. Furthermore, the emotion of "pleasure" is arranged on the upper side of the concentric circles, and the emotion of "discomfort" is arranged on the lower side. In this way, in the emotion map 400, multiple emotions are mapped based on the structure by which emotions are generated, and emotions that tend to occur simultaneously are mapped close to each other.

[1756] 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.

[1757] 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).

[1758] 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.

[1759] 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."

[1760] 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.

[1761] 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).

[1762] 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.

[1763] 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.

[1764] 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.

[1765] 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.

[1766] 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.

[1767] 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.

[1768] 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.

[1769] 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.

[1770] 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.

[1771] 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.

[1772] The following is further disclosed regarding the above embodiment.

[1773] (Claim 1)

[1774] A means of inputting data about each employee's skill set, work history, and interests;

[1775] a data storage means for storing the data;

[1776] generating means for analyzing the stored data and generating customized career plans and skill improvement proposals based on industry trends;

[1777] providing means for providing the generated proposals to the employees;

[1778] feedback collection means for collecting feedback on said suggestions and for improving said generating means;

[1779] A system including:

[1780] (Claim 2)

[1781] 2. The system of claim 1, wherein the generating means analyzes the employee data and industry trend data using a natural language processing model.

[1782] (Claim 3)

[1783] 2. The system according to claim 1, wherein the providing means simultaneously provides the employee and the human resources department or manager with a career plan and suggestions for skill improvement.

[1784] "Example 1"

[1785] (Claim 1)

[1786] A means of inputting data about each employee's skill set, work history, and interests;

[1787] a data storage means for storing the data;

[1788] generating means for analyzing the stored data and generating customized career plans and skill improvement proposals based on industry trends;

[1789] providing means for providing the generated proposals to the employees;

[1790] feedback collection means for collecting feedback on said suggestions and for improving said generating means;

[1791] the generation means acquiring user input data and analyzing it using a natural language processing model;

[1792] generating a customized career plan and skill improvement proposals based on the analysis results, which are tailored to the user's skills, interests, and inclinations;

[1793] A system including:

[1794] (Claim 2)

[1795] The system of claim 1, wherein the generating means analyzes the employee data and industry trend data by inputting prompts to a generating AI model and performing analysis.

[1796] (Claim 3)

[1797] 2. The system according to claim 1, wherein the providing means simultaneously provides the employee and the human resources department or manager with a career plan and suggestions for skill improvement.

[1798] "Application Example 1"

[1799] (Claim 1)

[1800] a means for inputting work task data and performance data for each robot;

[1801] a data storage means for storing the data;

[1802] a generating means for analyzing the stored data and generating a customized learning plan and a proposal for improving work efficiency based on the work efficiency of the factory;

[1803] providing means for providing the generated proposal to the robot;

[1804] feedback collection means for collecting feedback on said suggestions and for improving said generating means;

[1805] A system including:

[1806] (Claim 2)

[1807] The system of claim 1, wherein the generating means analyzes the robot data and business data using a generative AI model.

[1808] (Claim 3)

[1809] 2. The system according to claim 1, wherein the providing means simultaneously provides the robot and the manager with a learning plan and suggestions for improving work efficiency.

[1810] "Example 2: Combining Emotion Engines"

[1811] (Claim 1)

[1812] A means of inputting data about each employee's skill set, work history, and interests;

[1813] a data storage means for storing the data;

[1814] means for preprocessing the stored data, complementing missing values, and normalizing the data;

[1815] a generating means for analyzing the pre-processed data and generating customized career plans and skill improvement proposals based on industry trends;

[1816] an emotion engine that analyzes user emotion data and reflects it in generated suggestions;

[1817] providing means for providing the generated proposals to the employee and also to a human resources department and a manager;

[1818] feedback collection means for collecting feedback on said suggestions and for improving said generating means;

[1819] A system including:

[1820] (Claim 2)

[1821] 2. The system of claim 1, wherein the generating means uses a natural language processing model to analyze the employee data and industry trend data to generate customized recommendations.

[1822] (Claim 3)

[1823] 2. The system of claim 1, wherein the emotion engine analyzes text, voice, and facial expression data of a user to understand the user's emotional state.

[1824] "Application example 2 when combining emotion engines"

[1825] (Claim 1)

[1826] A means of inputting data about each employee's skill set, work history, and interests;

[1827] a data storage means for storing the data;

[1828] generating means for analyzing the stored data and generating customized career plans and skill improvement proposals based on industry trends;

[1829] providing means for providing the generated proposals to the employees;

[1830] feedback collection means for collecting feedback on said suggestions and for improving said generating means;

[1831] an emotion analysis means for analyzing input emotion data and reflecting the data in the proposal;

[1832] A system including:

[1833] (Claim 2)

[1834] 2. The system of claim 1, wherein the generating means analyzes the employee data and industry trend data using a natural language processing model.

[1835] (Claim 3)

[1836] 2. The system according to claim 1, wherein the providing means simultaneously provides the employee and the human resources department or manager with a career plan and suggestions for skill improvement.

[1837] (Claim 4)

[1838] 2. The system of claim 1, wherein the emotion analysis means uses voice data, text data, or facial expression data to assess the employee's emotional state.

[1839] (Claim 5)

[1840] 5. The system according to claim 4, wherein the generated proposals are provided with personalized career plans and skill improvement proposals by incorporating employee emotional data. [Explanation of symbols]

[1841] 10, 210, 310, 410 Data Processing Systems 12 Data Processing Device 14 Smart Devices 214 Smart Glasses 314 Headset-type terminal 414 Robot< / url:> < / url:> < / url:> < / url:>

Claims

1. A means of inputting data about each employee's skill set, work history, and interests; a data storage means for storing the data; generating means for analyzing the stored data and generating customized career plans and skill improvement proposals based on industry trends; providing means for providing the generated proposals to the employees; feedback collection means for collecting feedback on said suggestions and for improving said generating means; A system including:

2. The system of claim 1 , wherein the generating means analyzes the employee data and industry trend data using a natural language processing model.

3. 2. The system according to claim 1, wherein the providing means simultaneously provides the employee and the human resources department or manager with a career plan and a proposal for skill improvement.

Images