System

Abstract

A system is provided.SOLUTION: A system comprising: means for providing an interactive interface for inputting employee skills, experiences, and desired positions; means for collecting and analyzing said employee interactions; means for generating and storing employee profile data based on said analysis; means for matching said profile data with enterprise needs and generating optimal staffing plans; means for presenting said generated staffing plans to employees and receiving feedback; and means for re-evaluating and generating re-staffing plans based on said feedback.SELECTED DRAWING: Figure 1

Description

[Technical Field]

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

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

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

[0004] The inability to accurately grasp employees' abilities and desires leads to mismatched placements, resulting in lower productivity and a weakened organizational competitiveness. Current methods make it difficult to optimize personnel placements, and empathetic care and development of employees may be insufficient. Furthermore, the needs of companies and the desires of employees do not always match, so a system that can effectively bridge this gap is needed. [Means for solving the problem]

[0005] The present invention provides a system that includes an interactive interface providing means for inputting employee skills, experience, and desired positions, a natural language processing algorithm processing means for collecting and analyzing the content of employee dialogue, and a profile management means for generating and saving employee profile data based on the analysis results. Furthermore, the system also includes a matching algorithm processing means for matching the profile data with the company's needs to generate optimal personnel placement plans, a means for presenting the generated placement plans to employees and receiving feedback, and an optimization means for reevaluating and generating reallocation plans based on the feedback. This allows companies to optimally assign personnel based on the characteristics and preferences of their employees, improving the productivity and efficiency of the entire organization.

[0006] The "interactive interface providing means" is a means for providing a user interface for employees to interactively input information such as their skills, experience, and desired position.

[0007] The "natural language processing algorithm processing means" is a means for executing an algorithm to analyze the content of an employee's dialogue and extract information such as skills, experience, and preferences.

[0008] The "profile management means" is a means for generating employee profile data from data analyzed by the natural language processing algorithm processing means, and for storing and managing this data.

[0009] The "matching algorithm processing means" is a means for executing an algorithm to match the generated profile data with the needs of the company and generate an optimal personnel allocation plan.

[0010] The "optimization method" is a method that reevaluates employees based on feedback, employs a machine learning model that continuously learns, and generates redeployment plans.

[0011] An "employee" refers to an individual person employed by a company, and is the entity that provides information such as their skills, experience, and aspirations to the system.

[0012] "Profile data" is structured data that includes an employee's skills, experience, desired position, and past evaluations and achievements.

[0013] "Company needs" refers to the skills and role requirements a company has for a particular position or project. [Brief explanation of the drawings]

[0014] [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

[0015] 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.

[0016] First, the terms used in the following description will be explained.

[0017] 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).

[0018] 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.

[0019] 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.

[0020] 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.

[0021] 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."

[0022] [First embodiment]

[0023] FIG. 1 shows an example of the configuration of a data processing system 10 according to the first embodiment.

[0024] 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.

[0025] 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).

[0026] 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.

[0027] 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.

[0028] 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.

[0029] 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.

[0030] FIG. 2 shows an example of the main functions of the data processing device 12 and the smart device 14.

[0031] 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.

[0032] 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.

[0033] 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.

[0034] 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."

[0035] A specific embodiment for realizing the system of the present invention will be described. In this system, three parties, a server, a terminal, and a user, each play their respective roles and work together to optimally allocate employees.

[0036] Server Processing

[0037] 1. Data Collection

[0038] The server receives the user (employee) input data sent from the terminal, including skills, experience, desired position, etc. This data is stored in a database within the server.

[0039] 2. Data Analysis

[0040] The server runs a natural language processing (NLP) algorithm on the collected data to analyze it. Through the analysis, keywords such as employee skills, experience, and aspirations are extracted. Employee profile data is generated using the extracted data.

[0041] 3. Profile Management

[0042] The generated profile data is stored as structured data containing the employee's detailed skill set and desired position, allowing employees to see their capabilities at a glance.

[0043] 4. Proposal for optimal layout

[0044] The server runs a matching algorithm that matches employee profile data with the company's current needs (open positions and project requirements). The algorithm matches employee skills with the company's needs and generates optimal placement proposals.

[0045] 5. Reassess and optimize

[0046] The server receives feedback from employees and re-evaluates them based on this feedback. The re-evaluation uses a continuously learning machine learning model to regenerate placement proposals based on the feedback.

[0047] Terminal handling

[0048] 1. Providing a conversational interface

[0049] The terminal provides the user (employee) with an interactive interface through which the user can input information such as skills, experience, and desired position.

[0050] 2. Data transmission

[0051] The terminal transmits the information input by the user to the server in real time, allowing the server to receive the necessary data immediately.

[0052] 3. Displaying the results

[0053] The device displays the profile data and optimal placement proposals received from the server to the user, who can then review the placement proposals and provide feedback.

[0054] User Action

[0055] 1. Enter your information

[0056] The user uses the interactive interface of the terminal to input information such as his / her skills, experience, desired position, etc. This information is then sent from the terminal to the server.

[0057] 2. Providing Feedback

[0058] Users can input feedback on the placement proposals from the server, such as, "This position is interesting, but I would prefer a role that allows for more leadership."

[0059] Specific examples

[0060] For example, if an employee enters, "I have five years of software development experience, and I'm particularly good at Python and Java," the device sends this information to the server. The server uses natural language processing to analyze the employee's skills and experience and generate profile data. The server then matches this profile data with the company's needs and generates an optimal placement proposal. For example, it might suggest, "A software engineer position on a new AI project would be suitable." The device displays this proposal to the user, who then provides feedback, saying, "I'd also like to demonstrate leadership skills." Through reevaluation, the server again proposes the "leadership position on a new AI project."

[0061] As a result, the system of the present invention can realize optimal personnel allocation based on the characteristics and desires of each employee, thereby improving the productivity and efficiency of the entire company.

[0062] The processing flow will be explained below.

[0063] Step 1: The user initiates the interaction

[0064] Users access an interactive interface on their device and enter their skills, experience, and desired position, for example, "I have five years of software development experience, and I am particularly skilled in Python and Java."

[0065] Step 2: The device sends user input to the server

[0066] The device sends the information entered by the user to the server in real time, using API requests to transfer this data to the server.

[0067] Step 3: The server receives and stores the data

[0068] The server receives the user's input data sent from the terminal and stores it in a database, including skills, experience, desired position, etc.

[0069] Step 4: The server performs the data analysis

[0070] The server analyzes the stored data using natural language processing (NLP) algorithms, extracting keywords such as skills, experience, and aspirations, and converting them into structured data.

[0071] Step 5: The server generates the profile data

[0072] The server generates user profile data based on the extracted keywords, which includes the user's skill set, experience, and desired position.

[0073] Step 6: The server saves the profile data

[0074] The server stores the generated profile data in a database, which allows detailed employee information to be managed.

[0075] Step 7: The server gets the company's needs

[0076] The server retrieves data from a database about the company's current needs and open positions, including the skill requirements and responsibilities for each position.

[0077] Step 8: The server generates the optimal placement plan

[0078] The server runs a matching algorithm to match users' profile data with the company's needs, and generates optimal staffing recommendations based on skill matching and role compatibility.

[0079] Step 9: The server sends the placement plan to the device.

[0080] The server sends the generated placement plan to the terminal, allowing the user to check the proposed content.

[0081] Step 10: The device displays the layout plan to the user.

[0082] The terminal displays the placement proposal received from the server to the user, specifically displaying details of the placement proposal (e.g., a software engineer position for a new project).

[0083] Step 11: Users provide feedback

[0084] The user can then provide feedback on the proposed placement, such as, "This position is interesting, but I would also like to demonstrate leadership."

[0085] Step 12: Device sends feedback to server

[0086] The device receives the user's feedback and sends it to the server. The device forwards the feedback to the server using an API request.

[0087] Step 13: Server performs re-evaluation

[0088] The server reevaluates the system based on user feedback and uses a machine learning model to generate optimal relocation plans.

[0089] Step 14: The server sends the reevaluation result to the terminal.

[0090] The server transmits the re-evaluation results to the terminal, and the regenerated placement plan is transferred to the terminal.

[0091] Step 15: The terminal displays the reevaluation results to the user

[0092] The device displays the reevaluation results received from the server to the user, for example, "You are recommended for a leadership position in a new AI project."

[0093] Through these steps, the system of the present invention can realize optimal personnel allocation based on the characteristics and desires of employees, thereby improving productivity and efficiency across the entire company.

[0094] Example 1

[0095] 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."

[0096] Modern companies are required to assign personnel to positions that optimally reflect the characteristics and preferences of their employees. However, it is difficult to effectively collect and analyze employee skills, experience, and desired positions, and to assign personnel to positions that optimally meet the company's needs. Another challenge is collecting feedback from employees in real time and reevaluating and optimizing assignment plans based on that feedback.

[0097] 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.

[0098] In this invention, the server includes: an interactive interface providing means for inputting employee skills, experience, and desired positions; a natural language processing algorithm processing means for collecting and analyzing the content of the employee's dialogue; a profile management means for generating and saving employee profile data based on the analysis results; a matching algorithm processing means for matching the profile data with the company's needs and generating optimal personnel placement plans; a means for presenting the generated placement plans to employees and receiving feedback; an optimization means for reevaluating based on the feedback and generating reallocation plans; a data transmission means for transmitting information input by employees using the interface to the server; a means for the server to store the employee's input data in a database; and a means for the server to optimize the placement plans using a machine learning model. This enables companies to achieve optimal personnel placement based on the characteristics and preferences of their employees, thereby improving the productivity and efficiency of the entire company.

[0099] The "interactive interface providing means" is a means for providing an interface for employees to input their skills, experience, and desired position.

[0100] The "natural language processing algorithm processing means" is a means for executing an algorithm used to collect and analyze the content of employee dialogue.

[0101] The "profile management means" is a means for generating and storing employee profile data based on the analyzed data.

[0102] The "matching algorithm processing means" is a means for executing an algorithm that matches employee profile data with the needs of the company and generates optimal personnel allocation plans.

[0103] The "means for receiving feedback" is a means for presenting the generated placement plan to employees and receiving opinions and evaluations from the employees.

[0104] The "optimization method" is a method for reevaluating employees based on their feedback and generating a reassignment plan.

[0105] The "data transmission means" is a means for transmitting information entered by an employee using an interface to a server.

[0106] The "means for saving to a database" is the means by which the server saves the employee's input data to a database.

[0107] "Means for optimizing placement plans using machine learning models" refers to means for optimizing placement plans based on feedback from employees using machine learning models.

[0108] A specific embodiment for carrying out the present invention will be described below. In the system for carrying out the present invention, a server, a terminal, and a user each play their respective roles and work together to achieve optimal staffing.

[0109] Server Processing

[0110] The server first receives the user (employee) input data sent from the terminal. This data includes skills, experience, desired position, etc., and the server stores this in a database. The software used is a database management system (e.g., MySQL, PostgreSQL).

[0111] The server then runs a natural language processing (NLP) algorithm on the received data to analyze it. Specifically, it uses a Python NLP library (e.g., NLTK, SpaCy) to extract keywords such as employee skills, experience, and aspirations. The extracted data is used to generate employee profile data and store it in a database.

[0112] The server then runs a matching algorithm to match the generated profile data with the company's current needs (open positions and project requirements), using machine learning models (e.g., Scikit-learn classifiers), to match employee skills with the company's needs and generate optimal placement proposals.

[0113] The server also receives feedback from employees and uses machine learning models to reevaluate and optimize placement proposals, including a continuous learning process to incorporate feedback.

[0114] Terminal handling

[0115] The terminal provides the user (employee) with an interactive interface, which can be implemented, for example, as a web-based application (e.g., React or Angular), where the user can enter information such as skills, experience, and desired position.

[0116] The terminal transmits the information input by the user to the server in real time. The transmission process uses HTTP requests. Furthermore, a GUI is provided to display the profile data received from the server and the optimal placement plan to the user, allowing the user to easily input feedback.

[0117] User Action

[0118] The user uses the interactive interface of the terminal to input information such as his / her skills, experience, desired position, etc. This information is sent to the server via the terminal.

[0119] The user then reviews the placement proposals presented by the server and provides feedback if necessary. This feedback is then sent back to the server via the terminal and used to reevaluate and optimize the optimal placement proposal.

[0120] Specific examples

[0121] For example, an employee might enter, "I have five years of software development experience, and I'm particularly good at Python and Java." The device sends this information to the server using an HTTP request. The server uses NLTK for natural language processing to analyze the employee's skills and experience. The analyzed data is then saved as profile data and matched with the company's needs using a Scikit-learn classifier. As a result, a placement suggestion is generated: "A software engineer position on a new AI project would be suitable for you." This placement suggestion is displayed to the user via the device, and if the user adds feedback such as "I would also like to demonstrate leadership skills," it is sent back to the server. The server then reevaluates this feedback and proposes a new "leadership position on a new AI project."

[0122] This system allows companies to realize optimal allocation based on the characteristics and wishes of their employees, improving overall productivity and efficiency. By implementing this system, companies can maximize the potential of their human resources and achieve greater efficiency and improvement in their work.

[0123] The flow of the identification process in the first embodiment will be described with reference to FIG.

[0124] Step 1:

[0125] Entering and sending information (device operation)

[0126] Users input their skills, experience, and desired position through the device's interactive interface. Input information might include, "I have five years of software development experience, and I'm particularly good at Python and Java." The device receives this input information and sends it to the server using an HTTP request.

[0127] Input: User input data on skills, experience, and desired position

[0128] Output: Data sent in the form of an HTTP request

[0129] Specific operation: The user enters data into the input form and clicks the "Submit" button, which sends the data to the server.

[0130] Step 2:

[0131] Receiving and storing data (server operation)

[0132] The server receives the user's input data sent from the terminal and stores it in a database. The database management system used in this case may be MySQL or PostgreSQL.

[0133] Input: User input data sent from the terminal (HTTP request)

[0134] Output: Data stored in the database

[0135] What happens: The server parses the HTTP request and writes the information to a database.

[0136] Step 3:

[0137] Data analysis using natural language processing (server operation)

[0138] The server retrieves the user input data from the database and analyzes it using natural language processing (NLP) algorithms, specifically using Python NLP libraries (e.g., NLTK and SpaCy) to extract keywords related to employee skills, experience, and preferences.

[0139] Input: User-entered data stored in a database

[0140] Output: Parsed keywords and skill sets

[0141] Specific operation: The server runs an NLP algorithm to extract key keywords from the text data.

[0142] Step 4:

[0143] Generating and saving profile data (server operation)

[0144] The server generates employee profile data based on the data analyzed by NLP, which is then stored in a database as structured data including detailed skill sets and desired positions.

[0145] Input: Parsed keywords and skill sets

[0146] Output: Structured profile data

[0147] Specific operation: The server stores the generated profile data in a database.

[0148] Step 5:

[0149] Generating optimal placement plans (server operation)

[0150] The server runs a matching algorithm that matches employee profile data with the company's current needs (open positions and project requirements), using Scikit-learn classifiers. This process generates optimal staffing recommendations.

[0151] Input: Profile data, company needs

[0152] Output: Optimal staffing plan

[0153] Specific operation: The server executes a matching algorithm and generates placement proposals.

[0154] Step 6:

[0155] Presenting placement plans and receiving feedback (collaboration between terminals and servers)

[0156] The server sends the generated optimal placement plan to the terminal, which displays the placement plan to the user, who then inputs feedback on it. The terminal then sends the user's feedback back to the server.

[0157] Input: Optimal staffing plan, user feedback

[0158] Output: Received feedback

[0159] Specific operation: The server sends the placement plan to the terminal, which displays the placement plan in a GUI. The user enters feedback, and the terminal sends this information to the server.

[0160] Step 7:

[0161] Re-evaluation based on feedback and regeneration of optimal placement plan (server operation)

[0162] The server receives user feedback, re-evaluates it using machine learning models, and generates optimized relocation proposals. This process involves continuous training of the machine learning models.

[0163] Input: User feedback

[0164] Output: Optimized relocation plan

[0165] What it does: The server runs a machine learning algorithm and generates new placement suggestions based on the feedback.

[0166] Through this series of steps, the system can achieve optimal personnel allocation based on employees' characteristics and preferences, improving productivity and efficiency across the company.

[0167] (Application example 1)

[0168] Next, a description will be given of Application Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the smart device 14 will be referred to as a "terminal."

[0169] Conventional employee allocation systems can sometimes struggle to optimally allocate employees based on their skills, experience, and desired positions. It's also difficult to collect real-time operational status and performance data for factory robots and optimally allocate tasks based on that data. In particular, there's a lack of reevaluation and optimization based on feedback, preventing efficiency improvements over the long term. Therefore, there's a need for a system that can efficiently allocate and manage tasks for employees and factory robots.

[0170] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 1 is realized by the following means.

[0171] In this invention, the server includes: an interactive interface providing means for inputting employee skills, experience, and desired position; a natural language processing algorithm processing means for collecting and analyzing the content of the employee's dialogue; a profile management means for generating and saving employee profile data based on the analysis results; a matching algorithm processing means for matching the profile data with the company's needs and generating an optimal personnel allocation plan; a means for presenting the generated allocation plan to employees and receiving feedback; an optimization means for reevaluating based on the feedback and generating a reallocation plan; a data collection means for collecting factory robot operation status and performance data and sending it to the cloud server; a data analysis means for analyzing the collected data using a natural language processing algorithm and generating a robot skill profile; a profile management means for saving and managing the skill profile data generated based on the analysis results; a matching algorithm processing means for generating an optimal task allocation plan; and a reevaluation and optimization means for reevaluating based on feedback from the robot and generating an optimized allocation plan. This enables dynamic and efficient allocation and task management for both employees and factory robots.

[0172] The "interactive interface providing means" is a means for providing an interface for a user to input information such as skills, experience, and desired position.

[0173] "Natural language processing algorithm processing means" refers to a means that uses natural language processing technology to analyze the collected dialogue content and extract important keywords such as skills and experience.

[0174] The "profile management means" is a means for saving and managing the profile data of employees or robots generated based on the analysis results.

[0175] The "matching algorithm processing means" is a means for matching the generated profile data with the needs of the company or factory and using an algorithm to generate an optimal allocation plan or task allocation plan.

[0176] The "feedback means" is a means for presenting the generated placement plans and task placement plans to the user or robot and receiving their reactions and opinions.

[0177] The "optimization means" is a means for reevaluating based on feedback from users and robots and generating an even more optimal placement plan.

[0178] The "data collection means" is a means for collecting the operating status and performance data of factory robots in real time and sending it to a cloud server.

[0179] The "data analysis means" is a means for analyzing collected performance data and generating a skill profile of the robot.

[0180] The "reevaluation and optimization method" is a method for reevaluating the analysis algorithm constructed based on the robot's feedback and generating an optimal task allocation plan.

[0181] A "skill profile" is structured data that contains detailed information about the skills, abilities, and experience of employees and robots.

[0182] A specific embodiment for realizing the system of the present invention will be described. This system optimizes the allocation of employees and factory robots, with the server, terminals, and users each playing their respective roles and working together to optimally allocate personnel and tasks.

[0183] Server Processing

[0184] 1. Data Collection Methods

[0185] The server receives employee input data (skills, experience, desired position, etc.) sent from the terminal, and also collects the operating status and performance data of the factory robots. This data is stored on the server.

[0186] 2. Data analysis methods

[0187] The server runs a natural language processing (NLP) algorithm on the collected data to analyze it. This analysis extracts keywords related to the skills, experience, and preferences of employees and robots. Specific software used is an NLP library (Spacy or NLTK) or a machine learning model (Scikit-learn or TensorFlow).

[0188] 3. Profile Management Methods

[0189] The generated profile data is stored as structured data that includes detailed skill sets and preferences of employees and robots, making it possible to see their skills and preferences at a glance. The database uses MySQL or PostgreSQL.

[0190] 4. Matching Algorithm Processing Means

[0191] The server runs matching algorithms, such as segmental matching algorithms and genetic algorithms, to match employee and robot profile data with the company's current needs (vacant positions, project requirements, tasks, etc.), generating optimal placement proposals.

[0192] 5. Reevaluation and optimization measures

[0193] The server receives feedback from employees and robots and re-evaluates them based on this feedback. This re-evaluation uses a machine learning model that continuously learns and regenerates placement plans based on the feedback. This model uses reinforcement learning.

[0194] Terminal handling

[0195] 1. Means of providing a dialogue interface

[0196] The terminals provide employees and factory robots with an interactive interface through which users can input information such as skills, experience, and desired position.

[0197] 2. Means of data transmission

[0198] The terminals transmit information entered by employees and factory robots to the server in real time, allowing the server to receive the necessary data immediately.

[0199] 3. Display of results

[0200] The terminal receives profile data and optimal placement suggestions from the server and displays them to employees and robots, allowing users to review the placement suggestions and provide feedback.

[0201] User Action

[0202] 1. Enter your information

[0203] The user uses the interactive interface of the terminal to input information such as his / her skills, experience, desired position, etc. This information is then sent from the terminal to the server.

[0204] 2. Providing Feedback

[0205] Users can input feedback on the placement proposals from the server, such as, "This position is interesting, but I would prefer a role that allows for more leadership."

[0206] Specific examples

[0207] For example, suppose you input skill data about factory robot A. Based on past data, robot A is good at "welding work," and feedback from robot A indicates that it would be better suited to a role that allows it to take on more leadership roles.

[0208] The server will then use this information to propose the optimal welding leader position and generate an optimized placement plan through re-evaluation. Specific examples of prompts are as follows:

[0209] Example prompt sentence:

[0210] "Please enter the skill data for Robot A in your factory. Example: Robot A has excellent welding skills and is fast at work. He also desires a leadership role."

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

[0212] Step 1:

[0213] The server receives employee input data sent from the terminals, as well as factory robot operation status and performance data. This data includes employee skills, experience, desired positions, robot operating hours, error rates, and work speed. The received data is stored in a database on the server. Specific hardware used to collect data includes IoT sensors and sensors built into the robots.

[0214] Step 2:

[0215] The server runs a natural language processing (NLP) algorithm on the collected data. The NLP algorithm extracts keywords related to the skills and experience of employees and robots. This process uses NLP libraries (Spacy and NLTK) and machine learning models (Scikit-learn and TensorFlow). The input is the collected raw data, and the output is a list of keywords as a result of the analysis.

[0216] Step 3:

[0217] The server generates and stores profile data for employees and robots based on the extracted keywords. The profile data includes detailed information such as skill sets, experience, desired positions and tasks. This profile data is stored in a database using MySQL or PostgreSQL. The input is the analysis result from step 2, and the output is the stored profile data.

[0218] Step 4:

[0219] The server runs a matching algorithm to match employee and robot profile data with the company's needs. The matching takes into account the company's open positions, project requirements, and factory tasks. The algorithm uses a segmented matching algorithm or a genetic algorithm. The input is the profile data and the company's needs data, and the output is an optimal placement plan.

[0220] Step 5:

[0221] The terminal presents the generated placement plan to employees or robots and receives feedback. An example of feedback is a specific response such as, "This position is interesting, but I would prefer a role that allows me to demonstrate a bit more leadership." The input is the placement plan generated by the server, and the output is feedback from the user or robot.

[0222] Step 6:

[0223] The server reevaluates the system based on the received feedback and generates a relocation plan. A machine learning model (reinforcement learning model) that continuously learns is used for the reevaluation. This method optimizes the relocation plan based on the feedback. The input is the feedback from the user or robot, and the output is the regenerated optimal relocation plan.

[0224] Specific examples

[0225] For example, suppose you input skill data about factory robot A. Based on past data, robot A is good at "welding work," and feedback from robot A indicates that it would be better suited to a role that allows it to take on more leadership roles.

[0226] The server will then use this information to propose the optimal welding leader position and generate an optimized placement plan through re-evaluation. Specific examples of prompts are as follows:

[0227] Example prompt sentence:

[0228] "Please enter the skill data for Robot A in your factory. Example: Robot A has excellent welding skills and is fast at work. He also desires a leadership role."

[0229] 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.

[0230] A specific embodiment for realizing the system of the present invention will be described. In this system, three parties - a server, a terminal, and a user - each play their respective roles and work together to optimally allocate employees. Furthermore, by combining this with an emotion engine, it becomes possible to propose more effective allocations that take into account the user's emotions.

[0231] Server Processing

[0232] 1. Data Collection

[0233] The server receives the input data of the user (employee) sent from the terminal, including skills, experience, desired position, and conversation content. This data is stored in a database within the server.

[0234] 2. Data Analysis

[0235] The server runs a natural language processing (NLP) algorithm on the collected data to analyze it. Through the analysis, keywords such as employee skills, experience, and aspirations are extracted. Employee profile data is generated using the extracted data.

[0236] 3. Emotion analysis

[0237] The server uses an emotion engine to analyze the user's emotional state from the content of the conversation, for example, to detect whether the user is feeling stressed or excited during the conversation.

[0238] 4. Profile Management

[0239] The resulting profile data is stored as structured data containing the employee's detailed skill set, experience, desired position, and emotional state, providing an at-a-glance view of the employee's capabilities.

[0240] 5. Proposal for optimal layout

[0241] The server runs a matching algorithm that matches employee profile data with the company's current needs (open positions and project requirements). The algorithm matches the employee's skills with the company's needs and emotional state to generate optimal placement recommendations.

[0242] 6. Reassess and optimize

[0243] The server receives feedback from employees and re-evaluates them based on this. Using a continuously learning machine learning model, it generates reassignment plans based on the feedback. The results of sentiment analysis by the emotion engine are also taken into account.

[0244] Terminal handling

[0245] 1. Providing a conversational interface

[0246] The terminal provides the user (employee) with an interactive interface through which the user can input their skills, experience, desired position, and interaction content.

[0247] 2. Data transmission

[0248] The terminal transmits information entered by the user and the contents of the dialogue to the server in real time, allowing the server to receive the necessary data immediately.

[0249] 3. Displaying the results

[0250] The device displays the profile data and optimal placement proposals received from the server to the user, who can then review the proposals and provide feedback.

[0251] User Action

[0252] 1. Inputting information and interacting

[0253] The user uses the interactive interface of the terminal to input their skills, experience, desired position, and the content of the conversation. This information is sent from the terminal to the server, and the emotional state during the conversation is analyzed by the emotion engine.

[0254] 2. Providing Feedback

[0255] The user inputs feedback on the placement proposal from the server, for example, "This position is interesting, but I would also like to demonstrate leadership."

[0256] Specific examples

[0257] For example, if an employee enters, "I have five years of software development experience, and I'm particularly good at Python and Java," and then during the conversation says, "I'd like to try new technologies, but I'm a little nervous," the device sends this information to the server. The server uses natural language processing to analyze the employee's skills and experience, and further detects the emotion of nervousness using an emotion engine. It then generates profile data. The server then matches this profile data with the company's needs and generates an optimal placement proposal. For example, it might suggest, "A software engineer position on a new AI project would be suitable." The device displays this proposal to the user, who then provides feedback, saying, "I'd also like to demonstrate leadership." Through reevaluation, the server again proposes the "leadership position on a new AI project."

[0258] By utilizing the emotion engine, more optimal personnel placement can be achieved that takes into account the emotional state of employees, thereby improving productivity and efficiency across the entire company.

[0259] The processing flow will be explained below.

[0260] Step 1: The user initiates the interaction

[0261] Users access an interactive interface on their device and enter their skills, experience, and desired position, for example, "I have five years of software development experience, and I am particularly skilled in Python and Java."

[0262] Step 2: The device sends user input to the server

[0263] The device sends the information entered by the user to the server in real time, using API requests to transfer this data to the server.

[0264] Step 3: The device collects emotion data

[0265] The device analyzes the user's tone of voice and facial expressions during the conversation to collect emotional data, using audio recordings and cameras.

[0266] Step 4: The device sends the emotion data to the server.

[0267] The device transmits the collected emotional data to the server, which allows the server to recognize the emotional state.

[0268] Step 5: The server receives and stores the data

[0269] The server receives the user's input data and emotion data sent from the terminal and stores them in a database, including skills, experience, desired position, and emotion data.

[0270] Step 6: The server performs the data analysis

[0271] The server analyzes the stored data using natural language processing (NLP) algorithms, extracting keywords such as skills, experience, and aspirations, and converting them into structured data.

[0272] Step 7: The server performs sentiment analysis

[0273] The server uses an emotion engine to analyze the user's emotional state during the conversation, for example, to detect whether the user is feeling stressed or excited during the conversation.

[0274] Step 8: Server generates profile data

[0275] The server generates user profile data based on the extracted keywords and the results of sentiment analysis, which includes the user's skill set, experience, desired position, and emotional state.

[0276] Step 9: The server saves the profile data

[0277] The server stores the generated profile data in a database, which allows detailed employee information to be managed.

[0278] Step 10: The server captures the needs of the enterprise

[0279] The server retrieves data from a database about the company's current needs and open positions, including the skill requirements and responsibilities for each position.

[0280] Step 11: The server generates the optimal placement plan

[0281] The server runs a matching algorithm to match users' profile data with the company's needs, and generates optimal staffing recommendations based on skill matching and role compatibility.

[0282] Step 12: The server sends the placement plan to the device.

[0283] The server sends the generated placement plan to the terminal, allowing the user to check the proposed content.

[0284] Step 13: The device displays the layout plan to the user.

[0285] The device displays the placement proposal received from the server to the user, specifically displaying details of the placement proposal (e.g., a software engineer position for a new AI project).

[0286] Step 14: Users provide feedback

[0287] The user can then provide feedback on the proposed placement, such as, "This position is interesting, but I would also like to demonstrate leadership."

[0288] Step 15: Device sends feedback to server

[0289] The device receives the user's feedback and sends it to the server. The device forwards the feedback to the server using an API request.

[0290] Step 16: Server performs re-evaluation

[0291] The server reevaluates the system based on user feedback and uses a continuously learning machine learning model to generate optimal relocation plans based on the feedback.

[0292] Step 17: The server sends the reevaluation result to the terminal.

[0293] The server transmits the re-evaluation results to the terminal, and the regenerated placement plan is transferred to the terminal.

[0294] Step 18: The terminal displays the reevaluation results to the user

[0295] The device displays the reevaluation results received from the server to the user, for example, "You are recommended for a leadership position in a new AI project."

[0296] Through these steps, the system of the present invention can realize optimal personnel allocation based on employees' characteristics and preferences, improving the productivity and efficiency of the entire company. By utilizing the emotion engine, it is possible to propose more optimal personnel allocation that takes into account the emotional state of employees.

[0297] Example 2

[0298] 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."

[0299] When it comes to optimal personnel placement that takes into account employees' skills, experience, and desired positions, traditional profile analysis and matching algorithms alone have limitations, making it difficult to properly incorporate employees' emotional states and feedback. Furthermore, the reevaluation and reassignment process can be inefficient, negatively impacting employee satisfaction and corporate productivity. There is a need to solve these issues and provide a more effective and flexible personnel placement system.

[0300] The specific processing by the specific processing unit 290 of the data processing device 12 in the second embodiment is realized by the following means.

[0301] In this invention, the server includes an interactive interface providing means for inputting employee skills, experience, and desired positions, a natural language processing algorithm processing means for collecting and analyzing the content of employee dialogue, a profile management means for generating and saving employee profile data based on the analysis results, an emotion analysis means for analyzing the emotional state of employees from the content of dialogue, a matching algorithm processing means for matching the profile data with the needs of the company and generating an optimal personnel placement plan, a means for presenting the generated placement plan to employees and receiving feedback, and an optimization means for reevaluating based on the feedback and generating a reallocation plan. This makes it possible to generate flexible and effective placement plans that take into account the emotional state of employees, thereby improving employee satisfaction and corporate productivity.

[0302] An "interactive interface" is a user interface that allows employees to input information such as their skills, experience, and desired position.

[0303] A "natural language processing algorithm" is an algorithm that analyzes the content of employee conversations and extracts necessary information and keywords.

[0304] "Profile Data" is structured data that includes an employee's skills, experience, desired position, and other relevant information.

[0305] The "profile management means" is a means for saving and managing the generated profile data.

[0306] The "emotion analysis means" is a means for analyzing and detecting the emotional state of an employee from the content of their conversation.

[0307] The "matching algorithm" is an algorithm that matches profile data with the needs of the company and generates optimal personnel placement plans.

[0308] The "optimization means" is a means for reassessing employees based on their feedback and generating reassignment plans.

[0309] "Feedback" refers to the opinions and thoughts employees provide about proposed placements.

[0310] "Placement proposals" are suggestions for optimal personnel placement generated based on employee profile data and the company's needs.

[0311] The system of the present invention is designed to generate optimal personnel allocation plans that take into account employees' skills, experience, desired positions, and also their emotional state. This system operates in cooperation with three parties: a server, a terminal, and a user.

[0312] Server Processing

[0313] The server first receives the employee's input data sent from the terminal. This data includes the employee's skills, experience, desired position, and conversation content. The received data is then stored in a database. Specifically, a database management system such as MySQL or PostgreSQL can be used.

[0314] The server then runs natural language processing (NLP) algorithms on the stored data, using libraries like Python's NLTK and SpaCy, to analyze the data and extract keywords related to the employee's skills, experience, and aspirations.

[0315] Furthermore, the server uses an emotion engine to analyze the user's emotional state from the dialogue. For example, by using the Google Cloud Natural Language API, it can detect emotions such as stress or excitement felt by the user.

[0316] The generated profile data is stored as structured data that includes the employee's detailed skill set, experience, desired position, and emotional state.

[0317] The server then runs a matching algorithm that matches employee profile data with the company's needs using machine learning models such as Google Cloud AutoML and TensorFlow, generating optimal placement recommendations that match the employee's skills with the company's needs and emotional state.

[0318] The server receives feedback from users and reevaluates it using a machine learning model that continuously learns. This generates a relocation plan based on the feedback, taking into account the results of emotion analysis by the emotion engine.

[0319] Terminal handling

[0320] The terminal provides the user (employee) with an interactive interface through which the user can input their skills, experience, desired position, and interaction content.

[0321] The terminal transmits information entered by the user and the contents of the dialogue to the server in real time, allowing the server to receive the necessary data immediately.

[0322] The device also displays the profile data and optimal placement proposals received from the server to the user, who can then review the proposals and provide feedback.

[0323] User Action

[0324] The user uses the interactive interface of the terminal to input their skills, experience, desired position, and the content of the conversation. This information is sent from the terminal to the server, and the emotional state during the conversation is analyzed by the emotion engine.

[0325] Furthermore, users can input feedback on the placement proposals from the server, for example, "This position is interesting, but I would also like to demonstrate leadership skills."

[0326] Specific examples

[0327] As a specific example, if an employee types, "I have five years of software development experience and am particularly good at Python and Java," and then during the conversation says, "I would like to try new technologies, but I'm a little nervous," the device will send this information to the server.

[0328] The server analyzes the employee's skills and experience through natural language processing and detects anxiety using an emotion engine. It then generates profile data. The server matches this profile data with the company's needs and generates optimal placement recommendations. For example, it might suggest, "A software engineer position for a new AI project would be suitable."

[0329] The terminal displays the proposal to the user, who then provides feedback, saying, "I would also like to demonstrate leadership." Through reevaluation, the server can re-propose the "leadership position for a new AI project."

[0330] Prompt Sentence Examples

[0331] Below are some examples of specific prompt sentences to input into the generative AI model.

[0332] Prompt: I have 5 years of software development experience, particularly in Python and Java. I'd like to try new technologies but am a bit nervous. Please suggest a suitable position for me.

[0333] In this way, taking into account the emotional state of employees can lead to more effective and flexible staffing, improving productivity and efficiency across the company.

[0334] The flow of the identification process in the second embodiment will be described with reference to FIG.

[0335] Step 1: Data collection

[0336] The server receives user (employee) input data sent from the terminal. The input data includes the user's skills, experience, desired position, and dialogue content. This data is stored in a database (such as MySQL or PostgreSQL) on the server. For example, if a user enters "I have five years of software development experience, and I am particularly good at Python and Java," the terminal sends this information to the server, which stores it in a "user data" table.

[0337] Step 2: Data analysis

[0338] The server runs natural language processing (NLP) algorithms on the stored data to analyze it. Specifically, it uses Python's NLTK and SpaCy libraries to extract keywords related to the user's skills, experience, and desired position. For example, from an input such as "I have five years of software development experience, and I am particularly good at Python and Java," it extracts keywords such as "software development," "Python," and "Java."

[0339] Step 3: Sentiment Analysis

[0340] The server uses an emotion engine to analyze the user's emotional state from the dialogue content. Based on the input dialogue content, the emotion engine (e.g., Google Cloud Natural Language API) detects emotions such as "anxiety," "excitement," and "stress." For example, if a user inputs "I want to try a new technology, but I'm a little anxious," the emotion engine will detect the emotion "anxiety."

[0341] Step 4: Profile Management

[0342] The server generates employee profile data based on the extracted data and the results of sentiment analysis and stores it in a database. The generated profile data includes the employee's skill set, experience, desired position, and emotional state. For example, data such as "software development," "Python," "Java," and "anxiety" are stored in the "Employee Profile" table.

[0343] Step 5: Propose optimal layout

[0344] The server runs a matching algorithm that matches employee profile data with the company's needs. Using Google Cloud AutoML and TensorFlow, it generates optimal staffing recommendations based on the profile data and company needs. Using data on "software development," "Python," "Java," and "anxiety" as input, it compares these with the company's requirements for a "new AI project" and proposes a "software engineer position for a new AI project."

[0345] Step 6: Viewing results and feedback

[0346] The terminal displays the placement proposal received from the server to the user. The user checks the placement proposal and inputs feedback through an interactive interface. For example, if the user provides an opinion such as "This position is interesting, but I also want to demonstrate leadership," the terminal sends this feedback to the server.

[0347] Step 7: Reassess and optimize

[0348] The server receives feedback from users and reevaluates them using a continuously learning machine learning model. Based on the feedback and sentiment analysis results, it generates new reassignment proposals. For example, it may re-propose a "leadership position for a new AI project." This process can improve employee satisfaction and company productivity.

[0349] Prompt sentences with examples

[0350] Below are some examples of specific prompt sentences to input into the generative AI model.

[0351] Prompt: I have 5 years of software development experience, particularly in Python and Java. I'd like to try new technologies but am a bit nervous. Please suggest a suitable position for me.

[0352] (Application example 2)

[0353] 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."

[0354] Conventional systems that optimize the allocation of employee skills and experience do not take into account the emotional state of employees, resulting in a high risk of poor performance after allocation or employee turnover due to dissatisfaction. Furthermore, there was a lack of a system that could simultaneously analyze employee dialogue and emotions and quickly propose optimal allocations, so these issues need to be addressed.

[0355] The specific processing by the specific processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means. In this invention, the server includes an interactive interface providing means for inputting employee skills, experience, and desired positions, a natural language processing algorithm processing means for collecting and analyzing the content of employee dialogue, and a profile management means for generating and saving employee profile data based on the analysis results. This makes it possible to generate optimal placement plans that also take into account the emotional state of employees.

[0356] The "interactive interface providing means" is a means for providing an interactive interface for employees to input their skills, experience, and desired position.

[0357] The "natural language processing algorithm processing means" is a means that uses a natural language processing algorithm to collect and analyze the content of employee dialogue.

[0358] The "profile management means" is a means for generating and storing employee profile data based on the analysis results.

[0359] The "matching algorithm processing means" is a means that uses an algorithm to match profile data with the needs of the company and generate an optimal personnel allocation plan.

[0360] The "feedback receiving means" is a means for presenting the generated placement plan to employees and receiving their feedback.

[0361] The "re-evaluation means" is a means for performing a re-evaluation based on the feedback and generating a re-placement plan.

[0362] The "emotion analysis means" is a means for analyzing the emotional state of an employee from the content of their conversation.

[0363] "Means for adopting machine learning models" refers to means for adopting machine learning models that continuously learn based on employee feedback.

[0364] In the system for realizing the application example of the present invention, a server, a terminal, and a user work together. The following is a detailed description of how the system is implemented.

[0365] Server Processing

[0366] The server receives data sent from a terminal having an interactive interface supply means for inputting the employee's skills, experience, and desired position. The server analyzes the content of the dialogue using a natural language processing algorithm processing means, and generates and saves the analysis results as employee profile data using a profile management means.

[0367] The server analyzes the content of the employee's conversation using an emotion analysis means and also digitizes the employee's emotional state. It then compares the profile data with the company's needs and generates an optimal personnel placement plan using a matching algorithm processing means. The generated placement plan is then presented to the employee via their terminal, and the feedback from the employee is received using a feedback receiving means. A reevaluation means reevaluates the employee based on the feedback and generates a relocation plan. At this time, a machine learning model adoption means that continuously learns based on employee feedback is used to constantly update the optimal placement plan.

[0368] Terminal handling

[0369] The terminal provides a dialogue interface for users (employees) to input their skills, experience, and desired position. This information is sent to the server in real time. The dialogue is converted into text using voice recognition technology and sent to the server.

[0370] User Action

[0371] Users (employees) use the interactive interface on their terminals to input their skills, experience, desired position, and the content of their conversations. The input data is sent to the server, and their emotional state is analyzed using emotion analysis means. By providing feedback on the proposed placement plan, even more accurate placement plans can be regenerated.

[0372] Hardware and software used

[0373] The server uses the "TextBlob" library for natural language processing, the "NLTK" library for sentiment analysis, and the "scikit-learn" clustering algorithm. The device uses the "speech_recognition" library for speech recognition, converting user voice input into text data.

[0374] Specific examples

[0375] For example, if an employee says, "I'd like to help install a new logistics system, but I'm a little worried about the technology," the system can analyze the employee's concerns about the new technology and suggest an appropriate support system.

[0376] Example prompts to be input to the generative AI model

[0377] "Employees have expressed anxiety about new technology. What kind of assistance system should we suggest to employees who feel the same way?"

[0378] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[0379] Program processing flow

[0380] Step 1: Collecting user (employee) input data

[0381] The terminal provides an interactive interface for users to input their skills, experience, and desired position. The user inputs their skills, experience, desired position, and dialogue content through the interface. The terminal uses voice recognition technology to convert the user's voice input into text data. The generated text data is sent to the server in real time.

[0382] Input: User (employee) voice input

[0383] Data processing: Converting speech into text using voice recognition technology

[0384] Output: Text data

[0385] Step 2: Employee data analysis

[0386] The server receives the employee's conversation content sent from the terminal. Using a natural language processing algorithm, it extracts and analyzes information such as skills, experience, and desired position from the employee's conversation content. Based on this data, it generates employee profile data and stores it in a database.

[0387] Input: Text data

[0388] Data processing: Extraction and analysis of keywords using natural language processing algorithms

[0389] Output: Profile data

[0390] Step 3: Sentiment Analysis

[0391] The server uses emotion analysis means to analyze the employee's emotional state (e.g., stress, anxiety, excitement) based on the content of the employee's dialogue. The results of the emotion analysis are added to the profile data.

[0392] Input: Text data of the dialogue

[0393] Data processing: Emotion analysis algorithm analyzes emotional state

[0394] Output: Emotional state data

[0395] Step 4: Propose optimal layout

[0396] The server uses a matching algorithm processing means to match the generated profile data with the needs of the company, and generates an optimal personnel allocation plan by taking into account the employee's skills, experience, and emotional state. The allocation plan is presented to the employee via the terminal.

[0397] Input: Profile data, company needs

[0398] Data processing: Generate placement plans using a matching algorithm

[0399] Output: Optimal layout plan

[0400] Step 5: Receiving feedback

[0401] The terminal presents the generated placement plan to the employee, who then inputs feedback on the placement plan. The input feedback is sent to the server in real time.

[0402] Input: Optimal layout plan

[0403] Data processing: Employee feedback input

[0404] Output: Feedback data

[0405] Step 6: Reassess and optimize

[0406] The server performs re-evaluation based on the feedback received from employees. Using the re-evaluation method and the machine learning model adoption method, it generates a re-allocation plan that takes the feedback data into consideration. This enables optimal personnel allocation that takes into account the feedback and emotional state of employees.

[0407] Input: Feedback data

[0408] Data Transformation: Continuously train and reassess machine learning models

[0409] Output: Relocation proposal

[0410] Examples and prompts

[0411] For example, if an employee says, "I'd like to help install a new logistics system, but I'm a little worried about the technology," the system can analyze the employee's concerns about the new technology and suggest an appropriate support system.

[0412] Example prompts to input to a generative AI model:

[0413] "Employees have expressed anxiety about new technology. What kind of assistance system should we suggest to employees who feel the same way?"

[0414] 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.

[0415] 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.

[0416] 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.

[0417] [Second embodiment]

[0418] FIG. 3 shows an example of the configuration of a data processing system 210 according to the second embodiment.

[0419] 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.

[0420] 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).

[0421] 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.

[0422] 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.

[0423] 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).

[0424] 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.

[0425] 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.

[0426] 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.

[0427] 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.

[0428] In the smart glasses 214, 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.

[0429] 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."

[0430] A specific embodiment for realizing the system of the present invention will be described. In this system, three parties, a server, a terminal, and a user, each play their respective roles and work together to optimally allocate employees.

[0431] Server Processing

[0432] 1. Data Collection

[0433] The server receives the user (employee) input data sent from the terminal, including skills, experience, desired position, etc. This data is stored in a database within the server.

[0434] 2. Data Analysis

[0435] The server runs a natural language processing (NLP) algorithm on the collected data to analyze it. Through the analysis, keywords such as employee skills, experience, and aspirations are extracted. Employee profile data is generated using the extracted data.

[0436] 3. Profile Management

[0437] The generated profile data is stored as structured data containing the employee's detailed skill set and desired position, allowing employees to see their capabilities at a glance.

[0438] 4. Proposal for optimal layout

[0439] The server runs a matching algorithm that matches employee profile data with the company's current needs (open positions and project requirements). The algorithm matches employee skills with the company's needs and generates optimal placement proposals.

[0440] 5. Reassess and optimize

[0441] The server receives feedback from employees and re-evaluates them based on this feedback. The re-evaluation uses a continuously learning machine learning model to regenerate placement proposals based on the feedback.

[0442] Terminal handling

[0443] 1. Providing a conversational interface

[0444] The terminal provides the user (employee) with an interactive interface through which the user can input information such as skills, experience, and desired position.

[0445] 2. Data transmission

[0446] The terminal transmits the information input by the user to the server in real time, allowing the server to receive the necessary data immediately.

[0447] 3. Displaying the results

[0448] The device displays the profile data and optimal placement proposals received from the server to the user, who can then review the placement proposals and provide feedback.

[0449] User Action

[0450] 1. Enter your information

[0451] The user uses the interactive interface of the terminal to input information such as his / her skills, experience, desired position, etc. This information is then sent from the terminal to the server.

[0452] 2. Providing Feedback

[0453] Users can input feedback on the placement proposals from the server, such as, "This position is interesting, but I would prefer a role that allows for more leadership."

[0454] Specific examples

[0455] For example, if an employee enters, "I have five years of software development experience, and I'm particularly good at Python and Java," the device sends this information to the server. The server uses natural language processing to analyze the employee's skills and experience and generate profile data. The server then matches this profile data with the company's needs and generates an optimal placement proposal. For example, it might suggest, "A software engineer position on a new AI project would be suitable." The device displays this proposal to the user, who then provides feedback, saying, "I'd also like to demonstrate leadership skills." Through reevaluation, the server again proposes the "leadership position on a new AI project."

[0456] As a result, the system of the present invention can realize optimal personnel allocation based on the characteristics and desires of each employee, thereby improving the productivity and efficiency of the entire company.

[0457] The processing flow will be explained below.

[0458] Step 1: The user initiates the interaction

[0459] Users access an interactive interface on their device and enter their skills, experience, and desired position, for example, "I have five years of software development experience, and I am particularly skilled in Python and Java."

[0460] Step 2: The device sends user input to the server

[0461] The device sends the information entered by the user to the server in real time, using API requests to transfer this data to the server.

[0462] Step 3: The server receives and stores the data

[0463] The server receives the user's input data sent from the terminal and stores it in a database, including skills, experience, desired position, etc.

[0464] Step 4: The server performs the data analysis

[0465] The server analyzes the stored data using natural language processing (NLP) algorithms, extracting keywords such as skills, experience, and aspirations, and converting them into structured data.

[0466] Step 5: The server generates the profile data

[0467] The server generates user profile data based on the extracted keywords, which includes the user's skill set, experience, and desired position.

[0468] Step 6: The server saves the profile data

[0469] The server stores the generated profile data in a database, which allows detailed employee information to be managed.

[0470] Step 7: The server gets the company's needs

[0471] The server retrieves data from a database about the company's current needs and open positions, including the skill requirements and responsibilities for each position.

[0472] Step 8: The server generates the optimal placement plan

[0473] The server runs a matching algorithm to match users' profile data with the company's needs, and generates optimal staffing recommendations based on skill matching and role compatibility.

[0474] Step 9: The server sends the placement plan to the device.

[0475] The server sends the generated placement plan to the terminal, allowing the user to check the proposed content.

[0476] Step 10: The device displays the layout plan to the user.

[0477] The terminal displays the placement proposal received from the server to the user, specifically displaying details of the placement proposal (e.g., a software engineer position for a new project).

[0478] Step 11: Users provide feedback

[0479] The user can then provide feedback on the proposed placement, such as, "This position is interesting, but I would also like to demonstrate leadership."

[0480] Step 12: Device sends feedback to server

[0481] The device receives the user's feedback and sends it to the server. The device forwards the feedback to the server using an API request.

[0482] Step 13: Server performs re-evaluation

[0483] The server reevaluates the system based on user feedback and uses a machine learning model to generate optimal relocation plans.

[0484] Step 14: The server sends the reevaluation result to the terminal.

[0485] The server transmits the re-evaluation results to the terminal, and the regenerated placement plan is transferred to the terminal.

[0486] Step 15: The terminal displays the reevaluation results to the user

[0487] The device displays the reevaluation results received from the server to the user, for example, "You are recommended for a leadership position in a new AI project."

[0488] Through these steps, the system of the present invention can realize optimal personnel allocation based on the characteristics and desires of employees, thereby improving productivity and efficiency across the entire company.

[0489] Example 1

[0490] 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."

[0491] Modern companies are required to assign personnel to positions that optimally reflect the characteristics and preferences of their employees. However, it is difficult to effectively collect and analyze employee skills, experience, and desired positions, and to assign personnel to positions that optimally meet the company's needs. Another challenge is collecting feedback from employees in real time and reevaluating and optimizing assignment plans based on that feedback.

[0492] 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.

[0493] In this invention, the server includes: an interactive interface providing means for inputting employee skills, experience, and desired positions; a natural language processing algorithm processing means for collecting and analyzing the content of the employee's dialogue; a profile management means for generating and saving employee profile data based on the analysis results; a matching algorithm processing means for matching the profile data with the company's needs and generating optimal personnel placement plans; a means for presenting the generated placement plans to employees and receiving feedback; an optimization means for reevaluating based on the feedback and generating reallocation plans; a data transmission means for transmitting information input by employees using the interface to the server; a means for the server to store the employee's input data in a database; and a means for the server to optimize the placement plans using a machine learning model. This enables companies to achieve optimal personnel placement based on the characteristics and preferences of their employees, thereby improving the productivity and efficiency of the entire company.

[0494] The "interactive interface providing means" is a means for providing an interface for employees to input their skills, experience, and desired position.

[0495] The "natural language processing algorithm processing means" is a means for executing an algorithm used to collect and analyze the content of employee dialogue.

[0496] The "profile management means" is a means for generating and storing employee profile data based on the analyzed data.

[0497] The "matching algorithm processing means" is a means for executing an algorithm that matches employee profile data with the needs of the company and generates optimal personnel allocation plans.

[0498] The "means for receiving feedback" is a means for presenting the generated placement plan to employees and receiving opinions and evaluations from the employees.

[0499] The "optimization method" is a method for reevaluating employees based on their feedback and generating a reassignment plan.

[0500] The "data transmission means" is a means for transmitting information entered by an employee using an interface to a server.

[0501] The "means for saving to a database" is the means by which the server saves the employee's input data to a database.

[0502] "Means for optimizing placement plans using machine learning models" refers to means for optimizing placement plans based on feedback from employees using machine learning models.

[0503] A specific embodiment for carrying out the present invention will be described below. In the system for carrying out the present invention, a server, a terminal, and a user each play their respective roles and work together to achieve optimal staffing.

[0504] Server Processing

[0505] The server first receives the user (employee) input data sent from the terminal. This data includes skills, experience, desired position, etc., and the server stores this in a database. The software used is a database management system (e.g., MySQL, PostgreSQL).

[0506] The server then runs a natural language processing (NLP) algorithm on the received data to analyze it. Specifically, it uses a Python NLP library (e.g., NLTK, SpaCy) to extract keywords such as employee skills, experience, and aspirations. The extracted data is used to generate employee profile data and store it in a database.

[0507] The server then runs a matching algorithm to match the generated profile data with the company's current needs (open positions and project requirements), using machine learning models (e.g., Scikit-learn classifiers), to match employee skills with the company's needs and generate optimal placement proposals.

[0508] The server also receives feedback from employees and uses machine learning models to reevaluate and optimize placement proposals, including a continuous learning process to incorporate feedback.

[0509] Terminal handling

[0510] The terminal provides the user (employee) with an interactive interface, which can be implemented, for example, as a web-based application (e.g., React or Angular), where the user can enter information such as skills, experience, and desired position.

[0511] The terminal transmits the information input by the user to the server in real time. The transmission process uses HTTP requests. Furthermore, a GUI is provided to display the profile data received from the server and the optimal placement plan to the user, allowing the user to easily input feedback.

[0512] User Action

[0513] The user uses the interactive interface of the terminal to input information such as his / her skills, experience, desired position, etc. This information is sent to the server via the terminal.

[0514] The user then reviews the placement proposals presented by the server and provides feedback if necessary. This feedback is then sent back to the server via the terminal and used to reevaluate and optimize the optimal placement proposal.

[0515] Specific examples

[0516] For example, an employee might enter, "I have five years of software development experience, and I'm particularly good at Python and Java." The device sends this information to the server using an HTTP request. The server uses NLTK for natural language processing to analyze the employee's skills and experience. The analyzed data is then saved as profile data and matched with the company's needs using a Scikit-learn classifier. As a result, a placement suggestion is generated: "A software engineer position on a new AI project would be suitable for you." This placement suggestion is displayed to the user via the device, and if the user adds feedback such as "I would also like to demonstrate leadership skills," it is sent back to the server. The server then reevaluates this feedback and proposes a new "leadership position on a new AI project."

[0517] This system allows companies to realize optimal allocation based on the characteristics and wishes of their employees, improving overall productivity and efficiency. By implementing this system, companies can maximize the potential of their human resources and achieve greater efficiency and improvement in their work.

[0518] The flow of the identification process in the first embodiment will be described with reference to FIG.

[0519] Step 1:

[0520] Entering and sending information (device operation)

[0521] Users input their skills, experience, and desired position through the device's interactive interface. Input information might include, "I have five years of software development experience, and I'm particularly good at Python and Java." The device receives this input information and sends it to the server using an HTTP request.

[0522] Input: User input data on skills, experience, and desired position

[0523] Output: Data sent in the form of an HTTP request

[0524] Specific operation: The user enters data into the input form and clicks the "Submit" button, which sends the data to the server.

[0525] Step 2:

[0526] Receiving and storing data (server operation)

[0527] The server receives the user's input data sent from the terminal and stores it in a database. The database management system used in this case may be MySQL or PostgreSQL.

[0528] Input: User input data sent from the terminal (HTTP request)

[0529] Output: Data stored in the database

[0530] What happens: The server parses the HTTP request and writes the information to a database.

[0531] Step 3:

[0532] Data analysis using natural language processing (server operation)

[0533] The server retrieves the user input data from the database and analyzes it using natural language processing (NLP) algorithms, specifically using Python NLP libraries (e.g., NLTK and SpaCy) to extract keywords related to employee skills, experience, and preferences.

[0534] Input: User-entered data stored in a database

[0535] Output: Parsed keywords and skill sets

[0536] Specific operation: The server runs an NLP algorithm to extract key keywords from the text data.

[0537] Step 4:

[0538] Generating and saving profile data (server operation)

[0539] The server generates employee profile data based on the data analyzed by NLP, which is then stored in a database as structured data including detailed skill sets and desired positions.

[0540] Input: Parsed keywords and skill sets

[0541] Output: Structured profile data

[0542] Specific operation: The server stores the generated profile data in a database.

[0543] Step 5:

[0544] Generating optimal placement plans (server operation)

[0545] The server runs a matching algorithm that matches employee profile data with the company's current needs (open positions and project requirements), using Scikit-learn classifiers. This process generates optimal staffing recommendations.

[0546] Input: Profile data, company needs

[0547] Output: Optimal staffing plan

[0548] Specific operation: The server executes a matching algorithm and generates placement proposals.

[0549] Step 6:

[0550] Presenting placement plans and receiving feedback (collaboration between terminals and servers)

[0551] The server sends the generated optimal placement plan to the terminal, which displays the placement plan to the user, who then inputs feedback on it. The terminal then sends the user's feedback back to the server.

[0552] Input: Optimal staffing plan, user feedback

[0553] Output: Received feedback

[0554] Specific operation: The server sends the placement plan to the terminal, which displays the placement plan in a GUI. The user enters feedback, and the terminal sends this information to the server.

[0555] Step 7:

[0556] Re-evaluation based on feedback and regeneration of optimal placement plan (server operation)

[0557] The server receives user feedback, re-evaluates it using machine learning models, and generates optimized relocation proposals. This process involves continuous training of the machine learning models.

[0558] Input: User feedback

[0559] Output: Optimized relocation plan

[0560] What it does: The server runs a machine learning algorithm and generates new placement suggestions based on the feedback.

[0561] Through this series of steps, the system can achieve optimal personnel allocation based on employees' characteristics and preferences, improving productivity and efficiency across the company.

[0562] (Application example 1)

[0563] 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."

[0564] Conventional employee allocation systems can sometimes struggle to optimally allocate employees based on their skills, experience, and desired positions. It's also difficult to collect real-time operational status and performance data for factory robots and optimally allocate tasks based on that data. In particular, there's a lack of reevaluation and optimization based on feedback, preventing efficiency improvements over the long term. Therefore, there's a need for a system that can efficiently allocate and manage tasks for employees and factory robots.

[0565] 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.

[0566] In this invention, the server includes: an interactive interface providing means for inputting employee skills, experience, and desired position; a natural language processing algorithm processing means for collecting and analyzing the content of the employee's dialogue; a profile management means for generating and saving employee profile data based on the analysis results; a matching algorithm processing means for matching the profile data with the company's needs and generating an optimal personnel allocation plan; a means for presenting the generated allocation plan to employees and receiving feedback; an optimization means for reevaluating based on the feedback and generating a reallocation plan; a data collection means for collecting factory robot operation status and performance data and sending it to the cloud server; a data analysis means for analyzing the collected data using a natural language processing algorithm and generating a robot skill profile; a profile management means for saving and managing the skill profile data generated based on the analysis results; a matching algorithm processing means for generating an optimal task allocation plan; and a reevaluation and optimization means for reevaluating based on feedback from the robot and generating an optimized allocation plan. This enables dynamic and efficient allocation and task management for both employees and factory robots.

[0567] The "interactive interface providing means" is a means for providing an interface for a user to input information such as skills, experience, and desired position.

[0568] "Natural language processing algorithm processing means" refers to a means that uses natural language processing technology to analyze the collected dialogue content and extract important keywords such as skills and experience.

[0569] The "profile management means" is a means for saving and managing the profile data of employees or robots generated based on the analysis results.

[0570] The "matching algorithm processing means" is a means for matching the generated profile data with the needs of the company or factory and using an algorithm to generate an optimal allocation plan or task allocation plan.

[0571] The "feedback means" is a means for presenting the generated placement plans and task placement plans to the user or robot and receiving their reactions and opinions.

[0572] The "optimization means" is a means for reevaluating based on feedback from users and robots and generating an even more optimal placement plan.

[0573] The "data collection means" is a means for collecting the operating status and performance data of factory robots in real time and sending it to a cloud server.

[0574] The "data analysis means" is a means for analyzing collected performance data and generating a skill profile of the robot.

[0575] The "reevaluation and optimization method" is a method for reevaluating the analysis algorithm constructed based on the robot's feedback and generating an optimal task allocation plan.

[0576] A "skill profile" is structured data that contains detailed information about the skills, abilities, and experience of employees and robots.

[0577] A specific embodiment for realizing the system of the present invention will be described. This system optimizes the allocation of employees and factory robots, with the server, terminals, and users each playing their respective roles and working together to optimally allocate personnel and tasks.

[0578] Server Processing

[0579] 1. Data Collection Methods

[0580] The server receives employee input data (skills, experience, desired position, etc.) sent from the terminal, and also collects the operating status and performance data of the factory robots. This data is stored on the server.

[0581] 2. Data analysis methods

[0582] The server runs a natural language processing (NLP) algorithm on the collected data to analyze it. This analysis extracts keywords related to the skills, experience, and preferences of employees and robots. Specific software used is an NLP library (Spacy or NLTK) or a machine learning model (Scikit-learn or TensorFlow).

[0583] 3. Profile Management Methods

[0584] The generated profile data is stored as structured data that includes detailed skill sets and preferences of employees and robots, making it possible to see their skills and preferences at a glance. The database uses MySQL or PostgreSQL.

[0585] 4. Matching Algorithm Processing Means

[0586] The server runs matching algorithms, such as segmental matching algorithms and genetic algorithms, to match employee and robot profile data with the company's current needs (vacant positions, project requirements, tasks, etc.), generating optimal placement proposals.

[0587] 5. Reevaluation and optimization measures

[0588] The server receives feedback from employees and robots and re-evaluates them based on this feedback. This re-evaluation uses a machine learning model that continuously learns and regenerates placement plans based on the feedback. This model uses reinforcement learning.

[0589] Terminal handling

[0590] 1. Means of providing a dialogue interface

[0591] The terminals provide employees and factory robots with an interactive interface through which users can input information such as skills, experience, and desired position.

[0592] 2. Means of data transmission

[0593] The terminals transmit information entered by employees and factory robots to the server in real time, allowing the server to receive the necessary data immediately.

[0594] 3. Display of results

[0595] The terminal receives profile data and optimal placement suggestions from the server and displays them to employees and robots, allowing users to review the placement suggestions and provide feedback.

[0596] User Action

[0597] 1. Enter your information

[0598] The user uses the interactive interface of the terminal to input information such as his / her skills, experience, desired position, etc. This information is then sent from the terminal to the server.

[0599] 2. Providing Feedback

[0600] Users can input feedback on the placement proposals from the server, such as, "This position is interesting, but I would prefer a role that allows for more leadership."

[0601] Specific examples

[0602] For example, suppose you input skill data about factory robot A. Based on past data, robot A is good at "welding work," and feedback from robot A indicates that it would be better suited to a role that allows it to take on more leadership roles.

[0603] The server will then use this information to propose the optimal welding leader position and generate an optimized placement plan through re-evaluation. Specific examples of prompts are as follows:

[0604] Example prompt sentence:

[0605] "Please enter the skill data for Robot A in your factory. Example: Robot A has excellent welding skills and is fast at work. He also desires a leadership role."

[0606] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[0607] Step 1:

[0608] The server receives employee input data sent from the terminals, as well as factory robot operation status and performance data. This data includes employee skills, experience, desired positions, robot operating hours, error rates, and work speed. The received data is stored in a database on the server. Specific hardware used to collect data includes IoT sensors and sensors built into the robots.

[0609] Step 2:

[0610] The server runs a natural language processing (NLP) algorithm on the collected data. The NLP algorithm extracts keywords related to the skills and experience of employees and robots. This process uses NLP libraries (Spacy and NLTK) and machine learning models (Scikit-learn and TensorFlow). The input is the collected raw data, and the output is a list of keywords as a result of the analysis.

[0611] Step 3:

[0612] The server generates and stores profile data for employees and robots based on the extracted keywords. The profile data includes detailed information such as skill sets, experience, desired positions and tasks. This profile data is stored in a database using MySQL or PostgreSQL. The input is the analysis result from step 2, and the output is the stored profile data.

[0613] Step 4:

[0614] The server runs a matching algorithm to match employee and robot profile data with the company's needs. The matching takes into account the company's open positions, project requirements, and factory tasks. The algorithm uses a segmented matching algorithm or a genetic algorithm. The input is the profile data and the company's needs data, and the output is an optimal placement plan.

[0615] Step 5:

[0616] The terminal presents the generated placement plan to employees or robots and receives feedback. An example of feedback is a specific response such as, "This position is interesting, but I would prefer a role that allows me to demonstrate a bit more leadership." The input is the placement plan generated by the server, and the output is feedback from the user or robot.

[0617] Step 6:

[0618] The server reevaluates the system based on the received feedback and generates a relocation plan. A machine learning model (reinforcement learning model) that continuously learns is used for the reevaluation. This method optimizes the relocation plan based on the feedback. The input is the feedback from the user or robot, and the output is the regenerated optimal relocation plan.

[0619] Specific examples

[0620] For example, suppose you input skill data about factory robot A. Based on past data, robot A is good at "welding work," and feedback from robot A indicates that it would be better suited to a role that allows it to take on more leadership roles.

[0621] The server will then use this information to propose the optimal welding leader position and generate an optimized placement plan through re-evaluation. Specific examples of prompts are as follows:

[0622] Example prompt sentence:

[0623] "Please enter the skill data for Robot A in your factory. Example: Robot A has excellent welding skills and is fast at work. He also desires a leadership role."

[0624] 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.

[0625] A specific embodiment for realizing the system of the present invention will be described. In this system, three parties - a server, a terminal, and a user - each play their respective roles and work together to optimally allocate employees. Furthermore, by combining this with an emotion engine, it becomes possible to propose more effective allocations that take into account the user's emotions.

[0626] Server Processing

[0627] 1. Data Collection

[0628] The server receives the input data of the user (employee) sent from the terminal, including skills, experience, desired position, and conversation content. This data is stored in a database within the server.

[0629] 2. Data Analysis

[0630] The server runs a natural language processing (NLP) algorithm on the collected data to analyze it. Through the analysis, keywords such as employee skills, experience, and aspirations are extracted. Employee profile data is generated using the extracted data.

[0631] 3. Emotion analysis

[0632] The server uses an emotion engine to analyze the user's emotional state from the content of the conversation, for example, to detect whether the user is feeling stressed or excited during the conversation.

[0633] 4. Profile Management

[0634] The resulting profile data is stored as structured data containing the employee's detailed skill set, experience, desired position, and emotional state, providing an at-a-glance view of the employee's capabilities.

[0635] 5. Proposal for optimal layout

[0636] The server runs a matching algorithm that matches employee profile data with the company's current needs (open positions and project requirements). The algorithm matches the employee's skills with the company's needs and emotional state to generate optimal placement recommendations.

[0637] 6. Reassess and optimize

[0638] The server receives feedback from employees and re-evaluates them based on this. Using a continuously learning machine learning model, it generates reassignment plans based on the feedback. The results of sentiment analysis by the emotion engine are also taken into account.

[0639] Terminal handling

[0640] 1. Providing a conversational interface

[0641] The terminal provides the user (employee) with an interactive interface through which the user can input their skills, experience, desired position, and interaction content.

[0642] 2. Data transmission

[0643] The terminal transmits information entered by the user and the contents of the dialogue to the server in real time, allowing the server to receive the necessary data immediately.

[0644] 3. Displaying the results

[0645] The device displays the profile data and optimal placement proposals received from the server to the user, who can then review the proposals and provide feedback.

[0646] User Action

[0647] 1. Inputting information and interacting

[0648] The user uses the interactive interface of the terminal to input their skills, experience, desired position, and the content of the conversation. This information is sent from the terminal to the server, and the emotional state during the conversation is analyzed by the emotion engine.

[0649] 2. Providing Feedback

[0650] The user inputs feedback on the placement proposal from the server, for example, "This position is interesting, but I would also like to demonstrate leadership."

[0651] Specific examples

[0652] For example, if an employee enters, "I have five years of software development experience, and I'm particularly good at Python and Java," and then during the conversation says, "I'd like to try new technologies, but I'm a little nervous," the device sends this information to the server. The server uses natural language processing to analyze the employee's skills and experience, and further detects the emotion of nervousness using an emotion engine. It then generates profile data. The server then matches this profile data with the company's needs and generates an optimal placement proposal. For example, it might suggest, "A software engineer position on a new AI project would be suitable." The device displays this proposal to the user, who then provides feedback, saying, "I'd also like to demonstrate leadership." Through reevaluation, the server again proposes the "leadership position on a new AI project."

[0653] By utilizing the emotion engine, more optimal personnel placement can be achieved that takes into account the emotional state of employees, thereby improving productivity and efficiency across the entire company.

[0654] The processing flow will be explained below.

[0655] Step 1: The user initiates the interaction

[0656] Users access an interactive interface on their device and enter their skills, experience, and desired position, for example, "I have five years of software development experience, and I am particularly skilled in Python and Java."

[0657] Step 2: The device sends user input to the server

[0658] The device sends the information entered by the user to the server in real time, using API requests to transfer this data to the server.

[0659] Step 3: The device collects emotion data

[0660] The device analyzes the user's tone of voice and facial expressions during the conversation to collect emotional data, using audio recordings and cameras.

[0661] Step 4: The device sends the emotion data to the server.

[0662] The device transmits the collected emotional data to the server, which allows the server to recognize the emotional state.

[0663] Step 5: The server receives and stores the data

[0664] The server receives the user's input data and emotion data sent from the terminal and stores them in a database, including skills, experience, desired position, and emotion data.

[0665] Step 6: The server performs the data analysis

[0666] The server analyzes the stored data using natural language processing (NLP) algorithms, extracting keywords such as skills, experience, and aspirations, and converting them into structured data.

[0667] Step 7: The server performs sentiment analysis

[0668] The server uses an emotion engine to analyze the user's emotional state during the conversation, for example, to detect whether the user is feeling stressed or excited during the conversation.

[0669] Step 8: Server generates profile data

[0670] The server generates user profile data based on the extracted keywords and the results of sentiment analysis, which includes the user's skill set, experience, desired position, and emotional state.

[0671] Step 9: The server saves the profile data

[0672] The server stores the generated profile data in a database, which allows detailed employee information to be managed.

[0673] Step 10: The server captures the needs of the enterprise

[0674] The server retrieves data from a database about the company's current needs and open positions, including the skill requirements and responsibilities for each position.

[0675] Step 11: The server generates the optimal placement plan

[0676] The server runs a matching algorithm to match users' profile data with the company's needs, and generates optimal staffing recommendations based on skill matching and role compatibility.

[0677] Step 12: The server sends the placement plan to the device.

[0678] The server sends the generated placement plan to the terminal, allowing the user to check the proposed content.

[0679] Step 13: The device displays the layout plan to the user.

[0680] The device displays the placement proposal received from the server to the user, specifically displaying details of the placement proposal (e.g., a software engineer position for a new AI project).

[0681] Step 14: Users provide feedback

[0682] The user can then provide feedback on the proposed placement, such as, "This position is interesting, but I would also like to demonstrate leadership."

[0683] Step 15: Device sends feedback to server

[0684] The device receives the user's feedback and sends it to the server. The device forwards the feedback to the server using an API request.

[0685] Step 16: Server performs re-evaluation

[0686] The server reevaluates the system based on user feedback and uses a continuously learning machine learning model to generate optimal relocation plans based on the feedback.

[0687] Step 17: The server sends the reevaluation result to the terminal.

[0688] The server transmits the re-evaluation results to the terminal, and the regenerated placement plan is transferred to the terminal.

[0689] Step 18: The terminal displays the reevaluation results to the user

[0690] The device displays the reevaluation results received from the server to the user, for example, "You are recommended for a leadership position in a new AI project."

[0691] Through these steps, the system of the present invention can realize optimal personnel allocation based on employees' characteristics and preferences, improving the productivity and efficiency of the entire company. By utilizing the emotion engine, it is possible to propose more optimal personnel allocation that takes into account the emotional state of employees.

[0692] Example 2

[0693] 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."

[0694] When it comes to optimal personnel placement that takes into account employees' skills, experience, and desired positions, traditional profile analysis and matching algorithms alone have limitations, making it difficult to properly incorporate employees' emotional states and feedback. Furthermore, the reevaluation and reassignment process can be inefficient, negatively impacting employee satisfaction and corporate productivity. There is a need to solve these issues and provide a more effective and flexible personnel placement system.

[0695] The specific processing by the specific processing unit 290 of the data processing device 12 in the second embodiment is realized by the following means.

[0696] In this invention, the server includes an interactive interface providing means for inputting employee skills, experience, and desired positions, a natural language processing algorithm processing means for collecting and analyzing the content of employee dialogue, a profile management means for generating and saving employee profile data based on the analysis results, an emotion analysis means for analyzing the emotional state of employees from the content of dialogue, a matching algorithm processing means for matching the profile data with the needs of the company and generating an optimal personnel placement plan, a means for presenting the generated placement plan to employees and receiving feedback, and an optimization means for reevaluating based on the feedback and generating a reallocation plan. This makes it possible to generate flexible and effective placement plans that take into account the emotional state of employees, thereby improving employee satisfaction and corporate productivity.

[0697] An "interactive interface" is a user interface that allows employees to input information such as their skills, experience, and desired position.

[0698] A "natural language processing algorithm" is an algorithm that analyzes the content of employee conversations and extracts necessary information and keywords.

[0699] "Profile Data" is structured data that includes an employee's skills, experience, desired position, and other relevant information.

[0700] The "profile management means" is a means for saving and managing the generated profile data.

[0701] The "emotion analysis means" is a means for analyzing and detecting the emotional state of an employee from the content of their conversation.

[0702] The "matching algorithm" is an algorithm that matches profile data with the needs of the company and generates optimal personnel placement plans.

[0703] The "optimization means" is a means for reassessing employees based on their feedback and generating reassignment plans.

[0704] "Feedback" refers to the opinions and thoughts employees provide about proposed placements.

[0705] "Placement proposals" are suggestions for optimal personnel placement generated based on employee profile data and the company's needs.

[0706] The system of the present invention is designed to generate optimal personnel allocation plans that take into account employees' skills, experience, desired positions, and also their emotional state. This system operates in cooperation with three parties: a server, a terminal, and a user.

[0707] Server Processing

[0708] The server first receives the employee's input data sent from the terminal. This data includes the employee's skills, experience, desired position, and conversation content. The received data is then stored in a database. Specifically, a database management system such as MySQL or PostgreSQL can be used.

[0709] The server then runs natural language processing (NLP) algorithms on the stored data, using libraries like Python's NLTK and SpaCy, to analyze the data and extract keywords related to the employee's skills, experience, and aspirations.

[0710] Furthermore, the server uses an emotion engine to analyze the user's emotional state from the dialogue. For example, by using the Google Cloud Natural Language API, it can detect emotions such as stress or excitement felt by the user.

[0711] The generated profile data is stored as structured data that includes the employee's detailed skill set, experience, desired position, and emotional state.

[0712] The server then runs a matching algorithm that matches employee profile data with the company's needs using machine learning models such as Google Cloud AutoML and TensorFlow, generating optimal placement recommendations that match the employee's skills with the company's needs and emotional state.

[0713] The server receives feedback from users and reevaluates it using a machine learning model that continuously learns. This generates a relocation plan based on the feedback, taking into account the results of emotion analysis by the emotion engine.

[0714] Terminal handling

[0715] The terminal provides the user (employee) with an interactive interface through which the user can input their skills, experience, desired position, and interaction content.

[0716] The terminal transmits information entered by the user and the contents of the dialogue to the server in real time, allowing the server to receive the necessary data immediately.

[0717] The device also displays the profile data and optimal placement proposals received from the server to the user, who can then review the proposals and provide feedback.

[0718] User Action

[0719] The user uses the interactive interface of the terminal to input their skills, experience, desired position, and the content of the conversation. This information is sent from the terminal to the server, and the emotional state during the conversation is analyzed by the emotion engine.

[0720] Furthermore, users can input feedback on the placement proposals from the server, for example, "This position is interesting, but I would also like to demonstrate leadership skills."

[0721] Specific examples

[0722] As a specific example, if an employee types, "I have five years of software development experience and am particularly good at Python and Java," and then during the conversation says, "I would like to try new technologies, but I'm a little nervous," the device will send this information to the server.

[0723] The server analyzes the employee's skills and experience through natural language processing and detects anxiety using an emotion engine. It then generates profile data. The server matches this profile data with the company's needs and generates optimal placement recommendations. For example, it might suggest, "A software engineer position for a new AI project would be suitable."

[0724] The terminal displays the proposal to the user, who then provides feedback, saying, "I would also like to demonstrate leadership." Through reevaluation, the server can re-propose the "leadership position for a new AI project."

[0725] Prompt Sentence Examples

[0726] Below are some examples of specific prompt sentences to input into the generative AI model.

[0727] Prompt: I have 5 years of software development experience, particularly in Python and Java. I'd like to try new technologies but am a bit nervous. Please suggest a suitable position for me.

[0728] In this way, taking into account the emotional state of employees can lead to more effective and flexible staffing, improving productivity and efficiency across the company.

[0729] The flow of the identification process in the second embodiment will be described with reference to FIG.

[0730] Step 1: Data collection

[0731] The server receives user (employee) input data sent from the terminal. The input data includes the user's skills, experience, desired position, and dialogue content. This data is stored in a database (such as MySQL or PostgreSQL) on the server. For example, if a user enters "I have five years of software development experience, and I am particularly good at Python and Java," the terminal sends this information to the server, which stores it in a "user data" table.

[0732] Step 2: Data analysis

[0733] The server runs natural language processing (NLP) algorithms on the stored data to analyze it. Specifically, it uses Python's NLTK and SpaCy libraries to extract keywords related to the user's skills, experience, and desired position. For example, from an input such as "I have five years of software development experience, and I am particularly good at Python and Java," it extracts keywords such as "software development," "Python," and "Java."

[0734] Step 3: Sentiment Analysis

[0735] The server uses an emotion engine to analyze the user's emotional state from the dialogue content. Based on the input dialogue content, the emotion engine (e.g., Google Cloud Natural Language API) detects emotions such as "anxiety," "excitement," and "stress." For example, if a user inputs "I want to try a new technology, but I'm a little anxious," the emotion engine will detect the emotion "anxiety."

[0736] Step 4: Profile Management

[0737] The server generates employee profile data based on the extracted data and the results of sentiment analysis and stores it in a database. The generated profile data includes the employee's skill set, experience, desired position, and emotional state. For example, data such as "software development," "Python," "Java," and "anxiety" are stored in the "Employee Profile" table.

[0738] Step 5: Propose optimal layout

[0739] The server runs a matching algorithm that matches employee profile data with the company's needs. Using Google Cloud AutoML and TensorFlow, it generates optimal staffing recommendations based on the profile data and company needs. Using data on "software development," "Python," "Java," and "anxiety" as input, it compares these with the company's requirements for a "new AI project" and proposes a "software engineer position for a new AI project."

[0740] Step 6: Viewing results and feedback

[0741] The terminal displays the placement proposal received from the server to the user. The user checks the placement proposal and inputs feedback through an interactive interface. For example, if the user provides an opinion such as "This position is interesting, but I also want to demonstrate leadership," the terminal sends this feedback to the server.

[0742] Step 7: Reassess and optimize

[0743] The server receives feedback from users and reevaluates them using a continuously learning machine learning model. Based on the feedback and sentiment analysis results, it generates new reassignment proposals. For example, it may re-propose a "leadership position for a new AI project." This process can improve employee satisfaction and company productivity.

[0744] Prompt sentences with examples

[0745] Below are some examples of specific prompt sentences to input into the generative AI model.

[0746] Prompt: I have 5 years of software development experience, particularly in Python and Java. I'd like to try new technologies but am a bit nervous. Please suggest a suitable position for me.

[0747] (Application example 2)

[0748] 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."

[0749] Conventional systems that optimize the allocation of employee skills and experience do not take into account the emotional state of employees, resulting in a high risk of poor performance after allocation or employee turnover due to dissatisfaction. Furthermore, there was a lack of a system that could simultaneously analyze employee dialogue and emotions and quickly propose optimal allocations, so these issues need to be addressed.

[0750] The specific processing by the specific processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means. In this invention, the server includes an interactive interface providing means for inputting employee skills, experience, and desired positions, a natural language processing algorithm processing means for collecting and analyzing the content of employee dialogue, and a profile management means for generating and saving employee profile data based on the analysis results. This makes it possible to generate optimal placement plans that also take into account the emotional state of employees.

[0751] The "interactive interface providing means" is a means for providing an interactive interface for employees to input their skills, experience, and desired position.

[0752] The "natural language processing algorithm processing means" is a means that uses a natural language processing algorithm to collect and analyze the content of employee dialogue.

[0753] The "profile management means" is a means for generating and storing employee profile data based on the analysis results.

[0754] The "matching algorithm processing means" is a means that uses an algorithm to match profile data with the needs of the company and generate an optimal personnel allocation plan.

[0755] The "feedback receiving means" is a means for presenting the generated placement plan to employees and receiving their feedback.

[0756] The "re-evaluation means" is a means for performing a re-evaluation based on the feedback and generating a re-placement plan.

[0757] The "emotion analysis means" is a means for analyzing the emotional state of an employee from the content of their conversation.

[0758] "Means for adopting machine learning models" refers to means for adopting machine learning models that continuously learn based on employee feedback.

[0759] In the system for realizing the application example of the present invention, a server, a terminal, and a user work together. The following is a detailed description of how the system is implemented.

[0760] Server Processing

[0761] The server receives data sent from a terminal having an interactive interface supply means for inputting the employee's skills, experience, and desired position. The server analyzes the content of the dialogue using a natural language processing algorithm processing means, and generates and saves the analysis results as employee profile data using a profile management means.

[0762] The server analyzes the content of the employee's conversation using an emotion analysis means and also digitizes the employee's emotional state. It then compares the profile data with the company's needs and generates an optimal personnel placement plan using a matching algorithm processing means. The generated placement plan is then presented to the employee via their terminal, and the feedback from the employee is received using a feedback receiving means. A reevaluation means reevaluates the employee based on the feedback and generates a relocation plan. At this time, a machine learning model adoption means that continuously learns based on employee feedback is used to constantly update the optimal placement plan.

[0763] Terminal handling

[0764] The terminal provides a dialogue interface for users (employees) to input their skills, experience, and desired position. This information is sent to the server in real time. The dialogue is converted into text using voice recognition technology and sent to the server.

[0765] User Action

[0766] Users (employees) use the interactive interface on their terminals to input their skills, experience, desired position, and the content of their conversations. The input data is sent to the server, and their emotional state is analyzed using emotion analysis means. By providing feedback on the proposed placement plan, even more accurate placement plans can be regenerated.

[0767] Hardware and software used

[0768] The server uses the "TextBlob" library for natural language processing, the "NLTK" library for sentiment analysis, and the "scikit-learn" clustering algorithm. The device uses the "speech_recognition" library for speech recognition, converting user voice input into text data.

[0769] Specific examples

[0770] For example, if an employee says, "I'd like to help install a new logistics system, but I'm a little worried about the technology," the system can analyze the employee's concerns about the new technology and suggest an appropriate support system.

[0771] Example prompts to be input to the generative AI model

[0772] "Employees have expressed anxiety about new technology. What kind of assistance system should we suggest to employees who feel the same way?"

[0773] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[0774] Program processing flow

[0775] Step 1: Collecting user (employee) input data

[0776] The terminal provides an interactive interface for users to input their skills, experience, and desired position. The user inputs their skills, experience, desired position, and dialogue content through the interface. The terminal uses voice recognition technology to convert the user's voice input into text data. The generated text data is sent to the server in real time.

[0777] Input: User (employee) voice input

[0778] Data processing: Converting speech into text using voice recognition technology

[0779] Output: Text data

[0780] Step 2: Employee data analysis

[0781] The server receives the employee's conversation content sent from the terminal. Using a natural language processing algorithm, it extracts and analyzes information such as skills, experience, and desired position from the employee's conversation content. Based on this data, it generates employee profile data and stores it in a database.

[0782] Input: Text data

[0783] Data processing: Extraction and analysis of keywords using natural language processing algorithms

[0784] Output: Profile data

[0785] Step 3: Sentiment Analysis

[0786] The server uses emotion analysis means to analyze the employee's emotional state (e.g., stress, anxiety, excitement) based on the content of the employee's dialogue. The results of the emotion analysis are added to the profile data.

[0787] Input: Text data of the dialogue

[0788] Data processing: Emotion analysis algorithm analyzes emotional state

[0789] Output: Emotional state data

[0790] Step 4: Propose optimal layout

[0791] The server uses a matching algorithm processing means to match the generated profile data with the needs of the company, and generates an optimal personnel allocation plan by taking into account the employee's skills, experience, and emotional state. The allocation plan is presented to the employee via the terminal.

[0792] Input: Profile data, company needs

[0793] Data processing: Generate placement plans using a matching algorithm

[0794] Output: Optimal layout plan

[0795] Step 5: Receiving feedback

[0796] The terminal presents the generated placement plan to the employee, who then inputs feedback on the placement plan. The input feedback is sent to the server in real time.

[0797] Input: Optimal layout plan

[0798] Data processing: Employee feedback input

[0799] Output: Feedback data

[0800] Step 6: Reassess and optimize

[0801] The server performs re-evaluation based on the feedback received from employees. Using the re-evaluation method and the machine learning model adoption method, it generates a re-allocation plan that takes the feedback data into consideration. This enables optimal personnel allocation that takes into account the feedback and emotional state of employees.

[0802] Input: Feedback data

[0803] Data Transformation: Continuously train and reassess machine learning models

[0804] Output: Relocation proposal

[0805] Examples and prompts

[0806] For example, if an employee says, "I'd like to help install a new logistics system, but I'm a little worried about the technology," the system can analyze the employee's concerns about the new technology and suggest an appropriate support system.

[0807] Example prompts to input to a generative AI model:

[0808] "Employees have expressed anxiety about new technology. What kind of assistance system should we suggest to employees who feel the same way?"

[0809] 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.

[0810] 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.

[0811] 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.

[0812] [Third embodiment]

[0813] FIG. 5 shows an example of the configuration of a data processing system 310 according to the third embodiment.

[0814] 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.

[0815] 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).

[0816] 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.

[0817] 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.

[0818] 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).

[0819] 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.

[0820] 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.

[0821] 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.

[0822] 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.

[0823] 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.

[0824] 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."

[0825] A specific embodiment for realizing the system of the present invention will be described. In this system, three parties, a server, a terminal, and a user, each play their respective roles and work together to optimally allocate employees.

[0826] Server Processing

[0827] 1. Data Collection

[0828] The server receives the user (employee) input data sent from the terminal, including skills, experience, desired position, etc. This data is stored in a database within the server.

[0829] 2. Data Analysis

[0830] The server runs a natural language processing (NLP) algorithm on the collected data to analyze it. Through the analysis, keywords such as employee skills, experience, and aspirations are extracted. Employee profile data is generated using the extracted data.

[0831] 3. Profile Management

[0832] The generated profile data is stored as structured data containing the employee's detailed skill set and desired position, allowing employees to see their capabilities at a glance.

[0833] 4. Proposal for optimal layout

[0834] The server runs a matching algorithm that matches employee profile data with the company's current needs (open positions and project requirements). The algorithm matches employee skills with the company's needs and generates optimal placement proposals.

[0835] 5. Reassess and optimize

[0836] The server receives feedback from employees and re-evaluates them based on this feedback. The re-evaluation uses a continuously learning machine learning model to regenerate placement proposals based on the feedback.

[0837] Terminal handling

[0838] 1. Providing a conversational interface

[0839] The terminal provides the user (employee) with an interactive interface through which the user can input information such as skills, experience, and desired position.

[0840] 2. Data transmission

[0841] The terminal transmits the information input by the user to the server in real time, allowing the server to receive the necessary data immediately.

[0842] 3. Displaying the results

[0843] The device displays the profile data and optimal placement proposals received from the server to the user, who can then review the placement proposals and provide feedback.

[0844] User Action

[0845] 1. Enter your information

[0846] The user uses the interactive interface of the terminal to input information such as his / her skills, experience, desired position, etc. This information is then sent from the terminal to the server.

[0847] 2. Providing Feedback

[0848] Users can input feedback on the placement proposals from the server, such as, "This position is interesting, but I would prefer a role that allows for more leadership."

[0849] Specific examples

[0850] For example, if an employee enters, "I have five years of software development experience, and I'm particularly good at Python and Java," the device sends this information to the server. The server uses natural language processing to analyze the employee's skills and experience and generate profile data. The server then matches this profile data with the company's needs and generates an optimal placement proposal. For example, it might suggest, "A software engineer position on a new AI project would be suitable." The device displays this proposal to the user, who then provides feedback, saying, "I'd also like to demonstrate leadership skills." Through reevaluation, the server again proposes the "leadership position on a new AI project."

[0851] As a result, the system of the present invention can realize optimal personnel allocation based on the characteristics and desires of each employee, thereby improving the productivity and efficiency of the entire company.

[0852] The processing flow will be explained below.

[0853] Step 1: The user initiates the interaction

[0854] Users access an interactive interface on their device and enter their skills, experience, and desired position, for example, "I have five years of software development experience, and I am particularly skilled in Python and Java."

[0855] Step 2: The device sends user input to the server

[0856] The device sends the information entered by the user to the server in real time, using API requests to transfer this data to the server.

[0857] Step 3: The server receives and stores the data

[0858] The server receives the user's input data sent from the terminal and stores it in a database, including skills, experience, desired position, etc.

[0859] Step 4: The server performs the data analysis

[0860] The server analyzes the stored data using natural language processing (NLP) algorithms, extracting keywords such as skills, experience, and aspirations, and converting them into structured data.

[0861] Step 5: The server generates the profile data

[0862] The server generates user profile data based on the extracted keywords, which includes the user's skill set, experience, and desired position.

[0863] Step 6: The server saves the profile data

[0864] The server stores the generated profile data in a database, which allows detailed employee information to be managed.

[0865] Step 7: The server gets the company's needs

[0866] The server retrieves data from a database about the company's current needs and open positions, including the skill requirements and responsibilities for each position.

[0867] Step 8: The server generates the optimal placement plan

[0868] The server runs a matching algorithm to match users' profile data with the company's needs, and generates optimal staffing recommendations based on skill matching and role compatibility.

[0869] Step 9: The server sends the placement plan to the device.

[0870] The server sends the generated placement plan to the terminal, allowing the user to check the proposed content.

[0871] Step 10: The device displays the layout plan to the user.

[0872] The terminal displays the placement proposal received from the server to the user, specifically displaying details of the placement proposal (e.g., a software engineer position for a new project).

[0873] Step 11: Users provide feedback

[0874] The user can then provide feedback on the proposed placement, such as, "This position is interesting, but I would also like to demonstrate leadership."

[0875] Step 12: Device sends feedback to server

[0876] The device receives the user's feedback and sends it to the server. The device forwards the feedback to the server using an API request.

[0877] Step 13: Server performs re-evaluation

[0878] The server reevaluates the system based on user feedback and uses a machine learning model to generate optimal relocation plans.

[0879] Step 14: The server sends the reevaluation result to the terminal.

[0880] The server transmits the re-evaluation results to the terminal, and the regenerated placement plan is transferred to the terminal.

[0881] Step 15: The terminal displays the reevaluation results to the user

[0882] The device displays the reevaluation results received from the server to the user, for example, "You are recommended for a leadership position in a new AI project."

[0883] Through these steps, the system of the present invention can realize optimal personnel allocation based on the characteristics and desires of employees, thereby improving productivity and efficiency across the entire company.

[0884] Example 1

[0885] 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."

[0886] Modern companies are required to assign personnel to positions that optimally reflect the characteristics and preferences of their employees. However, it is difficult to effectively collect and analyze employee skills, experience, and desired positions, and to assign personnel to positions that optimally meet the company's needs. Another challenge is collecting feedback from employees in real time and reevaluating and optimizing assignment plans based on that feedback.

[0887] 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.

[0888] In this invention, the server includes: an interactive interface providing means for inputting employee skills, experience, and desired positions; a natural language processing algorithm processing means for collecting and analyzing the content of the employee's dialogue; a profile management means for generating and saving employee profile data based on the analysis results; a matching algorithm processing means for matching the profile data with the company's needs and generating optimal personnel placement plans; a means for presenting the generated placement plans to employees and receiving feedback; an optimization means for reevaluating based on the feedback and generating reallocation plans; a data transmission means for transmitting information input by employees using the interface to the server; a means for the server to store the employee's input data in a database; and a means for the server to optimize the placement plans using a machine learning model. This enables companies to achieve optimal personnel placement based on the characteristics and preferences of their employees, thereby improving the productivity and efficiency of the entire company.

[0889] The "interactive interface providing means" is a means for providing an interface for employees to input their skills, experience, and desired position.

[0890] The "natural language processing algorithm processing means" is a means for executing an algorithm used to collect and analyze the content of employee dialogue.

[0891] The "profile management means" is a means for generating and storing employee profile data based on the analyzed data.

[0892] The "matching algorithm processing means" is a means for executing an algorithm that matches employee profile data with the needs of the company and generates optimal personnel allocation plans.

[0893] The "means for receiving feedback" is a means for presenting the generated placement plan to employees and receiving opinions and evaluations from the employees.

[0894] The "optimization method" is a method for reevaluating employees based on their feedback and generating a reassignment plan.

[0895] The "data transmission means" is a means for transmitting information entered by an employee using an interface to a server.

[0896] The "means for saving to a database" is the means by which the server saves the employee's input data to a database.

[0897] "Means for optimizing placement plans using machine learning models" refers to means for optimizing placement plans based on feedback from employees using machine learning models.

[0898] A specific embodiment for carrying out the present invention will be described below. In the system for carrying out the present invention, a server, a terminal, and a user each play their respective roles and work together to achieve optimal staffing.

[0899] Server Processing

[0900] The server first receives the user (employee) input data sent from the terminal. This data includes skills, experience, desired position, etc., and the server stores this in a database. The software used is a database management system (e.g., MySQL, PostgreSQL).

[0901] The server then runs a natural language processing (NLP) algorithm on the received data to analyze it. Specifically, it uses a Python NLP library (e.g., NLTK, SpaCy) to extract keywords such as employee skills, experience, and aspirations. The extracted data is used to generate employee profile data and store it in a database.

[0902] The server then runs a matching algorithm to match the generated profile data with the company's current needs (open positions and project requirements), using machine learning models (e.g., Scikit-learn classifiers), to match employee skills with the company's needs and generate optimal placement proposals.

[0903] The server also receives feedback from employees and uses machine learning models to reevaluate and optimize placement proposals, including a continuous learning process to incorporate feedback.

[0904] Terminal handling

[0905] The terminal provides the user (employee) with an interactive interface, which can be implemented, for example, as a web-based application (e.g., React or Angular), where the user can enter information such as skills, experience, and desired position.

[0906] The terminal transmits the information input by the user to the server in real time. The transmission process uses HTTP requests. Furthermore, a GUI is provided to display the profile data received from the server and the optimal placement plan to the user, allowing the user to easily input feedback.

[0907] User Action

[0908] The user uses the interactive interface of the terminal to input information such as his / her skills, experience, desired position, etc. This information is sent to the server via the terminal.

[0909] The user then reviews the placement proposals presented by the server and provides feedback if necessary. This feedback is then sent back to the server via the terminal and used to reevaluate and optimize the optimal placement proposal.

[0910] Specific examples

[0911] For example, an employee might enter, "I have five years of software development experience, and I'm particularly good at Python and Java." The device sends this information to the server using an HTTP request. The server uses NLTK for natural language processing to analyze the employee's skills and experience. The analyzed data is then saved as profile data and matched with the company's needs using a Scikit-learn classifier. As a result, a placement suggestion is generated: "A software engineer position on a new AI project would be suitable for you." This placement suggestion is displayed to the user via the device, and if the user adds feedback such as "I would also like to demonstrate leadership skills," it is sent back to the server. The server then reevaluates this feedback and proposes a new "leadership position on a new AI project."

[0912] This system allows companies to realize optimal allocation based on the characteristics and wishes of their employees, improving overall productivity and efficiency. By implementing this system, companies can maximize the potential of their human resources and achieve greater efficiency and improvement in their work.

[0913] The flow of the identification process in the first embodiment will be described with reference to FIG.

[0914] Step 1:

[0915] Entering and sending information (device operation)

[0916] Users input their skills, experience, and desired position through the device's interactive interface. Input information might include, "I have five years of software development experience, and I'm particularly good at Python and Java." The device receives this input information and sends it to the server using an HTTP request.

[0917] Input: User input data on skills, experience, and desired position

[0918] Output: Data sent in the form of an HTTP request

[0919] Specific operation: The user enters data into the input form and clicks the "Submit" button, which sends the data to the server.

[0920] Step 2:

[0921] Receiving and storing data (server operation)

[0922] The server receives the user's input data sent from the terminal and stores it in a database. The database management system used in this case may be MySQL or PostgreSQL.

[0923] Input: User input data sent from the terminal (HTTP request)

[0924] Output: Data stored in the database

[0925] What happens: The server parses the HTTP request and writes the information to a database.

[0926] Step 3:

[0927] Data analysis using natural language processing (server operation)

[0928] The server retrieves the user input data from the database and analyzes it using natural language processing (NLP) algorithms, specifically using Python NLP libraries (e.g., NLTK and SpaCy) to extract keywords related to employee skills, experience, and preferences.

[0929] Input: User-entered data stored in a database

[0930] Output: Parsed keywords and skill sets

[0931] Specific operation: The server runs an NLP algorithm to extract key keywords from the text data.

[0932] Step 4:

[0933] Generating and saving profile data (server operation)

[0934] The server generates employee profile data based on the data analyzed by NLP, which is then stored in a database as structured data including detailed skill sets and desired positions.

[0935] Input: Parsed keywords and skill sets

[0936] Output: Structured profile data

[0937] Specific operation: The server stores the generated profile data in a database.

[0938] Step 5:

[0939] Generating optimal placement plans (server operation)

[0940] The server runs a matching algorithm that matches employee profile data with the company's current needs (open positions and project requirements), using Scikit-learn classifiers. This process generates optimal staffing recommendations.

[0941] Input: Profile data, company needs

[0942] Output: Optimal staffing plan

[0943] Specific operation: The server executes a matching algorithm and generates placement proposals.

[0944] Step 6:

[0945] Presenting placement plans and receiving feedback (collaboration between terminals and servers)

[0946] The server sends the generated optimal placement plan to the terminal, which displays the placement plan to the user, who then inputs feedback on it. The terminal then sends the user's feedback back to the server.

[0947] Input: Optimal staffing plan, user feedback

[0948] Output: Received feedback

[0949] Specific operation: The server sends the placement plan to the terminal, which displays the placement plan in a GUI. The user enters feedback, and the terminal sends this information to the server.

[0950] Step 7:

[0951] Re-evaluation based on feedback and regeneration of optimal placement plan (server operation)

[0952] The server receives user feedback, re-evaluates it using machine learning models, and generates optimized relocation proposals. This process involves continuous training of the machine learning models.

[0953] Input: User feedback

[0954] Output: Optimized relocation plan

[0955] What it does: The server runs a machine learning algorithm and generates new placement suggestions based on the feedback.

[0956] Through this series of steps, the system can achieve optimal personnel allocation based on employees' characteristics and preferences, improving productivity and efficiency across the company.

[0957] (Application example 1)

[0958] 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."

[0959] Conventional employee allocation systems can sometimes struggle to optimally allocate employees based on their skills, experience, and desired positions. It's also difficult to collect real-time operational status and performance data for factory robots and optimally allocate tasks based on that data. In particular, there's a lack of reevaluation and optimization based on feedback, preventing efficiency improvements over the long term. Therefore, there's a need for a system that can efficiently allocate and manage tasks for employees and factory robots.

[0960] 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.

[0961] In this invention, the server includes: an interactive interface providing means for inputting employee skills, experience, and desired position; a natural language processing algorithm processing means for collecting and analyzing the content of the employee's dialogue; a profile management means for generating and saving employee profile data based on the analysis results; a matching algorithm processing means for matching the profile data with the company's needs and generating an optimal personnel allocation plan; a means for presenting the generated allocation plan to employees and receiving feedback; an optimization means for reevaluating based on the feedback and generating a reallocation plan; a data collection means for collecting factory robot operation status and performance data and sending it to the cloud server; a data analysis means for analyzing the collected data using a natural language processing algorithm and generating a robot skill profile; a profile management means for saving and managing the skill profile data generated based on the analysis results; a matching algorithm processing means for generating an optimal task allocation plan; and a reevaluation and optimization means for reevaluating based on feedback from the robot and generating an optimized allocation plan. This enables dynamic and efficient allocation and task management for both employees and factory robots.

[0962] The "interactive interface providing means" is a means for providing an interface for a user to input information such as skills, experience, and desired position.

[0963] "Natural language processing algorithm processing means" refers to a means that uses natural language processing technology to analyze the collected dialogue content and extract important keywords such as skills and experience.

[0964] The "profile management means" is a means for saving and managing the profile data of employees or robots generated based on the analysis results.

[0965] The "matching algorithm processing means" is a means for matching the generated profile data with the needs of the company or factory and using an algorithm to generate an optimal allocation plan or task allocation plan.

[0966] The "feedback means" is a means for presenting the generated placement plans and task placement plans to the user or robot and receiving their reactions and opinions.

[0967] The "optimization means" is a means for reevaluating based on feedback from users and robots and generating an even more optimal placement plan.

[0968] The "data collection means" is a means for collecting the operating status and performance data of factory robots in real time and sending it to a cloud server.

[0969] The "data analysis means" is a means for analyzing collected performance data and generating a skill profile of the robot.

[0970] The "reevaluation and optimization method" is a method for reevaluating the analysis algorithm constructed based on the robot's feedback and generating an optimal task allocation plan.

[0971] A "skill profile" is structured data that contains detailed information about the skills, abilities, and experience of employees and robots.

[0972] A specific embodiment for realizing the system of the present invention will be described. This system optimizes the allocation of employees and factory robots, with the server, terminals, and users each playing their respective roles and working together to optimally allocate personnel and tasks.

[0973] Server Processing

[0974] 1. Data Collection Methods

[0975] The server receives employee input data (skills, experience, desired position, etc.) sent from the terminal, and also collects the operating status and performance data of the factory robots. This data is stored on the server.

[0976] 2. Data analysis methods

[0977] The server runs a natural language processing (NLP) algorithm on the collected data to analyze it. This analysis extracts keywords related to the skills, experience, and preferences of employees and robots. Specific software used is an NLP library (Spacy or NLTK) or a machine learning model (Scikit-learn or TensorFlow).

[0978] 3. Profile Management Methods

[0979] The generated profile data is stored as structured data that includes detailed skill sets and preferences of employees and robots, making it possible to see their skills and preferences at a glance. The database uses MySQL or PostgreSQL.

[0980] 4. Matching Algorithm Processing Means

[0981] The server runs matching algorithms, such as segmental matching algorithms and genetic algorithms, to match employee and robot profile data with the company's current needs (vacant positions, project requirements, tasks, etc.), generating optimal placement proposals.

[0982] 5. Reevaluation and optimization measures

[0983] The server receives feedback from employees and robots and re-evaluates them based on this feedback. This re-evaluation uses a machine learning model that continuously learns and regenerates placement plans based on the feedback. This model uses reinforcement learning.

[0984] Terminal handling

[0985] 1. Means of providing a dialogue interface

[0986] The terminals provide employees and factory robots with an interactive interface through which users can input information such as skills, experience, and desired position.

[0987] 2. Means of data transmission

[0988] The terminals transmit information entered by employees and factory robots to the server in real time, allowing the server to receive the necessary data immediately.

[0989] 3. Display of results

[0990] The terminal receives profile data and optimal placement suggestions from the server and displays them to employees and robots, allowing users to review the placement suggestions and provide feedback.

[0991] User Action

[0992] 1. Enter your information

[0993] The user uses the interactive interface of the terminal to input information such as his / her skills, experience, desired position, etc. This information is then sent from the terminal to the server.

[0994] 2. Providing Feedback

[0995] Users can input feedback on the placement proposals from the server, such as, "This position is interesting, but I would prefer a role that allows for more leadership."

[0996] Specific examples

[0997] For example, suppose you input skill data about factory robot A. Based on past data, robot A is good at "welding work," and feedback from robot A indicates that it would be better suited to a role that allows it to take on more leadership roles.

[0998] The server will then use this information to propose the optimal welding leader position and generate an optimized placement plan through re-evaluation. Specific examples of prompts are as follows:

[0999] Example prompt sentence:

[1000] "Please enter the skill data for Robot A in your factory. Example: Robot A has excellent welding skills and is fast at work. He also desires a leadership role."

[1001] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[1002] Step 1:

[1003] The server receives employee input data sent from the terminals, as well as factory robot operation status and performance data. This data includes employee skills, experience, desired positions, robot operating hours, error rates, and work speed. The received data is stored in a database on the server. Specific hardware used to collect data includes IoT sensors and sensors built into the robots.

[1004] Step 2:

[1005] The server runs a natural language processing (NLP) algorithm on the collected data. The NLP algorithm extracts keywords related to the skills and experience of employees and robots. This process uses NLP libraries (Spacy and NLTK) and machine learning models (Scikit-learn and TensorFlow). The input is the collected raw data, and the output is a list of keywords as a result of the analysis.

[1006] Step 3:

[1007] The server generates and stores profile data for employees and robots based on the extracted keywords. The profile data includes detailed information such as skill sets, experience, desired positions and tasks. This profile data is stored in a database using MySQL or PostgreSQL. The input is the analysis result from step 2, and the output is the stored profile data.

[1008] Step 4:

[1009] The server runs a matching algorithm to match employee and robot profile data with the company's needs. The matching takes into account the company's open positions, project requirements, and factory tasks. The algorithm uses a segmented matching algorithm or a genetic algorithm. The input is the profile data and the company's needs data, and the output is an optimal placement plan.

[1010] Step 5:

[1011] The terminal presents the generated placement plan to employees or robots and receives feedback. An example of feedback is a specific response such as, "This position is interesting, but I would prefer a role that allows me to demonstrate a bit more leadership." The input is the placement plan generated by the server, and the output is feedback from the user or robot.

[1012] Step 6:

[1013] The server reevaluates the system based on the received feedback and generates a relocation plan. A machine learning model (reinforcement learning model) that continuously learns is used for the reevaluation. This method optimizes the relocation plan based on the feedback. The input is the feedback from the user or robot, and the output is the regenerated optimal relocation plan.

[1014] Specific examples

[1015] For example, suppose you input skill data about factory robot A. Based on past data, robot A is good at "welding work," and feedback from robot A indicates that it would be better suited to a role that allows it to take on more leadership roles.

[1016] The server will then use this information to propose the optimal welding leader position and generate an optimized placement plan through re-evaluation. Specific examples of prompts are as follows:

[1017] Example prompt sentence:

[1018] "Please enter the skill data for Robot A in your factory. Example: Robot A has excellent welding skills and is fast at work. He also desires a leadership role."

[1019] 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.

[1020] A specific embodiment for realizing the system of the present invention will be described. In this system, three parties - a server, a terminal, and a user - each play their respective roles and work together to optimally allocate employees. Furthermore, by combining this with an emotion engine, it becomes possible to propose more effective allocations that take into account the user's emotions.

[1021] Server Processing

[1022] 1. Data Collection

[1023] The server receives the input data of the user (employee) sent from the terminal, including skills, experience, desired position, and conversation content. This data is stored in a database within the server.

[1024] 2. Data Analysis

[1025] The server runs a natural language processing (NLP) algorithm on the collected data to analyze it. Through the analysis, keywords such as employee skills, experience, and aspirations are extracted. Employee profile data is generated using the extracted data.

[1026] 3. Emotion analysis

[1027] The server uses an emotion engine to analyze the user's emotional state from the content of the conversation, for example, to detect whether the user is feeling stressed or excited during the conversation.

[1028] 4. Profile Management

[1029] The resulting profile data is stored as structured data containing the employee's detailed skill set, experience, desired position, and emotional state, providing an at-a-glance view of the employee's capabilities.

[1030] 5. Proposal for optimal layout

[1031] The server runs a matching algorithm that matches employee profile data with the company's current needs (open positions and project requirements). The algorithm matches the employee's skills with the company's needs and emotional state to generate optimal placement recommendations.

[1032] 6. Reassess and optimize

[1033] The server receives feedback from employees and re-evaluates them based on this. Using a continuously learning machine learning model, it generates reassignment plans based on the feedback. The results of sentiment analysis by the emotion engine are also taken into account.

[1034] Terminal handling

[1035] 1. Providing a conversational interface

[1036] The terminal provides the user (employee) with an interactive interface through which the user can input their skills, experience, desired position, and interaction content.

[1037] 2. Data transmission

[1038] The terminal transmits information entered by the user and the contents of the dialogue to the server in real time, allowing the server to receive the necessary data immediately.

[1039] 3. Displaying the results

[1040] The device displays the profile data and optimal placement proposals received from the server to the user, who can then review the proposals and provide feedback.

[1041] User Action

[1042] 1. Inputting information and interacting

[1043] The user uses the interactive interface of the terminal to input their skills, experience, desired position, and the content of the conversation. This information is sent from the terminal to the server, and the emotional state during the conversation is analyzed by the emotion engine.

[1044] 2. Providing Feedback

[1045] The user inputs feedback on the placement proposal from the server, for example, "This position is interesting, but I would also like to demonstrate leadership."

[1046] Specific examples

[1047] For example, if an employee enters, "I have five years of software development experience, and I'm particularly good at Python and Java," and then during the conversation says, "I'd like to try new technologies, but I'm a little nervous," the device sends this information to the server. The server uses natural language processing to analyze the employee's skills and experience, and further detects the emotion of nervousness using an emotion engine. It then generates profile data. The server then matches this profile data with the company's needs and generates an optimal placement proposal. For example, it might suggest, "A software engineer position on a new AI project would be suitable." The device displays this proposal to the user, who then provides feedback, saying, "I'd also like to demonstrate leadership." Through reevaluation, the server again proposes the "leadership position on a new AI project."

[1048] By utilizing the emotion engine, more optimal personnel placement can be achieved that takes into account the emotional state of employees, thereby improving productivity and efficiency across the entire company.

[1049] The processing flow will be explained below.

[1050] Step 1: The user initiates the interaction

[1051] Users access an interactive interface on their device and enter their skills, experience, and desired position, for example, "I have five years of software development experience, and I am particularly skilled in Python and Java."

[1052] Step 2: The device sends user input to the server

[1053] The device sends the information entered by the user to the server in real time, using API requests to transfer this data to the server.

[1054] Step 3: The device collects emotion data

[1055] The device analyzes the user's tone of voice and facial expressions during the conversation to collect emotional data, using audio recordings and cameras.

[1056] Step 4: The device sends the emotion data to the server.

[1057] The device transmits the collected emotional data to the server, which allows the server to recognize the emotional state.

[1058] Step 5: The server receives and stores the data

[1059] The server receives the user's input data and emotion data sent from the terminal and stores them in a database, including skills, experience, desired position, and emotion data.

[1060] Step 6: The server performs the data analysis

[1061] The server analyzes the stored data using natural language processing (NLP) algorithms, extracting keywords such as skills, experience, and aspirations, and converting them into structured data.

[1062] Step 7: The server performs sentiment analysis

[1063] The server uses an emotion engine to analyze the user's emotional state during the conversation, for example, to detect whether the user is feeling stressed or excited during the conversation.

[1064] Step 8: Server generates profile data

[1065] The server generates user profile data based on the extracted keywords and the results of sentiment analysis, which includes the user's skill set, experience, desired position, and emotional state.

[1066] Step 9: The server saves the profile data

[1067] The server stores the generated profile data in a database, which allows detailed employee information to be managed.

[1068] Step 10: The server captures the needs of the enterprise

[1069] The server retrieves data from a database about the company's current needs and open positions, including the skill requirements and responsibilities for each position.

[1070] Step 11: The server generates the optimal placement plan

[1071] The server runs a matching algorithm to match users' profile data with the company's needs, and generates optimal staffing recommendations based on skill matching and role compatibility.

[1072] Step 12: The server sends the placement plan to the device.

[1073] The server sends the generated placement plan to the terminal, allowing the user to check the proposed content.

[1074] Step 13: The device displays the layout plan to the user.

[1075] The device displays the placement proposal received from the server to the user, specifically displaying details of the placement proposal (e.g., a software engineer position for a new AI project).

[1076] Step 14: Users provide feedback

[1077] The user can then provide feedback on the proposed placement, such as, "This position is interesting, but I would also like to demonstrate leadership."

[1078] Step 15: Device sends feedback to server

[1079] The device receives the user's feedback and sends it to the server. The device forwards the feedback to the server using an API request.

[1080] Step 16: Server performs re-evaluation

[1081] The server reevaluates the system based on user feedback and uses a continuously learning machine learning model to generate optimal relocation plans based on the feedback.

[1082] Step 17: The server sends the reevaluation result to the terminal.

[1083] The server transmits the re-evaluation results to the terminal, and the regenerated placement plan is transferred to the terminal.

[1084] Step 18: The terminal displays the reevaluation results to the user

[1085] The device displays the reevaluation results received from the server to the user, for example, "You are recommended for a leadership position in a new AI project."

[1086] Through these steps, the system of the present invention can realize optimal personnel allocation based on employees' characteristics and preferences, improving the productivity and efficiency of the entire company. By utilizing the emotion engine, it is possible to propose more optimal personnel allocation that takes into account the emotional state of employees.

[1087] Example 2

[1088] 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."

[1089] When it comes to optimal personnel placement that takes into account employees' skills, experience, and desired positions, traditional profile analysis and matching algorithms alone have limitations, making it difficult to properly incorporate employees' emotional states and feedback. Furthermore, the reevaluation and reassignment process can be inefficient, negatively impacting employee satisfaction and corporate productivity. There is a need to solve these issues and provide a more effective and flexible personnel placement system.

[1090] The specific processing by the specific processing unit 290 of the data processing device 12 in the second embodiment is realized by the following means.

[1091] In this invention, the server includes an interactive interface providing means for inputting employee skills, experience, and desired positions, a natural language processing algorithm processing means for collecting and analyzing the content of employee dialogue, a profile management means for generating and saving employee profile data based on the analysis results, an emotion analysis means for analyzing the emotional state of employees from the content of dialogue, a matching algorithm processing means for matching the profile data with the needs of the company and generating an optimal personnel placement plan, a means for presenting the generated placement plan to employees and receiving feedback, and an optimization means for reevaluating based on the feedback and generating a reallocation plan. This makes it possible to generate flexible and effective placement plans that take into account the emotional state of employees, thereby improving employee satisfaction and corporate productivity.

[1092] An "interactive interface" is a user interface that allows employees to input information such as their skills, experience, and desired position.

[1093] A "natural language processing algorithm" is an algorithm that analyzes the content of employee conversations and extracts necessary information and keywords.

[1094] "Profile Data" is structured data that includes an employee's skills, experience, desired position, and other relevant information.

[1095] The "profile management means" is a means for saving and managing the generated profile data.

[1096] The "emotion analysis means" is a means for analyzing and detecting the emotional state of an employee from the content of their conversation.

[1097] The "matching algorithm" is an algorithm that matches profile data with the needs of the company and generates optimal personnel placement plans.

[1098] The "optimization means" is a means for reassessing employees based on their feedback and generating reassignment plans.

[1099] "Feedback" refers to the opinions and thoughts employees provide about proposed placements.

[1100] "Placement proposals" are suggestions for optimal personnel placement generated based on employee profile data and the company's needs.

[1101] The system of the present invention is designed to generate optimal personnel allocation plans that take into account employees' skills, experience, desired positions, and also their emotional state. This system operates in cooperation with three parties: a server, a terminal, and a user.

[1102] Server Processing

[1103] The server first receives the employee's input data sent from the terminal. This data includes the employee's skills, experience, desired position, and conversation content. The received data is then stored in a database. Specifically, a database management system such as MySQL or PostgreSQL can be used.

[1104] The server then runs natural language processing (NLP) algorithms on the stored data, using libraries like Python's NLTK and SpaCy, to analyze the data and extract keywords related to the employee's skills, experience, and aspirations.

[1105] Furthermore, the server uses an emotion engine to analyze the user's emotional state from the dialogue. For example, by using the Google Cloud Natural Language API, it can detect emotions such as stress or excitement felt by the user.

[1106] The generated profile data is stored as structured data that includes the employee's detailed skill set, experience, desired position, and emotional state.

[1107] The server then runs a matching algorithm that matches employee profile data with the company's needs using machine learning models such as Google Cloud AutoML and TensorFlow, generating optimal placement recommendations that match the employee's skills with the company's needs and emotional state.

[1108] The server receives feedback from users and reevaluates it using a machine learning model that continuously learns. This generates a relocation plan based on the feedback, taking into account the results of emotion analysis by the emotion engine.

[1109] Terminal handling

[1110] The terminal provides the user (employee) with an interactive interface through which the user can input their skills, experience, desired position, and interaction content.

[1111] The terminal transmits information entered by the user and the contents of the dialogue to the server in real time, allowing the server to receive the necessary data immediately.

[1112] The device also displays the profile data and optimal placement proposals received from the server to the user, who can then review the proposals and provide feedback.

[1113] User Action

[1114] The user uses the interactive interface of the terminal to input their skills, experience, desired position, and the content of the conversation. This information is sent from the terminal to the server, and the emotional state during the conversation is analyzed by the emotion engine.

[1115] Furthermore, users can input feedback on the placement proposals from the server, for example, "This position is interesting, but I would also like to demonstrate leadership skills."

[1116] Specific examples

[1117] As a specific example, if an employee types, "I have five years of software development experience and am particularly good at Python and Java," and then during the conversation says, "I would like to try new technologies, but I'm a little nervous," the device will send this information to the server.

[1118] The server analyzes the employee's skills and experience through natural language processing and detects anxiety using an emotion engine. It then generates profile data. The server matches this profile data with the company's needs and generates optimal placement recommendations. For example, it might suggest, "A software engineer position for a new AI project would be suitable."

[1119] The terminal displays the proposal to the user, who then provides feedback, saying, "I would also like to demonstrate leadership." Through reevaluation, the server can re-propose the "leadership position for a new AI project."

[1120] Prompt Sentence Examples

[1121] Below are some examples of specific prompt sentences to input into the generative AI model.

[1122] Prompt: I have 5 years of software development experience, particularly in Python and Java. I'd like to try new technologies but am a bit nervous. Please suggest a suitable position for me.

[1123] In this way, taking into account the emotional state of employees can lead to more effective and flexible staffing, improving productivity and efficiency across the company.

[1124] The flow of the identification process in the second embodiment will be described with reference to FIG.

[1125] Step 1: Data collection

[1126] The server receives user (employee) input data sent from the terminal. The input data includes the user's skills, experience, desired position, and dialogue content. This data is stored in a database (such as MySQL or PostgreSQL) on the server. For example, if a user enters "I have five years of software development experience, and I am particularly good at Python and Java," the terminal sends this information to the server, which stores it in a "user data" table.

[1127] Step 2: Data analysis

[1128] The server runs natural language processing (NLP) algorithms on the stored data to analyze it. Specifically, it uses Python's NLTK and SpaCy libraries to extract keywords related to the user's skills, experience, and desired position. For example, from an input such as "I have five years of software development experience, and I am particularly good at Python and Java," it extracts keywords such as "software development," "Python," and "Java."

[1129] Step 3: Sentiment Analysis

[1130] The server uses an emotion engine to analyze the user's emotional state from the dialogue content. Based on the input dialogue content, the emotion engine (e.g., Google Cloud Natural Language API) detects emotions such as "anxiety," "excitement," and "stress." For example, if a user inputs "I want to try a new technology, but I'm a little anxious," the emotion engine will detect the emotion "anxiety."

[1131] Step 4: Profile Management

[1132] The server generates employee profile data based on the extracted data and the results of sentiment analysis and stores it in a database. The generated profile data includes the employee's skill set, experience, desired position, and emotional state. For example, data such as "software development," "Python," "Java," and "anxiety" are stored in the "Employee Profile" table.

[1133] Step 5: Propose optimal layout

[1134] The server runs a matching algorithm that matches employee profile data with the company's needs. Using Google Cloud AutoML and TensorFlow, it generates optimal staffing recommendations based on the profile data and company needs. Using data on "software development," "Python," "Java," and "anxiety" as input, it compares these with the company's requirements for a "new AI project" and proposes a "software engineer position for a new AI project."

[1135] Step 6: Viewing results and feedback

[1136] The terminal displays the placement proposal received from the server to the user. The user checks the placement proposal and inputs feedback through an interactive interface. For example, if the user provides an opinion such as "This position is interesting, but I also want to demonstrate leadership," the terminal sends this feedback to the server.

[1137] Step 7: Reassess and optimize

[1138] The server receives feedback from users and reevaluates them using a continuously learning machine learning model. Based on the feedback and sentiment analysis results, it generates new reassignment proposals. For example, it may re-propose a "leadership position for a new AI project." This process can improve employee satisfaction and company productivity.

[1139] Prompt sentences with examples

[1140] Below are some examples of specific prompt sentences to input into the generative AI model.

[1141] Prompt: I have 5 years of software development experience, particularly in Python and Java. I'd like to try new technologies but am a bit nervous. Please suggest a suitable position for me.

[1142] (Application example 2)

[1143] 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."

[1144] Conventional systems that optimize the allocation of employee skills and experience do not take into account the emotional state of employees, resulting in a high risk of poor performance after allocation or employee turnover due to dissatisfaction. Furthermore, there was a lack of a system that could simultaneously analyze employee dialogue and emotions and quickly propose optimal allocations, so these issues need to be addressed.

[1145] The specific processing by the specific processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means. In this invention, the server includes an interactive interface providing means for inputting employee skills, experience, and desired positions, a natural language processing algorithm processing means for collecting and analyzing the content of employee dialogue, and a profile management means for generating and saving employee profile data based on the analysis results. This makes it possible to generate optimal placement plans that also take into account the emotional state of employees.

[1146] The "interactive interface providing means" is a means for providing an interactive interface for employees to input their skills, experience, and desired position.

[1147] The "natural language processing algorithm processing means" is a means that uses a natural language processing algorithm to collect and analyze the content of employee dialogue.

[1148] The "profile management means" is a means for generating and storing employee profile data based on the analysis results.

[1149] The "matching algorithm processing means" is a means that uses an algorithm to match profile data with the needs of the company and generate an optimal personnel allocation plan.

[1150] The "feedback receiving means" is a means for presenting the generated placement plan to employees and receiving their feedback.

[1151] The "re-evaluation means" is a means for performing a re-evaluation based on the feedback and generating a re-placement plan.

[1152] The "emotion analysis means" is a means for analyzing the emotional state of an employee from the content of their conversation.

[1153] "Means for adopting machine learning models" refers to means for adopting machine learning models that continuously learn based on employee feedback.

[1154] In the system for realizing the application example of the present invention, a server, a terminal, and a user work together. The following is a detailed description of how the system is implemented.

[1155] Server Processing

[1156] The server receives data sent from a terminal having an interactive interface supply means for inputting the employee's skills, experience, and desired position. The server analyzes the content of the dialogue using a natural language processing algorithm processing means, and generates and saves the analysis results as employee profile data using a profile management means.

[1157] The server analyzes the content of the employee's conversation using an emotion analysis means and also digitizes the employee's emotional state. It then compares the profile data with the company's needs and generates an optimal personnel placement plan using a matching algorithm processing means. The generated placement plan is then presented to the employee via their terminal, and the feedback from the employee is received using a feedback receiving means. A reevaluation means reevaluates the employee based on the feedback and generates a relocation plan. At this time, a machine learning model adoption means that continuously learns based on employee feedback is used to constantly update the optimal placement plan.

[1158] Terminal handling

[1159] The terminal provides a dialogue interface for users (employees) to input their skills, experience, and desired position. This information is sent to the server in real time. The dialogue is converted into text using voice recognition technology and sent to the server.

[1160] User Action

[1161] Users (employees) use the interactive interface on their terminals to input their skills, experience, desired position, and the content of their conversations. The input data is sent to the server, and their emotional state is analyzed using emotion analysis means. By providing feedback on the proposed placement plan, even more accurate placement plans can be regenerated.

[1162] Hardware and software used

[1163] The server uses the "TextBlob" library for natural language processing, the "NLTK" library for sentiment analysis, and the "scikit-learn" clustering algorithm. The device uses the "speech_recognition" library for speech recognition, converting user voice input into text data.

[1164] Specific examples

[1165] For example, if an employee says, "I'd like to help install a new logistics system, but I'm a little worried about the technology," the system can analyze the employee's concerns about the new technology and suggest an appropriate support system.

[1166] Example prompts to be input to the generative AI model

[1167] "Employees have expressed anxiety about new technology. What kind of assistance system should we suggest to employees who feel the same way?"

[1168] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[1169] Program processing flow

[1170] Step 1: Collecting user (employee) input data

[1171] The terminal provides an interactive interface for users to input their skills, experience, and desired position. The user inputs their skills, experience, desired position, and dialogue content through the interface. The terminal uses voice recognition technology to convert the user's voice input into text data. The generated text data is sent to the server in real time.

[1172] Input: User (employee) voice input

[1173] Data processing: Converting speech into text using voice recognition technology

[1174] Output: Text data

[1175] Step 2: Employee data analysis

[1176] The server receives the employee's conversation content sent from the terminal. Using a natural language processing algorithm, it extracts and analyzes information such as skills, experience, and desired position from the employee's conversation content. Based on this data, it generates employee profile data and stores it in a database.

[1177] Input: Text data

[1178] Data processing: Extraction and analysis of keywords using natural language processing algorithms

[1179] Output: Profile data

[1180] Step 3: Sentiment Analysis

[1181] The server uses emotion analysis means to analyze the employee's emotional state (e.g., stress, anxiety, excitement) based on the content of the employee's dialogue. The results of the emotion analysis are added to the profile data.

[1182] Input: Text data of the dialogue

[1183] Data processing: Emotion analysis algorithm analyzes emotional state

[1184] Output: Emotional state data

[1185] Step 4: Propose optimal layout

[1186] The server uses a matching algorithm processing means to match the generated profile data with the needs of the company, and generates an optimal personnel allocation plan by taking into account the employee's skills, experience, and emotional state. The allocation plan is presented to the employee via the terminal.

[1187] Input: Profile data, company needs

[1188] Data processing: Generate placement plans using a matching algorithm

[1189] Output: Optimal layout plan

[1190] Step 5: Receiving feedback

[1191] The terminal presents the generated placement plan to the employee, who then inputs feedback on the placement plan. The input feedback is sent to the server in real time.

[1192] Input: Optimal layout plan

[1193] Data processing: Employee feedback input

[1194] Output: Feedback data

[1195] Step 6: Reassess and optimize

[1196] The server performs re-evaluation based on the feedback received from employees. Using the re-evaluation method and the machine learning model adoption method, it generates a re-allocation plan that takes the feedback data into consideration. This enables optimal personnel allocation that takes into account the feedback and emotional state of employees.

[1197] Input: Feedback data

[1198] Data Transformation: Continuously train and reassess machine learning models

[1199] Output: Relocation proposal

[1200] Examples and prompts

[1201] For example, if an employee says, "I'd like to help install a new logistics system, but I'm a little worried about the technology," the system can analyze the employee's concerns about the new technology and suggest an appropriate support system.

[1202] Example prompts to input to a generative AI model:

[1203] "Employees have expressed anxiety about new technology. What kind of assistance system should we suggest to employees who feel the same way?"

[1204] 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.

[1205] 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.

[1206] 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.

[1207] [Fourth embodiment]

[1208] FIG. 7 shows an example of the configuration of a data processing system 410 according to the fourth embodiment.

[1209] 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.

[1210] 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).

[1211] 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.

[1212] 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.

[1213] 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).

[1214] 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.

[1215] 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.

[1216] 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.

[1217] 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.

[1218] 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.

[1219] 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.

[1220] 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."

[1221] A specific embodiment for realizing the system of the present invention will be described. In this system, three parties, a server, a terminal, and a user, each play their respective roles and work together to optimally allocate employees.

[1222] Server Processing

[1223] 1. Data Collection

[1224] The server receives the user (employee) input data sent from the terminal, including skills, experience, desired position, etc. This data is stored in a database within the server.

[1225] 2. Data Analysis

[1226] The server runs a natural language processing (NLP) algorithm on the collected data to analyze it. Through the analysis, keywords such as employee skills, experience, and aspirations are extracted. Employee profile data is generated using the extracted data.

[1227] 3. Profile Management

[1228] The generated profile data is stored as structured data containing the employee's detailed skill set and desired position, allowing employees to see their capabilities at a glance.

[1229] 4. Proposal for optimal layout

[1230] The server runs a matching algorithm that matches employee profile data with the company's current needs (open positions and project requirements). The algorithm matches employee skills with the company's needs and generates optimal placement proposals.

[1231] 5. Reassess and optimize

[1232] The server receives feedback from employees and re-evaluates them based on this feedback. The re-evaluation uses a continuously learning machine learning model to regenerate placement proposals based on the feedback.

[1233] Terminal handling

[1234] 1. Providing a conversational interface

[1235] The terminal provides the user (employee) with an interactive interface through which the user can input information such as skills, experience, and desired position.

[1236] 2. Data transmission

[1237] The terminal transmits the information input by the user to the server in real time, allowing the server to receive the necessary data immediately.

[1238] 3. Displaying the results

[1239] The device displays the profile data and optimal placement proposals received from the server to the user, who can then review the placement proposals and provide feedback.

[1240] User Action

[1241] 1. Enter your information

[1242] The user uses the interactive interface of the terminal to input information such as his / her skills, experience, desired position, etc. This information is then sent from the terminal to the server.

[1243] 2. Providing Feedback

[1244] Users can input feedback on the placement proposals from the server, such as, "This position is interesting, but I would prefer a role that allows for more leadership."

[1245] Specific examples

[1246] For example, if an employee enters, "I have five years of software development experience, and I'm particularly good at Python and Java," the device sends this information to the server. The server uses natural language processing to analyze the employee's skills and experience and generate profile data. The server then matches this profile data with the company's needs and generates an optimal placement proposal. For example, it might suggest, "A software engineer position on a new AI project would be suitable." The device displays this proposal to the user, who then provides feedback, saying, "I'd also like to demonstrate leadership skills." Through reevaluation, the server again proposes the "leadership position on a new AI project."

[1247] As a result, the system of the present invention can realize optimal personnel allocation based on the characteristics and desires of each employee, thereby improving the productivity and efficiency of the entire company.

[1248] The processing flow will be explained below.

[1249] Step 1: The user initiates the interaction

[1250] Users access an interactive interface on their device and enter their skills, experience, and desired position, for example, "I have five years of software development experience, and I am particularly skilled in Python and Java."

[1251] Step 2: The device sends user input to the server

[1252] The device sends the information entered by the user to the server in real time, using API requests to transfer this data to the server.

[1253] Step 3: The server receives and stores the data

[1254] The server receives the user's input data sent from the terminal and stores it in a database, including skills, experience, desired position, etc.

[1255] Step 4: The server performs the data analysis

[1256] The server analyzes the stored data using natural language processing (NLP) algorithms, extracting keywords such as skills, experience, and aspirations, and converting them into structured data.

[1257] Step 5: The server generates the profile data

[1258] The server generates user profile data based on the extracted keywords, which includes the user's skill set, experience, and desired position.

[1259] Step 6: The server saves the profile data

[1260] The server stores the generated profile data in a database, which allows detailed employee information to be managed.

[1261] Step 7: The server gets the company's needs

[1262] The server retrieves data from a database about the company's current needs and open positions, including the skill requirements and responsibilities for each position.

[1263] Step 8: The server generates the optimal placement plan

[1264] The server runs a matching algorithm to match users' profile data with the company's needs, and generates optimal staffing recommendations based on skill matching and role compatibility.

[1265] Step 9: The server sends the placement plan to the device.

[1266] The server sends the generated placement plan to the terminal, allowing the user to check the proposed content.

[1267] Step 10: The device displays the layout plan to the user.

[1268] The terminal displays the placement proposal received from the server to the user, specifically displaying details of the placement proposal (e.g., a software engineer position for a new project).

[1269] Step 11: Users provide feedback

[1270] The user can then provide feedback on the proposed placement, such as, "This position is interesting, but I would also like to demonstrate leadership."

[1271] Step 12: Device sends feedback to server

[1272] The device receives the user's feedback and sends it to the server. The device forwards the feedback to the server using an API request.

[1273] Step 13: Server performs re-evaluation

[1274] The server reevaluates the system based on user feedback and uses a machine learning model to generate optimal relocation plans.

[1275] Step 14: The server sends the reevaluation result to the terminal.

[1276] The server transmits the re-evaluation results to the terminal, and the regenerated placement plan is transferred to the terminal.

[1277] Step 15: The terminal displays the reevaluation results to the user

[1278] The device displays the reevaluation results received from the server to the user, for example, "You are recommended for a leadership position in a new AI project."

[1279] Through these steps, the system of the present invention can realize optimal personnel allocation based on the characteristics and desires of employees, thereby improving productivity and efficiency across the entire company.

[1280] Example 1

[1281] 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."

[1282] Modern companies are required to assign personnel to positions that optimally reflect the characteristics and preferences of their employees. However, it is difficult to effectively collect and analyze employee skills, experience, and desired positions, and to assign personnel to positions that optimally meet the company's needs. Another challenge is collecting feedback from employees in real time and reevaluating and optimizing assignment plans based on that feedback.

[1283] 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.

[1284] In this invention, the server includes: an interactive interface providing means for inputting employee skills, experience, and desired positions; a natural language processing algorithm processing means for collecting and analyzing the content of the employee's dialogue; a profile management means for generating and saving employee profile data based on the analysis results; a matching algorithm processing means for matching the profile data with the company's needs and generating optimal personnel placement plans; a means for presenting the generated placement plans to employees and receiving feedback; an optimization means for reevaluating based on the feedback and generating reallocation plans; a data transmission means for transmitting information input by employees using the interface to the server; a means for the server to store the employee's input data in a database; and a means for the server to optimize the placement plans using a machine learning model. This enables companies to achieve optimal personnel placement based on the characteristics and preferences of their employees, thereby improving the productivity and efficiency of the entire company.

[1285] The "interactive interface providing means" is a means for providing an interface for employees to input their skills, experience, and desired position.

[1286] The "natural language processing algorithm processing means" is a means for executing an algorithm used to collect and analyze the content of employee dialogue.

[1287] The "profile management means" is a means for generating and storing employee profile data based on the analyzed data.

[1288] The "matching algorithm processing means" is a means for executing an algorithm that matches employee profile data with the needs of the company and generates optimal personnel allocation plans.

[1289] The "means for receiving feedback" is a means for presenting the generated placement plan to employees and receiving opinions and evaluations from the employees.

[1290] The "optimization method" is a method for reevaluating employees based on their feedback and generating a reassignment plan.

[1291] The "data transmission means" is a means for transmitting information entered by an employee using an interface to a server.

[1292] The "means for saving to a database" is the means by which the server saves the employee's input data to a database.

[1293] "Means for optimizing placement plans using machine learning models" refers to means for optimizing placement plans based on feedback from employees using machine learning models.

[1294] A specific embodiment for carrying out the present invention will be described below. In the system for carrying out the present invention, a server, a terminal, and a user each play their respective roles and work together to achieve optimal staffing.

[1295] Server Processing

[1296] The server first receives the user (employee) input data sent from the terminal. This data includes skills, experience, desired position, etc., and the server stores this in a database. The software used is a database management system (e.g., MySQL, PostgreSQL).

[1297] The server then runs a natural language processing (NLP) algorithm on the received data to analyze it. Specifically, it uses a Python NLP library (e.g., NLTK, SpaCy) to extract keywords such as employee skills, experience, and aspirations. The extracted data is used to generate employee profile data and store it in a database.

[1298] The server then runs a matching algorithm to match the generated profile data with the company's current needs (open positions and project requirements), using machine learning models (e.g., Scikit-learn classifiers), to match employee skills with the company's needs and generate optimal placement proposals.

[1299] The server also receives feedback from employees and uses machine learning models to reevaluate and optimize placement proposals, including a continuous learning process to incorporate feedback.

[1300] Terminal handling

[1301] The terminal provides the user (employee) with an interactive interface, which can be implemented, for example, as a web-based application (e.g., React or Angular), where the user can enter information such as skills, experience, and desired position.

[1302] The terminal transmits the information input by the user to the server in real time. The transmission process uses HTTP requests. Furthermore, a GUI is provided to display the profile data received from the server and the optimal placement plan to the user, allowing the user to easily input feedback.

[1303] User Action

[1304] The user uses the interactive interface of the terminal to input information such as his / her skills, experience, desired position, etc. This information is sent to the server via the terminal.

[1305] The user then reviews the placement proposals presented by the server and provides feedback if necessary. This feedback is then sent back to the server via the terminal and used to reevaluate and optimize the optimal placement proposal.

[1306] Specific examples

[1307] For example, an employee might enter, "I have five years of software development experience, and I'm particularly good at Python and Java." The device sends this information to the server using an HTTP request. The server uses NLTK for natural language processing to analyze the employee's skills and experience. The analyzed data is then saved as profile data and matched with the company's needs using a Scikit-learn classifier. As a result, a placement suggestion is generated: "A software engineer position on a new AI project would be suitable for you." This placement suggestion is displayed to the user via the device, and if the user adds feedback such as "I would also like to demonstrate leadership skills," it is sent back to the server. The server then reevaluates this feedback and proposes a new "leadership position on a new AI project."

[1308] This system allows companies to realize optimal allocation based on the characteristics and wishes of their employees, improving overall productivity and efficiency. By implementing this system, companies can maximize the potential of their human resources and achieve greater efficiency and improvement in their work.

[1309] The flow of the identification process in the first embodiment will be described with reference to FIG.

[1310] Step 1:

[1311] Entering and sending information (device operation)

[1312] Users input their skills, experience, and desired position through the device's interactive interface. Input information might include, "I have five years of software development experience, and I'm particularly good at Python and Java." The device receives this input information and sends it to the server using an HTTP request.

[1313] Input: User input data on skills, experience, and desired position

[1314] Output: Data sent in the form of an HTTP request

[1315] Specific operation: The user enters data into the input form and clicks the "Submit" button, which sends the data to the server.

[1316] Step 2:

[1317] Receiving and storing data (server operation)

[1318] The server receives the user's input data sent from the terminal and stores it in a database. The database management system used in this case may be MySQL or PostgreSQL.

[1319] Input: User input data sent from the terminal (HTTP request)

[1320] Output: Data stored in the database

[1321] What happens: The server parses the HTTP request and writes the information to a database.

[1322] Step 3:

[1323] Data analysis using natural language processing (server operation)

[1324] The server retrieves the user input data from the database and analyzes it using natural language processing (NLP) algorithms, specifically using Python NLP libraries (e.g., NLTK and SpaCy) to extract keywords related to employee skills, experience, and preferences.

[1325] Input: User-entered data stored in a database

[1326] Output: Parsed keywords and skill sets

[1327] Specific operation: The server runs an NLP algorithm to extract key keywords from the text data.

[1328] Step 4:

[1329] Generating and saving profile data (server operation)

[1330] The server generates employee profile data based on the data analyzed by NLP, which is then stored in a database as structured data including detailed skill sets and desired positions.

[1331] Input: Parsed keywords and skill sets

[1332] Output: Structured profile data

[1333] Specific operation: The server stores the generated profile data in a database.

[1334] Step 5:

[1335] Generating optimal placement plans (server operation)

[1336] The server runs a matching algorithm that matches employee profile data with the company's current needs (open positions and project requirements), using Scikit-learn classifiers. This process generates optimal staffing recommendations.

[1337] Input: Profile data, company needs

[1338] Output: Optimal staffing plan

[1339] Specific operation: The server executes a matching algorithm and generates placement proposals.

[1340] Step 6:

[1341] Presenting placement plans and receiving feedback (collaboration between terminals and servers)

[1342] The server sends the generated optimal placement plan to the terminal, which displays the placement plan to the user, who then inputs feedback on it. The terminal then sends the user's feedback back to the server.

[1343] Input: Optimal staffing plan, user feedback

[1344] Output: Received feedback

[1345] Specific operation: The server sends the placement plan to the terminal, which displays the placement plan in a GUI. The user enters feedback, and the terminal sends this information to the server.

[1346] Step 7:

[1347] Re-evaluation based on feedback and regeneration of optimal placement plan (server operation)

[1348] The server receives user feedback, re-evaluates it using machine learning models, and generates optimized relocation proposals. This process involves continuous training of the machine learning models.

[1349] Input: User feedback

[1350] Output: Optimized relocation plan

[1351] What it does: The server runs a machine learning algorithm and generates new placement suggestions based on the feedback.

[1352] Through this series of steps, the system can achieve optimal personnel allocation based on employees' characteristics and preferences, improving productivity and efficiency across the company.

[1353] (Application example 1)

[1354] 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."

[1355] Conventional employee allocation systems can sometimes struggle to optimally allocate employees based on their skills, experience, and desired positions. It's also difficult to collect real-time operational status and performance data for factory robots and optimally allocate tasks based on that data. In particular, there's a lack of reevaluation and optimization based on feedback, preventing efficiency improvements over the long term. Therefore, there's a need for a system that can efficiently allocate and manage tasks for employees and factory robots.

[1356] 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.

[1357] In this invention, the server includes: an interactive interface providing means for inputting employee skills, experience, and desired position; a natural language processing algorithm processing means for collecting and analyzing the content of the employee's dialogue; a profile management means for generating and saving employee profile data based on the analysis results; a matching algorithm processing means for matching the profile data with the company's needs and generating an optimal personnel allocation plan; a means for presenting the generated allocation plan to employees and receiving feedback; an optimization means for reevaluating based on the feedback and generating a reallocation plan; a data collection means for collecting factory robot operation status and performance data and sending it to the cloud server; a data analysis means for analyzing the collected data using a natural language processing algorithm and generating a robot skill profile; a profile management means for saving and managing the skill profile data generated based on the analysis results; a matching algorithm processing means for generating an optimal task allocation plan; and a reevaluation and optimization means for reevaluating based on feedback from the robot and generating an optimized allocation plan. This enables dynamic and efficient allocation and task management for both employees and factory robots.

[1358] The "interactive interface providing means" is a means for providing an interface for a user to input information such as skills, experience, and desired position.

[1359] "Natural language processing algorithm processing means" refers to a means that uses natural language processing technology to analyze the collected dialogue content and extract important keywords such as skills and experience.

[1360] The "profile management means" is a means for saving and managing the profile data of employees or robots generated based on the analysis results.

[1361] The "matching algorithm processing means" is a means for matching the generated profile data with the needs of the company or factory and using an algorithm to generate an optimal allocation plan or task allocation plan.

[1362] The "feedback means" is a means for presenting the generated placement plans and task placement plans to the user or robot and receiving their reactions and opinions.

[1363] The "optimization means" is a means for reevaluating based on feedback from users and robots and generating an even more optimal placement plan.

[1364] The "data collection means" is a means for collecting the operating status and performance data of factory robots in real time and sending it to a cloud server.

[1365] The "data analysis means" is a means for analyzing collected performance data and generating a skill profile of the robot.

[1366] The "reevaluation and optimization method" is a method for reevaluating the analysis algorithm constructed based on the robot's feedback and generating an optimal task allocation plan.

[1367] A "skill profile" is structured data that contains detailed information about the skills, abilities, and experience of employees and robots.

[1368] A specific embodiment for realizing the system of the present invention will be described. This system optimizes the allocation of employees and factory robots, with the server, terminals, and users each playing their respective roles and working together to optimally allocate personnel and tasks.

[1369] Server Processing

[1370] 1. Data Collection Methods

[1371] The server receives employee input data (skills, experience, desired position, etc.) sent from the terminal, and also collects the operating status and performance data of the factory robots. This data is stored on the server.

[1372] 2. Data analysis methods

[1373] The server runs a natural language processing (NLP) algorithm on the collected data to analyze it. This analysis extracts keywords related to the skills, experience, and preferences of employees and robots. Specific software used is an NLP library (Spacy or NLTK) or a machine learning model (Scikit-learn or TensorFlow).

[1374] 3. Profile Management Methods

[1375] The generated profile data is stored as structured data that includes detailed skill sets and preferences of employees and robots, making it possible to see their skills and preferences at a glance. The database uses MySQL or PostgreSQL.

[1376] 4. Matching Algorithm Processing Means

[1377] The server runs matching algorithms, such as segmental matching algorithms and genetic algorithms, to match employee and robot profile data with the company's current needs (vacant positions, project requirements, tasks, etc.), generating optimal placement proposals.

[1378] 5. Reevaluation and optimization measures

[1379] The server receives feedback from employees and robots and re-evaluates them based on this feedback. This re-evaluation uses a machine learning model that continuously learns and regenerates placement plans based on the feedback. This model uses reinforcement learning.

[1380] Terminal handling

[1381] 1. Means of providing a dialogue interface

[1382] The terminals provide employees and factory robots with an interactive interface through which users can input information such as skills, experience, and desired position.

[1383] 2. Means of data transmission

[1384] The terminals transmit information entered by employees and factory robots to the server in real time, allowing the server to receive the necessary data immediately.

[1385] 3. Display of results

[1386] The terminal receives profile data and optimal placement suggestions from the server and displays them to employees and robots, allowing users to review the placement suggestions and provide feedback.

[1387] User Action

[1388] 1. Enter your information

[1389] The user uses the interactive interface of the terminal to input information such as his / her skills, experience, desired position, etc. This information is then sent from the terminal to the server.

[1390] 2. Providing Feedback

[1391] Users can input feedback on the placement proposals from the server, such as, "This position is interesting, but I would prefer a role that allows for more leadership."

[1392] Specific examples

[1393] For example, suppose you input skill data about factory robot A. Based on past data, robot A is good at "welding work," and feedback from robot A indicates that it would be better suited to a role that allows it to take on more leadership roles.

[1394] The server will then use this information to propose the optimal welding leader position and generate an optimized placement plan through re-evaluation. Specific examples of prompts are as follows:

[1395] Example prompt sentence:

[1396] "Please enter the skill data for Robot A in your factory. Example: Robot A has excellent welding skills and is fast at work. He also desires a leadership role."

[1397] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[1398] Step 1:

[1399] The server receives employee input data sent from the terminals, as well as factory robot operation status and performance data. This data includes employee skills, experience, desired positions, robot operating hours, error rates, and work speed. The received data is stored in a database on the server. Specific hardware used to collect data includes IoT sensors and sensors built into the robots.

[1400] Step 2:

[1401] The server runs a natural language processing (NLP) algorithm on the collected data. The NLP algorithm extracts keywords related to the skills and experience of employees and robots. This process uses NLP libraries (Spacy and NLTK) and machine learning models (Scikit-learn and TensorFlow). The input is the collected raw data, and the output is a list of keywords as a result of the analysis.

[1402] Step 3:

[1403] The server generates and stores profile data for employees and robots based on the extracted keywords. The profile data includes detailed information such as skill sets, experience, desired positions and tasks. This profile data is stored in a database using MySQL or PostgreSQL. The input is the analysis result from step 2, and the output is the stored profile data.

[1404] Step 4:

[1405] The server runs a matching algorithm to match employee and robot profile data with the company's needs. The matching takes into account the company's open positions, project requirements, and factory tasks. The algorithm uses a segmented matching algorithm or a genetic algorithm. The input is the profile data and the company's needs data, and the output is an optimal placement plan.

[1406] Step 5:

[1407] The terminal presents the generated placement plan to employees or robots and receives feedback. An example of feedback is a specific response such as, "This position is interesting, but I would prefer a role that allows me to demonstrate a bit more leadership." The input is the placement plan generated by the server, and the output is feedback from the user or robot.

[1408] Step 6:

[1409] The server reevaluates the system based on the received feedback and generates a relocation plan. A machine learning model (reinforcement learning model) that continuously learns is used for the reevaluation. This method optimizes the relocation plan based on the feedback. The input is the feedback from the user or robot, and the output is the regenerated optimal relocation plan.

[1410] Specific examples

[1411] For example, suppose you input skill data about factory robot A. Based on past data, robot A is good at "welding work," and feedback from robot A indicates that it would be better suited to a role that allows it to take on more leadership roles.

[1412] The server will then use this information to propose the optimal welding leader position and generate an optimized placement plan through re-evaluation. Specific examples of prompts are as follows:

[1413] Example prompt sentence:

[1414] "Please enter the skill data for Robot A in your factory. Example: Robot A has excellent welding skills and is fast at work. He also desires a leadership role."

[1415] 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.

[1416] A specific embodiment for realizing the system of the present invention will be described. In this system, three parties - a server, a terminal, and a user - each play their respective roles and work together to optimally allocate employees. Furthermore, by combining this with an emotion engine, it becomes possible to propose more effective allocations that take into account the user's emotions.

[1417] Server Processing

[1418] 1. Data Collection

[1419] The server receives the input data of the user (employee) sent from the terminal, including skills, experience, desired position, and conversation content. This data is stored in a database within the server.

[1420] 2. Data Analysis

[1421] The server runs a natural language processing (NLP) algorithm on the collected data to analyze it. Through the analysis, keywords such as employee skills, experience, and aspirations are extracted. Employee profile data is generated using the extracted data.

[1422] 3. Emotion analysis

[1423] The server uses an emotion engine to analyze the user's emotional state from the content of the conversation, for example, to detect whether the user is feeling stressed or excited during the conversation.

[1424] 4. Profile Management

[1425] The resulting profile data is stored as structured data containing the employee's detailed skill set, experience, desired position, and emotional state, providing an at-a-glance view of the employee's capabilities.

[1426] 5. Proposal for optimal layout

[1427] The server runs a matching algorithm that matches employee profile data with the company's current needs (open positions and project requirements). The algorithm matches the employee's skills with the company's needs and emotional state to generate optimal placement recommendations.

[1428] 6. Reassess and optimize

[1429] The server receives feedback from employees and re-evaluates them based on this. Using a continuously learning machine learning model, it generates reassignment plans based on the feedback. The results of sentiment analysis by the emotion engine are also taken into account.

[1430] Terminal handling

[1431] 1. Providing a conversational interface

[1432] The terminal provides the user (employee) with an interactive interface through which the user can input their skills, experience, desired position, and interaction content.

[1433] 2. Data transmission

[1434] The terminal transmits information entered by the user and the contents of the dialogue to the server in real time, allowing the server to receive the necessary data immediately.

[1435] 3. Displaying the results

[1436] The device displays the profile data and optimal placement proposals received from the server to the user, who can then review the proposals and provide feedback.

[1437] User Action

[1438] 1. Inputting information and interacting

[1439] The user uses the interactive interface of the terminal to input their skills, experience, desired position, and the content of the conversation. This information is sent from the terminal to the server, and the emotional state during the conversation is analyzed by the emotion engine.

[1440] 2. Providing Feedback

[1441] The user inputs feedback on the placement proposal from the server, for example, "This position is interesting, but I would also like to demonstrate leadership."

[1442] Specific examples

[1443] For example, if an employee enters, "I have five years of software development experience, and I'm particularly good at Python and Java," and then during the conversation says, "I'd like to try new technologies, but I'm a little nervous," the device sends this information to the server. The server uses natural language processing to analyze the employee's skills and experience, and further detects the emotion of nervousness using an emotion engine. It then generates profile data. The server then matches this profile data with the company's needs and generates an optimal placement proposal. For example, it might suggest, "A software engineer position on a new AI project would be suitable." The device displays this proposal to the user, who then provides feedback, saying, "I'd also like to demonstrate leadership." Through reevaluation, the server again proposes the "leadership position on a new AI project."

[1444] By utilizing the emotion engine, more optimal personnel placement can be achieved that takes into account the emotional state of employees, thereby improving productivity and efficiency across the entire company.

[1445] The processing flow will be explained below.

[1446] Step 1: The user initiates the interaction

[1447] Users access an interactive interface on their device and enter their skills, experience, and desired position, for example, "I have five years of software development experience, and I am particularly skilled in Python and Java."

[1448] Step 2: The device sends user input to the server

[1449] The device sends the information entered by the user to the server in real time, using API requests to transfer this data to the server.

[1450] Step 3: The device collects emotion data

[1451] The device analyzes the user's tone of voice and facial expressions during the conversation to collect emotional data, using audio recordings and cameras.

[1452] Step 4: The device sends the emotion data to the server.

[1453] The device transmits the collected emotional data to the server, which allows the server to recognize the emotional state.

[1454] Step 5: The server receives and stores the data

[1455] The server receives the user's input data and emotion data sent from the terminal and stores them in a database, including skills, experience, desired position, and emotion data.

[1456] Step 6: The server performs the data analysis

[1457] The server analyzes the stored data using natural language processing (NLP) algorithms, extracting keywords such as skills, experience, and aspirations, and converting them into structured data.

[1458] Step 7: The server performs sentiment analysis

[1459] The server uses an emotion engine to analyze the user's emotional state during the conversation, for example, to detect whether the user is feeling stressed or excited during the conversation.

[1460] Step 8: Server generates profile data

[1461] The server generates user profile data based on the extracted keywords and the results of sentiment analysis, which includes the user's skill set, experience, desired position, and emotional state.

[1462] Step 9: The server saves the profile data

[1463] The server stores the generated profile data in a database, which allows detailed employee information to be managed.

[1464] Step 10: The server captures the needs of the enterprise

[1465] The server retrieves data from a database about the company's current needs and open positions, including the skill requirements and responsibilities for each position.

[1466] Step 11: The server generates the optimal placement plan

[1467] The server runs a matching algorithm to match users' profile data with the company's needs, and generates optimal staffing recommendations based on skill matching and role compatibility.

[1468] Step 12: The server sends the placement plan to the device.

[1469] The server sends the generated placement plan to the terminal, allowing the user to check the proposed content.

[1470] Step 13: The device displays the layout plan to the user.

[1471] The device displays the placement proposal received from the server to the user, specifically displaying details of the placement proposal (e.g., a software engineer position for a new AI project).

[1472] Step 14: Users provide feedback

[1473] The user can then provide feedback on the proposed placement, such as, "This position is interesting, but I would also like to demonstrate leadership."

[1474] Step 15: Device sends feedback to server

[1475] The device receives the user's feedback and sends it to the server. The device forwards the feedback to the server using an API request.

[1476] Step 16: Server performs re-evaluation

[1477] The server reevaluates the system based on user feedback and uses a continuously learning machine learning model to generate optimal relocation plans based on the feedback.

[1478] Step 17: The server sends the reevaluation result to the terminal.

[1479] The server transmits the re-evaluation results to the terminal, and the regenerated placement plan is transferred to the terminal.

[1480] Step 18: The terminal displays the reevaluation results to the user

[1481] The device displays the reevaluation results received from the server to the user, for example, "You are recommended for a leadership position in a new AI project."

[1482] Through these steps, the system of the present invention can realize optimal personnel allocation based on employees' characteristics and preferences, improving the productivity and efficiency of the entire company. By utilizing the emotion engine, it is possible to propose more optimal personnel allocation that takes into account the emotional state of employees.

[1483] Example 2

[1484] 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."

[1485] When it comes to optimal personnel placement that takes into account employees' skills, experience, and desired positions, traditional profile analysis and matching algorithms alone have limitations, making it difficult to properly incorporate employees' emotional states and feedback. Furthermore, the reevaluation and reassignment process can be inefficient, negatively impacting employee satisfaction and corporate productivity. There is a need to solve these issues and provide a more effective and flexible personnel placement system.

[1486] The specific processing by the specific processing unit 290 of the data processing device 12 in the second embodiment is realized by the following means.

[1487] In this invention, the server includes an interactive interface providing means for inputting employee skills, experience, and desired positions, a natural language processing algorithm processing means for collecting and analyzing the content of employee dialogue, a profile management means for generating and saving employee profile data based on the analysis results, an emotion analysis means for analyzing the emotional state of employees from the content of dialogue, a matching algorithm processing means for matching the profile data with the needs of the company and generating an optimal personnel placement plan, a means for presenting the generated placement plan to employees and receiving feedback, and an optimization means for reevaluating based on the feedback and generating a reallocation plan. This makes it possible to generate flexible and effective placement plans that take into account the emotional state of employees, thereby improving employee satisfaction and corporate productivity.

[1488] An "interactive interface" is a user interface that allows employees to input information such as their skills, experience, and desired position.

[1489] A "natural language processing algorithm" is an algorithm that analyzes the content of employee conversations and extracts necessary information and keywords.

[1490] "Profile Data" is structured data that includes an employee's skills, experience, desired position, and other relevant information.

[1491] The "profile management means" is a means for saving and managing the generated profile data.

[1492] The "emotion analysis means" is a means for analyzing and detecting the emotional state of an employee from the content of their conversation.

[1493] The "matching algorithm" is an algorithm that matches profile data with the needs of the company and generates optimal personnel placement plans.

[1494] The "optimization means" is a means for reassessing employees based on their feedback and generating reassignment plans.

[1495] "Feedback" refers to the opinions and thoughts employees provide about proposed placements.

[1496] "Placement proposals" are suggestions for optimal personnel placement generated based on employee profile data and the company's needs.

[1497] The system of the present invention is designed to generate optimal personnel allocation plans that take into account employees' skills, experience, desired positions, and also their emotional state. This system operates in cooperation with three parties: a server, a terminal, and a user.

[1498] Server Processing

[1499] The server first receives the employee's input data sent from the terminal. This data includes the employee's skills, experience, desired position, and conversation content. The received data is then stored in a database. Specifically, a database management system such as MySQL or PostgreSQL can be used.

[1500] The server then runs natural language processing (NLP) algorithms on the stored data, using libraries like Python's NLTK and SpaCy, to analyze the data and extract keywords related to the employee's skills, experience, and aspirations.

[1501] Furthermore, the server uses an emotion engine to analyze the user's emotional state from the dialogue. For example, by using the Google Cloud Natural Language API, it can detect emotions such as stress or excitement felt by the user.

[1502] The generated profile data is stored as structured data that includes the employee's detailed skill set, experience, desired position, and emotional state.

[1503] The server then runs a matching algorithm that matches employee profile data with the company's needs using machine learning models such as Google Cloud AutoML and TensorFlow, generating optimal placement recommendations that match the employee's skills with the company's needs and emotional state.

[1504] The server receives feedback from users and reevaluates it using a machine learning model that continuously learns. This generates a relocation plan based on the feedback, taking into account the results of emotion analysis by the emotion engine.

[1505] Terminal handling

[1506] The terminal provides the user (employee) with an interactive interface through which the user can input their skills, experience, desired position, and interaction content.

[1507] The terminal transmits information entered by the user and the contents of the dialogue to the server in real time, allowing the server to receive the necessary data immediately.

[1508] The device also displays the profile data and optimal placement proposals received from the server to the user, who can then review the proposals and provide feedback.

[1509] User Action

[1510] The user uses the interactive interface of the terminal to input their skills, experience, desired position, and the content of the conversation. This information is sent from the terminal to the server, and the emotional state during the conversation is analyzed by the emotion engine.

[1511] Furthermore, users can input feedback on the placement proposals from the server, for example, "This position is interesting, but I would also like to demonstrate leadership skills."

[1512] Specific examples

[1513] As a specific example, if an employee types, "I have five years of software development experience and am particularly good at Python and Java," and then during the conversation says, "I would like to try new technologies, but I'm a little nervous," the device will send this information to the server.

[1514] The server analyzes the employee's skills and experience through natural language processing and detects anxiety using an emotion engine. It then generates profile data. The server matches this profile data with the company's needs and generates optimal placement recommendations. For example, it might suggest, "A software engineer position for a new AI project would be suitable."

[1515] The terminal displays the proposal to the user, who then provides feedback, saying, "I would also like to demonstrate leadership." Through reevaluation, the server can re-propose the "leadership position for a new AI project."

[1516] Prompt Sentence Examples

[1517] Below are some examples of specific prompt sentences to input into the generative AI model.

[1518] Prompt: I have 5 years of software development experience, particularly in Python and Java. I'd like to try new technologies but am a bit nervous. Please suggest a suitable position for me.

[1519] In this way, taking into account the emotional state of employees can lead to more effective and flexible staffing, improving productivity and efficiency across the company.

[1520] The flow of the identification process in the second embodiment will be described with reference to FIG.

[1521] Step 1: Data collection

[1522] The server receives user (employee) input data sent from the terminal. The input data includes the user's skills, experience, desired position, and dialogue content. This data is stored in a database (such as MySQL or PostgreSQL) on the server. For example, if a user enters "I have five years of software development experience, and I am particularly good at Python and Java," the terminal sends this information to the server, which stores it in a "user data" table.

[1523] Step 2: Data analysis

[1524] The server runs natural language processing (NLP) algorithms on the stored data to analyze it. Specifically, it uses Python's NLTK and SpaCy libraries to extract keywords related to the user's skills, experience, and desired position. For example, from an input such as "I have five years of software development experience, and I am particularly good at Python and Java," it extracts keywords such as "software development," "Python," and "Java."

[1525] Step 3: Sentiment Analysis

[1526] The server uses an emotion engine to analyze the user's emotional state from the dialogue content. Based on the input dialogue content, the emotion engine (e.g., Google Cloud Natural Language API) detects emotions such as "anxiety," "excitement," and "stress." For example, if a user inputs "I want to try a new technology, but I'm a little anxious," the emotion engine will detect the emotion "anxiety."

[1527] Step 4: Profile Management

[1528] The server generates employee profile data based on the extracted data and the results of sentiment analysis and stores it in a database. The generated profile data includes the employee's skill set, experience, desired position, and emotional state. For example, data such as "software development," "Python," "Java," and "anxiety" are stored in the "Employee Profile" table.

[1529] Step 5: Propose optimal layout

[1530] The server runs a matching algorithm that matches employee profile data with the company's needs. Using Google Cloud AutoML and TensorFlow, it generates optimal staffing recommendations based on the profile data and company needs. Using data on "software development," "Python," "Java," and "anxiety" as input, it compares these with the company's requirements for a "new AI project" and proposes a "software engineer position for a new AI project."

[1531] Step 6: Viewing results and feedback

[1532] The terminal displays the placement proposal received from the server to the user. The user checks the placement proposal and inputs feedback through an interactive interface. For example, if the user provides an opinion such as "This position is interesting, but I also want to demonstrate leadership," the terminal sends this feedback to the server.

[1533] Step 7: Reassess and optimize

[1534] The server receives feedback from users and reevaluates them using a continuously learning machine learning model. Based on the feedback and sentiment analysis results, it generates new reassignment proposals. For example, it may re-propose a "leadership position for a new AI project." This process can improve employee satisfaction and company productivity.

[1535] Prompt sentences with examples

[1536] Below are some examples of specific prompt sentences to input into the generative AI model.

[1537] Prompt: I have 5 years of software development experience, particularly in Python and Java. I'd like to try new technologies but am a bit nervous. Please suggest a suitable position for me.

[1538] (Application example 2)

[1539] 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."

[1540] Conventional systems that optimize the allocation of employee skills and experience do not take into account the emotional state of employees, resulting in a high risk of poor performance after allocation or employee turnover due to dissatisfaction. Furthermore, there was a lack of a system that could simultaneously analyze employee dialogue and emotions and quickly propose optimal allocations, so these issues need to be addressed.

[1541] The specific processing by the specific processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means. In this invention, the server includes an interactive interface providing means for inputting employee skills, experience, and desired positions, a natural language processing algorithm processing means for collecting and analyzing the content of employee dialogue, and a profile management means for generating and saving employee profile data based on the analysis results. This makes it possible to generate optimal placement plans that also take into account the emotional state of employees.

[1542] The "interactive interface providing means" is a means for providing an interactive interface for employees to input their skills, experience, and desired position.

[1543] The "natural language processing algorithm processing means" is a means that uses a natural language processing algorithm to collect and analyze the content of employee dialogue.

[1544] The "profile management means" is a means for generating and storing employee profile data based on the analysis results.

[1545] The "matching algorithm processing means" is a means that uses an algorithm to match profile data with the needs of the company and generate an optimal personnel allocation plan.

[1546] The "feedback receiving means" is a means for presenting the generated placement plan to employees and receiving their feedback.

[1547] The "re-evaluation means" is a means for performing a re-evaluation based on the feedback and generating a re-placement plan.

[1548] The "emotion analysis means" is a means for analyzing the emotional state of an employee from the content of their conversation.

[1549] "Means for adopting machine learning models" refers to means for adopting machine learning models that continuously learn based on employee feedback.

[1550] In the system for realizing the application example of the present invention, a server, a terminal, and a user work together. The following is a detailed description of how the system is implemented.

[1551] Server Processing

[1552] The server receives data sent from a terminal having an interactive interface supply means for inputting the employee's skills, experience, and desired position. The server analyzes the content of the dialogue using a natural language processing algorithm processing means, and generates and saves the analysis results as employee profile data using a profile management means.

[1553] The server analyzes the content of the employee's conversation using an emotion analysis means and also digitizes the employee's emotional state. It then compares the profile data with the company's needs and generates an optimal personnel placement plan using a matching algorithm processing means. The generated placement plan is then presented to the employee via their terminal, and the feedback from the employee is received using a feedback receiving means. A reevaluation means reevaluates the employee based on the feedback and generates a relocation plan. At this time, a machine learning model adoption means that continuously learns based on employee feedback is used to constantly update the optimal placement plan.

[1554] Terminal handling

[1555] The terminal provides a dialogue interface for users (employees) to input their skills, experience, and desired position. This information is sent to the server in real time. The dialogue is converted into text using voice recognition technology and sent to the server.

[1556] User Action

[1557] Users (employees) use the interactive interface on their terminals to input their skills, experience, desired position, and the content of their conversations. The input data is sent to the server, and their emotional state is analyzed using emotion analysis means. By providing feedback on the proposed placement plan, even more accurate placement plans can be regenerated.

[1558] Hardware and software used

[1559] The server uses the "TextBlob" library for natural language processing, the "NLTK" library for sentiment analysis, and the "scikit-learn" clustering algorithm. The device uses the "speech_recognition" library for speech recognition, converting user voice input into text data.

[1560] Specific examples

[1561] For example, if an employee says, "I'd like to help install a new logistics system, but I'm a little worried about the technology," the system can analyze the employee's concerns about the new technology and suggest an appropriate support system.

[1562] Example prompts to be input to the generative AI model

[1563] "Employees have expressed anxiety about new technology. What kind of assistance system should we suggest to employees who feel the same way?"

[1564] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[1565] Program processing flow

[1566] Step 1: Collecting user (employee) input data

[1567] The terminal provides an interactive interface for users to input their skills, experience, and desired position. The user inputs their skills, experience, desired position, and dialogue content through the interface. The terminal uses voice recognition technology to convert the user's voice input into text data. The generated text data is sent to the server in real time.

[1568] Input: User (employee) voice input

[1569] Data processing: Converting speech into text using voice recognition technology

[1570] Output: Text data

[1571] Step 2: Employee data analysis

[1572] The server receives the employee's conversation content sent from the terminal. Using a natural language processing algorithm, it extracts and analyzes information such as skills, experience, and desired position from the employee's conversation content. Based on this data, it generates employee profile data and stores it in a database.

[1573] Input: Text data

[1574] Data processing: Extraction and analysis of keywords using natural language processing algorithms

[1575] Output: Profile data

[1576] Step 3: Sentiment Analysis

[1577] The server uses emotion analysis means to analyze the employee's emotional state (e.g., stress, anxiety, excitement) based on the content of the employee's dialogue. The results of the emotion analysis are added to the profile data.

[1578] Input: Text data of the dialogue

[1579] Data processing: Emotion analysis algorithm analyzes emotional state

[1580] Output: Emotional state data

[1581] Step 4: Propose optimal layout

[1582] The server uses a matching algorithm processing means to match the generated profile data with the needs of the company, and generates an optimal personnel allocation plan by taking into account the employee's skills, experience, and emotional state. The allocation plan is presented to the employee via the terminal.

[1583] Input: Profile data, company needs

[1584] Data processing: Generate placement plans using a matching algorithm

[1585] Output: Optimal layout plan

[1586] Step 5: Receiving feedback

[1587] The terminal presents the generated placement plan to the employee, who then inputs feedback on the placement plan. The input feedback is sent to the server in real time.

[1588] Input: Optimal layout plan

[1589] Data processing: Employee feedback input

[1590] Output: Feedback data

[1591] Step 6: Reassess and optimize

[1592] The server performs re-evaluation based on the feedback received from employees. Using the re-evaluation method and the machine learning model adoption method, it generates a re-allocation plan that takes the feedback data into consideration. This enables optimal personnel allocation that takes into account the feedback and emotional state of employees.

[1593] Input: Feedback data

[1594] Data Transformation: Continuously train and reassess machine learning models

[1595] Output: Relocation proposal

[1596] Examples and prompts

[1597] For example, if an employee says, "I'd like to help install a new logistics system, but I'm a little worried about the technology," the system can analyze the employee's concerns about the new technology and suggest an appropriate support system.

[1598] Example prompts to input to a generative AI model:

[1599] "Employees have expressed anxiety about new technology. What kind of assistance system should we suggest to employees who feel the same way?"

[1600] 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.

[1601] 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.

[1602] 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.

[1603] 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.

[1604] FIG. 9 is a diagram illustrating an emotion map 400 on which multiple emotions are mapped. In the emotion map 400, emotions are arranged in concentric circles radiating from the center. Emotions closer to the center of the concentric circles are more primitive. Emotions representing states and actions arising from a state of mind are arranged on the outer edges of the concentric circles. The concept of emotion includes both affect and mental states. Emotions generally generated from reactions occurring in the brain are arranged on the left side of the concentric circles. Emotions generally induced by situational judgment are arranged on the right side of the concentric circles. Emotions generally generated from reactions occurring in the brain and induced by situational judgment are arranged on the upper and lower sides of the concentric circles. Furthermore, the emotion of "pleasure" is arranged on the upper side of the concentric circles, and the emotion of "discomfort" is arranged on the lower side. In this way, in the emotion map 400, multiple emotions are mapped based on the structure by which emotions are generated, and emotions that tend to occur simultaneously are mapped close to each other.

[1605] 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.

[1606] 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).

[1607] 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.

[1608] 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."

[1609] 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.

[1610] 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).

[1611] 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.

[1612] 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.

[1613] 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.

[1614] 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.

[1615] 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.

[1616] 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.

[1617] 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.

[1618] 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.

[1619] 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.

[1620] 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.

[1621] The following is further disclosed regarding the above embodiment.

[1622] (Claim 1)

[1623] means for providing an interactive interface for inputting employee skills, experience, and desired positions;

[1624] a natural language processing algorithm processing means for collecting and analyzing the dialogue content of the employee;

[1625] a profile management means for generating and storing employee profile data based on the analysis results;

[1626] a matching algorithm processing means for matching the profile data with the needs of the company and generating an optimal personnel allocation plan;

[1627] means for presenting the generated placement plan to employees and receiving feedback;

[1628] an optimization means for re-evaluating based on the feedback and generating a relocation plan;

[1629] A system including:

[1630] (Claim 2)

[1631] The system of claim 1 , wherein the matching algorithm processing means generates staffing recommendations by taking into account data including employee past evaluations and performance.

[1632] (Claim 3)

[1633] 10. The system of claim 1, wherein the optimization means employs a machine learning model that continuously learns based on employee feedback.

[1634] "Example 1"

[1635] (Claim 1)

[1636] means for providing an interactive interface for inputting employee skills, experience, and desired positions;

[1637] a natural language processing algorithm processing means for collecting and analyzing the dialogue content of the employee;

[1638] a profile management means for generating and storing employee profile data based on the analysis results;

[1639] a matching algorithm processing means for matching the profile data with the needs of the company and generating an optimal personnel allocation plan;

[1640] means for presenting the generated placement plan to employees and receiving feedback;

[1641] an optimization means for re-evaluating based on the feedback and generating a relocation plan;

[1642] a data transmission means for transmitting information input by an employee using the interface to a server;

[1643] means for the server to store employee input data in a database;

[1644] A means for the server to optimize placement plans using a machine learning model;

[1645] A system including:

[1646] (Claim 2)

[1647] The system of claim 1 , wherein the matching algorithm processing means generates staffing recommendations by taking into account data including employee past evaluations and performance.

[1648] (Claim 3)

[1649] 10. The system of claim 1, wherein the optimization means employs a machine learning model that continuously learns based on employee feedback.

[1650] "Application Example 1"

[1651] (Claim 1)

[1652] means for providing an interactive interface for inputting employee skills, experience, and desired positions;

[1653] a natural language processing algorithm processing means for collecting and analyzing the dialogue content of the employee;

[1654] a profile management means for generating and storing employee profile data based on the analysis results;

[1655] a matching algorithm processing means for matching the profile data with the needs of the company and generating an optimal personnel allocation plan;

[1656] means for presenting the generated placement plan to employees and receiving feedback;

[1657] an optimization means for re-evaluating based on the feedback and generating a relocation plan;

[1658] a data collection means for collecting operational status and performance data of the factory robot and transmitting the data to a cloud server;

[1659] a data analysis means for analyzing the collected data using a natural language processing algorithm to generate a skill profile of the robot;

[1660] a profile management means for storing and managing skill profile data generated based on the analysis results;

[1661] a matching algorithm processing means for generating an optimal task placement plan;

[1662] A re-evaluation and optimization means for re-evaluating the robot based on feedback and generating an optimized placement plan;

[1663] A system including:

[1664] (Claim 2)

[1665] The system of claim 1 , wherein the matching algorithm processing means generates staffing recommendations by taking into account data including employee past evaluations and performance.

[1666] (Claim 3)

[1667] 10. The system of claim 1, wherein the optimization means employs a machine learning model that continuously learns based on employee feedback.

[1668] "Example 2: Combining Emotion Engines"

[1669] (Claim 1)

[1670] means for providing an interactive interface for inputting employee skills, experience, and desired positions;

[1671] a natural language processing algorithm processing means for collecting and analyzing the dialogue content of the employee;

[1672] a profile management means for generating and storing employee profile data based on the analysis results;

[1673] emotion analysis means for analyzing the emotional state of the employee from the content of the dialogue;

[1674] a matching algorithm processing means for matching the profile data with the needs of the company and generating an optimal personnel allocation plan;

[1675] means for presenting the generated placement plan to employees and receiving feedback;

[1676] an optimization means for re-evaluating based on the feedback and generating a relocation plan;

[1677] A system including:

[1678] (Claim 2)

[1679] The system of claim 1 , wherein the matching algorithm processing means generates staffing recommendations by taking into account data including employee past evaluations and performance.

[1680] (Claim 3)

[1681] 10. The system of claim 1, wherein the optimization means employs a machine learning model that continuously learns based on employee feedback.

[1682] "Application example 2 when combining emotion engines"

[1683] (Claim 1)

[1684] means for providing an interactive interface for inputting employee skills, experience, and desired positions;

[1685] a natural language processing algorithm processing means for collecting and analyzing the dialogue content of the employee;

[1686] a profile management means for generating and storing employee profile data based on the analysis results;

[1687] a matching algorithm processing means for matching the profile data with the needs of the company and generating an optimal personnel allocation plan;

[1688] means for presenting the generated placement plan to employees and receiving feedback;

[1689] an optimization means for re-evaluating based on the feedback and generating a relocation plan;

[1690] an emotion analysis means for analyzing the emotional state of each employee;

[1691] a means for generating a personnel allocation plan taking into consideration the analysis result of the emotion analysis means;

[1692] A system including:

[1693] (Claim 2)

[1694] The system of claim 1 , wherein the matching algorithm processing means generates staffing recommendations by taking into account data including employee past evaluations and performance.

[1695] (Claim 3)

[1696] 10. The system of claim 1, wherein the optimization means employs a machine learning model that continuously learns based on employee feedback. [Explanation of symbols]

[1697] 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. means for providing an interactive interface for inputting employee skills, experience, and desired positions; a natural language processing algorithm processing means for collecting and analyzing the dialogue content of the employee; a profile management means for generating and storing employee profile data based on the analysis results; a matching algorithm processing means for matching the profile data with the needs of the company and generating an optimal personnel allocation plan; means for presenting the generated placement plan to employees and receiving feedback; an optimization means for re-evaluating based on the feedback and generating a relocation plan; A system including:

2. The system of claim 1 , wherein the matching algorithm processing means generates staffing recommendations by taking into account data including employee past evaluations and performance.

3. The system of claim 1 , wherein the optimization means employs a machine learning model that continuously learns based on employee feedback.

Images