System

Abstract

A system is provided.SOLUTION: The system includes a means for collecting data on job history, results, strengths / weaknesses, characteristics, desires, and human relationships of employees, a means for preprocessing and analyzing the collected data, a means for learning a generation AI model for predicting appropriateness and allocation of employees based on an analysis result, a means for generating an optimal personnel allocation plan using the learned generation AI model, a means for suggesting appropriate project members, and a means for monitoring an organization result after allocation and improving accuracy of the generation AI model.SELECTED DRAWING: Figure 1

Description

[Technical Field]

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

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

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

[0004] Human resource allocation is often based on employee preferences, evaluations, performance, and self-analysis, which means there are limitations to the judgment due to the strong secular elements. Another problem is that it is difficult to see the organizational results after allocation. Furthermore, it is difficult to create appropriate allocation plans and discover hidden, excellent human resources, which hinders the improvement of the efficiency of the entire organization. The purpose of this invention is to solve these problems by streamlining the management of human resource resources and making the most of human resources in the right places. [Means for solving the problem]

[0005] The present invention collects data on employees' work history, achievements, strengths and weaknesses, characteristics, aspirations, and relationships, performs preprocessing and analysis, and trains a generative AI model based on the analysis results. The trained generative AI model is used to generate optimal personnel allocation plans and suggest appropriate project members. The system also includes a system that monitors organizational performance after allocation, adjusts the parameters of the generative AI model based on the results, and re-trains it to consistently provide highly accurate allocation plans. Furthermore, by providing a means to detect and correct duplicate and incomplete data, data accuracy is improved and reliable analysis results are guaranteed.

[0006] "Employee" refers to an individual worker employed by a business or organization.

[0007] "Work history" refers to the history of jobs and positions held by an employee.

[0008] "Results" refers to the concrete results of an employee's achievements and contributions in the past.

[0009] "Strengths and weaknesses" refer to the skills and abilities in which an employee is particularly good, as well as the areas and abilities in which they are weak.

[0010] "Traits" refer to the elements that characterize an employee's personality, behavioral patterns, and aptitudes.

[0011] "Aspirations" refers to the employee's requests for the job or position they would like to take on in the future.

[0012] "Human relationships" refers to communication, cooperation, and mutual evaluation between employees.

[0013] "Data collection tools" refers to methods and devices used to collect information such as employee work history and performance.

[0014] "Preprocessing" refers to the process of preparing collected data for analysis.

[0015] A "generative AI model" refers to an artificial intelligence model that is trained using machine learning algorithms to predict employee aptitude and placement.

[0016] A "placement plan" refers to a specific plan for efficiently placing employees in the right positions.

[0017] "Suggestion" refers to proposing appropriate project members and placement plans.

[0018] "Monitoring" refers to the continuous observation and recording of a condition or process.

[0019] "Retraining" refers to the process of retraining a generative AI model based on new data collected.

[0020] "Duplicate data" refers to data in which the same information is recorded multiple times.

[0021] "Incomplete data" refers to data that is incomplete and lacks necessary information. [Brief explanation of the drawings]

[0022] [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

[0023] 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.

[0024] First, the terms used in the following description will be explained.

[0025] 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).

[0026] 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.

[0027] 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.

[0028] 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.

[0029] 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."

[0030] [First embodiment]

[0031] FIG. 1 shows an example of the configuration of a data processing system 10 according to the first embodiment.

[0032] 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.

[0033] 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).

[0034] 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.

[0035] 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.

[0036] 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.

[0037] 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.

[0038] FIG. 2 shows an example of the main functions of the data processing device 12 and the smart device 14.

[0039] 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.

[0040] 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.

[0041] 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.

[0042] 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."

[0043] This invention relates to a system that analyzes employee information and generates an optimal personnel allocation plan. This system collects data such as employees' work history, achievements, strengths and weaknesses, characteristics, aspirations, and relationships, and trains a generative AI model based on that data. The trained generative AI model is used to achieve efficient personnel allocation in companies and organizations. Specific embodiments for implementing this system are described below.

[0044] Data collection

[0045] The server automatically collects data on employees' work history, achievements, strengths and weaknesses, characteristics, aspirations, and relationships from personnel management systems, evaluation systems, employee surveys, etc. This allows a wide range of information to be obtained in a timely manner.

[0046] Data Preprocessing

[0047] The server preprocesses the collected data, normalizing it, filling in missing values, correcting outliers, and detecting and deleting duplicate data, enabling highly accurate analysis.

[0048] Data analysis and model training

[0049] The server analyzes the preprocessed data and evaluates the characteristics of each employee. Based on the analysis results, it trains a generative AI model, which contains an algorithm for predicting the optimal placement of employees.

[0050] Generate optimal placement plans

[0051] The terminal receives input requirements from the user (e.g., details of a new project, required skill sets). It then uses the analytical data obtained from the server and the generative AI model to generate an optimal staffing plan. The generated staffing plan is then presented to the user.

[0052] Recommended talent suggestions

[0053] The device will suggest suitable personnel for specific projects or department restructuring, allowing users to easily identify the most suitable members and achieve efficient project management and department restructuring.

[0054] Monitoring and relearning deployment results

[0055] The server monitors organizational performance after deployment. It periodically collects data such as sales fluctuations and employee satisfaction to evaluate the effectiveness of the deployment plan. Based on the results of this evaluation, it adjusts the parameters of the generative AI model and performs re-learning. This improves the accuracy of future deployment plans.

[0056] Specific examples

[0057] Example 1: Launching a new sales department

[0058] 1. A user enters the required skill sets and job titles to launch a new sales department into a terminal.

[0059] 2. The server analyzes data on all employees and identifies suitable candidates with strong sales skills and leadership abilities.

[0060] 3. The device suggests "Employee A" as a potential sales department leader and recommends "Employee B" and "Employee C" as team members.

[0061] 4. The user checks the device recommendations and decides on the placement.

[0062] Example 2: Suggesting talent for a new project

[0063] 1. A user inputs the necessary skill set to start a new project (e.g., updating an IT system) into a terminal.

[0064] 2. The server analyzes employee data and identifies "Employee D," who has successfully completed similar projects in the past, as the project leader.

[0065] 3. The terminal recommends "Employee E" and "Employee F," who have strong development skills and have good project experience with "Employee D" in the past.

[0066] 4. The user checks the recommendations from the device, corrects them if necessary, and decides on the placement.

[0067] Through this implementation, companies can maximize the skills and attributes of their employees, improving efficiency and performance across the organization.

[0068] The processing flow will be explained below.

[0069] Step 1: Data collection

[0070] The server collects data on employees' work history, achievements, strengths and weaknesses, characteristics, aspirations, and relationships from data sources such as personnel management systems, personnel evaluation systems, employee surveys, etc. This data is scheduled to be collected automatically on a regular basis.

[0071] Step 2: Data Preprocessing

[0072] The server preprocesses the collected data, specifically by standardizing the data format (normalization), filling in missing values, detecting and correcting outliers, and eliminating duplicate data, creating a clean dataset suitable for analysis.

[0073] Step 3: Characterization and evaluation

[0074] The server analyzes the pre-processed data and evaluates employee traits (e.g., leadership ability, collaboration) and skill sets (e.g., coding skills, sales skills). This analysis uses machine learning algorithms to calculate a specific evaluation score for each employee.

[0075] Step 4: Training the generative AI model

[0076] The server trains a generative AI model based on the analysis results. This model includes an algorithm for predicting optimal employee placement. Past placement history and its results (e.g., sales increase, project success rate) are used as training data.

[0077] Step 5: Fill out your deployment request

[0078] Users use their devices to input specific requirements for new projects or department restructuring (e.g., required skills, number of people, job titles), and this request information is sent to the generative AI model.

[0079] Step 6: Generate optimal layout plans

[0080] The device generates an optimal deployment plan using data obtained from the server and a generative AI model. Specifically, it selects the most suitable personnel based on the specified conditions, taking into account the characteristics and skill sets of each employee.

[0081] Step 7: Present the layout plan

[0082] The device presents the generated deployment plan to the user, displaying specific recommendations such as, "Employee A is recommended as the sales department leader, and Employees B and C are optimal team members."

[0083] Step 8: Deployment and Implementation

[0084] The user checks the proposed deployment plan, modifies it as necessary, and finalizes the deployment. After the plan is finalized, it is put into practice.

[0085] Step 9: Monitoring the deployment results

[0086] The server monitors organizational performance after deployment, specifically by continuously observing and collecting data on sales fluctuations, employee satisfaction, project progress, etc.

[0087] Step 10: Retraining the generative AI model

[0088] Based on the monitoring results, the server adjusts the parameters of the generated AI model and performs re-learning, thereby improving the accuracy of future deployment plans.

[0089] This series of steps results in a system that makes the most of the characteristics and skills of your employees, improving efficiency and performance across the organization.

[0090] Example 1

[0091] Next, a description will be given of Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the smart device 14 will be referred to as a "terminal."

[0092] Currently, human resource allocation planning in companies is often based on experience and intuition, which can result in less than optimal allocation. Furthermore, employee information is scattered across multiple systems, making it difficult to integrate and normalize the data. Furthermore, there is no system in place to centrally monitor employee performance after allocation and incorporate feedback. A system that can solve these issues and achieve efficient and effective human resource allocation is needed.

[0093] The specific processing by the specific processing unit 290 of the data processing device 12 in the first embodiment is realized by the following means.

[0094] In this invention, the server includes: means for collecting information on employees' work history, achievements, strengths and weaknesses, characteristics, aspirations, and interpersonal relationships; means for normalizing the collected information, filling in missing values, correcting outliers, and detecting and deleting duplicate data; and means for analyzing the preprocessed information, evaluating employee characteristics, and training a generative AI model based on the analysis results. This enables accurate collection and analysis of detailed employee information and the generation of optimal personnel allocation plans based on the results. Additionally, by monitoring organizational performance after allocation, adjusting the parameters of the generative AI model, and retraining, the accuracy of the allocation plan can be continuously improved. Furthermore, by suggesting appropriate project members for specific projects or department restructuring, efficient personnel management is possible.

[0095] Employee's work history

[0096] This is information that indicates the job content and experience that an employee has had in the past.

[0097] "Results"

[0098] This is information that shows the specific achievements and accomplishments that an employee has achieved through their work.

[0099] "Strengths and Weaknesses"

[0100] This is information that indicates an employee's specialized skills and abilities, as well as any deficiencies.

[0101] "Characteristics"

[0102] This is information that indicates an employee's personality, behavioral characteristics, and thought patterns.

[0103] "Hope"

[0104] This is information that indicates the job content, career path, and working conditions that an employee desires in the future.

[0105] "Human relationships"

[0106] This is information that indicates the relationships that an employee has with other employees within the company.

[0107] "Normalization"

[0108] It is the process of standardizing collected data based on certain criteria.

[0109] "Missing value imputation"

[0110] is the process of filling in missing values ​​in a dataset with appropriate values.

[0111] "Correction of outliers"

[0112] is the process of detecting outliers in a data set and correcting them to appropriate values.

[0113] "Detecting and Removing Duplicate Data"

[0114] is the process of detecting duplicate data within a dataset and removing unnecessary duplicate data.

[0115] "Generative AI model"

[0116] is an algorithm that is generated using machine learning and deep learning techniques based on collected data to make predictions about personnel placement and other matters.

[0117] "Preprocessing"

[0118] This is a series of data processing processes carried out to prepare collected data in a form that makes it easier to analyze.

[0119] "analysis"

[0120] It is the process of analysis that uses collected and preprocessed data to reveal characteristics and relationships.

[0121] "Optimal personnel allocation planning"

[0122] It is a plan that shows the most efficient allocation of employees to departments and projects, taking into account their characteristics and skills and the company's requirements.

[0123] "Project member suggestions"

[0124] is the process of recommending employees who are best suited for a particular project.

[0125] "monitoring"

[0126] This is the process of continuously observing and recording the performance of organizations and employees after deployment.

[0127] "Parameter Adjustment"

[0128] This is the process of changing internal variables and settings to improve the predictive accuracy of a generative AI model.

[0129] "Relearning"

[0130] This is the process of retraining an existing generative AI model with new data to improve its predictive accuracy.

[0131] This invention is a system for efficiently allocating personnel to a company. The system collects detailed information about employees, analyzes and learns from that data, and then generates and proposes optimal personnel allocation plans.

[0132] To implement this system, the following hardware and software are used.

[0133] Hardware and software used

[0134] Server: Collects data, preprocesses, analyzes, and trains AI models.

[0135] Human Resources Management System Example: "Human Resources Management System"

[0136] Database example: "SQL Database"

[0137] Example of software for model training: "TensorFlow"

[0138] Examples of data preprocessing software: "Python", "pandas", "scikit-learn"

[0139] Terminal: Receives input from the user and presents analysis results and deployment plans.

[0140] Example of interface software: "Web browser"

[0141] Data collection

[0142] The server collects employee information from various internal personnel management systems, evaluation systems, and survey tools. It uses APIs to seamlessly integrate data. For example, an API call retrieves information about work history and achievements from a personnel management system.

[0143] Data Preprocessing

[0144] The server normalizes the collected data, fills in missing values, corrects outliers, and detects and removes duplicate data, creating a dataset suitable for analysis. Specifically, the server cleans the data using the Python pandas library and scales the numerical data using scikit-learn's StandardScaler.

[0145] Data analysis and model training

[0146] The server uses the preprocessed data to evaluate the characteristics of each employee. Based on these evaluation results, it trains a generative AI model. TensorFlow is used to train the model. The server saves the trained model and uses it to generate future placement plans.

[0147] Generate optimal staffing plans

[0148] The terminal receives input conditions from the user. The user enters the details of a new project and the required skill set into the terminal. For example, the user enters a prompt such as "We are looking for a leader for a new IT project." The terminal then sends this to the server, and generates an optimal staffing plan using the analytical data obtained from the server and the generative AI model. The results are displayed to the user through a GUI.

[0149] Recommended talent suggestions

[0150] The terminal suggests suitable project members for specific projects or department restructuring. The user inputs a prompt such as "Please recommend the best employees for a new project." The terminal uses a generative AI model to generate a list of recommended personnel and presents it to the user.

[0151] Monitoring and relearning deployment results

[0152] The server monitors organizational performance after deployment. It analyzes sales data and employee satisfaction to evaluate the effectiveness of the generative AI model. For example, it uses new data obtained from sales data and employee satisfaction surveys to adjust the model parameters and retrain. This improves the accuracy of future deployment plans.

[0153] Specific examples

[0154] Example 1: A user inputs the "skill set and job title required to launch a new sales department" into a terminal. The server identifies personnel with sales skills and leadership skills, and the terminal recommends "Employee A" and "Employee B."

[0155] Example 2: The user inputs "the leader and development team of a new IT project" into the terminal. The server identifies "Employee D" who has had successful projects in the past, and the terminal recommends "Employee D" and "Employee E."

[0156] Through this system, companies can make the most of the skills and attributes of their employees, improving efficiency and performance across the organization.

[0157] The flow of the identification process in the first embodiment will be described with reference to FIG.

[0158] Program processing flow

[0159] Step 1:

[0160] The server collects information on employees' work history, achievements, strengths and weaknesses, characteristics, aspirations, and relationships from various systems (human resource management systems, evaluation systems, survey tools, etc.). Specifically, it connects using an "API" and stores the acquired information in an "SQL database."

[0161] Input: Employee information from HR management systems, appraisal systems, and survey tools.

[0162] Output: Employee information in a SQL database.

[0163] Step 2:

[0164] The server preprocesses employee information stored in an SQL database using Python and pandas to normalize data, impute missing values, correct outliers, and detect and remove duplicate data.

[0165] Input: Collected employee information on a SQL database.

[0166] Output: Preprocessed employee information.

[0167] Step 3:

[0168] The server analyzes the preprocessed data, assessing employee characteristics and using the results to train a generative AI model using TensorFlow, which includes an algorithm for predicting staffing levels.

[0169] Input: Preprocessed employee information.

[0170] Output: A trained generative AI model.

[0171] Step 4:

[0172] The terminal receives input from the user, such as details of a new project and the required skill set, and sends it to the server, for example, by entering a prompt statement such as "We are looking for a leader for a new IT project."

[0173] Input: A prompt from the user.

[0174] Output: Analysis conditions passed to the generative AI model.

[0175] Step 5:

[0176] The server receives a prompt from the user and generates an optimal staffing plan using the preprocessed employee information and the trained generative AI model, such as "Identify employees with the skills required to launch a new sales department." The generated staffing plan is then sent back to the terminal.

[0177] Input: Analysis conditions from the terminal.

[0178] Output: Optimal staffing plan.

[0179] Step 6:

[0180] The terminal displays the allocation plan sent from the server to the user on a GUI, allowing the user to determine the optimal personnel allocation based on this information.

[0181] Input: The deployment plan sent by the server.

[0182] Output: A layout plan display provided to the user.

[0183] Step 7:

[0184] After the deployment plan is implemented, the server periodically monitors organizational outcomes such as sales data and employee satisfaction, and obtains new data from Google Analytics and internal databases to evaluate the accuracy of the generative AI model.

[0185] Input: Organizational outcomes data.

[0186] Output: The evaluated generative AI model.

[0187] Step 8:

[0188] The server adjusts the parameters of the generative AI model based on the monitoring results and performs re-learning, thereby improving the accuracy of future personnel allocation plans.

[0189] Input: An evaluated generative AI model.

[0190] Output: The retrained generative AI model.

[0191] (Application example 1)

[0192] 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."

[0193] In logistics centers, proper employee allocation is extremely important for efficient business operations. However, considering the skill sets, experience, and preferences of multiple employees at once and assigning the most suitable personnel is a significant burden for managers. Furthermore, manual allocation planning is prone to errors and bias, which can reduce operational efficiency. Furthermore, it is difficult to obtain feedback on work results and employee satisfaction after allocation. Conventional methods have limited means of efficiently resolving these issues.

[0194] 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.

[0195] In this invention, the server includes: means for collecting data on employee work history, achievements, strengths and weaknesses, characteristics, preferences, and interpersonal relationships; means for preprocessing and analyzing the collected data; means for training a generative AI model that predicts employee aptitude and placement based on the analysis results; means for generating an optimal personnel placement plan using the trained generative AI model; means for inputting required skill sets and job title requirements; means for analyzing employee data within the logistics center and suggesting optimal personnel placement; and means for monitoring organizational performance after placement and improving the accuracy of the generative AI model. This enables optimal personnel placement in logistics centers that takes into account employee skill sets and preferences, thereby improving business efficiency. By monitoring feedback after placement, continuous model improvement and efficiency can be expected.

[0196] "Employee work history" refers to each employee's past work experience and the history of the positions they have held.

[0197] "Results" refers to the results or accomplishments that an employee achieves in their work.

[0198] "Strengths and weaknesses" refer to the strengths and weaknesses of an employee in specific skills and abilities.

[0199] "Traits" refer to an employee's personality, behavioral patterns, aptitude for work, and other characteristics.

[0200] "Aspirations" refers to the hopes and demands that employees have about their work and the career path they desire in the future.

[0201] "Human relationships" refers to the relationships between employees, mutual trust, and cooperative systems.

[0202] "Means of collecting data" refers to the methods and tools used to automatically or manually capture the required data.

[0203] "Preprocessing" refers to the process of converting collected data into an analyzable form.

[0204] "Analysis" refers to the process of evaluating employee characteristics and suitability based on pre-processed data.

[0205] A "generative AI model" refers to an artificial intelligence model trained based on employee data.

[0206] "Optimal personnel allocation planning" refers to an allocation plan that makes the most of employees' skills and characteristics and achieves efficient business operations.

[0207] A "skill set" refers to the collection of techniques and knowledge required to perform a specific job.

[0208] "Position" refers to the job or position assigned to an employee within an organization.

[0209] "Means for inputting requirements" refers to the methods and tools for inputting the necessary conditions and skills to realize the deployment plan into the system.

[0210] "Means for suggesting personnel placement" refers to systems or algorithms that recommend the most suitable personnel based on the results of analysis.

[0211] "Organizational results" refers to the performance and achievements of employees and the organization as a whole after deployment.

[0212] "Monitoring" refers to the activity of regularly observing organizational results and employee performance and collecting data.

[0213] This invention relates to a system for realizing efficient personnel allocation in logistics centers. The system uses a generative AI model to collect and analyze data on employees' work history, achievements, strengths and weaknesses, characteristics, aspirations, and relationships, and to generate optimal allocation plans.

[0214] Data collection

[0215] The server collects data on employees' work history, achievements, strengths and weaknesses, characteristics, aspirations, and relationships from personnel management systems, evaluation systems, employee surveys, etc. This makes it possible to obtain a wide range of information in a timely manner.

[0216] Data Preprocessing

[0217] The server performs preprocessing on the collected data, such as normalizing it, filling in missing values, correcting outliers, and detecting and deleting duplicate data, enabling highly accurate analysis.

[0218] Data analysis and model training

[0219] The server analyzes the preprocessed data and evaluates the characteristics of each employee. The results of this analysis are used to train a generative AI model, which includes an algorithm for predicting optimal employee placement.

[0220] Generate optimal placement plans

[0221] The terminal receives input conditions from the user (e.g., details of the new project, required skill set, job title), and generates an optimal personnel allocation plan using analytical data obtained from the server and a generative AI model. The generated allocation plan is then presented to the user.

[0222] Recommended talent suggestions

[0223] The device will suggest suitable personnel for specific projects or department restructuring, allowing users to easily identify the most suitable members and achieve efficient project management and department restructuring.

[0224] Monitoring and relearning deployment results

[0225] The server monitors organizational performance after deployment. It periodically collects data such as sales fluctuations and employee satisfaction to evaluate the effectiveness of the deployment plan. Based on the results of this evaluation, it adjusts the parameters of the generative AI model and performs re-learning. This improves the accuracy of future deployment plans.

[0226] Specific examples

[0227] Example: Suggesting talent for a new logistics project

[0228] 1. A user enters into a terminal the required skill set and job title to start a new project (e.g., a large-scale inventory cleanup).

[0229] 2. The server analyzes employee data to identify employees who have successfully completed similar projects in the past.

[0230] 3. The terminal recommends employees with forklift driving skills and experience in sorting goods.

[0231] 4. The user checks the recommendations from the device, corrects them if necessary, and decides on the placement.

[0232] Prompt Sentence Examples

[0233] We need people who can operate forklifts and sort goods.

[0234] This embodiment allows distribution center managers to maximize employee skill sets and characteristics, realize efficient staffing, and continuously improve the model through post-deployment feedback.

[0235] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[0236] Step 1:

[0237] The server collects employee data (work history, achievements, strengths and weaknesses, characteristics, aspirations, relationships).

[0238] Inputs: Data from HR management systems, appraisal systems, and employee surveys.

[0239] Specific operation: Retrieve the necessary information from the database via API.

[0240] Output: A set of collected employee data.

[0241] Step 2:

[0242] The server pre-processes the collected data.

[0243] Input: Employee data collected in Step 1.

[0244] Specific operations: data normalization, missing value imputation, outlier correction, duplicate data detection and removal.

[0245] Output: A preprocessed and clean dataset.

[0246] Step 3:

[0247] The server analyzes the pre-processed data and evaluates the characteristics of each employee.

[0248] Input: The preprocessed data from step 2.

[0249] What it does: Uses machine learning algorithms to assess skills, experience, and attributes.

[0250] Output: Evaluation results for each employee.

[0251] Step 4:

[0252] The server trains the generative AI model based on the evaluation results.

[0253] Input: The employee's evaluation results from step 3.

[0254] Specific operation: The evaluation results are fed into the AI ​​to optimize the model parameters.

[0255] Output: A trained generative AI model.

[0256] Step 5:

[0257] The terminal receives input conditions (required skill set and job title requirements) from the user.

[0258] Input: A prompt from the user (e.g., "We need people who can drive forklifts and sort goods").

[0259] Specific operation: Obtain conditions from input forms or voice input.

[0260] Output: User-specified skillset and job title requirements.

[0261] Step 6:

[0262] The server generates an optimal personnel allocation plan using the analytical data acquired and the generated AI model.

[0263] Input: The user input conditions from step 5 and the generative AI model from step 4.

[0264] Specific operation: Input the user's requirements into the model and list suitable candidates.

[0265] Output: Optimal staffing plan.

[0266] Step 7:

[0267] The terminal presents the user with the optimal staffing plan.

[0268] Input: The staffing plan generated in step 6.

[0269] Specific actions: Display the plan via the user interface.

[0270] Output: Staffing plan presented to the user.

[0271] Step 8:

[0272] The server monitors organizational performance after deployment and collects data.

[0273] Input: Outcome data such as sales data, employee satisfaction data, etc.

[0274] Specific actions: Regularly collect performance data and analyze trends.

[0275] Output: Monitored outcome data.

[0276] Step 9:

[0277] The server adjusts the parameters of the generated AI model based on the monitoring results and performs re-learning.

[0278] Input: Outcome data from Step 8.

[0279] Specific operations: Readjust the parameters of the AI ​​model based on the performance data and repeat the learning process.

[0280] Output: An improved generative AI model.

[0281] 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.

[0282] This invention relates to a system that analyzes employee information and generates optimal personnel allocation plans. In particular, by combining it with an emotion engine, it takes into account the emotional state of the user to realize more accurate personnel allocation plans.

[0283] Data collection

[0284] The server collects data on employees' work history, achievements, strengths and weaknesses, characteristics, aspirations, and interpersonal relationships from data sources such as personnel management systems, personnel evaluation systems, employee surveys, etc. This data collection is carried out periodically, making it possible to analyze based on the latest information.

[0285] Data Preprocessing

[0286] The server preprocesses the collected data by normalizing it, imputing missing values, detecting and correcting outliers, and eliminating duplicate data, creating a clean dataset suitable for analysis.

[0287] Characterization and evaluation

[0288] The server analyzes the pre-processed data and evaluates each employee's characteristics and skill set using machine learning algorithms to calculate an evaluation score for each employee.

[0289] Training generative AI models

[0290] The server trains a generative AI model based on the analysis results. This model includes an algorithm for predicting optimal employee placement. Past placement history and its results (e.g., sales increase, project success rate) are used as training data.

[0291] Emotion engine integration

[0292] The device is equipped with an emotion engine that recognizes the user's emotions. This engine analyzes the emotions (e.g., joy, anger, anxiety) expressed when the user interacts with the system in real time.

[0293] Generate and adjust optimal layout plans

[0294] The device receives input conditions from the user (e.g., details of a new project, required skill sets), and generates an optimal deployment plan using data obtained from the server and a generative AI model.Furthermore, the device fine-tunes the deployment plan by reflecting the user's emotional state analyzed by an emotion engine.

[0295] Presenting the layout plan

[0296] The terminal presents the generated allocation plan to the user, for example, displaying a message such as, "Employee A is recommended as the leader of the sales department, and Employees B and C are optimal as team members."

[0297] Placement decision and implementation

[0298] The user checks the proposed deployment plan, makes adjustments as necessary, and finally decides on the deployment. After the decision is made, the plan is put into action.

[0299] Monitoring and relearning deployment results

[0300] The server monitors organizational performance after deployment, continuously observing and collecting data on factors such as sales fluctuations, employee satisfaction, and project progress. Based on the results of this monitoring, the parameters of the generative AI model are adjusted and re-learned, improving the accuracy of future deployment plans.

[0301] Specific examples

[0302] Example 1: Launching a new sales department

[0303] 1. A user enters the required skill sets and job titles to launch a new sales department into a terminal.

[0304] 2. The server analyzes data on all employees and identifies suitable candidates with strong sales skills and leadership abilities.

[0305] 3. The device suggests "Employee A" as a potential sales department leader and recommends "Employee B" and "Employee C" as team members.

[0306] 4. The emotion engine analyzes how the user perceives this in real time, and if it recognizes that the user is feeling anxious, it presents questions to provide feedback on the reason. The user answers these questions, and the deployment plan is further adjusted.

[0307] 5. The user finally checks the revised deployment plan and decides on the deployment.

[0308] Example 2: Suggesting talent for a new project

[0309] 1. A user inputs the necessary skill set to start a new project (e.g., updating an IT system) into a terminal.

[0310] 2. The server analyzes employee data and identifies "Employee D," who has successfully completed similar projects in the past, as the project leader.

[0311] 3. The terminal recommends "Employee E" and "Employee F," who have strong development skills and have good project experience with "Employee D" in the past.

[0312] 4. The emotion engine analyzes the user's emotional state and checks whether the user has a positive reaction to the recommended member. If so, the suggestion is presented as is; if not, the option to reselect an alternative member is presented.

[0313] 5. The user checks the recommendations, corrects them if necessary, and then decides on the placement.

[0314] Through this embodiment, enterprises can realize optimal staffing planning that makes the most of employees' characteristics and skills and takes into account users' emotional states, thereby improving the efficiency and performance of the entire organization.

[0315] The processing flow will be explained below.

[0316] Step 1: Data collection

[0317] The server connects to various data sources, such as the personnel management system, personnel evaluation system, and questionnaire system, to collect data on employees' work history, achievements, strengths and weaknesses, characteristics, aspirations, and relationships. Data is collected automatically and periodically via APIs and database queries.

[0318] Step 2: Data Preprocessing

[0319] The server performs preprocessing on the collected data. Specifically, it performs the following processes:

[0320] Data normalization: Standardizing the format of data.

[0321] Imputing missing values: Imputing missing information with estimates or default values.

[0322] Outlier detection and correction: Remove or correct extreme outliers.

[0323] De-duplicate data: Identify duplicate data entries and delete one.

[0324] This creates a clean dataset suitable for analysis.

[0325] Step 3: Characterization and evaluation

[0326] The server analyzes the pre-processed data and evaluates employee traits and skill sets using machine learning algorithms to calculate specific evaluation scores for each employee, such as a leadership score, technical score, and collaboration score.

[0327] Step 4: Training the generative AI model

[0328] The server trains a generative AI model based on the results of the characteristic analysis. It uses past deployment history and its results (e.g., sales increase, project success rate) as training data to build an accurate predictive model. This model predicts the appropriate deployment of employees.

[0329] Step 5: Integrating the Emotion Engine

[0330] The device is equipped with an emotion engine that recognizes the user's emotional state in real time. The emotion engine uses a camera and microphone to analyze the user's facial expressions and tone of voice to identify emotions such as joy, anger, and anxiety.

[0331] Step 6: Fill out your deployment request

[0332] Users use their devices to input specific requirements for a new project or department restructuring (e.g., required skill sets, job titles, and number of people), which are then sent to the server and applied to the generative AI model.

[0333] Step 7: Generating optimal placement plans and emotional adjustment

[0334] The device uses data obtained from the server and a generative AI model to generate an optimal deployment plan. This plan reflects the characteristics and skill sets of employees. Furthermore, an emotion engine analyzes the user's emotional state and fine-tunes the deployment plan accordingly. For example, if the user is feeling anxious, the reason for this can be identified and reflected in the deployment plan.

[0335] Step 8: Present the layout plan

[0336] The terminal presents the generated deployment plan to the user, specifically displaying the message, "Employee A is recommended as the sales department leader, and Employees B and C are optimal team members."

[0337] Step 9: Deployment and Implementation

[0338] The user checks the proposed layout plan and fine-tunes it as necessary. Once the final layout is decided, the plan moves to the implementation stage.

[0339] Step 10: Monitoring the deployment results

[0340] The server monitors organizational performance after deployment, observing and collecting data in real time on things like sales fluctuations, employee satisfaction, and project progress.

[0341] Step 11: Retraining the generative AI model

[0342] The server adjusts the parameters of the generated AI model based on the monitoring results and performs re-learning, thereby improving the accuracy of future deployment plans.

[0343] Through this specific processing step, enterprises can make the most of employee characteristics and skills, as well as the emotional state of users, to improve the efficiency and performance of the entire organization.

[0344] Example 2

[0345] 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."

[0346] Appropriate personnel allocation plans are necessary to maximize employee characteristics and skills and improve overall company efficiency and performance. However, current systems simply base allocations on past data without taking employees' emotional states into account, making it difficult to achieve optimal allocations. In addition, insufficient data preprocessing reduces analysis accuracy. Furthermore, there is no mechanism in place to properly monitor organizational performance after allocation and improve the accuracy of the generative AI model. Therefore, a new system for creating more accurate personnel allocation plans is needed.

[0347] 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.

[0348] In this invention, the server includes: means for collecting data on employee work history, achievements, strengths and weaknesses, characteristics, aspirations, and interpersonal relationships; means for normalizing the collected data, filling in missing values, detecting and correcting outliers, and eliminating duplicate data; means for evaluating employee characteristics and skill sets based on the preprocessed and analyzed data; means for training a generative AI model that predicts employee aptitude and placement based on the analysis results; means for analyzing a user's emotional state in real time and reflecting it in a placement plan; means for generating an optimal personnel placement plan using the trained generative AI model; means for suggesting appropriate project members; and means for monitoring organizational performance after placement and improving the accuracy of the generative AI model. This makes it possible to realize a personnel placement plan that makes the most of employee characteristics and skills and also takes into account the user's emotional state.

[0349] "Employee Data" means data about an employee's work history, achievements, strengths and weaknesses, characteristics, preferences, and relationships.

[0350] "Data collection means" refers to means for extracting necessary employee data from data sources such as personnel management systems, personnel evaluation systems, and employee surveys.

[0351] "Data preprocessing means" refers to means for normalizing collected data, filling in missing values, detecting and correcting outliers, and eliminating duplicate data.

[0352] The "evaluation means" is a means for analyzing employee characteristics and skill sets based on preprocessed data and calculating an evaluation score.

[0353] A "generative AI model" is a model that includes machine learning algorithms to predict optimal employee placement.

[0354] A "model learning means" is a means of adjusting the parameters of a generated AI model based on the analysis results and conducting learning.

[0355] The "emotion analysis means" is a means for analyzing the user's emotional state in real time and reflecting this in the placement plan.

[0356] The "staffing plan generation means" is a means for generating an optimal staffing plan using a trained generative AI model.

[0357] The "project member suggestion means" is a means for recommending suitable project members.

[0358] "Organizational performance monitoring measures" are measures for continuously observing organizational performance after deployment and collecting data.

[0359] The "relearning means" is a means of adjusting the parameters of the generative AI model based on the monitoring results and performing relearning.

[0360] This invention relates to a system that analyzes employee data and generates an optimal personnel allocation plan. In particular, it aims to realize a more accurate personnel allocation plan by incorporating emotion analysis means and taking into account the emotional state of the user.

[0361] Data collection

[0362] The server collects data on employees' work history, achievements, strengths and weaknesses, characteristics, aspirations, and relationships from data sources such as the personnel management system, personnel evaluation system, employee surveys, etc. This data is collected periodically via API and the latest information is stored in the database.

[0363] Data Preprocessing

[0364] The server preprocesses the collected data by normalizing it, imputing missing values, detecting and correcting outliers, and eliminating duplicates. For example, a commonly used tool is the Python pandas library. This produces a clean dataset suitable for subsequent analysis.

[0365] Characterization and evaluation

[0366] The server analyzes the preprocessed data and evaluates each employee's characteristics and skill set. This evaluation is performed using machine learning algorithms, such as the scikit-learn library or TensorFlow, to build a model. The server then calculates an evaluation score for each employee and stores it in a database.

[0367] Training generative AI models

[0368] The server trains a generative AI model based on the analysis results. The training data includes past deployment history and its results (e.g., sales increase, project success rate). The model is built and trained using deep learning libraries such as TensorFlow and PyTorch.

[0369] Emotion engine integration

[0370] The device is equipped with an emotion engine that recognizes the user's emotions. This engine uses facial expression recognition technology (e.g., OpenCV) and natural language processing technology (e.g., Google Cloud Natural Language API) to analyze the user's emotions (e.g., joy, anger, anxiety) in real time as they interact with the system.

[0371] Generate and adjust optimal layout plans

[0372] The device receives input conditions from the user (e.g., details of a new project, required skill sets), and generates an optimal deployment plan using data obtained from the server and the generative AI model. Furthermore, the device reflects the user's emotional state analyzed by the emotion analysis means and fine-tunes the deployment plan. For example, if the user is feeling anxious, the device identifies the cause and presents countermeasure options.

[0373] Presenting the layout plan

[0374] The terminal presents the generated deployment plan to the user, for example, displaying a message such as, "Employee A is recommended as the leader of the sales department because he has a leadership score of 95 and has had excellent sales performance over the past five years. Employees B and C are also ideal team members."

[0375] Placement decision and implementation

[0376] The user reviews the proposed deployment plan, makes adjustments as necessary, and finally decides on the deployment. After the decision is made, the plan is put into action. For example, notifications reflecting the new organizational structure are sent to each employee, and the changes are reflected in related information systems (e.g., time attendance management systems, payroll management systems).

[0377] Monitoring and relearning deployment results

[0378] The server continuously monitors organizational performance after deployment, collecting data such as sales fluctuations, employee satisfaction, and project progress, and uses this data to adjust the parameters of the generative AI model. For example, the results can be visualized on a dashboard, and re-training can be performed to improve the accuracy of future deployment plans.

[0379] Specific examples

[0380] Example 1: Launching a new sales department

[0381] 1. A user enters the required skill sets and job titles to launch a new sales department into a terminal.

[0382] 2. The server analyzes data on all employees and identifies suitable candidates with strong sales skills and leadership abilities.

[0383] 3. The device suggests "Employee A" as a potential sales department leader and recommends "Employee B" and "Employee C" as team members.

[0384] 4. The emotion analysis means analyzes the user's reactions in real time, and if anxiety is high, identifies the reason and provides feedback.

[0385] 5. The user finally checks the revised deployment plan and decides on the deployment.

[0386] Example 2: Suggesting talent for a new project

[0387] 1. A user inputs the necessary skill set to start a new project (e.g., updating an IT system) into a terminal.

[0388] 2. The server analyzes employee data and identifies "Employee D," who has successfully completed similar projects in the past, as the project leader.

[0389] 3. The terminal recommends "Employee E" and "Employee F," who have strong development skills and have good project experience with "Employee D" in the past.

[0390] 4. The emotion analysis means analyzes the user's emotional state and checks whether they have a positive reaction to the recommended member. If they have a positive reaction, they will continue to recommend them, but if they have a negative reaction, they will re-evaluate and select alternative members.

[0391] 5. The user checks the recommendations, corrects them if necessary, and then decides on the placement.

[0392] Through this embodiment, enterprises can make the most of employees' characteristics and skills and realize optimal staffing planning that takes into account users' emotional states, thereby improving the efficiency and performance of the entire organization.

[0393] The flow of the identification process in the second embodiment will be described with reference to FIG.

[0394] Step 1:

[0395] The server collects data about employees' work history, achievements, strengths and weaknesses, characteristics, aspirations, and relationships from data sources such as a personnel management system, personnel evaluation system, and employee surveys. This is done using HTTP requests via APIs, with the input being the API endpoint and authentication information, and the output being a JSON-formatted response with employee data. For example, the server periodically accesses each endpoint, retrieves the required information, and stores it in a database.

[0396] Step 2:

[0397] The server preprocesses the collected data. Specifically, it first normalizes the data and unifies data in different formats. Next, it imputes missing values, for example, by using mean imputation or a predictive model. Statistical methods (e.g., Z-score) are used to detect outliers, and these are then corrected or removed. Finally, it removes duplicate data based on a unique identifier (e.g., employee ID). The input is the collected raw data, and the output is a clean dataset.

[0398] Step 3:

[0399] The server analyzes the preprocessed data and evaluates each employee's characteristics and skill set. This evaluation uses machine learning algorithms (random forest, SVM, neural network). The input is the preprocessed, clean dataset, and the output is an evaluation score for each employee (e.g., leadership score, technical score). Specifically, the server builds a model using scikit-learn or TensorFlow, inputs the data, and calculates the score.

[0400] Step 4:

[0401] The server trains a generative AI model based on the analysis results. Past deployment history and its results (e.g., sales increase rate, project success rate) are used as training data. The input is the evaluation score and past deployment history data, and the output is the trained generative AI model. Specifically, TensorFlow and PyTorch are used to train a deep learning model and find the optimal parameters.

[0402] Step 5:

[0403] The device integrates an emotion engine that analyzes the user's emotions in real time. This engine uses facial expression recognition and natural language processing technologies to analyze the emotions (e.g., joy, anger, anxiety) when the user interacts with the system. The input is the user's facial image and input text, and the output is the analyzed emotional state. For example, facial expressions are recognized using OpenCV, and text is analyzed using the Google Cloud Natural Language API.

[0404] Step 6:

[0405] The terminal receives input conditions from the user (e.g., details of a new project, required skill sets) and generates an optimal deployment plan using data obtained from the server and the generative AI model. Furthermore, the deployment plan is fine-tuned to reflect the user's emotional state analyzed by the sentiment analysis means. The input is a prompt from the user and the results of sentiment analysis, and the output is an optimal personnel deployment plan. For example, the terminal receives user input, sends a request to the server, and receives the optimal deployment plan. At that time, the sentiment analysis results are fed back to adjust the plan.

[0406] Step 7:

[0407] The terminal presents the generated deployment plan to the user. The input is the generated deployment plan, and the output is a display screen that the user can check. For example, it displays specific content such as, "Employee A is recommended as the leader of the sales department because he has a leadership score of 95 and has excellent sales performance over the past five years."

[0408] Step 8:

[0409] The user reviews the presented deployment plan and makes adjustments as necessary. Finally, the deployment is decided. After the decision is made, the plan is put into action. The input is the user's feedback and final decision, and the output is the implementation plan. For example, the user reviews the deployment plan and finally presses the approval button to finalize the plan.

[0410] Step 9:

[0411] The server continuously monitors organizational performance after deployment. It collects data such as sales fluctuations, employee satisfaction, and project progress, and uses this data to adjust the parameters of the generative AI model. The input is the post-deployment performance data, and the output is the adjusted generative AI model. For example, it periodically updates the dashboard, checks the monitoring results, and re-trains as necessary.

[0412] (Application example 2)

[0413] 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."

[0414] Creating optimal staffing plans that take into account information including employee characteristics, skills, and emotional states is extremely complex and cannot be easily achieved with conventional systems. Therefore, in order to maximize organizational efficiency and performance, it is necessary to analyze users' emotional states in real time and reflect them in staffing plans.

[0415] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 2 is realized by the following means.

[0416] In this invention, the server includes a means for collecting data on employee work history, achievements, strengths and weaknesses, characteristics, aspirations, and interpersonal relationships; a means for preprocessing and analyzing the collected data; and a means for training a generative AI model that predicts employee aptitude and placement based on the analysis results. This makes it possible to evaluate employee characteristics and skill sets and develop optimal placement plans. Furthermore, by integrating an emotion engine and including a means for analyzing the user's emotional state in real time and a means for adjusting the generated placement plan based on the emotion engine, it is possible to generate placement plans that are more in line with the user's intentions and emotions. Furthermore, by monitoring organizational performance after placement and improving the accuracy of the generative AI model, it is possible to improve placement accuracy in subsequent placements.

[0417] An "employee" is someone who belongs to a company or organization and performs their duties.

[0418] "Work history" refers to the job titles, positions, and employment history of an employee.

[0419] "Results" refers to the achievements and goal attainment achieved by an employee during their employment.

[0420] "Strengths and weaknesses" refer to the skills and abilities of individual employees, particularly those in which they excel and those in which they need improvement.

[0421] "Characteristics" refer to an employee's personality, behavioral patterns, communication style, etc.

[0422] "Hope" refers to an employee's desired working conditions, career path, placement, and other requests.

[0423] "Interpersonal relationships" refers to interactions between employees and relationships within the workplace.

[0424] "Data collection tools" refer to methods and systems for obtaining various information about employees.

[0425] "Preprocessing and analysis methods" refer to the processes and tools used to convert collected raw data into an analyzable format and remove unnecessary data.

[0426] A "generative AI model" is an artificial intelligence model trained using machine learning algorithms to make predictions and optimizations.

[0427] A "learning tool" is a method or algorithm that trains a generative AI model based on data to improve its accuracy.

[0428] An "optimal staffing plan" is a plan that allocates employees in the most efficient and effective way, taking into account their skills, characteristics, and emotional state.

[0429] A "project member suggestion tool" is a method or system that recommends employees with the skills and characteristics required for a particular project.

[0430] "Monitoring measures" refer to methods and tools for continuously observing and collecting data on the results and status of employees after placement.

[0431] An "emotion engine" is a technology that analyzes a user's emotional state in real time and adjusts the system's behavior based on the results.

[0432] The "adjustment means" refers to a method or system for optimizing the generated placement plan based on information obtained from the emotion engine.

[0433] This invention is a system that analyzes employee information and generates optimal personnel allocation plans, and by combining it with an emotion engine, provides allocation plans that take into account the emotional state of the user. The main components of the system include a server, a terminal, and a user.

[0434] Server Features

[0435] The server first collects data about employees, including work history, achievements, strengths and weaknesses, characteristics, aspirations, and relationships, from data sources such as the personnel management system, personnel evaluation system, and employee surveys. This data is updated regularly, ensuring that the latest information is always analyzed.

[0436] After collecting the data, the server preprocesses the data by normalizing it, imputing missing values, detecting and correcting outliers, removing duplicates, etc. This process creates a clean dataset suitable for analysis.

[0437] Using the preprocessed data, the characteristics and skill sets of each employee are evaluated, and a machine learning algorithm (e.g., RandomForestClassifier) ​​is used to build a generative AI model, which is trained using past deployment history and its results (e.g., sales increase, project success rate).

[0438] Device Features

[0439] The device is equipped with an emotion engine that analyzes emotions (e.g., joy, anger, anxiety) expressed by users in real time as they operate the system. Upon receiving input from the user (e.g., details of a new project, required skill sets), the system generates an optimal deployment plan using data obtained from the server and a generative AI model.

[0440] The generated placement plan is fine-tuned based on the analysis results of the emotion engine. The device then suggests the most suitable project members and presents them to the user. The user can review this, make adjustments as necessary, and decide on the final placement.

[0441] User Roles

[0442] Users input new projects and required skill sets through their devices, review the proposed deployment plan, and make adjustments or final decisions. The system analyzes the user's emotional state in real time, and adjusts the deployment plan based on their feedback.

[0443] Hardware and software used

[0444] The hardware used includes a server that collects and processes data, a terminal that interfaces with the emotion engine, and a user interface. The software includes a database system (e.g., HRDatabase), machine learning algorithms (e.g., RandomForestClassifier), and an emotion engine (e.g., EmotionEngine).

[0445] Specific examples

[0446] For example, a user can input the skill sets and job titles required to set up a new assembly line. The system then analyzes employee data and sensor data to suggest suitable employees. Based on the user's emotional response, the emotion engine makes real-time adjustments and presents the optimal placement plan.

[0447] Prompt Sentence Examples

[0448] "Nominate candidates for new assembly line leaders. Required skill sets include electrical engineering, robotics, and leadership."

[0449] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[0450] Processing Steps

[0451] Step 1: Data collection

[0452] The server collects data on employees' work history, achievements, strengths and weaknesses, characteristics, aspirations, and relationships from data sources such as a personnel management system, a personnel evaluation system, and employee surveys.

[0453] Input: Raw data from each data source.

[0454] Data processing and calculation: Query the database and extract the required information.

[0455] Output: A collection of collected raw data.

[0456] Step 2: Data Preprocessing

[0457] The server preprocesses the collected data, specifically normalizing the data, imputing missing values, detecting and correcting outliers, and eliminating duplicate data.

[0458] Input: The raw data collected.

[0459] Data processing and calculation: Apply data cleansing algorithms to shape the data.

[0460] Output: A clean dataset.

[0461] Step 3: Characterization and evaluation

[0462] The server analyzes the pre-processed data and evaluates each employee's characteristics and skill set using machine learning algorithms to calculate an evaluation score for each employee.

[0463] Input: A clean dataset.

[0464] Data processing and calculation: Feature extraction and evaluation score calculation (e.g., using RandomForestClassifier).

[0465] Output: Evaluation score for each employee.

[0466] Step 4: Training the generative AI model

[0467] The server trains a generative AI model based on the analysis results. This model includes an algorithm for predicting optimal employee placement, using past placement history and results as training data.

[0468] Input: Employee evaluation scores and past placement history data.

[0469] Data processing and calculation: Execute the model training process.

[0470] Output: A trained generative AI model.

[0471] Step 5: Integrating the Emotion Engine

[0472] The device is equipped with an emotion engine that recognizes the user's emotions and analyzes the emotions expressed when the user operates the system in real time.

[0473] Input: Facial expressions and behavioral data during user operation.

[0474] Data processing and computation: Application of emotion recognition algorithms.

[0475] Output: Real-time analysis of the user's emotional state.

[0476] Step 6: Generate and refine optimal layout plans

[0477] The device receives input conditions from the user and generates an optimal placement plan using data obtained from the server and the generative AI model.The device then fine-tunes the placement plan by reflecting the user's emotional state analyzed by the emotion engine.

[0478] Input: User input conditions, trained generative AI model, and emotion engine analysis results.

[0479] Data processing and calculation: Implementing optimal placement algorithms and reflecting emotional states.

[0480] Output: The adjusted optimal placement plan.

[0481] Step 7: Present the layout plan

[0482] The terminal presents the generated placement plan to the user.

[0483] Input: The adjusted optimal placement plan.

[0484] Data processing and calculation: Visualization and presentation of layout plans.

[0485] Output: Deployment plan information for the user.

[0486] Step 8: Deployment and Implementation

[0487] The user checks the proposed deployment plan, makes adjustments as necessary, and finally decides on the deployment. After the decision is made, the plan is put into action.

[0488] Input: Proposed layout plan.

[0489] Data processing and calculation: Final confirmation and adjustment by the user.

[0490] Output: Final placement decision and implementation.

[0491] Step 9: Monitoring deployment results and retraining

[0492] The server monitors organizational performance after deployment, continuously observing and collecting data on sales fluctuations, employee satisfaction, project progress, etc. Based on the results of this monitoring, the parameters of the generative AI model are adjusted and re-trained.

[0493] Input: Post-placement organizational outcome data.

[0494] Data processing and calculation: Analyzing performance data and retraining the generated AI model.

[0495] Output: An updated generative AI model.

[0496] Examples of concrete examples and prompts

[0497] A concrete example would be to input the skill sets and job titles required to set up a new assembly line. Use the following prompt:

[0498] "Nominate candidates for new assembly line leaders. Required skill sets include electrical engineering, robotics, and leadership."

[0499] By inputting this prompt, the system generates an optimal placement plan and makes adjustments that take into account the user's emotional state.

[0500] 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.

[0501] 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.

[0502] 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.

[0503] [Second embodiment]

[0504] FIG. 3 shows an example of the configuration of a data processing system 210 according to the second embodiment.

[0505] 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.

[0506] 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).

[0507] 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.

[0508] 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.

[0509] 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).

[0510] 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.

[0511] 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.

[0512] 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.

[0513] 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.

[0514] In the smart glasses 214, the reception output process is performed by the processor 46. A reception output program 60 is stored in the storage 50. The processor 46 reads the reception output program 60 from the storage 50 and executes the read reception output program 60 on the RAM 48. The reception output process is realized by the processor 46 operating as the control unit 46A in accordance with the reception output program 60 executed on the RAM 48.

[0515] 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."

[0516] This invention relates to a system that analyzes employee information and generates an optimal personnel allocation plan. This system collects data such as employees' work history, achievements, strengths and weaknesses, characteristics, aspirations, and relationships, and trains a generative AI model based on that data. The trained generative AI model is used to achieve efficient personnel allocation in companies and organizations. Specific embodiments for implementing this system are described below.

[0517] Data collection

[0518] The server automatically collects data on employees' work history, achievements, strengths and weaknesses, characteristics, aspirations, and relationships from personnel management systems, evaluation systems, employee surveys, etc. This allows a wide range of information to be obtained in a timely manner.

[0519] Data Preprocessing

[0520] The server preprocesses the collected data, normalizing it, filling in missing values, correcting outliers, and detecting and deleting duplicate data, enabling highly accurate analysis.

[0521] Data analysis and model training

[0522] The server analyzes the preprocessed data and evaluates the characteristics of each employee. Based on the analysis results, it trains a generative AI model, which contains an algorithm for predicting the optimal placement of employees.

[0523] Generate optimal placement plans

[0524] The terminal receives input requirements from the user (e.g., details of a new project, required skill sets). It then uses the analytical data obtained from the server and the generative AI model to generate an optimal staffing plan. The generated staffing plan is then presented to the user.

[0525] Recommended talent suggestions

[0526] The device will suggest suitable personnel for specific projects or department restructuring, allowing users to easily identify the most suitable members and achieve efficient project management and department restructuring.

[0527] Monitoring and relearning deployment results

[0528] The server monitors organizational performance after deployment. It periodically collects data such as sales fluctuations and employee satisfaction to evaluate the effectiveness of the deployment plan. Based on the results of this evaluation, it adjusts the parameters of the generative AI model and performs re-learning. This improves the accuracy of future deployment plans.

[0529] Specific examples

[0530] Example 1: Launching a new sales department

[0531] 1. A user enters the required skill sets and job titles to launch a new sales department into a terminal.

[0532] 2. The server analyzes data on all employees and identifies suitable candidates with strong sales skills and leadership abilities.

[0533] 3. The device suggests "Employee A" as a potential sales department leader and recommends "Employee B" and "Employee C" as team members.

[0534] 4. The user checks the device recommendations and decides on the placement.

[0535] Example 2: Suggesting talent for a new project

[0536] 1. A user inputs the necessary skill set to start a new project (e.g., updating an IT system) into a terminal.

[0537] 2. The server analyzes employee data and identifies "Employee D," who has successfully completed similar projects in the past, as the project leader.

[0538] 3. The terminal recommends "Employee E" and "Employee F," who have strong development skills and have good project experience with "Employee D" in the past.

[0539] 4. The user checks the recommendations from the device, corrects them if necessary, and decides on the placement.

[0540] Through this implementation, companies can maximize the skills and attributes of their employees, improving efficiency and performance across the organization.

[0541] The processing flow will be explained below.

[0542] Step 1: Data collection

[0543] The server collects data on employees' work history, achievements, strengths and weaknesses, characteristics, aspirations, and relationships from data sources such as personnel management systems, personnel evaluation systems, employee surveys, etc. This data is scheduled to be collected automatically on a regular basis.

[0544] Step 2: Data Preprocessing

[0545] The server preprocesses the collected data, specifically by standardizing the data format (normalization), filling in missing values, detecting and correcting outliers, and eliminating duplicate data, creating a clean dataset suitable for analysis.

[0546] Step 3: Characterization and evaluation

[0547] The server analyzes the pre-processed data and evaluates employee traits (e.g., leadership ability, collaboration) and skill sets (e.g., coding skills, sales skills). This analysis uses machine learning algorithms to calculate a specific evaluation score for each employee.

[0548] Step 4: Training the generative AI model

[0549] The server trains a generative AI model based on the analysis results. This model includes an algorithm for predicting optimal employee placement. Past placement history and its results (e.g., sales increase, project success rate) are used as training data.

[0550] Step 5: Fill out your deployment request

[0551] Users use their devices to input specific requirements for new projects or department restructuring (e.g., required skills, number of people, job titles), and this request information is sent to the generative AI model.

[0552] Step 6: Generate optimal layout plans

[0553] The device generates an optimal deployment plan using data obtained from the server and a generative AI model. Specifically, it selects the most suitable personnel based on the specified conditions, taking into account the characteristics and skill sets of each employee.

[0554] Step 7: Present the layout plan

[0555] The device presents the generated deployment plan to the user. For example, it displays a specific recommendation such as, "Employee A is recommended as the leader of the sales department, and Employees B and C are optimal as team members."

[0556] Step 8: Deployment and Implementation

[0557] The user checks the proposed deployment plan, modifies it as necessary, and finalizes the deployment. After the plan is finalized, it is put into practice.

[0558] Step 9: Monitoring the deployment results

[0559] The server monitors organizational performance after deployment, specifically by continuously observing and collecting data on sales fluctuations, employee satisfaction, project progress, etc.

[0560] Step 10: Retraining the generative AI model

[0561] Based on the monitoring results, the server adjusts the parameters of the generated AI model and performs re-learning, thereby improving the accuracy of future deployment plans.

[0562] This series of steps results in a system that makes the most of the characteristics and skills of your employees, improving efficiency and performance across the organization.

[0563] Example 1

[0564] 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."

[0565] Currently, human resource allocation planning in companies is often based on experience and intuition, which can result in less than optimal allocation. Furthermore, employee information is scattered across multiple systems, making it difficult to integrate and normalize the data. Furthermore, there is no system in place to centrally monitor employee performance after allocation and incorporate feedback. A system that can solve these issues and achieve efficient and effective human resource allocation is needed.

[0566] 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.

[0567] In this invention, the server includes: means for collecting information on employees' work history, achievements, strengths and weaknesses, characteristics, aspirations, and interpersonal relationships; means for normalizing the collected information, filling in missing values, correcting outliers, and detecting and deleting duplicate data; and means for analyzing the preprocessed information, evaluating employee characteristics, and training a generative AI model based on the analysis results. This enables accurate collection and analysis of detailed employee information and the generation of optimal personnel allocation plans based on the results. Additionally, by monitoring organizational performance after allocation, adjusting the parameters of the generative AI model, and retraining, the accuracy of the allocation plan can be continuously improved. Furthermore, by suggesting appropriate project members for specific projects or department restructuring, efficient personnel management is possible.

[0568] Employee's work history

[0569] This is information that indicates the job content and experience that an employee has had in the past.

[0570] "Results"

[0571] This is information that shows the specific achievements and accomplishments that an employee has achieved through their work.

[0572] "Strengths and Weaknesses"

[0573] This is information that indicates an employee's specialized skills and abilities, as well as any deficiencies.

[0574] "Characteristics"

[0575] This is information that indicates an employee's personality, behavioral characteristics, and thought patterns.

[0576] "Hope"

[0577] This is information that indicates the job content, career path, and working conditions that an employee desires in the future.

[0578] "Human relationships"

[0579] This is information that indicates the relationships that an employee has with other employees within the company.

[0580] "Normalization"

[0581] It is the process of standardizing collected data based on certain criteria.

[0582] "Missing value imputation"

[0583] is the process of filling in missing values ​​in a dataset with appropriate values.

[0584] "Correction of outliers"

[0585] is the process of detecting outliers in a data set and correcting them to appropriate values.

[0586] "Detecting and Removing Duplicate Data"

[0587] is the process of detecting duplicate data within a dataset and removing unnecessary duplicate data.

[0588] "Generative AI model"

[0589] is an algorithm that is generated using machine learning and deep learning techniques based on collected data to make predictions about personnel placement and other matters.

[0590] "Preprocessing"

[0591] This is a series of data processing processes carried out to prepare collected data in a form that makes it easier to analyze.

[0592] "analysis"

[0593] It is the process of analysis that uses collected and preprocessed data to reveal characteristics and relationships.

[0594] "Optimal personnel allocation planning"

[0595] It is a plan that shows the most efficient allocation of employees to departments and projects, taking into account their characteristics and skills and the company's requirements.

[0596] "Project member suggestions"

[0597] is the process of recommending employees who are best suited for a particular project.

[0598] "monitoring"

[0599] This is the process of continuously observing and recording the performance of organizations and employees after deployment.

[0600] "Parameter Adjustment"

[0601] This is the process of changing internal variables and settings to improve the predictive accuracy of a generative AI model.

[0602] "Relearning"

[0603] This is the process of retraining an existing generative AI model with new data to improve its predictive accuracy.

[0604] This invention is a system for efficiently allocating personnel to a company. The system collects detailed information about employees, analyzes and learns from that data, and then generates and proposes optimal personnel allocation plans.

[0605] To implement this system, the following hardware and software are used.

[0606] Hardware and software used

[0607] Server: Collects data, preprocesses, analyzes, and trains AI models.

[0608] Human Resources Management System Example: "Human Resources Management System"

[0609] Database example: "SQL Database"

[0610] Example of software for model training: "TensorFlow"

[0611] Examples of data preprocessing software: "Python", "pandas", "scikit-learn"

[0612] Terminal: Receives input from the user and presents analysis results and deployment plans.

[0613] Example of interface software: "Web browser"

[0614] Data collection

[0615] The server collects employee information from various internal personnel management systems, evaluation systems, and survey tools. It uses APIs to seamlessly integrate data. For example, an API call retrieves information about work history and achievements from a personnel management system.

[0616] Data Preprocessing

[0617] The server normalizes the collected data, fills in missing values, corrects outliers, and detects and removes duplicate data, creating a dataset suitable for analysis. Specifically, the server cleans the data using the Python pandas library and scales the numerical data using scikit-learn's StandardScaler.

[0618] Data analysis and model training

[0619] The server uses the preprocessed data to evaluate the characteristics of each employee. Based on these evaluation results, it trains a generative AI model. TensorFlow is used to train the model. The server saves the trained model and uses it to generate future placement plans.

[0620] Generate optimal staffing plans

[0621] The terminal receives input conditions from the user. The user enters the details of a new project and the required skill set into the terminal. For example, the user enters a prompt such as "We are looking for a leader for a new IT project." The terminal then sends this to the server, and generates an optimal staffing plan using the analytical data obtained from the server and the generative AI model. The results are displayed to the user through a GUI.

[0622] Recommended talent suggestions

[0623] The terminal suggests suitable project members for specific projects or department restructuring. The user inputs a prompt such as "Please recommend the best employees for a new project." The terminal uses a generative AI model to generate a list of recommended personnel and presents it to the user.

[0624] Monitoring and relearning deployment results

[0625] The server monitors organizational performance after deployment. It analyzes sales data and employee satisfaction to evaluate the effectiveness of the generative AI model. For example, it uses new data obtained from sales data and employee satisfaction surveys to adjust the model parameters and retrain. This improves the accuracy of future deployment plans.

[0626] Specific examples

[0627] Example 1: A user inputs the "skill set and job title required to launch a new sales department" into a terminal. The server identifies personnel with sales skills and leadership skills, and the terminal recommends "Employee A" and "Employee B."

[0628] Example 2: The user inputs "the leader and development team of a new IT project" into the terminal. The server identifies "Employee D" who has had successful projects in the past, and the terminal recommends "Employee D" and "Employee E."

[0629] Through this system, companies can make the most of the skills and attributes of their employees, improving efficiency and performance across the organization.

[0630] The flow of the identification process in the first embodiment will be described with reference to FIG.

[0631] Program processing flow

[0632] Step 1:

[0633] The server collects information on employees' work history, achievements, strengths and weaknesses, characteristics, aspirations, and relationships from various systems (human resource management systems, evaluation systems, survey tools, etc.). Specifically, it connects using an "API" and stores the acquired information in an "SQL database."

[0634] Input: Employee information from HR management systems, appraisal systems, and survey tools.

[0635] Output: Employee information in a SQL database.

[0636] Step 2:

[0637] The server preprocesses employee information stored in an SQL database using Python and pandas to normalize data, impute missing values, correct outliers, and detect and remove duplicate data.

[0638] Input: Collected employee information on a SQL database.

[0639] Output: Preprocessed employee information.

[0640] Step 3:

[0641] The server analyzes the preprocessed data, assessing employee characteristics and using the results to train a generative AI model using TensorFlow, which includes an algorithm for predicting staffing levels.

[0642] Input: Preprocessed employee information.

[0643] Output: A trained generative AI model.

[0644] Step 4:

[0645] The terminal receives input from the user, such as details of a new project and the required skill set, and sends it to the server, for example, by entering a prompt statement such as "We are looking for a leader for a new IT project."

[0646] Input: A prompt from the user.

[0647] Output: Analysis conditions passed to the generative AI model.

[0648] Step 5:

[0649] The server receives a prompt from the user and generates an optimal staffing plan using the preprocessed employee information and the trained generative AI model, such as "Identify employees with the skills required to launch a new sales department." The generated staffing plan is then sent back to the terminal.

[0650] Input: Analysis conditions from the terminal.

[0651] Output: Optimal staffing plan.

[0652] Step 6:

[0653] The terminal displays the allocation plan sent from the server to the user on a GUI, allowing the user to determine the optimal personnel allocation based on this information.

[0654] Input: The deployment plan sent by the server.

[0655] Output: A layout plan display provided to the user.

[0656] Step 7:

[0657] After the deployment plan is implemented, the server periodically monitors organizational outcomes such as sales data and employee satisfaction, and obtains new data from Google Analytics and internal databases to evaluate the accuracy of the generative AI model.

[0658] Input: Organizational outcomes data.

[0659] Output: The evaluated generative AI model.

[0660] Step 8:

[0661] The server adjusts the parameters of the generative AI model based on the monitoring results and performs re-learning, thereby improving the accuracy of future personnel allocation plans.

[0662] Input: An evaluated generative AI model.

[0663] Output: The retrained generative AI model.

[0664] (Application example 1)

[0665] 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."

[0666] In logistics centers, proper employee allocation is extremely important for efficient business operations. However, considering the skill sets, experience, and preferences of multiple employees at once and assigning the most suitable personnel is a significant burden for managers. Furthermore, manual allocation planning is prone to errors and bias, which can reduce operational efficiency. Furthermore, it is difficult to obtain feedback on work results and employee satisfaction after allocation. Conventional methods have limited means of efficiently resolving these issues.

[0667] 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.

[0668] In this invention, the server includes: means for collecting data on employee work history, achievements, strengths and weaknesses, characteristics, preferences, and interpersonal relationships; means for preprocessing and analyzing the collected data; means for training a generative AI model that predicts employee aptitude and placement based on the analysis results; means for generating an optimal personnel placement plan using the trained generative AI model; means for inputting required skill sets and job title requirements; means for analyzing employee data within the logistics center and suggesting optimal personnel placement; and means for monitoring organizational performance after placement and improving the accuracy of the generative AI model. This enables optimal personnel placement in logistics centers that takes into account employee skill sets and preferences, thereby improving business efficiency. By monitoring feedback after placement, continuous model improvement and efficiency can be expected.

[0669] "Employee work history" refers to each employee's past work experience and the history of the positions they have held.

[0670] "Results" refers to the results or accomplishments that an employee achieves in their work.

[0671] "Strengths and weaknesses" refer to the strengths and weaknesses of an employee in specific skills and abilities.

[0672] "Traits" refer to an employee's personality, behavioral patterns, aptitude for work, and other characteristics.

[0673] "Aspirations" refers to the hopes and demands that employees have about their work and the career path they desire in the future.

[0674] "Human relationships" refers to the relationships between employees, mutual trust, and cooperative systems.

[0675] "Means of collecting data" refers to the methods and tools used to automatically or manually capture the required data.

[0676] "Preprocessing" refers to the process of converting collected data into an analyzable form.

[0677] "Analysis" refers to the process of evaluating employee characteristics and suitability based on pre-processed data.

[0678] A "generative AI model" refers to an artificial intelligence model trained based on employee data.

[0679] "Optimal personnel allocation planning" refers to an allocation plan that makes the most of employees' skills and characteristics and achieves efficient business operations.

[0680] A "skill set" refers to the collection of techniques and knowledge required to perform a specific job.

[0681] "Position" refers to the job or position assigned to an employee within an organization.

[0682] "Means for inputting requirements" refers to the methods and tools for inputting the necessary conditions and skills to realize the deployment plan into the system.

[0683] "Means for suggesting personnel placement" refers to systems or algorithms that recommend the most suitable personnel based on the results of analysis.

[0684] "Organizational results" refers to the performance and achievements of employees and the organization as a whole after deployment.

[0685] "Monitoring" refers to the activity of regularly observing organizational results and employee performance and collecting data.

[0686] This invention relates to a system for realizing efficient personnel allocation in logistics centers. The system uses a generative AI model to collect and analyze data on employees' work history, achievements, strengths and weaknesses, characteristics, aspirations, and relationships, and to generate optimal allocation plans.

[0687] Data collection

[0688] The server collects data on employees' work history, achievements, strengths and weaknesses, characteristics, aspirations, and relationships from personnel management systems, evaluation systems, employee surveys, etc. This makes it possible to obtain a wide range of information in a timely manner.

[0689] Data Preprocessing

[0690] The server performs preprocessing on the collected data, such as normalizing it, filling in missing values, correcting outliers, and detecting and deleting duplicate data, enabling highly accurate analysis.

[0691] Data analysis and model training

[0692] The server analyzes the preprocessed data and evaluates the characteristics of each employee. The results of this analysis are used to train a generative AI model, which includes an algorithm for predicting optimal employee placement.

[0693] Generate optimal placement plans

[0694] The terminal receives input conditions from the user (e.g., details of the new project, required skill set, job title), and generates an optimal personnel allocation plan using analytical data obtained from the server and a generative AI model. The generated allocation plan is then presented to the user.

[0695] Recommended talent suggestions

[0696] The device will suggest suitable personnel for specific projects or department restructuring, allowing users to easily identify the most suitable members and achieve efficient project management and department restructuring.

[0697] Monitoring and relearning deployment results

[0698] The server monitors organizational performance after deployment. It periodically collects data such as sales fluctuations and employee satisfaction to evaluate the effectiveness of the deployment plan. Based on the results of this evaluation, it adjusts the parameters of the generative AI model and performs re-learning. This improves the accuracy of future deployment plans.

[0699] Specific examples

[0700] Example: Suggesting talent for a new logistics project

[0701] 1. A user enters into a terminal the required skill set and job title to start a new project (e.g., a large-scale inventory cleanup).

[0702] 2. The server analyzes employee data to identify employees who have successfully completed similar projects in the past.

[0703] 3. The terminal recommends employees with forklift driving skills and experience in sorting goods.

[0704] 4. The user checks the recommendations from the device, corrects them if necessary, and decides on the placement.

[0705] Prompt Sentence Examples

[0706] We need people who can operate forklifts and sort goods.

[0707] This embodiment allows distribution center managers to maximize employee skill sets and characteristics, realize efficient staffing, and continuously improve the model through post-deployment feedback.

[0708] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[0709] Step 1:

[0710] The server collects employee data (work history, achievements, strengths and weaknesses, characteristics, aspirations, relationships).

[0711] Inputs: Data from HR management systems, appraisal systems, and employee surveys.

[0712] Specific operation: Retrieve the necessary information from the database via API.

[0713] Output: A set of collected employee data.

[0714] Step 2:

[0715] The server pre-processes the collected data.

[0716] Input: Employee data collected in Step 1.

[0717] Specific operations: data normalization, missing value imputation, outlier correction, duplicate data detection and removal.

[0718] Output: A preprocessed and clean dataset.

[0719] Step 3:

[0720] The server analyzes the pre-processed data and evaluates the characteristics of each employee.

[0721] Input: The preprocessed data from step 2.

[0722] What it does: Uses machine learning algorithms to assess skills, experience, and attributes.

[0723] Output: Evaluation results for each employee.

[0724] Step 4:

[0725] The server trains the generative AI model based on the evaluation results.

[0726] Input: The employee's evaluation results from step 3.

[0727] Specific operation: The evaluation results are fed into the AI ​​to optimize the model parameters.

[0728] Output: A trained generative AI model.

[0729] Step 5:

[0730] The terminal receives input conditions (required skill set and job title requirements) from the user.

[0731] Input: A prompt from the user (e.g., "We need people who can drive forklifts and sort goods").

[0732] Specific operation: Obtain conditions from input forms or voice input.

[0733] Output: User-specified skillset and job title requirements.

[0734] Step 6:

[0735] The server generates an optimal personnel allocation plan using the analytical data acquired and the generated AI model.

[0736] Input: The user input conditions from step 5 and the generative AI model from step 4.

[0737] Specific operation: Input the user's requirements into the model and list suitable candidates.

[0738] Output: Optimal staffing plan.

[0739] Step 7:

[0740] The terminal presents the user with the optimal staffing plan.

[0741] Input: The staffing plan generated in step 6.

[0742] Specific actions: Display the plan via the user interface.

[0743] Output: Staffing plan presented to the user.

[0744] Step 8:

[0745] The server monitors organizational performance after deployment and collects data.

[0746] Input: Outcome data such as sales data, employee satisfaction data, etc.

[0747] Specific actions: Regularly collect performance data and analyze trends.

[0748] Output: Monitored outcome data.

[0749] Step 9:

[0750] The server adjusts the parameters of the generated AI model based on the monitoring results and performs re-learning.

[0751] Input: Outcome data from Step 8.

[0752] Specific operations: Readjust the parameters of the AI ​​model based on the performance data and repeat the learning process.

[0753] Output: An improved generative AI model.

[0754] 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.

[0755] This invention relates to a system that analyzes employee information and generates optimal personnel allocation plans. In particular, by combining it with an emotion engine, it takes into account the emotional state of the user to realize more accurate personnel allocation plans.

[0756] Data collection

[0757] The server collects data on employees' work history, achievements, strengths and weaknesses, characteristics, aspirations, and interpersonal relationships from data sources such as personnel management systems, personnel evaluation systems, employee surveys, etc. This data collection is carried out periodically, making it possible to analyze based on the latest information.

[0758] Data Preprocessing

[0759] The server preprocesses the collected data by normalizing it, imputing missing values, detecting and correcting outliers, and eliminating duplicate data, creating a clean dataset suitable for analysis.

[0760] Characterization and evaluation

[0761] The server analyzes the pre-processed data and evaluates each employee's characteristics and skill set using machine learning algorithms to calculate an evaluation score for each employee.

[0762] Training generative AI models

[0763] The server trains a generative AI model based on the analysis results. This model includes an algorithm for predicting optimal employee placement. Past placement history and its results (e.g., sales increase, project success rate) are used as training data.

[0764] Emotion engine integration

[0765] The device is equipped with an emotion engine that recognizes the user's emotions. This engine analyzes the emotions (e.g., joy, anger, anxiety) expressed when the user interacts with the system in real time.

[0766] Generate and adjust optimal layout plans

[0767] The device receives input conditions from the user (e.g., details of a new project, required skill sets), and generates an optimal deployment plan using data obtained from the server and a generative AI model.Furthermore, the device fine-tunes the deployment plan by reflecting the user's emotional state analyzed by an emotion engine.

[0768] Presenting the layout plan

[0769] The terminal presents the generated allocation plan to the user, for example, displaying a message such as, "Employee A is recommended as the leader of the sales department, and Employees B and C are optimal as team members."

[0770] Placement decision and implementation

[0771] The user checks the proposed deployment plan, makes adjustments as necessary, and finally decides on the deployment. After the decision is made, the plan is put into action.

[0772] Monitoring and relearning deployment results

[0773] The server monitors organizational performance after deployment, continuously observing and collecting data on factors such as sales fluctuations, employee satisfaction, and project progress. Based on the results of this monitoring, the parameters of the generative AI model are adjusted and re-learned, improving the accuracy of future deployment plans.

[0774] Specific examples

[0775] Example 1: Launching a new sales department

[0776] 1. A user enters the required skill sets and job titles to launch a new sales department into a terminal.

[0777] 2. The server analyzes data on all employees and identifies suitable candidates with strong sales skills and leadership abilities.

[0778] 3. The device suggests "Employee A" as a potential sales department leader and recommends "Employee B" and "Employee C" as team members.

[0779] 4. The emotion engine analyzes how the user perceives this in real time, and if it recognizes that the user is feeling anxious, it presents questions to provide feedback on the reason. The user answers these questions, and the deployment plan is further adjusted.

[0780] 5. The user finally checks the revised deployment plan and decides on the deployment.

[0781] Example 2: Suggesting talent for a new project

[0782] 1. A user inputs the necessary skill set to start a new project (e.g., updating an IT system) into a terminal.

[0783] 2. The server analyzes employee data and identifies "Employee D," who has successfully completed similar projects in the past, as the project leader.

[0784] 3. The terminal recommends "Employee E" and "Employee F," who have strong development skills and have good project experience with "Employee D" in the past.

[0785] 4. The emotion engine analyzes the user's emotional state and checks whether the user has a positive reaction to the recommended member. If so, the suggestion is presented as is; if not, the option to reselect an alternative member is presented.

[0786] 5. The user checks the recommendations, corrects them if necessary, and then decides on the placement.

[0787] Through this embodiment, enterprises can realize optimal staffing planning that makes the most of employees' characteristics and skills and takes into account users' emotional states, thereby improving the efficiency and performance of the entire organization.

[0788] The processing flow will be explained below.

[0789] Step 1: Data collection

[0790] The server connects to various data sources, such as the personnel management system, personnel evaluation system, and questionnaire system, to collect data on employees' work history, achievements, strengths and weaknesses, characteristics, aspirations, and relationships. Data is collected automatically and periodically via APIs and database queries.

[0791] Step 2: Data Preprocessing

[0792] The server performs preprocessing on the collected data. Specifically, it performs the following processes:

[0793] Data normalization: Standardizing the format of data.

[0794] Imputing missing values: Imputing missing information with estimates or default values.

[0795] Outlier detection and correction: Remove or correct extreme outliers.

[0796] De-duplicate data: Identify duplicate data entries and delete one.

[0797] This creates a clean dataset suitable for analysis.

[0798] Step 3: Characterization and evaluation

[0799] The server analyzes the pre-processed data and evaluates employee traits and skill sets using machine learning algorithms to calculate specific evaluation scores for each employee, such as a leadership score, technical score, and collaboration score.

[0800] Step 4: Training the generative AI model

[0801] The server trains a generative AI model based on the results of the characteristic analysis. It uses past deployment history and its results (e.g., sales increase, project success rate) as training data to build an accurate predictive model. This model predicts the appropriate deployment of employees.

[0802] Step 5: Integrating the Emotion Engine

[0803] The device is equipped with an emotion engine that recognizes the user's emotional state in real time. The emotion engine uses a camera and microphone to analyze the user's facial expressions and tone of voice to identify emotions such as joy, anger, and anxiety.

[0804] Step 6: Fill out your deployment request

[0805] Users use their devices to input specific requirements for a new project or department restructuring (e.g., required skill sets, job titles, and number of people), which are then sent to the server and applied to the generative AI model.

[0806] Step 7: Generating optimal placement plans and emotional adjustment

[0807] The device uses data obtained from the server and a generative AI model to generate an optimal deployment plan. This plan reflects the characteristics and skill sets of employees. Furthermore, an emotion engine analyzes the user's emotional state and fine-tunes the deployment plan accordingly. For example, if the user is feeling anxious, the reason for this can be identified and reflected in the deployment plan.

[0808] Step 8: Present the layout plan

[0809] The terminal presents the generated deployment plan to the user, specifically displaying the message, "Employee A is recommended as the sales department leader, and Employees B and C are optimal team members."

[0810] Step 9: Deployment and Implementation

[0811] The user checks the proposed layout plan and fine-tunes it as necessary. Once the final layout is decided, the plan moves to the implementation stage.

[0812] Step 10: Monitoring the deployment results

[0813] The server monitors organizational performance after deployment, observing and collecting data in real time on things like sales fluctuations, employee satisfaction, and project progress.

[0814] Step 11: Retraining the generative AI model

[0815] The server adjusts the parameters of the generated AI model based on the monitoring results and performs re-learning, thereby improving the accuracy of future deployment plans.

[0816] Through this specific processing step, enterprises can make the most of employee characteristics and skills, as well as the emotional state of users, to improve the efficiency and performance of the entire organization.

[0817] Example 2

[0818] 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."

[0819] Appropriate personnel allocation plans are necessary to maximize employee characteristics and skills and improve overall company efficiency and performance. However, current systems simply base allocations on past data without taking employees' emotional states into account, making it difficult to achieve optimal allocations. In addition, insufficient data preprocessing reduces analysis accuracy. Furthermore, there is no mechanism in place to properly monitor organizational performance after allocation and improve the accuracy of the generative AI model. Therefore, a new system for creating more accurate personnel allocation plans is needed.

[0820] 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.

[0821] In this invention, the server includes: means for collecting data on employee work history, achievements, strengths and weaknesses, characteristics, aspirations, and interpersonal relationships; means for normalizing the collected data, filling in missing values, detecting and correcting outliers, and eliminating duplicate data; means for evaluating employee characteristics and skill sets based on the preprocessed and analyzed data; means for training a generative AI model that predicts employee aptitude and placement based on the analysis results; means for analyzing a user's emotional state in real time and reflecting it in a placement plan; means for generating an optimal personnel placement plan using the trained generative AI model; means for suggesting appropriate project members; and means for monitoring organizational performance after placement and improving the accuracy of the generative AI model. This makes it possible to realize a personnel placement plan that makes the most of employee characteristics and skills and also takes into account the user's emotional state.

[0822] "Employee Data" means data about an employee's work history, achievements, strengths and weaknesses, characteristics, preferences, and relationships.

[0823] "Data collection means" refers to means for extracting necessary employee data from data sources such as personnel management systems, personnel evaluation systems, and employee surveys.

[0824] "Data preprocessing means" refers to means for normalizing collected data, filling in missing values, detecting and correcting outliers, and eliminating duplicate data.

[0825] The "evaluation means" is a means for analyzing employee characteristics and skill sets based on preprocessed data and calculating an evaluation score.

[0826] A "generative AI model" is a model that includes machine learning algorithms to predict optimal employee placement.

[0827] A "model learning means" is a means of adjusting the parameters of a generated AI model based on the analysis results and conducting learning.

[0828] The "emotion analysis means" is a means for analyzing the user's emotional state in real time and reflecting this in the placement plan.

[0829] The "staffing plan generation means" is a means for generating an optimal staffing plan using a trained generative AI model.

[0830] The "project member suggestion means" is a means for recommending suitable project members.

[0831] "Organizational performance monitoring measures" are measures for continuously observing organizational performance after deployment and collecting data.

[0832] The "relearning means" is a means of adjusting the parameters of the generative AI model based on the monitoring results and performing relearning.

[0833] This invention relates to a system that analyzes employee data and generates an optimal personnel allocation plan. In particular, it aims to realize a more accurate personnel allocation plan by incorporating emotion analysis means and taking into account the emotional state of the user.

[0834] Data collection

[0835] The server collects data on employees' work history, achievements, strengths and weaknesses, characteristics, aspirations, and relationships from data sources such as the personnel management system, personnel evaluation system, employee surveys, etc. This data is collected periodically via API and the latest information is stored in the database.

[0836] Data Preprocessing

[0837] The server preprocesses the collected data by normalizing it, imputing missing values, detecting and correcting outliers, and eliminating duplicates. For example, a commonly used tool is the Python pandas library. This produces a clean dataset suitable for subsequent analysis.

[0838] Characterization and evaluation

[0839] The server analyzes the preprocessed data and evaluates each employee's characteristics and skill set. This evaluation is performed using machine learning algorithms, such as the scikit-learn library or TensorFlow, to build a model. The server then calculates an evaluation score for each employee and stores it in a database.

[0840] Training generative AI models

[0841] The server trains a generative AI model based on the analysis results. The training data includes past deployment history and its results (e.g., sales increase, project success rate). The model is built and trained using deep learning libraries such as TensorFlow and PyTorch.

[0842] Emotion engine integration

[0843] The device is equipped with an emotion engine that recognizes the user's emotions. This engine uses facial expression recognition technology (e.g., OpenCV) and natural language processing technology (e.g., Google Cloud Natural Language API) to analyze the user's emotions (e.g., joy, anger, anxiety) in real time as they interact with the system.

[0844] Generate and adjust optimal layout plans

[0845] The device receives input conditions from the user (e.g., details of a new project, required skill sets), and generates an optimal deployment plan using data obtained from the server and the generative AI model. Furthermore, the device reflects the user's emotional state analyzed by the emotion analysis means and fine-tunes the deployment plan. For example, if the user is feeling anxious, the device identifies the cause and presents countermeasure options.

[0846] Presenting the layout plan

[0847] The terminal presents the generated deployment plan to the user, for example, displaying a message such as, "Employee A is recommended as the leader of the sales department because he has a leadership score of 95 and has had excellent sales performance over the past five years. Employees B and C are also ideal team members."

[0848] Placement decision and implementation

[0849] The user reviews the proposed deployment plan, makes adjustments as necessary, and finally decides on the deployment. After the decision is made, the plan is put into action. For example, notifications reflecting the new organizational structure are sent to each employee, and the changes are reflected in related information systems (e.g., time attendance management systems, payroll management systems).

[0850] Monitoring and relearning deployment results

[0851] The server continuously monitors organizational performance after deployment, collecting data such as sales fluctuations, employee satisfaction, and project progress, and uses this data to adjust the parameters of the generative AI model. For example, the results can be visualized on a dashboard, and re-training can be performed to improve the accuracy of future deployment plans.

[0852] Specific examples

[0853] Example 1: Launching a new sales department

[0854] 1. A user enters the required skill sets and job titles to launch a new sales department into a terminal.

[0855] 2. The server analyzes data on all employees and identifies suitable candidates with strong sales skills and leadership abilities.

[0856] 3. The device suggests "Employee A" as a potential sales department leader and recommends "Employee B" and "Employee C" as team members.

[0857] 4. The emotion analysis means analyzes the user's reactions in real time, and if anxiety is high, identifies the reason and provides feedback.

[0858] 5. The user finally checks the revised deployment plan and decides on the deployment.

[0859] Example 2: Suggesting talent for a new project

[0860] 1. A user inputs the necessary skill set to start a new project (e.g., updating an IT system) into a terminal.

[0861] 2. The server analyzes employee data and identifies "Employee D," who has successfully completed similar projects in the past, as the project leader.

[0862] 3. The terminal recommends "Employee E" and "Employee F," who have strong development skills and have good project experience with "Employee D" in the past.

[0863] 4. The emotion analysis means analyzes the user's emotional state and checks whether they have a positive reaction to the recommended member. If they have a positive reaction, they will continue to recommend them, but if they have a negative reaction, they will re-evaluate and select alternative members.

[0864] 5. The user checks the recommendations, corrects them if necessary, and then decides on the placement.

[0865] Through this embodiment, enterprises can make the most of employees' characteristics and skills and realize optimal staffing planning that takes into account users' emotional states, thereby improving the efficiency and performance of the entire organization.

[0866] The flow of the identification process in the second embodiment will be described with reference to FIG.

[0867] Step 1:

[0868] The server collects data about employees' work history, achievements, strengths and weaknesses, characteristics, aspirations, and relationships from data sources such as a personnel management system, personnel evaluation system, and employee surveys. This is done using HTTP requests via APIs, with the input being the API endpoint and authentication information, and the output being a JSON-formatted response with employee data. For example, the server periodically accesses each endpoint, retrieves the required information, and stores it in a database.

[0869] Step 2:

[0870] The server preprocesses the collected data. Specifically, it first normalizes the data and unifies data in different formats. Next, it imputes missing values, for example, by using mean imputation or a predictive model. Statistical methods (e.g., Z-score) are used to detect outliers, and these are then corrected or removed. Finally, it removes duplicate data based on a unique identifier (e.g., employee ID). The input is the collected raw data, and the output is a clean dataset.

[0871] Step 3:

[0872] The server analyzes the preprocessed data and evaluates each employee's characteristics and skill set. This evaluation uses machine learning algorithms (random forest, SVM, neural network). The input is the preprocessed, clean dataset, and the output is an evaluation score for each employee (e.g., leadership score, technical score). Specifically, the server builds a model using scikit-learn or TensorFlow, inputs the data, and calculates the score.

[0873] Step 4:

[0874] The server trains a generative AI model based on the analysis results. Past deployment history and its results (e.g., sales increase rate, project success rate) are used as training data. The input is the evaluation score and past deployment history data, and the output is the trained generative AI model. Specifically, TensorFlow and PyTorch are used to train a deep learning model and find the optimal parameters.

[0875] Step 5:

[0876] The device integrates an emotion engine that analyzes the user's emotions in real time. This engine uses facial expression recognition and natural language processing technologies to analyze the emotions (e.g., joy, anger, anxiety) when the user interacts with the system. The input is the user's facial image and input text, and the output is the analyzed emotional state. For example, facial expressions are recognized using OpenCV, and text is analyzed using the Google Cloud Natural Language API.

[0877] Step 6:

[0878] The terminal receives input conditions from the user (e.g., details of a new project, required skill sets) and generates an optimal deployment plan using data obtained from the server and the generative AI model. Furthermore, the deployment plan is fine-tuned to reflect the user's emotional state analyzed by the sentiment analysis means. The input is a prompt from the user and the results of sentiment analysis, and the output is an optimal personnel deployment plan. For example, the terminal receives user input, sends a request to the server, and receives the optimal deployment plan. At that time, the sentiment analysis results are fed back to adjust the plan.

[0879] Step 7:

[0880] The terminal presents the generated deployment plan to the user. The input is the generated deployment plan, and the output is a display screen that the user can check. For example, it displays specific content such as, "Employee A is recommended as the leader of the sales department because he has a leadership score of 95 and has excellent sales performance over the past five years."

[0881] Step 8:

[0882] The user reviews the presented deployment plan and makes adjustments as necessary. Finally, the deployment is decided. After the decision is made, the plan is put into action. The input is the user's feedback and final decision, and the output is the implementation plan. For example, the user reviews the deployment plan and finally presses the approval button to finalize the plan.

[0883] Step 9:

[0884] The server continuously monitors organizational performance after deployment. It collects data such as sales fluctuations, employee satisfaction, and project progress, and uses this data to adjust the parameters of the generative AI model. The input is the post-deployment performance data, and the output is the adjusted generative AI model. For example, it periodically updates the dashboard, checks the monitoring results, and re-trains as necessary.

[0885] (Application example 2)

[0886] 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."

[0887] Creating optimal staffing plans that take into account information including employee characteristics, skills, and emotional states is extremely complex and cannot be easily achieved with conventional systems. Therefore, in order to maximize organizational efficiency and performance, it is necessary to analyze users' emotional states in real time and reflect them in staffing plans.

[0888] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 2 is realized by the following means.

[0889] In this invention, the server includes a means for collecting data on employee work history, achievements, strengths and weaknesses, characteristics, aspirations, and interpersonal relationships; a means for preprocessing and analyzing the collected data; and a means for training a generative AI model that predicts employee aptitude and placement based on the analysis results. This makes it possible to evaluate employee characteristics and skill sets and develop optimal placement plans. Furthermore, by integrating an emotion engine and including a means for analyzing the user's emotional state in real time and a means for adjusting the generated placement plan based on the emotion engine, it is possible to generate placement plans that are more in line with the user's intentions and emotions. Furthermore, by monitoring organizational performance after placement and improving the accuracy of the generative AI model, it is possible to improve placement accuracy in subsequent placements.

[0890] An "employee" is someone who belongs to a company or organization and performs their duties.

[0891] "Work history" refers to the job titles, positions, and employment history of an employee.

[0892] "Results" refers to the achievements and goal attainment achieved by an employee during their employment.

[0893] "Strengths and weaknesses" refer to the skills and abilities of individual employees, particularly those in which they excel and those in which they need improvement.

[0894] "Characteristics" refer to an employee's personality, behavioral patterns, communication style, etc.

[0895] "Hope" refers to an employee's desired working conditions, career path, placement, and other requests.

[0896] "Interpersonal relationships" refers to interactions between employees and relationships within the workplace.

[0897] "Data collection tools" refer to methods and systems for obtaining various information about employees.

[0898] "Preprocessing and analysis methods" refer to the processes and tools used to convert collected raw data into an analyzable format and remove unnecessary data.

[0899] A "generative AI model" is an artificial intelligence model trained using machine learning algorithms to make predictions and optimizations.

[0900] A "learning tool" is a method or algorithm that trains a generative AI model based on data to improve its accuracy.

[0901] An "optimal staffing plan" is a plan that allocates employees in the most efficient and effective way, taking into account their skills, characteristics, and emotional state.

[0902] A "project member suggestion tool" is a method or system that recommends employees with the skills and characteristics required for a particular project.

[0903] "Monitoring measures" refer to methods and tools for continuously observing and collecting data on the results and status of employees after placement.

[0904] An "emotion engine" is a technology that analyzes a user's emotional state in real time and adjusts the system's behavior based on the results.

[0905] The "adjustment means" refers to a method or system for optimizing the generated placement plan based on information obtained from the emotion engine.

[0906] This invention is a system that analyzes employee information and generates optimal personnel allocation plans, and by combining it with an emotion engine, provides allocation plans that take into account the emotional state of the user. The main components of the system include a server, a terminal, and a user.

[0907] Server Features

[0908] The server first collects data about employees, including work history, achievements, strengths and weaknesses, characteristics, aspirations, and relationships, from data sources such as the personnel management system, personnel evaluation system, and employee surveys. This data is updated regularly, ensuring that the latest information is always analyzed.

[0909] After collecting the data, the server preprocesses the data by normalizing it, imputing missing values, detecting and correcting outliers, removing duplicates, etc. This process creates a clean dataset suitable for analysis.

[0910] Using the preprocessed data, the characteristics and skill sets of each employee are evaluated, and a machine learning algorithm (e.g., RandomForestClassifier) ​​is used to build a generative AI model, which is trained using past deployment history and its results (e.g., sales increase, project success rate).

[0911] Device Features

[0912] The device is equipped with an emotion engine that analyzes emotions (e.g., joy, anger, anxiety) expressed by users in real time as they operate the system. Upon receiving input from the user (e.g., details of a new project, required skill sets), the system generates an optimal deployment plan using data obtained from the server and a generative AI model.

[0913] The generated placement plan is fine-tuned based on the analysis results of the emotion engine. The device then suggests the most suitable project members and presents them to the user. The user can review this, make adjustments as necessary, and decide on the final placement.

[0914] User Roles

[0915] Users input new projects and required skill sets through their devices, review the proposed deployment plan, and make adjustments or final decisions. The system analyzes the user's emotional state in real time, and adjusts the deployment plan based on their feedback.

[0916] Hardware and software used

[0917] The hardware used includes a server that collects and processes data, a terminal that interfaces with the emotion engine, and a user interface. The software includes a database system (e.g., HRDatabase), machine learning algorithms (e.g., RandomForestClassifier), and an emotion engine (e.g., EmotionEngine).

[0918] Specific examples

[0919] For example, a user can input the skill sets and job titles required to set up a new assembly line. The system then analyzes employee data and sensor data to suggest suitable employees. Based on the user's emotional response, the emotion engine makes real-time adjustments and presents the optimal placement plan.

[0920] Prompt Sentence Examples

[0921] "Nominate candidates for new assembly line leaders. Required skill sets include electrical engineering, robotics, and leadership."

[0922] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[0923] Processing Steps

[0924] Step 1: Data collection

[0925] The server collects data on employees' work history, achievements, strengths and weaknesses, characteristics, aspirations, and relationships from data sources such as a personnel management system, a personnel evaluation system, and employee surveys.

[0926] Input: Raw data from each data source.

[0927] Data processing and calculation: Query the database and extract the required information.

[0928] Output: A collection of collected raw data.

[0929] Step 2: Data Preprocessing

[0930] The server preprocesses the collected data, specifically normalizing the data, imputing missing values, detecting and correcting outliers, and eliminating duplicate data.

[0931] Input: The raw data collected.

[0932] Data processing and calculation: Apply data cleansing algorithms to shape the data.

[0933] Output: A clean dataset.

[0934] Step 3: Characterization and evaluation

[0935] The server analyzes the pre-processed data and evaluates each employee's characteristics and skill set using machine learning algorithms to calculate an evaluation score for each employee.

[0936] Input: A clean dataset.

[0937] Data processing and calculation: Feature extraction and evaluation score calculation (e.g., using RandomForestClassifier).

[0938] Output: Evaluation score for each employee.

[0939] Step 4: Training the generative AI model

[0940] The server trains a generative AI model based on the analysis results. This model includes an algorithm for predicting optimal employee placement, using past placement history and results as training data.

[0941] Input: Employee evaluation scores and past placement history data.

[0942] Data processing and calculation: Execute the model training process.

[0943] Output: A trained generative AI model.

[0944] Step 5: Integrating the Emotion Engine

[0945] The device is equipped with an emotion engine that recognizes the user's emotions and analyzes the emotions expressed when the user operates the system in real time.

[0946] Input: Facial expressions and behavioral data during user operation.

[0947] Data processing and computation: Application of emotion recognition algorithms.

[0948] Output: Real-time analysis of the user's emotional state.

[0949] Step 6: Generate and refine optimal layout plans

[0950] The device receives input conditions from the user and generates an optimal placement plan using data obtained from the server and the generative AI model.The device then fine-tunes the placement plan by reflecting the user's emotional state analyzed by the emotion engine.

[0951] Input: User input conditions, trained generative AI model, and emotion engine analysis results.

[0952] Data processing and calculation: Implementing optimal placement algorithms and reflecting emotional states.

[0953] Output: The adjusted optimal placement plan.

[0954] Step 7: Present the layout plan

[0955] The terminal presents the generated placement plan to the user.

[0956] Input: The adjusted optimal placement plan.

[0957] Data processing and calculation: Visualization and presentation of layout plans.

[0958] Output: Deployment plan information for the user.

[0959] Step 8: Deployment and Implementation

[0960] The user checks the proposed deployment plan, makes adjustments as necessary, and finally decides on the deployment. After the decision is made, the plan is put into action.

[0961] Input: Proposed layout plan.

[0962] Data processing and calculation: Final confirmation and adjustment by the user.

[0963] Output: Final placement decision and implementation.

[0964] Step 9: Monitoring deployment results and retraining

[0965] The server monitors organizational performance after deployment, continuously observing and collecting data on sales fluctuations, employee satisfaction, project progress, etc. Based on the results of this monitoring, the parameters of the generative AI model are adjusted and re-trained.

[0966] Input: Post-placement organizational outcome data.

[0967] Data processing and calculation: Analyzing performance data and retraining the generated AI model.

[0968] Output: An updated generative AI model.

[0969] Examples of concrete examples and prompts

[0970] A concrete example would be to input the skill sets and job titles required to set up a new assembly line. Use the following prompt:

[0971] "Nominate candidates for new assembly line leaders. Required skill sets include electrical engineering, robotics, and leadership."

[0972] By inputting this prompt, the system generates an optimal placement plan and makes adjustments that take into account the user's emotional state.

[0973] 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.

[0974] 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.

[0975] 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.

[0976] [Third embodiment]

[0977] FIG. 5 shows an example of the configuration of a data processing system 310 according to the third embodiment.

[0978] 5, the data processing system 310 includes the data processing device 12 and a headset type terminal 314. An example of the data processing device 12 is a server.

[0979] 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).

[0980] 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.

[0981] 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.

[0982] 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).

[0983] 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.

[0984] 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.

[0985] 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.

[0986] 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.

[0987] 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.

[0988] 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."

[0989] This invention relates to a system that analyzes employee information and generates an optimal personnel allocation plan. This system collects data such as employees' work history, achievements, strengths and weaknesses, characteristics, aspirations, and relationships, and trains a generative AI model based on that data. The trained generative AI model is used to achieve efficient personnel allocation in companies and organizations. Specific embodiments for implementing this system are described below.

[0990] Data collection

[0991] The server automatically collects data on employees' work history, achievements, strengths and weaknesses, characteristics, aspirations, and relationships from personnel management systems, evaluation systems, employee surveys, etc. This allows a wide range of information to be obtained in a timely manner.

[0992] Data Preprocessing

[0993] The server preprocesses the collected data, normalizing it, filling in missing values, correcting outliers, and detecting and deleting duplicate data, enabling highly accurate analysis.

[0994] Data analysis and model training

[0995] The server analyzes the preprocessed data and evaluates the characteristics of each employee. Based on the analysis results, it trains a generative AI model, which contains an algorithm for predicting the optimal placement of employees.

[0996] Generate optimal placement plans

[0997] The terminal receives input requirements from the user (e.g., details of a new project, required skill sets). It then uses the analytical data obtained from the server and the generative AI model to generate an optimal staffing plan. The generated staffing plan is then presented to the user.

[0998] Recommended talent suggestions

[0999] The device will suggest suitable personnel for specific projects or department restructuring, allowing users to easily identify the most suitable members and achieve efficient project management and department restructuring.

[1000] Monitoring and relearning deployment results

[1001] The server monitors organizational performance after deployment. It periodically collects data such as sales fluctuations and employee satisfaction to evaluate the effectiveness of the deployment plan. Based on the results of this evaluation, it adjusts the parameters of the generative AI model and performs re-learning. This improves the accuracy of future deployment plans.

[1002] Specific examples

[1003] Example 1: Launching a new sales department

[1004] 1. A user enters the required skill sets and job titles to launch a new sales department into a terminal.

[1005] 2. The server analyzes data on all employees and identifies suitable candidates with strong sales skills and leadership abilities.

[1006] 3. The device suggests "Employee A" as a potential sales department leader and recommends "Employee B" and "Employee C" as team members.

[1007] 4. The user checks the device recommendations and decides on the placement.

[1008] Example 2: Suggesting talent for a new project

[1009] 1. A user inputs the necessary skill set to start a new project (e.g., updating an IT system) into a terminal.

[1010] 2. The server analyzes employee data and identifies "Employee D," who has successfully completed similar projects in the past, as the project leader.

[1011] 3. The terminal recommends "Employee E" and "Employee F," who have strong development skills and have good project experience with "Employee D" in the past.

[1012] 4. The user checks the recommendations from the device, corrects them if necessary, and decides on the placement.

[1013] Through this implementation, companies can maximize the skills and attributes of their employees, improving efficiency and performance across the organization.

[1014] The processing flow will be explained below.

[1015] Step 1: Data collection

[1016] The server collects data on employees' work history, achievements, strengths and weaknesses, characteristics, aspirations, and relationships from data sources such as personnel management systems, personnel evaluation systems, employee surveys, etc. This data is scheduled to be collected automatically on a regular basis.

[1017] Step 2: Data Preprocessing

[1018] The server preprocesses the collected data, specifically by standardizing the data format (normalization), filling in missing values, detecting and correcting outliers, and eliminating duplicate data, creating a clean dataset suitable for analysis.

[1019] Step 3: Characterization and evaluation

[1020] The server analyzes the pre-processed data and evaluates employee traits (e.g., leadership ability, collaboration) and skill sets (e.g., coding skills, sales skills). This analysis uses machine learning algorithms to calculate a specific evaluation score for each employee.

[1021] Step 4: Training the generative AI model

[1022] The server trains a generative AI model based on the analysis results. This model includes an algorithm for predicting optimal employee placement. Past placement history and its results (e.g., sales increase, project success rate) are used as training data.

[1023] Step 5: Fill out your deployment request

[1024] Users use their devices to input specific requirements for new projects or department restructuring (e.g., required skills, number of people, job titles), and this request information is sent to the generative AI model.

[1025] Step 6: Generate optimal layout plans

[1026] The device generates an optimal deployment plan using data obtained from the server and a generative AI model. Specifically, it selects the most suitable personnel based on the specified conditions, taking into account the characteristics and skill sets of each employee.

[1027] Step 7: Present the layout plan

[1028] The device presents the generated deployment plan to the user. For example, it displays a specific recommendation such as, "Employee A is recommended as the leader of the sales department, and Employees B and C are optimal as team members."

[1029] Step 8: Deployment and Implementation

[1030] The user checks the proposed deployment plan, modifies it as necessary, and finalizes the deployment. After the plan is finalized, it is put into practice.

[1031] Step 9: Monitoring the deployment results

[1032] The server monitors organizational performance after deployment, specifically by continuously observing and collecting data on sales fluctuations, employee satisfaction, project progress, etc.

[1033] Step 10: Retraining the generative AI model

[1034] Based on the monitoring results, the server adjusts the parameters of the generated AI model and performs re-learning, thereby improving the accuracy of future deployment plans.

[1035] This series of steps results in a system that makes the most of the characteristics and skills of your employees, improving efficiency and performance across the organization.

[1036] Example 1

[1037] 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."

[1038] Currently, human resource allocation planning in companies is often based on experience and intuition, which can result in less than optimal allocation. Furthermore, employee information is scattered across multiple systems, making it difficult to integrate and normalize the data. Furthermore, there is no system in place to centrally monitor employee performance after allocation and incorporate feedback. A system that can solve these issues and achieve efficient and effective human resource allocation is needed.

[1039] 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.

[1040] In this invention, the server includes: means for collecting information on employees' work history, achievements, strengths and weaknesses, characteristics, aspirations, and interpersonal relationships; means for normalizing the collected information, filling in missing values, correcting outliers, and detecting and deleting duplicate data; and means for analyzing the preprocessed information, evaluating employee characteristics, and training a generative AI model based on the analysis results. This enables accurate collection and analysis of detailed employee information and the generation of optimal personnel allocation plans based on the results. Additionally, by monitoring organizational performance after allocation, adjusting the parameters of the generative AI model, and retraining, the accuracy of the allocation plan can be continuously improved. Furthermore, by suggesting appropriate project members for specific projects or department restructuring, efficient personnel management is possible.

[1041] Employee's work history

[1042] This is information that indicates the job content and experience that an employee has had in the past.

[1043] "Results"

[1044] This is information that shows the specific achievements and accomplishments that an employee has achieved through their work.

[1045] "Strengths and Weaknesses"

[1046] This is information that indicates an employee's specialized skills and abilities, as well as any deficiencies.

[1047] "Characteristics"

[1048] This is information that indicates an employee's personality, behavioral characteristics, and thought patterns.

[1049] "Hope"

[1050] This is information that indicates the job content, career path, and working conditions that an employee desires in the future.

[1051] "Human relationships"

[1052] This is information that indicates the relationships that an employee has with other employees within the company.

[1053] "Normalization"

[1054] It is the process of standardizing collected data based on certain criteria.

[1055] "Missing value imputation"

[1056] is the process of filling in missing values ​​in a dataset with appropriate values.

[1057] "Correction of outliers"

[1058] is the process of detecting outliers in a data set and correcting them to appropriate values.

[1059] "Detecting and Removing Duplicate Data"

[1060] is the process of detecting duplicate data within a dataset and removing unnecessary duplicate data.

[1061] "Generative AI model"

[1062] is an algorithm that is generated using machine learning and deep learning techniques based on collected data to make predictions about personnel placement and other matters.

[1063] "Preprocessing"

[1064] This is a series of data processing processes carried out to prepare collected data in a form that makes it easier to analyze.

[1065] "analysis"

[1066] It is the process of analysis that uses collected and preprocessed data to reveal characteristics and relationships.

[1067] "Optimal personnel allocation planning"

[1068] It is a plan that shows the most efficient allocation of employees to departments and projects, taking into account their characteristics and skills and the company's requirements.

[1069] "Project member suggestions"

[1070] is the process of recommending employees who are best suited for a particular project.

[1071] "monitoring"

[1072] This is the process of continuously observing and recording the performance of organizations and employees after deployment.

[1073] "Parameter Adjustment"

[1074] This is the process of changing internal variables and settings to improve the predictive accuracy of a generative AI model.

[1075] "Relearning"

[1076] This is the process of retraining an existing generative AI model with new data to improve its predictive accuracy.

[1077] This invention is a system for efficiently allocating personnel to a company. The system collects detailed information about employees, analyzes and learns from that data, and then generates and proposes optimal personnel allocation plans.

[1078] To implement this system, the following hardware and software are used.

[1079] Hardware and software used

[1080] Server: Collects data, preprocesses, analyzes, and trains AI models.

[1081] Human Resources Management System Example: "Human Resources Management System"

[1082] Database example: "SQL Database"

[1083] Example of software for model training: "TensorFlow"

[1084] Examples of data preprocessing software: "Python", "pandas", "scikit-learn"

[1085] Terminal: Receives input from the user and presents analysis results and deployment plans.

[1086] Example of interface software: "Web browser"

[1087] Data collection

[1088] The server collects employee information from various internal personnel management systems, evaluation systems, and survey tools. It uses APIs to seamlessly integrate data. For example, an API call retrieves information about work history and achievements from a personnel management system.

[1089] Data Preprocessing

[1090] The server normalizes the collected data, fills in missing values, corrects outliers, and detects and removes duplicate data, creating a dataset suitable for analysis. Specifically, the server cleans the data using the Python pandas library and scales the numerical data using scikit-learn's StandardScaler.

[1091] Data analysis and model training

[1092] The server uses the preprocessed data to evaluate the characteristics of each employee. Based on these evaluation results, it trains a generative AI model. TensorFlow is used to train the model. The server saves the trained model and uses it to generate future placement plans.

[1093] Generate optimal staffing plans

[1094] The terminal receives input conditions from the user. The user enters the details of a new project and the required skill set into the terminal. For example, the user enters a prompt such as "We are looking for a leader for a new IT project." The terminal then sends this to the server, and generates an optimal staffing plan using the analytical data obtained from the server and the generative AI model. The results are displayed to the user through a GUI.

[1095] Recommended talent suggestions

[1096] The terminal suggests suitable project members for specific projects or department restructuring. The user inputs a prompt such as "Please recommend the best employees for a new project." The terminal uses a generative AI model to generate a list of recommended personnel and presents it to the user.

[1097] Monitoring and relearning deployment results

[1098] The server monitors organizational performance after deployment. It analyzes sales data and employee satisfaction to evaluate the effectiveness of the generative AI model. For example, it uses new data obtained from sales data and employee satisfaction surveys to adjust the model parameters and retrain. This improves the accuracy of future deployment plans.

[1099] Specific examples

[1100] Example 1: A user inputs the "skill set and job title required to launch a new sales department" into a terminal. The server identifies personnel with sales skills and leadership skills, and the terminal recommends "Employee A" and "Employee B."

[1101] Example 2: The user inputs "the leader and development team of a new IT project" into the terminal. The server identifies "Employee D" who has had successful projects in the past, and the terminal recommends "Employee D" and "Employee E."

[1102] Through this system, companies can make the most of the skills and attributes of their employees, improving efficiency and performance across the organization.

[1103] The flow of the identification process in the first embodiment will be described with reference to FIG.

[1104] Program processing flow

[1105] Step 1:

[1106] The server collects information on employees' work history, achievements, strengths and weaknesses, characteristics, aspirations, and relationships from various systems (human resource management systems, evaluation systems, survey tools, etc.). Specifically, it connects using an "API" and stores the acquired information in an "SQL database."

[1107] Input: Employee information from HR management systems, appraisal systems, and survey tools.

[1108] Output: Employee information in a SQL database.

[1109] Step 2:

[1110] The server preprocesses employee information stored in an SQL database using Python and pandas to normalize data, impute missing values, correct outliers, and detect and remove duplicate data.

[1111] Input: Collected employee information on a SQL database.

[1112] Output: Preprocessed employee information.

[1113] Step 3:

[1114] The server analyzes the preprocessed data, assessing employee characteristics and using the results to train a generative AI model using TensorFlow, which includes an algorithm for predicting staffing levels.

[1115] Input: Preprocessed employee information.

[1116] Output: A trained generative AI model.

[1117] Step 4:

[1118] The terminal receives input from the user, such as details of a new project and the required skill set, and sends it to the server, for example, by entering a prompt statement such as "We are looking for a leader for a new IT project."

[1119] Input: A prompt from the user.

[1120] Output: Analysis conditions passed to the generative AI model.

[1121] Step 5:

[1122] The server receives a prompt from the user and generates an optimal staffing plan using the preprocessed employee information and the trained generative AI model, such as "Identify employees with the skills required to launch a new sales department." The generated staffing plan is then sent back to the terminal.

[1123] Input: Analysis conditions from the terminal.

[1124] Output: Optimal staffing plan.

[1125] Step 6:

[1126] The terminal displays the allocation plan sent from the server to the user on a GUI, allowing the user to determine the optimal personnel allocation based on this information.

[1127] Input: The deployment plan sent by the server.

[1128] Output: A layout plan display provided to the user.

[1129] Step 7:

[1130] After the deployment plan is implemented, the server periodically monitors organizational outcomes such as sales data and employee satisfaction, and obtains new data from Google Analytics and internal databases to evaluate the accuracy of the generative AI model.

[1131] Input: Organizational outcomes data.

[1132] Output: The evaluated generative AI model.

[1133] Step 8:

[1134] The server adjusts the parameters of the generative AI model based on the monitoring results and performs re-learning, thereby improving the accuracy of future personnel allocation plans.

[1135] Input: An evaluated generative AI model.

[1136] Output: The retrained generative AI model.

[1137] (Application example 1)

[1138] 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."

[1139] In logistics centers, proper employee allocation is extremely important for efficient business operations. However, considering the skill sets, experience, and preferences of multiple employees at once and assigning the most suitable personnel is a significant burden for managers. Furthermore, manual allocation planning is prone to errors and bias, which can reduce operational efficiency. Furthermore, it is difficult to obtain feedback on work results and employee satisfaction after allocation. Conventional methods have limited means of efficiently resolving these issues.

[1140] 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.

[1141] In this invention, the server includes: means for collecting data on employee work history, achievements, strengths and weaknesses, characteristics, preferences, and interpersonal relationships; means for preprocessing and analyzing the collected data; means for training a generative AI model that predicts employee aptitude and placement based on the analysis results; means for generating an optimal personnel placement plan using the trained generative AI model; means for inputting required skill sets and job title requirements; means for analyzing employee data within the logistics center and suggesting optimal personnel placement; and means for monitoring organizational performance after placement and improving the accuracy of the generative AI model. This enables optimal personnel placement in logistics centers that takes into account employee skill sets and preferences, thereby improving business efficiency. By monitoring feedback after placement, continuous model improvement and efficiency can be expected.

[1142] "Employee work history" refers to each employee's past work experience and the history of the positions they have held.

[1143] "Results" refers to the results or accomplishments that an employee achieves in their work.

[1144] "Strengths and weaknesses" refer to the strengths and weaknesses of an employee in specific skills and abilities.

[1145] "Traits" refer to an employee's personality, behavioral patterns, aptitude for work, and other characteristics.

[1146] "Aspirations" refers to the hopes and demands that employees have about their work and the career path they desire in the future.

[1147] "Human relationships" refers to the relationships between employees, mutual trust, and cooperative systems.

[1148] "Means of collecting data" refers to the methods and tools used to automatically or manually capture the required data.

[1149] "Preprocessing" refers to the process of converting collected data into an analyzable form.

[1150] "Analysis" refers to the process of evaluating employee characteristics and suitability based on pre-processed data.

[1151] A "generative AI model" refers to an artificial intelligence model trained based on employee data.

[1152] "Optimal personnel allocation planning" refers to an allocation plan that makes the most of employees' skills and characteristics and achieves efficient business operations.

[1153] A "skill set" refers to the collection of techniques and knowledge required to perform a specific job.

[1154] "Position" refers to the job or position assigned to an employee within an organization.

[1155] "Means for inputting requirements" refers to the methods and tools for inputting the necessary conditions and skills to realize the deployment plan into the system.

[1156] "Means for suggesting personnel placement" refers to systems or algorithms that recommend the most suitable personnel based on the results of analysis.

[1157] "Organizational results" refers to the performance and achievements of employees and the organization as a whole after deployment.

[1158] "Monitoring" refers to the activity of regularly observing organizational results and employee performance and collecting data.

[1159] This invention relates to a system for realizing efficient personnel allocation in logistics centers. The system uses a generative AI model to collect and analyze data on employees' work history, achievements, strengths and weaknesses, characteristics, aspirations, and relationships, and to generate optimal allocation plans.

[1160] Data collection

[1161] The server collects data on employees' work history, achievements, strengths and weaknesses, characteristics, aspirations, and relationships from personnel management systems, evaluation systems, employee surveys, etc. This makes it possible to obtain a wide range of information in a timely manner.

[1162] Data Preprocessing

[1163] The server performs preprocessing on the collected data, such as normalizing it, filling in missing values, correcting outliers, and detecting and deleting duplicate data, enabling highly accurate analysis.

[1164] Data analysis and model training

[1165] The server analyzes the preprocessed data and evaluates the characteristics of each employee. The results of this analysis are used to train a generative AI model, which includes an algorithm for predicting optimal employee placement.

[1166] Generate optimal placement plans

[1167] The terminal receives input conditions from the user (e.g., details of the new project, required skill set, job title), and generates an optimal personnel allocation plan using analytical data obtained from the server and a generative AI model. The generated allocation plan is then presented to the user.

[1168] Recommended talent suggestions

[1169] The device will suggest suitable personnel for specific projects or department restructuring, allowing users to easily identify the most suitable members and achieve efficient project management and department restructuring.

[1170] Monitoring and relearning deployment results

[1171] The server monitors organizational performance after deployment. It periodically collects data such as sales fluctuations and employee satisfaction to evaluate the effectiveness of the deployment plan. Based on the results of this evaluation, it adjusts the parameters of the generative AI model and performs re-learning. This improves the accuracy of future deployment plans.

[1172] Specific examples

[1173] Example: Suggesting talent for a new logistics project

[1174] 1. A user enters into a terminal the required skill set and job title to start a new project (e.g., a large-scale inventory cleanup).

[1175] 2. The server analyzes employee data to identify employees who have successfully completed similar projects in the past.

[1176] 3. The terminal recommends employees with forklift driving skills and experience in sorting goods.

[1177] 4. The user checks the recommendations from the device, corrects them if necessary, and decides on the placement.

[1178] Prompt Sentence Examples

[1179] We need people who can operate forklifts and sort goods.

[1180] This embodiment allows distribution center managers to maximize employee skill sets and characteristics, realize efficient staffing, and continuously improve the model through post-deployment feedback.

[1181] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[1182] Step 1:

[1183] The server collects employee data (work history, achievements, strengths and weaknesses, characteristics, aspirations, relationships).

[1184] Inputs: Data from HR management systems, appraisal systems, and employee surveys.

[1185] Specific operation: Retrieve the necessary information from the database via API.

[1186] Output: A set of collected employee data.

[1187] Step 2:

[1188] The server pre-processes the collected data.

[1189] Input: Employee data collected in Step 1.

[1190] Specific operations: data normalization, missing value imputation, outlier correction, duplicate data detection and removal.

[1191] Output: A preprocessed and clean dataset.

[1192] Step 3:

[1193] The server analyzes the pre-processed data and evaluates the characteristics of each employee.

[1194] Input: The preprocessed data from step 2.

[1195] What it does: Uses machine learning algorithms to assess skills, experience, and attributes.

[1196] Output: Evaluation results for each employee.

[1197] Step 4:

[1198] The server trains the generative AI model based on the evaluation results.

[1199] Input: The employee's evaluation results from step 3.

[1200] Specific operation: The evaluation results are fed into the AI ​​to optimize the model parameters.

[1201] Output: A trained generative AI model.

[1202] Step 5:

[1203] The terminal receives input conditions (required skill set and job title requirements) from the user.

[1204] Input: A prompt from the user (e.g., "We need people who can drive forklifts and sort goods").

[1205] Specific operation: Obtain conditions from input forms or voice input.

[1206] Output: User-specified skillset and job title requirements.

[1207] Step 6:

[1208] The server generates an optimal personnel allocation plan using the analytical data acquired and the generated AI model.

[1209] Input: The user input conditions from step 5 and the generative AI model from step 4.

[1210] Specific operation: Input the user's requirements into the model and list suitable candidates.

[1211] Output: Optimal staffing plan.

[1212] Step 7:

[1213] The terminal presents the user with the optimal staffing plan.

[1214] Input: The staffing plan generated in step 6.

[1215] Specific actions: Display the plan via the user interface.

[1216] Output: Staffing plan presented to the user.

[1217] Step 8:

[1218] The server monitors organizational performance after deployment and collects data.

[1219] Input: Outcome data such as sales data, employee satisfaction data, etc.

[1220] Specific actions: Regularly collect performance data and analyze trends.

[1221] Output: Monitored outcome data.

[1222] Step 9:

[1223] The server adjusts the parameters of the generated AI model based on the monitoring results and performs re-learning.

[1224] Input: Outcome data from Step 8.

[1225] Specific operations: Readjust the parameters of the AI ​​model based on the performance data and repeat the learning process.

[1226] Output: An improved generative AI model.

[1227] 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.

[1228] This invention relates to a system that analyzes employee information and generates optimal personnel allocation plans. In particular, by combining it with an emotion engine, it takes into account the emotional state of the user to realize more accurate personnel allocation plans.

[1229] Data collection

[1230] The server collects data on employees' work history, achievements, strengths and weaknesses, characteristics, aspirations, and interpersonal relationships from data sources such as personnel management systems, personnel evaluation systems, employee surveys, etc. This data collection is carried out periodically, making it possible to analyze based on the latest information.

[1231] Data Preprocessing

[1232] The server preprocesses the collected data by normalizing it, imputing missing values, detecting and correcting outliers, and eliminating duplicate data, creating a clean dataset suitable for analysis.

[1233] Characterization and evaluation

[1234] The server analyzes the pre-processed data and evaluates each employee's characteristics and skill set using machine learning algorithms to calculate an evaluation score for each employee.

[1235] Training generative AI models

[1236] The server trains a generative AI model based on the analysis results. This model includes an algorithm for predicting optimal employee placement. Past placement history and its results (e.g., sales increase, project success rate) are used as training data.

[1237] Emotion engine integration

[1238] The device is equipped with an emotion engine that recognizes the user's emotions. This engine analyzes the emotions (e.g., joy, anger, anxiety) expressed when the user interacts with the system in real time.

[1239] Generate and adjust optimal layout plans

[1240] The device receives input conditions from the user (e.g., details of a new project, required skill sets), and generates an optimal deployment plan using data obtained from the server and a generative AI model.Furthermore, the device fine-tunes the deployment plan by reflecting the user's emotional state analyzed by an emotion engine.

[1241] Presenting the layout plan

[1242] The terminal presents the generated allocation plan to the user, for example, displaying a message such as, "Employee A is recommended as the leader of the sales department, and Employees B and C are optimal as team members."

[1243] Placement decision and implementation

[1244] The user checks the proposed deployment plan, makes adjustments as necessary, and finally decides on the deployment. After the decision is made, the plan is put into action.

[1245] Monitoring and relearning deployment results

[1246] The server monitors organizational performance after deployment, continuously observing and collecting data on factors such as sales fluctuations, employee satisfaction, and project progress. Based on the results of this monitoring, the parameters of the generative AI model are adjusted and re-learned, improving the accuracy of future deployment plans.

[1247] Specific examples

[1248] Example 1: Launching a new sales department

[1249] 1. A user enters the required skill sets and job titles to launch a new sales department into a terminal.

[1250] 2. The server analyzes data on all employees and identifies suitable candidates with strong sales skills and leadership abilities.

[1251] 3. The device suggests "Employee A" as a potential sales department leader and recommends "Employee B" and "Employee C" as team members.

[1252] 4. The emotion engine analyzes how the user perceives this in real time, and if it recognizes that the user is feeling anxious, it presents questions to provide feedback on the reason. The user answers these questions, and the deployment plan is further adjusted.

[1253] 5. The user finally checks the revised deployment plan and decides on the deployment.

[1254] Example 2: Suggesting talent for a new project

[1255] 1. A user inputs the necessary skill set to start a new project (e.g., updating an IT system) into a terminal.

[1256] 2. The server analyzes employee data and identifies "Employee D," who has successfully completed similar projects in the past, as the project leader.

[1257] 3. The terminal recommends "Employee E" and "Employee F," who have strong development skills and have good project experience with "Employee D" in the past.

[1258] 4. The emotion engine analyzes the user's emotional state and checks whether the user has a positive reaction to the recommended member. If so, the suggestion is presented as is; if not, the option to reselect an alternative member is presented.

[1259] 5. The user checks the recommendations, corrects them if necessary, and then decides on the placement.

[1260] Through this embodiment, enterprises can realize optimal staffing planning that makes the most of employees' characteristics and skills and takes into account users' emotional states, thereby improving the efficiency and performance of the entire organization.

[1261] The processing flow will be explained below.

[1262] Step 1: Data collection

[1263] The server connects to various data sources, such as the personnel management system, personnel evaluation system, and questionnaire system, to collect data on employees' work history, achievements, strengths and weaknesses, characteristics, aspirations, and relationships. Data is collected automatically and periodically via APIs and database queries.

[1264] Step 2: Data Preprocessing

[1265] The server performs preprocessing on the collected data. Specifically, it performs the following processes:

[1266] Data normalization: Standardizing the format of data.

[1267] Imputing missing values: Imputing missing information with estimates or default values.

[1268] Outlier detection and correction: Remove or correct extreme outliers.

[1269] De-duplicate data: Identify duplicate data entries and delete one.

[1270] This creates a clean dataset suitable for analysis.

[1271] Step 3: Characterization and evaluation

[1272] The server analyzes the pre-processed data and evaluates employee traits and skill sets using machine learning algorithms to calculate specific evaluation scores for each employee, such as a leadership score, technical score, and collaboration score.

[1273] Step 4: Training the generative AI model

[1274] The server trains a generative AI model based on the results of the characteristic analysis. It uses past deployment history and its results (e.g., sales increase, project success rate) as training data to build an accurate predictive model. This model predicts the appropriate deployment of employees.

[1275] Step 5: Integrating the Emotion Engine

[1276] The device is equipped with an emotion engine that recognizes the user's emotional state in real time. The emotion engine uses a camera and microphone to analyze the user's facial expressions and tone of voice to identify emotions such as joy, anger, and anxiety.

[1277] Step 6: Fill out your deployment request

[1278] Users use their devices to input specific requirements for a new project or department restructuring (e.g., required skill sets, job titles, and number of people), which are then sent to the server and applied to the generative AI model.

[1279] Step 7: Generating optimal placement plans and emotional adjustment

[1280] The device uses data obtained from the server and a generative AI model to generate an optimal deployment plan. This plan reflects the characteristics and skill sets of employees. Furthermore, an emotion engine analyzes the user's emotional state and fine-tunes the deployment plan accordingly. For example, if the user is feeling anxious, the reason for this can be identified and reflected in the deployment plan.

[1281] Step 8: Present the layout plan

[1282] The terminal presents the generated deployment plan to the user, specifically displaying the message, "Employee A is recommended as the sales department leader, and Employees B and C are optimal team members."

[1283] Step 9: Deployment and Implementation

[1284] The user checks the proposed layout plan and fine-tunes it as necessary. Once the final layout is decided, the plan moves to the implementation stage.

[1285] Step 10: Monitoring the deployment results

[1286] The server monitors organizational performance after deployment, observing and collecting data in real time on things like sales fluctuations, employee satisfaction, and project progress.

[1287] Step 11: Retraining the generative AI model

[1288] The server adjusts the parameters of the generated AI model based on the monitoring results and performs re-learning, thereby improving the accuracy of future deployment plans.

[1289] Through this specific processing step, enterprises can make the most of employee characteristics and skills, as well as the emotional state of users, to improve the efficiency and performance of the entire organization.

[1290] Example 2

[1291] 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."

[1292] Appropriate personnel allocation plans are necessary to maximize employee characteristics and skills and improve overall company efficiency and performance. However, current systems simply base allocations on past data without taking employees' emotional states into account, making it difficult to achieve optimal allocations. In addition, insufficient data preprocessing reduces analysis accuracy. Furthermore, there is no mechanism in place to properly monitor organizational performance after allocation and improve the accuracy of the generative AI model. Therefore, a new system for creating more accurate personnel allocation plans is needed.

[1293] 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.

[1294] In this invention, the server includes: means for collecting data on employee work history, achievements, strengths and weaknesses, characteristics, aspirations, and interpersonal relationships; means for normalizing the collected data, filling in missing values, detecting and correcting outliers, and eliminating duplicate data; means for evaluating employee characteristics and skill sets based on the preprocessed and analyzed data; means for training a generative AI model that predicts employee aptitude and placement based on the analysis results; means for analyzing a user's emotional state in real time and reflecting it in a placement plan; means for generating an optimal personnel placement plan using the trained generative AI model; means for suggesting appropriate project members; and means for monitoring organizational performance after placement and improving the accuracy of the generative AI model. This makes it possible to realize a personnel placement plan that makes the most of employee characteristics and skills and also takes into account the user's emotional state.

[1295] "Employee Data" means data about an employee's work history, achievements, strengths and weaknesses, characteristics, preferences, and relationships.

[1296] "Data collection means" refers to means for extracting necessary employee data from data sources such as personnel management systems, personnel evaluation systems, and employee surveys.

[1297] "Data preprocessing means" refers to means for normalizing collected data, filling in missing values, detecting and correcting outliers, and eliminating duplicate data.

[1298] The "evaluation means" is a means for analyzing employee characteristics and skill sets based on preprocessed data and calculating an evaluation score.

[1299] A "generative AI model" is a model that includes machine learning algorithms to predict optimal employee placement.

[1300] A "model learning means" is a means of adjusting the parameters of a generated AI model based on the analysis results and conducting learning.

[1301] The "emotion analysis means" is a means for analyzing the user's emotional state in real time and reflecting this in the placement plan.

[1302] The "staffing plan generation means" is a means for generating an optimal staffing plan using a trained generative AI model.

[1303] The "project member suggestion means" is a means for recommending suitable project members.

[1304] "Organizational performance monitoring measures" are measures for continuously observing organizational performance after deployment and collecting data.

[1305] The "relearning means" is a means of adjusting the parameters of the generative AI model based on the monitoring results and performing relearning.

[1306] This invention relates to a system that analyzes employee data and generates an optimal personnel allocation plan. In particular, it aims to realize a more accurate personnel allocation plan by incorporating emotion analysis means and taking into account the emotional state of the user.

[1307] Data collection

[1308] The server collects data on employees' work history, achievements, strengths and weaknesses, characteristics, aspirations, and relationships from data sources such as the personnel management system, personnel evaluation system, employee surveys, etc. This data is collected periodically via API and the latest information is stored in the database.

[1309] Data Preprocessing

[1310] The server preprocesses the collected data by normalizing it, imputing missing values, detecting and correcting outliers, and eliminating duplicates. For example, a commonly used tool is the Python pandas library. This produces a clean dataset suitable for subsequent analysis.

[1311] Characterization and evaluation

[1312] The server analyzes the preprocessed data and evaluates each employee's characteristics and skill set. This evaluation is performed using machine learning algorithms, such as the scikit-learn library or TensorFlow, to build a model. The server then calculates an evaluation score for each employee and stores it in a database.

[1313] Training generative AI models

[1314] The server trains a generative AI model based on the analysis results. The training data includes past deployment history and its results (e.g., sales increase, project success rate). The model is built and trained using deep learning libraries such as TensorFlow and PyTorch.

[1315] Emotion engine integration

[1316] The device is equipped with an emotion engine that recognizes the user's emotions. This engine uses facial expression recognition technology (e.g., OpenCV) and natural language processing technology (e.g., Google Cloud Natural Language API) to analyze the user's emotions (e.g., joy, anger, anxiety) in real time as they interact with the system.

[1317] Generate and adjust optimal layout plans

[1318] The device receives input conditions from the user (e.g., details of a new project, required skill sets), and generates an optimal deployment plan using data obtained from the server and the generative AI model. Furthermore, the device reflects the user's emotional state analyzed by the emotion analysis means and fine-tunes the deployment plan. For example, if the user is feeling anxious, the device identifies the cause and presents countermeasure options.

[1319] Presenting the layout plan

[1320] The terminal presents the generated deployment plan to the user, for example, displaying a message such as, "Employee A is recommended as the leader of the sales department because he has a leadership score of 95 and has had excellent sales performance over the past five years. Employees B and C are also ideal team members."

[1321] Placement decision and implementation

[1322] The user reviews the proposed deployment plan, makes adjustments as necessary, and finally decides on the deployment. After the decision is made, the plan is put into action. For example, notifications reflecting the new organizational structure are sent to each employee, and the changes are reflected in related information systems (e.g., time attendance management systems, payroll management systems).

[1323] Monitoring and relearning deployment results

[1324] The server continuously monitors organizational performance after deployment, collecting data such as sales fluctuations, employee satisfaction, and project progress, and uses this data to adjust the parameters of the generative AI model. For example, the results can be visualized on a dashboard, and re-training can be performed to improve the accuracy of future deployment plans.

[1325] Specific examples

[1326] Example 1: Launching a new sales department

[1327] 1. A user enters the required skill sets and job titles to launch a new sales department into a terminal.

[1328] 2. The server analyzes data on all employees and identifies suitable candidates with strong sales skills and leadership abilities.

[1329] 3. The device suggests "Employee A" as a potential sales department leader and recommends "Employee B" and "Employee C" as team members.

[1330] 4. The emotion analysis means analyzes the user's reactions in real time, and if anxiety is high, identifies the reason and provides feedback.

[1331] 5. The user finally checks the revised deployment plan and decides on the deployment.

[1332] Example 2: Suggesting talent for a new project

[1333] 1. A user inputs the necessary skill set to start a new project (e.g., updating an IT system) into a terminal.

[1334] 2. The server analyzes employee data and identifies "Employee D," who has successfully completed similar projects in the past, as the project leader.

[1335] 3. The terminal recommends "Employee E" and "Employee F," who have strong development skills and have good project experience with "Employee D" in the past.

[1336] 4. The emotion analysis means analyzes the user's emotional state and checks whether they have a positive reaction to the recommended member. If they have a positive reaction, they will continue to recommend them, but if they have a negative reaction, they will re-evaluate and select alternative members.

[1337] 5. The user checks the recommendations, corrects them if necessary, and then decides on the placement.

[1338] Through this embodiment, enterprises can make the most of employees' characteristics and skills and realize optimal staffing planning that takes into account users' emotional states, thereby improving the efficiency and performance of the entire organization.

[1339] The flow of the identification process in the second embodiment will be described with reference to FIG.

[1340] Step 1:

[1341] The server collects data about employees' work history, achievements, strengths and weaknesses, characteristics, aspirations, and relationships from data sources such as a personnel management system, personnel evaluation system, and employee surveys. This is done using HTTP requests via APIs, with the input being the API endpoint and authentication information, and the output being a JSON-formatted response with employee data. For example, the server periodically accesses each endpoint, retrieves the required information, and stores it in a database.

[1342] Step 2:

[1343] The server preprocesses the collected data. Specifically, it first normalizes the data and unifies data in different formats. Next, it imputes missing values, for example, by using mean imputation or a predictive model. Statistical methods (e.g., Z-score) are used to detect outliers, and these are then corrected or removed. Finally, it removes duplicate data based on a unique identifier (e.g., employee ID). The input is the collected raw data, and the output is a clean dataset.

[1344] Step 3:

[1345] The server analyzes the preprocessed data and evaluates each employee's characteristics and skill set. This evaluation uses machine learning algorithms (random forest, SVM, neural network). The input is the preprocessed, clean dataset, and the output is an evaluation score for each employee (e.g., leadership score, technical score). Specifically, the server builds a model using scikit-learn or TensorFlow, inputs the data, and calculates the score.

[1346] Step 4:

[1347] The server trains a generative AI model based on the analysis results. Past deployment history and its results (e.g., sales increase rate, project success rate) are used as training data. The input is the evaluation score and past deployment history data, and the output is the trained generative AI model. Specifically, TensorFlow and PyTorch are used to train a deep learning model and find the optimal parameters.

[1348] Step 5:

[1349] The device integrates an emotion engine that analyzes the user's emotions in real time. This engine uses facial expression recognition and natural language processing technologies to analyze the emotions (e.g., joy, anger, anxiety) when the user interacts with the system. The input is the user's facial image and input text, and the output is the analyzed emotional state. For example, facial expressions are recognized using OpenCV, and text is analyzed using the Google Cloud Natural Language API.

[1350] Step 6:

[1351] The terminal receives input conditions from the user (e.g., details of a new project, required skill sets) and generates an optimal deployment plan using data obtained from the server and the generative AI model. Furthermore, the deployment plan is fine-tuned to reflect the user's emotional state analyzed by the sentiment analysis means. The input is a prompt from the user and the results of sentiment analysis, and the output is an optimal personnel deployment plan. For example, the terminal receives user input, sends a request to the server, and receives the optimal deployment plan. At that time, the sentiment analysis results are fed back to adjust the plan.

[1352] Step 7:

[1353] The terminal presents the generated deployment plan to the user. The input is the generated deployment plan, and the output is a display screen that the user can check. For example, it displays specific content such as, "Employee A is recommended as the leader of the sales department because he has a leadership score of 95 and has excellent sales performance over the past five years."

[1354] Step 8:

[1355] The user reviews the presented deployment plan and makes adjustments as necessary. Finally, the deployment is decided. After the decision is made, the plan is put into action. The input is the user's feedback and final decision, and the output is the implementation plan. For example, the user reviews the deployment plan and finally presses the approval button to finalize the plan.

[1356] Step 9:

[1357] The server continuously monitors organizational performance after deployment. It collects data such as sales fluctuations, employee satisfaction, and project progress, and uses this data to adjust the parameters of the generative AI model. The input is the post-deployment performance data, and the output is the adjusted generative AI model. For example, it periodically updates the dashboard, checks the monitoring results, and re-trains as necessary.

[1358] (Application example 2)

[1359] 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."

[1360] Creating optimal staffing plans that take into account information including employee characteristics, skills, and emotional states is extremely complex and cannot be easily achieved with conventional systems. Therefore, in order to maximize organizational efficiency and performance, it is necessary to analyze users' emotional states in real time and reflect them in staffing plans.

[1361] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 2 is realized by the following means.

[1362] In this invention, the server includes a means for collecting data on employee work history, achievements, strengths and weaknesses, characteristics, aspirations, and interpersonal relationships; a means for preprocessing and analyzing the collected data; and a means for training a generative AI model that predicts employee aptitude and placement based on the analysis results. This makes it possible to evaluate employee characteristics and skill sets and develop optimal placement plans. Furthermore, by integrating an emotion engine and including a means for analyzing the user's emotional state in real time and a means for adjusting the generated placement plan based on the emotion engine, it is possible to generate placement plans that are more in line with the user's intentions and emotions. Furthermore, by monitoring organizational performance after placement and improving the accuracy of the generative AI model, it is possible to improve placement accuracy in subsequent placements.

[1363] An "employee" is someone who belongs to a company or organization and performs their duties.

[1364] "Work history" refers to the job titles, positions, and employment history of an employee.

[1365] "Results" refers to the achievements and goal attainment achieved by an employee during their employment.

[1366] "Strengths and weaknesses" refer to the skills and abilities of individual employees, particularly those in which they excel and those in which they need improvement.

[1367] "Characteristics" refer to an employee's personality, behavioral patterns, communication style, etc.

[1368] "Hope" refers to an employee's desired working conditions, career path, placement, and other requests.

[1369] "Interpersonal relationships" refers to interactions between employees and relationships within the workplace.

[1370] "Data collection tools" refer to methods and systems for obtaining various information about employees.

[1371] "Preprocessing and analysis methods" refer to the processes and tools used to convert collected raw data into an analyzable format and remove unnecessary data.

[1372] A "generative AI model" is an artificial intelligence model trained using machine learning algorithms to make predictions and optimizations.

[1373] A "learning tool" is a method or algorithm that trains a generative AI model based on data to improve its accuracy.

[1374] An "optimal staffing plan" is a plan that allocates employees in the most efficient and effective way, taking into account their skills, characteristics, and emotional state.

[1375] A "project member suggestion tool" is a method or system that recommends employees with the skills and characteristics required for a particular project.

[1376] "Monitoring measures" refer to methods and tools for continuously observing and collecting data on the results and status of employees after placement.

[1377] An "emotion engine" is a technology that analyzes a user's emotional state in real time and adjusts the system's behavior based on the results.

[1378] The "adjustment means" refers to a method or system for optimizing the generated placement plan based on information obtained from the emotion engine.

[1379] This invention is a system that analyzes employee information and generates optimal personnel allocation plans, and by combining it with an emotion engine, provides allocation plans that take into account the emotional state of the user. The main components of the system include a server, a terminal, and a user.

[1380] Server Features

[1381] The server first collects data about employees, including work history, achievements, strengths and weaknesses, characteristics, aspirations, and relationships, from data sources such as the personnel management system, personnel evaluation system, and employee surveys. This data is updated regularly, ensuring that the latest information is always analyzed.

[1382] After collecting the data, the server preprocesses the data by normalizing it, imputing missing values, detecting and correcting outliers, removing duplicates, etc. This process creates a clean dataset suitable for analysis.

[1383] Using the preprocessed data, the characteristics and skill sets of each employee are evaluated, and a machine learning algorithm (e.g., RandomForestClassifier) ​​is used to build a generative AI model, which is trained using past deployment history and its results (e.g., sales increase, project success rate).

[1384] Device Features

[1385] The device is equipped with an emotion engine that analyzes emotions (e.g., joy, anger, anxiety) expressed by users in real time as they operate the system. Upon receiving input from the user (e.g., details of a new project, required skill sets), the system generates an optimal deployment plan using data obtained from the server and a generative AI model.

[1386] The generated placement plan is fine-tuned based on the analysis results of the emotion engine. The device then suggests the most suitable project members and presents them to the user. The user can review this, make adjustments as necessary, and decide on the final placement.

[1387] User Roles

[1388] Users input new projects and required skill sets through their devices, review the proposed deployment plan, and make adjustments or final decisions. The system analyzes the user's emotional state in real time, and adjusts the deployment plan based on their feedback.

[1389] Hardware and software used

[1390] The hardware used includes a server that collects and processes data, a terminal that interfaces with the emotion engine, and a user interface. The software includes a database system (e.g., HRDatabase), machine learning algorithms (e.g., RandomForestClassifier), and an emotion engine (e.g., EmotionEngine).

[1391] Specific examples

[1392] For example, a user can input the skill sets and job titles required to set up a new assembly line. The system then analyzes employee data and sensor data to suggest suitable employees. Based on the user's emotional response, the emotion engine makes real-time adjustments and presents the optimal placement plan.

[1393] Prompt Sentence Examples

[1394] "Nominate candidates for new assembly line leaders. Required skill sets include electrical engineering, robotics, and leadership."

[1395] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[1396] Processing Steps

[1397] Step 1: Data collection

[1398] The server collects data on employees' work history, achievements, strengths and weaknesses, characteristics, aspirations, and relationships from data sources such as a personnel management system, a personnel evaluation system, and employee surveys.

[1399] Input: Raw data from each data source.

[1400] Data processing and calculation: Query the database and extract the required information.

[1401] Output: A collection of collected raw data.

[1402] Step 2: Data Preprocessing

[1403] The server preprocesses the collected data, specifically normalizing the data, imputing missing values, detecting and correcting outliers, and eliminating duplicate data.

[1404] Input: The raw data collected.

[1405] Data processing and calculation: Apply data cleansing algorithms to shape the data.

[1406] Output: A clean dataset.

[1407] Step 3: Characterization and evaluation

[1408] The server analyzes the pre-processed data and evaluates each employee's characteristics and skill set using machine learning algorithms to calculate an evaluation score for each employee.

[1409] Input: A clean dataset.

[1410] Data processing and calculation: Feature extraction and evaluation score calculation (e.g., using RandomForestClassifier).

[1411] Output: Evaluation score for each employee.

[1412] Step 4: Training the generative AI model

[1413] The server trains a generative AI model based on the analysis results. This model includes an algorithm for predicting optimal employee placement, using past placement history and results as training data.

[1414] Input: Employee evaluation scores and past placement history data.

[1415] Data processing and calculation: Execute the model training process.

[1416] Output: A trained generative AI model.

[1417] Step 5: Integrating the Emotion Engine

[1418] The device is equipped with an emotion engine that recognizes the user's emotions and analyzes the emotions expressed when the user operates the system in real time.

[1419] Input: Facial expressions and behavioral data during user operation.

[1420] Data processing and computation: Application of emotion recognition algorithms.

[1421] Output: Real-time analysis of the user's emotional state.

[1422] Step 6: Generate and refine optimal layout plans

[1423] The device receives input conditions from the user and generates an optimal placement plan using data obtained from the server and the generative AI model.The device then fine-tunes the placement plan by reflecting the user's emotional state analyzed by the emotion engine.

[1424] Input: User input conditions, trained generative AI model, and emotion engine analysis results.

[1425] Data processing and calculation: Implementing optimal placement algorithms and reflecting emotional states.

[1426] Output: The adjusted optimal placement plan.

[1427] Step 7: Present the layout plan

[1428] The terminal presents the generated placement plan to the user.

[1429] Input: The adjusted optimal placement plan.

[1430] Data processing and calculation: Visualization and presentation of layout plans.

[1431] Output: Deployment plan information for the user.

[1432] Step 8: Deployment and Implementation

[1433] The user checks the proposed deployment plan, makes adjustments as necessary, and finally decides on the deployment. After the decision is made, the plan is put into action.

[1434] Input: Proposed layout plan.

[1435] Data processing and calculation: Final confirmation and adjustment by the user.

[1436] Output: Final placement decision and implementation.

[1437] Step 9: Monitoring deployment results and retraining

[1438] The server monitors organizational performance after deployment, continuously observing and collecting data on sales fluctuations, employee satisfaction, project progress, etc. Based on the results of this monitoring, the parameters of the generative AI model are adjusted and re-trained.

[1439] Input: Post-placement organizational outcome data.

[1440] Data processing and calculation: Analyzing performance data and retraining the generated AI model.

[1441] Output: An updated generative AI model.

[1442] Examples of concrete examples and prompts

[1443] A concrete example would be to input the skill sets and job titles required to set up a new assembly line. Use the following prompt:

[1444] "Nominate candidates for new assembly line leaders. Required skill sets include electrical engineering, robotics, and leadership."

[1445] By inputting this prompt, the system generates an optimal placement plan and makes adjustments that take into account the user's emotional state.

[1446] 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.

[1447] 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.

[1448] 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.

[1449] [Fourth embodiment]

[1450] FIG. 7 shows an example of the configuration of a data processing system 410 according to the fourth embodiment.

[1451] 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.

[1452] 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).

[1453] 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.

[1454] 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.

[1455] 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).

[1456] 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.

[1457] 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.

[1458] 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.

[1459] 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.

[1460] 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.

[1461] 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.

[1462] 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."

[1463] This invention relates to a system that analyzes employee information and generates an optimal personnel allocation plan. This system collects data such as employees' work history, achievements, strengths and weaknesses, characteristics, aspirations, and relationships, and trains a generative AI model based on that data. The trained generative AI model is used to achieve efficient personnel allocation in companies and organizations. Specific embodiments for implementing this system are described below.

[1464] Data collection

[1465] The server automatically collects data on employees' work history, achievements, strengths and weaknesses, characteristics, aspirations, and relationships from personnel management systems, evaluation systems, employee surveys, etc. This allows a wide range of information to be obtained in a timely manner.

[1466] Data Preprocessing

[1467] The server preprocesses the collected data, normalizing it, filling in missing values, correcting outliers, and detecting and deleting duplicate data, enabling highly accurate analysis.

[1468] Data analysis and model training

[1469] The server analyzes the preprocessed data and evaluates the characteristics of each employee. Based on the analysis results, it trains a generative AI model, which contains an algorithm for predicting the optimal placement of employees.

[1470] Generate optimal placement plans

[1471] The terminal receives input requirements from the user (e.g., details of a new project, required skill sets). It then uses the analytical data obtained from the server and the generative AI model to generate an optimal staffing plan. The generated staffing plan is then presented to the user.

[1472] Recommended talent suggestions

[1473] The device will suggest suitable personnel for specific projects or department restructuring, allowing users to easily identify the most suitable members and achieve efficient project management and department restructuring.

[1474] Monitoring and relearning deployment results

[1475] The server monitors organizational performance after deployment. It periodically collects data such as sales fluctuations and employee satisfaction to evaluate the effectiveness of the deployment plan. Based on the results of this evaluation, it adjusts the parameters of the generative AI model and performs re-learning. This improves the accuracy of future deployment plans.

[1476] Specific examples

[1477] Example 1: Launching a new sales department

[1478] 1. A user enters the required skill sets and job titles to launch a new sales department into a terminal.

[1479] 2. The server analyzes data on all employees and identifies suitable candidates with strong sales skills and leadership abilities.

[1480] 3. The device suggests "Employee A" as a potential sales department leader and recommends "Employee B" and "Employee C" as team members.

[1481] 4. The user checks the device recommendations and decides on the placement.

[1482] Example 2: Suggesting talent for a new project

[1483] 1. A user inputs the necessary skill set to start a new project (e.g., updating an IT system) into a terminal.

[1484] 2. The server analyzes employee data and identifies "Employee D," who has successfully completed similar projects in the past, as the project leader.

[1485] 3. The terminal recommends "Employee E" and "Employee F," who have strong development skills and have good project experience with "Employee D" in the past.

[1486] 4. The user checks the recommendations from the device, corrects them if necessary, and decides on the placement.

[1487] Through this implementation, companies can maximize the skills and attributes of their employees, improving efficiency and performance across the organization.

[1488] The processing flow will be explained below.

[1489] Step 1: Data collection

[1490] The server collects data on employees' work history, achievements, strengths and weaknesses, characteristics, aspirations, and relationships from data sources such as personnel management systems, personnel evaluation systems, employee surveys, etc. This data is scheduled to be collected automatically on a regular basis.

[1491] Step 2: Data Preprocessing

[1492] The server preprocesses the collected data, specifically by standardizing the data format (normalization), filling in missing values, detecting and correcting outliers, and eliminating duplicate data, creating a clean dataset suitable for analysis.

[1493] Step 3: Characterization and evaluation

[1494] The server analyzes the pre-processed data and evaluates employee traits (e.g., leadership ability, collaboration) and skill sets (e.g., coding skills, sales skills). This analysis uses machine learning algorithms to calculate a specific evaluation score for each employee.

[1495] Step 4: Training the generative AI model

[1496] The server trains a generative AI model based on the analysis results. This model includes an algorithm for predicting optimal employee placement. Past placement history and its results (e.g., sales increase, project success rate) are used as training data.

[1497] Step 5: Fill out your deployment request

[1498] Users use their devices to input specific requirements for new projects or department restructuring (e.g., required skills, number of people, job titles), and this request information is sent to the generative AI model.

[1499] Step 6: Generate optimal layout plans

[1500] The device generates an optimal deployment plan using data obtained from the server and a generative AI model. Specifically, it selects the most suitable personnel based on the specified conditions, taking into account the characteristics and skill sets of each employee.

[1501] Step 7: Present the layout plan

[1502] The device presents the generated deployment plan to the user. For example, it displays a specific recommendation such as, "Employee A is recommended as the leader of the sales department, and Employees B and C are optimal as team members."

[1503] Step 8: Deployment and Implementation

[1504] The user checks the proposed deployment plan, modifies it as necessary, and finalizes the deployment. After the plan is finalized, it is put into practice.

[1505] Step 9: Monitoring the deployment results

[1506] The server monitors organizational performance after deployment, specifically by continuously observing and collecting data on sales fluctuations, employee satisfaction, project progress, etc.

[1507] Step 10: Retraining the generative AI model

[1508] Based on the monitoring results, the server adjusts the parameters of the generated AI model and performs re-learning, thereby improving the accuracy of future deployment plans.

[1509] This series of steps results in a system that makes the most of the characteristics and skills of your employees, improving efficiency and performance across the organization.

[1510] Example 1

[1511] 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."

[1512] Currently, human resource allocation planning in companies is often based on experience and intuition, which can result in less than optimal allocation. Furthermore, employee information is scattered across multiple systems, making it difficult to integrate and normalize the data. Furthermore, there is no system in place to centrally monitor employee performance after allocation and incorporate feedback. A system that can solve these issues and achieve efficient and effective human resource allocation is needed.

[1513] 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.

[1514] In this invention, the server includes: means for collecting information on employees' work history, achievements, strengths and weaknesses, characteristics, aspirations, and interpersonal relationships; means for normalizing the collected information, filling in missing values, correcting outliers, and detecting and deleting duplicate data; and means for analyzing the preprocessed information, evaluating employee characteristics, and training a generative AI model based on the analysis results. This enables accurate collection and analysis of detailed employee information and the generation of optimal personnel allocation plans based on the results. Additionally, by monitoring organizational performance after allocation, adjusting the parameters of the generative AI model, and retraining, the accuracy of the allocation plan can be continuously improved. Furthermore, by suggesting appropriate project members for specific projects or department restructuring, efficient personnel management is possible.

[1515] Employee's work history

[1516] This is information that indicates the job content and experience that an employee has had in the past.

[1517] "Results"

[1518] This is information that shows the specific achievements and accomplishments that an employee has achieved through their work.

[1519] "Strengths and Weaknesses"

[1520] This is information that indicates an employee's specialized skills and abilities, as well as any deficiencies.

[1521] "Characteristics"

[1522] This is information that indicates an employee's personality, behavioral characteristics, and thought patterns.

[1523] "Hope"

[1524] This is information that indicates the job content, career path, and working conditions that an employee desires in the future.

[1525] "Human relationships"

[1526] This is information that indicates the relationships that an employee has with other employees within the company.

[1527] "Normalization"

[1528] It is the process of standardizing collected data based on certain criteria.

[1529] "Missing value imputation"

[1530] is the process of filling in missing values ​​in a dataset with appropriate values.

[1531] "Correction of outliers"

[1532] is the process of detecting outliers in a data set and correcting them to appropriate values.

[1533] "Detecting and Removing Duplicate Data"

[1534] is the process of detecting duplicate data within a dataset and removing unnecessary duplicate data.

[1535] "Generative AI model"

[1536] is an algorithm that is generated using machine learning and deep learning techniques based on collected data to make predictions about personnel placement and other matters.

[1537] "Preprocessing"

[1538] This is a series of data processing processes carried out to prepare collected data in a form that makes it easier to analyze.

[1539] "analysis"

[1540] It is the process of analysis that uses collected and preprocessed data to reveal characteristics and relationships.

[1541] "Optimal personnel allocation planning"

[1542] It is a plan that shows the most efficient allocation of employees to departments and projects, taking into account their characteristics and skills and the company's requirements.

[1543] "Project member suggestions"

[1544] is the process of recommending employees who are best suited for a particular project.

[1545] "monitoring"

[1546] This is the process of continuously observing and recording the performance of organizations and employees after deployment.

[1547] "Parameter Adjustment"

[1548] This is the process of changing internal variables and settings to improve the predictive accuracy of a generative AI model.

[1549] "Relearning"

[1550] This is the process of retraining an existing generative AI model with new data to improve its predictive accuracy.

[1551] This invention is a system for efficiently allocating personnel to a company. The system collects detailed information about employees, analyzes and learns from that data, and then generates and proposes optimal personnel allocation plans.

[1552] To implement this system, the following hardware and software are used.

[1553] Hardware and software used

[1554] Server: Collects data, preprocesses, analyzes, and trains AI models.

[1555] Human Resources Management System Example: "Human Resources Management System"

[1556] Database example: "SQL Database"

[1557] Example of software for model training: "TensorFlow"

[1558] Examples of data preprocessing software: "Python", "pandas", "scikit-learn"

[1559] Terminal: Receives input from the user and presents analysis results and deployment plans.

[1560] Example of interface software: "Web browser"

[1561] Data collection

[1562] The server collects employee information from various internal personnel management systems, evaluation systems, and survey tools. It uses APIs to seamlessly integrate data. For example, an API call retrieves information about work history and achievements from a personnel management system.

[1563] Data Preprocessing

[1564] The server normalizes the collected data, fills in missing values, corrects outliers, and detects and removes duplicate data, creating a dataset suitable for analysis. Specifically, the server cleans the data using the Python pandas library and scales the numerical data using scikit-learn's StandardScaler.

[1565] Data analysis and model training

[1566] The server uses the preprocessed data to evaluate the characteristics of each employee. Based on these evaluation results, it trains a generative AI model. TensorFlow is used to train the model. The server saves the trained model and uses it to generate future placement plans.

[1567] Generate optimal staffing plans

[1568] The terminal receives input conditions from the user. The user enters the details of a new project and the required skill set into the terminal. For example, the user enters a prompt such as "We are looking for a leader for a new IT project." The terminal then sends this to the server, and generates an optimal staffing plan using the analytical data obtained from the server and the generative AI model. The results are displayed to the user through a GUI.

[1569] Recommended talent suggestions

[1570] The terminal suggests suitable project members for specific projects or department restructuring. The user inputs a prompt such as "Please recommend the best employees for a new project." The terminal uses a generative AI model to generate a list of recommended personnel and presents it to the user.

[1571] Monitoring and relearning deployment results

[1572] The server monitors organizational performance after deployment. It analyzes sales data and employee satisfaction to evaluate the effectiveness of the generative AI model. For example, it uses new data obtained from sales data and employee satisfaction surveys to adjust the model parameters and retrain. This improves the accuracy of future deployment plans.

[1573] Specific examples

[1574] Example 1: A user inputs the "skill set and job title required to launch a new sales department" into a terminal. The server identifies personnel with sales skills and leadership skills, and the terminal recommends "Employee A" and "Employee B."

[1575] Example 2: The user inputs "the leader and development team of a new IT project" into the terminal. The server identifies "Employee D" who has had successful projects in the past, and the terminal recommends "Employee D" and "Employee E."

[1576] Through this system, companies can make the most of the skills and attributes of their employees, improving efficiency and performance across the organization.

[1577] The flow of the identification process in the first embodiment will be described with reference to FIG.

[1578] Program processing flow

[1579] Step 1:

[1580] The server collects information on employees' work history, achievements, strengths and weaknesses, characteristics, aspirations, and relationships from various systems (human resource management systems, evaluation systems, survey tools, etc.). Specifically, it connects using an "API" and stores the acquired information in an "SQL database."

[1581] Input: Employee information from HR management systems, appraisal systems, and survey tools.

[1582] Output: Employee information in a SQL database.

[1583] Step 2:

[1584] The server preprocesses employee information stored in an SQL database using Python and pandas to normalize data, impute missing values, correct outliers, and detect and remove duplicate data.

[1585] Input: Collected employee information on a SQL database.

[1586] Output: Preprocessed employee information.

[1587] Step 3:

[1588] The server analyzes the preprocessed data, assessing employee characteristics and using the results to train a generative AI model using TensorFlow, which includes an algorithm for predicting staffing levels.

[1589] Input: Preprocessed employee information.

[1590] Output: A trained generative AI model.

[1591] Step 4:

[1592] The terminal receives input from the user, such as details of a new project and the required skill set, and sends it to the server, for example, by entering a prompt statement such as "We are looking for a leader for a new IT project."

[1593] Input: A prompt from the user.

[1594] Output: Analysis conditions passed to the generative AI model.

[1595] Step 5:

[1596] The server receives a prompt from the user and generates an optimal staffing plan using the preprocessed employee information and the trained generative AI model, such as "Identify employees with the skills required to launch a new sales department." The generated staffing plan is then sent back to the terminal.

[1597] Input: Analysis conditions from the terminal.

[1598] Output: Optimal staffing plan.

[1599] Step 6:

[1600] The terminal displays the allocation plan sent from the server to the user on a GUI, allowing the user to determine the optimal personnel allocation based on this information.

[1601] Input: The deployment plan sent by the server.

[1602] Output: A layout plan display provided to the user.

[1603] Step 7:

[1604] After the deployment plan is implemented, the server periodically monitors organizational outcomes such as sales data and employee satisfaction, and obtains new data from Google Analytics and internal databases to evaluate the accuracy of the generative AI model.

[1605] Input: Organizational outcomes data.

[1606] Output: The evaluated generative AI model.

[1607] Step 8:

[1608] The server adjusts the parameters of the generative AI model based on the monitoring results and performs re-learning, thereby improving the accuracy of future personnel allocation plans.

[1609] Input: An evaluated generative AI model.

[1610] Output: The retrained generative AI model.

[1611] (Application example 1)

[1612] 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."

[1613] In logistics centers, proper employee allocation is extremely important for efficient business operations. However, considering the skill sets, experience, and preferences of multiple employees at once and assigning the most suitable personnel is a significant burden for managers. Furthermore, manual allocation planning is prone to errors and bias, which can reduce operational efficiency. Furthermore, it is difficult to obtain feedback on work results and employee satisfaction after allocation. Conventional methods have limited means of efficiently resolving these issues.

[1614] 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.

[1615] In this invention, the server includes: means for collecting data on employee work history, achievements, strengths and weaknesses, characteristics, preferences, and interpersonal relationships; means for preprocessing and analyzing the collected data; means for training a generative AI model that predicts employee aptitude and placement based on the analysis results; means for generating an optimal personnel placement plan using the trained generative AI model; means for inputting required skill sets and job title requirements; means for analyzing employee data within the logistics center and suggesting optimal personnel placement; and means for monitoring organizational performance after placement and improving the accuracy of the generative AI model. This enables optimal personnel placement in logistics centers that takes into account employee skill sets and preferences, thereby improving business efficiency. By monitoring feedback after placement, continuous model improvement and efficiency can be expected.

[1616] "Employee work history" refers to each employee's past work experience and the history of the positions they have held.

[1617] "Results" refers to the results or accomplishments that an employee achieves in their work.

[1618] "Strengths and weaknesses" refer to the strengths and weaknesses of an employee in specific skills and abilities.

[1619] "Traits" refer to an employee's personality, behavioral patterns, aptitude for work, and other characteristics.

[1620] "Aspirations" refers to the hopes and demands that employees have about their work and the career path they desire in the future.

[1621] "Human relationships" refers to the relationships between employees, mutual trust, and cooperative systems.

[1622] "Means of collecting data" refers to the methods and tools used to automatically or manually capture the required data.

[1623] "Preprocessing" refers to the process of converting collected data into an analyzable form.

[1624] "Analysis" refers to the process of evaluating employee characteristics and suitability based on pre-processed data.

[1625] A "generative AI model" refers to an artificial intelligence model trained based on employee data.

[1626] "Optimal personnel allocation planning" refers to an allocation plan that makes the most of employees' skills and characteristics and achieves efficient business operations.

[1627] A "skill set" refers to the collection of techniques and knowledge required to perform a specific job.

[1628] "Position" refers to the job or position assigned to an employee within an organization.

[1629] "Means for inputting requirements" refers to the methods and tools for inputting the necessary conditions and skills to realize the deployment plan into the system.

[1630] "Means for suggesting personnel placement" refers to systems or algorithms that recommend the most suitable personnel based on the results of analysis.

[1631] "Organizational results" refers to the performance and achievements of employees and the organization as a whole after deployment.

[1632] "Monitoring" refers to the activity of regularly observing organizational results and employee performance and collecting data.

[1633] This invention relates to a system for realizing efficient personnel allocation in logistics centers. The system uses a generative AI model to collect and analyze data on employees' work history, achievements, strengths and weaknesses, characteristics, aspirations, and relationships, and to generate optimal allocation plans.

[1634] Data collection

[1635] The server collects data on employees' work history, achievements, strengths and weaknesses, characteristics, aspirations, and relationships from personnel management systems, evaluation systems, employee surveys, etc. This makes it possible to obtain a wide range of information in a timely manner.

[1636] Data Preprocessing

[1637] The server performs preprocessing on the collected data, such as normalizing it, filling in missing values, correcting outliers, and detecting and deleting duplicate data, enabling highly accurate analysis.

[1638] Data analysis and model training

[1639] The server analyzes the preprocessed data and evaluates the characteristics of each employee. The results of this analysis are used to train a generative AI model, which includes an algorithm for predicting optimal employee placement.

[1640] Generate optimal placement plans

[1641] The terminal receives input conditions from the user (e.g., details of the new project, required skill set, job title), and generates an optimal personnel allocation plan using analytical data obtained from the server and a generative AI model. The generated allocation plan is then presented to the user.

[1642] Recommended talent suggestions

[1643] The device will suggest suitable personnel for specific projects or department restructuring, allowing users to easily identify the most suitable members and achieve efficient project management and department restructuring.

[1644] Monitoring and relearning deployment results

[1645] The server monitors organizational performance after deployment. It periodically collects data such as sales fluctuations and employee satisfaction to evaluate the effectiveness of the deployment plan. Based on the results of this evaluation, it adjusts the parameters of the generative AI model and performs re-learning. This improves the accuracy of future deployment plans.

[1646] Specific examples

[1647] Example: Suggesting talent for a new logistics project

[1648] 1. A user enters into a terminal the required skill set and job title to start a new project (e.g., a large-scale inventory cleanup).

[1649] 2. The server analyzes employee data to identify employees who have successfully completed similar projects in the past.

[1650] 3. The terminal recommends employees with forklift driving skills and experience in sorting goods.

[1651] 4. The user checks the recommendations from the device, corrects them if necessary, and decides on the placement.

[1652] Prompt Sentence Examples

[1653] We need people who can operate forklifts and sort goods.

[1654] This embodiment allows distribution center managers to maximize employee skill sets and characteristics, realize efficient staffing, and continuously improve the model through post-deployment feedback.

[1655] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[1656] Step 1:

[1657] The server collects employee data (work history, achievements, strengths and weaknesses, characteristics, aspirations, relationships).

[1658] Inputs: Data from HR management systems, appraisal systems, and employee surveys.

[1659] Specific operation: Retrieve the necessary information from the database via API.

[1660] Output: A set of collected employee data.

[1661] Step 2:

[1662] The server pre-processes the collected data.

[1663] Input: Employee data collected in Step 1.

[1664] Specific operations: data normalization, missing value imputation, outlier correction, duplicate data detection and removal.

[1665] Output: A preprocessed and clean dataset.

[1666] Step 3:

[1667] The server analyzes the pre-processed data and evaluates the characteristics of each employee.

[1668] Input: The preprocessed data from step 2.

[1669] What it does: Uses machine learning algorithms to assess skills, experience, and attributes.

[1670] Output: Evaluation results for each employee.

[1671] Step 4:

[1672] The server trains the generative AI model based on the evaluation results.

[1673] Input: The employee's evaluation results from step 3.

[1674] Specific operation: The evaluation results are fed into the AI ​​to optimize the model parameters.

[1675] Output: A trained generative AI model.

[1676] Step 5:

[1677] The terminal receives input conditions (required skill set and job title requirements) from the user.

[1678] Input: A prompt from the user (e.g., "We need people who can drive forklifts and sort goods").

[1679] Specific operation: Obtain conditions from input forms or voice input.

[1680] Output: User-specified skillset and job title requirements.

[1681] Step 6:

[1682] The server generates an optimal personnel allocation plan using the analytical data acquired and the generated AI model.

[1683] Input: The user input conditions from step 5 and the generative AI model from step 4.

[1684] Specific operation: Input the user's requirements into the model and list suitable candidates.

[1685] Output: Optimal staffing plan.

[1686] Step 7:

[1687] The terminal presents the user with the optimal staffing plan.

[1688] Input: The staffing plan generated in step 6.

[1689] Specific actions: Display the plan via the user interface.

[1690] Output: Staffing plan presented to the user.

[1691] Step 8:

[1692] The server monitors organizational performance after deployment and collects data.

[1693] Input: Outcome data such as sales data, employee satisfaction data, etc.

[1694] Specific actions: Regularly collect performance data and analyze trends.

[1695] Output: Monitored outcome data.

[1696] Step 9:

[1697] The server adjusts the parameters of the generated AI model based on the monitoring results and performs re-learning.

[1698] Input: Outcome data from Step 8.

[1699] Specific operations: Readjust the parameters of the AI ​​model based on the performance data and repeat the learning process.

[1700] Output: An improved generative AI model.

[1701] 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.

[1702] This invention relates to a system that analyzes employee information and generates optimal personnel allocation plans. In particular, by combining it with an emotion engine, it takes into account the emotional state of the user to realize more accurate personnel allocation plans.

[1703] Data collection

[1704] The server collects data on employees' work history, achievements, strengths and weaknesses, characteristics, aspirations, and interpersonal relationships from data sources such as personnel management systems, personnel evaluation systems, employee surveys, etc. This data collection is carried out periodically, making it possible to analyze based on the latest information.

[1705] Data Preprocessing

[1706] The server preprocesses the collected data by normalizing it, imputing missing values, detecting and correcting outliers, and eliminating duplicate data, creating a clean dataset suitable for analysis.

[1707] Characterization and evaluation

[1708] The server analyzes the pre-processed data and evaluates each employee's characteristics and skill set using machine learning algorithms to calculate an evaluation score for each employee.

[1709] Training generative AI models

[1710] The server trains a generative AI model based on the analysis results. This model includes an algorithm for predicting optimal employee placement. Past placement history and its results (e.g., sales increase, project success rate) are used as training data.

[1711] Emotion engine integration

[1712] The device is equipped with an emotion engine that recognizes the user's emotions. This engine analyzes the emotions (e.g., joy, anger, anxiety) expressed when the user interacts with the system in real time.

[1713] Generate and adjust optimal layout plans

[1714] The device receives input conditions from the user (e.g., details of a new project, required skill sets), and generates an optimal deployment plan using data obtained from the server and a generative AI model.Furthermore, the device fine-tunes the deployment plan by reflecting the user's emotional state analyzed by an emotion engine.

[1715] Presenting the layout plan

[1716] The terminal presents the generated allocation plan to the user, for example, displaying a message such as, "Employee A is recommended as the leader of the sales department, and Employees B and C are optimal as team members."

[1717] Placement decision and implementation

[1718] The user checks the proposed deployment plan, makes adjustments as necessary, and finally decides on the deployment. After the decision is made, the plan is put into action.

[1719] Monitoring and relearning deployment results

[1720] The server monitors organizational performance after deployment, continuously observing and collecting data on factors such as sales fluctuations, employee satisfaction, and project progress. Based on the results of this monitoring, the parameters of the generative AI model are adjusted and re-learned, improving the accuracy of future deployment plans.

[1721] Specific examples

[1722] Example 1: Launching a new sales department

[1723] 1. A user enters the required skill sets and job titles to launch a new sales department into a terminal.

[1724] 2. The server analyzes data on all employees and identifies suitable candidates with strong sales skills and leadership abilities.

[1725] 3. The device suggests "Employee A" as a potential sales department leader and recommends "Employee B" and "Employee C" as team members.

[1726] 4. The emotion engine analyzes how the user perceives this in real time, and if it recognizes that the user is feeling anxious, it presents questions to provide feedback on the reason. The user answers these questions, and the deployment plan is further adjusted.

[1727] 5. The user finally checks the revised deployment plan and decides on the deployment.

[1728] Example 2: Suggesting talent for a new project

[1729] 1. A user inputs the necessary skill set to start a new project (e.g., updating an IT system) into a terminal.

[1730] 2. The server analyzes employee data and identifies "Employee D," who has successfully completed similar projects in the past, as the project leader.

[1731] 3. The terminal recommends "Employee E" and "Employee F," who have strong development skills and have good project experience with "Employee D" in the past.

[1732] 4. The emotion engine analyzes the user's emotional state and checks whether the user has a positive reaction to the recommended member. If so, the suggestion is presented as is; if not, the option to reselect an alternative member is presented.

[1733] 5. The user checks the recommendations, corrects them if necessary, and then decides on the placement.

[1734] Through this embodiment, enterprises can realize optimal staffing planning that makes the most of employees' characteristics and skills and takes into account users' emotional states, thereby improving the efficiency and performance of the entire organization.

[1735] The processing flow will be explained below.

[1736] Step 1: Data collection

[1737] The server connects to various data sources, such as the personnel management system, personnel evaluation system, and questionnaire system, to collect data on employees' work history, achievements, strengths and weaknesses, characteristics, aspirations, and relationships. Data is collected automatically and periodically via APIs and database queries.

[1738] Step 2: Data Preprocessing

[1739] The server performs preprocessing on the collected data. Specifically, it performs the following processes:

[1740] Data normalization: Standardizing the format of data.

[1741] Imputing missing values: Imputing missing information with estimates or default values.

[1742] Outlier detection and correction: Remove or correct extreme outliers.

[1743] De-duplicate data: Identify duplicate data entries and delete one.

[1744] This creates a clean dataset suitable for analysis.

[1745] Step 3: Characterization and evaluation

[1746] The server analyzes the pre-processed data and evaluates employee traits and skill sets using machine learning algorithms to calculate specific evaluation scores for each employee, such as a leadership score, technical score, and collaboration score.

[1747] Step 4: Training the generative AI model

[1748] The server trains a generative AI model based on the results of the characteristic analysis. It uses past deployment history and its results (e.g., sales increase, project success rate) as training data to build an accurate predictive model. This model predicts the appropriate deployment of employees.

[1749] Step 5: Integrating the Emotion Engine

[1750] The device is equipped with an emotion engine that recognizes the user's emotional state in real time. The emotion engine uses a camera and microphone to analyze the user's facial expressions and tone of voice to identify emotions such as joy, anger, and anxiety.

[1751] Step 6: Fill out your deployment request

[1752] Users use their devices to input specific requirements for a new project or department restructuring (e.g., required skill sets, job titles, and number of people), which are then sent to the server and applied to the generative AI model.

[1753] Step 7: Generating optimal placement plans and emotional adjustment

[1754] The device uses data obtained from the server and a generative AI model to generate an optimal deployment plan. This plan reflects the characteristics and skill sets of employees. Furthermore, an emotion engine analyzes the user's emotional state and fine-tunes the deployment plan accordingly. For example, if the user is feeling anxious, the reason for this can be identified and reflected in the deployment plan.

[1755] Step 8: Present the layout plan

[1756] The terminal presents the generated deployment plan to the user, specifically displaying the message, "Employee A is recommended as the sales department leader, and Employees B and C are optimal team members."

[1757] Step 9: Deployment and Implementation

[1758] The user checks the proposed layout plan and fine-tunes it as necessary. Once the final layout is decided, the plan moves to the implementation stage.

[1759] Step 10: Monitoring the deployment results

[1760] The server monitors organizational performance after deployment, observing and collecting data in real time on things like sales fluctuations, employee satisfaction, and project progress.

[1761] Step 11: Retraining the generative AI model

[1762] The server adjusts the parameters of the generated AI model based on the monitoring results and performs re-learning, thereby improving the accuracy of future deployment plans.

[1763] Through this specific processing step, enterprises can make the most of employee characteristics and skills, as well as the emotional state of users, to improve the efficiency and performance of the entire organization.

[1764] Example 2

[1765] 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."

[1766] Appropriate personnel allocation plans are necessary to maximize employee characteristics and skills and improve overall company efficiency and performance. However, current systems simply base allocations on past data without taking employees' emotional states into account, making it difficult to achieve optimal allocations. In addition, insufficient data preprocessing reduces analysis accuracy. Furthermore, there is no mechanism in place to properly monitor organizational performance after allocation and improve the accuracy of the generative AI model. Therefore, a new system for creating more accurate personnel allocation plans is needed.

[1767] 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.

[1768] In this invention, the server includes: means for collecting data on employee work history, achievements, strengths and weaknesses, characteristics, aspirations, and interpersonal relationships; means for normalizing the collected data, filling in missing values, detecting and correcting outliers, and eliminating duplicate data; means for evaluating employee characteristics and skill sets based on the preprocessed and analyzed data; means for training a generative AI model that predicts employee aptitude and placement based on the analysis results; means for analyzing a user's emotional state in real time and reflecting it in a placement plan; means for generating an optimal personnel placement plan using the trained generative AI model; means for suggesting appropriate project members; and means for monitoring organizational performance after placement and improving the accuracy of the generative AI model. This makes it possible to realize a personnel placement plan that makes the most of employee characteristics and skills and also takes into account the user's emotional state.

[1769] "Employee Data" means data about an employee's work history, achievements, strengths and weaknesses, characteristics, preferences, and relationships.

[1770] "Data collection means" refers to means for extracting necessary employee data from data sources such as personnel management systems, personnel evaluation systems, and employee surveys.

[1771] "Data preprocessing means" refers to means for normalizing collected data, filling in missing values, detecting and correcting outliers, and eliminating duplicate data.

[1772] The "evaluation means" is a means for analyzing employee characteristics and skill sets based on preprocessed data and calculating an evaluation score.

[1773] A "generative AI model" is a model that includes machine learning algorithms to predict optimal employee placement.

[1774] A "model learning means" is a means of adjusting the parameters of a generated AI model based on the analysis results and conducting learning.

[1775] The "emotion analysis means" is a means for analyzing the user's emotional state in real time and reflecting this in the placement plan.

[1776] The "staffing plan generation means" is a means for generating an optimal staffing plan using a trained generative AI model.

[1777] The "project member suggestion means" is a means for recommending suitable project members.

[1778] "Organizational performance monitoring measures" are measures for continuously observing organizational performance after deployment and collecting data.

[1779] The "relearning means" is a means of adjusting the parameters of the generative AI model based on the monitoring results and performing relearning.

[1780] This invention relates to a system that analyzes employee data and generates an optimal personnel allocation plan. In particular, it aims to realize a more accurate personnel allocation plan by incorporating emotion analysis means and taking into account the emotional state of the user.

[1781] Data collection

[1782] The server collects data on employees' work history, achievements, strengths and weaknesses, characteristics, aspirations, and relationships from data sources such as the personnel management system, personnel evaluation system, employee surveys, etc. This data is collected periodically via API and the latest information is stored in the database.

[1783] Data Preprocessing

[1784] The server preprocesses the collected data by normalizing it, imputing missing values, detecting and correcting outliers, and eliminating duplicates. For example, a commonly used tool is the Python pandas library. This produces a clean dataset suitable for subsequent analysis.

[1785] Characterization and evaluation

[1786] The server analyzes the preprocessed data and evaluates each employee's characteristics and skill set. This evaluation is performed using machine learning algorithms, such as the scikit-learn library or TensorFlow, to build a model. The server then calculates an evaluation score for each employee and stores it in a database.

[1787] Training generative AI models

[1788] The server trains a generative AI model based on the analysis results. The training data includes past deployment history and its results (e.g., sales increase, project success rate). The model is built and trained using deep learning libraries such as TensorFlow and PyTorch.

[1789] Emotion engine integration

[1790] The device is equipped with an emotion engine that recognizes the user's emotions. This engine uses facial expression recognition technology (e.g., OpenCV) and natural language processing technology (e.g., Google Cloud Natural Language API) to analyze the user's emotions (e.g., joy, anger, anxiety) in real time as they interact with the system.

[1791] Generate and adjust optimal layout plans

[1792] The device receives input conditions from the user (e.g., details of a new project, required skill sets), and generates an optimal deployment plan using data obtained from the server and the generative AI model. Furthermore, the device reflects the user's emotional state analyzed by the emotion analysis means and fine-tunes the deployment plan. For example, if the user is feeling anxious, the device identifies the cause and presents countermeasure options.

[1793] Presenting the layout plan

[1794] The terminal presents the generated deployment plan to the user, for example, displaying a message such as, "Employee A is recommended as the leader of the sales department because he has a leadership score of 95 and has had excellent sales performance over the past five years. Employees B and C are also ideal team members."

[1795] Placement decision and implementation

[1796] The user reviews the proposed deployment plan, makes adjustments as necessary, and finally decides on the deployment. After the decision is made, the plan is put into action. For example, notifications reflecting the new organizational structure are sent to each employee, and the changes are reflected in related information systems (e.g., time attendance management systems, payroll management systems).

[1797] Monitoring and relearning deployment results

[1798] The server continuously monitors organizational performance after deployment, collecting data such as sales fluctuations, employee satisfaction, and project progress, and uses this data to adjust the parameters of the generative AI model. For example, the results can be visualized on a dashboard, and re-training can be performed to improve the accuracy of future deployment plans.

[1799] Specific examples

[1800] Example 1: Launching a new sales department

[1801] 1. A user enters the required skill sets and job titles to launch a new sales department into a terminal.

[1802] 2. The server analyzes data on all employees and identifies suitable candidates with strong sales skills and leadership abilities.

[1803] 3. The device suggests "Employee A" as a potential sales department leader and recommends "Employee B" and "Employee C" as team members.

[1804] 4. The emotion analysis means analyzes the user's reactions in real time, and if anxiety is high, identifies the reason and provides feedback.

[1805] 5. The user finally checks the revised deployment plan and decides on the deployment.

[1806] Example 2: Suggesting talent for a new project

[1807] 1. A user inputs the necessary skill set to start a new project (e.g., updating an IT system) into a terminal.

[1808] 2. The server analyzes employee data and identifies "Employee D," who has successfully completed similar projects in the past, as the project leader.

[1809] 3. The terminal recommends "Employee E" and "Employee F," who have strong development skills and have good project experience with "Employee D" in the past.

[1810] 4. The emotion analysis means analyzes the user's emotional state and checks whether they have a positive reaction to the recommended member. If they have a positive reaction, they will continue to recommend them, but if they have a negative reaction, they will re-evaluate and select alternative members.

[1811] 5. The user checks the recommendations, corrects them if necessary, and then decides on the placement.

[1812] Through this embodiment, enterprises can make the most of employees' characteristics and skills and realize optimal staffing planning that takes into account users' emotional states, thereby improving the efficiency and performance of the entire organization.

[1813] The flow of the identification process in the second embodiment will be described with reference to FIG.

[1814] Step 1:

[1815] The server collects data about employees' work history, achievements, strengths and weaknesses, characteristics, aspirations, and relationships from data sources such as a personnel management system, personnel evaluation system, and employee surveys. This is done using HTTP requests via APIs, with the input being the API endpoint and authentication information, and the output being a JSON-formatted response with employee data. For example, the server periodically accesses each endpoint, retrieves the required information, and stores it in a database.

[1816] Step 2:

[1817] The server preprocesses the collected data. Specifically, it first normalizes the data and unifies data in different formats. Next, it imputes missing values, for example, by using mean imputation or a predictive model. Statistical methods (e.g., Z-score) are used to detect outliers, and these are then corrected or removed. Finally, it removes duplicate data based on a unique identifier (e.g., employee ID). The input is the collected raw data, and the output is a clean dataset.

[1818] Step 3:

[1819] The server analyzes the preprocessed data and evaluates each employee's characteristics and skill set. This evaluation uses machine learning algorithms (random forest, SVM, neural network). The input is the preprocessed, clean dataset, and the output is an evaluation score for each employee (e.g., leadership score, technical score). Specifically, the server builds a model using scikit-learn or TensorFlow, inputs the data, and calculates the score.

[1820] Step 4:

[1821] The server trains a generative AI model based on the analysis results. Past deployment history and its results (e.g., sales increase rate, project success rate) are used as training data. The input is the evaluation score and past deployment history data, and the output is the trained generative AI model. Specifically, TensorFlow and PyTorch are used to train a deep learning model and find the optimal parameters.

[1822] Step 5:

[1823] The device integrates an emotion engine that analyzes the user's emotions in real time. This engine uses facial expression recognition and natural language processing technologies to analyze the emotions (e.g., joy, anger, anxiety) when the user interacts with the system. The input is the user's facial image and input text, and the output is the analyzed emotional state. For example, facial expressions are recognized using OpenCV, and text is analyzed using the Google Cloud Natural Language API.

[1824] Step 6:

[1825] The terminal receives input conditions from the user (e.g., details of a new project, required skill sets) and generates an optimal deployment plan using data obtained from the server and the generative AI model. Furthermore, the deployment plan is fine-tuned to reflect the user's emotional state analyzed by the sentiment analysis means. The input is a prompt from the user and the results of sentiment analysis, and the output is an optimal personnel deployment plan. For example, the terminal receives user input, sends a request to the server, and receives the optimal deployment plan. At that time, the sentiment analysis results are fed back to adjust the plan.

[1826] Step 7:

[1827] The terminal presents the generated deployment plan to the user. The input is the generated deployment plan, and the output is a display screen that the user can check. For example, it displays specific content such as, "Employee A is recommended as the leader of the sales department because he has a leadership score of 95 and has excellent sales performance over the past five years."

[1828] Step 8:

[1829] The user reviews the presented deployment plan and makes adjustments as necessary. Finally, the deployment is decided. After the decision is made, the plan is put into action. The input is the user's feedback and final decision, and the output is the implementation plan. For example, the user reviews the deployment plan and finally presses the approval button to finalize the plan.

[1830] Step 9:

[1831] The server continuously monitors organizational performance after deployment. It collects data such as sales fluctuations, employee satisfaction, and project progress, and uses this data to adjust the parameters of the generative AI model. The input is the post-deployment performance data, and the output is the adjusted generative AI model. For example, it periodically updates the dashboard, checks the monitoring results, and re-trains as necessary.

[1832] (Application example 2)

[1833] 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."

[1834] Creating optimal staffing plans that take into account information including employee characteristics, skills, and emotional states is extremely complex and cannot be easily achieved with conventional systems. Therefore, in order to maximize organizational efficiency and performance, it is necessary to analyze users' emotional states in real time and reflect them in staffing plans.

[1835] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 2 is realized by the following means.

[1836] In this invention, the server includes a means for collecting data on employee work history, achievements, strengths and weaknesses, characteristics, aspirations, and interpersonal relationships; a means for preprocessing and analyzing the collected data; and a means for training a generative AI model that predicts employee aptitude and placement based on the analysis results. This makes it possible to evaluate employee characteristics and skill sets and develop optimal placement plans. Furthermore, by integrating an emotion engine and including a means for analyzing the user's emotional state in real time and a means for adjusting the generated placement plan based on the emotion engine, it is possible to generate placement plans that are more in line with the user's intentions and emotions. Furthermore, by monitoring organizational performance after placement and improving the accuracy of the generative AI model, it is possible to improve placement accuracy in subsequent placements.

[1837] An "employee" is someone who belongs to a company or organization and performs their duties.

[1838] "Work history" refers to the job titles, positions, and employment history of an employee.

[1839] "Results" refers to the achievements and goal attainment achieved by an employee during their employment.

[1840] "Strengths and weaknesses" refer to the skills and abilities of individual employees, particularly those in which they excel and those in which they need improvement.

[1841] "Characteristics" refer to an employee's personality, behavioral patterns, communication style, etc.

[1842] "Hope" refers to an employee's desired working conditions, career path, placement, and other requests.

[1843] "Interpersonal relationships" refers to interactions between employees and relationships within the workplace.

[1844] "Data collection tools" refer to methods and systems for obtaining various information about employees.

[1845] "Preprocessing and analysis methods" refer to the processes and tools used to convert collected raw data into an analyzable format and remove unnecessary data.

[1846] A "generative AI model" is an artificial intelligence model trained using machine learning algorithms to make predictions and optimizations.

[1847] A "learning tool" is a method or algorithm that trains a generative AI model based on data to improve its accuracy.

[1848] An "optimal staffing plan" is a plan that allocates employees in the most efficient and effective way, taking into account their skills, characteristics, and emotional state.

[1849] A "project member suggestion tool" is a method or system that recommends employees with the skills and characteristics required for a particular project.

[1850] "Monitoring measures" refer to methods and tools for continuously observing and collecting data on the results and status of employees after placement.

[1851] An "emotion engine" is a technology that analyzes a user's emotional state in real time and adjusts the system's behavior based on the results.

[1852] The "adjustment means" refers to a method or system for optimizing the generated placement plan based on information obtained from the emotion engine.

[1853] This invention is a system that analyzes employee information and generates optimal personnel allocation plans, and by combining it with an emotion engine, provides allocation plans that take into account the emotional state of the user. The main components of the system include a server, a terminal, and a user.

[1854] Server Features

[1855] The server first collects data about employees, including work history, achievements, strengths and weaknesses, characteristics, aspirations, and relationships, from data sources such as the personnel management system, personnel evaluation system, and employee surveys. This data is updated regularly, ensuring that the latest information is always analyzed.

[1856] After collecting the data, the server preprocesses the data by normalizing it, imputing missing values, detecting and correcting outliers, removing duplicates, etc. This process creates a clean dataset suitable for analysis.

[1857] Using the preprocessed data, the characteristics and skill sets of each employee are evaluated, and a machine learning algorithm (e.g., RandomForestClassifier) ​​is used to build a generative AI model, which is trained using past deployment history and its results (e.g., sales increase, project success rate).

[1858] Device Features

[1859] The device is equipped with an emotion engine that analyzes emotions (e.g., joy, anger, anxiety) expressed by users in real time as they operate the system. Upon receiving input from the user (e.g., details of a new project, required skill sets), the system generates an optimal deployment plan using data obtained from the server and a generative AI model.

[1860] The generated placement plan is fine-tuned based on the analysis results of the emotion engine. The device then suggests the most suitable project members and presents them to the user. The user can review this, make adjustments as necessary, and decide on the final placement.

[1861] User Roles

[1862] Users input new projects and required skill sets through their devices, review the proposed deployment plan, and make adjustments or final decisions. The system analyzes the user's emotional state in real time, and adjusts the deployment plan based on their feedback.

[1863] Hardware and software used

[1864] The hardware used includes a server that collects and processes data, a terminal that interfaces with the emotion engine, and a user interface. The software includes a database system (e.g., HRDatabase), machine learning algorithms (e.g., RandomForestClassifier), and an emotion engine (e.g., EmotionEngine).

[1865] Specific examples

[1866] For example, a user can input the skill sets and job titles required to set up a new assembly line. The system then analyzes employee data and sensor data to suggest suitable employees. Based on the user's emotional response, the emotion engine makes real-time adjustments and presents the optimal placement plan.

[1867] Prompt Sentence Examples

[1868] "Nominate candidates for new assembly line leaders. Required skill sets include electrical engineering, robotics, and leadership."

[1869] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[1870] Processing Steps

[1871] Step 1: Data collection

[1872] The server collects data on employees' work history, achievements, strengths and weaknesses, characteristics, aspirations, and relationships from data sources such as a personnel management system, a personnel evaluation system, and employee surveys.

[1873] Input: Raw data from each data source.

[1874] Data processing and calculation: Query the database and extract the required information.

[1875] Output: A collection of collected raw data.

[1876] Step 2: Data Preprocessing

[1877] The server preprocesses the collected data, specifically normalizing the data, imputing missing values, detecting and correcting outliers, and eliminating duplicate data.

[1878] Input: The raw data collected.

[1879] Data processing and calculation: Apply data cleansing algorithms to shape the data.

[1880] Output: A clean dataset.

[1881] Step 3: Characterization and evaluation

[1882] The server analyzes the pre-processed data and evaluates each employee's characteristics and skill set using machine learning algorithms to calculate an evaluation score for each employee.

[1883] Input: A clean dataset.

[1884] Data processing and calculation: Feature extraction and evaluation score calculation (e.g., using RandomForestClassifier).

[1885] Output: Evaluation score for each employee.

[1886] Step 4: Training the generative AI model

[1887] The server trains a generative AI model based on the analysis results. This model includes an algorithm for predicting optimal employee placement, using past placement history and results as training data.

[1888] Input: Employee evaluation scores and past placement history data.

[1889] Data processing and calculation: Execute the model training process.

[1890] Output: A trained generative AI model.

[1891] Step 5: Integrating the Emotion Engine

[1892] The device is equipped with an emotion engine that recognizes the user's emotions and analyzes the emotions expressed when the user operates the system in real time.

[1893] Input: Facial expressions and behavioral data during user operation.

[1894] Data processing and computation: Application of emotion recognition algorithms.

[1895] Output: Real-time analysis of the user's emotional state.

[1896] Step 6: Generate and refine optimal layout plans

[1897] The device receives input conditions from the user and generates an optimal placement plan using data obtained from the server and the generative AI model.The device then fine-tunes the placement plan by reflecting the user's emotional state analyzed by the emotion engine.

[1898] Input: User input conditions, trained generative AI model, and emotion engine analysis results.

[1899] Data processing and calculation: Implementing optimal placement algorithms and reflecting emotional states.

[1900] Output: The adjusted optimal placement plan.

[1901] Step 7: Present the layout plan

[1902] The terminal presents the generated placement plan to the user.

[1903] Input: The adjusted optimal placement plan.

[1904] Data processing and calculation: Visualization and presentation of layout plans.

[1905] Output: Deployment plan information for the user.

[1906] Step 8: Deployment and Implementation

[1907] The user checks the proposed deployment plan, makes adjustments as necessary, and finally decides on the deployment. After the decision is made, the plan is put into action.

[1908] Input: Proposed layout plan.

[1909] Data processing and calculation: Final confirmation and adjustment by the user.

[1910] Output: Final placement decision and implementation.

[1911] Step 9: Monitoring deployment results and retraining

[1912] The server monitors organizational performance after deployment, continuously observing and collecting data on sales fluctuations, employee satisfaction, project progress, etc. Based on the results of this monitoring, the parameters of the generative AI model are adjusted and re-trained.

[1913] Input: Post-placement organizational outcome data.

[1914] Data processing and calculation: Analyzing performance data and re...

Claims

1. A means of collecting data on employees' work history, achievements, strengths and weaknesses, characteristics, aspirations, and relationships; A means of preprocessing and analyzing the collected data; Based on the analysis results, a means of training a generative AI model that predicts employee aptitude and placement, and A means for generating an optimal staffing plan using the learned generative AI model; A means of suggesting appropriate project members, A means to monitor organizational performance after deployment and improve the accuracy of the generative AI model; A system including:

2. 2. The system according to claim 1, further comprising means for detecting and correcting duplicate data and incomplete data from the collected data.

3. The system according to claim 1 , further comprising means for adjusting parameters of the generative AI model and performing re-learning based on the monitoring results.

Images