System

Abstract

A system is provided.SOLUTION: A system comprising: means for collecting personnel information from each department or organization; means for complementing missing values of the collected personnel information and detecting and correcting abnormal values; means for analyzing characteristics of active personnel using generated AI based on the preprocessed personnel information; means for generating an optimal personnel allocation plan based on the characteristics of the active personnel; and means for informing a user of the generated allocation plan.SELECTED DRAWING: Figure 1

Description

[Technical Field]

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

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

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

[0004] In the past, companies have relied mainly on experience and intuition to assign, promote, and hire personnel. However, this has the following problems:

[0005] 1. Mismatches in personnel are likely to occur.

[0006] 1. Lack of proper promotion leads to a decrease in organizational efficiency.

[0007] 1. It is difficult to properly evaluate job applicants, making it difficult to hire talented personnel.

[0008] These problems cause companies to suffer from high employee turnover and low productivity. Therefore, it is necessary to provide a system that solves these problems and realizes optimal personnel allocation, promotion, and recruitment. [Means for solving the problem]

[0009] The present invention solves these problems by the following means.

[0010] The system includes a means for collecting personnel information from each department and organization, a means for complementing missing values ​​in the collected personnel information and detecting and correcting outliers, a means for analyzing the characteristics of active personnel using a generation AI based on the preprocessed personnel information, a means for generating an optimal personnel placement plan based on the characteristics of active personnel, a means for notifying a user of the above-generated placement plan, and a means for cleansing data of job applicants and generating interview questions.

[0011] The present invention also provides a system that further includes a means for defining promotion requirements using a generation AI based on preprocessed human resource information, thereby optimizing promotions.

[0012] Furthermore, the present invention builds an active talent model based on the preprocessed talent information, thereby realizing efficient and effective talent management.

[0013] A "department" is a division within a company organized for a specific task or function.

[0014] An "organization" is a group of people formed to work toward a common goal.

[0015] "Human resource information" refers to various data about employees, such as employee performance data, skill sheets, and evaluation information.

[0016] "Missing values" are pieces of information that are missing in a dataset.

[0017] An "outlier" is a value that is significantly different from the other data in a dataset.

[0018] "Preprocessing" is the process of complementing data and correcting outliers before analysis.

[0019] "Generative AI" refers to algorithms that use artificial intelligence technology to generate new insights and models from data.

[0020] "High-performing employees" are employees who demonstrate outstanding performance based on specific criteria.

[0021] "Feature analysis" is the process of extracting significant characteristics or patterns from data.

[0022] A "placement plan" is a plan that proposes the optimal placement and roles for employees.

[0023] "Notification" is the act of informing the user of important information.

[0024] A "job applicant" refers to an individual who applies to a company in search of a new position.

[0025] "Cleansing" is the process of removing and correcting duplicates and inconsistencies in data to improve data quality.

[0026] "Interview questions" are questions used to evaluate an applicant's aptitude and skills.

[0027] "Promotion requirements" are the criteria that define the skills and experience necessary to be promoted to a particular position.

[0028] A "model" is a mathematical or algorithmic framework that represents a particular pattern or phenomenon based on data. [Brief explanation of the drawings]

[0029] [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

[0030] 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.

[0031] First, the terms used in the following description will be explained.

[0032] 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).

[0033] 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.

[0034] 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.

[0035] 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.

[0036] 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."

[0037] [First embodiment]

[0038] FIG. 1 shows an example of the configuration of a data processing system 10 according to the first embodiment.

[0039] 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.

[0040] 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).

[0041] 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.

[0042] 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.

[0043] 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.

[0044] 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.

[0045] FIG. 2 shows an example of the main functions of the data processing device 12 and the smart device 14.

[0046] 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.

[0047] 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.

[0048] 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.

[0049] 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."

[0050] The present invention is a system for optimizing personnel allocation, promotion, and recruitment in a company. This system collects personnel information from each department within the company, preprocesses the collected data, and analyzes it to achieve optimal personnel management. Below, we will describe in detail the embodiments for implementing the system of the present invention.

[0051] Data collection methods

[0052] server

[0053] Build a system to automatically collect personnel information from each department, including employee performance data, skill sheets, performance evaluations, and 360-degree reviews.

[0054] Set up a system to periodically retrieve information using APIs or database queries.

[0055] Specific examples

[0056] The server collects sales results from the sales department, campaign performance evaluations from the marketing department, and technical evaluations from the technical department.

[0057] Data preprocessing methods

[0058] server

[0059] Implement algorithms to impute missing values ​​and detect and correct outliers in the collected data, thereby ensuring data quality.

[0060] Specific examples

[0061] The server imputes missing values ​​using the KNN method and detects and corrects outliers using Z-scores.

[0062] Analysis of the characteristics of successful personnel

[0063] server

[0064] The pre-processed data is then fed into an AI model (such as clustering or regression analysis) to extract the characteristics of successful employees, thereby identifying patterns of employees who will be successful in a particular role or department.

[0065] Specific examples

[0066] The server uses a clustering algorithm (K-means) to analyze the patterns of successful sales personnel. As a result, it finds that those with "high communication skills," "initiative," and "excellent problem-solving abilities" are more likely to succeed.

[0067] Form of generating optimal staffing plan

[0068] server

[0069] Implement an algorithm that generates optimal placement plans for existing employees based on the characteristics of successful employees, taking into account the employee's skill set, desired placement, and performance.

[0070] Specific examples

[0071] The server generates a proposal to place technical employee X as a leader of a new project based on his skill set and past performance.

[0072] Form of definition of promotion requirements

[0073] server

[0074] Define promotion requirements based on the characteristics of your top performers. These requirements are based on specific competencies, skill sets, and past performance.

[0075] Specific examples

[0076] Server defines the promotion requirements for managers as "strong leadership," "experience in supervising subordinates," and "project management skills."

[0077] Cleansing applicant information and generating interview questions

[0078] server

[0079] We will build a system that collects and cleans information on job applicants and automatically generates questions to be used in interviews.

[0080] Specific examples

[0081] The server extracts career data from applicant Y's resume, removes duplicate and inconsistent data, and then generates interview questions such as "What was the most difficult problem you solved in your previous job?" and "What kind of leadership experience do you have?"

[0082] Notifications and User Interface Forms

[0083] server

[0084] Implement a system to notify users of generated placement proposals, promotion requirements, and interview questions, allowing them to make data-driven decisions.

[0085] User

[0086] The user will then make optimal personnel allocation, promotion, and recruitment decisions based on the information provided. The system aims to have an interface that allows users to operate it efficiently and effectively.

[0087] Specific examples

[0088] Human resources personnel log in to the system to check the optimal personnel placement plans for new departments, and also use it to set promotion requirements and interview job applicants.

[0089] The system of the present invention performs data collection, preprocessing, analysis, and notification in an integrated manner, thereby enhancing a company's human resource management, reducing employee turnover and improving productivity.

[0090] The processing flow will be explained below.

[0091] Program processing steps

[0092] Step 1:

[0093] server

[0094] Collect human resource information from each department, including performance data, skill sheets, performance reviews, and 360-degree evaluations, using APIs and database queries.

[0095] Specific actions

[0096] 1. Send a request to an API endpoint to retrieve data from each department's system.

[0097] 2. Run an SQL query to extract historical performance data from the database.

[0098] Step 2:

[0099] server

[0100] Preprocessing of collected data is performed, specifically, missing values ​​are complemented and outliers are detected and corrected.

[0101] Specific actions

[0102] 1. Run the missing value imputation algorithm (KNN method) to estimate and impute missing data.

[0103] 2. An outlier detection algorithm (Z-score) is used to correct abnormal data points.

[0104] Step 3:

[0105] server

[0106] The preprocessed data is used to analyze the characteristics of successful employees, specifically through clustering and regression analysis.

[0107] Specific actions

[0108] 1. Run a clustering algorithm (K-means) to classify the personnel into multiple groups.

[0109] 2. Use regression analysis to assess the contribution of specific skills and achievements to success.

[0110] Step 4:

[0111] server

[0112] Generate optimal employee placement recommendations based on the characteristics of top performers, taking into account employee skill sets, performance, and individual placement preferences.

[0113] Specific actions

[0114] 1. Use the Thriving Talent Model to map each employee's skill set to the job needs.

[0115] 2. Use a selection algorithm to suggest the best department and role.

[0116] Step 5:

[0117] server

[0118] Define promotion requirements, including specific competencies, skill sets, and past performance.

[0119] Specific actions

[0120] 1. Use a decision tree algorithm to define the requirements for promotion.

[0121] 2. Save the defined requirements in the database and notify the person in charge.

[0122] Step 6:

[0123] server

[0124] Cleanse job applicant data and generate interview questions.

[0125] Specific actions

[0126] 1. Run data cleansing algorithms to remove inconsistencies and duplicate data.

[0127] 2. Uses Natural Language Processing (NLP) technology to generate appropriate interview questions from applicants' resumes.

[0128] Step 7:

[0129] server

[0130] The generated placement proposals, promotion requirements, and interview questions are notified to the user.

[0131] User

[0132] Based on the information provided, specific decisions regarding personnel placement, promotion, and hiring are made.

[0133] Specific actions

[0134] 1. Generates a notification containing the analysis results and displays it on the user's dashboard.

[0135] 2. The user logs into the system to review and use the suggestions.

[0136] In this way, this system enhances a company's human resource management through a series of steps, including data collection, analysis of the characteristics of successful personnel, generation of optimal placement plans, definition of promotion requirements, and processing related to job applicants.

[0137] Example 1

[0138] 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."

[0139] Conventional human resource management systems have the problem that it is difficult to efficiently grasp the skills and performance of individual employees, cooperation between departments, and the appropriateness of promotions and placements, making it difficult to contribute to improving productivity and turnover rates across the company.In addition, collecting information on job applicants and preparing for interviews requires a great deal of effort and time, so there was a need for efficiency improvements.

[0140] 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.

[0141] In this invention, the server includes: means for collecting human resource information from each department and organization; means for completing missing values ​​in the collected human resource information and detecting and correcting outliers; means for analyzing the characteristics of active personnel using a generative AI model based on the preprocessed human resource information; means for generating an optimal human resource placement plan based on the characteristics of active personnel; means for notifying a user of the generated placement plan; means for cleansing job applicant data and generating interview questions; means for generating an optimal human resource placement plan taking into account employee skill sets, desired placements, and performance; and means for notifying a user of the generated interview questions and supporting job applicant interviews. This improves the efficiency of human resource management across the company, realizes appropriate human resource placement and promotion, and simplifies job applicant interview preparation, thereby improving corporate productivity and reducing employee turnover.

[0142] "Human resource information" refers to information including the performance, skills, work evaluations, and 360-degree evaluations of employees working in each department and organization of a company.

[0143] "Missing values" are values ​​that are missing in a dataset and are a factor that impairs the accuracy of data analysis.

[0144] An "outlier" is a value in a dataset that is significantly different from other data and may affect the results of data analysis.

[0145] A "generative AI model" is an algorithm that uses artificial intelligence to extract and analyze specific patterns and features from data.

[0146] "Characteristics of successful employees" refer to the skills and characteristics common to employees who achieve outstanding results in specific roles or departments within a company.

[0147] A "staffing proposal" is a plan that proposes the optimal staffing arrangement within a company, and is generated based on employees' skill sets, performance, desired placement, etc.

[0148] "Notification" is the act of informing the user of important information such as the generated personnel allocation plan and interview questions.

[0149] "Cleansing" is the process of detecting, deleting, or correcting duplicates and inconsistencies in data collected from a database.

[0150] "Interview questions" are questions used during interviews with job applicants or employees, and are used to evaluate the applicant's abilities and experience.

[0151] A "skill set" is the collection of skills and abilities that a particular employee possesses.

[0152] "Desired placement" refers to the department or role that an employee desires.

[0153] "Performance" refers to an employee's past achievements and evaluations in performing their duties.

[0154] The above definitions allow each element of the system to be clearly understood.

[0155] The present invention is a system for optimizing personnel allocation, promotion, and recruitment in a company. This system collects personnel information from each department within the company, preprocesses the collected data, and analyzes it to achieve optimal personnel management. Below, we will describe in detail the embodiments for implementing the system of the present invention.

[0156] Data collection methods

[0157] server

[0158] The server automatically collects personnel information such as employee performance data, skill sheets, work evaluations, and 360-degree evaluations from each department of the company. This information is periodically retrieved using APIs and database queries. Specifically, it collects sales performance from the sales department, campaign success evaluations from the marketing department, and technical evaluations from the technical department.

[0159] Data preprocessing methods

[0160] server

[0161] The server runs algorithms to impute missing values ​​in the collected data and to detect and correct outliers, for example, imputing missing values ​​using the KNN (k-Nearest Neighbors) method and detecting outliers using Z-scores.

[0162] Analysis of the characteristics of successful personnel

[0163] server

[0164] The server inputs the preprocessed data into a generative AI model (such as clustering or regression analysis) to extract the characteristics of successful employees. Specifically, the K-means clustering algorithm can be used to analyze successful employees in the sales department. The results show that those with "high communication skills," "proactive action," and "excellent problem-solving abilities" are more likely to succeed.

[0165] Form of generating optimal staffing plan

[0166] server

[0167] The server generates optimal personnel placement proposals based on the characteristics of active personnel, taking into account the employee's skill set, desired placement, and performance. For example, it generates a proposal to place employee X in the technical department as a leader of a new project based on his skill set and past performance.

[0168] Form of definition of promotion requirements

[0169] server

[0170] The server defines promotion requirements based on the characteristics of successful employees. These requirements are set based on specific abilities, skill sets, and past performance. For example, the server defines "high leadership," "experience in mentoring subordinates," and "project management ability" as promotion requirements for managerial positions.

[0171] Cleansing applicant information and generating interview questions

[0172] server

[0173] The server collects and cleans information on job applicants and automatically generates interview questions. Specifically, it extracts resume data for applicant Y, deletes inconsistent and duplicate data, and then generates interview questions such as "What was the most difficult problem you solved in your previous job?" and "What kind of leadership experience do you have?"

[0174] Notifications and User Interface Forms

[0175] server

[0176] The server implements a system that notifies the user of the generated placement proposals, promotion requirements, and interview questions, allowing the user to make data-based decisions.

[0177] User

[0178] Based on the information provided, users can make optimal personnel placements, promotions, and hiring decisions. The system provides an interface that users can use efficiently and effectively. Specifically, human resources personnel can log in to the system, check the optimal personnel placement proposals for new departments, and use the results to set promotion requirements and interview job applicants.

[0179] Prompt Sentence Examples

[0180] "Analyze patterns of successful talent using sales performance and campaign success evaluation data."

[0181] "Generate a placement plan to select the best person to lead a new project in the technology department."

[0182] "Extract applicant biographical data and generate interview questions."

[0183] This system will enhance a company's human resource management by consistently collecting, preprocessing, analyzing, and notifying data, thereby reducing employee turnover and improving productivity.

[0184] The flow of the identification process in the first embodiment will be described with reference to FIG.

[0185] Step 1:

[0186] Data collection

[0187] The server has a means of collecting human resource information from each department and organization. In this case, the input is information such as employee performance data, skill sheets, work evaluations, and 360-degree evaluations stored in each department's database. The server periodically obtains the necessary information using API requests and database queries. The server then stores the obtained data in storage. For example, the server might collect sales performance from the sales department, campaign success evaluations from the marketing department, and technical evaluations from the technical department.

[0188] Step 2:

[0189] Data Preprocessing

[0190] The server preprocesses the collected data. The input is the raw data collected in step 1. Specifically, the server first detects missing values ​​in the data and imputes them using the KNN (k-Nearest Neighbors) method. Next, it calculates Z-scores to detect outliers. If an outlier is found, the server corrects or removes it. The final output is clean data with missing and outlier values ​​corrected.

[0191] Step 3:

[0192] Analysis of the characteristics of successful personnel

[0193] The server inputs the clean data into the generative AI model and analyzes the characteristics of successful employees. The input is the data preprocessed in step 2. Specifically, the server runs the K-means clustering algorithm. It analyzes the clustering results and identifies the characteristics of each cluster. These characteristics include "good communication skills," "proactive action," and "excellent problem-solving ability." The output is a list of the characteristics of successful employees.

[0194] Step 4:

[0195] Generate optimal staffing plans

[0196] The server generates a personnel placement plan based on the characteristics of the active personnel. The inputs are the characteristics of the active personnel obtained in step 3, the employee's skill set, desired placement, and performance data. Specifically, the server compares each employee's data with the characteristics of the active personnel to generate an optimal placement plan. For example, the server references the skill set and past performance of employee X in the technical department and generates a plan to place him as the leader of a new project. The output is an optimal personnel placement plan.

[0197] Step 5:

[0198] Define promotion requirements

[0199] The server defines promotion requirements based on the characteristics of successful employees. The input is the list of characteristics obtained in step 3. Specifically, the server extracts the abilities, skill sets, and experience required for a specific position from the characteristics of successful employees. For example, it defines "high leadership," "experience in supervising subordinates," and "project management ability" as promotion requirements for managerial positions. The output is a list of described promotion requirements.

[0200] Step 6:

[0201] Cleansing applicant information and generating interview questions

[0202] The server cleanses the information of job applicants and generates interview questions. The input is the resume data of job applicants. Specifically, the server analyzes the resume data and removes or corrects duplicate and inconsistent data. Next, based on the cleansed data, it generates questions to be used in interviews. For example, it generates questions such as "What was the most difficult problem you solved in your previous job?" and "What kind of leadership experience do you have?" The output is the cleansed applicant information and the generated interview questions.

[0203] Step 7:

[0204] Notifications and User Interface

[0205] The server notifies the user of the generated placement plans, promotion requirements, and interview questions. The input is the output of steps 4, 5, and 6. Specifically, the server presents the generated results to the user in the form of a dashboard or email notification. The user then uses the notified information to make optimal personnel placements, promotions, and recruitment. For example, a human resources officer logs into the system, checks the optimal personnel placement plans for a new department, and uses this information to set promotion requirements and interview job applicants. The output is a notification to the user and an interface that the user can use.

[0206] (Application example 1)

[0207] 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."

[0208] In conventional factories, managing robot operating status and maintenance schedules required individual data management and manual adjustments, making it difficult to achieve optimal operating efficiency and maintenance plans. Furthermore, the collection and analysis of human resource information required a great deal of effort, preventing optimal personnel placement and promotion. There is a need to improve this situation and increase the efficiency and productivity of factories and organizations as a whole.

[0209] 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.

[0210] In this invention, the server includes: means for collecting human resource information from each department and organization; means for completing missing values ​​in the collected human resource information and detecting and correcting outliers; means for analyzing the characteristics of active human resources using a generation AI based on the preprocessed human resource information; means for generating an optimal human resource deployment plan based on the characteristics of active human resources; means for notifying a user of the generated deployment plan; means for collecting operation information, work efficiency, and maintenance history; means for preprocessing the collected operation information and detecting and correcting outliers; means for generating an optimal robot deployment plan and maintenance schedule using a generation AI based on the preprocessed operation information; means for cleansing job applicant data and generating interview questions; and means for providing a user interface for confirming the optimal deployment and schedule based on the notified information. This enables optimization of the operating efficiency of robots in factories, formulation of preventative maintenance schedules, and appropriate human resource deployment and promotion.

[0211] "Each department or organization" refers to different divisions, teams, or functional groups within a company or factory.

[0212] "Human resources information" refers to relevant data about employees and job seekers, such as performance, skills, evaluations, and work history.

[0213] "Means of collection" refers to the systems and methods for obtaining the necessary information through various databases and APIs.

[0214] "Missing value imputation" refers to the process of estimating and filling in missing values ​​in a dataset.

[0215] "Outlier detection and correction" refers to the process of finding values ​​in a data set that are outside of the normal range and changing them to appropriate values.

[0216] "Preprocessed human resources information" refers to clean data that has been collected and has undergone missing value imputation and outlier correction.

[0217] "Generative AI" refers to artificial intelligence algorithms used to rapidly analyze large amounts of data and extract specific patterns and features.

[0218] "High-performing talent" refers to employees who perform well in specific conditions or roles.

[0219] "Means for analyzing features" means methods that use data analytics and machine learning algorithms to extract trends and patterns from data.

[0220] "Optimal human resource allocation plan" refers to the assignment of departments and projects that allow employees to work most effectively.

[0221] "Means for notifying the user" refers to an interface or method for notifying the user of generated information or results.

[0222] "Operational information" refers to data on how robots and systems are actually operating.

[0223] "Work efficiency" refers to the ratio of productive output to effort put in.

[0224] "Maintenance history" means a record of the maintenance that a device or system has undergone.

[0225] An "allocation plan" refers to a plan for how to allocate equipment and personnel to operating departments or specific projects.

[0226] A "maintenance schedule" refers to a schedule for systematically carrying out maintenance work on equipment and systems.

[0227] "Job applicants" refers to individuals who have applied for a new position.

[0228] "Data cleansing" refers to the process of removing unnecessary information from raw data and preparing it for analysis.

[0229] "Interview questions" refer to questions used in interviews.

[0230] "User interface" refers to the screens and operating methods that allow users to directly interact with a system.

[0231] This invention is a system that collects and analyzes data on the operational status, work efficiency, and maintenance history of robots in factories, and generates optimal robot placement and maintenance schedules. This system performs all processes, from collecting data on operational information, work efficiency, and maintenance history to notifying users of the placement plans and schedules it generates.

[0232] Data collection

[0233] The server has a means to automatically collect operational information, work efficiency, and maintenance history from each robot operating in the factory. This collection process is carried out through sensors installed on each robot and API, and the data is sent to the server.

[0234] Examples:

[0235] The server collects operating hours, number of completed tasks, and recent maintenance history from each robot in the factory via an API.

[0236] Data Preprocessing

[0237] The server implements algorithms to fill in missing values ​​in the collected data and detect and correct outliers, a process that ensures data quality and enables accurate analysis.

[0238] Examples:

[0239] Missing values ​​in the dataset collected by the server are imputed using the KNN method, and outliers are detected and corrected using Z scores.

[0240] Generation of optimal robot placement plans and maintenance schedules

[0241] Based on the pre-processed data, generative AI models (such as clustering and regression analysis) are used to generate optimal robot placement plans and maintenance schedules. The results suggest the most efficient use of robots in factory operations.

[0242] Examples:

[0243] The server uses a clustering algorithm (K-means) to analyze the operating patterns of each robot and identify robots with "high operating time," "efficient task completion," and "low maintenance frequency."

[0244] Notification of placement plan and schedule

[0245] The generated optimal deployment plan and maintenance schedule are notified to the user. The server is responsible for this notification process, and the information is displayed and shared through the user interface.

[0246] Examples:

[0247] The server notifies the user of the generated deployment plan and maintenance schedule via email or a dedicated dashboard.

[0248] Based on the information provided, users can plan optimal robot placement and maintenance, improving productivity and efficiency within their factories.

[0249] Example prompt sentence:

[0250] Input the operation data and maintenance history data of the robots in the factory, analyze the characteristics of the active robots, and generate optimal placement plans and maintenance schedules.

[0251] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[0252] Step 1:

[0253] The server collects operational information, work efficiency, and maintenance history from the robots operating in the factory via API. The input is data from each robot's sensors and internal systems, which is obtained via API. The output is a raw dataset that we use for preprocessing. This dataset includes each robot's operating time, number of completed tasks, and maintenance history.

[0254] Step 2:

[0255] The server performs preprocessing of the collected data. First, it performs missing value imputation. It uses KNN imputation to estimate and fill missing values ​​in the dataset. Next, it performs outlier detection and correction. It uses Z-score to detect data points that fall outside the normal range and corrects them. This ensures the quality of the data. The input is the original dataset collected in step 1, and the output is clean data with missing and outlier values ​​corrected.

[0256] Step 3:

[0257] The server inputs the preprocessed data into the generative AI model to analyze the robot's operating patterns. A clustering algorithm (e.g., K-means) is used for this analysis. The input is the clean data generated in step 2, and the output is the robot patterns classified by cluster. Specifically, the feature values ​​of each robot (operating time, work efficiency, etc.) are input into the algorithm to perform clustering.

[0258] Step 4:

[0259] The server uses the generative AI model to generate optimal robot placement plans and maintenance schedules. The input is the data classified by cluster in Step 3. Based on the data, it formulates placement plans for robots with high operating efficiency and a corresponding preventive maintenance schedule. The output is the optimal placement plan and maintenance schedule. Specifically, based on the characteristics of each cluster, it determines which robots should be placed in which areas and when maintenance is required.

[0260] Step 5:

[0261] The server notifies the user of the generated deployment plan and maintenance schedule. Notifications are made via email or a dedicated dashboard. The input is the deployment plan and maintenance schedule generated in step 4, and the output is the information displayed on the user's operation screen. Specifically, the generated information is converted into an appropriate format and displayed through the user interface.

[0262] Step 6:

[0263] The user checks the notified deployment plan and maintenance schedule and puts them into action. The input is the information displayed in step 5. The user makes the necessary adjustments based on the optimal deployment plan and schedule to optimize the operation of the robots. The output is the adjusted operation plan and maintenance schedule. In concrete terms, the user deploys each robot and performs maintenance work on-site based on the notified content.

[0264] 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.

[0265] The present invention achieves more effective human resource management than ever before by combining a system for optimizing personnel allocation, promotion, and recruitment in a company with a new emotion engine that recognizes user emotions. Below, a detailed description is given of an embodiment of the system of the present invention.

[0266] Data collection methods

[0267] server

[0268] Build a system to automatically collect personnel information from each department, including employee performance data, skill sheets, performance evaluations, and 360-degree reviews.

[0269] Set up a system to periodically retrieve information using APIs or database queries.

[0270] Specific examples

[0271] The server collects sales results from the sales department, campaign performance evaluations from the marketing department, and technical evaluations from the technical department.

[0272] Data preprocessing methods

[0273] server

[0274] Implement algorithms to impute missing values ​​and detect and correct outliers in the collected data, thereby ensuring data quality.

[0275] Specific examples

[0276] The server imputes missing values ​​using the KNN method and detects and corrects outliers using Z-scores.

[0277] Analysis of the characteristics of successful personnel

[0278] server

[0279] The pre-processed data is then fed into an AI model (such as clustering or regression analysis) to extract the characteristics of successful employees, thereby identifying patterns of employees who will be successful in a particular role or department.

[0280] Specific examples

[0281] The server uses a clustering algorithm (K-means) to analyze the patterns of successful sales personnel. As a result, it finds that those with "high communication skills," "initiative," and "excellent problem-solving abilities" are more likely to succeed.

[0282] Form of generating optimal staffing plan

[0283] server

[0284] We will implement an algorithm that generates optimal employee placement plans based on the characteristics of successful employees, taking into account the employee's skill set, desired placement, performance, and even user sentiment.

[0285] Specific examples

[0286] The server generates a proposal to appoint Employee X in the technical department as a leader of a new project based on his skill set and past performance. It also analyzes Employee X's emotional information using an emotion engine to confirm that his stress level is low.

[0287] Form of definition of promotion requirements

[0288] server

[0289] Define promotion requirements based on the characteristics of your top performers. These requirements are based on specific competencies, skill sets, and past performance, as well as emotional information provided by the emotion engine.

[0290] Specific examples

[0291] Sarver defines the promotion requirements for managers as "high leadership," "experience in supervising subordinates," and "project management skills," and adds "stable emotional control ability."

[0292] Cleansing applicant information and generating interview questions

[0293] server

[0294] We will build a system that collects and cleans information on job applicants and automatically generates questions to be used in interviews. Furthermore, we will obtain the user's emotional information in real time during the interview and provide adaptive questions.

[0295] Specific examples

[0296] The server extracts career data from applicant Y's resume, removes duplicate and inconsistent data, and then generates questions to be used in the interview, such as "What was the most difficult problem you solved in your previous job?" and "What kind of leadership experience do you have?" During the interview, the emotion engine recognizes the emotions of the users (interviewer and applicant), and if they are feeling stressed, it inserts questions to help them relax.

[0297] Notifications and User Interface Forms

[0298] server

[0299] Implement a system to notify users of generated placement proposals, promotion requirements, and interview questions, allowing them to make data-driven decisions.

[0300] User

[0301] The user will then make optimal personnel allocation, promotion, and recruitment decisions based on the information provided. The system aims to have an interface that allows users to operate it efficiently and effectively.

[0302] Specific examples

[0303] Human resources personnel log in to the system and check the optimal personnel placement plan for new departments, and also use it to set promotion requirements and interview job applicants. They also consider the emotional data provided by the emotion engine to make optimal decisions.

[0304] The system of the present invention performs data collection, preprocessing, analysis, emotion recognition, and notification in an integrated manner, thereby enhancing a company's human resource management, reducing employee turnover and improving productivity.

[0305] The processing flow will be explained below.

[0306] Program processing steps

[0307] Step 1:

[0308] server

[0309] Collect human resource information from each department, including performance data, skill sheets, performance reviews, and 360-degree evaluations, using APIs and database queries.

[0310] Specific actions

[0311] 1. Send requests to API endpoints to retrieve data from each department's system.

[0312] 2. Run an SQL query to extract historical performance data from the database.

[0313] Step 2:

[0314] server

[0315] Preprocessing of collected data is performed, specifically, missing values ​​are complemented and outliers are detected and corrected.

[0316] Specific actions

[0317] 1. Run the missing value imputation algorithm (KNN method) to estimate and impute missing data.

[0318] 2. Correct anomalous data points using an outlier detection algorithm (Z-score).

[0319] Step 3:

[0320] server

[0321] The preprocessed data is used to analyze the characteristics of successful employees, specifically through clustering and regression analysis.

[0322] Specific actions

[0323] 1. Run a clustering algorithm (K-means) to classify the personnel into multiple groups.

[0324] 2. Use regression analysis to assess the contribution of specific skills and achievements to success.

[0325] Step 4:

[0326] server

[0327] Generate optimal employee placement plans based on the characteristics of top performers, taking into account employee skill sets, desired placements, performance, and even user sentiment.

[0328] Specific actions

[0329] 1. Use a talent model to map each employee's skill set to the needs of the job.

[0330] 2. Use a selection algorithm to suggest the best departments and roles.

[0331] 3. Analyze emotional data from the emotion engine and adjust placement recommendations based on the employee's current emotional state.

[0332] Step 5:

[0333] server

[0334] Define promotion requirements based on specific competencies, skill sets, and past performance, as well as emotional information provided by the emotion engine.

[0335] Specific actions

[0336] 1. Use a decision tree algorithm to define the requirements for promotion.

[0337] 2. Adjust the defined requirements taking into account the data from the emotion engine.

[0338] 3. Save the defined promotion requirements in the database and notify the person in charge.

[0339] Step 6:

[0340] server

[0341] The system cleanses job applicant data and generates interview questions. It also analyzes the user's emotional information during the interview in real time and provides adaptive questions.

[0342] Specific actions

[0343] 1. Run a data cleansing algorithm to remove inconsistencies and duplicate data.

[0344] 2. Use Natural Language Processing (NLP) technology to generate appropriate interview questions from applicants' resumes.

[0345] 3. During the interview, the emotion engine analyzes the emotions of the user (interviewer and applicant) and generates and inserts questions to relax them if they are feeling stressed.

[0346] Step 7:

[0347] server

[0348] The generated placement proposals, promotion requirements, and interview questions are notified to the user.

[0349] Specific actions

[0350] 1. Generate a notification containing the analysis results and display it on the user's dashboard.

[0351] 2. The user logs in to the system and checks and uses the suggestions.

[0352] Step 8:

[0353] User

[0354] Make specific staffing, promotion, and hiring decisions based on the information provided.

[0355] Specific actions

[0356] 1. A user logs in to the system and checks the optimal staffing plan for a new department.

[0357] 2. Using emotional data to determine promotion requirements and interview job applicants.

[0358] This system will enhance a company's human resource management by collecting data, analyzing the characteristics of successful personnel, generating optimal placement plans, defining promotion requirements, screening applicants, generating interview questions, and recognizing emotions, thereby reducing employee turnover and improving productivity.

[0359] Example 2

[0360] 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."

[0361] Traditional human resource management systems primarily analyze employees' performance and skills, making it difficult to optimize placement and promotion. Furthermore, because they do not take emotional information into account, they are unable to properly manage employee stress and motivation. Furthermore, because they are unable to generate appropriate questions based on real-time emotional analysis during interviews, the quality of interviews can decline.

[0362] The identification processing by the identification processing unit 290 of the data processing device 12 in Example 2 is realized by the following means. In this invention, the server includes: means for automatically collecting personnel information from each department and organization; means for complementing missing values ​​in the collected personnel information and detecting and correcting outliers; means for analyzing the characteristics of active personnel using a generative AI model based on the preprocessed personnel information; means for generating an optimal personnel allocation plan based on the characteristics of active personnel, taking into account employee skill sets, desired allocations, performance, and emotional information; means for notifying the user of the generated personnel allocation plan, promotion requirements, and interview questions; means for cleansing job applicant data and generating interview questions; and means for acquiring the user's emotional information during interviews in real time and providing adapted questions. This enables optimal personnel allocation and promotion based on data and effective personnel management that takes into account employees' emotional information. Furthermore, real-time emotional analysis during interviews can improve the quality of interviews.

[0363] "Each department or organization" refers to different divisions or organizational units within a company, each with its own unique tasks and roles.

[0364] "Human resource information" refers to detailed data about employees, such as performance data, skill sheets, work evaluations, and 360-degree evaluations.

[0365] "Missing value imputation" refers to the use of estimations or algorithms to fill in missing values ​​in collected data.

[0366] "Detecting and correcting outliers" refers to identifying values ​​in data that fall outside the normal range and correcting or eliminating them.

[0367] "Preprocessed human resources information" refers to human resources information that has been preprocessed to improve data quality, such as by completing missing values ​​and correcting outliers.

[0368] A "generative AI model" refers to a model designed to learn patterns and features from data using artificial intelligence techniques.

[0369] "Characteristics of successful employees" refers to the common traits and skills that employees who succeed in a particular role or department have in common.

[0370] A "skill set" refers to the collection of expertise and abilities that an employee possesses.

[0371] "Desired placement" refers to the job or placement that an employee desires.

[0372] "Performance" refers to an employee's past work performance and achievements.

[0373] "Emotional information" refers to data that indicates an employee's emotional state, and primarily refers to information related to stress levels and motivation.

[0374] "Optimal staffing proposal" refers to the most appropriate staffing proposal, taking into account employees' skill sets, desired placements, performance, and emotional information.

[0375] "Promotion requirements" refer to the skills, experience, abilities, and other conditions that an employee must meet in order to be promoted.

[0376] "Interview questions" refer to questions asked to job applicants during an interview.

[0377] "Job applicant data" refers to detailed information such as resumes and job histories provided by job seekers.

[0378] "Cleansing" refers to the process of correcting data duplication and inconsistencies to create an accurate and consistent data set.

[0379] "Real-time acquisition" refers to acquiring data at the moment it is processed.

[0380] "Providing adaptive questions" refers to the actual use of questions generated according to the situation during the interview.

[0381] The present invention is a system for optimizing personnel allocation, promotion, and recruitment in a company, and by combining it with a new emotion engine that recognizes the user's emotions, it achieves more effective personnel management than ever before. Below, a detailed description is given of an embodiment of the system of the present invention.

[0382] Data collection methods

[0383] server

[0384] The server automatically collects human resource information from each department, including employee performance data, skill sheets, performance reviews, 360-degree evaluations, etc. It periodically retrieves information using APIs and database queries.

[0385] Specific examples

[0386] The server collects sales results from the sales department, campaign performance evaluations from the marketing department, and technical evaluations from the technical department. For example, you can set a timer to collect data at 6:00 PM every day.

[0387] Data preprocessing methods

[0388] server

[0389] The server implements algorithms to impute missing values ​​and detect and correct outliers in the collected data, thereby ensuring data quality.

[0390] Specific examples

[0391] The server imputes missing values ​​using the KNN method and detects and corrects outliers using Z-scores, e.g., absent data are estimated from neighboring data points and anomalous values ​​are corrected using statistical methods.

[0392] Analysis of the characteristics of successful personnel

[0393] server

[0394] The server then inputs the pre-processed data into a generative AI model (e.g., clustering or regression analysis) to extract the characteristics of successful employees, thereby identifying patterns of employees who will be successful in a particular role or department.

[0395] Specific examples

[0396] The server uses a clustering algorithm (K-means) to analyze the patterns of successful sales personnel. For example, it can identify that those with "high communication skills," "initiative," and "excellent problem-solving abilities" are more likely to succeed.

[0397] Form of generating optimal staffing plan

[0398] server

[0399] The server implements an algorithm that generates optimal placement plans based on the characteristics of successful employees, taking into account the employee's skill set, desired placement, performance, and even the user's emotional information.

[0400] Specific examples

[0401] The server generates a proposal to assign Employee X in the technical department as a leader of a new project based on his skill set and past performance. It also analyzes Employee X's emotional information using an emotion engine to confirm that his stress level is low.

[0402] Form of definition of promotion requirements

[0403] server

[0404] The server defines promotion requirements based on the characteristics of the top performers. These requirements are based on specific competencies, skill sets, and past performance, as well as emotional information provided by the emotion engine.

[0405] Specific examples

[0406] Sarver defines the promotion requirements for managers as "high leadership," "experience in supervising subordinates," and "project management skills," and adds "stable emotional control ability."

[0407] Cleansing applicant information and generating interview questions

[0408] server

[0409] The server collects and cleans information on job applicants, and builds a system that automatically generates questions to be used in interviews. It also obtains the user's emotional information in real time during the interview and provides adaptive questions.

[0410] Specific examples

[0411] The server extracts career data from applicant Y's resume, removes duplicate and inconsistent data, and then generates questions to be used in the interview, such as "What was the most difficult problem you solved in your previous job?" and "What kind of leadership experience do you have?" During the interview, the emotion engine recognizes the emotions of the users (interviewer and applicant), and if they are feeling stressed, it inserts questions to help them relax.

[0412] Notifications and User Interface Forms

[0413] server

[0414] The server implements a system that notifies the user of the generated placement proposals, promotion requirements, and interview questions.

[0415] User

[0416] The user can then use the information provided to make optimal personnel placements, promotions, and recruitment. The system provides an interface that allows users to operate the system efficiently and effectively.

[0417] Specific examples

[0418] Human resources personnel log in to the system and check the optimal personnel placement plan for new departments, and also use it to set promotion requirements and interview job applicants. They also consider the emotional data provided by the emotion engine to make optimal decisions.

[0419] Prompt Sentence Examples

[0420] 1. "What are the characteristics of an ideal person for a technical project leader?"

[0421] 2. "Define the promotion requirements for your sales department and include the necessary skill sets and emotional information."

[0422] The system of the present invention is a system that enhances a company's human resource management by consistently performing data collection, preprocessing, analysis, emotion recognition, and notification, thereby reducing employee turnover and improving productivity.

[0423] The flow of the identification process in the second embodiment will be described with reference to FIG.

[0424] Step 1: Data collection

[0425] server

[0426] Input: Human resource information from each department (performance data, skill sheets, work evaluations, 360-degree evaluations, etc.)

[0427] Processing: Use APIs and database queries to periodically collect personnel information from each department. For example, set a timer to retrieve data at 6:00 PM every day.

[0428] Output: Raw data collected

[0429] Specific operation: The server connects to the database and periodically retrieves data such as the sales performance of the sales department, the campaign results of the marketing department, and the technical evaluation of the technical department.

[0430] Step 2: Data Preprocessing

[0431] server

[0432] Input: Raw data collected

[0433] Processing: Apply missing value imputation and outlier detection / correction algorithms, e.g., KNN imputation and Z-score outlier detection / correction.

[0434] Output: Quality-assured pre-processed data

[0435] Specific operation: The server estimates missing data points using the KNN method and corrects abnormal data points using statistical methods.

[0436] Step 3: Identifying the characteristics of successful employees

[0437] server

[0438] Input: Preprocessed data

[0439] Processing: Use generative AI models (e.g., clustering and regression analysis) to extract traits of top performers. Run a clustering algorithm (e.g., K-means) to analyze patterns.

[0440] Output: List of characteristics of successful employees

[0441] How it works: The server inputs the preprocessed data into the K-means clustering algorithm to identify features such as "good communication skills," "proactive behavior," and "excellent problem-solving ability."

[0442] Step 4: Generate optimal staffing plans

[0443] server

[0444] Input: List of characteristics of successful personnel, employee skill set, desired placement, performance, emotional information

[0445] Processing: Based on the generated features, the optimal placement plan is generated using a personnel placement algorithm. Data from the emotion engine is taken in to consider the optimal placement.

[0446] Output: Optimal staffing plan

[0447] Specific operation: The server confirms that the stress level of technical department employee X is low, and then generates a proposal to place him as the leader of a new project, taking into account his skill set and achievements.

[0448] Step 5: Define promotion requirements

[0449] server

[0450] Input: List of characteristics of successful personnel, emotional information

[0451] Processing: Using a generative AI model to define promotion requirements for specific roles, such as managerial positions, including specific competencies, skill sets, and even emotional control skills.

[0452] Output: Promotion requirements list

[0453] Specific operation: The server generates promotion requirements including "high leadership," "experience in supervising subordinates," "project management ability," and "stable emotional control ability."

[0454] Step 6: Cleanse applicant information and generate interview questions

[0455] server

[0456] Input: Raw data of job applicants (resume, curriculum vitae, etc.)

[0457] Processing: Data cleansing is performed, questions are automatically generated for use in interviews, and emotional information during the interview is acquired in real time to provide adaptive questions.

[0458] Output: Cleansed applicant data, interview question list

[0459] Specific operation: The server removes duplicate and inconsistent data and generates questions such as "What was the most difficult problem you solved in your previous job?" and "What kind of leadership experience do you have?" based on information extracted from the resume. During the interview, questions to put the candidate at ease are added based on emotional data obtained from the emotion engine.

[0460] Step 7: Notifications and User Interface

[0461] server

[0462] Input: Optimal personnel placement plan, promotion requirements list, interview questions list

[0463] Processing: Implement a system that notifies the user of the generated information. Design an interface that allows the user to check and manipulate the information.

[0464] Output: Information notified to the user

[0465] Specific operation: A human resources officer logs into the system, checks the staffing plan for a new project, the promotion requirements for managerial positions, and the interview questions for applicants, and makes a decision based on the information. Data from the emotion engine is also referenced to make a comprehensive judgment.

[0466] (Application example 2)

[0467] 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."

[0468] Conventional personnel allocation systems did not take into account emotional information in their personnel management, making it difficult to optimally allocate and promote employees based on their stress levels and emotional states. Real-time employee emotional recognition in physical stores and flexible personnel allocation based on this recognition are also needed. This will improve the performance of physical stores and customer satisfaction.

[0469] The identification processing by the identification processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means. In this invention, the server includes means for collecting human resource information from each department and organization, means for complementing missing values ​​in the collected human resource information and detecting and correcting outliers, means for analyzing the characteristics of active personnel using a generation AI based on the preprocessed human resource information, means for generating an optimal human resource allocation plan based on the characteristics of the active personnel, means for notifying the user of the generated human resource allocation plan, means for cleansing data on job applicants and generating interview questions, and means for collecting emotional information from employees at physical stores and reflecting the information in an analysis of the characteristics of active personnel and in an optimal human resource allocation plan. This makes it possible to generate optimal human resource allocation plans and promotion plans that reflect employee emotional information.

[0470] "Means for collecting human resources information from each department and organization" refers to a system that automatically obtains information such as employee skills, performance, and evaluations from different departments and organizations within the company.

[0471] "Means for completing missing values ​​in collected human resources information and detecting and correcting outliers" refers to algorithms and methods for completing missing information in collected data and finding and correcting outliers.

[0472] "Method of analyzing the characteristics of successful employees using generative AI based on preprocessed human resources information" refers to a method of using information that has undergone data preprocessing and generative AI to extract patterns and characteristics of employees who are likely to be successful.

[0473] "Means for generating optimal personnel placement plans based on the characteristics of successful personnel" is a system for determining the placement in which each employee can work most effectively, based on the characteristics of successful employees.

[0474] The "means for notifying the user of the generated personnel placement plan" is a method for notifying a company's personnel manager or a person in charge of human resources of the generated personnel placement plan.

[0475] "Method for cleansing job applicant data and generating interview questions" refers to a method for organizing and processing job applicant information, deleting unnecessary data, and automatically creating questions to be used in interviews.

[0476] "Means for collecting emotional information from employees in physical stores and reflecting it in an analysis of the characteristics of successful employees and in generating optimal personnel placement plans" refers to a method for collecting the emotional state of employees working in stores in real time and using that information to analyze the characteristics of successful employees and generate personnel placement plans.

[0477] To implement the present invention, it is necessary to build a system that performs the following steps in order: The following describes in detail the hardware, software, and processing procedures of the actual system.

[0478] System configuration

[0479] 1. Hardware

[0480] Server (general server or cloud infrastructure: AWS, Microsoft Azure, etc.)

[0481] User devices (PCs, tablets, smartphones, etc.)

[0482] 2. Software

[0483] Data processing and preprocessing: Python, Pandas

[0484] Outcome analysis and clustering: Scikit-Learn (StandardScaler, K-Means Clustering)

[0485] Emotion Recognition Engine

[0486] Notification system: Email service or in-app notifications

[0487] Data collection and preprocessing

[0488] The server automatically collects employee information from each department within the company using APIs and database queries, including employee performance data, skill sets, performance reviews, and 360-degree feedback.

[0489] Next, missing values ​​in the collected data are imputed and outliers are detected and corrected. For example, missing values ​​are imputed using the KNN method, and outliers are detected and corrected using Z-scores.

[0490] Analysis of the characteristics of successful personnel

[0491] The preprocessed data is then input into an AI model to extract the characteristics of successful employees. Specifically, the data is analyzed using a clustering algorithm (K-means). This allows us to understand the patterns of employees who are successful in specific roles or departments.

[0492] Creation and notification of staffing plans

[0493] We implement an algorithm that generates optimal staffing plans based on the characteristics of successful employees. This algorithm takes into account employees' skill sets, desired placements, performance, and even emotional information obtained from an emotion recognition engine. The generated placement plans are then notified to users via email services or an in-app notification system.

[0494] Generating interview questions

[0495] The system uses an emotion recognition engine to collect and cleanse information from job applicants, obtain real-time emotional information during interviews, and generate appropriate questions based on that information.

[0496] Specific Examples

[0497] For example, in a physical store, the performance data and emotional information of employees A, B, and C are collected and analyzed, and it is discovered that employee A has excellent leadership skills and can make calm decisions even under pressure. Based on this information, a proposal is made to assign employee A as the leader of a new project. This proposal is notified to the store manager's terminal.

[0498] Prompt Sentence Examples

[0499] Here is an example of a prompt to input to a generative AI model:

[0500] "Generate optimal staffing recommendations based on employee performance data and sentiment information. For example, recommend the best roles for employees A, B, and C in the sales department and generate questions using sentiment information."

[0501] This makes it possible to provide optimal placement and promotion plans that take into account the emotional information of employees in physical stores.

[0502] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[0503] Program processing steps

[0504] Step 1:

[0505] The server collects talent information from each department within the company using database queries and APIs. Specific inputs include employee performance data, skill sets, performance reviews, and 360-degree reviews. This data is stored as raw data on the server. The output is an unprocessed talent information dataset.

[0506] Step 2:

[0507] The server performs data preprocessing to complete missing values ​​in the collected human resources information and detect and correct outliers. Specifically, it completes missing values ​​using the KNN method and detects and corrects outliers using Z-scores. The input for this step is the raw human resources information dataset, and the output is the preprocessed human resources information dataset.

[0508] Step 3:

[0509] The server inputs the preprocessed personnel information data into a generative AI model (such as K-means clustering) to analyze the characteristics of successful personnel. Specifically, it performs clustering taking into account employee skills, performance, and emotional information. The input is the preprocessed personnel information dataset, and the output is the clustering results that represent the characteristics of successful personnel.

[0510] Step 4:

[0511] The server generates an optimal personnel allocation plan based on the characteristics of the active personnel, using the clustering results. Specifically, it uses an algorithm to perform an allocation simulation while taking into account the characteristics of the employees. The input is the clustering results, and the output is the optimal personnel allocation plan.

[0512] Step 5:

[0513] The server notifies the generated optimal staffing plan to the user's (e.g., human resources officer or manager) device. Specifically, the plan is sent using an email service or an in-app notification system. The input is the optimal staffing plan, and the output is a notification to the user.

[0514] Step 6:

[0515] The server collects and cleans information about job applicants and generates interview questions. Specifically, it removes invalid data from the applicant's historical data and applies an algorithm to generate interview questions. The input is the applicant's raw data, and the output is the cleansed data and generated interview questions.

[0516] Step 7:

[0517] The server collects emotional information from store employees in real time and reflects this in the analysis of the characteristics of successful employees and in optimal staffing proposals. Specifically, it uses an emotion recognition engine to collect employee emotional data and incorporates it into a generative AI model. The input is the emotional information collected in real time, and the output is clustering results that reflect the emotional information and staffing proposals.

[0518] 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.

[0519] 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.

[0520] 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.

[0521] [Second embodiment]

[0522] FIG. 3 shows an example of the configuration of a data processing system 210 according to the second embodiment.

[0523] 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.

[0524] 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).

[0525] 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.

[0526] 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.

[0527] 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).

[0528] 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. 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.

[0529] 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.

[0530] 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.

[0531] 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.

[0532] In the smart glasses 214, the processor 46 performs the reception output process. A reception output program 60 is stored in the storage 50. The processor 46 reads the reception output program 60 from the storage 50 and executes the read reception output program 60 on the RAM 48. The reception output process is realized by the processor 46 operating as the control unit 46A in accordance with the reception output program 60 executed on the RAM 48.

[0533] 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."

[0534] The present invention is a system for optimizing personnel allocation, promotion, and recruitment in a company. This system collects personnel information from each department within the company, preprocesses the collected data, and analyzes it to achieve optimal personnel management. Below, we will describe in detail the embodiments for implementing the system of the present invention.

[0535] Data collection methods

[0536] server

[0537] Build a system to automatically collect personnel information from each department, including employee performance data, skill sheets, performance evaluations, and 360-degree reviews.

[0538] Set up a system to periodically retrieve information using APIs or database queries.

[0539] Specific examples

[0540] The server collects sales results from the sales department, campaign performance evaluations from the marketing department, and technical evaluations from the technical department.

[0541] Data preprocessing methods

[0542] server

[0543] Implement algorithms to impute missing values ​​and detect and correct outliers in the collected data, thereby ensuring data quality.

[0544] Specific examples

[0545] The server imputes missing values ​​using the KNN method and detects and corrects outliers using Z-scores.

[0546] Analysis of the characteristics of successful personnel

[0547] server

[0548] The pre-processed data is then fed into an AI model (such as clustering or regression analysis) to extract the characteristics of successful employees, thereby identifying patterns of employees who will be successful in a particular role or department.

[0549] Specific examples

[0550] The server uses a clustering algorithm (K-means) to analyze the patterns of successful sales personnel. As a result, it finds that those with "high communication skills," "initiative," and "excellent problem-solving abilities" are more likely to succeed.

[0551] Form of generating optimal staffing plan

[0552] server

[0553] Implement an algorithm that generates optimal placement plans for existing employees based on the characteristics of successful employees, taking into account the employee's skill set, desired placement, and performance.

[0554] Specific examples

[0555] The server generates a proposal to place technical employee X as a leader of a new project based on his skill set and past performance.

[0556] Form of definition of promotion requirements

[0557] server

[0558] Define promotion requirements based on the characteristics of your top performers. These requirements are based on specific competencies, skill sets, and past performance.

[0559] Specific examples

[0560] Server defines the promotion requirements for managers as "strong leadership," "experience in supervising subordinates," and "project management skills."

[0561] Cleansing applicant information and generating interview questions

[0562] server

[0563] We will build a system that collects and cleans information on job applicants and automatically generates questions to be used in interviews.

[0564] Specific examples

[0565] The server extracts career data from applicant Y's resume, removes duplicate and inconsistent data, and then generates interview questions such as "What was the most difficult problem you solved in your previous job?" and "What kind of leadership experience do you have?"

[0566] Notifications and User Interface Forms

[0567] server

[0568] Implement a system to notify users of generated placement proposals, promotion requirements, and interview questions, allowing them to make data-driven decisions.

[0569] User

[0570] The user will then make optimal personnel allocation, promotion, and recruitment decisions based on the information provided. The system aims to have an interface that allows users to operate it efficiently and effectively.

[0571] Specific examples

[0572] Human resources personnel log in to the system to check the optimal personnel placement plans for new departments, and also use it to set promotion requirements and interview job applicants.

[0573] The system of the present invention performs data collection, preprocessing, analysis, and notification in an integrated manner, thereby enhancing a company's human resource management, reducing employee turnover and improving productivity.

[0574] The processing flow will be explained below.

[0575] Program processing steps

[0576] Step 1:

[0577] server

[0578] Collect human resource information from each department, including performance data, skill sheets, performance reviews, and 360-degree evaluations, using APIs and database queries.

[0579] Specific actions

[0580] 1. Send a request to an API endpoint to retrieve data from each department's system.

[0581] 2. Run an SQL query to extract historical performance data from the database.

[0582] Step 2:

[0583] server

[0584] Preprocessing of collected data is performed, specifically, missing values ​​are complemented and outliers are detected and corrected.

[0585] Specific actions

[0586] 1. Run the missing value imputation algorithm (KNN method) to estimate and impute missing data.

[0587] 2. An outlier detection algorithm (Z-score) is used to correct abnormal data points.

[0588] Step 3:

[0589] server

[0590] The preprocessed data is used to analyze the characteristics of successful employees, specifically through clustering and regression analysis.

[0591] Specific actions

[0592] 1. Run a clustering algorithm (K-means) to classify the personnel into multiple groups.

[0593] 2. Use regression analysis to assess the contribution of specific skills and achievements to success.

[0594] Step 4:

[0595] server

[0596] Generate optimal employee placement recommendations based on the characteristics of top performers, taking into account employee skill sets, performance, and individual placement preferences.

[0597] Specific actions

[0598] 1. Use the Thriving Talent Model to map each employee's skill set to the job needs.

[0599] 2. Use a selection algorithm to suggest the best department and role.

[0600] Step 5:

[0601] server

[0602] Define promotion requirements, including specific competencies, skill sets, and past performance.

[0603] Specific actions

[0604] 1. Use a decision tree algorithm to define the requirements for promotion.

[0605] 2. Save the defined requirements in the database and notify the person in charge.

[0606] Step 6:

[0607] server

[0608] Cleanse job applicant data and generate interview questions.

[0609] Specific actions

[0610] 1. Run data cleansing algorithms to remove inconsistencies and duplicate data.

[0611] 2. Uses Natural Language Processing (NLP) technology to generate appropriate interview questions from applicants' resumes.

[0612] Step 7:

[0613] server

[0614] The generated placement proposals, promotion requirements, and interview questions are notified to the user.

[0615] User

[0616] Based on the information provided, specific decisions regarding personnel placement, promotion, and hiring are made.

[0617] Specific actions

[0618] 1. Generates a notification containing the analysis results and displays it on the user's dashboard.

[0619] 2. The user logs into the system to review and use the suggestions.

[0620] In this way, this system enhances a company's human resource management through a series of steps, including data collection, analysis of the characteristics of successful personnel, generation of optimal placement plans, definition of promotion requirements, and processing related to job applicants.

[0621] Example 1

[0622] 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."

[0623] Conventional human resource management systems have the problem that it is difficult to efficiently grasp the skills and performance of individual employees, cooperation between departments, and the appropriateness of promotions and placements, making it difficult to contribute to improving productivity and turnover rates across the company.In addition, collecting information on job applicants and preparing for interviews requires a great deal of effort and time, so there was a need for efficiency improvements.

[0624] 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.

[0625] In this invention, the server includes: means for collecting human resource information from each department and organization; means for completing missing values ​​in the collected human resource information and detecting and correcting outliers; means for analyzing the characteristics of active personnel using a generative AI model based on the preprocessed human resource information; means for generating an optimal human resource placement plan based on the characteristics of active personnel; means for notifying a user of the generated placement plan; means for cleansing job applicant data and generating interview questions; means for generating an optimal human resource placement plan taking into account employee skill sets, desired placements, and performance; and means for notifying a user of the generated interview questions and supporting job applicant interviews. This improves the efficiency of human resource management across the company, realizes appropriate human resource placement and promotion, and simplifies job applicant interview preparation, thereby improving corporate productivity and reducing employee turnover.

[0626] "Human resource information" refers to information including the performance, skills, work evaluations, and 360-degree evaluations of employees working in each department and organization of a company.

[0627] "Missing values" are values ​​that are missing in a dataset and are a factor that impairs the accuracy of data analysis.

[0628] An "outlier" is a value in a dataset that is significantly different from other data and may affect the results of data analysis.

[0629] A "generative AI model" is an algorithm that uses artificial intelligence to extract and analyze specific patterns and features from data.

[0630] "Characteristics of successful employees" refer to the skills and characteristics common to employees who achieve outstanding results in specific roles or departments within a company.

[0631] A "staffing proposal" is a plan that proposes the optimal staffing arrangement within a company, and is generated based on employees' skill sets, performance, desired placement, etc.

[0632] "Notification" is the act of informing the user of important information such as the generated personnel allocation plan and interview questions.

[0633] "Cleansing" is the process of detecting, deleting, or correcting duplicates and inconsistencies in data collected from a database.

[0634] "Interview questions" are questions used during interviews with job applicants or employees, and are used to evaluate the applicant's abilities and experience.

[0635] A "skill set" is the collection of skills and abilities that a particular employee possesses.

[0636] "Desired placement" refers to the department or role that an employee desires.

[0637] "Performance" refers to an employee's past achievements and evaluations in performing their duties.

[0638] The above definitions allow each element of the system to be clearly understood.

[0639] The present invention is a system for optimizing personnel allocation, promotion, and recruitment in a company. This system collects personnel information from each department within the company, preprocesses the collected data, and analyzes it to achieve optimal personnel management. Below, we will describe in detail the embodiments for implementing the system of the present invention.

[0640] Data collection methods

[0641] server

[0642] The server automatically collects personnel information such as employee performance data, skill sheets, work evaluations, and 360-degree evaluations from each department of the company. This information is periodically retrieved using APIs and database queries. Specifically, it collects sales performance from the sales department, campaign success evaluations from the marketing department, and technical evaluations from the technical department.

[0643] Data preprocessing methods

[0644] server

[0645] The server runs algorithms to impute missing values ​​in the collected data and to detect and correct outliers, for example, imputing missing values ​​using the KNN (k-Nearest Neighbors) method and detecting outliers using Z-scores.

[0646] Analysis of the characteristics of successful personnel

[0647] server

[0648] The server inputs the preprocessed data into a generative AI model (such as clustering or regression analysis) to extract the characteristics of successful employees. Specifically, the K-means clustering algorithm can be used to analyze successful employees in the sales department. The results show that those with "high communication skills," "proactive action," and "excellent problem-solving abilities" are more likely to succeed.

[0649] Form of generating optimal staffing plan

[0650] server

[0651] The server generates optimal personnel placement proposals based on the characteristics of active personnel, taking into account the employee's skill set, desired placement, and performance. For example, it generates a proposal to place employee X in the technical department as a leader of a new project based on his skill set and past performance.

[0652] Form of definition of promotion requirements

[0653] server

[0654] The server defines promotion requirements based on the characteristics of successful employees. These requirements are set based on specific abilities, skill sets, and past performance. For example, the server defines "high leadership," "experience in mentoring subordinates," and "project management ability" as promotion requirements for managerial positions.

[0655] Cleansing applicant information and generating interview questions

[0656] server

[0657] The server collects and cleans information on job applicants and automatically generates interview questions. Specifically, it extracts resume data for applicant Y, deletes inconsistent and duplicate data, and then generates interview questions such as "What was the most difficult problem you solved in your previous job?" and "What kind of leadership experience do you have?"

[0658] Notifications and User Interface Forms

[0659] server

[0660] The server implements a system that notifies the user of the generated placement proposals, promotion requirements, and interview questions, allowing the user to make data-based decisions.

[0661] User

[0662] Based on the information provided, users can make optimal personnel placements, promotions, and hiring decisions. The system provides an interface that users can use efficiently and effectively. Specifically, human resources personnel can log in to the system, check the optimal personnel placement proposals for new departments, and use the results to set promotion requirements and interview job applicants.

[0663] Prompt Sentence Examples

[0664] "Analyze patterns of successful talent using sales performance and campaign success evaluation data."

[0665] "Generate a placement plan to select the best person to lead a new project in the technology department."

[0666] "Extract applicant biographical data and generate interview questions."

[0667] This system will enhance a company's human resource management by consistently collecting, preprocessing, analyzing, and notifying data, thereby reducing employee turnover and improving productivity.

[0668] The flow of the identification process in the first embodiment will be described with reference to FIG.

[0669] Step 1:

[0670] Data collection

[0671] The server has a means of collecting human resource information from each department and organization. In this case, the input is information such as employee performance data, skill sheets, work evaluations, and 360-degree evaluations stored in each department's database. The server periodically obtains the necessary information using API requests and database queries. The server then stores the obtained data in storage. For example, the server might collect sales performance from the sales department, campaign success evaluations from the marketing department, and technical evaluations from the technical department.

[0672] Step 2:

[0673] Data Preprocessing

[0674] The server preprocesses the collected data. The input is the raw data collected in step 1. Specifically, the server first detects missing values ​​in the data and imputes them using the KNN (k-Nearest Neighbors) method. Next, it calculates Z-scores to detect outliers. If an outlier is found, the server corrects or removes it. The final output is clean data with missing and outlier values ​​corrected.

[0675] Step 3:

[0676] Analysis of the characteristics of successful personnel

[0677] The server inputs the clean data into the generative AI model and analyzes the characteristics of successful employees. The input is the data preprocessed in step 2. Specifically, the server runs the K-means clustering algorithm. It analyzes the clustering results and identifies the characteristics of each cluster. These characteristics include "good communication skills," "proactive action," and "excellent problem-solving ability." The output is a list of the characteristics of successful employees.

[0678] Step 4:

[0679] Generate optimal staffing plans

[0680] The server generates a personnel placement plan based on the characteristics of the active personnel. The inputs are the characteristics of the active personnel obtained in step 3, the employee's skill set, desired placement, and performance data. Specifically, the server compares each employee's data with the characteristics of the active personnel to generate an optimal placement plan. For example, the server references the skill set and past performance of employee X in the technical department and generates a plan to place him as the leader of a new project. The output is an optimal personnel placement plan.

[0681] Step 5:

[0682] Define promotion requirements

[0683] The server defines promotion requirements based on the characteristics of successful employees. The input is the list of characteristics obtained in step 3. Specifically, the server extracts the abilities, skill sets, and experience required for a specific position from the characteristics of successful employees. For example, it defines "high leadership," "experience in supervising subordinates," and "project management ability" as promotion requirements for managerial positions. The output is a list of described promotion requirements.

[0684] Step 6:

[0685] Cleansing applicant information and generating interview questions

[0686] The server cleanses the information of job applicants and generates interview questions. The input is the resume data of job applicants. Specifically, the server analyzes the resume data and removes or corrects duplicate and inconsistent data. Next, based on the cleansed data, it generates questions to be used in interviews. For example, it generates questions such as "What was the most difficult problem you solved in your previous job?" and "What kind of leadership experience do you have?" The output is the cleansed applicant information and the generated interview questions.

[0687] Step 7:

[0688] Notifications and User Interface

[0689] The server notifies the user of the generated placement plans, promotion requirements, and interview questions. The input is the output of steps 4, 5, and 6. Specifically, the server presents the generated results to the user in the form of a dashboard or email notification. The user then uses the notified information to make optimal personnel placements, promotions, and recruitment. For example, a human resources officer logs into the system, checks the optimal personnel placement plans for a new department, and uses this information to set promotion requirements and interview job applicants. The output is a notification to the user and an interface that the user can use.

[0690] (Application example 1)

[0691] 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."

[0692] In conventional factories, managing robot operating status and maintenance schedules required individual data management and manual adjustments, making it difficult to achieve optimal operating efficiency and maintenance plans. Furthermore, the collection and analysis of human resource information required a great deal of effort, preventing optimal personnel placement and promotion. There is a need to improve this situation and increase the efficiency and productivity of factories and organizations as a whole.

[0693] 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.

[0694] In this invention, the server includes: means for collecting human resource information from each department and organization; means for completing missing values ​​in the collected human resource information and detecting and correcting outliers; means for analyzing the characteristics of active human resources using a generation AI based on the preprocessed human resource information; means for generating an optimal human resource deployment plan based on the characteristics of active human resources; means for notifying a user of the generated deployment plan; means for collecting operation information, work efficiency, and maintenance history; means for preprocessing the collected operation information and detecting and correcting outliers; means for generating an optimal robot deployment plan and maintenance schedule using a generation AI based on the preprocessed operation information; means for cleansing job applicant data and generating interview questions; and means for providing a user interface for confirming the optimal deployment and schedule based on the notified information. This enables optimization of the operating efficiency of robots in factories, formulation of preventative maintenance schedules, and appropriate human resource deployment and promotion.

[0695] "Each department or organization" refers to different divisions, teams, or functional groups within a company or factory.

[0696] "Human resources information" refers to relevant data about employees and job seekers, such as performance, skills, evaluations, and work history.

[0697] "Means of collection" refers to the systems and methods for obtaining the necessary information through various databases and APIs.

[0698] "Missing value imputation" refers to the process of estimating and filling in missing values ​​in a dataset.

[0699] "Outlier detection and correction" refers to the process of finding values ​​in a data set that are outside of the normal range and changing them to appropriate values.

[0700] "Preprocessed human resources information" refers to clean data that has been collected and has undergone missing value imputation and outlier correction.

[0701] "Generative AI" refers to artificial intelligence algorithms used to rapidly analyze large amounts of data and extract specific patterns and features.

[0702] "High-performing talent" refers to employees who perform well in specific conditions or roles.

[0703] "Means for analyzing features" means methods that use data analytics and machine learning algorithms to extract trends and patterns from data.

[0704] "Optimal human resource allocation plan" refers to the assignment of departments and projects that allow employees to work most effectively.

[0705] "Means for notifying the user" refers to an interface or method for notifying the user of generated information or results.

[0706] "Operational information" refers to data on how robots and systems are actually operating.

[0707] "Work efficiency" refers to the ratio of productive output to effort put in.

[0708] "Maintenance history" means a record of the maintenance that a device or system has undergone.

[0709] An "allocation plan" refers to a plan for how to allocate equipment and personnel to operating departments or specific projects.

[0710] A "maintenance schedule" refers to a schedule for systematically carrying out maintenance work on equipment and systems.

[0711] "Job applicants" refers to individuals who have applied for a new position.

[0712] "Data cleansing" refers to the process of removing unnecessary information from raw data and preparing it for analysis.

[0713] "Interview questions" refer to questions used in interviews.

[0714] "User interface" refers to the screens and operating methods that allow users to directly interact with a system.

[0715] This invention is a system that collects and analyzes data on the operational status, work efficiency, and maintenance history of robots in factories, and generates optimal robot placement and maintenance schedules. This system performs all processes, from collecting data on operational information, work efficiency, and maintenance history to notifying users of the placement plans and schedules it generates.

[0716] Data collection

[0717] The server has a means to automatically collect operational information, work efficiency, and maintenance history from each robot operating in the factory. This collection process is carried out through sensors installed on each robot and API, and the data is sent to the server.

[0718] Examples:

[0719] The server collects operating hours, number of completed tasks, and recent maintenance history from each robot in the factory via an API.

[0720] Data Preprocessing

[0721] The server implements algorithms to fill in missing values ​​in the collected data and detect and correct outliers, a process that ensures data quality and enables accurate analysis.

[0722] Examples:

[0723] Missing values ​​in the dataset collected by the server are imputed using the KNN method, and outliers are detected and corrected using Z scores.

[0724] Generation of optimal robot placement plans and maintenance schedules

[0725] Based on the pre-processed data, generative AI models (such as clustering and regression analysis) are used to generate optimal robot placement plans and maintenance schedules. The results suggest the most efficient use of robots in factory operations.

[0726] Examples:

[0727] The server uses a clustering algorithm (K-means) to analyze the operating patterns of each robot and identify robots with "high operating time," "efficient task completion," and "low maintenance frequency."

[0728] Notification of placement plan and schedule

[0729] The generated optimal deployment plan and maintenance schedule are notified to the user. The server is responsible for this notification process, and the information is displayed and shared through the user interface.

[0730] Examples:

[0731] The server notifies the user of the generated deployment plan and maintenance schedule via email or a dedicated dashboard.

[0732] Based on the information provided, users can plan optimal robot placement and maintenance, improving productivity and efficiency within their factories.

[0733] Example prompt sentence:

[0734] Input the operation data and maintenance history data of the robots in the factory, analyze the characteristics of the active robots, and generate optimal placement plans and maintenance schedules.

[0735] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[0736] Step 1:

[0737] The server collects operational information, work efficiency, and maintenance history from the robots operating in the factory via API. The input is data from each robot's sensors and internal systems, which is obtained via API. The output is a raw dataset that we use for preprocessing. This dataset includes each robot's operating time, number of completed tasks, and maintenance history.

[0738] Step 2:

[0739] The server performs preprocessing of the collected data. First, it performs missing value imputation. It uses KNN imputation to estimate and fill missing values ​​in the dataset. Next, it performs outlier detection and correction. It uses Z-score to detect data points that fall outside the normal range and corrects them. This ensures the quality of the data. The input is the original dataset collected in step 1, and the output is clean data with missing and outlier values ​​corrected.

[0740] Step 3:

[0741] The server inputs the preprocessed data into the generative AI model to analyze the robot's operating patterns. A clustering algorithm (e.g., K-means) is used for this analysis. The input is the clean data generated in step 2, and the output is the robot patterns classified by cluster. Specifically, the feature values ​​of each robot (operating time, work efficiency, etc.) are input into the algorithm to perform clustering.

[0742] Step 4:

[0743] The server uses the generative AI model to generate optimal robot placement plans and maintenance schedules. The input is the data classified by cluster in Step 3. Based on the data, it formulates placement plans for robots with high operating efficiency and a corresponding preventive maintenance schedule. The output is the optimal placement plan and maintenance schedule. Specifically, based on the characteristics of each cluster, it determines which robots should be placed in which areas and when maintenance is required.

[0744] Step 5:

[0745] The server notifies the user of the generated deployment plan and maintenance schedule. Notifications are made via email or a dedicated dashboard. The input is the deployment plan and maintenance schedule generated in step 4, and the output is the information displayed on the user's operation screen. Specifically, the generated information is converted into an appropriate format and displayed through the user interface.

[0746] Step 6:

[0747] The user checks the notified deployment plan and maintenance schedule and puts them into action. The input is the information displayed in step 5. The user makes the necessary adjustments based on the optimal deployment plan and schedule to optimize the operation of the robots. The output is the adjusted operation plan and maintenance schedule. In concrete terms, the user deploys each robot and performs maintenance work on-site based on the notified content.

[0748] 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.

[0749] The present invention achieves more effective human resource management than ever before by combining a system for optimizing personnel allocation, promotion, and recruitment in a company with a new emotion engine that recognizes user emotions. Below, a detailed description is given of an embodiment of the system of the present invention.

[0750] Data collection methods

[0751] server

[0752] Build a system to automatically collect personnel information from each department, including employee performance data, skill sheets, performance evaluations, and 360-degree reviews.

[0753] Set up a system to periodically retrieve information using APIs or database queries.

[0754] Specific examples

[0755] The server collects sales results from the sales department, campaign performance evaluations from the marketing department, and technical evaluations from the technical department.

[0756] Data preprocessing methods

[0757] server

[0758] Implement algorithms to impute missing values ​​and detect and correct outliers in the collected data, thereby ensuring data quality.

[0759] Specific examples

[0760] The server imputes missing values ​​using the KNN method and detects and corrects outliers using Z-scores.

[0761] Analysis of the characteristics of successful personnel

[0762] server

[0763] The pre-processed data is then fed into an AI model (such as clustering or regression analysis) to extract the characteristics of successful employees, thereby identifying patterns of employees who will be successful in a particular role or department.

[0764] Specific examples

[0765] The server uses a clustering algorithm (K-means) to analyze the patterns of successful sales personnel. As a result, it finds that those with "high communication skills," "initiative," and "excellent problem-solving abilities" are more likely to succeed.

[0766] Form of generating optimal staffing plan

[0767] server

[0768] We will implement an algorithm that generates optimal employee placement plans based on the characteristics of successful employees, taking into account the employee's skill set, desired placement, performance, and even user sentiment.

[0769] Specific examples

[0770] The server generates a proposal to appoint Employee X in the technical department as a leader of a new project based on his skill set and past performance. It also analyzes Employee X's emotional information using an emotion engine to confirm that his stress level is low.

[0771] Form of definition of promotion requirements

[0772] server

[0773] Define promotion requirements based on the characteristics of your top performers. These requirements are based on specific competencies, skill sets, and past performance, as well as emotional information provided by the emotion engine.

[0774] Specific examples

[0775] Sarver defines the promotion requirements for managers as "high leadership," "experience in supervising subordinates," and "project management skills," and adds "stable emotional control ability."

[0776] Cleansing applicant information and generating interview questions

[0777] server

[0778] We will build a system that collects and cleans information on job applicants and automatically generates questions to be used in interviews. Furthermore, we will obtain the user's emotional information in real time during the interview and provide adaptive questions.

[0779] Specific examples

[0780] The server extracts career data from applicant Y's resume, removes duplicate and inconsistent data, and then generates questions to be used in the interview, such as "What was the most difficult problem you solved in your previous job?" and "What kind of leadership experience do you have?" During the interview, the emotion engine recognizes the emotions of the users (interviewer and applicant), and if they are feeling stressed, it inserts questions to help them relax.

[0781] Notifications and User Interface Forms

[0782] server

[0783] Implement a system to notify users of generated placement proposals, promotion requirements, and interview questions, allowing them to make data-driven decisions.

[0784] User

[0785] The user will then make optimal personnel allocation, promotion, and recruitment decisions based on the information provided. The system aims to have an interface that allows users to operate it efficiently and effectively.

[0786] Specific examples

[0787] Human resources personnel log in to the system and check the optimal personnel placement plan for new departments, and also use it to set promotion requirements and interview job applicants. They also consider the emotional data provided by the emotion engine to make optimal decisions.

[0788] The system of the present invention performs data collection, preprocessing, analysis, emotion recognition, and notification in an integrated manner, thereby enhancing a company's human resource management, reducing employee turnover and improving productivity.

[0789] The processing flow will be explained below.

[0790] Program processing steps

[0791] Step 1:

[0792] server

[0793] Collect human resource information from each department, including performance data, skill sheets, performance reviews, and 360-degree evaluations, using APIs and database queries.

[0794] Specific actions

[0795] 1. Send requests to API endpoints to retrieve data from each department's system.

[0796] 2. Run an SQL query to extract historical performance data from the database.

[0797] Step 2:

[0798] server

[0799] Preprocessing of collected data is performed, specifically, missing values ​​are complemented and outliers are detected and corrected.

[0800] Specific actions

[0801] 1. Run the missing value imputation algorithm (KNN method) to estimate and impute missing data.

[0802] 2. Correct anomalous data points using an outlier detection algorithm (Z-score).

[0803] Step 3:

[0804] server

[0805] The preprocessed data is used to analyze the characteristics of successful employees, specifically through clustering and regression analysis.

[0806] Specific actions

[0807] 1. Run a clustering algorithm (K-means) to classify the personnel into multiple groups.

[0808] 2. Use regression analysis to assess the contribution of specific skills and achievements to success.

[0809] Step 4:

[0810] server

[0811] Generate optimal employee placement plans based on the characteristics of top performers, taking into account employee skill sets, desired placements, performance, and even user sentiment.

[0812] Specific actions

[0813] 1. Use a talent model to map each employee's skill set to the needs of the job.

[0814] 2. Use a selection algorithm to suggest the best departments and roles.

[0815] 3. Analyze emotional data from the emotion engine and adjust placement recommendations based on the employee's current emotional state.

[0816] Step 5:

[0817] server

[0818] Define promotion requirements based on specific competencies, skill sets, and past performance, as well as emotional information provided by the emotion engine.

[0819] Specific actions

[0820] 1. Use a decision tree algorithm to define the requirements for promotion.

[0821] 2. Adjust the defined requirements taking into account the data from the emotion engine.

[0822] 3. Save the defined promotion requirements in the database and notify the person in charge.

[0823] Step 6:

[0824] server

[0825] The system cleanses job applicant data and generates interview questions. It also analyzes the user's emotional information during the interview in real time and provides adaptive questions.

[0826] Specific actions

[0827] 1. Run a data cleansing algorithm to remove inconsistencies and duplicate data.

[0828] 2. Use Natural Language Processing (NLP) technology to generate appropriate interview questions from applicants' resumes.

[0829] 3. During the interview, the emotion engine analyzes the emotions of the user (interviewer and applicant) and generates and inserts questions to relax them if they are feeling stressed.

[0830] Step 7:

[0831] server

[0832] The generated placement proposals, promotion requirements, and interview questions are notified to the user.

[0833] Specific actions

[0834] 1. Generate a notification containing the analysis results and display it on the user's dashboard.

[0835] 2. The user logs in to the system and checks and uses the suggestions.

[0836] Step 8:

[0837] User

[0838] Make specific staffing, promotion, and hiring decisions based on the information provided.

[0839] Specific actions

[0840] 1. A user logs in to the system and checks the optimal staffing plan for a new department.

[0841] 2. Using emotional data to determine promotion requirements and interview job applicants.

[0842] This system will enhance a company's human resource management by collecting data, analyzing the characteristics of successful personnel, generating optimal placement plans, defining promotion requirements, screening applicants, generating interview questions, and recognizing emotions, thereby reducing employee turnover and improving productivity.

[0843] Example 2

[0844] 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."

[0845] Traditional human resource management systems primarily analyze employees' performance and skills, making it difficult to optimize placement and promotion. Furthermore, because they do not take emotional information into account, they are unable to properly manage employee stress and motivation. Furthermore, because they are unable to generate appropriate questions based on real-time emotional analysis during interviews, the quality of interviews can decline.

[0846] The identification processing by the identification processing unit 290 of the data processing device 12 in Example 2 is realized by the following means. In this invention, the server includes: means for automatically collecting personnel information from each department and organization; means for complementing missing values ​​in the collected personnel information and detecting and correcting outliers; means for analyzing the characteristics of active personnel using a generative AI model based on the preprocessed personnel information; means for generating an optimal personnel allocation plan based on the characteristics of active personnel, taking into account employee skill sets, desired allocations, performance, and emotional information; means for notifying the user of the generated personnel allocation plan, promotion requirements, and interview questions; means for cleansing job applicant data and generating interview questions; and means for acquiring the user's emotional information during interviews in real time and providing adapted questions. This enables optimal personnel allocation and promotion based on data and effective personnel management that takes into account employees' emotional information. Furthermore, real-time emotional analysis during interviews can improve the quality of interviews.

[0847] "Each department or organization" refers to different divisions or organizational units within a company, each with its own unique tasks and roles.

[0848] "Human resource information" refers to detailed data about employees, such as performance data, skill sheets, work evaluations, and 360-degree evaluations.

[0849] "Missing value imputation" refers to the use of estimations or algorithms to fill in missing values ​​in collected data.

[0850] "Detecting and correcting outliers" refers to identifying values ​​in data that fall outside the normal range and correcting or eliminating them.

[0851] "Preprocessed human resources information" refers to human resources information that has been preprocessed to improve data quality, such as by completing missing values ​​and correcting outliers.

[0852] A "generative AI model" refers to a model designed to learn patterns and features from data using artificial intelligence techniques.

[0853] "Characteristics of successful employees" refers to the common traits and skills that employees who succeed in a particular role or department have in common.

[0854] A "skill set" refers to the collection of expertise and abilities that an employee possesses.

[0855] "Desired placement" refers to the job or placement that an employee desires.

[0856] "Performance" refers to an employee's past work performance and achievements.

[0857] "Emotional information" refers to data that indicates an employee's emotional state, and primarily refers to information related to stress levels and motivation.

[0858] "Optimal staffing proposal" refers to the most appropriate staffing proposal, taking into account employees' skill sets, desired placements, performance, and emotional information.

[0859] "Promotion requirements" refer to the skills, experience, abilities, and other conditions that an employee must meet in order to be promoted.

[0860] "Interview questions" refer to questions asked to job applicants during an interview.

[0861] "Job applicant data" refers to detailed information such as resumes and job histories provided by job seekers.

[0862] "Cleansing" refers to the process of correcting data duplication and inconsistencies to create an accurate and consistent data set.

[0863] "Real-time acquisition" refers to acquiring data at the moment it is processed.

[0864] "Providing adaptive questions" refers to the actual use of questions generated according to the situation during the interview.

[0865] The present invention is a system for optimizing personnel allocation, promotion, and recruitment in a company, and by combining it with a new emotion engine that recognizes the user's emotions, it achieves more effective personnel management than ever before. Below, a detailed description is given of an embodiment of the system of the present invention.

[0866] Data collection methods

[0867] server

[0868] The server automatically collects human resource information from each department, including employee performance data, skill sheets, performance reviews, 360-degree evaluations, etc. It periodically retrieves information using APIs and database queries.

[0869] Specific examples

[0870] The server collects sales results from the sales department, campaign performance evaluations from the marketing department, and technical evaluations from the technical department. For example, you can set a timer to collect data at 6:00 PM every day.

[0871] Data preprocessing methods

[0872] server

[0873] The server implements algorithms to impute missing values ​​and detect and correct outliers in the collected data, thereby ensuring data quality.

[0874] Specific examples

[0875] The server imputes missing values ​​using the KNN method and detects and corrects outliers using Z-scores, e.g., absent data are estimated from neighboring data points and anomalous values ​​are corrected using statistical methods.

[0876] Analysis of the characteristics of successful personnel

[0877] server

[0878] The server then inputs the pre-processed data into a generative AI model (e.g., clustering or regression analysis) to extract the characteristics of successful employees, thereby identifying patterns of employees who will be successful in a particular role or department.

[0879] Specific examples

[0880] The server uses a clustering algorithm (K-means) to analyze the patterns of successful sales personnel. For example, it can identify that those with "high communication skills," "initiative," and "excellent problem-solving abilities" are more likely to succeed.

[0881] Form of generating optimal staffing plan

[0882] server

[0883] The server implements an algorithm that generates optimal placement plans based on the characteristics of successful employees, taking into account the employee's skill set, desired placement, performance, and even the user's emotional information.

[0884] Specific examples

[0885] The server generates a proposal to assign Employee X in the technical department as a leader of a new project based on his skill set and past performance. It also analyzes Employee X's emotional information using an emotion engine to confirm that his stress level is low.

[0886] Form of definition of promotion requirements

[0887] server

[0888] The server defines promotion requirements based on the characteristics of the top performers. These requirements are based on specific competencies, skill sets, and past performance, as well as emotional information provided by the emotion engine.

[0889] Specific examples

[0890] Sarver defines the promotion requirements for managers as "high leadership," "experience in supervising subordinates," and "project management skills," and adds "stable emotional control ability."

[0891] Cleansing applicant information and generating interview questions

[0892] server

[0893] The server collects and cleans information on job applicants, and builds a system that automatically generates questions to be used in interviews. It also obtains the user's emotional information in real time during the interview and provides adaptive questions.

[0894] Specific examples

[0895] The server extracts career data from applicant Y's resume, removes duplicate and inconsistent data, and then generates questions to be used in the interview, such as "What was the most difficult problem you solved in your previous job?" and "What kind of leadership experience do you have?" During the interview, the emotion engine recognizes the emotions of the users (interviewer and applicant), and if they are feeling stressed, it inserts questions to help them relax.

[0896] Notifications and User Interface Forms

[0897] server

[0898] The server implements a system that notifies the user of the generated placement proposals, promotion requirements, and interview questions.

[0899] User

[0900] The user can then use the information provided to make optimal personnel placements, promotions, and recruitment. The system provides an interface that allows users to operate the system efficiently and effectively.

[0901] Specific examples

[0902] Human resources personnel log in to the system and check the optimal personnel placement plan for new departments, and also use it to set promotion requirements and interview job applicants. They also consider the emotional data provided by the emotion engine to make optimal decisions.

[0903] Prompt Sentence Examples

[0904] 1. "What are the characteristics of an ideal person for a technical project leader?"

[0905] 2. "Define the promotion requirements for your sales department and include the necessary skill sets and emotional information."

[0906] The system of the present invention is a system that enhances a company's human resource management by consistently performing data collection, preprocessing, analysis, emotion recognition, and notification, thereby reducing employee turnover and improving productivity.

[0907] The flow of the identification process in the second embodiment will be described with reference to FIG.

[0908] Step 1: Data collection

[0909] server

[0910] Input: Human resource information from each department (performance data, skill sheets, work evaluations, 360-degree evaluations, etc.)

[0911] Processing: Use APIs and database queries to periodically collect personnel information from each department. For example, set a timer to retrieve data at 6:00 PM every day.

[0912] Output: Raw data collected

[0913] Specific operation: The server connects to the database and periodically retrieves data such as the sales performance of the sales department, the campaign results of the marketing department, and the technical evaluation of the technical department.

[0914] Step 2: Data Preprocessing

[0915] server

[0916] Input: Raw data collected

[0917] Processing: Apply missing value imputation and outlier detection / correction algorithms, e.g., KNN imputation and Z-score outlier detection / correction.

[0918] Output: Quality-assured pre-processed data

[0919] Specific operation: The server estimates missing data points using the KNN method and corrects abnormal data points using statistical methods.

[0920] Step 3: Identifying the characteristics of successful employees

[0921] server

[0922] Input: Preprocessed data

[0923] Processing: Use generative AI models (e.g., clustering and regression analysis) to extract traits of top performers. Run a clustering algorithm (e.g., K-means) to analyze patterns.

[0924] Output: List of characteristics of successful employees

[0925] How it works: The server inputs the preprocessed data into the K-means clustering algorithm to identify features such as "good communication skills," "proactive behavior," and "excellent problem-solving ability."

[0926] Step 4: Generate optimal staffing plans

[0927] server

[0928] Input: List of characteristics of successful personnel, employee skill set, desired placement, performance, emotional information

[0929] Processing: Based on the generated features, the optimal placement plan is generated using a personnel placement algorithm. Data from the emotion engine is taken in to consider the optimal placement.

[0930] Output: Optimal staffing plan

[0931] Specific operation: The server confirms that the stress level of technical department employee X is low, and then generates a proposal to place him as the leader of a new project, taking into account his skill set and achievements.

[0932] Step 5: Define promotion requirements

[0933] server

[0934] Input: List of characteristics of successful personnel, emotional information

[0935] Processing: Using a generative AI model to define promotion requirements for specific roles, such as managerial positions, including specific competencies, skill sets, and even emotional control skills.

[0936] Output: Promotion requirements list

[0937] Specific operation: The server generates promotion requirements including "high leadership," "experience in supervising subordinates," "project management ability," and "stable emotional control ability."

[0938] Step 6: Cleanse applicant information and generate interview questions

[0939] server

[0940] Input: Raw data of job applicants (resume, curriculum vitae, etc.)

[0941] Processing: Data cleansing is performed, questions are automatically generated for use in interviews, and emotional information during the interview is acquired in real time to provide adaptive questions.

[0942] Output: Cleansed applicant data, interview question list

[0943] Specific operation: The server removes duplicate and inconsistent data and generates questions such as "What was the most difficult problem you solved in your previous job?" and "What kind of leadership experience do you have?" based on information extracted from the resume. During the interview, questions to put the candidate at ease are added based on emotional data obtained from the emotion engine.

[0944] Step 7: Notifications and User Interface

[0945] server

[0946] Input: Optimal personnel placement plan, promotion requirements list, interview questions list

[0947] Processing: Implement a system that notifies the user of the generated information. Design an interface that allows the user to check and manipulate the information.

[0948] Output: Information notified to the user

[0949] Specific operation: A human resources officer logs into the system, checks the staffing plan for a new project, the promotion requirements for managerial positions, and the interview questions for applicants, and makes a decision based on the information. Data from the emotion engine is also referenced to make a comprehensive judgment.

[0950] (Application example 2)

[0951] 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."

[0952] Conventional personnel allocation systems did not take into account emotional information in their personnel management, making it difficult to optimally allocate and promote employees based on their stress levels and emotional states. Real-time employee emotional recognition in physical stores and flexible personnel allocation based on this recognition are also needed. This will improve the performance of physical stores and customer satisfaction.

[0953] The identification processing by the identification processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means. In this invention, the server includes means for collecting human resource information from each department and organization, means for complementing missing values ​​in the collected human resource information and detecting and correcting outliers, means for analyzing the characteristics of active personnel using a generation AI based on the preprocessed human resource information, means for generating an optimal human resource allocation plan based on the characteristics of the active personnel, means for notifying the user of the generated human resource allocation plan, means for cleansing data on job applicants and generating interview questions, and means for collecting emotional information from employees at physical stores and reflecting the information in an analysis of the characteristics of active personnel and in an optimal human resource allocation plan. This makes it possible to generate optimal human resource allocation plans and promotion plans that reflect employee emotional information.

[0954] "Means for collecting human resources information from each department and organization" refers to a system that automatically obtains information such as employee skills, performance, and evaluations from different departments and organizations within the company.

[0955] "Means for completing missing values ​​in collected human resources information and detecting and correcting outliers" refers to algorithms and methods for completing missing information in collected data and finding and correcting outliers.

[0956] "Method of analyzing the characteristics of successful employees using generative AI based on preprocessed human resources information" refers to a method of using information that has undergone data preprocessing and generative AI to extract patterns and characteristics of employees who are likely to be successful.

[0957] "Means for generating optimal personnel placement plans based on the characteristics of successful personnel" is a system for determining the placement in which each employee can work most effectively, based on the characteristics of successful employees.

[0958] The "means for notifying the user of the generated personnel placement plan" is a method for notifying a company's personnel manager or a person in charge of human resources of the generated personnel placement plan.

[0959] "Method for cleansing job applicant data and generating interview questions" refers to a method for organizing and processing job applicant information, deleting unnecessary data, and automatically creating questions to be used in interviews.

[0960] "Means for collecting emotional information from employees in physical stores and reflecting it in an analysis of the characteristics of successful employees and in generating optimal personnel placement plans" refers to a method for collecting the emotional state of employees working in stores in real time and using that information to analyze the characteristics of successful employees and generate personnel placement plans.

[0961] To implement the present invention, it is necessary to build a system that performs the following steps in order: The following describes in detail the hardware, software, and processing procedures of the actual system.

[0962] System configuration

[0963] 1. Hardware

[0964] Server (general server or cloud infrastructure: AWS, Microsoft Azure, etc.)

[0965] User devices (PCs, tablets, smartphones, etc.)

[0966] 2. Software

[0967] Data processing and preprocessing: Python, Pandas

[0968] Outcome analysis and clustering: Scikit-Learn (StandardScaler, K-Means Clustering)

[0969] Emotion Recognition Engine

[0970] Notification system: Email service or in-app notifications

[0971] Data collection and preprocessing

[0972] The server automatically collects employee information from each department within the company using APIs and database queries, including employee performance data, skill sets, performance reviews, and 360-degree feedback.

[0973] Next, missing values ​​in the collected data are imputed and outliers are detected and corrected. For example, missing values ​​are imputed using the KNN method, and outliers are detected and corrected using Z-scores.

[0974] Analysis of the characteristics of successful personnel

[0975] The preprocessed data is then input into an AI model to extract the characteristics of successful employees. Specifically, the data is analyzed using a clustering algorithm (K-means). This allows us to understand the patterns of employees who are successful in specific roles or departments.

[0976] Creation and notification of staffing plans

[0977] We implement an algorithm that generates optimal staffing plans based on the characteristics of successful employees. This algorithm takes into account employees' skill sets, desired placements, performance, and even emotional information obtained from an emotion recognition engine. The generated placement plans are then notified to users via email services or an in-app notification system.

[0978] Generating interview questions

[0979] The system uses an emotion recognition engine to collect and cleanse information from job applicants, obtain real-time emotional information during interviews, and generate appropriate questions based on that information.

[0980] Specific Examples

[0981] For example, in a physical store, the performance data and emotional information of employees A, B, and C are collected and analyzed, and it is discovered that employee A has excellent leadership skills and can make calm decisions even under pressure. Based on this information, a proposal is made to assign employee A as the leader of a new project. This proposal is notified to the store manager's terminal.

[0982] Prompt Sentence Examples

[0983] Here is an example of a prompt to input to a generative AI model:

[0984] "Generate optimal staffing recommendations based on employee performance data and sentiment information. For example, recommend the best roles for employees A, B, and C in the sales department and generate questions using sentiment information."

[0985] This makes it possible to provide optimal placement and promotion plans that take into account the emotional information of employees in physical stores.

[0986] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[0987] Program processing steps

[0988] Step 1:

[0989] The server collects talent information from each department within the company using database queries and APIs. Specific inputs include employee performance data, skill sets, performance reviews, and 360-degree reviews. This data is stored as raw data on the server. The output is an unprocessed talent information dataset.

[0990] Step 2:

[0991] The server performs data preprocessing to complete missing values ​​in the collected human resources information and detect and correct outliers. Specifically, it completes missing values ​​using the KNN method and detects and corrects outliers using Z-scores. The input for this step is the raw human resources information dataset, and the output is the preprocessed human resources information dataset.

[0992] Step 3:

[0993] The server inputs the preprocessed personnel information data into a generative AI model (such as K-means clustering) to analyze the characteristics of successful personnel. Specifically, it performs clustering taking into account employee skills, performance, and emotional information. The input is the preprocessed personnel information dataset, and the output is the clustering results that represent the characteristics of successful personnel.

[0994] Step 4:

[0995] The server generates an optimal personnel allocation plan based on the characteristics of the active personnel, using the clustering results. Specifically, it uses an algorithm to perform an allocation simulation while taking into account the characteristics of the employees. The input is the clustering results, and the output is the optimal personnel allocation plan.

[0996] Step 5:

[0997] The server notifies the generated optimal staffing plan to the user's (e.g., human resources officer or manager) device. Specifically, the plan is sent using an email service or an in-app notification system. The input is the optimal staffing plan, and the output is a notification to the user.

[0998] Step 6:

[0999] The server collects and cleans information about job applicants and generates interview questions. Specifically, it removes invalid data from the applicant's historical data and applies an algorithm to generate interview questions. The input is the applicant's raw data, and the output is the cleansed data and generated interview questions.

[1000] Step 7:

[1001] The server collects emotional information from store employees in real time and reflects this in the analysis of the characteristics of successful employees and in optimal staffing proposals. Specifically, it uses an emotion recognition engine to collect employee emotional data and incorporates it into a generative AI model. The input is the emotional information collected in real time, and the output is clustering results that reflect the emotional information and staffing proposals.

[1002] 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.

[1003] 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.

[1004] 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.

[1005] [Third embodiment]

[1006] FIG. 5 shows an example of the configuration of a data processing system 310 according to the third embodiment.

[1007] 5, the data processing system 310 includes the data processing device 12 and a headset terminal 314. An example of the data processing device 12 is a server.

[1008] 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).

[1009] 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.

[1010] 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.

[1011] 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).

[1012] 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. 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.

[1013] 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.

[1014] 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.

[1015] 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.

[1016] 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.

[1017] 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."

[1018] The present invention is a system for optimizing personnel allocation, promotion, and recruitment in a company. This system collects personnel information from each department within the company, preprocesses the collected data, and analyzes it to achieve optimal personnel management. Below, we will describe in detail the embodiments for implementing the system of the present invention.

[1019] Data collection methods

[1020] server

[1021] Build a system to automatically collect personnel information from each department, including employee performance data, skill sheets, performance evaluations, and 360-degree reviews.

[1022] Set up a system to periodically retrieve information using APIs or database queries.

[1023] Specific examples

[1024] The server collects sales results from the sales department, campaign performance evaluations from the marketing department, and technical evaluations from the technical department.

[1025] Data preprocessing methods

[1026] server

[1027] Implement algorithms to impute missing values ​​and detect and correct outliers in the collected data, thereby ensuring data quality.

[1028] Specific examples

[1029] The server imputes missing values ​​using the KNN method and detects and corrects outliers using Z-scores.

[1030] Analysis of the characteristics of successful personnel

[1031] server

[1032] The pre-processed data is then fed into an AI model (such as clustering or regression analysis) to extract the characteristics of successful employees, thereby identifying patterns of employees who will be successful in a particular role or department.

[1033] Specific examples

[1034] The server uses a clustering algorithm (K-means) to analyze the patterns of successful sales personnel. As a result, it finds that those with "high communication skills," "initiative," and "excellent problem-solving abilities" are more likely to succeed.

[1035] Form of generating optimal staffing plan

[1036] server

[1037] Implement an algorithm that generates optimal placement plans for existing employees based on the characteristics of successful employees, taking into account the employee's skill set, desired placement, and performance.

[1038] Specific examples

[1039] The server generates a proposal to place technical employee X as a leader of a new project based on his skill set and past performance.

[1040] Form of definition of promotion requirements

[1041] server

[1042] Define promotion requirements based on the characteristics of your top performers. These requirements are based on specific competencies, skill sets, and past performance.

[1043] Specific examples

[1044] Server defines the promotion requirements for managers as "strong leadership," "experience in supervising subordinates," and "project management skills."

[1045] Cleansing applicant information and generating interview questions

[1046] server

[1047] We will build a system that collects and cleans information on job applicants and automatically generates questions to be used in interviews.

[1048] Specific examples

[1049] The server extracts career data from applicant Y's resume, removes duplicate and inconsistent data, and then generates interview questions such as "What was the most difficult problem you solved in your previous job?" and "What kind of leadership experience do you have?"

[1050] Notifications and User Interface Forms

[1051] server

[1052] Implement a system to notify users of generated placement proposals, promotion requirements, and interview questions, allowing them to make data-driven decisions.

[1053] User

[1054] The user will then make optimal personnel allocation, promotion, and recruitment decisions based on the information provided. The system aims to have an interface that allows users to operate it efficiently and effectively.

[1055] Specific examples

[1056] Human resources personnel log in to the system to check the optimal personnel placement plans for new departments, and also use it to set promotion requirements and interview job applicants.

[1057] The system of the present invention performs data collection, preprocessing, analysis, and notification in an integrated manner, thereby enhancing a company's human resource management, reducing employee turnover and improving productivity.

[1058] The processing flow will be explained below.

[1059] Program processing steps

[1060] Step 1:

[1061] server

[1062] Collect human resource information from each department, including performance data, skill sheets, performance reviews, and 360-degree evaluations, using APIs and database queries.

[1063] Specific actions

[1064] 1. Send a request to an API endpoint to retrieve data from each department's system.

[1065] 2. Run an SQL query to extract historical performance data from the database.

[1066] Step 2:

[1067] server

[1068] Preprocessing of collected data is performed, specifically, missing values ​​are complemented and outliers are detected and corrected.

[1069] Specific actions

[1070] 1. Run the missing value imputation algorithm (KNN method) to estimate and impute missing data.

[1071] 2. An outlier detection algorithm (Z-score) is used to correct abnormal data points.

[1072] Step 3:

[1073] server

[1074] The preprocessed data is used to analyze the characteristics of successful employees, specifically through clustering and regression analysis.

[1075] Specific actions

[1076] 1. Run a clustering algorithm (K-means) to classify the personnel into multiple groups.

[1077] 2. Use regression analysis to assess the contribution of specific skills and achievements to success.

[1078] Step 4:

[1079] server

[1080] Generate optimal employee placement recommendations based on the characteristics of top performers, taking into account employee skill sets, performance, and individual placement preferences.

[1081] Specific actions

[1082] 1. Use the Thriving Talent Model to map each employee's skill set to the job needs.

[1083] 2. Use a selection algorithm to suggest the best department and role.

[1084] Step 5:

[1085] server

[1086] Define promotion requirements, including specific competencies, skill sets, and past performance.

[1087] Specific actions

[1088] 1. Use a decision tree algorithm to define the requirements for promotion.

[1089] 2. Save the defined requirements in the database and notify the person in charge.

[1090] Step 6:

[1091] server

[1092] Cleanse job applicant data and generate interview questions.

[1093] Specific actions

[1094] 1. Run data cleansing algorithms to remove inconsistencies and duplicate data.

[1095] 2. Uses Natural Language Processing (NLP) technology to generate appropriate interview questions from applicants' resumes.

[1096] Step 7:

[1097] server

[1098] The generated placement proposals, promotion requirements, and interview questions are notified to the user.

[1099] User

[1100] Based on the information provided, specific decisions regarding personnel placement, promotion, and hiring are made.

[1101] Specific actions

[1102] 1. Generates a notification containing the analysis results and displays it on the user's dashboard.

[1103] 2. The user logs into the system to review and use the suggestions.

[1104] In this way, this system enhances a company's human resource management through a series of steps, including data collection, analysis of the characteristics of successful personnel, generation of optimal placement plans, definition of promotion requirements, and processing related to job applicants.

[1105] Example 1

[1106] 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."

[1107] Conventional human resource management systems have the problem that it is difficult to efficiently grasp the skills and performance of individual employees, cooperation between departments, and the appropriateness of promotions and placements, making it difficult to contribute to improving productivity and turnover rates across the company.In addition, collecting information on job applicants and preparing for interviews requires a great deal of effort and time, so there was a need for efficiency improvements.

[1108] 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.

[1109] In this invention, the server includes: means for collecting human resource information from each department and organization; means for completing missing values ​​in the collected human resource information and detecting and correcting outliers; means for analyzing the characteristics of active personnel using a generative AI model based on the preprocessed human resource information; means for generating an optimal human resource placement plan based on the characteristics of active personnel; means for notifying a user of the generated placement plan; means for cleansing job applicant data and generating interview questions; means for generating an optimal human resource placement plan taking into account employee skill sets, desired placements, and performance; and means for notifying a user of the generated interview questions and supporting job applicant interviews. This improves the efficiency of human resource management across the company, realizes appropriate human resource placement and promotion, and simplifies job applicant interview preparation, thereby improving corporate productivity and reducing employee turnover.

[1110] "Human resource information" refers to information including the performance, skills, work evaluations, and 360-degree evaluations of employees working in each department and organization of a company.

[1111] "Missing values" are values ​​that are missing in a dataset and are a factor that impairs the accuracy of data analysis.

[1112] An "outlier" is a value in a dataset that is significantly different from other data and may affect the results of data analysis.

[1113] A "generative AI model" is an algorithm that uses artificial intelligence to extract and analyze specific patterns and features from data.

[1114] "Characteristics of successful employees" refer to the skills and characteristics common to employees who achieve outstanding results in specific roles or departments within a company.

[1115] A "staffing proposal" is a plan that proposes the optimal staffing arrangement within a company, and is generated based on employees' skill sets, performance, desired placement, etc.

[1116] "Notification" is the act of informing the user of important information such as the generated personnel allocation plan and interview questions.

[1117] "Cleansing" is the process of detecting, deleting, or correcting duplicates and inconsistencies in data collected from a database.

[1118] "Interview questions" are questions used during interviews with job applicants or employees, and are used to evaluate the applicant's abilities and experience.

[1119] A "skill set" is the collection of skills and abilities that a particular employee possesses.

[1120] "Desired placement" refers to the department or role that an employee desires.

[1121] "Performance" refers to an employee's past achievements and evaluations in performing their duties.

[1122] The above definitions allow each element of the system to be clearly understood.

[1123] The present invention is a system for optimizing personnel allocation, promotion, and recruitment in a company. This system collects personnel information from each department within the company, preprocesses the collected data, and analyzes it to achieve optimal personnel management. Below, we will describe in detail the embodiments for implementing the system of the present invention.

[1124] Data collection methods

[1125] server

[1126] The server automatically collects personnel information such as employee performance data, skill sheets, work evaluations, and 360-degree evaluations from each department of the company. This information is periodically retrieved using APIs and database queries. Specifically, it collects sales performance from the sales department, campaign success evaluations from the marketing department, and technical evaluations from the technical department.

[1127] Data preprocessing methods

[1128] server

[1129] The server runs algorithms to impute missing values ​​in the collected data and to detect and correct outliers, for example, imputing missing values ​​using the KNN (k-Nearest Neighbors) method and detecting outliers using Z-scores.

[1130] Analysis of the characteristics of successful personnel

[1131] server

[1132] The server inputs the preprocessed data into a generative AI model (such as clustering or regression analysis) to extract the characteristics of successful employees. Specifically, the K-means clustering algorithm can be used to analyze successful employees in the sales department. The results show that those with "high communication skills," "proactive action," and "excellent problem-solving abilities" are more likely to succeed.

[1133] Form of generating optimal staffing plan

[1134] server

[1135] The server generates optimal personnel placement proposals based on the characteristics of active personnel, taking into account the employee's skill set, desired placement, and performance. For example, it generates a proposal to place employee X in the technical department as a leader of a new project based on his skill set and past performance.

[1136] Form of definition of promotion requirements

[1137] server

[1138] The server defines promotion requirements based on the characteristics of successful employees. These requirements are set based on specific abilities, skill sets, and past performance. For example, the server defines "high leadership," "experience in mentoring subordinates," and "project management ability" as promotion requirements for managerial positions.

[1139] Cleansing applicant information and generating interview questions

[1140] server

[1141] The server collects and cleans information on job applicants and automatically generates interview questions. Specifically, it extracts resume data for applicant Y, deletes inconsistent and duplicate data, and then generates interview questions such as "What was the most difficult problem you solved in your previous job?" and "What kind of leadership experience do you have?"

[1142] Notifications and User Interface Forms

[1143] server

[1144] The server implements a system that notifies the user of the generated placement proposals, promotion requirements, and interview questions, allowing the user to make data-based decisions.

[1145] User

[1146] Based on the information provided, users can make optimal personnel placements, promotions, and hiring decisions. The system provides an interface that users can use efficiently and effectively. Specifically, human resources personnel can log in to the system, check the optimal personnel placement proposals for new departments, and use the results to set promotion requirements and interview job applicants.

[1147] Prompt Sentence Examples

[1148] "Analyze patterns of successful talent using sales performance and campaign success evaluation data."

[1149] "Generate a placement plan to select the best person to lead a new project in the technology department."

[1150] "Extract applicant biographical data and generate interview questions."

[1151] This system will enhance a company's human resource management by consistently collecting, preprocessing, analyzing, and notifying data, thereby reducing employee turnover and improving productivity.

[1152] The flow of the identification process in the first embodiment will be described with reference to FIG.

[1153] Step 1:

[1154] Data collection

[1155] The server has a means of collecting human resource information from each department and organization. In this case, the input is information such as employee performance data, skill sheets, work evaluations, and 360-degree evaluations stored in each department's database. The server periodically obtains the necessary information using API requests and database queries. The server then stores the obtained data in storage. For example, the server might collect sales performance from the sales department, campaign success evaluations from the marketing department, and technical evaluations from the technical department.

[1156] Step 2:

[1157] Data Preprocessing

[1158] The server preprocesses the collected data. The input is the raw data collected in step 1. Specifically, the server first detects missing values ​​in the data and imputes them using the KNN (k-Nearest Neighbors) method. Next, it calculates Z-scores to detect outliers. If an outlier is found, the server corrects or removes it. The final output is clean data with missing and outlier values ​​corrected.

[1159] Step 3:

[1160] Analysis of the characteristics of successful personnel

[1161] The server inputs the clean data into the generative AI model and analyzes the characteristics of successful employees. The input is the data preprocessed in step 2. Specifically, the server runs the K-means clustering algorithm. It analyzes the clustering results and identifies the characteristics of each cluster. These characteristics include "good communication skills," "proactive action," and "excellent problem-solving ability." The output is a list of the characteristics of successful employees.

[1162] Step 4:

[1163] Generate optimal staffing plans

[1164] The server generates a personnel placement plan based on the characteristics of the active personnel. The inputs are the characteristics of the active personnel obtained in step 3, the employee's skill set, desired placement, and performance data. Specifically, the server compares each employee's data with the characteristics of the active personnel to generate an optimal placement plan. For example, the server references the skill set and past performance of employee X in the technical department and generates a plan to place him as the leader of a new project. The output is an optimal personnel placement plan.

[1165] Step 5:

[1166] Define promotion requirements

[1167] The server defines promotion requirements based on the characteristics of successful employees. The input is the list of characteristics obtained in step 3. Specifically, the server extracts the abilities, skill sets, and experience required for a specific position from the characteristics of successful employees. For example, it defines "high leadership," "experience in supervising subordinates," and "project management ability" as promotion requirements for managerial positions. The output is a list of described promotion requirements.

[1168] Step 6:

[1169] Cleansing applicant information and generating interview questions

[1170] The server cleanses the information of job applicants and generates interview questions. The input is the resume data of job applicants. Specifically, the server analyzes the resume data and removes or corrects duplicate and inconsistent data. Next, based on the cleansed data, it generates questions to be used in interviews. For example, it generates questions such as "What was the most difficult problem you solved in your previous job?" and "What kind of leadership experience do you have?" The output is the cleansed applicant information and the generated interview questions.

[1171] Step 7:

[1172] Notifications and User Interface

[1173] The server notifies the user of the generated placement plans, promotion requirements, and interview questions. The input is the output of steps 4, 5, and 6. Specifically, the server presents the generated results to the user in the form of a dashboard or email notification. The user then uses the notified information to make optimal personnel placements, promotions, and recruitment. For example, a human resources officer logs into the system, checks the optimal personnel placement plans for a new department, and uses this information to set promotion requirements and interview job applicants. The output is a notification to the user and an interface that the user can use.

[1174] (Application example 1)

[1175] 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."

[1176] In conventional factories, managing robot operating status and maintenance schedules required individual data management and manual adjustments, making it difficult to achieve optimal operating efficiency and maintenance plans. Furthermore, the collection and analysis of human resource information required a great deal of effort, preventing optimal personnel placement and promotion. There is a need to improve this situation and increase the efficiency and productivity of factories and organizations as a whole.

[1177] 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.

[1178] In this invention, the server includes: means for collecting human resource information from each department and organization; means for completing missing values ​​in the collected human resource information and detecting and correcting outliers; means for analyzing the characteristics of active human resources using a generation AI based on the preprocessed human resource information; means for generating an optimal human resource deployment plan based on the characteristics of active human resources; means for notifying a user of the generated deployment plan; means for collecting operation information, work efficiency, and maintenance history; means for preprocessing the collected operation information and detecting and correcting outliers; means for generating an optimal robot deployment plan and maintenance schedule using a generation AI based on the preprocessed operation information; means for cleansing job applicant data and generating interview questions; and means for providing a user interface for confirming the optimal deployment and schedule based on the notified information. This enables optimization of the operating efficiency of robots in factories, formulation of preventative maintenance schedules, and appropriate human resource deployment and promotion.

[1179] "Each department or organization" refers to different divisions, teams, or functional groups within a company or factory.

[1180] "Human resources information" refers to relevant data about employees and job seekers, such as performance, skills, evaluations, and work history.

[1181] "Means of collection" refers to the systems and methods for obtaining the necessary information through various databases and APIs.

[1182] "Missing value imputation" refers to the process of estimating and filling in missing values ​​in a dataset.

[1183] "Outlier detection and correction" refers to the process of finding values ​​in a data set that are outside of the normal range and changing them to appropriate values.

[1184] "Preprocessed human resources information" refers to clean data that has been collected and has undergone missing value imputation and outlier correction.

[1185] "Generative AI" refers to artificial intelligence algorithms used to rapidly analyze large amounts of data and extract specific patterns and features.

[1186] "High-performing talent" refers to employees who perform well in specific conditions or roles.

[1187] "Means for analyzing features" means methods that use data analytics and machine learning algorithms to extract trends and patterns from data.

[1188] "Optimal human resource allocation plan" refers to the assignment of departments and projects that allow employees to work most effectively.

[1189] "Means for notifying the user" refers to an interface or method for notifying the user of generated information or results.

[1190] "Operational information" refers to data on how robots and systems are actually operating.

[1191] "Work efficiency" refers to the ratio of productive output to effort put in.

[1192] "Maintenance history" means a record of the maintenance that a device or system has undergone.

[1193] An "allocation plan" refers to a plan for how to allocate equipment and personnel to operating departments or specific projects.

[1194] A "maintenance schedule" refers to a schedule for systematically carrying out maintenance work on equipment and systems.

[1195] "Job applicants" refers to individuals who have applied for a new position.

[1196] "Data cleansing" refers to the process of removing unnecessary information from raw data and preparing it for analysis.

[1197] "Interview questions" refer to questions used in interviews.

[1198] "User interface" refers to the screens and operating methods that allow users to directly interact with a system.

[1199] This invention is a system that collects and analyzes data on the operational status, work efficiency, and maintenance history of robots in factories, and generates optimal robot placement and maintenance schedules. This system performs all processes, from collecting data on operational information, work efficiency, and maintenance history to notifying users of the placement plans and schedules it generates.

[1200] Data collection

[1201] The server has a means to automatically collect operational information, work efficiency, and maintenance history from each robot operating in the factory. This collection process is carried out through sensors installed on each robot and API, and the data is sent to the server.

[1202] Examples:

[1203] The server collects operating hours, number of completed tasks, and recent maintenance history from each robot in the factory via an API.

[1204] Data Preprocessing

[1205] The server implements algorithms to fill in missing values ​​in the collected data and detect and correct outliers, a process that ensures data quality and enables accurate analysis.

[1206] Examples:

[1207] Missing values ​​in the dataset collected by the server are imputed using the KNN method, and outliers are detected and corrected using Z scores.

[1208] Generation of optimal robot placement plans and maintenance schedules

[1209] Based on the pre-processed data, generative AI models (such as clustering and regression analysis) are used to generate optimal robot placement plans and maintenance schedules. The results suggest the most efficient use of robots in factory operations.

[1210] Examples:

[1211] The server uses a clustering algorithm (K-means) to analyze the operating patterns of each robot and identify robots with "high operating time," "efficient task completion," and "low maintenance frequency."

[1212] Notification of placement plan and schedule

[1213] The generated optimal deployment plan and maintenance schedule are notified to the user. The server is responsible for this notification process, and the information is displayed and shared through the user interface.

[1214] Examples:

[1215] The server notifies the user of the generated deployment plan and maintenance schedule via email or a dedicated dashboard.

[1216] Based on the information provided, users can plan optimal robot placement and maintenance, improving productivity and efficiency within their factories.

[1217] Example prompt sentence:

[1218] Input the operation data and maintenance history data of the robots in the factory, analyze the characteristics of the active robots, and generate optimal placement plans and maintenance schedules.

[1219] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[1220] Step 1:

[1221] The server collects operational information, work efficiency, and maintenance history from the robots operating in the factory via API. The input is data from each robot's sensors and internal systems, which is obtained via API. The output is a raw dataset that we use for preprocessing. This dataset includes each robot's operating time, number of completed tasks, and maintenance history.

[1222] Step 2:

[1223] The server performs preprocessing of the collected data. First, it performs missing value imputation. It uses KNN imputation to estimate and fill missing values ​​in the dataset. Next, it performs outlier detection and correction. It uses Z-score to detect data points that fall outside the normal range and corrects them. This ensures the quality of the data. The input is the original dataset collected in step 1, and the output is clean data with missing and outlier values ​​corrected.

[1224] Step 3:

[1225] The server inputs the preprocessed data into the generative AI model to analyze the robot's operating patterns. A clustering algorithm (e.g., K-means) is used for this analysis. The input is the clean data generated in step 2, and the output is the robot patterns classified by cluster. Specifically, the feature values ​​of each robot (operating time, work efficiency, etc.) are input into the algorithm to perform clustering.

[1226] Step 4:

[1227] The server uses the generative AI model to generate optimal robot placement plans and maintenance schedules. The input is the data classified by cluster in Step 3. Based on the data, it formulates placement plans for robots with high operating efficiency and a corresponding preventive maintenance schedule. The output is the optimal placement plan and maintenance schedule. Specifically, based on the characteristics of each cluster, it determines which robots should be placed in which areas and when maintenance is required.

[1228] Step 5:

[1229] The server notifies the user of the generated deployment plan and maintenance schedule. Notifications are made via email or a dedicated dashboard. The input is the deployment plan and maintenance schedule generated in step 4, and the output is the information displayed on the user's operation screen. Specifically, the generated information is converted into an appropriate format and displayed through the user interface.

[1230] Step 6:

[1231] The user checks the notified deployment plan and maintenance schedule and puts them into action. The input is the information displayed in step 5. The user makes the necessary adjustments based on the optimal deployment plan and schedule to optimize the operation of the robots. The output is the adjusted operation plan and maintenance schedule. In concrete terms, the user deploys each robot and performs maintenance work on-site based on the notified content.

[1232] 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.

[1233] The present invention achieves more effective human resource management than ever before by combining a system for optimizing personnel allocation, promotion, and recruitment in a company with a new emotion engine that recognizes user emotions. Below, a detailed description is given of an embodiment of the system of the present invention.

[1234] Data collection methods

[1235] server

[1236] Build a system to automatically collect personnel information from each department, including employee performance data, skill sheets, performance evaluations, and 360-degree reviews.

[1237] Set up a system to periodically retrieve information using APIs or database queries.

[1238] Specific examples

[1239] The server collects sales results from the sales department, campaign performance evaluations from the marketing department, and technical evaluations from the technical department.

[1240] Data preprocessing methods

[1241] server

[1242] Implement algorithms to impute missing values ​​and detect and correct outliers in the collected data, thereby ensuring data quality.

[1243] Specific examples

[1244] The server imputes missing values ​​using the KNN method and detects and corrects outliers using Z-scores.

[1245] Analysis of the characteristics of successful personnel

[1246] server

[1247] The pre-processed data is then fed into an AI model (such as clustering or regression analysis) to extract the characteristics of successful employees, thereby identifying patterns of employees who will be successful in a particular role or department.

[1248] Specific examples

[1249] The server uses a clustering algorithm (K-means) to analyze the patterns of successful sales personnel. As a result, it finds that those with "high communication skills," "initiative," and "excellent problem-solving abilities" are more likely to succeed.

[1250] Form of generating optimal staffing plan

[1251] server

[1252] We will implement an algorithm that generates optimal employee placement plans based on the characteristics of successful employees, taking into account the employee's skill set, desired placement, performance, and even user sentiment.

[1253] Specific examples

[1254] The server generates a proposal to appoint Employee X in the technical department as a leader of a new project based on his skill set and past performance. It also analyzes Employee X's emotional information using an emotion engine to confirm that his stress level is low.

[1255] Form of definition of promotion requirements

[1256] server

[1257] Define promotion requirements based on the characteristics of your top performers. These requirements are based on specific competencies, skill sets, and past performance, as well as emotional information provided by the emotion engine.

[1258] Specific examples

[1259] Sarver defines the promotion requirements for managers as "high leadership," "experience in supervising subordinates," and "project management skills," and adds "stable emotional control ability."

[1260] Cleansing applicant information and generating interview questions

[1261] server

[1262] We will build a system that collects and cleans information on job applicants and automatically generates questions to be used in interviews. Furthermore, we will obtain the user's emotional information in real time during the interview and provide adaptive questions.

[1263] Specific examples

[1264] The server extracts career data from applicant Y's resume, removes duplicate and inconsistent data, and then generates questions to be used in the interview, such as "What was the most difficult problem you solved in your previous job?" and "What kind of leadership experience do you have?" During the interview, the emotion engine recognizes the emotions of the users (interviewer and applicant), and if they are feeling stressed, it inserts questions to help them relax.

[1265] Notifications and User Interface Forms

[1266] server

[1267] Implement a system to notify users of generated placement proposals, promotion requirements, and interview questions, allowing them to make data-driven decisions.

[1268] User

[1269] The user will then make optimal personnel allocation, promotion, and recruitment decisions based on the information provided. The system aims to have an interface that allows users to operate it efficiently and effectively.

[1270] Specific examples

[1271] Human resources personnel log in to the system and check the optimal personnel placement plan for new departments, and also use it to set promotion requirements and interview job applicants. They also consider the emotional data provided by the emotion engine to make optimal decisions.

[1272] The system of the present invention performs data collection, preprocessing, analysis, emotion recognition, and notification in an integrated manner, thereby enhancing a company's human resource management, reducing employee turnover and improving productivity.

[1273] The processing flow will be explained below.

[1274] Program processing steps

[1275] Step 1:

[1276] server

[1277] Collect human resource information from each department, including performance data, skill sheets, performance reviews, and 360-degree evaluations, using APIs and database queries.

[1278] Specific actions

[1279] 1. Send requests to API endpoints to retrieve data from each department's system.

[1280] 2. Run an SQL query to extract historical performance data from the database.

[1281] Step 2:

[1282] server

[1283] Preprocessing of collected data is performed, specifically, missing values ​​are complemented and outliers are detected and corrected.

[1284] Specific actions

[1285] 1. Run the missing value imputation algorithm (KNN method) to estimate and impute missing data.

[1286] 2. Correct anomalous data points using an outlier detection algorithm (Z-score).

[1287] Step 3:

[1288] server

[1289] The preprocessed data is used to analyze the characteristics of successful employees, specifically through clustering and regression analysis.

[1290] Specific actions

[1291] 1. Run a clustering algorithm (K-means) to classify the personnel into multiple groups.

[1292] 2. Use regression analysis to assess the contribution of specific skills and achievements to success.

[1293] Step 4:

[1294] server

[1295] Generate optimal employee placement plans based on the characteristics of top performers, taking into account employee skill sets, desired placements, performance, and even user sentiment.

[1296] Specific actions

[1297] 1. Use a talent model to map each employee's skill set to the needs of the job.

[1298] 2. Use a selection algorithm to suggest the best departments and roles.

[1299] 3. Analyze emotional data from the emotion engine and adjust placement recommendations based on the employee's current emotional state.

[1300] Step 5:

[1301] server

[1302] Define promotion requirements based on specific competencies, skill sets, and past performance, as well as emotional information provided by the emotion engine.

[1303] Specific actions

[1304] 1. Use a decision tree algorithm to define the requirements for promotion.

[1305] 2. Adjust the defined requirements taking into account the data from the emotion engine.

[1306] 3. Save the defined promotion requirements in the database and notify the person in charge.

[1307] Step 6:

[1308] server

[1309] The system cleanses job applicant data and generates interview questions. It also analyzes the user's emotional information during the interview in real time and provides adaptive questions.

[1310] Specific actions

[1311] 1. Run a data cleansing algorithm to remove inconsistencies and duplicate data.

[1312] 2. Use Natural Language Processing (NLP) technology to generate appropriate interview questions from applicants' resumes.

[1313] 3. During the interview, the emotion engine analyzes the emotions of the user (interviewer and applicant) and generates and inserts questions to relax them if they are feeling stressed.

[1314] Step 7:

[1315] server

[1316] The generated placement proposals, promotion requirements, and interview questions are notified to the user.

[1317] Specific actions

[1318] 1. Generate a notification containing the analysis results and display it on the user's dashboard.

[1319] 2. The user logs in to the system and checks and uses the suggestions.

[1320] Step 8:

[1321] User

[1322] Make specific staffing, promotion, and hiring decisions based on the information provided.

[1323] Specific actions

[1324] 1. A user logs in to the system and checks the optimal staffing plan for a new department.

[1325] 2. Using emotional data to determine promotion requirements and interview job applicants.

[1326] This system will enhance a company's human resource management by collecting data, analyzing the characteristics of successful personnel, generating optimal placement plans, defining promotion requirements, screening applicants, generating interview questions, and recognizing emotions, thereby reducing employee turnover and improving productivity.

[1327] Example 2

[1328] 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."

[1329] Traditional human resource management systems primarily analyze employees' performance and skills, making it difficult to optimize placement and promotion. Furthermore, because they do not take emotional information into account, they are unable to properly manage employee stress and motivation. Furthermore, because they are unable to generate appropriate questions based on real-time emotional analysis during interviews, the quality of interviews can decline.

[1330] The identification processing by the identification processing unit 290 of the data processing device 12 in Example 2 is realized by the following means. In this invention, the server includes: means for automatically collecting personnel information from each department and organization; means for complementing missing values ​​in the collected personnel information and detecting and correcting outliers; means for analyzing the characteristics of active personnel using a generative AI model based on the preprocessed personnel information; means for generating an optimal personnel allocation plan based on the characteristics of active personnel, taking into account employee skill sets, desired allocations, performance, and emotional information; means for notifying the user of the generated personnel allocation plan, promotion requirements, and interview questions; means for cleansing job applicant data and generating interview questions; and means for acquiring the user's emotional information during interviews in real time and providing adapted questions. This enables optimal personnel allocation and promotion based on data and effective personnel management that takes into account employees' emotional information. Furthermore, real-time emotional analysis during interviews can improve the quality of interviews.

[1331] "Each department or organization" refers to different divisions or organizational units within a company, each with its own unique tasks and roles.

[1332] "Human resource information" refers to detailed data about employees, such as performance data, skill sheets, work evaluations, and 360-degree evaluations.

[1333] "Missing value imputation" refers to the use of estimations or algorithms to fill in missing values ​​in collected data.

[1334] "Detecting and correcting outliers" refers to identifying values ​​in data that fall outside the normal range and correcting or eliminating them.

[1335] "Preprocessed human resources information" refers to human resources information that has been preprocessed to improve data quality, such as by completing missing values ​​and correcting outliers.

[1336] A "generative AI model" refers to a model designed to learn patterns and features from data using artificial intelligence techniques.

[1337] "Characteristics of successful employees" refers to the common traits and skills that employees who succeed in a particular role or department have in common.

[1338] A "skill set" refers to the collection of expertise and abilities that an employee possesses.

[1339] "Desired placement" refers to the job or placement that an employee desires.

[1340] "Performance" refers to an employee's past work performance and achievements.

[1341] "Emotional information" refers to data that indicates an employee's emotional state, and primarily refers to information related to stress levels and motivation.

[1342] "Optimal staffing proposal" refers to the most appropriate staffing proposal, taking into account employees' skill sets, desired placements, performance, and emotional information.

[1343] "Promotion requirements" refer to the skills, experience, abilities, and other conditions that an employee must meet in order to be promoted.

[1344] "Interview questions" refer to questions asked to job applicants during an interview.

[1345] "Job applicant data" refers to detailed information such as resumes and job histories provided by job seekers.

[1346] "Cleansing" refers to the process of correcting data duplication and inconsistencies to create an accurate and consistent data set.

[1347] "Real-time acquisition" refers to acquiring data at the moment it is processed.

[1348] "Providing adaptive questions" refers to the actual use of questions generated according to the situation during the interview.

[1349] The present invention is a system for optimizing personnel allocation, promotion, and recruitment in a company, and by combining it with a new emotion engine that recognizes the user's emotions, it achieves more effective personnel management than ever before. Below, a detailed description is given of an embodiment of the system of the present invention.

[1350] Data collection methods

[1351] server

[1352] The server automatically collects human resource information from each department, including employee performance data, skill sheets, performance reviews, 360-degree evaluations, etc. It periodically retrieves information using APIs and database queries.

[1353] Specific examples

[1354] The server collects sales results from the sales department, campaign performance evaluations from the marketing department, and technical evaluations from the technical department. For example, you can set a timer to collect data at 6:00 PM every day.

[1355] Data preprocessing methods

[1356] server

[1357] The server implements algorithms to impute missing values ​​and detect and correct outliers in the collected data, thereby ensuring data quality.

[1358] Specific examples

[1359] The server imputes missing values ​​using the KNN method and detects and corrects outliers using Z-scores, e.g., absent data are estimated from neighboring data points and anomalous values ​​are corrected using statistical methods.

[1360] Analysis of the characteristics of successful personnel

[1361] server

[1362] The server then inputs the pre-processed data into a generative AI model (e.g., clustering or regression analysis) to extract the characteristics of successful employees, thereby identifying patterns of employees who will be successful in a particular role or department.

[1363] Specific examples

[1364] The server uses a clustering algorithm (K-means) to analyze the patterns of successful sales personnel. For example, it can identify that those with "high communication skills," "initiative," and "excellent problem-solving abilities" are more likely to succeed.

[1365] Form of generating optimal staffing plan

[1366] server

[1367] The server implements an algorithm that generates optimal placement plans based on the characteristics of successful employees, taking into account the employee's skill set, desired placement, performance, and even the user's emotional information.

[1368] Specific examples

[1369] The server generates a proposal to assign Employee X in the technical department as a leader of a new project based on his skill set and past performance. It also analyzes Employee X's emotional information using an emotion engine to confirm that his stress level is low.

[1370] Form of definition of promotion requirements

[1371] server

[1372] The server defines promotion requirements based on the characteristics of the top performers. These requirements are based on specific competencies, skill sets, and past performance, as well as emotional information provided by the emotion engine.

[1373] Specific examples

[1374] Sarver defines the promotion requirements for managers as "high leadership," "experience in supervising subordinates," and "project management skills," and adds "stable emotional control ability."

[1375] Cleansing applicant information and generating interview questions

[1376] server

[1377] The server collects and cleans information on job applicants, and builds a system that automatically generates questions to be used in interviews. It also obtains the user's emotional information in real time during the interview and provides adaptive questions.

[1378] Specific examples

[1379] The server extracts career data from applicant Y's resume, removes duplicate and inconsistent data, and then generates questions to be used in the interview, such as "What was the most difficult problem you solved in your previous job?" and "What kind of leadership experience do you have?" During the interview, the emotion engine recognizes the emotions of the users (interviewer and applicant), and if they are feeling stressed, it inserts questions to help them relax.

[1380] Notifications and User Interface Forms

[1381] server

[1382] The server implements a system that notifies the user of the generated placement proposals, promotion requirements, and interview questions.

[1383] User

[1384] The user can then use the information provided to make optimal personnel placements, promotions, and recruitment. The system provides an interface that allows users to operate the system efficiently and effectively.

[1385] Specific examples

[1386] Human resources personnel log in to the system and check the optimal personnel placement plan for new departments, and also use it to set promotion requirements and interview job applicants. They also consider the emotional data provided by the emotion engine to make optimal decisions.

[1387] Prompt Sentence Examples

[1388] 1. "What are the characteristics of an ideal person for a technical project leader?"

[1389] 2. "Define the promotion requirements for your sales department and include the necessary skill sets and emotional information."

[1390] The system of the present invention is a system that enhances a company's human resource management by consistently performing data collection, preprocessing, analysis, emotion recognition, and notification, thereby reducing employee turnover and improving productivity.

[1391] The flow of the identification process in the second embodiment will be described with reference to FIG.

[1392] Step 1: Data collection

[1393] server

[1394] Input: Human resource information from each department (performance data, skill sheets, work evaluations, 360-degree evaluations, etc.)

[1395] Processing: Use APIs and database queries to periodically collect personnel information from each department. For example, set a timer to retrieve data at 6:00 PM every day.

[1396] Output: Raw data collected

[1397] Specific operation: The server connects to the database and periodically retrieves data such as the sales performance of the sales department, the campaign results of the marketing department, and the technical evaluation of the technical department.

[1398] Step 2: Data Preprocessing

[1399] server

[1400] Input: Raw data collected

[1401] Processing: Apply missing value imputation and outlier detection / correction algorithms, e.g., KNN imputation and Z-score outlier detection / correction.

[1402] Output: Quality-assured pre-processed data

[1403] Specific operation: The server estimates missing data points using the KNN method and corrects abnormal data points using statistical methods.

[1404] Step 3: Identifying the characteristics of successful employees

[1405] server

[1406] Input: Preprocessed data

[1407] Processing: Use generative AI models (e.g., clustering and regression analysis) to extract traits of top performers. Run a clustering algorithm (e.g., K-means) to analyze patterns.

[1408] Output: List of characteristics of successful employees

[1409] How it works: The server inputs the preprocessed data into the K-means clustering algorithm to identify features such as "good communication skills," "proactive behavior," and "excellent problem-solving ability."

[1410] Step 4: Generate optimal staffing plans

[1411] server

[1412] Input: List of characteristics of successful personnel, employee skill set, desired placement, performance, emotional information

[1413] Processing: Based on the generated features, the optimal placement plan is generated using a personnel placement algorithm. Data from the emotion engine is taken in to consider the optimal placement.

[1414] Output: Optimal staffing plan

[1415] Specific operation: The server confirms that the stress level of technical department employee X is low, and then generates a proposal to place him as the leader of a new project, taking into account his skill set and achievements.

[1416] Step 5: Define promotion requirements

[1417] server

[1418] Input: List of characteristics of successful personnel, emotional information

[1419] Processing: Using a generative AI model to define promotion requirements for specific roles, such as managerial positions, including specific competencies, skill sets, and even emotional control skills.

[1420] Output: Promotion requirements list

[1421] Specific operation: The server generates promotion requirements including "high leadership," "experience in supervising subordinates," "project management ability," and "stable emotional control ability."

[1422] Step 6: Cleanse applicant information and generate interview questions

[1423] server

[1424] Input: Raw data of job applicants (resume, curriculum vitae, etc.)

[1425] Processing: Data cleansing is performed, questions are automatically generated for use in interviews, and emotional information during the interview is acquired in real time to provide adaptive questions.

[1426] Output: Cleansed applicant data, interview question list

[1427] Specific operation: The server removes duplicate and inconsistent data and generates questions such as "What was the most difficult problem you solved in your previous job?" and "What kind of leadership experience do you have?" based on information extracted from the resume. During the interview, questions to put the candidate at ease are added based on emotional data obtained from the emotion engine.

[1428] Step 7: Notifications and User Interface

[1429] server

[1430] Input: Optimal personnel placement plan, promotion requirements list, interview questions list

[1431] Processing: Implement a system that notifies the user of the generated information. Design an interface that allows the user to check and manipulate the information.

[1432] Output: Information notified to the user

[1433] Specific operation: A human resources officer logs into the system, checks the staffing plan for a new project, the promotion requirements for managerial positions, and the interview questions for applicants, and makes a decision based on the information. Data from the emotion engine is also referenced to make a comprehensive judgment.

[1434] (Application example 2)

[1435] 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."

[1436] Conventional personnel allocation systems did not take into account emotional information in their personnel management, making it difficult to optimally allocate and promote employees based on their stress levels and emotional states. Real-time employee emotional recognition in physical stores and flexible personnel allocation based on this recognition are also needed. This will improve the performance of physical stores and customer satisfaction.

[1437] The identification processing by the identification processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means. In this invention, the server includes means for collecting human resource information from each department and organization, means for complementing missing values ​​in the collected human resource information and detecting and correcting outliers, means for analyzing the characteristics of active personnel using a generation AI based on the preprocessed human resource information, means for generating an optimal human resource allocation plan based on the characteristics of the active personnel, means for notifying the user of the generated human resource allocation plan, means for cleansing data on job applicants and generating interview questions, and means for collecting emotional information from employees at physical stores and reflecting the information in an analysis of the characteristics of active personnel and in an optimal human resource allocation plan. This makes it possible to generate optimal human resource allocation plans and promotion plans that reflect employee emotional information.

[1438] "Means for collecting human resources information from each department and organization" refers to a system that automatically obtains information such as employee skills, performance, and evaluations from different departments and organizations within the company.

[1439] "Means for completing missing values ​​in collected human resources information and detecting and correcting outliers" refers to algorithms and methods for completing missing information in collected data and finding and correcting outliers.

[1440] "Method of analyzing the characteristics of successful employees using generative AI based on preprocessed human resources information" refers to a method of using information that has undergone data preprocessing and generative AI to extract patterns and characteristics of employees who are likely to be successful.

[1441] "Means for generating optimal personnel placement plans based on the characteristics of successful personnel" is a system for determining the placement in which each employee can work most effectively, based on the characteristics of successful employees.

[1442] The "means for notifying the user of the generated personnel placement plan" is a method for notifying a company's personnel manager or a person in charge of human resources of the generated personnel placement plan.

[1443] "Method for cleansing job applicant data and generating interview questions" refers to a method for organizing and processing job applicant information, deleting unnecessary data, and automatically creating questions to be used in interviews.

[1444] "Means for collecting emotional information from employees in physical stores and reflecting it in an analysis of the characteristics of successful employees and in generating optimal personnel placement plans" refers to a method for collecting the emotional state of employees working in stores in real time and using that information to analyze the characteristics of successful employees and generate personnel placement plans.

[1445] To implement the present invention, it is necessary to build a system that performs the following steps in order: The following describes in detail the hardware, software, and processing procedures of the actual system.

[1446] System configuration

[1447] 1. Hardware

[1448] Server (general server or cloud infrastructure: AWS, Microsoft Azure, etc.)

[1449] User devices (PCs, tablets, smartphones, etc.)

[1450] 2. Software

[1451] Data processing and preprocessing: Python, Pandas

[1452] Outcome analysis and clustering: Scikit-Learn (StandardScaler, K-Means Clustering)

[1453] Emotion Recognition Engine

[1454] Notification system: Email service or in-app notifications

[1455] Data collection and preprocessing

[1456] The server automatically collects employee information from each department within the company using APIs and database queries, including employee performance data, skill sets, performance reviews, and 360-degree feedback.

[1457] Next, missing values ​​in the collected data are imputed and outliers are detected and corrected. For example, missing values ​​are imputed using the KNN method, and outliers are detected and corrected using Z-scores.

[1458] Analysis of the characteristics of successful personnel

[1459] The preprocessed data is then input into an AI model to extract the characteristics of successful employees. Specifically, the data is analyzed using a clustering algorithm (K-means). This allows us to understand the patterns of employees who are successful in specific roles or departments.

[1460] Creation and notification of staffing plans

[1461] We implement an algorithm that generates optimal staffing plans based on the characteristics of successful employees. This algorithm takes into account employees' skill sets, desired placements, performance, and even emotional information obtained from an emotion recognition engine. The generated placement plans are then notified to users via email services or an in-app notification system.

[1462] Generating interview questions

[1463] The system uses an emotion recognition engine to collect and cleanse information from job applicants, obtain real-time emotional information during interviews, and generate appropriate questions based on that information.

[1464] Specific Examples

[1465] For example, in a physical store, the performance data and emotional information of employees A, B, and C are collected and analyzed, and it is discovered that employee A has excellent leadership skills and can make calm decisions even under pressure. Based on this information, a proposal is made to assign employee A as the leader of a new project. This proposal is notified to the store manager's terminal.

[1466] Prompt Sentence Examples

[1467] Here is an example of a prompt to input to a generative AI model:

[1468] "Generate optimal staffing recommendations based on employee performance data and sentiment information. For example, recommend the best roles for employees A, B, and C in the sales department and generate questions using sentiment information."

[1469] This makes it possible to provide optimal placement and promotion plans that take into account the emotional information of employees in physical stores.

[1470] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[1471] Program processing steps

[1472] Step 1:

[1473] The server collects talent information from each department within the company using database queries and APIs. Specific inputs include employee performance data, skill sets, performance reviews, and 360-degree reviews. This data is stored as raw data on the server. The output is an unprocessed talent information dataset.

[1474] Step 2:

[1475] The server performs data preprocessing to complete missing values ​​in the collected human resources information and detect and correct outliers. Specifically, it completes missing values ​​using the KNN method and detects and corrects outliers using Z-scores. The input for this step is the raw human resources information dataset, and the output is the preprocessed human resources information dataset.

[1476] Step 3:

[1477] The server inputs the preprocessed personnel information data into a generative AI model (such as K-means clustering) to analyze the characteristics of successful personnel. Specifically, it performs clustering taking into account employee skills, performance, and emotional information. The input is the preprocessed personnel information dataset, and the output is the clustering results that represent the characteristics of successful personnel.

[1478] Step 4:

[1479] The server generates an optimal personnel allocation plan based on the characteristics of the active personnel, using the clustering results. Specifically, it uses an algorithm to perform an allocation simulation while taking into account the characteristics of the employees. The input is the clustering results, and the output is the optimal personnel allocation plan.

[1480] Step 5:

[1481] The server notifies the generated optimal staffing plan to the user's (e.g., human resources officer or manager) device. Specifically, the plan is sent using an email service or an in-app notification system. The input is the optimal staffing plan, and the output is a notification to the user.

[1482] Step 6:

[1483] The server collects and cleans information about job applicants and generates interview questions. Specifically, it removes invalid data from the applicant's historical data and applies an algorithm to generate interview questions. The input is the applicant's raw data, and the output is the cleansed data and generated interview questions.

[1484] Step 7:

[1485] The server collects emotional information from store employees in real time and reflects this in the analysis of the characteristics of successful employees and in optimal staffing proposals. Specifically, it uses an emotion recognition engine to collect employee emotional data and incorporates it into a generative AI model. The input is the emotional information collected in real time, and the output is clustering results that reflect the emotional information and staffing proposals.

[1486] 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.

[1487] 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.

[1488] 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.

[1489] [Fourth embodiment]

[1490] FIG. 7 shows an example of the configuration of a data processing system 410 according to the fourth embodiment.

[1491] 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.

[1492] 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).

[1493] 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.

[1494] 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.

[1495] 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).

[1496] 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. 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.

[1497] 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.

[1498] 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.

[1499] 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.

[1500] 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.

[1501] 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.

[1502] 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."

[1503] The present invention is a system for optimizing personnel allocation, promotion, and recruitment in a company. This system collects personnel information from each department within the company, preprocesses the collected data, and analyzes it to achieve optimal personnel management. Below, we will describe in detail the embodiments for implementing the system of the present invention.

[1504] Data collection methods

[1505] server

[1506] Build a system to automatically collect personnel information from each department, including employee performance data, skill sheets, performance evaluations, and 360-degree reviews.

[1507] Set up a system to periodically retrieve information using APIs or database queries.

[1508] Specific examples

[1509] The server collects sales results from the sales department, campaign performance evaluations from the marketing department, and technical evaluations from the technical department.

[1510] Data preprocessing methods

[1511] server

[1512] Implement algorithms to impute missing values ​​and detect and correct outliers in the collected data, thereby ensuring data quality.

[1513] Specific examples

[1514] The server imputes missing values ​​using the KNN method and detects and corrects outliers using Z-scores.

[1515] Analysis of the characteristics of successful personnel

[1516] server

[1517] The pre-processed data is then fed into an AI model (such as clustering or regression analysis) to extract the characteristics of successful employees, thereby identifying patterns of employees who will be successful in a particular role or department.

[1518] Specific examples

[1519] The server uses a clustering algorithm (K-means) to analyze the patterns of successful sales personnel. As a result, it finds that those with "high communication skills," "initiative," and "excellent problem-solving abilities" are more likely to succeed.

[1520] Form of generating optimal staffing plan

[1521] server

[1522] Implement an algorithm that generates optimal placement plans for existing employees based on the characteristics of successful employees, taking into account the employee's skill set, desired placement, and performance.

[1523] Specific examples

[1524] The server generates a proposal to place technical employee X as a leader of a new project based on his skill set and past performance.

[1525] Form of definition of promotion requirements

[1526] server

[1527] Define promotion requirements based on the characteristics of your top performers. These requirements are based on specific competencies, skill sets, and past performance.

[1528] Specific examples

[1529] Server defines the promotion requirements for managers as "strong leadership," "experience in supervising subordinates," and "project management skills."

[1530] Cleansing applicant information and generating interview questions

[1531] server

[1532] We will build a system that collects and cleans information on job applicants and automatically generates questions to be used in interviews.

[1533] Specific examples

[1534] The server extracts career data from applicant Y's resume, removes duplicate and inconsistent data, and then generates interview questions such as "What was the most difficult problem you solved in your previous job?" and "What kind of leadership experience do you have?"

[1535] Notifications and User Interface Forms

[1536] server

[1537] Implement a system to notify users of generated placement proposals, promotion requirements, and interview questions, allowing them to make data-driven decisions.

[1538] User

[1539] The user will then make optimal personnel allocation, promotion, and recruitment decisions based on the information provided. The system aims to have an interface that allows users to operate it efficiently and effectively.

[1540] Specific examples

[1541] Human resources personnel log in to the system to check the optimal personnel placement plans for new departments, and also use it to set promotion requirements and interview job applicants.

[1542] The system of the present invention performs data collection, preprocessing, analysis, and notification in an integrated manner, thereby enhancing a company's human resource management, reducing employee turnover and improving productivity.

[1543] The processing flow will be explained below.

[1544] Program processing steps

[1545] Step 1:

[1546] server

[1547] Collect human resource information from each department, including performance data, skill sheets, performance reviews, and 360-degree evaluations, using APIs and database queries.

[1548] Specific actions

[1549] 1. Send a request to an API endpoint to retrieve data from each department's system.

[1550] 2. Run an SQL query to extract historical performance data from the database.

[1551] Step 2:

[1552] server

[1553] Preprocessing of collected data is performed, specifically, missing values ​​are complemented and outliers are detected and corrected.

[1554] Specific actions

[1555] 1. Run the missing value imputation algorithm (KNN method) to estimate and impute missing data.

[1556] 2. An outlier detection algorithm (Z-score) is used to correct abnormal data points.

[1557] Step 3:

[1558] server

[1559] The preprocessed data is used to analyze the characteristics of successful employees, specifically through clustering and regression analysis.

[1560] Specific actions

[1561] 1. Run a clustering algorithm (K-means) to classify the personnel into multiple groups.

[1562] 2. Use regression analysis to assess the contribution of specific skills and achievements to success.

[1563] Step 4:

[1564] server

[1565] Generate optimal employee placement recommendations based on the characteristics of top performers, taking into account employee skill sets, performance, and individual placement preferences.

[1566] Specific actions

[1567] 1. Use the Thriving Talent Model to map each employee's skill set to the job needs.

[1568] 2. Use a selection algorithm to suggest the best department and role.

[1569] Step 5:

[1570] server

[1571] Define promotion requirements, including specific competencies, skill sets, and past performance.

[1572] Specific actions

[1573] 1. Use a decision tree algorithm to define the requirements for promotion.

[1574] 2. Save the defined requirements in the database and notify the person in charge.

[1575] Step 6:

[1576] server

[1577] Cleanse job applicant data and generate interview questions.

[1578] Specific actions

[1579] 1. Run data cleansing algorithms to remove inconsistencies and duplicate data.

[1580] 2. Uses Natural Language Processing (NLP) technology to generate appropriate interview questions from applicants' resumes.

[1581] Step 7:

[1582] server

[1583] The generated placement proposals, promotion requirements, and interview questions are notified to the user.

[1584] User

[1585] Based on the information provided, specific decisions regarding personnel placement, promotion, and hiring are made.

[1586] Specific actions

[1587] 1. Generates a notification containing the analysis results and displays it on the user's dashboard.

[1588] 2. The user logs into the system to review and use the suggestions.

[1589] In this way, this system enhances a company's human resource management through a series of steps, including data collection, analysis of the characteristics of successful personnel, generation of optimal placement plans, definition of promotion requirements, and processing related to job applicants.

[1590] Example 1

[1591] 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."

[1592] Conventional human resource management systems have the problem that it is difficult to efficiently grasp the skills and performance of individual employees, cooperation between departments, and the appropriateness of promotions and placements, making it difficult to contribute to improving productivity and turnover rates across the company.In addition, collecting information on job applicants and preparing for interviews requires a great deal of effort and time, so there was a need for efficiency improvements.

[1593] 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.

[1594] In this invention, the server includes: means for collecting human resource information from each department and organization; means for completing missing values ​​in the collected human resource information and detecting and correcting outliers; means for analyzing the characteristics of active personnel using a generative AI model based on the preprocessed human resource information; means for generating an optimal human resource placement plan based on the characteristics of active personnel; means for notifying a user of the generated placement plan; means for cleansing job applicant data and generating interview questions; means for generating an optimal human resource placement plan taking into account employee skill sets, desired placements, and performance; and means for notifying a user of the generated interview questions and supporting job applicant interviews. This improves the efficiency of human resource management across the company, realizes appropriate human resource placement and promotion, and simplifies job applicant interview preparation, thereby improving corporate productivity and reducing employee turnover.

[1595] "Human resource information" refers to information including the performance, skills, work evaluations, and 360-degree evaluations of employees working in each department and organization of a company.

[1596] "Missing values" are values ​​that are missing in a dataset and are a factor that impairs the accuracy of data analysis.

[1597] An "outlier" is a value in a dataset that is significantly different from other data and may affect the results of data analysis.

[1598] A "generative AI model" is an algorithm that uses artificial intelligence to extract and analyze specific patterns and features from data.

[1599] "Characteristics of successful employees" refer to the skills and characteristics common to employees who achieve outstanding results in specific roles or departments within a company.

[1600] A "staffing proposal" is a plan that proposes the optimal staffing arrangement within a company, and is generated based on employees' skill sets, performance, desired placement, etc.

[1601] "Notification" is the act of informing the user of important information such as the generated personnel allocation plan and interview questions.

[1602] "Cleansing" is the process of detecting, deleting, or correcting duplicates and inconsistencies in data collected from a database.

[1603] "Interview questions" are questions used during interviews with job applicants or employees, and are used to evaluate the applicant's abilities and experience.

[1604] A "skill set" is the collection of skills and abilities that a particular employee possesses.

[1605] "Desired placement" refers to the department or role that an employee desires.

[1606] "Performance" refers to an employee's past achievements and evaluations in performing their duties.

[1607] The above definitions allow each element of the system to be clearly understood.

[1608] The present invention is a system for optimizing personnel allocation, promotion, and recruitment in a company. This system collects personnel information from each department within the company, preprocesses the collected data, and analyzes it to achieve optimal personnel management. Below, we will describe in detail the embodiments for implementing the system of the present invention.

[1609] Data collection methods

[1610] server

[1611] The server automatically collects personnel information such as employee performance data, skill sheets, work evaluations, and 360-degree evaluations from each department of the company. This information is periodically retrieved using APIs and database queries. Specifically, it collects sales performance from the sales department, campaign success evaluations from the marketing department, and technical evaluations from the technical department.

[1612] Data preprocessing methods

[1613] server

[1614] The server runs algorithms to impute missing values ​​in the collected data and to detect and correct outliers, for example, imputing missing values ​​using the KNN (k-Nearest Neighbors) method and detecting outliers using Z-scores.

[1615] Analysis of the characteristics of successful personnel

[1616] server

[1617] The server inputs the preprocessed data into a generative AI model (such as clustering or regression analysis) to extract the characteristics of successful employees. Specifically, the K-means clustering algorithm can be used to analyze successful employees in the sales department. The results show that those with "high communication skills," "proactive action," and "excellent problem-solving abilities" are more likely to succeed.

[1618] Form of generating optimal staffing plan

[1619] server

[1620] The server generates optimal personnel placement proposals based on the characteristics of active personnel, taking into account the employee's skill set, desired placement, and performance. For example, it generates a proposal to place employee X in the technical department as a leader of a new project based on his skill set and past performance.

[1621] Form of definition of promotion requirements

[1622] server

[1623] The server defines promotion requirements based on the characteristics of successful employees. These requirements are set based on specific abilities, skill sets, and past performance. For example, the server defines "high leadership," "experience in mentoring subordinates," and "project management ability" as promotion requirements for managerial positions.

[1624] Cleansing applicant information and generating interview questions

[1625] server

[1626] The server collects and cleans information on job applicants and automatically generates interview questions. Specifically, it extracts resume data for applicant Y, deletes inconsistent and duplicate data, and then generates interview questions such as "What was the most difficult problem you solved in your previous job?" and "What kind of leadership experience do you have?"

[1627] Notifications and User Interface Forms

[1628] server

[1629] The server implements a system that notifies the user of the generated placement proposals, promotion requirements, and interview questions, allowing the user to make data-based decisions.

[1630] User

[1631] Based on the information provided, users can make optimal personnel placements, promotions, and hiring decisions. The system provides an interface that users can use efficiently and effectively. Specifically, human resources personnel can log in to the system, check the optimal personnel placement proposals for new departments, and use the results to set promotion requirements and interview job applicants.

[1632] Prompt Sentence Examples

[1633] "Analyze patterns of successful talent using sales performance and campaign success evaluation data."

[1634] "Generate a placement plan to select the best person to lead a new project in the technology department."

[1635] "Extract applicant biographical data and generate interview questions."

[1636] This system will enhance a company's human resource management by consistently collecting, preprocessing, analyzing, and notifying data, thereby reducing employee turnover and improving productivity.

[1637] The flow of the identification process in the first embodiment will be described with reference to FIG.

[1638] Step 1:

[1639] Data collection

[1640] The server has a means of collecting human resource information from each department and organization. In this case, the input is information such as employee performance data, skill sheets, work evaluations, and 360-degree evaluations stored in each department's database. The server periodically obtains the necessary information using API requests and database queries. The server then stores the obtained data in storage. For example, the server might collect sales performance from the sales department, campaign success evaluations from the marketing department, and technical evaluations from the technical department.

[1641] Step 2:

[1642] Data Preprocessing

[1643] The server preprocesses the collected data. The input is the raw data collected in step 1. Specifically, the server first detects missing values ​​in the data and imputes them using the KNN (k-Nearest Neighbors) method. Next, it calculates Z-scores to detect outliers. If an outlier is found, the server corrects or removes it. The final output is clean data with missing and outlier values ​​corrected.

[1644] Step 3:

[1645] Analysis of the characteristics of successful personnel

[1646] The server inputs the clean data into the generative AI model and analyzes the characteristics of successful employees. The input is the data preprocessed in step 2. Specifically, the server runs the K-means clustering algorithm. It analyzes the clustering results and identifies the characteristics of each cluster. These characteristics include "good communication skills," "proactive action," and "excellent problem-solving ability." The output is a list of the characteristics of successful employees.

[1647] Step 4:

[1648] Generate optimal staffing plans

[1649] The server generates a personnel placement plan based on the characteristics of the active personnel. The inputs are the characteristics of the active personnel obtained in step 3, the employee's skill set, desired placement, and performance data. Specifically, the server compares each employee's data with the characteristics of the active personnel to generate an optimal placement plan. For example, the server references the skill set and past performance of employee X in the technical department and generates a plan to place him as the leader of a new project. The output is an optimal personnel placement plan.

[1650] Step 5:

[1651] Define promotion requirements

[1652] The server defines promotion requirements based on the characteristics of successful employees. The input is the list of characteristics obtained in step 3. Specifically, the server extracts the abilities, skill sets, and experience required for a specific position from the characteristics of successful employees. For example, it defines "high leadership," "experience in supervising subordinates," and "project management ability" as promotion requirements for managerial positions. The output is a list of described promotion requirements.

[1653] Step 6:

[1654] Cleansing applicant information and generating interview questions

[1655] The server cleanses the information of job applicants and generates interview questions. The input is the resume data of job applicants. Specifically, the server analyzes the resume data and removes or corrects duplicate and inconsistent data. Next, based on the cleansed data, it generates questions to be used in interviews. For example, it generates questions such as "What was the most difficult problem you solved in your previous job?" and "What kind of leadership experience do you have?" The output is the cleansed applicant information and the generated interview questions.

[1656] Step 7:

[1657] Notifications and User Interface

[1658] The server notifies the user of the generated placement plans, promotion requirements, and interview questions. The input is the output of steps 4, 5, and 6. Specifically, the server presents the generated results to the user in the form of a dashboard or email notification. The user then uses the notified information to make optimal personnel placements, promotions, and recruitment. For example, a human resources officer logs into the system, checks the optimal personnel placement plans for a new department, and uses this information to set promotion requirements and interview job applicants. The output is a notification to the user and an interface that the user can use.

[1659] (Application example 1)

[1660] 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."

[1661] In conventional factories, managing robot operating status and maintenance schedules required individual data management and manual adjustments, making it difficult to achieve optimal operating efficiency and maintenance plans. Furthermore, the collection and analysis of human resource information required a great deal of effort, preventing optimal personnel placement and promotion. There is a need to improve this situation and increase the efficiency and productivity of factories and organizations as a whole.

[1662] 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.

[1663] In this invention, the server includes: means for collecting human resource information from each department and organization; means for completing missing values ​​in the collected human resource information and detecting and correcting outliers; means for analyzing the characteristics of active human resources using a generation AI based on the preprocessed human resource information; means for generating an optimal human resource deployment plan based on the characteristics of active human resources; means for notifying a user of the generated deployment plan; means for collecting operation information, work efficiency, and maintenance history; means for preprocessing the collected operation information and detecting and correcting outliers; means for generating an optimal robot deployment plan and maintenance schedule using a generation AI based on the preprocessed operation information; means for cleansing job applicant data and generating interview questions; and means for providing a user interface for confirming the optimal deployment and schedule based on the notified information. This enables optimization of the operating efficiency of robots in factories, formulation of preventative maintenance schedules, and appropriate human resource deployment and promotion.

[1664] "Each department or organization" refers to different divisions, teams, or functional groups within a company or factory.

[1665] "Human resources information" refers to relevant data about employees and job seekers, such as performance, skills, evaluations, and work history.

[1666] "Means of collection" refers to the systems and methods for obtaining the necessary information through various databases and APIs.

[1667] "Missing value imputation" refers to the process of estimating and filling in missing values ​​in a dataset.

[1668] "Outlier detection and correction" refers to the process of finding values ​​in a data set that are outside of the normal range and changing them to appropriate values.

[1669] "Preprocessed human resources information" refers to clean data that has been collected and has undergone missing value imputation and outlier correction.

[1670] "Generative AI" refers to artificial intelligence algorithms used to rapidly analyze large amounts of data and extract specific patterns and features.

[1671] "High-performing talent" refers to employees who perform well in specific conditions or roles.

[1672] "Means for analyzing features" means methods that use data analytics and machine learning algorithms to extract trends and patterns from data.

[1673] "Optimal human resource allocation plan" refers to the assignment of departments and projects that allow employees to work most effectively.

[1674] "Means for notifying the user" refers to an interface or method for notifying the user of generated information or results.

[1675] "Operational information" refers to data on how robots and systems are actually operating.

[1676] "Work efficiency" refers to the ratio of productive output to effort put in.

[1677] "Maintenance history" means a record of the maintenance that a device or system has undergone.

[1678] An "allocation plan" refers to a plan for how to allocate equipment and personnel to operating departments or specific projects.

[1679] A "maintenance schedule" refers to a schedule for systematically carrying out maintenance work on equipment and systems.

[1680] "Job applicants" refers to individuals who have applied for a new position.

[1681] "Data cleansing" refers to the process of removing unnecessary information from raw data and preparing it for analysis.

[1682] "Interview questions" refer to questions used in interviews.

[1683] "User interface" refers to the screens and operating methods that allow users to directly interact with a system.

[1684] This invention is a system that collects and analyzes data on the operational status, work efficiency, and maintenance history of robots in factories, and generates optimal robot placement and maintenance schedules. This system performs all processes, from collecting data on operational information, work efficiency, and maintenance history to notifying users of the placement plans and schedules it generates.

[1685] Data collection

[1686] The server has a means to automatically collect operational information, work efficiency, and maintenance history from each robot operating in the factory. This collection process is carried out through sensors installed on each robot and API, and the data is sent to the server.

[1687] Examples:

[1688] The server collects operating hours, number of completed tasks, and recent maintenance history from each robot in the factory via an API.

[1689] Data Preprocessing

[1690] The server implements algorithms to fill in missing values ​​in the collected data and detect and correct outliers, a process that ensures data quality and enables accurate analysis.

[1691] Examples:

[1692] Missing values ​​in the dataset collected by the server are imputed using the KNN method, and outliers are detected and corrected using Z scores.

[1693] Generation of optimal robot placement plans and maintenance schedules

[1694] Based on the pre-processed data, generative AI models (such as clustering and regression analysis) are used to generate optimal robot placement plans and maintenance schedules. The results suggest the most efficient use of robots in factory operations.

[1695] Examples:

[1696] The server uses a clustering algorithm (K-means) to analyze the operating patterns of each robot and identify robots with "high operating time," "efficient task completion," and "low maintenance frequency."

[1697] Notification of placement plan and schedule

[1698] The generated optimal deployment plan and maintenance schedule are notified to the user. The server is responsible for this notification process, and the information is displayed and shared through the user interface.

[1699] Examples:

[1700] The server notifies the user of the generated deployment plan and maintenance schedule via email or a dedicated dashboard.

[1701] Based on the information provided, users can plan optimal robot placement and maintenance, improving productivity and efficiency within their factories.

[1702] Example prompt sentence:

[1703] Input the operation data and maintenance history data of the robots in the factory, analyze the characteristics of the active robots, and generate optimal placement plans and maintenance schedules.

[1704] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[1705] Step 1:

[1706] The server collects operational information, work efficiency, and maintenance history from the robots operating in the factory via API. The input is data from each robot's sensors and internal systems, which is obtained via API. The output is a raw dataset that we use for preprocessing. This dataset includes each robot's operating time, number of completed tasks, and maintenance history.

[1707] Step 2:

[1708] The server performs preprocessing of the collected data. First, it performs missing value imputation. It uses KNN imputation to estimate and fill missing values ​​in the dataset. Next, it performs outlier detection and correction. It uses Z-score to detect data points that fall outside the normal range and corrects them. This ensures the quality of the data. The input is the original dataset collected in step 1, and the output is clean data with missing and outlier values ​​corrected.

[1709] Step 3:

[1710] The server inputs the preprocessed data into the generative AI model to analyze the robot's operating patterns. A clustering algorithm (e.g., K-means) is used for this analysis. The input is the clean data generated in step 2, and the output is the robot patterns classified by cluster. Specifically, the feature values ​​of each robot (operating time, work efficiency, etc.) are input into the algorithm to perform clustering.

[1711] Step 4:

[1712] The server uses the generative AI model to generate optimal robot placement plans and maintenance schedules. The input is the data classified by cluster in Step 3. Based on the data, it formulates placement plans for robots with high operating efficiency and a corresponding preventive maintenance schedule. The output is the optimal placement plan and maintenance schedule. Specifically, based on the characteristics of each cluster, it determines which robots should be placed in which areas and when maintenance is required.

[1713] Step 5:

[1714] The server notifies the user of the generated deployment plan and maintenance schedule. Notifications are made via email or a dedicated dashboard. The input is the deployment plan and maintenance schedule generated in step 4, and the output is the information displayed on the user's operation screen. Specifically, the generated information is converted into an appropriate format and displayed through the user interface.

[1715] Step 6:

[1716] The user checks the notified deployment plan and maintenance schedule and puts them into action. The input is the information displayed in step 5. The user makes the necessary adjustments based on the optimal deployment plan and schedule to optimize the operation of the robots. The output is the adjusted operation plan and maintenance schedule. In concrete terms, the user deploys each robot and performs maintenance work on-site based on the notified content.

[1717] 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.

[1718] The present invention achieves more effective human resource management than ever before by combining a system for optimizing personnel allocation, promotion, and recruitment in a company with a new emotion engine that recognizes user emotions. Below, a detailed description is given of an embodiment of the system of the present invention.

[1719] Data collection methods

[1720] server

[1721] Build a system to automatically collect personnel information from each department, including employee performance data, skill sheets, performance evaluations, and 360-degree reviews.

[1722] Set up a system to periodically retrieve information using APIs or database queries.

[1723] Specific examples

[1724] The server collects sales results from the sales department, campaign performance evaluations from the marketing department, and technical evaluations from the technical department.

[1725] Data preprocessing methods

[1726] server

[1727] Implement algorithms to impute missing values ​​and detect and correct outliers in the collected data, thereby ensuring data quality.

[1728] Specific examples

[1729] The server imputes missing values ​​using the KNN method and detects and corrects outliers using Z-scores.

[1730] Analysis of the characteristics of successful personnel

[1731] server

[1732] The pre-processed data is then fed into an AI model (such as clustering or regression analysis) to extract the characteristics of successful employees, thereby identifying patterns of employees who will be successful in a particular role or department.

[1733] Specific examples

[1734] The server uses a clustering algorithm (K-means) to analyze the patterns of successful sales personnel. As a result, it finds that those with "high communication skills," "initiative," and "excellent problem-solving abilities" are more likely to succeed.

[1735] Form of generating optimal staffing plan

[1736] server

[1737] We will implement an algorithm that generates optimal employee placement plans based on the characteristics of successful employees, taking into account the employee's skill set, desired placement, performance, and even user sentiment.

[1738] Specific examples

[1739] The server generates a proposal to appoint Employee X in the technical department as a leader of a new project based on his skill set and past performance. It also analyzes Employee X's emotional information using an emotion engine to confirm that his stress level is low.

[1740] Form of definition of promotion requirements

[1741] server

[1742] Define promotion requirements based on the characteristics of your top performers. These requirements are based on specific competencies, skill sets, and past performance, as well as emotional information provided by the emotion engine.

[1743] Specific examples

[1744] Sarver defines the promotion requirements for managers as "high leadership," "experience in supervising subordinates," and "project management skills," and adds "stable emotional control ability."

[1745] Cleansing applicant information and generating interview questions

[1746] server

[1747] We will build a system that collects and cleans information on job applicants and automatically generates questions to be used in interviews. Furthermore, we will obtain the user's emotional information in real time during the interview and provide adaptive questions.

[1748] Specific examples

[1749] The server extracts career data from applicant Y's resume, removes duplicate and inconsistent data, and then generates questions to be used in the interview, such as "What was the most difficult problem you solved in your previous job?" and "What kind of leadership experience do you have?" During the interview, the emotion engine recognizes the emotions of the users (interviewer and applicant), and if they are feeling stressed, it inserts questions to help them relax.

[1750] Notifications and User Interface Forms

[1751] server

[1752] Implement a system to notify users of generated placement proposals, promotion requirements, and interview questions, allowing them to make data-driven decisions.

[1753] User

[1754] The user will then make optimal personnel allocation, promotion, and recruitment decisions based on the information provided. The system aims to have an interface that allows users to operate it efficiently and effectively.

[1755] Specific examples

[1756] Human resources personnel log in to the system and check the optimal personnel placement plan for new departments, and also use it to set promotion requirements and interview job applicants. They also consider the emotional data provided by the emotion engine to make optimal decisions.

[1757] The system of the present invention performs data collection, preprocessing, analysis, emotion recognition, and notification in an integrated manner, thereby enhancing a company's human resource management, reducing employee turnover and improving productivity.

[1758] The processing flow will be explained below.

[1759] Program processing steps

[1760] Step 1:

[1761] server

[1762] Collect human resource information from each department, including performance data, skill sheets, performance reviews, and 360-degree evaluations, using APIs and database queries.

[1763] Specific actions

[1764] 1. Send requests to API endpoints to retrieve data from each department's system.

[1765] 2. Run an SQL query to extract historical performance data from the database.

[1766] Step 2:

[1767] server

[1768] Preprocessing of collected data is performed, specifically, missing values ​​are complemented and outliers are detected and corrected.

[1769] Specific actions

[1770] 1. Run the missing value imputation algorithm (KNN method) to estimate and impute missing data.

[1771] 2. Correct anomalous data points using an outlier detection algorithm (Z-score).

[1772] Step 3:

[1773] server

[1774] The preprocessed data is used to analyze the characteristics of successful employees, specifically through clustering and regression analysis.

[1775] Specific actions

[1776] 1. Run a clustering algorithm (K-means) to classify the personnel into multiple groups.

[1777] 2. Use regression analysis to assess the contribution of specific skills and achievements to success.

[1778] Step 4:

[1779] server

[1780] Generate optimal employee placement plans based on the characteristics of top performers, taking into account employee skill sets, desired placements, performance, and even user sentiment.

[1781] Specific actions

[1782] 1. Use a talent model to map each employee's skill set to the needs of the job.

[1783] 2. Use a selection algorithm to suggest the best departments and roles.

[1784] 3. Analyze emotional data from the emotion engine and adjust placement recommendations based on the employee's current emotional state.

[1785] Step 5:

[1786] server

[1787] Define promotion requirements based on specific competencies, skill sets, and past performance, as well as emotional information provided by the emotion engine.

[1788] Specific actions

[1789] 1. Use a decision tree algorithm to define the requirements for promotion.

[1790] 2. Adjust the defined requirements taking into account the data from the emotion engine.

[1791] 3. Save the defined promotion requirements in the database and notify the person in charge.

[1792] Step 6:

[1793] server

[1794] The system cleanses job applicant data and generates interview questions. It also analyzes the user's emotional information during the interview in real time and provides adaptive questions.

[1795] Specific actions

[1796] 1. Run a data cleansing algorithm to remove inconsistencies and duplicate data.

[1797] 2. Use Natural Language Processing (NLP) technology to generate appropriate interview questions from applicants' resumes.

[1798] 3. During the interview, the emotion engine analyzes the emotions of the user (interviewer and applicant) and generates and inserts questions to relax them if they are feeling stressed.

[1799] Step 7:

[1800] server

[1801] The generated placement proposals, promotion requirements, and interview questions are notified to the user.

[1802] Specific actions

[1803] 1. Generate a notification containing the analysis results and display it on the user's dashboard.

[1804] 2. The user logs in to the system and checks and uses the suggestions.

[1805] Step 8:

[1806] User

[1807] Make specific staffing, promotion, and hiring decisions based on the information provided.

[1808] Specific actions

[1809] 1. A user logs in to the system and checks the optimal staffing plan for a new department.

[1810] 2. Using emotional data to determine promotion requirements and interview job applicants.

[1811] This system will enhance a company's human resource management by collecting data, analyzing the characteristics of successful personnel, generating optimal placement plans, defining promotion requirements, screening applicants, generating interview questions, and recognizing emotions, thereby reducing employee turnover and improving productivity.

[1812] Example 2

[1813] 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."

[1814] Traditional human resource management systems primarily analyze employees' performance and skills, making it difficult to optimize placement and promotion. Furthermore, because they do not take emotional information into account, they are unable to properly manage employee stress and motivation. Furthermore, because they are unable to generate appropriate questions based on real-time emotional analysis during interviews, the quality of interviews can decline.

[1815] The identification processing by the identification processing unit 290 of the data processing device 12 in Example 2 is realized by the following means. In this invention, the server includes: means for automatically collecting personnel information from each department and organization; means for complementing missing values ​​in the collected personnel information and detecting and correcting outliers; means for analyzing the characteristics of active personnel using a generative AI model based on the preprocessed personnel information; means for generating an optimal personnel allocation plan based on the characteristics of active personnel, taking into account employee skill sets, desired allocations, performance, and emotional information; means for notifying the user of the generated personnel allocation plan, promotion requirements, and interview questions; means for cleansing job applicant data and generating interview questions; and means for acquiring the user's emotional information during interviews in real time and providing adapted questions. This enables optimal personnel allocation and promotion based on data and effective personnel management that takes into account employees' emotional information. Furthermore, real-time emotional analysis during interviews can improve the quality of interviews.

[1816] "Each department or organization" refers to different divisions or organizational units within a company, each with its own unique tasks and roles.

[1817] "Human resource information" refers to detailed data about employees, such as performance data, skill sheets, work evaluations, and 360-degree evaluations.

[1818] "Missing value imputation" refers to the use of estimations or algorithms to fill in missing values ​​in collected data.

[1819] "Detecting and correcting outliers" refers to identifying values ​​in data that fall outside the normal range and correcting or eliminating them.

[1820] "Preprocessed human resources information" refers to human resources information that has been preprocessed to improve data quality, such as by completing missing values ​​and correcting outliers.

[1821] A "generative AI model" refers to a model designed to learn patterns and features from data using artificial intelligence techniques.

[1822] "Characteristics of successful employees" refers to the common traits and skills that employees who succeed in a particular role or department have in common.

[1823] A "skill set" refers to the collection of expertise and abilities that an employee possesses.

[1824] "Desired placement" refers to the job or placement that an employee desires.

[1825] "Performance" refers to an employee's past work performance and achievements.

[1826] "Emotional information" refers to data that indicates an employee's emotional state, and primarily refers to information related to stress levels and motivation.

[1827] "Optimal staffing proposal" refers to the most appropriate staffing proposal, taking into account employees' skill sets, desired placements, performance, and emotional information.

[1828] "Promotion requirements" refer to the skills, experience, abilities, and other conditions that an employee must meet in order to be promoted.

[1829] "Interview questions" refer to questions asked to job applicants during an interview.

[1830] "Job applicant data" refers to detailed information such as resumes and job histories provided by job seekers.

[1831] "Cleansing" refers to the process of correcting data duplication and inconsistencies to create an accurate and consistent data set.

[1832] "Real-time acquisition" refers to acquiring data at the moment it is processed.

[1833] "Providing adaptive questions" refers to the actual use of questions generated according to the situation during the interview.

[1834] The present invention is a system for optimizing personnel allocation, promotion, and recruitment in a company, and by combining it with a new emotion engine that recognizes the user's emotions, it achieves more effective personnel management than ever before. Below, a detailed description is given of an embodiment of the system of the present invention.

[1835] Data collection methods

[1836] server

[1837] The server automatically collects human resource information from each department, including employee performance data, skill sheets, performance reviews, 360-degree evaluations, etc. It periodically retrieves information using APIs and database queries.

[1838] Specific examples

[1839] The server collects sales results from the sales department, campaign performance evaluations from the marketing department, and technical evaluations from the technical department. For example, you can set a timer to collect data at 6:00 PM every day.

[1840] Data preprocessing methods

[1841] server

[1842] The server implements algorithms to impute missing values ​​and detect and correct outliers in the collected data, thereby ensuring data quality.

[1843] Specific examples

[1844] The server imputes missing values ​​using the KNN method and detects and corrects outliers using Z-scores, e.g., absent data are estimated from neighboring data points and anomalous values ​​are corrected using statistical methods.

[1845] Analysis of the characteristics of successful personnel

[1846] server

[1847] The server then inputs the pre-processed data into a generative AI model (e.g., clustering or regression analysis) to extract the characteristics of successful employees, thereby identifying patterns of employees who will be successful in a particular role or department.

[1848] Specific examples

[1849] The server uses a clustering algorithm (K-means) to analyze the patterns of successful sales personnel. For example, it can identify that those with "high communication skills," "initiative," and "excellent problem-solving abilities" are more likely to succeed.

[1850] Form of generating optimal staffing plan

[1851] server

[1852] The server implements an algorithm that generates optimal placement plans based on the characteristics of successful employees, taking into account the employee's skill set, desired placement, performance, and even the user's emotional information.

[1853] Specific examples

[1854] The server generates a proposal to assign Employee X in the technical department as a leader of a new project based on his skill set and past performance. It also analyzes Employee X's emotional information using an emotion engine to confirm that his stress level is low.

[1855] Form of definition of promotion requirements

[1856] server

[1857] The server defines promotion requirements based on the characteristics of the top performers. These requirements are based on specific competencies, skill sets, and past performance, as well as emotional information provided by the emotion engine.

[1858] Specific examples

[1859] Sarver defines the promotion requirements for managers as "high leadership," "experience in supervising subordinates," and "project management skills," and adds "stable emotional control ability."

[1860] Cleansing applicant information and generating interview questions

[1861] server

[1862] The server collects and cleans information on job applicants, and builds a system that automatically generates questions to be used in interviews. It also obtains the user's emotional information in real time during the interview and provides adaptive questions.

[1863] Specific examples

[1864] The server extracts career data from applicant Y's resume, removes duplicate and inconsistent data, and then generates questions to be used in the interview, such as "What was the most difficult problem you solved in your previous job?" and "What kind of leadership experience do you have?" During the interview, the emotion engine recognizes the emotions of the users (interviewer and applicant), and if they are feeling stressed, it inserts questions to help them relax.

[1865] Notifications and User Interface Forms

[1866] server

[1867] The server implements a system that notifies the user of the generated placement proposals, promotion requirements, and interview questions.

[1868] User

[1869] The user can then use the information provided to make optimal personnel placements, promotions, and recruitment. The system provides an interface that allows users to operate the system efficiently and effectively.

[1870] Specific examples

[1871] Human resources personnel log in to the system and check the optimal personnel placement plan for new departments, and also use it to set promotion requirements and interview job applicants. They also consider the emotional data provided by the emotion engine to make optimal decisions.

[1872] Prompt Sentence Examples

[1873] 1. "What are the characteristics of an ideal person for a technical project leader?"

[1874] 2. "Define the promotion requirements for your sales department and include the necessary skill sets and emotional information."

[1875] The system of the present invention is a system that enhances a company's human resource management by consistently performing data collection, preprocessing, analysis, emotion recognition, and notification, thereby reducing employee turnover and improving productivity.

[1876] The flow of the identification process in the second embodiment will be described with reference to FIG.

[1877] Step 1: Data collection

[1878] server

[1879] Input: Human resource information from each department (performance data, skill sheets, work evaluations, 360-degree evaluations, etc.)

[1880] Processing: Use APIs and database queries to periodically collect personnel information from each department. For example, set a timer to retrieve data at 6:00 PM every day.

[1881] Output: Raw data collected

[1882] Specific operation: The server connects to the database and periodically retrieves data such as the sales performance of the sales department, the campaign results of the marketing department, and the technical evaluation of the technical department.

[1883] Step 2: Data Preprocessing

[1884] server

[1885] Input: Raw data collected

[1886] Processing: Apply missing value imputation and outlier detection / correction algorithms, e.g., KNN imputation and Z-score outlier detection / correction.

[1887] Output: Quality-assured pre-processed data

[1888] Specific operation: The server estimates missing data points using the KNN method and corrects abnormal data points using statistical methods.

[1889] Step 3: Identifying the characteristics of successful employees

[1890] server

[1891] Input: Preprocessed data

[1892] Processing: Use generative AI models (e.g., clustering and regression analysis) to extract traits of top performers. Run a clustering algorithm (e.g., K-means) to analyze patterns.

[1893] Output: List of characteristics of successful employees

[1894] How it works: The server inputs the preprocessed data into the K-means clustering algorithm to identify features such as "good communication skills," "proactive behavior," and "excellent problem-solving ability."

[1895] Step 4: Generate optimal staffing plans

[1896] server

[1897] Input: List of characteristics of successful personnel, employee skill set, desired placement, performance, emotional information

[1898] Processing: Based on the generated features, the optimal placement plan is generated using a personnel placement algorithm. Data from the emotion engine is taken in to consider the optimal placement.

[1899] Output: Optimal staffing plan

[1900] Specific operation: The server confirms that the stress level of technical department employee X is low, and then generates a proposal to place him as the leader of a new project, taking into account his skill set and achievements.

[1901] Step 5: Define promotion requirements

[1902] server

[1903] Input: List of characteristics of successful personnel, emotional information

[1904] Processing: Using a generative AI model to define promotion requirements for specific roles, such as managerial positions, including specific competencies, skill sets, and even emotional control skills.

[1905] Output: Promotion requirements list

[1906] Specific operation: The server generates promotion requirements including "high leadership," "experience in supervising subordinates," "project management ability," and "stable emotional control ability."

[1907] Step 6: Cleanse applicant information and generate interview questions

[1908] server

[1909] Input: Raw data of job applicants (resume, curriculum vitae, etc.)

[1910] Processing: Data cleansing is performed, questions are automatically generated for use in interviews, and emotional information during the interview is acquired in real time to provide adaptive questions.

[1911] Output: Cleansed applicant data, interview question list

[1912] Specific operation: The server removes duplicate and inconsistent data and generates questions such as "What was the most difficult problem you solved in your previous job?" and "What kind of leadership experience do you have?" based on information extracted from the resume. During the interview, questions to put the candidate at ease are added based on emotional data obtained from the emotion engine.

[1913] Step 7: Notifications and User Interface

[1914] server

[1915] Input: Optimal personnel placement plan, promotion requirements list, interview questions list

[1916] Processing: Implement a system that notifies the user of the generated information. Design an interface that allows the user to check and manipulate the information.

[1917] Output: Information notified to the user

[1918] Specific operation: A human resources officer logs into the system, checks the staffing plan for a new project, the promotion requirements for managerial positions, and the interview questions for applicants, and makes a decision based on the information. Data from the emotion engine is also referenced to make a comprehensive judgment.

[1919] (Application example 2)

[1920] 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."

[1921] Conventional personnel allocation systems did not take into account emotional information in their personnel management, making it difficult to optimally allocate and promote employees based on their stress levels and emotional states. Real-time employee emotional recognition in physical stores and flexible personnel allocation based on this recognition are also needed. This will improve the performance of physical stores and customer satisfaction.

[1922] The identification processing by the identification processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means. In this invention, the server includes means for collecting human resource information from each department and organization, means for complementing missing values ​​in the collected human resource information and detecting and correcting outliers, means for analyzing the characteristics of active personnel using a generation AI based on the preprocessed human resource information, means for generating an optimal human resource allocation plan based on the characteristics of the active personnel, means for notifying the user of the generated human resource allocation plan, means for cleansing data on job applicants and generating interview questions, and means for collecting emotional information from employees at physical stores and reflecting the information in an analysis of the characteristics of active personnel and in an optimal human resource allocation plan. This makes it possible to generate optimal human resource allocation plans and promotion plans that reflect employee emotional information.

[1923] "Means for collecting human resources information from each department and organization" refers to a system that automatically obtains information such as employee skills, performance, and evaluations from different departments and organizations within the company.

[1924] "Means for completing missing values ​​in collected human resources information and detecting and correcting outliers" refers to algorithms and methods for completing missing information in collected data and finding and correcting outliers.

[1925] "Method of analyzing the characteristics of successful employees using generative AI based on preprocessed human resources information" refers to a method of using information that has undergone data preprocessing and generative AI to extract patterns and characteristics of employees who are likely to be successful.

[1926] "Means for generating optimal personnel placement plans based on the characteristics of successful personnel" is a system for determining the placement in which each employee can work most effectively, based on the characteristics of successful employees.

[1927] The "means for notifying the user of the generated personnel placement plan" is a method for notifying a company's personnel manager or a person in charge of human resources of the generated personnel placement plan.

[1928] "Method for cleansing job applicant data and generating interview questions" refers to a method for organizing and processing job applicant information, deleting unnecessary data, and automatically creating questions to be used in interviews.

[1929] "Means for collecting emotional information from employees in physical stores and reflecting it in an analysis of the characteristics of successful employees and in generating optimal personnel placement plans" refers to a method for collecting the emotional state of employees working in stores in real time and using that information to analyze the characteristics of successful employees and generate personnel placement plans.

[1930] To implement the present invention, it is necessary to build a system that performs the following steps in order: The following describes in detail the hardware, software, and processing procedures of the actual system.

[1931] System configuration

[1932] 1. Hardware

[1933] Server (general server or cloud infrastructure: AWS, Microsoft Azure, etc.)

[1934] User devices (PCs, tablets, smartphones, etc.)

[1935] 2. Software

[1936] Data processing and preprocessing: Python, Pandas

[1937] Outcome analysis and clustering: Scikit-Learn (StandardScaler, K-Means Clustering)

[1938] Emotion Recognition Engine

[1939] Notification system: Email service or in-app notifications

[1940] Data collection and preprocessing

[1941] The server automatically collects employee information from each department within the company using APIs and database queries, including employee performance data, skill sets, performance reviews, and 360-degree feedback.

[1942] Next, missing values ​​in the collected data are imputed and outliers are detected and corrected. For example, missing values ​​are imputed using the KNN method, and outliers are detected and corrected using Z-scores.

[1943] Analysis of the characteristics of successful personnel

[1944] The preprocessed data is then input into an AI model to extract the characteristics of successful employees. Specifically, the data is analyzed using a clustering algorithm (K-means). This allows us to understand the patterns of employees who are successful in specific roles or departments.

[1945] Creation and notification of staffing plans

[1946] We implement an algorithm that generates optimal staffing plans based on the characteristics of successful employees. This algorithm takes into account employees' skill sets, desired placements, performance, and even emotional information obtained from an emotion recognition engine. The generated placement plans are then notified to users via email services or an in-app notification system.

[1947] Generating interview questions

[1948] The system uses an emotion recognition engine to collect and cleanse information from job applicants, obtain real-time emotional information during interviews, and generate appropriate questions based on that information.

[1949] Specific Examples

[1950] For example, in a physical store, the performance data and emotional information of employees A, B, and C are collected and analyzed, and it is discovered that employee A has excellent leadership skills and can make calm decisions even under pressure. Based on this information, a proposal is made to assign employee A as the leader of a new project. This proposal is notified to the store manager's terminal.

[1951] Prompt Sentence Examples

[1952] Here is an example of a prompt to input to a generative AI model:

[1953] "Generate optimal staffing recommendations based on employee performance data and sentiment information. For example, recommend the best roles for employees A, B, and C in the sales department and generate questions using sentiment information."

[1954] This makes it possible to provide optimal placemen...

Claims

1. A means of collecting human resources information from each department and organization, A means to complement missing values ​​in the collected human resources information and to detect and correct outliers; Based on the pre-processed human resource information, a method for analyzing the characteristics of active personnel using generative AI, and A means for generating an optimal personnel allocation plan based on the characteristics of active personnel; means for notifying a user of the generated placement plan; A means for cleansing job applicant data and generating interview questions; A system including:

2. The system of claim 1 , further comprising means for defining promotion requirements using a generative AI based on the preprocessed human resources information.

3. The system according to claim 1 , further comprising means for constructing an active talent model based on the preprocessed talent information.

Images