System

Abstract

A system is provided.SOLUTION: A system, comprising: means for generating feedback for an employee by using a trained assessment model; means for sending the generated feedback to a device of the employee; and means for suggesting a career path based on historical assessment results and / or career goals of the employee; wherein the historical assessment results and / or the career goals are obtained from the employee's daily report, assessment sheet, and / or human resource development chart.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 modern companies, employee evaluation and career path development are important tasks, but as daily work progress and challenges increase, it becomes difficult to provide consistent quality support for human resource development. This problem stems from the personalization of personnel evaluation and career path development, particularly the lack of transparency and consistency in evaluation. This can lead to problems such as a decline in employee motivation and an inability to map out appropriate career paths. Therefore, there is a need for a system that can ensure the quality of employee evaluation and career path proposals and carry them out efficiently. [Means for solving the problem]

[0005] The present invention provides a system that includes a means for collecting data such as employee daily reports, evaluation sheets, and human resource development charts in a database, a means for cleansing and preprocessing the collected data, a means for generating feedback for employees using a trained evaluation model, a means for transmitting the generated feedback to the employee's terminal, and a means for proposing a career path based on the employee's past evaluation results and career goals. Specifically, employees enter their daily work details into their terminals, and the data is transmitted to a server in real time and stored in a database. Data cleansing and preprocessing are then performed, and feedback is generated based on the trained evaluation model. The generated feedback is transmitted to the employee's terminal, allowing the employee to consider work improvement measures based on the feedback. The system also proposes an optimal career path based on past evaluation results and career goals. This ensures transparency and consistency in evaluations and enables efficient human resource development support.

[0006] "Employee daily report data" refers to data recorded by employees on their daily work progress, challenges, and accomplished tasks.

[0007] An "evaluation sheet" is a paper or electronic format used to evaluate an employee's work or performance.

[0008] A "human resource development chart" is long-term human resource management information that records an employee's skills, performance, career goals, etc.

[0009] "Database collection means" refers to the processes and techniques used to obtain information from multiple data sources, organize it, and store it in a database.

[0010] "Data cleansing" is the process of removing errors and inconsistencies from collected data to make it accurate and consistent.

[0011] "Preprocessing" is a process carried out as a preliminary step to prepare raw data in a form suitable for analysis or model input.

[0012] A "trained evaluation model" is a model for evaluating employees that is trained by a machine learning algorithm using historical data.

[0013] A "means for generating feedback" is a technology that automatically generates evaluations and advice for employees based on collected and processed data.

[0014] The "means for transmitting feedback to an employee's terminal" is a system for transmitting the generated feedback to a terminal used by a specific employee and displaying it.

[0015] "Means for proposing career paths" refers to techniques for designing and proposing future career plans for employees based on their past evaluation results and career goals. [Brief explanation of the drawings]

[0016] [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

[0017] 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.

[0018] First, the terms used in the following description will be explained.

[0019] 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).

[0020] 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.

[0021] 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.

[0022] 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.

[0023] 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."

[0024] [First embodiment]

[0025] FIG. 1 shows an example of the configuration of a data processing system 10 according to the first embodiment.

[0026] 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.

[0027] 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).

[0028] 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.

[0029] 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.

[0030] 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.

[0031] 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.

[0032] FIG. 2 shows an example of the main functions of the data processing device 12 and the smart device 14.

[0033] 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.

[0034] 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.

[0035] 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.

[0036] 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."

[0037] This invention is a human resource development support system that collects and processes data such as employee daily reports, evaluation sheets, and human resource development charts, and then provides feedback and career path suggestions based on that data. This system is comprised of a server, terminals, and users, and these elements work together to collect and process data, generate feedback, and suggest career paths.

[0038] System configuration

[0039] Server: Mainly responsible for collecting and processing data, generating feedback, and proposing career paths.

[0040] Terminal: The user's interface, where they enter daily reports, check feedback, and select their career path.

[0041] Users: Employees and managers who use the system.

[0042] Overview of program processing

[0043] 1. Data Collection Phase

[0044] Terminal: The user enters a daily work report and sends the data to the server. For example, the user enters "Completed task A and worked on project B."

[0045] Server: Receives daily report data and stores it in a database.

[0046] 2. Data Processing Phase

[0047] Server: Performs data cleansing and preprocessing, converting collected daily report data and past evaluation materials into a unified format. For example, it corrects inconsistent data and imputes missing values.

[0048] Server: Uses trained assessment models to prepare feedback and career path suggestions based on data.

[0049] 3. Feedback generation phase

[0050] Server: Inputs daily report data into the trained evaluation model and generates feedback based on common criteria. For example, it generates comments about the user's work achievements and areas for improvement.

[0051] Server: Stores the generated feedback and prepares it for transmission to the user's device.

[0052] 4. Feedback provision phase

[0053] Server: Sends feedback and notifies the user's device.

[0054] Terminal: User sees feedback.

[0055] User: Consider ways to improve their work based on the feedback provided. For example, consider specific actions such as "Maybe I should spend a little more time on the next task C."

[0056] 5. Career path proposal phase

[0057] Server: Analyzes the evaluation data and suggests optimal career paths based on the employee's past evaluation results and career goals. For example, it generates a message such as, "Based on User A's technical skills and evaluation, we recommend promotion to project manager."

[0058] Server: Sends career path suggestions to the user's device.

[0059] Terminal: User reviews career path suggestions and is offered options.

[0060] User: Review the proposed career paths and select the most suitable plan. Users can make future career plans based on the career paths provided.

[0061] Specific examples

[0062] Data Collection Phase

[0063] Terminal: User enters daily report. Example: "I completed task A and started working on new project B."

[0064] Server: Receives the data and stores it in a database.

[0065] Data Processing Phase

[0066] Server: Cleanses and pre-processes the collected daily report data. For example, record that task A is completed and new project B has started.

[0067] Server: Analyzes the data using the trained evaluation model.

[0068] Feedback generation phase

[0069] Server: Generates feedback. Example: "User A completes Task A efficiently and transitions quickly to new work."

[0070] Feedback provision phase

[0071] Server: Sends the generated feedback to the device.

[0072] Terminal: Show feedback and notify the user.

[0073] User: Review the feedback and decide on the next action.

[0074] Career path proposal phase

[0075] Server: Suggests optimal career paths. Example: "Based on the evaluation results of User A, we recommend promotion to project manager."

[0076] Terminal: Displays suggestions and gives the user choices.

[0077] User: Review the proposals and choose the most suitable career plan.

[0078] In this way, the system can efficiently evaluate employees and create career paths, ensuring transparency and consistency.

[0079] The processing flow will be explained below.

[0080] Step 1:

[0081] Terminal: The user enters a daily work report. The user fills in the input form in detail with the work content, progress, and any issues that have arisen that day. For example, the user might write, "I have completed Task A and started working on Project B."

[0082] Step 2:

[0083] Terminal: Sends the entered daily report data to the server. Once the entry is complete, the daily report data is automatically sent to the server. Data is transferred in real time using a communication protocol.

[0084] Step 3:

[0085] Server: Receives daily report data and stores it in a database. The server analyzes the received data and stores it in the database in an appropriate format. At this time, validation is performed to ensure the consistency and completeness of the data.

[0086] Step 4:

[0087] Server: Performs data cleansing and preprocessing. Converts collected daily report data and past evaluation materials into a unified format and corrects errors and inconsistencies. For example, fills in missing values ​​and standardizes data.

[0088] Step 5:

[0089] Server: Analyzes the data using a trained evaluation model. The cleansed data is input into the evaluation model, preparing it for feedback. This model is trained on past data, enabling highly accurate evaluation.

[0090] Step 6:

[0091] Server: Generates feedback. Based on the trained evaluation model, the server automatically generates feedback on employees' work performance and areas for improvement. For example, it generates specific comments such as, "User A completed Task A efficiently and is recognized for quickly transitioning to new tasks."

[0092] Step 7:

[0093] Server: Stores the generated feedback and prepares it for transmission to the user's device. The feedback is temporarily stored in a database and then transmitted to the user's device in an appropriate format.

[0094] Step 8:

[0095] Server: Sends feedback to the user's device. The sent feedback is delivered to the device so that the user can check it.

[0096] Step 9:

[0097] Device: The user receives and checks the feedback. The user opens the feedback message on the device and checks its contents. For example, the user may consider taking specific actions, such as "Maybe I should spend a little more time on the next task C."

[0098] Step 10:

[0099] Server: Analyzes assessment data to generate career path suggestions. Designs optimal career paths based on the user's past assessment results, skill sets, career goals, etc. This analysis creates a long-term career plan for the user.

[0100] Step 11:

[0101] Server: Sends the career path proposal to the user's device. The generated career path proposal is sent to the user's device, where the user can check it.

[0102] Step 12:

[0103] Device: The user receives and confirms the career path proposal. The user reviews the proposal displayed on the device in detail and considers their career options.

[0104] Step 13:

[0105] User: Selects his / her own career plan based on the proposed career paths. The user considers the suggestions, selects the most suitable career path, and decides on the next step. For example, if the proposed career path is promotion to project manager, the user creates an action plan to achieve that goal.

[0106] Example 1

[0107] 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."

[0108] In conventional employee evaluation systems, information such as daily report data and evaluation sheets was not managed in a unified format, making data cleansing and preprocessing cumbersome. Furthermore, feedback was not automatically generated using a trained evaluation model, placing a heavy burden on administrators. Furthermore, there was a lack of support for users to consider work improvement measures based on their own feedback. This resulted in a lack of transparency and consistency in employee evaluations, making it difficult to suggest optimal career paths.

[0109] 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.

[0110] In this invention, the server includes means for collecting data such as users' daily report data, evaluation sheets, and development charts in a database, means for cleansing and preprocessing the collected data, means for generating feedback for the user using a trained evaluation model, means for transmitting the generated feedback to the user's terminal, means for proposing a career path based on the user's past evaluation results and career goals, and means for considering business improvement measures based on the user's feedback. This significantly improves the transparency and consistency of user evaluations, enabling effective feedback and the suggestion of appropriate career paths.

[0111] A "user" is an individual or organizational member who uses the system to enter daily report data and receive feedback.

[0112] "Daily report data" is information that a user inputs to report daily work content and progress.

[0113] An "evaluation sheet" is a document or table used to evaluate a user's work performance, behavior, etc.

[0114] A "development chart" is a document or database that keeps records for users' ability development and skill improvement.

[0115] A "database" is a digital storage system for efficiently storing, managing, and retrieving collected data.

[0116] "Cleansing" is a process of removing inconsistencies and unnecessary information from collected data to improve the quality of the data.

[0117] "Preprocessing" refers to the preparation of data to convert it into a format suitable for analysis or model input.

[0118] An "assessment model" is a set of algorithms that uses training data to evaluate a user's job performance and generate feedback.

[0119] "Feedback" refers to comments and advice regarding the user's business achievements and areas for improvement, which are generated from the evaluation model.

[0120] A "career path" is a plan of future jobs and roles suggested based on a user's past work performance and career goals.

[0121] "Business improvement measures" are specific actions or methods that users should take in their next business operation based on the feedback.

[0122] This system allows users to collect data such as daily reports, evaluation sheets, and development charts, cleanses and preprocesses the data, generates feedback using a trained evaluation model, and suggests career paths for users. This system consists of three main components: a server, a terminal, and a user.

[0123] server

[0124] The server is the core of this system and plays the following roles:

[0125] Data collection and storage: The server receives the daily report data, evaluation sheets, and development charts entered by the user and stores them in a database. Specifically, MySQL or PostgreSQL is used as the database.

[0126] Data cleansing and preprocessing: To ensure data consistency, use scripts such as Python or R to correct inconsistent data and impute missing values.

[0127] Execution of the evaluation model: The trained evaluation model is built using scikit-learn and TensorFlow, and is used to generate feedback based on the user's performance and areas for improvement.

[0128] Feedback and career path generation: The generated feedback and career path suggestions are stored in a database and prepared for transmission to the user's device.

[0129] Terminal

[0130] The terminal provides an interface for users to input daily report data and check feedback and career paths. It has the following functions:

[0131] Data entry and transmission: Users use a device (PC or tablet) to enter daily report data through a dedicated web application and send it to the server. Communication is carried out using the HTTPS protocol.

[0132] Show Feedback: Displays the feedback received from the server for the user to review.

[0133] Review Career Paths: Display suggested career paths and allow users to review and select.

[0134] User

[0135] Users use the system to input daily report data, receive feedback, and consider their career paths. The specific operations are as follows:

[0136] Entering daily report data: The user enters work details into an input form on the terminal, such as "Completed task A and worked on project B."

[0137] Review feedback: The user reviews the feedback received from the server and considers improvements.

[0138] Career path selection: Based on the career paths provided, select the most suitable career plan and make future plans.

[0139] Specific examples

[0140] Entering daily report data

[0141] The user accesses the web application on the terminal and enters the daily report data.

[0142] For example: "I completed task A and started working on new project B."

[0143] Generate feedback

[0144] The server generates feedback using the trained evaluation model.

[0145] For example: "User A completes Task A efficiently and transitions quickly to new tasks."

[0146] Career path suggestions

[0147] The server suggests career paths based on the user's past evaluation results and career goals.

[0148] Example: "Based on the results of User A's evaluation, I would like to recommend promotion to Project Manager."

[0149] Examples of prompt statements

[0150] "User A's daily report data: Completed Task A and started working on Project B. Past evaluation: Good. Areas for improvement: Needs detailed project plan." Use this daily report data to generate feedback and career path suggestions.

[0151] As described above, the system provides an efficient process for consistently conducting employee evaluations and career path proposals, ensuring transparency and consistency.

[0152] The flow of the identification process in the first embodiment will be described with reference to FIG.

[0153] Step 1: Data collection

[0154] On the device, the user opens a dedicated web application and enters daily report data. Input items include the completion status of tasks and details of projects worked on. For example, the user might enter, "Completed Task A and worked on Project B."

[0155] Input: User's daily report data (Task A completed, Project B started)

[0156] Output: Sending daily report data to the server

[0157] Step 2: Send and store data

[0158] Terminal: The entered daily report data is sent to the server via the HTTPS protocol. The user clicks the "Send" button, and the data is transferred to the server.

[0159] Input: User's daily report data

[0160] Output: Daily report data sent to the server

[0161] Server: The received daily report data is saved in a database (e.g., MySQL, PostgreSQL). The database stores information such as the date, user ID, and task ID as records.

[0162] Input: Daily report data sent from the terminal

[0163] Output: Daily report data stored in the database

[0164] Step 3: Data cleansing and preprocessing

[0165] Server: Using Python and R scripts, the incoming daily report data is cleansed and inconsistencies and missing values ​​are corrected, for example, to standardize date formats and add specific tagging.

[0166] Input: Saved daily report data

[0167] Output: Cleansed and preprocessed data

[0168] Step 4: Run the evaluation model

[0169] Server: Analyzes the pre-processed data using a trained evaluation model (e.g., scikit-learn, TensorFlow). This model generates feedback based on the user's performance and areas for improvement.

[0170] Input: Cleansed and preprocessed data

[0171] Output: Generated feedback

[0172] Step 5: Generate and save your feedback

[0173] Server: Stores the generated feedback in a database. Feedback is managed for each user and stored for review.

[0174] Input: Feedback generated from the evaluation model

[0175] Output: Feedback stored in a database

[0176] Step 6: Submit your feedback

[0177] Server: Sends the saved feedback to the user's device via HTTPS protocol, and the feedback is ready for the user to receive.

[0178] Input: Feedback stored in the database

[0179] Output: Feedback sent to the user's device

[0180] Step 7: View your feedback

[0181] On the device: The user opens the application to view the feedback. The feedback is displayed in a list format. The user receives a notification and can view the details.

[0182] Input: Notification that feedback was received

[0183] Output: Feedback displayed on the terminal

[0184] Step 8: Analyze and generate career paths

[0185] Server: Based on the user's past evaluation data and career goals, the server proposes a career path that combines the evaluation data and goals. To this end, it analyzes data collected in advance and generates an optimal career plan.

[0186] Input: Past evaluation data, career goals

[0187] Output: Generated career path suggestions

[0188] Step 9: Submit and view your career path

[0189] Server: The generated career path is sent to the user's device using the HTTPS protocol, allowing the user to check the career path after it has been sent.

[0190] Input: Generated career path proposal

[0191] Output: Career path proposal sent to the user device

[0192] On the device: The user opens the application to view the career path suggestions and explore their options. Career paths are displayed in a dedicated section of the dashboard.

[0193] Input: Career path proposal

[0194] Output: Career path suggestions displayed on the device

[0195] Step 10: Consider business improvement measures

[0196] Users: Based on the feedback and career path suggestions, users consider ways to improve their work and decide on specific actions to take to plan their next work or personal development.

[0197] Input: Feedback and career path suggestions displayed

[0198] Output: Considered business improvement measures and career plans

[0199] In this way, through a series of processing steps, this system can efficiently generate evaluations and career plans from users' daily report data, ensuring transparency and consistency.

[0200] (Application example 1)

[0201] 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."

[0202] Current human resource development support systems mainly focus on evaluating employee performance and proposing career paths in office work, but do not address the evaluation and career development of operators engaged in practical work in factories. As a result, there is a lack of means to efficiently support factory operators in improving their skills and building their career paths. To solve this problem, a system is needed to collect, evaluate, and provide feedback on the work data of factory operators.

[0203] 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.

[0204] In this invention, the server includes means for collecting data such as employee daily report data, evaluation sheets, and human resource development charts in a database, means for cleansing and preprocessing the collected data, means for generating feedback for employees using a trained evaluation model, means for sending the generated feedback to the employee's terminal, means for proposing a career path based on the employee's past evaluation results and career goals, means for collecting factory robot operation data and operator daily work reports, means for preprocessing the collected robot operation data and providing feedback to the operator, and means for proposing improvements to robot operation skills based on the operator's evaluation results. This makes it possible to improve the skills of factory operators and create career paths.

[0205] "Employee daily report data" refers to data about the progress of work and completed tasks that employees record in their daily work reports.

[0206] An "evaluation sheet" is a written or electronic format for recording an employee's performance evaluation or performance rating.

[0207] A "human resources development chart" is a database that records employees' past evaluation results and education and training history.

[0208] "Data cleansing" is the process of improving data quality by correcting inconsistent data, filling in missing values, etc.

[0209] "Preprocessing" is the process of converting data into a format suitable for input into data analysis or machine learning models.

[0210] A "trained evaluation model" is an analytical model that has been trained by a machine learning algorithm using historical data.

[0211] "Feedback generation" is a process that generates written recommendations for improvement and evaluation results for employees based on evaluation data.

[0212] "Feedback transmission" is the process of sending the generated feedback to the employee's terminal.

[0213] "Career path proposal" is a process that suggests the next job or position an employee should take based on their evaluation data and career goals.

[0214] "Factory robot operation data" refers to data related to the tasks and actions performed by robots used in factories.

[0215] The "operator's daily work report" is daily report data recorded by a factory operator regarding the work content and progress of the day.

[0216] "Improving robot operation skills" is the process of making suggestions and providing training to improve factory operators' robot operation capabilities based on evaluation data.

[0217] This invention is a system for supporting the operation of robots in factories and the training of their operators. This system is composed of a server, terminals, and user elements, which work together to collect and process data, generate feedback, and propose career paths.

[0218] System configuration

[0219] 1. Server: Responsible for collecting and processing data, generating feedback, and proposing career paths. Python and machine learning frameworks (TensorFlow, PyTorch) are used to run the program.

[0220] 2. Device: An interface where users can enter their daily reports and view feedback and career path suggestions. Devices include smartphones and smart glasses.

[0221] 3. Users: Factory operators and their managers who use the system.

[0222] Overview of program processing

[0223] 1. Data collection phase:

[0224] Terminal: The user inputs the daily work report and sends the data to the server. For example, the user inputs "Robot A has completed the inspection work and is now on the next manufacturing task."

[0225] Server: Receives daily report data and saves it in the database. The data format is JSON.

[0226] 2. Data Processing Phase:

[0227] Server: Performs data cleansing and preprocessing, converting collected daily work report data and past evaluation materials into a unified format. For example, it corrects inconsistent data and imputes missing values. It uses the Python pandas library.

[0228] Server: Uses the trained evaluation model to prepare feedback and career path suggestions based on the data. Uses scikit-learn to train the machine learning model.

[0229] 3. Feedback generation phase:

[0230] Server: Inputs the daily work report data into the trained evaluation model and generates feedback based on common criteria. For example, it generates comments about the user's work progress and areas for improvement.

[0231] Server: Stores the generated feedback and prepares it for transmission to the user's device.

[0232] 4. Feedback provision phase:

[0233] Server: Sends feedback and notifies the user's device.

[0234] Device: The user sees the feedback, which is displayed through a smartphone app or smart glasses.

[0235] User: Consider ways to improve their own work based on the feedback provided.

[0236] 5. Career path proposal phase:

[0237] Server: Analyzes the evaluation data and proposes the optimal career path based on the operator's past evaluation results and career goals. For example, it generates a message such as, "Based on the evaluation results of Operator A, we propose training in machine maintenance."

[0238] Server: Sends career path suggestions to the user's device.

[0239] Terminal: User reviews career path suggestions and is offered options.

[0240] User: Review the proposed career paths and select the most suitable plan. Users can make future career plans based on the career paths provided.

[0241] Example prompt sentence:

[0242] "Based on the operators' daily reports, generate feedback on their work performance and areas for improvement in their next assignment. Also, provide career path suggestions."

[0243] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[0244] Step 1:

[0245] Terminal: The user inputs the daily work report. Specifically, the user uses a smartphone or smart glasses to record the work details, such as "Robot A's inspection work has been completed and it has moved on to the next manufacturing task," and presses the send button. The data entered includes the work details, date, completion status, etc., and is sent to the server in JSON format. The output is the data sent to the server.

[0246] Step 2:

[0247] Server: Receives the sent daily work report data and saves it in a database. Specifically, the server parses the received JSON data and stores it in a database (e.g., MySQL, PostgreSQL). The input is the daily work report data sent from the terminal, and the output is the data saved in the database.

[0248] Step 3:

[0249] Server: Cleanses and preprocesses the daily report data. Specifically, it uses Python's pandas library to complement missing data and correct inconsistent data. The input is the daily work report data stored in the database, and the output is the data after cleansing and preprocessing.

[0250] Step 4:

[0251] Server: Using the trained evaluation model, analyze the daily work report data and prepare for feedback generation. Specifically, the preprocessed data is input into a machine learning model (e.g., scikit-learn's RandomForestRegressor) to predict the user's work achievement and areas for improvement. The input is the preprocessed daily work report data, and the output is the evaluation results necessary for feedback generation.

[0252] Step 5:

[0253] Server: Generates feedback using the trained evaluation model. Specifically, it generates feedback sentences based on the evaluation results and provides specific advice, such as "Operator A's task achievement rate is 80%. It would be desirable to shorten the inspection time a little more for the next task." The input is the evaluation results, and the output is the generated feedback sentences.

[0254] Step 6:

[0255] Server: Sends the generated feedback to the user's device. Specifically, it sends a message to a smartphone or smart glasses using an API for notifying the device of the feedback. The input is the generated feedback text, and the output is the feedback displayed on the user's device.

[0256] Step 7:

[0257] Device: The user checks the feedback. Specifically, the user clicks on the notification on the device to check the feedback content. Based on the information obtained from the feedback, an action plan for the next task is considered. The input is the feedback sent from the server, and the output is the user's action plan based on the feedback.

[0258] Step 8:

[0259] Server: Analyzes evaluation data and proposes career paths based on the operator's past evaluation results and career goals. Specifically, it uses evaluation data to generate career path options, proposing content such as "Based on the evaluation results of Operator A, we propose training in machine maintenance." The input is evaluation data, and the output is a written career path proposal.

[0260] Step 9:

[0261] Server: Sends career path suggestions to the user's device. Specifically, similar to feedback, it sends career path suggestions using an API to notify the device. The input is the career path suggestion text, and the output is the career path suggestion displayed on the user's device.

[0262] Step 10:

[0263] Device: The user reviews the career path proposals and selects the most suitable plan. Specifically, the user clicks on the notification on the device to review the career path proposals and decides whether to adopt them as their own career plan. The input is the career path proposal sent from the server, and the output is the career plan selected by the user.

[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] This invention is a human resource development support system that collects and processes data such as employee daily reports, evaluation sheets, and human resource development charts, and provides feedback and career path suggestions. This system incorporates an emotion engine that recognizes the user's emotions, and individual feedback and career path suggestions are adjusted taking into account the user's emotional state.

[0266] System configuration

[0267] Server: Performs functions of data collection, processing, feedback generation, career path suggestions, and sentiment analysis.

[0268] Terminal: Functions as an interface with the user, allowing them to enter daily reports, display feedback, transmit emotional data, and select career paths.

[0269] Users: Employees and managers who use the system.

[0270] Emotion Engine: Recognizes user emotions and reflects them in feedback and career path suggestions.

[0271] Overview of program processing

[0272] 1. Data Collection Phase

[0273] Terminal: The user enters a work report, for example, "I completed task A and started working on project B."

[0274] Terminal: Daily report data is automatically sent to the server.

[0275] 2. Data Processing Phase

[0276] Server: Stores the received daily report data in a database and performs data cleansing and preprocessing, filling in missing values ​​and standardizing the data.

[0277] Server: Uses the trained evaluation model to prepare feedback and career path suggestions.

[0278] 3. Feedback generation phase

[0279] Server: Inputs daily report data into the evaluation model and generates feedback. For example, it creates specific comments such as "User A is highly evaluated because he completed Task A efficiently."

[0280] Server: Analyzes the user's emotional data using the emotion engine. Adjusts the feedback based on the user's emotional state. For example, if the user is feeling stressed, the server adds a comment to the feedback such as "Please reconsider your work balance and take a rest."

[0281] 4. Feedback provision phase

[0282] Server: Sends the generated feedback to the user's device.

[0283] Terminal: Display feedback so that the user can see it.

[0284] 5. Emotional Data Collection Phase

[0285] Terminal: Collects emotional data from user input and reactions. The emotional data is sent to the server in real time.

[0286] Emotion Engine: Analyzes the emotion data collected from the user and evaluates their current emotional state.

[0287] 6. Career path proposal phase

[0288] Server: Analyzes the evaluation data and suggests the best career path. For example, "Based on User A's past evaluation results and technical skills, we suggest promotion to project manager."

[0289] Server: Uses an emotion engine to tailor career path suggestions to the user's emotional state. For example, if the user is feeling anxious, the server might add "support systems" or "training programs" to the suggestions.

[0290] Server: Sends career path suggestions to the user's device.

[0291] Terminal: User reviews career path suggestions.

[0292] User: Select your own career plan based on the suggestions.

[0293] Specific examples

[0294] Data Collection Phase

[0295] Terminal: User enters daily report. Example: "I completed task A and started working on new project B."

[0296] Server: Receives the data and stores it in a database.

[0297] Data Processing Phase

[0298] Server: Cleanses and pre-processes the collected daily report data. For example, record that task A is completed and new project B has started.

[0299] Server: Analyzes the data using the trained evaluation model.

[0300] Feedback generation phase

[0301] Server: Generates feedback. Example: "User A completes Task A efficiently and transitions quickly to new work."

[0302] Server: Uses the emotion engine to analyze the user's emotional state and reflect it in the feedback. For example, if the user is feeling stressed, add a comment such as "Please reconsider your work balance and take a rest."

[0303] Feedback provision phase

[0304] Server: Sends the generated feedback to the device.

[0305] Terminal: Show feedback and notify the user.

[0306] User: Review the feedback and decide on the next action.

[0307] Career path proposal phase

[0308] Server: Suggests optimal career paths. Example: "Based on the evaluation results of User A, we recommend promotion to project manager."

[0309] Server: Uses an emotion engine to generate career path suggestions that reflect the user's emotional state. For example, if the user is feeling anxious, add "support systems" and "training programs" to the suggestions.

[0310] Device: Display the suggestion and make it available for the user to review.

[0311] User: Review the proposals and choose the most suitable career plan.

[0312] The processing flow will be explained below.

[0313] Step 1:

[0314] Terminal: The user enters a daily work report. The user fills in the input form on the terminal with details of the day's work, progress, and any issues they encountered. For example, they might write, "I completed task A and started working on a new project B."

[0315] Step 2:

[0316] Terminal: Sends the entered daily report data to the server. After input is complete, the daily report data is automatically sent to the server. Transmission is secure using encrypted communication protocols such as SSL.

[0317] Step 3:

[0318] Server: Receives daily report data and saves it in the database. The server converts the received daily report data into an appropriate format and stores it in the database. When saving, a validation check is performed to confirm the consistency of the data.

[0319] Step 4:

[0320] Server: Performs data cleansing and preprocessing. Corrects errors and inconsistencies in the collected daily report data and converts it into a unified format. For example, it fills in missing values ​​and standardizes date formats.

[0321] Step 5:

[0322] Server: Analyzes the data using a trained evaluation model. The cleansed data is fed into the evaluation model, preparing it for feedback generation. The model is trained using machine learning algorithms, enabling highly accurate evaluations.

[0323] Step 6:

[0324] Server: Works with the device to collect user emotion data. The emotion engine runs and collects user input and reactions, such as keystroke speed and back arching.

[0325] Step 7:

[0326] Emotion engine: Analyzes collected data and evaluates the user's emotional state. For example, if a user types faster than usual, it recognizes that the user is under stress.

[0327] Step 8:

[0328] Server: The emotion data obtained from the emotion engine is reflected in the evaluation model and feedback is generated. For example, if a user is under stress, a comment such as "Please reconsider your work balance and take some rest" is added.

[0329] Step 9:

[0330] Server: Stores the generated feedback in a database and prepares it for transmission to the user's device.

[0331] Step 10:

[0332] Server: Sends the generated feedback to the user's device. Uses a notification system to notify the user that the feedback has arrived.

[0333] Step 11:

[0334] Terminal: Feedback is displayed and made available for the user to check. The user can check the feedback on their terminal and use it to improve their own work.

[0335] Step 12:

[0336] Server: Proposes optimal career paths based on evaluation data. Generates career paths taking into account past evaluation results, the user's skill set, and long-term career goals.

[0337] Step 13:

[0338] Server: Adjust the career path suggestions based on the results of the emotion engine. For example, if the user feels anxious, add support systems or training programs to the suggestions.

[0339] Step 14:

[0340] Server: Sends tailored career path proposals to the user's device.

[0341] Step 15:

[0342] Device: The career path proposal is displayed and made available for the user to review. The user reviews the proposal in detail and considers their own career plan.

[0343] Step 16:

[0344] User: Selects his / her own career plan based on the suggested career paths. The user considers the suggestions and selects the most suitable career path. For example, if a promotion to project manager is proposed, the user creates an action plan for that promotion.

[0345] Example 2

[0346] 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."

[0347] Although conventional human resource management systems can collect employee daily report data and evaluation sheets, they do not take into account the emotional state of each employee when making feedback or career path suggestions, which means that employee motivation and performance cannot be optimized, limiting the efficiency of the organization as a whole.In addition, because employee career path suggestions are standardized, flexible suggestions based on the characteristics and goals of each employee cannot be made.

[0348] The specific processing by the specific processing unit 290 of the data processing device 12 in the second embodiment is realized by the following means.

[0349] In this invention, the server includes a means for collecting data such as employee daily reports, evaluation sheets, and human resource development charts in a database, a means for cleansing and preprocessing the collected data, a means for generating feedback for employees using a trained evaluation model, a means for analyzing user emotion data and adjusting the feedback and career path suggestions, and a means for sending the generated feedback to the employee's terminal. This enables flexible and appropriate feedback and career path suggestions that take into account the emotional state of each employee.

[0350] A "database" is a system for storing, managing, and searching data in an organized manner.

[0351] "Data cleansing" is the process of filling in missing values, correcting inaccurate data, and standardizing it.

[0352] "Preprocessing" refers to the preparatory work done before inputting data into data analysis or machine learning models, and includes data formatting and normalization.

[0353] An "evaluation model" is a trained algorithm that evaluates employee performance based on input data and generates feedback.

[0354] "Feedback" refers to evaluations and comments on employees' performance, with the aim of improving work and increasing motivation.

[0355] "Emotional data" is data used to measure and analyze a user's emotional state, and is collected from the user's input, reactions, etc.

[0356] A "career path" is the path of goals and positions that an employee should pursue within a company, including plans for growth and promotion.

[0357] The "Emotion Engine" is a system that analyzes users' emotional data and reflects it in feedback and career path suggestions.

[0358] "Collection means" refers to the method or system for collecting daily report data, evaluation sheets, etc. into a database.

[0359] "Cleansing and preprocessing means" refers to methods and systems used to prepare collected data and make it suitable for analysis.

[0360] "Feedback generator" means a method or system for generating ratings and comments for employees using a trained rating model.

[0361] "Emotion data analysis means" refers to a method or system for analyzing a user's emotional data and reflecting the results in feedback and career path suggestions.

[0362] "Transmission means" refers to a method or system for sending the generated feedback and career path suggestions to the employee's terminal.

[0363] This invention relates to a human resource development support system that collects and processes data such as employee daily reports, evaluation sheets, and human resource development charts, and provides feedback and career path suggestions. This system incorporates an emotion engine that recognizes the user's emotions, and the feedback and career path suggestions are adjusted taking into account the user's emotional state.

[0364] System configuration

[0365] Server: Performs functions such as data collection, processing, feedback generation, career path suggestions, and sentiment analysis. The server can utilize cloud-based infrastructure (e.g., AWS, Google Cloud).

[0366] Terminal: Functions as an interface with the user, allowing them to input daily reports, display feedback, transmit emotional data, and select career paths. Terminals include, for example, personal computers and smartphones.

[0367] Users: Employees and managers who use the system.

[0368] Emotion engine: Recognizes the user's emotions and reflects them in feedback and career path suggestions. For example, the IBM Watson Tone Analyzer can be used as an emotion engine.

[0369] Data collection

[0370] The terminal provides an interface for users to input daily work reports. The daily report data entered by the user is sent from the terminal to a server. The transmission is secure using a security protocol (e.g., HTTPS). The server stores the received daily report data in a database. This database uses a database management system such as "PostgreSQL."

[0371] Data Processing

[0372] The server cleanses and preprocesses the daily report data stored in the database. This process includes filling in missing values ​​and standardizing the data. Cleansing and preprocessing improves the accuracy and reliability of the data. A trained evaluation model can be built using TensorFlow, for example. The daily report data is input into this evaluation model and analyzed.

[0373] Feedback Generation

[0374] The server creates feedback based on the data generated by the evaluation model. For example, it generates a comment such as, "Employee A is highly evaluated because he completed Task A efficiently." The server also analyzes the user's emotional data using an emotion engine and adjusts the content of the feedback. For example, if the user is feeling stressed, it adds a comment such as, "It is recommended that you reconsider your work balance and take a rest."

[0375] Providing Feedback

[0376] The server sends the generated feedback to the user's device. For example, a notification service such as Firebase Cloud Messaging can be used for this purpose. The device displays the feedback and notifies the user.

[0377] Emotional Data Collection

[0378] The device collects emotional data from the user's input and reactions, which is then sent to a server in real time and analyzed by an emotion engine.

[0379] Career path suggestions

[0380] The server proposes optimal career paths based on the collected and analyzed evaluation data. For example, it generates a proposal such as, "Based on Employee A's past evaluation results and technical skills, we propose promotion to project manager." The server can also use an emotion engine to adjust the proposal content according to the user's emotional state. For example, if the user is feeling anxious, it can add a "support system" or "training program" to the proposal. The career path proposal is sent to the terminal, and the user can select their own career plan based on the proposal.

[0381] Specific examples

[0382] For example, a user enters a daily report stating, "I completed Task A and started working on new Project B." This data is sent to the server via the device and stored in a database. The server cleanses and preprocesses the data, inputs it into an evaluation model, and generates feedback. The generated feedback might be, "User A completed Task A efficiently and is moving quickly to new work." Furthermore, if the user is determined to be feeling stressed, a comment such as, "Please reconsider your work balance and take a rest" is added.

[0383] Prompt Sentence Examples

[0384] "Please explain the program of a system that generates feedback based on employees' daily report data and suggests career paths that reflect the user's emotional state. Please explain the process in detail using specific examples."

[0385] This system enables flexible and appropriate feedback and career path suggestions that take into account employees' emotional state, which is expected to improve efficiency and motivation throughout the organization.

[0386] The flow of the identification process in the second embodiment will be described with reference to FIG.

[0387] Step 1:

[0388] The user inputs a daily work report. The user uses a terminal to input daily report data, such as "Task A completed and started working on new project B." Once input is complete, the data is automatically sent from the terminal to the server.

[0389] Step 2:

[0390] The terminal sends the daily report data to the server. A security protocol (e.g. HTTPS) is used for transmission, and the data is transferred safely. Terminal input: Daily report data entered by the user. Output: Daily report data sent.

[0391] Step 3:

[0392] The server stores the received daily report data in a database. For example, "PostgreSQL" is used as the database. Server input: Daily report data sent from the terminal. Output: Daily report data stored in the database.

[0393] Step 4:

[0394] The server performs data cleansing and preprocessing. The server fills in any missing values ​​in the daily report data and standardizes the data. Server input: Daily report data read from the database. Output: Data after cleansing and preprocessing.

[0395] Step 5:

[0396] The server analyzes the data using a trained evaluation model, for example, a model built using TensorFlow. Server input: cleansed and preprocessed data. Output: analysis results.

[0397] Step 6:

[0398] The server generates feedback based on the data generated by the evaluation model. For example, it generates specific comments such as "Employee A is highly evaluated because he completed task A efficiently." Server input: Analysis results. Output: Generated feedback.

[0399] Step 7:

[0400] The server uses an emotion engine to analyze the user's emotion data and adjust the feedback content. The emotion engine used is something like "IBM Watson Tone Analyzer." For example, if the user is feeling stressed, it adds a comment saying, "We recommend that you reconsider your work balance and take a rest." Server input: Feedback and emotion data. Output: Adjusted feedback.

[0401] Step 8:

[0402] The server sends the generated feedback to the user's device. This is done using a notification service such as Firebase Cloud Messaging. Server input: Adjusted feedback. Output: Feedback sent to the user's device.

[0403] Step 9:

[0404] The device displays feedback and notifies the user. Notifications can be done using popup messages or in-app notifications. Device input: Feedback sent from the server. Output: Feedback displayed to the user.

[0405] Step 10:

[0406] The user checks the feedback on the device, and as a next step, decides on the next action and reflects it in their work.

[0407] Step 11:

[0408] The device collects emotional data from the user's input and reactions. Emotional data is collected using the user's keystroke analysis and screen touch data. Device input: User's input and reactions. Output: Collected emotional data.

[0409] Step 12:

[0410] The device sends the collected emotion data to the server in real time. Device input: Collected emotion data. Output: Emotion data sent to the server.

[0411] Step 13:

[0412] The emotion engine analyzes the user's emotional state on the server and records it in the emotion database. The analysis results are used as feedback for the generative AI model. Server input: collected emotion data. Output: analysis results and recorded emotion data.

[0413] Step 14:

[0414] The server analyzes the user's daily report data and past evaluation data to propose the optimal career path. For example, it generates a proposal such as "Based on the evaluation results of employee A, recommend promotion to project manager." Server input: Daily report data and past evaluation data. Output: Career path proposal.

[0415] Step 15:

[0416] The server uses an emotion engine to adjust the career path suggestions to fit the user's emotional state. For example, if the user is feeling anxious, the suggestions will be adjusted to include "support systems" and "training programs." Server input: Career path suggestions and emotion data. Output: Adjusted career path suggestions.

[0417] Step 16:

[0418] The server sends the career path proposal to the user's device. Server input: Adjusted career path proposal. Output: Career path proposal sent to the user's device.

[0419] Step 17:

[0420] The terminal displays the career path proposal for the user to review. Terminal input: Career path proposal sent from the server. Output: Career path proposal displayed to the user.

[0421] Step 18:

[0422] The user checks the career path suggestions on the terminal and selects the most suitable career plan. The selected career plan is sent back to the server and recorded in the database. User input: Career plan selection. Output: Selected career plan sent to the server.

[0423] The above is the specific processing flow of the program of this system.

[0424] (Application example 2)

[0425] 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."

[0426] While conventional human resource development support systems can provide feedback based on employee daily reports and evaluations, they lack the ability to provide feedback and career path suggestions that take into account employees' emotional states and the operation data of the machines used on-site. Furthermore, particularly in manufacturing sites, they are unable to provide feedback or career path suggestions that include production data and error history from machines such as robots, making it difficult to efficiently manage personnel and machines and improve their performance. Another problem is the inability to analyze emotional data collected in real time and adjust feedback accordingly.

[0427] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 2 is realized by the following means.

[0428] In this invention, the server includes means for collecting employee daily report data, evaluation sheets, human resource development charts, product production data, error history, and operator feedback data in a database, means for cleansing and preprocessing the collected data, means for generating feedback for employees and machines using a trained evaluation model, means for transmitting the generated feedback to the terminals of the employees and machine operators, means for proposing career paths for the employees and machine operators based on their past evaluation results and career goals, means for collecting and analyzing emotional data for the machine operators in real time, and means for adjusting the feedback and career path proposals based on their emotional states. This enables efficient feedback and career path proposals that take into account the emotional states of the employees and machine operators and the machine's production data.

[0429] "Employee daily report data" refers to data in which employees record their daily work progress and completed tasks.

[0430] An "appraisal sheet" is a written or electronic format used for the purpose of evaluating an employee's performance or skills.

[0431] A "human resources development chart" is a data sheet that records an employee's skills, career path, training history, etc.

[0432] "Product production data" refers to data that records the work content and production results of machines and robots used in manufacturing sites.

[0433] "Error history" is data that records details of errors and malfunctions that occur during manufacturing processes or machine operation.

[0434] "Operator feedback data" is data that records opinions and evaluations submitted by employees in charge of operating machines or robots regarding their work.

[0435] "Means of collecting data in a database" refers to functions and systems for organizing various data and storing it centrally.

[0436] "Data cleansing and preprocessing means" refers to functions and systems that perform preprocessing to improve data quality, such as filling in missing data values ​​and removing outliers.

[0437] A "trained evaluation model" is an algorithm or system that learns from past data and predicts and evaluates the performance of employees or machines.

[0438] "Means for generating feedback" refers to functions or systems for providing appropriate advice and areas for improvement based on the evaluation results.

[0439] The "means for sending feedback" refers to a communication function or system for delivering the generated feedback to the terminals of employees or operators.

[0440] "Means for suggesting career paths" are functions or systems that show employees and operators the optimal career path based on their past performance and goals.

[0441] "Means for collecting and analyzing emotional data in real time" refers to functions and systems for obtaining the emotional state of employees and operators in a timely manner and analyzing that data.

[0442] The "means for adjusting feedback and career path suggestions based on emotional state" refers to a function or system that optimizes the content of feedback and career path suggestions based on analyzed emotional data.

[0443] This invention is a system for collecting and processing employee daily report data, evaluation sheets, human resource development charts, product production data, error history, and operator feedback data, and providing feedback and career path suggestions. This system includes an emotion engine that analyzes emotional states and reflects them in feedback and career path suggestions.

[0444] The main components of the system are as follows:

[0445] Server: Responsible for data collection, data cleansing, pre-processing, feedback generation, career path suggestions, and sentiment analysis.

[0446] Terminal: Serves as an interface with the user, allowing them to enter daily reports, view feedback, send emotional data, and select career paths.

[0447] Users: Employees and machine operators who use the system.

[0448] Emotion Engine: Recognizes user emotions and reflects them in feedback and career path suggestions.

[0449] The system first collects daily report data and feedback data from employees and operators via their terminals and sends it to the server. The server stores the received data in a database and performs data cleansing and preprocessing. This process is performed using the Python pandas library, for example, by filling in missing values ​​and standardizing the data. Next, the trained evaluation model is used to generate feedback for employees and machine operators. The scikit-learn library is used to train the evaluation model.

[0450] The generated feedback is sent from the server to the device and displayed for the user to review. For example, if an employee enters "I completed Task A and started working on new Project B," the feedback displayed will read, "I commend you for completing Task A efficiently and moving quickly to new work."

[0451] The emotion engine also analyzes the user's emotional state and adjusts the feedback accordingly. For example, if the user is feeling stressed, it might add a comment like, "Reconsider your work balance and take a break." The nltk library is used to analyze emotion data. In particular, the nltk.sentiment library is used for emotion analysis.

[0452] Furthermore, the server suggests career paths based on the user's past evaluation results and career goals. For example, it might suggest, "Based on User A's past evaluation results, we suggest transitioning to a new position exclusively for Process Z." The content of this suggestion is also adjusted according to the user's emotional state. For example, if the user is feeling anxious, it might add a "training session for a smooth transition."

[0453] As a concrete example, when a user inputs a daily report, the prompt may be something like, "Please write specifically about today's work. For example, the robot frequently produced errors, but the cause was identified and corrected." This prompt is important for maintaining consistency in the input data.

[0454] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[0455] Step 1:

[0456] Data Collection Phase

[0457] Terminals: Users (employees and machine operators) enter daily report data and feedback data. For example, an employee may enter "I have completed task A and started working on new project B."

[0458] Input: Daily report data, feedback data

[0459] Output: Raw data collected

[0460] Specific operation: When a user enters data using a dedicated application and presses the "Submit" button, the data is sent to the server in real time.

[0461] Step 2:

[0462] Data transmission phase

[0463] Terminal: Automatically sends collected daily report data and feedback data to the server.

[0464] Input: Raw data collected

[0465] Output: Data sent to the server

[0466] Specific operation: The terminal uploads data to the server via the network and stores it in the database.

[0467] Step 3:

[0468] Data cleansing and preprocessing phase

[0469] Server: Cleanses and preprocesses the received data, specifically filling in missing values ​​and standardizing the data.

[0470] Input: Data stored on the server

[0471] Output: Preprocessed and clean data

[0472] Specific operation: Create a data frame using Python's pandas library, impute missing values, and standardize.

[0473] Step 4:

[0474] Feedback generation phase

[0475] Server: Uses the trained evaluation model to generate feedback, such as "User A completed task A efficiently and therefore deserves high praise."

[0476] Input: Preprocessed and clean data

[0477] Output: Generated feedback

[0478] What it does: Uses the scikit-learn library to input data into an evaluation model and generate feedback based on the prediction results.

[0479] Step 5:

[0480] Sentiment Analysis Phase

[0481] Server: Uses an emotion engine to analyze the emotional state from the user's input and reactions.

[0482] Input: User input data, response data

[0483] Output: Parsed emotional state

[0484] Specific operation: Analyzes emotional states using the nltk.sentiment module of the nltk library.

[0485] Step 6:

[0486] Feedback Adjustment Phase

[0487] Server: Adjust the feedback based on the analyzed emotional state. For example, if the user is feeling stressed, add a comment like "Please rebalance your work and take some rest."

[0488] Input: Generated feedback, parsed emotional state

[0489] Output: Regulated Feedback

[0490] Specific operation: Using the results of sentiment analysis, the feedback content is modified appropriately and the final feedback sentence is generated.

[0491] Step 7:

[0492] Feedback sending phase

[0493] Server: Sends the generated feedback to the user's device.

[0494] Input: Calibrated Feedback

[0495] Output: Feedback sent to the terminal

[0496] Specific operation: Sends data from the server to the device and displays a notification on the device.

[0497] Step 8:

[0498] Feedback display phase

[0499] Terminal: Display feedback so that the user can see it.

[0500] Input: Feedback sent by the server

[0501] Output: Displayed feedback

[0502] Specific operation: The feedback content is displayed on the device's user interface and the user is notified.

[0503] Step 9:

[0504] Career path proposal phase

[0505] Server: Proposes a career path based on the user's past evaluation results and career goals. For example, "Based on User A's past evaluation results, we propose a transition to a new, dedicated role in Process Z."

[0506] Input: User's past evaluation results, career goals

[0507] Output: Generated career path suggestions

[0508] Specific actions: Analyze evaluation data, generate appropriate career paths, and create proposals.

[0509] Step 10:

[0510] Career path proposal adjustment phase

[0511] Server: Uses an emotion engine to tailor career path suggestions based on the user's emotional state. For example, if the user is feeling anxious, add a "training session for a smooth transition."

[0512] Input: Generated career path suggestions, analyzed emotional states

[0513] Output: Tailored career path suggestions

[0514] Specific operation: Based on the results of the sentiment analysis, the content of the career path is modified as appropriate and the final proposal is generated.

[0515] Step 11:

[0516] Career path submission phase

[0517] Server: Sends the generated career path proposal to the terminal.

[0518] Input: Tailored career path proposals

[0519] Output: Career path proposal sent to the device

[0520] Specific operation: Sends data from the server to the device and displays a notification on the device.

[0521] Step 12:

[0522] Career path display phase

[0523] Terminal: Display career path suggestions and make them available for user review.

[0524] Input: Career path proposal sent from the server

[0525] Output: Displayed career path suggestions

[0526] Specific operation: The career path suggestions are displayed on the device's user interface and notified to the user.

[0527] 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.

[0528] 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.

[0529] 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.

[0530] [Second embodiment]

[0531] FIG. 3 shows an example of the configuration of a data processing system 210 according to the second embodiment.

[0532] 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.

[0533] 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).

[0534] 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.

[0535] 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.

[0536] 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).

[0537] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 are responsible for the exchange of various information between the processor 46 and the processor 28 via the network 54. The exchange of various information between the processor 46 and the processor 28 using the communication I / Fs 44 and 26 is carried out in a secure state.

[0538] 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.

[0539] 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.

[0540] 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.

[0541] In the smart glasses 214, the reception output process is performed by the processor 46. A reception output program 60 is stored in the storage 50. The processor 46 reads the reception output program 60 from the storage 50 and executes the read reception output program 60 on the RAM 48. The reception output process is realized by the processor 46 operating as the control unit 46A in accordance with the reception output program 60 executed on the RAM 48.

[0542] 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."

[0543] This invention is a human resource development support system that collects and processes data such as employee daily reports, evaluation sheets, and human resource development charts, and then provides feedback and career path suggestions based on that data. This system is comprised of a server, terminals, and users, and these elements work together to collect and process data, generate feedback, and suggest career paths.

[0544] System configuration

[0545] Server: Mainly responsible for collecting and processing data, generating feedback, and proposing career paths.

[0546] Terminal: The user's interface, where they enter daily reports, check feedback, and select their career path.

[0547] Users: Employees and managers who use the system.

[0548] Overview of program processing

[0549] 1. Data Collection Phase

[0550] Terminal: The user enters a daily work report and sends the data to the server. For example, the user enters "Completed task A and worked on project B."

[0551] Server: Receives daily report data and stores it in a database.

[0552] 2. Data Processing Phase

[0553] Server: Performs data cleansing and preprocessing, converting collected daily report data and past evaluation materials into a unified format. For example, it corrects inconsistent data and imputes missing values.

[0554] Server: Uses trained assessment models to prepare feedback and career path suggestions based on data.

[0555] 3. Feedback generation phase

[0556] Server: Inputs daily report data into the trained evaluation model and generates feedback based on common criteria. For example, it generates comments about the user's work achievements and areas for improvement.

[0557] Server: Stores the generated feedback and prepares it for transmission to the user's device.

[0558] 4. Feedback provision phase

[0559] Server: Sends feedback and notifies the user's device.

[0560] Terminal: User sees feedback.

[0561] User: Consider ways to improve their work based on the feedback provided. For example, consider specific actions such as "Maybe I should spend a little more time on the next task C."

[0562] 5. Career path proposal phase

[0563] Server: Analyzes the evaluation data and suggests optimal career paths based on the employee's past evaluation results and career goals. For example, it generates a message such as, "Based on User A's technical skills and evaluation, we recommend promotion to project manager."

[0564] Server: Sends career path suggestions to the user's device.

[0565] Terminal: User reviews career path suggestions and is offered options.

[0566] User: Review the proposed career paths and select the most suitable plan. Users can make future career plans based on the career paths provided.

[0567] Specific examples

[0568] Data Collection Phase

[0569] Terminal: User enters daily report. Example: "I completed task A and started working on new project B."

[0570] Server: Receives the data and stores it in a database.

[0571] Data Processing Phase

[0572] Server: Cleanses and pre-processes the collected daily report data. For example, record that task A is completed and new project B has started.

[0573] Server: Analyzes the data using the trained evaluation model.

[0574] Feedback generation phase

[0575] Server: Generates feedback. Example: "User A completes Task A efficiently and transitions quickly to new work."

[0576] Feedback provision phase

[0577] Server: Sends the generated feedback to the device.

[0578] Terminal: Show feedback and notify the user.

[0579] User: Review the feedback and decide on the next action.

[0580] Career path proposal phase

[0581] Server: Suggests optimal career paths. Example: "Based on the evaluation results of User A, we recommend promotion to project manager."

[0582] Terminal: Displays suggestions and gives the user choices.

[0583] User: Review the proposals and choose the most suitable career plan.

[0584] In this way, the system can efficiently evaluate employees and create career paths, ensuring transparency and consistency.

[0585] The processing flow will be explained below.

[0586] Step 1:

[0587] Terminal: The user enters a daily work report. The user fills in the input form in detail with the work content, progress, and any issues that have arisen that day. For example, the user might write, "I have completed Task A and started working on Project B."

[0588] Step 2:

[0589] Terminal: Sends the entered daily report data to the server. Once the entry is complete, the daily report data is automatically sent to the server. Data is transferred in real time using a communication protocol.

[0590] Step 3:

[0591] Server: Receives daily report data and stores it in a database. The server analyzes the received data and stores it in the database in an appropriate format. At this time, validation is performed to ensure the consistency and completeness of the data.

[0592] Step 4:

[0593] Server: Performs data cleansing and preprocessing. Converts collected daily report data and past evaluation materials into a unified format and corrects errors and inconsistencies. For example, fills in missing values ​​and standardizes data.

[0594] Step 5:

[0595] Server: Analyzes the data using a trained evaluation model. The cleansed data is input into the evaluation model, preparing it for feedback. This model is trained on past data, enabling highly accurate evaluation.

[0596] Step 6:

[0597] Server: Generates feedback. Based on the trained evaluation model, the server automatically generates feedback on employees' work performance and areas for improvement. For example, it generates specific comments such as, "User A completed Task A efficiently and is recognized for quickly transitioning to new tasks."

[0598] Step 7:

[0599] Server: Stores the generated feedback and prepares it for transmission to the user's device. The feedback is temporarily stored in a database and then transmitted to the user's device in an appropriate format.

[0600] Step 8:

[0601] Server: Sends feedback to the user's device. The sent feedback is delivered to the device so that the user can check it.

[0602] Step 9:

[0603] Device: The user receives and checks the feedback. The user opens the feedback message on the device and checks its contents. For example, the user may consider taking specific actions, such as "Maybe I should spend a little more time on the next task C."

[0604] Step 10:

[0605] Server: Analyzes assessment data to generate career path suggestions. Designs optimal career paths based on the user's past assessment results, skill sets, career goals, etc. This analysis creates a long-term career plan for the user.

[0606] Step 11:

[0607] Server: Sends the career path proposal to the user's device. The generated career path proposal is sent to the user's device, where the user can check it.

[0608] Step 12:

[0609] Device: The user receives and confirms the career path proposal. The user reviews the proposal displayed on the device in detail and considers their career options.

[0610] Step 13:

[0611] User: Selects his / her own career plan based on the proposed career paths. The user considers the suggestions, selects the most suitable career path, and decides on the next step. For example, if the proposed career path is promotion to project manager, the user creates an action plan to achieve that goal.

[0612] Example 1

[0613] 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."

[0614] In conventional employee evaluation systems, information such as daily report data and evaluation sheets was not managed in a unified format, making data cleansing and preprocessing cumbersome. Furthermore, feedback was not automatically generated using a trained evaluation model, placing a heavy burden on administrators. Furthermore, there was a lack of support for users to consider work improvement measures based on their own feedback. This resulted in a lack of transparency and consistency in employee evaluations, making it difficult to suggest optimal career paths.

[0615] 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.

[0616] In this invention, the server includes means for collecting data such as users' daily report data, evaluation sheets, and development charts in a database, means for cleansing and preprocessing the collected data, means for generating feedback for the user using a trained evaluation model, means for transmitting the generated feedback to the user's terminal, means for proposing a career path based on the user's past evaluation results and career goals, and means for considering business improvement measures based on the user's feedback. This significantly improves the transparency and consistency of user evaluations, enabling effective feedback and the suggestion of appropriate career paths.

[0617] A "user" is an individual or organizational member who uses the system to enter daily report data and receive feedback.

[0618] "Daily report data" is information that a user inputs to report daily work content and progress.

[0619] An "evaluation sheet" is a document or table used to evaluate a user's work performance, behavior, etc.

[0620] A "development chart" is a document or database that keeps records for users' ability development and skill improvement.

[0621] A "database" is a digital storage system for efficiently storing, managing, and retrieving collected data.

[0622] "Cleansing" is a process of removing inconsistencies and unnecessary information from collected data to improve the quality of the data.

[0623] "Preprocessing" refers to the preparation of data to convert it into a format suitable for analysis or model input.

[0624] An "assessment model" is a set of algorithms that uses training data to evaluate a user's job performance and generate feedback.

[0625] "Feedback" refers to comments and advice regarding the user's business achievements and areas for improvement, which are generated from the evaluation model.

[0626] A "career path" is a plan of future jobs and roles suggested based on a user's past work performance and career goals.

[0627] "Business improvement measures" are specific actions or methods that users should take in their next business operation based on the feedback.

[0628] This system allows users to collect data such as daily reports, evaluation sheets, and development charts, cleanses and preprocesses the data, generates feedback using a trained evaluation model, and suggests career paths for users. This system consists of three main components: a server, a terminal, and a user.

[0629] server

[0630] The server is the core of this system and plays the following roles:

[0631] Data collection and storage: The server receives the daily report data, evaluation sheets, and development charts entered by the user and stores them in a database. Specifically, MySQL or PostgreSQL is used as the database.

[0632] Data cleansing and preprocessing: To ensure data consistency, use scripts such as Python or R to correct inconsistent data and impute missing values.

[0633] Execution of the evaluation model: The trained evaluation model is built using scikit-learn and TensorFlow, and is used to generate feedback based on the user's performance and areas for improvement.

[0634] Feedback and career path generation: The generated feedback and career path suggestions are stored in a database and prepared for transmission to the user's device.

[0635] Terminal

[0636] The terminal provides an interface for users to input daily report data and check feedback and career paths. It has the following functions:

[0637] Data entry and transmission: Users use a device (PC or tablet) to enter daily report data through a dedicated web application and send it to the server. Communication is carried out using the HTTPS protocol.

[0638] Show Feedback: Displays the feedback received from the server for the user to review.

[0639] Review Career Paths: Display suggested career paths and allow users to review and select.

[0640] User

[0641] Users use the system to input daily report data, receive feedback, and consider their career paths. The specific operations are as follows:

[0642] Entering daily report data: The user enters work details into an input form on the terminal, such as "Completed task A and worked on project B."

[0643] Review feedback: The user reviews the feedback received from the server and considers improvements.

[0644] Career path selection: Based on the career paths provided, select the most suitable career plan and make future plans.

[0645] Specific examples

[0646] Entering daily report data

[0647] The user accesses the web application on the terminal and enters the daily report data.

[0648] For example: "I completed task A and started working on new project B."

[0649] Generate feedback

[0650] The server generates feedback using the trained evaluation model.

[0651] For example: "User A completes Task A efficiently and transitions quickly to new tasks."

[0652] Career path suggestions

[0653] The server suggests career paths based on the user's past evaluation results and career goals.

[0654] Example: "Based on the results of User A's evaluation, I would like to recommend promotion to Project Manager."

[0655] Examples of prompt statements

[0656] "User A's daily report data: Completed Task A and started working on Project B. Past evaluation: Good. Areas for improvement: Needs detailed project plan." Use this daily report data to generate feedback and career path suggestions.

[0657] As described above, the system provides an efficient process for consistently conducting employee evaluations and career path proposals, ensuring transparency and consistency.

[0658] The flow of the identification process in the first embodiment will be described with reference to FIG.

[0659] Step 1: Data collection

[0660] On the device, the user opens a dedicated web application and enters daily report data. Input items include the completion status of tasks and details of projects worked on. For example, the user might enter, "Completed Task A and worked on Project B."

[0661] Input: User's daily report data (Task A completed, Project B started)

[0662] Output: Sending daily report data to the server

[0663] Step 2: Send and store data

[0664] Terminal: The entered daily report data is sent to the server via the HTTPS protocol. The user clicks the "Send" button, and the data is transferred to the server.

[0665] Input: User's daily report data

[0666] Output: Daily report data sent to the server

[0667] Server: The received daily report data is saved in a database (e.g., MySQL, PostgreSQL). The database stores information such as the date, user ID, and task ID as records.

[0668] Input: Daily report data sent from the terminal

[0669] Output: Daily report data stored in the database

[0670] Step 3: Data cleansing and preprocessing

[0671] Server: Using Python and R scripts, the incoming daily report data is cleansed and inconsistencies and missing values ​​are corrected, for example, to standardize date formats and add specific tagging.

[0672] Input: Saved daily report data

[0673] Output: Cleansed and preprocessed data

[0674] Step 4: Run the evaluation model

[0675] Server: Analyzes the pre-processed data using a trained evaluation model (e.g., scikit-learn, TensorFlow). This model generates feedback based on the user's performance and areas for improvement.

[0676] Input: Cleansed and preprocessed data

[0677] Output: Generated feedback

[0678] Step 5: Generate and save your feedback

[0679] Server: Stores the generated feedback in a database. Feedback is managed for each user and stored for review.

[0680] Input: Feedback generated from the evaluation model

[0681] Output: Feedback stored in a database

[0682] Step 6: Submit your feedback

[0683] Server: Sends the saved feedback to the user's device via HTTPS protocol, and the feedback is ready for the user to receive.

[0684] Input: Feedback stored in the database

[0685] Output: Feedback sent to the user's device

[0686] Step 7: View your feedback

[0687] On the device: The user opens the application to view the feedback. The feedback is displayed in a list format. The user receives a notification and can view the details.

[0688] Input: Notification that feedback was received

[0689] Output: Feedback displayed on the terminal

[0690] Step 8: Analyze and generate career paths

[0691] Server: Based on the user's past evaluation data and career goals, the server proposes a career path that combines the evaluation data and goals. To this end, it analyzes data collected in advance and generates an optimal career plan.

[0692] Input: Past evaluation data, career goals

[0693] Output: Generated career path suggestions

[0694] Step 9: Submit and view your career path

[0695] Server: The generated career path is sent to the user's device using the HTTPS protocol, allowing the user to check the career path after it has been sent.

[0696] Input: Generated career path proposal

[0697] Output: Career path proposal sent to the user device

[0698] On the device: The user opens the application to view the career path suggestions and explore their options. Career paths are displayed in a dedicated section of the dashboard.

[0699] Input: Career path proposal

[0700] Output: Career path suggestions displayed on the device

[0701] Step 10: Consider business improvement measures

[0702] Users: Based on the feedback and career path suggestions, users consider ways to improve their work and decide on specific actions to take to plan their next work or personal development.

[0703] Input: Feedback and career path suggestions displayed

[0704] Output: Considered business improvement measures and career plans

[0705] In this way, through a series of processing steps, this system can efficiently generate evaluations and career plans from users' daily report data, ensuring transparency and consistency.

[0706] (Application example 1)

[0707] 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."

[0708] Current human resource development support systems mainly focus on evaluating employee performance and proposing career paths in office work, but do not address the evaluation and career development of operators engaged in practical work in factories. As a result, there is a lack of means to efficiently support factory operators in improving their skills and building their career paths. To solve this problem, a system is needed to collect, evaluate, and provide feedback on the work data of factory operators.

[0709] 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.

[0710] In this invention, the server includes means for collecting data such as employee daily report data, evaluation sheets, and human resource development charts in a database, means for cleansing and preprocessing the collected data, means for generating feedback for employees using a trained evaluation model, means for sending the generated feedback to the employee's terminal, means for proposing a career path based on the employee's past evaluation results and career goals, means for collecting factory robot operation data and operator daily work reports, means for preprocessing the collected robot operation data and providing feedback to the operator, and means for proposing improvements to robot operation skills based on the operator's evaluation results. This makes it possible to improve the skills of factory operators and create career paths.

[0711] "Employee daily report data" refers to data about the progress of work and completed tasks that employees record in their daily work reports.

[0712] An "evaluation sheet" is a written or electronic format for recording an employee's performance evaluation or performance rating.

[0713] A "human resources development chart" is a database that records employees' past evaluation results and education and training history.

[0714] "Data cleansing" is the process of improving data quality by correcting inconsistent data, filling in missing values, etc.

[0715] "Preprocessing" is the process of converting data into a format suitable for input into data analysis or machine learning models.

[0716] A "trained evaluation model" is an analytical model that has been trained by a machine learning algorithm using historical data.

[0717] "Feedback generation" is a process that generates written recommendations for improvement and evaluation results for employees based on evaluation data.

[0718] "Feedback transmission" is the process of sending the generated feedback to the employee's terminal.

[0719] "Career path proposal" is a process that suggests the next job or position an employee should take based on their evaluation data and career goals.

[0720] "Factory robot operation data" refers to data related to the tasks and actions performed by robots used in factories.

[0721] The "operator's daily work report" is daily report data recorded by a factory operator regarding the work content and progress of the day.

[0722] "Improving robot operation skills" is the process of making suggestions and providing training to improve factory operators' robot operation capabilities based on evaluation data.

[0723] This invention is a system for supporting the operation of robots in factories and the training of their operators. This system is composed of a server, terminals, and user elements, which work together to collect and process data, generate feedback, and propose career paths.

[0724] System configuration

[0725] 1. Server: Responsible for collecting and processing data, generating feedback, and proposing career paths. Python and machine learning frameworks (TensorFlow, PyTorch) are used to run the program.

[0726] 2. Device: An interface where users can enter their daily reports and view feedback and career path suggestions. Devices include smartphones and smart glasses.

[0727] 3. Users: Factory operators and their managers who use the system.

[0728] Overview of program processing

[0729] 1. Data collection phase:

[0730] Terminal: The user inputs the daily work report and sends the data to the server. For example, the user inputs "Robot A has completed the inspection work and is now on the next manufacturing task."

[0731] Server: Receives daily report data and saves it in the database. The data format is JSON.

[0732] 2. Data Processing Phase:

[0733] Server: Performs data cleansing and preprocessing, converting collected daily work report data and past evaluation materials into a unified format. For example, it corrects inconsistent data and imputes missing values. It uses the Python pandas library.

[0734] Server: Uses the trained evaluation model to prepare feedback and career path suggestions based on the data. Uses scikit-learn to train the machine learning model.

[0735] 3. Feedback generation phase:

[0736] Server: Inputs the daily work report data into the trained evaluation model and generates feedback based on common criteria. For example, it generates comments about the user's work progress and areas for improvement.

[0737] Server: Stores the generated feedback and prepares it for transmission to the user's device.

[0738] 4. Feedback provision phase:

[0739] Server: Sends feedback and notifies the user's device.

[0740] Device: The user sees the feedback, which is displayed through a smartphone app or smart glasses.

[0741] User: Consider ways to improve their own work based on the feedback provided.

[0742] 5. Career path proposal phase:

[0743] Server: Analyzes the evaluation data and proposes the optimal career path based on the operator's past evaluation results and career goals. For example, it generates a message such as, "Based on the evaluation results of Operator A, we propose training in machine maintenance."

[0744] Server: Sends career path suggestions to the user's device.

[0745] Terminal: User reviews career path suggestions and is offered options.

[0746] User: Review the proposed career paths and select the most suitable plan. Users can make future career plans based on the career paths provided.

[0747] Example prompt sentence:

[0748] "Based on the operators' daily reports, generate feedback on their work performance and areas for improvement in their next assignment. Also, provide career path suggestions."

[0749] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[0750] Step 1:

[0751] Terminal: The user inputs the daily work report. Specifically, the user uses a smartphone or smart glasses to record the work details, such as "Robot A's inspection work has been completed and it has moved on to the next manufacturing task," and presses the send button. The data entered includes the work details, date, completion status, etc., and is sent to the server in JSON format. The output is the data sent to the server.

[0752] Step 2:

[0753] Server: Receives the sent daily work report data and saves it in a database. Specifically, the server parses the received JSON data and stores it in a database (e.g., MySQL, PostgreSQL). The input is the daily work report data sent from the terminal, and the output is the data saved in the database.

[0754] Step 3:

[0755] Server: Cleanses and preprocesses the daily report data. Specifically, it uses Python's pandas library to complement missing data and correct inconsistent data. The input is the daily work report data stored in the database, and the output is the data after cleansing and preprocessing.

[0756] Step 4:

[0757] Server: Using the trained evaluation model, analyze the daily work report data and prepare for feedback generation. Specifically, the preprocessed data is input into a machine learning model (e.g., scikit-learn's RandomForestRegressor) to predict the user's work achievement and areas for improvement. The input is the preprocessed daily work report data, and the output is the evaluation results necessary for feedback generation.

[0758] Step 5:

[0759] Server: Generates feedback using the trained evaluation model. Specifically, it generates feedback sentences based on the evaluation results and provides specific advice, such as "Operator A's task achievement rate is 80%. It would be desirable to shorten the inspection time a little more for the next task." The input is the evaluation results, and the output is the generated feedback sentences.

[0760] Step 6:

[0761] Server: Sends the generated feedback to the user's device. Specifically, it sends a message to a smartphone or smart glasses using an API for notifying the device of the feedback. The input is the generated feedback text, and the output is the feedback displayed on the user's device.

[0762] Step 7:

[0763] Device: The user checks the feedback. Specifically, the user clicks on the notification on the device to check the feedback content. Based on the information obtained from the feedback, an action plan for the next task is considered. The input is the feedback sent from the server, and the output is the user's action plan based on the feedback.

[0764] Step 8:

[0765] Server: Analyzes evaluation data and proposes career paths based on the operator's past evaluation results and career goals. Specifically, it uses evaluation data to generate career path options, proposing content such as "Based on the evaluation results of Operator A, we propose training in machine maintenance." The input is evaluation data, and the output is a written career path proposal.

[0766] Step 9:

[0767] Server: Sends career path suggestions to the user's device. Specifically, similar to feedback, it sends career path suggestions using an API to notify the device. The input is the career path suggestion text, and the output is the career path suggestion displayed on the user's device.

[0768] Step 10:

[0769] Device: The user reviews the career path proposals and selects the most suitable plan. Specifically, the user clicks on the notification on the device to review the career path proposals and decides whether to adopt them as their own career plan. The input is the career path proposal sent from the server, and the output is the career plan selected by the user.

[0770] 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.

[0771] This invention is a human resource development support system that collects and processes data such as employee daily reports, evaluation sheets, and human resource development charts, and provides feedback and career path suggestions. This system incorporates an emotion engine that recognizes the user's emotions, and individual feedback and career path suggestions are adjusted taking into account the user's emotional state.

[0772] System configuration

[0773] Server: Performs functions of data collection, processing, feedback generation, career path suggestions, and sentiment analysis.

[0774] Terminal: Functions as an interface with the user, allowing them to enter daily reports, display feedback, transmit emotional data, and select career paths.

[0775] Users: Employees and managers who use the system.

[0776] Emotion Engine: Recognizes user emotions and reflects them in feedback and career path suggestions.

[0777] Overview of program processing

[0778] 1. Data Collection Phase

[0779] Terminal: The user enters a work report, for example, "I completed task A and started working on project B."

[0780] Terminal: Daily report data is automatically sent to the server.

[0781] 2. Data Processing Phase

[0782] Server: Stores the received daily report data in a database and performs data cleansing and preprocessing, filling in missing values ​​and standardizing the data.

[0783] Server: Uses the trained evaluation model to prepare feedback and career path suggestions.

[0784] 3. Feedback generation phase

[0785] Server: Inputs daily report data into the evaluation model and generates feedback. For example, it creates specific comments such as "User A is highly evaluated because he completed Task A efficiently."

[0786] Server: Analyzes the user's emotional data using the emotion engine. Adjusts the feedback based on the user's emotional state. For example, if the user is feeling stressed, the server adds a comment to the feedback such as "Please reconsider your work balance and take a rest."

[0787] 4. Feedback provision phase

[0788] Server: Sends the generated feedback to the user's device.

[0789] Terminal: Display feedback so that the user can see it.

[0790] 5. Emotional Data Collection Phase

[0791] Terminal: Collects emotional data from user input and reactions. The emotional data is sent to the server in real time.

[0792] Emotion Engine: Analyzes the emotion data collected from the user and evaluates their current emotional state.

[0793] 6. Career path proposal phase

[0794] Server: Analyzes the evaluation data and suggests the best career path. For example, "Based on User A's past evaluation results and technical skills, we suggest promotion to project manager."

[0795] Server: Uses an emotion engine to tailor career path suggestions to the user's emotional state. For example, if the user is feeling anxious, the server might add "support systems" or "training programs" to the suggestions.

[0796] Server: Sends career path suggestions to the user's device.

[0797] Terminal: User reviews career path suggestions.

[0798] User: Select your own career plan based on the suggestions.

[0799] Specific examples

[0800] Data Collection Phase

[0801] Terminal: User enters daily report. Example: "I completed task A and started working on new project B."

[0802] Server: Receives the data and stores it in a database.

[0803] Data Processing Phase

[0804] Server: Cleanses and pre-processes the collected daily report data. For example, record that task A is completed and new project B has started.

[0805] Server: Analyzes the data using the trained evaluation model.

[0806] Feedback generation phase

[0807] Server: Generates feedback. Example: "User A completes Task A efficiently and transitions quickly to new work."

[0808] Server: Uses the emotion engine to analyze the user's emotional state and reflect it in the feedback. For example, if the user is feeling stressed, add a comment such as "Please reconsider your work balance and take a rest."

[0809] Feedback provision phase

[0810] Server: Sends the generated feedback to the device.

[0811] Terminal: Show feedback and notify the user.

[0812] User: Review the feedback and decide on the next action.

[0813] Career path proposal phase

[0814] Server: Suggests optimal career paths. Example: "Based on the evaluation results of User A, we recommend promotion to project manager."

[0815] Server: Uses an emotion engine to generate career path suggestions that reflect the user's emotional state. For example, if the user is feeling anxious, add "support systems" and "training programs" to the suggestions.

[0816] Device: Display the suggestion and make it available for the user to review.

[0817] User: Review the proposals and choose the most suitable career plan.

[0818] The processing flow will be explained below.

[0819] Step 1:

[0820] Terminal: The user enters a daily work report. The user fills in the input form on the terminal with details of the day's work, progress, and any issues they encountered. For example, they might write, "I completed task A and started working on a new project B."

[0821] Step 2:

[0822] Terminal: Sends the entered daily report data to the server. After input is complete, the daily report data is automatically sent to the server. Transmission is secure using encrypted communication protocols such as SSL.

[0823] Step 3:

[0824] Server: Receives daily report data and saves it in the database. The server converts the received daily report data into an appropriate format and stores it in the database. When saving, a validation check is performed to confirm the consistency of the data.

[0825] Step 4:

[0826] Server: Performs data cleansing and preprocessing. Corrects errors and inconsistencies in the collected daily report data and converts it into a unified format. For example, it fills in missing values ​​and standardizes date formats.

[0827] Step 5:

[0828] Server: Analyzes the data using a trained evaluation model. The cleansed data is fed into the evaluation model, preparing it for feedback generation. The model is trained using machine learning algorithms, enabling highly accurate evaluations.

[0829] Step 6:

[0830] Server: Works with the device to collect user emotion data. The emotion engine runs and collects user input and reactions, such as keystroke speed and back arching.

[0831] Step 7:

[0832] Emotion engine: Analyzes collected data and evaluates the user's emotional state. For example, if a user types faster than usual, it recognizes that the user is under stress.

[0833] Step 8:

[0834] Server: The emotion data obtained from the emotion engine is reflected in the evaluation model and feedback is generated. For example, if a user is under stress, a comment such as "Please reconsider your work balance and take some rest" is added.

[0835] Step 9:

[0836] Server: Stores the generated feedback in a database and prepares it for transmission to the user's device.

[0837] Step 10:

[0838] Server: Sends the generated feedback to the user's device. Uses a notification system to notify the user that the feedback has arrived.

[0839] Step 11:

[0840] Terminal: Feedback is displayed and made available for the user to check. The user can check the feedback on their terminal and use it to improve their own work.

[0841] Step 12:

[0842] Server: Proposes optimal career paths based on evaluation data. Generates career paths taking into account past evaluation results, the user's skill set, and long-term career goals.

[0843] Step 13:

[0844] Server: Adjust the career path suggestions based on the results of the emotion engine. For example, if the user feels anxious, add support systems or training programs to the suggestions.

[0845] Step 14:

[0846] Server: Sends tailored career path proposals to the user's device.

[0847] Step 15:

[0848] Device: The career path proposal is displayed and made available for the user to review. The user reviews the proposal in detail and considers their own career plan.

[0849] Step 16:

[0850] User: Selects his / her own career plan based on the suggested career paths. The user considers the suggestions and selects the most suitable career path. For example, if a promotion to project manager is proposed, the user creates an action plan for that promotion.

[0851] Example 2

[0852] 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."

[0853] Although conventional human resource management systems can collect employee daily report data and evaluation sheets, they do not take into account the emotional state of each employee when making feedback or career path suggestions, which means that employee motivation and performance cannot be optimized, limiting the efficiency of the organization as a whole.In addition, because employee career path suggestions are standardized, flexible suggestions based on the characteristics and goals of each employee cannot be made.

[0854] The specific processing by the specific processing unit 290 of the data processing device 12 in the second embodiment is realized by the following means.

[0855] In this invention, the server includes a means for collecting data such as employee daily reports, evaluation sheets, and human resource development charts in a database, a means for cleansing and preprocessing the collected data, a means for generating feedback for employees using a trained evaluation model, a means for analyzing user emotion data and adjusting the feedback and career path suggestions, and a means for sending the generated feedback to the employee's terminal. This enables flexible and appropriate feedback and career path suggestions that take into account the emotional state of each employee.

[0856] A "database" is a system for storing, managing, and searching data in an organized manner.

[0857] "Data cleansing" is the process of filling in missing values, correcting inaccurate data, and standardizing it.

[0858] "Preprocessing" refers to the preparatory work done before inputting data into data analysis or machine learning models, and includes data formatting and normalization.

[0859] An "evaluation model" is a trained algorithm that evaluates employee performance based on input data and generates feedback.

[0860] "Feedback" refers to evaluations and comments on employees' performance, with the aim of improving work and increasing motivation.

[0861] "Emotional data" is data used to measure and analyze a user's emotional state, and is collected from the user's input, reactions, etc.

[0862] A "career path" is the path of goals and positions that an employee should pursue within a company, including plans for growth and promotion.

[0863] The "Emotion Engine" is a system that analyzes users' emotional data and reflects it in feedback and career path suggestions.

[0864] "Collection means" refers to the method or system for collecting daily report data, evaluation sheets, etc. into a database.

[0865] "Cleansing and preprocessing means" refers to methods and systems used to prepare collected data and make it suitable for analysis.

[0866] "Feedback generator" means a method or system for generating ratings and comments for employees using a trained rating model.

[0867] "Emotion data analysis means" refers to a method or system for analyzing a user's emotional data and reflecting the results in feedback and career path suggestions.

[0868] "Transmission means" refers to a method or system for sending the generated feedback and career path suggestions to the employee's terminal.

[0869] This invention relates to a human resource development support system that collects and processes data such as employee daily reports, evaluation sheets, and human resource development charts, and provides feedback and career path suggestions. This system incorporates an emotion engine that recognizes the user's emotions, and the feedback and career path suggestions are adjusted taking into account the user's emotional state.

[0870] System configuration

[0871] Server: Performs functions such as data collection, processing, feedback generation, career path suggestions, and sentiment analysis. The server can utilize cloud-based infrastructure (e.g., AWS, Google Cloud).

[0872] Terminal: Functions as an interface with the user, allowing them to input daily reports, display feedback, transmit emotional data, and select career paths. Terminals include, for example, personal computers and smartphones.

[0873] Users: Employees and managers who use the system.

[0874] Emotion engine: Recognizes the user's emotions and reflects them in feedback and career path suggestions. For example, the IBM Watson Tone Analyzer can be used as an emotion engine.

[0875] Data collection

[0876] The terminal provides an interface for users to input daily work reports. The daily report data entered by the user is sent from the terminal to a server. The transmission is secure using a security protocol (e.g., HTTPS). The server stores the received daily report data in a database. This database uses a database management system such as "PostgreSQL."

[0877] Data Processing

[0878] The server cleanses and preprocesses the daily report data stored in the database. This process includes filling in missing values ​​and standardizing the data. Cleansing and preprocessing improves the accuracy and reliability of the data. A trained evaluation model can be built using TensorFlow, for example. The daily report data is input into this evaluation model and analyzed.

[0879] Feedback Generation

[0880] The server creates feedback based on the data generated by the evaluation model. For example, it generates a comment such as, "Employee A is highly evaluated because he completed Task A efficiently." The server also analyzes the user's emotional data using an emotion engine and adjusts the content of the feedback. For example, if the user is feeling stressed, it adds a comment such as, "It is recommended that you reconsider your work balance and take a rest."

[0881] Providing Feedback

[0882] The server sends the generated feedback to the user's device. For example, a notification service such as Firebase Cloud Messaging can be used for this purpose. The device displays the feedback and notifies the user.

[0883] Emotional Data Collection

[0884] The device collects emotional data from the user's input and reactions, which is then sent to a server in real time and analyzed by an emotion engine.

[0885] Career path suggestions

[0886] The server proposes optimal career paths based on the collected and analyzed evaluation data. For example, it generates a proposal such as, "Based on Employee A's past evaluation results and technical skills, we propose promotion to project manager." The server can also use an emotion engine to adjust the proposal content according to the user's emotional state. For example, if the user is feeling anxious, it can add a "support system" or "training program" to the proposal. The career path proposal is sent to the terminal, and the user can select their own career plan based on the proposal.

[0887] Specific examples

[0888] For example, a user enters a daily report stating, "I completed Task A and started working on new Project B." This data is sent to the server via the device and stored in a database. The server cleanses and preprocesses the data, inputs it into an evaluation model, and generates feedback. The generated feedback might be, "User A completed Task A efficiently and is moving quickly to new work." Furthermore, if the user is determined to be feeling stressed, a comment such as, "Please reconsider your work balance and take a rest" is added.

[0889] Prompt Sentence Examples

[0890] "Please explain the program of a system that generates feedback based on employees' daily report data and suggests career paths that reflect the user's emotional state. Please explain the process in detail using specific examples."

[0891] This system enables flexible and appropriate feedback and career path suggestions that take into account employees' emotional state, which is expected to improve efficiency and motivation throughout the organization.

[0892] The flow of the identification process in the second embodiment will be described with reference to FIG.

[0893] Step 1:

[0894] The user inputs a daily work report. The user uses a terminal to input daily report data, such as "Task A completed and started working on new project B." Once input is complete, the data is automatically sent from the terminal to the server.

[0895] Step 2:

[0896] The terminal sends the daily report data to the server. A security protocol (e.g. HTTPS) is used for transmission, and the data is transferred safely. Terminal input: Daily report data entered by the user. Output: Daily report data sent.

[0897] Step 3:

[0898] The server stores the received daily report data in a database. For example, "PostgreSQL" is used as the database. Server input: Daily report data sent from the terminal. Output: Daily report data stored in the database.

[0899] Step 4:

[0900] The server performs data cleansing and preprocessing. The server fills in any missing values ​​in the daily report data and standardizes the data. Server input: Daily report data read from the database. Output: Data after cleansing and preprocessing.

[0901] Step 5:

[0902] The server analyzes the data using a trained evaluation model, for example, a model built using TensorFlow. Server input: cleansed and preprocessed data. Output: analysis results.

[0903] Step 6:

[0904] The server generates feedback based on the data generated by the evaluation model. For example, it generates specific comments such as "Employee A is highly evaluated because he completed task A efficiently." Server input: Analysis results. Output: Generated feedback.

[0905] Step 7:

[0906] The server uses an emotion engine to analyze the user's emotion data and adjust the feedback content. The emotion engine used is something like "IBM Watson Tone Analyzer." For example, if the user is feeling stressed, it adds a comment saying, "We recommend that you reconsider your work balance and take a rest." Server input: Feedback and emotion data. Output: Adjusted feedback.

[0907] Step 8:

[0908] The server sends the generated feedback to the user's device. This is done using a notification service such as Firebase Cloud Messaging. Server input: Adjusted feedback. Output: Feedback sent to the user's device.

[0909] Step 9:

[0910] The device displays feedback and notifies the user. Notifications can be done using popup messages or in-app notifications. Device input: Feedback sent from the server. Output: Feedback displayed to the user.

[0911] Step 10:

[0912] The user checks the feedback on the device, and as a next step, decides on the next action and reflects it in their work.

[0913] Step 11:

[0914] The device collects emotional data from the user's input and reactions. Emotional data is collected using the user's keystroke analysis and screen touch data. Device input: User's input and reactions. Output: Collected emotional data.

[0915] Step 12:

[0916] The device sends the collected emotion data to the server in real time. Device input: Collected emotion data. Output: Emotion data sent to the server.

[0917] Step 13:

[0918] The emotion engine analyzes the user's emotional state on the server and records it in the emotion database. The analysis results are used as feedback for the generative AI model. Server input: collected emotion data. Output: analysis results and recorded emotion data.

[0919] Step 14:

[0920] The server analyzes the user's daily report data and past evaluation data to propose the optimal career path. For example, it generates a proposal such as "Based on the evaluation results of employee A, recommend promotion to project manager." Server input: Daily report data and past evaluation data. Output: Career path proposal.

[0921] Step 15:

[0922] The server uses an emotion engine to adjust the career path suggestions to fit the user's emotional state. For example, if the user is feeling anxious, the suggestions will be adjusted to include "support systems" and "training programs." Server input: Career path suggestions and emotion data. Output: Adjusted career path suggestions.

[0923] Step 16:

[0924] The server sends the career path proposal to the user's device. Server input: Adjusted career path proposal. Output: Career path proposal sent to the user's device.

[0925] Step 17:

[0926] The terminal displays the career path proposal for the user to review. Terminal input: Career path proposal sent from the server. Output: Career path proposal displayed to the user.

[0927] Step 18:

[0928] The user checks the career path suggestions on the terminal and selects the most suitable career plan. The selected career plan is sent back to the server and recorded in the database. User input: Career plan selection. Output: Selected career plan sent to the server.

[0929] The above is the specific processing flow of the program of this system.

[0930] (Application example 2)

[0931] 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."

[0932] While conventional human resource development support systems can provide feedback based on employee daily reports and evaluations, they lack the ability to provide feedback and career path suggestions that take into account employees' emotional states and the operation data of the machines used on-site. Furthermore, particularly in manufacturing sites, they are unable to provide feedback or career path suggestions that include production data and error history from machines such as robots, making it difficult to efficiently manage personnel and machines and improve their performance. Another problem is the inability to analyze emotional data collected in real time and adjust feedback accordingly.

[0933] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 2 is realized by the following means.

[0934] In this invention, the server includes means for collecting employee daily report data, evaluation sheets, human resource development charts, product production data, error history, and operator feedback data in a database, means for cleansing and preprocessing the collected data, means for generating feedback for employees and machines using a trained evaluation model, means for transmitting the generated feedback to the terminals of the employees and machine operators, means for proposing career paths for the employees and machine operators based on their past evaluation results and career goals, means for collecting and analyzing emotional data for the machine operators in real time, and means for adjusting the feedback and career path proposals based on their emotional states. This enables efficient feedback and career path proposals that take into account the emotional states of the employees and machine operators and the machine's production data.

[0935] "Employee daily report data" refers to data in which employees record their daily work progress and completed tasks.

[0936] An "appraisal sheet" is a written or electronic format used for the purpose of evaluating an employee's performance or skills.

[0937] A "human resources development chart" is a data sheet that records an employee's skills, career path, training history, etc.

[0938] "Product production data" refers to data that records the work content and production results of machines and robots used in manufacturing sites.

[0939] "Error history" is data that records details of errors and malfunctions that occur during manufacturing processes or machine operation.

[0940] "Operator feedback data" is data that records opinions and evaluations submitted by employees in charge of operating machines or robots regarding their work.

[0941] "Means of collecting data in a database" refers to functions and systems for organizing various data and storing it centrally.

[0942] "Data cleansing and preprocessing means" refers to functions and systems that perform preprocessing to improve data quality, such as filling in missing data values ​​and removing outliers.

[0943] A "trained evaluation model" is an algorithm or system that learns from past data and predicts and evaluates the performance of employees or machines.

[0944] "Means for generating feedback" refers to functions or systems for providing appropriate advice and areas for improvement based on the evaluation results.

[0945] The "means for sending feedback" refers to a communication function or system for delivering the generated feedback to the terminals of employees or operators.

[0946] "Means for suggesting career paths" are functions or systems that show employees and operators the optimal career path based on their past performance and goals.

[0947] "Means for collecting and analyzing emotional data in real time" refers to functions and systems for obtaining the emotional state of employees and operators in a timely manner and analyzing that data.

[0948] The "means for adjusting feedback and career path suggestions based on emotional state" refers to a function or system that optimizes the content of feedback and career path suggestions based on analyzed emotional data.

[0949] This invention is a system for collecting and processing employee daily report data, evaluation sheets, human resource development charts, product production data, error history, and operator feedback data, and providing feedback and career path suggestions. This system includes an emotion engine that analyzes emotional states and reflects them in feedback and career path suggestions.

[0950] The main components of the system are as follows:

[0951] Server: Responsible for data collection, data cleansing, pre-processing, feedback generation, career path suggestions, and sentiment analysis.

[0952] Terminal: Serves as an interface with the user, allowing them to enter daily reports, view feedback, send emotional data, and select career paths.

[0953] Users: Employees and machine operators who use the system.

[0954] Emotion Engine: Recognizes user emotions and reflects them in feedback and career path suggestions.

[0955] The system first collects daily report data and feedback data from employees and operators via their terminals and sends it to the server. The server stores the received data in a database and performs data cleansing and preprocessing. This process is performed using the Python pandas library, for example, by filling in missing values ​​and standardizing the data. Next, the trained evaluation model is used to generate feedback for employees and machine operators. The scikit-learn library is used to train the evaluation model.

[0956] The generated feedback is sent from the server to the device and displayed for the user to review. For example, if an employee enters "I completed Task A and started working on new Project B," the feedback displayed will read, "I commend you for completing Task A efficiently and moving quickly to new work."

[0957] The emotion engine also analyzes the user's emotional state and adjusts the feedback accordingly. For example, if the user is feeling stressed, it might add a comment like, "Reconsider your work balance and take a break." The nltk library is used to analyze emotion data. In particular, the nltk.sentiment library is used for emotion analysis.

[0958] Furthermore, the server suggests career paths based on the user's past evaluation results and career goals. For example, it might suggest, "Based on User A's past evaluation results, we suggest transitioning to a new position exclusively for Process Z." The content of this suggestion is also adjusted according to the user's emotional state. For example, if the user is feeling anxious, it might add a "training session for a smooth transition."

[0959] As a concrete example, when a user inputs a daily report, the prompt may be something like, "Please write specifically about today's work. For example, the robot frequently produced errors, but the cause was identified and corrected." This prompt is important for maintaining consistency in the input data.

[0960] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[0961] Step 1:

[0962] Data Collection Phase

[0963] Terminals: Users (employees and machine operators) enter daily report data and feedback data. For example, an employee may enter "I have completed task A and started working on new project B."

[0964] Input: Daily report data, feedback data

[0965] Output: Raw data collected

[0966] Specific operation: When a user enters data using a dedicated application and presses the "Submit" button, the data is sent to the server in real time.

[0967] Step 2:

[0968] Data transmission phase

[0969] Terminal: Automatically sends collected daily report data and feedback data to the server.

[0970] Input: Raw data collected

[0971] Output: Data sent to the server

[0972] Specific operation: The terminal uploads data to the server via the network and stores it in the database.

[0973] Step 3:

[0974] Data cleansing and preprocessing phase

[0975] Server: Cleanses and preprocesses the received data, specifically filling in missing values ​​and standardizing the data.

[0976] Input: Data stored on the server

[0977] Output: Preprocessed and clean data

[0978] Specific operation: Create a data frame using Python's pandas library, impute missing values, and standardize.

[0979] Step 4:

[0980] Feedback generation phase

[0981] Server: Uses the trained evaluation model to generate feedback, such as "User A completed task A efficiently and therefore deserves high praise."

[0982] Input: Preprocessed and clean data

[0983] Output: Generated feedback

[0984] What it does: Uses the scikit-learn library to input data into an evaluation model and generate feedback based on the prediction results.

[0985] Step 5:

[0986] Sentiment Analysis Phase

[0987] Server: Uses an emotion engine to analyze the emotional state from the user's input and reactions.

[0988] Input: User input data, response data

[0989] Output: Parsed emotional state

[0990] Specific operation: Analyzes emotional states using the nltk.sentiment module of the nltk library.

[0991] Step 6:

[0992] Feedback Adjustment Phase

[0993] Server: Adjust the feedback based on the analyzed emotional state. For example, if the user is feeling stressed, add a comment like "Please rebalance your work and take some rest."

[0994] Input: Generated feedback, parsed emotional state

[0995] Output: Regulated Feedback

[0996] Specific operation: Using the results of sentiment analysis, the feedback content is modified appropriately and the final feedback sentence is generated.

[0997] Step 7:

[0998] Feedback sending phase

[0999] Server: Sends the generated feedback to the user's device.

[1000] Input: Calibrated Feedback

[1001] Output: Feedback sent to the terminal

[1002] Specific operation: Sends data from the server to the device and displays a notification on the device.

[1003] Step 8:

[1004] Feedback display phase

[1005] Terminal: Display feedback so that the user can see it.

[1006] Input: Feedback sent by the server

[1007] Output: Displayed feedback

[1008] Specific operation: The feedback content is displayed on the device's user interface and the user is notified.

[1009] Step 9:

[1010] Career path proposal phase

[1011] Server: Proposes a career path based on the user's past evaluation results and career goals. For example, "Based on User A's past evaluation results, we propose a transition to a new, dedicated role in Process Z."

[1012] Input: User's past evaluation results, career goals

[1013] Output: Generated career path suggestions

[1014] Specific actions: Analyze evaluation data, generate appropriate career paths, and create proposals.

[1015] Step 10:

[1016] Career path proposal adjustment phase

[1017] Server: Uses an emotion engine to tailor career path suggestions based on the user's emotional state. For example, if the user is feeling anxious, add a "training session for a smooth transition."

[1018] Input: Generated career path suggestions, analyzed emotional states

[1019] Output: Tailored career path suggestions

[1020] Specific operation: Based on the results of the sentiment analysis, the content of the career path is modified as appropriate and the final proposal is generated.

[1021] Step 11:

[1022] Career path submission phase

[1023] Server: Sends the generated career path proposal to the terminal.

[1024] Input: Tailored career path proposals

[1025] Output: Career path proposal sent to the device

[1026] Specific operation: Sends data from the server to the device and displays a notification on the device.

[1027] Step 12:

[1028] Career path display phase

[1029] Terminal: Display career path suggestions and make them available for user review.

[1030] Input: Career path proposal sent from the server

[1031] Output: Displayed career path suggestions

[1032] Specific operation: The career path suggestions are displayed on the device's user interface and notified to the user.

[1033] 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.

[1034] 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.

[1035] 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.

[1036] [Third embodiment]

[1037] FIG. 5 shows an example of the configuration of a data processing system 310 according to the third embodiment.

[1038] 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.

[1039] 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).

[1040] 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.

[1041] 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.

[1042] 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).

[1043] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 are responsible for the exchange of various information between the processor 46 and the processor 28 via the network 54. The exchange of various information between the processor 46 and the processor 28 using the communication I / Fs 44 and 26 is carried out in a secure state.

[1044] 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.

[1045] 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.

[1046] 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.

[1047] 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.

[1048] 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."

[1049] This invention is a human resource development support system that collects and processes data such as employee daily reports, evaluation sheets, and human resource development charts, and then provides feedback and career path suggestions based on that data. This system is comprised of a server, terminals, and users, and these elements work together to collect and process data, generate feedback, and suggest career paths.

[1050] System configuration

[1051] Server: Mainly responsible for collecting and processing data, generating feedback, and proposing career paths.

[1052] Terminal: The user's interface, where they enter daily reports, check feedback, and select their career path.

[1053] Users: Employees and managers who use the system.

[1054] Overview of program processing

[1055] 1. Data Collection Phase

[1056] Terminal: The user enters a daily work report and sends the data to the server. For example, the user enters "Completed task A and worked on project B."

[1057] Server: Receives daily report data and stores it in a database.

[1058] 2. Data Processing Phase

[1059] Server: Performs data cleansing and preprocessing, converting collected daily report data and past evaluation materials into a unified format. For example, it corrects inconsistent data and imputes missing values.

[1060] Server: Uses trained assessment models to prepare feedback and career path suggestions based on data.

[1061] 3. Feedback generation phase

[1062] Server: Inputs daily report data into the trained evaluation model and generates feedback based on common criteria. For example, it generates comments about the user's work achievements and areas for improvement.

[1063] Server: Stores the generated feedback and prepares it for transmission to the user's device.

[1064] 4. Feedback provision phase

[1065] Server: Sends feedback and notifies the user's device.

[1066] Terminal: User sees feedback.

[1067] User: Consider ways to improve their work based on the feedback provided. For example, consider specific actions such as "Maybe I should spend a little more time on the next task C."

[1068] 5. Career path proposal phase

[1069] Server: Analyzes the evaluation data and suggests optimal career paths based on the employee's past evaluation results and career goals. For example, it generates a message such as, "Based on User A's technical skills and evaluation, we recommend promotion to project manager."

[1070] Server: Sends career path suggestions to the user's device.

[1071] Terminal: User reviews career path suggestions and is offered options.

[1072] User: Review the proposed career paths and select the most suitable plan. Users can make future career plans based on the career paths provided.

[1073] Specific examples

[1074] Data Collection Phase

[1075] Terminal: User enters daily report. Example: "I completed task A and started working on new project B."

[1076] Server: Receives the data and stores it in a database.

[1077] Data Processing Phase

[1078] Server: Cleanses and pre-processes the collected daily report data. For example, record that task A is completed and new project B has started.

[1079] Server: Analyzes the data using the trained evaluation model.

[1080] Feedback generation phase

[1081] Server: Generates feedback. Example: "User A completes Task A efficiently and transitions quickly to new work."

[1082] Feedback provision phase

[1083] Server: Sends the generated feedback to the device.

[1084] Terminal: Show feedback and notify the user.

[1085] User: Review the feedback and decide on the next action.

[1086] Career path proposal phase

[1087] Server: Suggests optimal career paths. Example: "Based on the evaluation results of User A, we recommend promotion to project manager."

[1088] Terminal: Displays suggestions and gives the user choices.

[1089] User: Review the proposals and choose the most suitable career plan.

[1090] In this way, the system can efficiently evaluate employees and create career paths, ensuring transparency and consistency.

[1091] The processing flow will be explained below.

[1092] Step 1:

[1093] Terminal: The user enters a daily work report. The user fills in the input form in detail with the work content, progress, and any issues that have arisen that day. For example, the user might write, "I have completed Task A and started working on Project B."

[1094] Step 2:

[1095] Terminal: Sends the entered daily report data to the server. Once the entry is complete, the daily report data is automatically sent to the server. Data is transferred in real time using a communication protocol.

[1096] Step 3:

[1097] Server: Receives daily report data and stores it in a database. The server analyzes the received data and stores it in the database in an appropriate format. At this time, validation is performed to ensure the consistency and completeness of the data.

[1098] Step 4:

[1099] Server: Performs data cleansing and preprocessing. Converts collected daily report data and past evaluation materials into a unified format and corrects errors and inconsistencies. For example, fills in missing values ​​and standardizes data.

[1100] Step 5:

[1101] Server: Analyzes the data using a trained evaluation model. The cleansed data is input into the evaluation model, preparing it for feedback. This model is trained on past data, enabling highly accurate evaluation.

[1102] Step 6:

[1103] Server: Generates feedback. Based on the trained evaluation model, the server automatically generates feedback on employees' work performance and areas for improvement. For example, it generates specific comments such as, "User A completed Task A efficiently and is recognized for quickly transitioning to new tasks."

[1104] Step 7:

[1105] Server: Stores the generated feedback and prepares it for transmission to the user's device. The feedback is temporarily stored in a database and then transmitted to the user's device in an appropriate format.

[1106] Step 8:

[1107] Server: Sends feedback to the user's device. The sent feedback is delivered to the device so that the user can check it.

[1108] Step 9:

[1109] Device: The user receives and checks the feedback. The user opens the feedback message on the device and checks its contents. For example, the user may consider taking specific actions, such as "Maybe I should spend a little more time on the next task C."

[1110] Step 10:

[1111] Server: Analyzes assessment data to generate career path suggestions. Designs optimal career paths based on the user's past assessment results, skill sets, career goals, etc. This analysis creates a long-term career plan for the user.

[1112] Step 11:

[1113] Server: Sends the career path proposal to the user's device. The generated career path proposal is sent to the user's device, where the user can check it.

[1114] Step 12:

[1115] Device: The user receives and confirms the career path proposal. The user reviews the proposal displayed on the device in detail and considers their career options.

[1116] Step 13:

[1117] User: Selects his / her own career plan based on the proposed career paths. The user considers the suggestions, selects the most suitable career path, and decides on the next step. For example, if the proposed career path is promotion to project manager, the user creates an action plan to achieve that goal.

[1118] Example 1

[1119] 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."

[1120] In conventional employee evaluation systems, information such as daily report data and evaluation sheets was not managed in a unified format, making data cleansing and preprocessing cumbersome. Furthermore, feedback was not automatically generated using a trained evaluation model, placing a heavy burden on administrators. Furthermore, there was a lack of support for users to consider work improvement measures based on their own feedback. This resulted in a lack of transparency and consistency in employee evaluations, making it difficult to suggest optimal career paths.

[1121] 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.

[1122] In this invention, the server includes means for collecting data such as users' daily report data, evaluation sheets, and development charts in a database, means for cleansing and preprocessing the collected data, means for generating feedback for the user using a trained evaluation model, means for transmitting the generated feedback to the user's terminal, means for proposing a career path based on the user's past evaluation results and career goals, and means for considering business improvement measures based on the user's feedback. This significantly improves the transparency and consistency of user evaluations, enabling effective feedback and the suggestion of appropriate career paths.

[1123] A "user" is an individual or organizational member who uses the system to enter daily report data and receive feedback.

[1124] "Daily report data" is information that a user inputs to report daily work content and progress.

[1125] An "evaluation sheet" is a document or table used to evaluate a user's work performance, behavior, etc.

[1126] A "development chart" is a document or database that keeps records for users' ability development and skill improvement.

[1127] A "database" is a digital storage system for efficiently storing, managing, and retrieving collected data.

[1128] "Cleansing" is a process of removing inconsistencies and unnecessary information from collected data to improve the quality of the data.

[1129] "Preprocessing" refers to the preparation of data to convert it into a format suitable for analysis or model input.

[1130] An "assessment model" is a set of algorithms that uses training data to evaluate a user's job performance and generate feedback.

[1131] "Feedback" refers to comments and advice regarding the user's business achievements and areas for improvement, which are generated from the evaluation model.

[1132] A "career path" is a plan of future jobs and roles suggested based on a user's past work performance and career goals.

[1133] "Business improvement measures" are specific actions or methods that users should take in their next business operation based on the feedback.

[1134] This system allows users to collect data such as daily reports, evaluation sheets, and development charts, cleanses and preprocesses the data, generates feedback using a trained evaluation model, and suggests career paths for users. This system consists of three main components: a server, a terminal, and a user.

[1135] server

[1136] The server is the core of this system and plays the following roles:

[1137] Data collection and storage: The server receives the daily report data, evaluation sheets, and development charts entered by the user and stores them in a database. Specifically, MySQL or PostgreSQL is used as the database.

[1138] Data cleansing and preprocessing: To ensure data consistency, use scripts such as Python or R to correct inconsistent data and impute missing values.

[1139] Execution of the evaluation model: The trained evaluation model is built using scikit-learn and TensorFlow, and is used to generate feedback based on the user's performance and areas for improvement.

[1140] Feedback and career path generation: The generated feedback and career path suggestions are stored in a database and prepared for transmission to the user's device.

[1141] Terminal

[1142] The terminal provides an interface for users to input daily report data and check feedback and career paths. It has the following functions:

[1143] Data entry and transmission: Users use a device (PC or tablet) to enter daily report data through a dedicated web application and send it to the server. Communication is carried out using the HTTPS protocol.

[1144] Show Feedback: Displays the feedback received from the server for the user to review.

[1145] Review Career Paths: Display suggested career paths and allow users to review and select.

[1146] User

[1147] Users use the system to input daily report data, receive feedback, and consider their career paths. The specific operations are as follows:

[1148] Entering daily report data: The user enters work details into an input form on the terminal, such as "Completed task A and worked on project B."

[1149] Review feedback: The user reviews the feedback received from the server and considers improvements.

[1150] Career path selection: Based on the career paths provided, select the most suitable career plan and make future plans.

[1151] Specific examples

[1152] Entering daily report data

[1153] The user accesses the web application on the terminal and enters the daily report data.

[1154] For example: "I completed task A and started working on new project B."

[1155] Generate feedback

[1156] The server generates feedback using the trained evaluation model.

[1157] For example: "User A completes Task A efficiently and transitions quickly to new tasks."

[1158] Career path suggestions

[1159] The server suggests career paths based on the user's past evaluation results and career goals.

[1160] Example: "Based on the results of User A's evaluation, I would like to recommend promotion to Project Manager."

[1161] Examples of prompt statements

[1162] "User A's daily report data: Completed Task A and started working on Project B. Past evaluation: Good. Areas for improvement: Needs detailed project plan." Use this daily report data to generate feedback and career path suggestions.

[1163] As described above, the system provides an efficient process for consistently conducting employee evaluations and career path proposals, ensuring transparency and consistency.

[1164] The flow of the identification process in the first embodiment will be described with reference to FIG.

[1165] Step 1: Data collection

[1166] On the device, the user opens a dedicated web application and enters daily report data. Input items include the completion status of tasks and details of projects worked on. For example, the user might enter, "Completed Task A and worked on Project B."

[1167] Input: User's daily report data (Task A completed, Project B started)

[1168] Output: Sending daily report data to the server

[1169] Step 2: Send and store data

[1170] Terminal: The entered daily report data is sent to the server via the HTTPS protocol. The user clicks the "Send" button, and the data is transferred to the server.

[1171] Input: User's daily report data

[1172] Output: Daily report data sent to the server

[1173] Server: The received daily report data is saved in a database (e.g., MySQL, PostgreSQL). The database stores information such as the date, user ID, and task ID as records.

[1174] Input: Daily report data sent from the terminal

[1175] Output: Daily report data stored in the database

[1176] Step 3: Data cleansing and preprocessing

[1177] Server: Using Python and R scripts, the incoming daily report data is cleansed and inconsistencies and missing values ​​are corrected, for example, to standardize date formats and add specific tagging.

[1178] Input: Saved daily report data

[1179] Output: Cleansed and preprocessed data

[1180] Step 4: Run the evaluation model

[1181] Server: Analyzes the pre-processed data using a trained evaluation model (e.g., scikit-learn, TensorFlow). This model generates feedback based on the user's performance and areas for improvement.

[1182] Input: Cleansed and preprocessed data

[1183] Output: Generated feedback

[1184] Step 5: Generate and save your feedback

[1185] Server: Stores the generated feedback in a database. Feedback is managed for each user and stored for review.

[1186] Input: Feedback generated from the evaluation model

[1187] Output: Feedback stored in a database

[1188] Step 6: Submit your feedback

[1189] Server: Sends the saved feedback to the user's device via HTTPS protocol, and the feedback is ready for the user to receive.

[1190] Input: Feedback stored in the database

[1191] Output: Feedback sent to the user's device

[1192] Step 7: View your feedback

[1193] On the device: The user opens the application to view the feedback. The feedback is displayed in a list format. The user receives a notification and can view the details.

[1194] Input: Notification that feedback was received

[1195] Output: Feedback displayed on the terminal

[1196] Step 8: Analyze and generate career paths

[1197] Server: Based on the user's past evaluation data and career goals, the server proposes a career path that combines the evaluation data and goals. To this end, it analyzes data collected in advance and generates an optimal career plan.

[1198] Input: Past evaluation data, career goals

[1199] Output: Generated career path suggestions

[1200] Step 9: Submit and view your career path

[1201] Server: The generated career path is sent to the user's device using the HTTPS protocol, allowing the user to check the career path after it has been sent.

[1202] Input: Generated career path proposal

[1203] Output: Career path proposal sent to the user device

[1204] On the device: The user opens the application to view the career path suggestions and explore their options. Career paths are displayed in a dedicated section of the dashboard.

[1205] Input: Career path proposal

[1206] Output: Career path suggestions displayed on the device

[1207] Step 10: Consider business improvement measures

[1208] Users: Based on the feedback and career path suggestions, users consider ways to improve their work and decide on specific actions to take to plan their next work or personal development.

[1209] Input: Feedback and career path suggestions displayed

[1210] Output: Considered business improvement measures and career plans

[1211] In this way, through a series of processing steps, this system can efficiently generate evaluations and career plans from users' daily report data, ensuring transparency and consistency.

[1212] (Application example 1)

[1213] 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."

[1214] Current human resource development support systems mainly focus on evaluating employee performance and proposing career paths in office work, but do not address the evaluation and career development of operators engaged in practical work in factories. As a result, there is a lack of means to efficiently support factory operators in improving their skills and building their career paths. To solve this problem, a system is needed to collect, evaluate, and provide feedback on the work data of factory operators.

[1215] 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.

[1216] In this invention, the server includes means for collecting data such as employee daily report data, evaluation sheets, and human resource development charts in a database, means for cleansing and preprocessing the collected data, means for generating feedback for employees using a trained evaluation model, means for sending the generated feedback to the employee's terminal, means for proposing a career path based on the employee's past evaluation results and career goals, means for collecting factory robot operation data and operator daily work reports, means for preprocessing the collected robot operation data and providing feedback to the operator, and means for proposing improvements to robot operation skills based on the operator's evaluation results. This makes it possible to improve the skills of factory operators and create career paths.

[1217] "Employee daily report data" refers to data about the progress of work and completed tasks that employees record in their daily work reports.

[1218] An "evaluation sheet" is a written or electronic format for recording an employee's performance evaluation or performance rating.

[1219] A "human resources development chart" is a database that records employees' past evaluation results and education and training history.

[1220] "Data cleansing" is the process of improving data quality by correcting inconsistent data, filling in missing values, etc.

[1221] "Preprocessing" is the process of converting data into a format suitable for input into data analysis or machine learning models.

[1222] A "trained evaluation model" is an analytical model that has been trained by a machine learning algorithm using historical data.

[1223] "Feedback generation" is a process that generates written recommendations for improvement and evaluation results for employees based on evaluation data.

[1224] "Feedback transmission" is the process of sending the generated feedback to the employee's terminal.

[1225] "Career path proposal" is a process that suggests the next job or position an employee should take based on their evaluation data and career goals.

[1226] "Factory robot operation data" refers to data related to the tasks and actions performed by robots used in factories.

[1227] The "operator's daily work report" is daily report data recorded by a factory operator regarding the work content and progress of the day.

[1228] "Improving robot operation skills" is the process of making suggestions and providing training to improve factory operators' robot operation capabilities based on evaluation data.

[1229] This invention is a system for supporting the operation of robots in factories and the training of their operators. This system is composed of a server, terminals, and user elements, which work together to collect and process data, generate feedback, and propose career paths.

[1230] System configuration

[1231] 1. Server: Responsible for collecting and processing data, generating feedback, and proposing career paths. Python and machine learning frameworks (TensorFlow, PyTorch) are used to run the program.

[1232] 2. Device: An interface where users can enter their daily reports and view feedback and career path suggestions. Devices include smartphones and smart glasses.

[1233] 3. Users: Factory operators and their managers who use the system.

[1234] Overview of program processing

[1235] 1. Data collection phase:

[1236] Terminal: The user inputs the daily work report and sends the data to the server. For example, the user inputs "Robot A has completed the inspection work and is now on the next manufacturing task."

[1237] Server: Receives daily report data and saves it in the database. The data format is JSON.

[1238] 2. Data Processing Phase:

[1239] Server: Performs data cleansing and preprocessing, converting collected daily work report data and past evaluation materials into a unified format. For example, it corrects inconsistent data and imputes missing values. It uses the Python pandas library.

[1240] Server: Uses the trained evaluation model to prepare feedback and career path suggestions based on the data. Uses scikit-learn to train the machine learning model.

[1241] 3. Feedback generation phase:

[1242] Server: Inputs the daily work report data into the trained evaluation model and generates feedback based on common criteria. For example, it generates comments about the user's work progress and areas for improvement.

[1243] Server: Stores the generated feedback and prepares it for transmission to the user's device.

[1244] 4. Feedback provision phase:

[1245] Server: Sends feedback and notifies the user's device.

[1246] Device: The user sees the feedback, which is displayed through a smartphone app or smart glasses.

[1247] User: Consider ways to improve their own work based on the feedback provided.

[1248] 5. Career path proposal phase:

[1249] Server: Analyzes the evaluation data and proposes the optimal career path based on the operator's past evaluation results and career goals. For example, it generates a message such as, "Based on the evaluation results of Operator A, we propose training in machine maintenance."

[1250] Server: Sends career path suggestions to the user's device.

[1251] Terminal: User reviews career path suggestions and is offered options.

[1252] User: Review the proposed career paths and select the most suitable plan. Users can make future career plans based on the career paths provided.

[1253] Example prompt sentence:

[1254] "Based on the operators' daily reports, generate feedback on their work performance and areas for improvement in their next assignment. Also, provide career path suggestions."

[1255] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[1256] Step 1:

[1257] Terminal: The user inputs the daily work report. Specifically, the user uses a smartphone or smart glasses to record the work details, such as "Robot A's inspection work has been completed and it has moved on to the next manufacturing task," and presses the send button. The data entered includes the work details, date, completion status, etc., and is sent to the server in JSON format. The output is the data sent to the server.

[1258] Step 2:

[1259] Server: Receives the sent daily work report data and saves it in a database. Specifically, the server parses the received JSON data and stores it in a database (e.g., MySQL, PostgreSQL). The input is the daily work report data sent from the terminal, and the output is the data saved in the database.

[1260] Step 3:

[1261] Server: Cleanses and preprocesses the daily report data. Specifically, it uses Python's pandas library to complement missing data and correct inconsistent data. The input is the daily work report data stored in the database, and the output is the data after cleansing and preprocessing.

[1262] Step 4:

[1263] Server: Using the trained evaluation model, analyze the daily work report data and prepare for feedback generation. Specifically, the preprocessed data is input into a machine learning model (e.g., scikit-learn's RandomForestRegressor) to predict the user's work achievement and areas for improvement. The input is the preprocessed daily work report data, and the output is the evaluation results necessary for feedback generation.

[1264] Step 5:

[1265] Server: Generates feedback using the trained evaluation model. Specifically, it generates feedback sentences based on the evaluation results and provides specific advice, such as "Operator A's task achievement rate is 80%. It would be desirable to shorten the inspection time a little more for the next task." The input is the evaluation results, and the output is the generated feedback sentences.

[1266] Step 6:

[1267] Server: Sends the generated feedback to the user's device. Specifically, it sends a message to a smartphone or smart glasses using an API for notifying the device of the feedback. The input is the generated feedback text, and the output is the feedback displayed on the user's device.

[1268] Step 7:

[1269] Device: The user checks the feedback. Specifically, the user clicks on the notification on the device to check the feedback content. Based on the information obtained from the feedback, an action plan for the next task is considered. The input is the feedback sent from the server, and the output is the user's action plan based on the feedback.

[1270] Step 8:

[1271] Server: Analyzes evaluation data and proposes career paths based on the operator's past evaluation results and career goals. Specifically, it uses evaluation data to generate career path options, proposing content such as "Based on the evaluation results of Operator A, we propose training in machine maintenance." The input is evaluation data, and the output is a written career path proposal.

[1272] Step 9:

[1273] Server: Sends career path suggestions to the user's device. Specifically, similar to feedback, it sends career path suggestions using an API to notify the device. The input is the career path suggestion text, and the output is the career path suggestion displayed on the user's device.

[1274] Step 10:

[1275] Device: The user reviews the career path proposals and selects the most suitable plan. Specifically, the user clicks on the notification on the device to review the career path proposals and decides whether to adopt them as their own career plan. The input is the career path proposal sent from the server, and the output is the career plan selected by the user.

[1276] 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.

[1277] This invention is a human resource development support system that collects and processes data such as employee daily reports, evaluation sheets, and human resource development charts, and provides feedback and career path suggestions. This system incorporates an emotion engine that recognizes the user's emotions, and individual feedback and career path suggestions are adjusted taking into account the user's emotional state.

[1278] System configuration

[1279] Server: Performs functions of data collection, processing, feedback generation, career path suggestions, and sentiment analysis.

[1280] Terminal: Functions as an interface with the user, allowing them to enter daily reports, display feedback, transmit emotional data, and select career paths.

[1281] Users: Employees and managers who use the system.

[1282] Emotion Engine: Recognizes user emotions and reflects them in feedback and career path suggestions.

[1283] Overview of program processing

[1284] 1. Data Collection Phase

[1285] Terminal: The user enters a work report, for example, "I completed task A and started working on project B."

[1286] Terminal: Daily report data is automatically sent to the server.

[1287] 2. Data Processing Phase

[1288] Server: Stores the received daily report data in a database and performs data cleansing and preprocessing, filling in missing values ​​and standardizing the data.

[1289] Server: Uses the trained evaluation model to prepare feedback and career path suggestions.

[1290] 3. Feedback generation phase

[1291] Server: Inputs daily report data into the evaluation model and generates feedback. For example, it creates specific comments such as "User A is highly evaluated because he completed Task A efficiently."

[1292] Server: Analyzes the user's emotional data using the emotion engine. Adjusts the feedback based on the user's emotional state. For example, if the user is feeling stressed, the server adds a comment to the feedback such as "Please reconsider your work balance and take a rest."

[1293] 4. Feedback provision phase

[1294] Server: Sends the generated feedback to the user's device.

[1295] Terminal: Display feedback so that the user can see it.

[1296] 5. Emotional Data Collection Phase

[1297] Terminal: Collects emotional data from user input and reactions. The emotional data is sent to the server in real time.

[1298] Emotion Engine: Analyzes the emotion data collected from the user and evaluates their current emotional state.

[1299] 6. Career path proposal phase

[1300] Server: Analyzes the evaluation data and suggests the best career path. For example, "Based on User A's past evaluation results and technical skills, we suggest promotion to project manager."

[1301] Server: Uses an emotion engine to tailor career path suggestions to the user's emotional state. For example, if the user is feeling anxious, the server might add "support systems" or "training programs" to the suggestions.

[1302] Server: Sends career path suggestions to the user's device.

[1303] Terminal: User reviews career path suggestions.

[1304] User: Select your own career plan based on the suggestions.

[1305] Specific examples

[1306] Data Collection Phase

[1307] Terminal: User enters daily report. Example: "I completed task A and started working on new project B."

[1308] Server: Receives the data and stores it in a database.

[1309] Data Processing Phase

[1310] Server: Cleanses and pre-processes the collected daily report data. For example, record that task A is completed and new project B has started.

[1311] Server: Analyzes the data using the trained evaluation model.

[1312] Feedback generation phase

[1313] Server: Generates feedback. Example: "User A completes Task A efficiently and transitions quickly to new work."

[1314] Server: Uses the emotion engine to analyze the user's emotional state and reflect it in the feedback. For example, if the user is feeling stressed, add a comment such as "Please reconsider your work balance and take a rest."

[1315] Feedback provision phase

[1316] Server: Sends the generated feedback to the device.

[1317] Terminal: Show feedback and notify the user.

[1318] User: Review the feedback and decide on the next action.

[1319] Career path proposal phase

[1320] Server: Suggests optimal career paths. Example: "Based on the evaluation results of User A, we recommend promotion to project manager."

[1321] Server: Uses an emotion engine to generate career path suggestions that reflect the user's emotional state. For example, if the user is feeling anxious, add "support systems" and "training programs" to the suggestions.

[1322] Device: Display the suggestion and make it available for the user to review.

[1323] User: Review the proposals and choose the most suitable career plan.

[1324] The processing flow will be explained below.

[1325] Step 1:

[1326] Terminal: The user enters a daily work report. The user fills in the input form on the terminal with details of the day's work, progress, and any issues they encountered. For example, they might write, "I completed task A and started working on a new project B."

[1327] Step 2:

[1328] Terminal: Sends the entered daily report data to the server. After input is complete, the daily report data is automatically sent to the server. Transmission is secure using encrypted communication protocols such as SSL.

[1329] Step 3:

[1330] Server: Receives daily report data and saves it in the database. The server converts the received daily report data into an appropriate format and stores it in the database. When saving, a validation check is performed to confirm the consistency of the data.

[1331] Step 4:

[1332] Server: Performs data cleansing and preprocessing. Corrects errors and inconsistencies in the collected daily report data and converts it into a unified format. For example, it fills in missing values ​​and standardizes date formats.

[1333] Step 5:

[1334] Server: Analyzes the data using a trained evaluation model. The cleansed data is fed into the evaluation model, preparing it for feedback generation. The model is trained using machine learning algorithms, enabling highly accurate evaluations.

[1335] Step 6:

[1336] Server: Works with the device to collect user emotion data. The emotion engine runs and collects user input and reactions, such as keystroke speed and back arching.

[1337] Step 7:

[1338] Emotion engine: Analyzes collected data and evaluates the user's emotional state. For example, if a user types faster than usual, it recognizes that the user is under stress.

[1339] Step 8:

[1340] Server: The emotion data obtained from the emotion engine is reflected in the evaluation model and feedback is generated. For example, if a user is under stress, a comment such as "Please reconsider your work balance and take some rest" is added.

[1341] Step 9:

[1342] Server: Stores the generated feedback in a database and prepares it for transmission to the user's device.

[1343] Step 10:

[1344] Server: Sends the generated feedback to the user's device. Uses a notification system to notify the user that the feedback has arrived.

[1345] Step 11:

[1346] Terminal: Feedback is displayed and made available for the user to check. The user can check the feedback on their terminal and use it to improve their own work.

[1347] Step 12:

[1348] Server: Proposes optimal career paths based on evaluation data. Generates career paths taking into account past evaluation results, the user's skill set, and long-term career goals.

[1349] Step 13:

[1350] Server: Adjust the career path suggestions based on the results of the emotion engine. For example, if the user feels anxious, add support systems or training programs to the suggestions.

[1351] Step 14:

[1352] Server: Sends tailored career path proposals to the user's device.

[1353] Step 15:

[1354] Device: The career path proposal is displayed and made available for the user to review. The user reviews the proposal in detail and considers their own career plan.

[1355] Step 16:

[1356] User: Selects his / her own career plan based on the suggested career paths. The user considers the suggestions and selects the most suitable career path. For example, if a promotion to project manager is proposed, the user creates an action plan for that promotion.

[1357] Example 2

[1358] 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."

[1359] Although conventional human resource management systems can collect employee daily report data and evaluation sheets, they do not take into account the emotional state of each employee when making feedback or career path suggestions, which means that employee motivation and performance cannot be optimized, limiting the efficiency of the organization as a whole.In addition, because employee career path suggestions are standardized, flexible suggestions based on the characteristics and goals of each employee cannot be made.

[1360] The specific processing by the specific processing unit 290 of the data processing device 12 in the second embodiment is realized by the following means.

[1361] In this invention, the server includes a means for collecting data such as employee daily reports, evaluation sheets, and human resource development charts in a database, a means for cleansing and preprocessing the collected data, a means for generating feedback for employees using a trained evaluation model, a means for analyzing user emotion data and adjusting the feedback and career path suggestions, and a means for sending the generated feedback to the employee's terminal. This enables flexible and appropriate feedback and career path suggestions that take into account the emotional state of each employee.

[1362] A "database" is a system for storing, managing, and searching data in an organized manner.

[1363] "Data cleansing" is the process of filling in missing values, correcting inaccurate data, and standardizing it.

[1364] "Preprocessing" refers to the preparatory work done before inputting data into data analysis or machine learning models, and includes data formatting and normalization.

[1365] An "evaluation model" is a trained algorithm that evaluates employee performance based on input data and generates feedback.

[1366] "Feedback" refers to evaluations and comments on employees' performance, with the aim of improving work and increasing motivation.

[1367] "Emotional data" is data used to measure and analyze a user's emotional state, and is collected from the user's input, reactions, etc.

[1368] A "career path" is the path of goals and positions that an employee should pursue within a company, including plans for growth and promotion.

[1369] The "Emotion Engine" is a system that analyzes users' emotional data and reflects it in feedback and career path suggestions.

[1370] "Collection means" refers to the method or system for collecting daily report data, evaluation sheets, etc. into a database.

[1371] "Cleansing and preprocessing means" refers to methods and systems used to prepare collected data and make it suitable for analysis.

[1372] "Feedback generator" means a method or system for generating ratings and comments for employees using a trained rating model.

[1373] "Emotion data analysis means" refers to a method or system for analyzing a user's emotional data and reflecting the results in feedback and career path suggestions.

[1374] "Transmission means" refers to a method or system for sending the generated feedback and career path suggestions to the employee's terminal.

[1375] This invention relates to a human resource development support system that collects and processes data such as employee daily reports, evaluation sheets, and human resource development charts, and provides feedback and career path suggestions. This system incorporates an emotion engine that recognizes the user's emotions, and the feedback and career path suggestions are adjusted taking into account the user's emotional state.

[1376] System configuration

[1377] Server: Performs functions such as data collection, processing, feedback generation, career path suggestions, and sentiment analysis. The server can utilize cloud-based infrastructure (e.g., AWS, Google Cloud).

[1378] Terminal: Functions as an interface with the user, allowing them to input daily reports, display feedback, transmit emotional data, and select career paths. Terminals include, for example, personal computers and smartphones.

[1379] Users: Employees and managers who use the system.

[1380] Emotion engine: Recognizes the user's emotions and reflects them in feedback and career path suggestions. For example, the IBM Watson Tone Analyzer can be used as an emotion engine.

[1381] Data collection

[1382] The terminal provides an interface for users to input daily work reports. The daily report data entered by the user is sent from the terminal to a server. The transmission is secure using a security protocol (e.g., HTTPS). The server stores the received daily report data in a database. This database uses a database management system such as "PostgreSQL."

[1383] Data Processing

[1384] The server cleanses and preprocesses the daily report data stored in the database. This process includes filling in missing values ​​and standardizing the data. Cleansing and preprocessing improves the accuracy and reliability of the data. A trained evaluation model can be built using TensorFlow, for example. The daily report data is input into this evaluation model and analyzed.

[1385] Feedback Generation

[1386] The server creates feedback based on the data generated by the evaluation model. For example, it generates a comment such as, "Employee A is highly evaluated because he completed Task A efficiently." The server also analyzes the user's emotional data using an emotion engine and adjusts the content of the feedback. For example, if the user is feeling stressed, it adds a comment such as, "It is recommended that you reconsider your work balance and take a rest."

[1387] Providing Feedback

[1388] The server sends the generated feedback to the user's device. For example, a notification service such as Firebase Cloud Messaging can be used for this purpose. The device displays the feedback and notifies the user.

[1389] Emotional Data Collection

[1390] The device collects emotional data from the user's input and reactions, which is then sent to a server in real time and analyzed by an emotion engine.

[1391] Career path suggestions

[1392] The server proposes optimal career paths based on the collected and analyzed evaluation data. For example, it generates a proposal such as, "Based on Employee A's past evaluation results and technical skills, we propose promotion to project manager." The server can also use an emotion engine to adjust the proposal content according to the user's emotional state. For example, if the user is feeling anxious, it can add a "support system" or "training program" to the proposal. The career path proposal is sent to the terminal, and the user can select their own career plan based on the proposal.

[1393] Specific examples

[1394] For example, a user enters a daily report stating, "I completed Task A and started working on new Project B." This data is sent to the server via the device and stored in a database. The server cleanses and preprocesses the data, inputs it into an evaluation model, and generates feedback. The generated feedback might be, "User A completed Task A efficiently and is moving quickly to new work." Furthermore, if the user is determined to be feeling stressed, a comment such as, "Please reconsider your work balance and take a rest" is added.

[1395] Prompt Sentence Examples

[1396] "Please explain the program of a system that generates feedback based on employees' daily report data and suggests career paths that reflect the user's emotional state. Please explain the process in detail using specific examples."

[1397] This system enables flexible and appropriate feedback and career path suggestions that take into account employees' emotional state, which is expected to improve efficiency and motivation throughout the organization.

[1398] The flow of the identification process in the second embodiment will be described with reference to FIG.

[1399] Step 1:

[1400] The user inputs a daily work report. The user uses a terminal to input daily report data, such as "Task A completed and started working on new project B." Once input is complete, the data is automatically sent from the terminal to the server.

[1401] Step 2:

[1402] The terminal sends the daily report data to the server. A security protocol (e.g. HTTPS) is used for transmission, and the data is transferred safely. Terminal input: Daily report data entered by the user. Output: Daily report data sent.

[1403] Step 3:

[1404] The server stores the received daily report data in a database. For example, "PostgreSQL" is used as the database. Server input: Daily report data sent from the terminal. Output: Daily report data stored in the database.

[1405] Step 4:

[1406] The server performs data cleansing and preprocessing. The server fills in any missing values ​​in the daily report data and standardizes the data. Server input: Daily report data read from the database. Output: Data after cleansing and preprocessing.

[1407] Step 5:

[1408] The server analyzes the data using a trained evaluation model, for example, a model built using TensorFlow. Server input: cleansed and preprocessed data. Output: analysis results.

[1409] Step 6:

[1410] The server generates feedback based on the data generated by the evaluation model. For example, it generates specific comments such as "Employee A is highly evaluated because he completed task A efficiently." Server input: Analysis results. Output: Generated feedback.

[1411] Step 7:

[1412] The server uses an emotion engine to analyze the user's emotion data and adjust the feedback content. The emotion engine used is something like "IBM Watson Tone Analyzer." For example, if the user is feeling stressed, it adds a comment saying, "We recommend that you reconsider your work balance and take a rest." Server input: Feedback and emotion data. Output: Adjusted feedback.

[1413] Step 8:

[1414] The server sends the generated feedback to the user's device. This is done using a notification service such as Firebase Cloud Messaging. Server input: Adjusted feedback. Output: Feedback sent to the user's device.

[1415] Step 9:

[1416] The device displays feedback and notifies the user. Notifications can be done using popup messages or in-app notifications. Device input: Feedback sent from the server. Output: Feedback displayed to the user.

[1417] Step 10:

[1418] The user checks the feedback on the device, and as a next step, decides on the next action and reflects it in their work.

[1419] Step 11:

[1420] The device collects emotional data from the user's input and reactions. Emotional data is collected using the user's keystroke analysis and screen touch data. Device input: User's input and reactions. Output: Collected emotional data.

[1421] Step 12:

[1422] The device sends the collected emotion data to the server in real time. Device input: Collected emotion data. Output: Emotion data sent to the server.

[1423] Step 13:

[1424] The emotion engine analyzes the user's emotional state on the server and records it in the emotion database. The analysis results are used as feedback for the generative AI model. Server input: collected emotion data. Output: analysis results and recorded emotion data.

[1425] Step 14:

[1426] The server analyzes the user's daily report data and past evaluation data to propose the optimal career path. For example, it generates a proposal such as "Based on the evaluation results of employee A, recommend promotion to project manager." Server input: Daily report data and past evaluation data. Output: Career path proposal.

[1427] Step 15:

[1428] The server uses an emotion engine to adjust the career path suggestions to fit the user's emotional state. For example, if the user is feeling anxious, the suggestions will be adjusted to include "support systems" and "training programs." Server input: Career path suggestions and emotion data. Output: Adjusted career path suggestions.

[1429] Step 16:

[1430] The server sends the career path proposal to the user's device. Server input: Adjusted career path proposal. Output: Career path proposal sent to the user's device.

[1431] Step 17:

[1432] The terminal displays the career path proposal for the user to review. Terminal input: Career path proposal sent from the server. Output: Career path proposal displayed to the user.

[1433] Step 18:

[1434] The user checks the career path suggestions on the terminal and selects the most suitable career plan. The selected career plan is sent back to the server and recorded in the database. User input: Career plan selection. Output: Selected career plan sent to the server.

[1435] The above is the specific processing flow of the program of this system.

[1436] (Application example 2)

[1437] 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."

[1438] While conventional human resource development support systems can provide feedback based on employee daily reports and evaluations, they lack the ability to provide feedback and career path suggestions that take into account employees' emotional states and the operation data of the machines used on-site. Furthermore, particularly in manufacturing sites, they are unable to provide feedback or career path suggestions that include production data and error history from machines such as robots, making it difficult to efficiently manage personnel and machines and improve their performance. Another problem is the inability to analyze emotional data collected in real time and adjust feedback accordingly.

[1439] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 2 is realized by the following means.

[1440] In this invention, the server includes means for collecting employee daily report data, evaluation sheets, human resource development charts, product production data, error history, and operator feedback data in a database, means for cleansing and preprocessing the collected data, means for generating feedback for employees and machines using a trained evaluation model, means for transmitting the generated feedback to the terminals of the employees and machine operators, means for proposing career paths for the employees and machine operators based on their past evaluation results and career goals, means for collecting and analyzing emotional data for the machine operators in real time, and means for adjusting the feedback and career path proposals based on their emotional states. This enables efficient feedback and career path proposals that take into account the emotional states of the employees and machine operators and the machine's production data.

[1441] "Employee daily report data" refers to data in which employees record their daily work progress and completed tasks.

[1442] An "appraisal sheet" is a written or electronic format used for the purpose of evaluating an employee's performance or skills.

[1443] A "human resources development chart" is a data sheet that records an employee's skills, career path, training history, etc.

[1444] "Product production data" refers to data that records the work content and production results of machines and robots used in manufacturing sites.

[1445] "Error history" is data that records details of errors and malfunctions that occur during manufacturing processes or machine operation.

[1446] "Operator feedback data" is data that records opinions and evaluations submitted by employees in charge of operating machines or robots regarding their work.

[1447] "Means of collecting data in a database" refers to functions and systems for organizing various data and storing it centrally.

[1448] "Data cleansing and preprocessing means" refers to functions and systems that perform preprocessing to improve data quality, such as filling in missing data values ​​and removing outliers.

[1449] A "trained evaluation model" is an algorithm or system that learns from past data and predicts and evaluates the performance of employees or machines.

[1450] "Means for generating feedback" refers to functions or systems for providing appropriate advice and areas for improvement based on the evaluation results.

[1451] The "means for sending feedback" refers to a communication function or system for delivering the generated feedback to the terminals of employees or operators.

[1452] "Means for suggesting career paths" are functions or systems that show employees and operators the optimal career path based on their past performance and goals.

[1453] "Means for collecting and analyzing emotional data in real time" refers to functions and systems for obtaining the emotional state of employees and operators in a timely manner and analyzing that data.

[1454] The "means for adjusting feedback and career path suggestions based on emotional state" refers to a function or system that optimizes the content of feedback and career path suggestions based on analyzed emotional data.

[1455] This invention is a system for collecting and processing employee daily report data, evaluation sheets, human resource development charts, product production data, error history, and operator feedback data, and providing feedback and career path suggestions. This system includes an emotion engine that analyzes emotional states and reflects them in feedback and career path suggestions.

[1456] The main components of the system are as follows:

[1457] Server: Responsible for data collection, data cleansing, pre-processing, feedback generation, career path suggestions, and sentiment analysis.

[1458] Terminal: Serves as an interface with the user, allowing them to enter daily reports, view feedback, send emotional data, and select career paths.

[1459] Users: Employees and machine operators who use the system.

[1460] Emotion Engine: Recognizes user emotions and reflects them in feedback and career path suggestions.

[1461] The system first collects daily report data and feedback data from employees and operators via their terminals and sends it to the server. The server stores the received data in a database and performs data cleansing and preprocessing. This process is performed using the Python pandas library, for example, by filling in missing values ​​and standardizing the data. Next, the trained evaluation model is used to generate feedback for employees and machine operators. The scikit-learn library is used to train the evaluation model.

[1462] The generated feedback is sent from the server to the device and displayed for the user to review. For example, if an employee enters "I completed Task A and started working on new Project B," the feedback displayed will read, "I commend you for completing Task A efficiently and moving quickly to new work."

[1463] The emotion engine also analyzes the user's emotional state and adjusts the feedback accordingly. For example, if the user is feeling stressed, it might add a comment like, "Reconsider your work balance and take a break." The nltk library is used to analyze emotion data. In particular, the nltk.sentiment library is used for emotion analysis.

[1464] Furthermore, the server suggests career paths based on the user's past evaluation results and career goals. For example, it might suggest, "Based on User A's past evaluation results, we suggest transitioning to a new position exclusively for Process Z." The content of this suggestion is also adjusted according to the user's emotional state. For example, if the user is feeling anxious, it might add a "training session for a smooth transition."

[1465] As a concrete example, when a user inputs a daily report, the prompt may be something like, "Please write specifically about today's work. For example, the robot frequently produced errors, but the cause was identified and corrected." This prompt is important for maintaining consistency in the input data.

[1466] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[1467] Step 1:

[1468] Data Collection Phase

[1469] Terminals: Users (employees and machine operators) enter daily report data and feedback data. For example, an employee may enter "I have completed task A and started working on new project B."

[1470] Input: Daily report data, feedback data

[1471] Output: Raw data collected

[1472] Specific operation: When a user enters data using a dedicated application and presses the "Submit" button, the data is sent to the server in real time.

[1473] Step 2:

[1474] Data transmission phase

[1475] Terminal: Automatically sends collected daily report data and feedback data to the server.

[1476] Input: Raw data collected

[1477] Output: Data sent to the server

[1478] Specific operation: The terminal uploads data to the server via the network and stores it in the database.

[1479] Step 3:

[1480] Data cleansing and preprocessing phase

[1481] Server: Cleanses and preprocesses the received data, specifically filling in missing values ​​and standardizing the data.

[1482] Input: Data stored on the server

[1483] Output: Preprocessed and clean data

[1484] Specific operation: Create a data frame using Python's pandas library, impute missing values, and standardize.

[1485] Step 4:

[1486] Feedback generation phase

[1487] Server: Uses the trained evaluation model to generate feedback, such as "User A completed task A efficiently and therefore deserves high praise."

[1488] Input: Preprocessed and clean data

[1489] Output: Generated feedback

[1490] What it does: Uses the scikit-learn library to input data into an evaluation model and generate feedback based on the prediction results.

[1491] Step 5:

[1492] Sentiment Analysis Phase

[1493] Server: Uses an emotion engine to analyze the emotional state from the user's input and reactions.

[1494] Input: User input data, response data

[1495] Output: Parsed emotional state

[1496] Specific operation: Analyzes emotional states using the nltk.sentiment module of the nltk library.

[1497] Step 6:

[1498] Feedback Adjustment Phase

[1499] Server: Adjust the feedback based on the analyzed emotional state. For example, if the user is feeling stressed, add a comment like "Please rebalance your work and take some rest."

[1500] Input: Generated feedback, parsed emotional state

[1501] Output: Regulated Feedback

[1502] Specific operation: Using the results of sentiment analysis, the feedback content is modified appropriately and the final feedback sentence is generated.

[1503] Step 7:

[1504] Feedback sending phase

[1505] Server: Sends the generated feedback to the user's device.

[1506] Input: Calibrated Feedback

[1507] Output: Feedback sent to the terminal

[1508] Specific operation: Sends data from the server to the device and displays a notification on the device.

[1509] Step 8:

[1510] Feedback display phase

[1511] Terminal: Display feedback so that the user can see it.

[1512] Input: Feedback sent by the server

[1513] Output: Displayed feedback

[1514] Specific operation: The feedback content is displayed on the device's user interface and the user is notified.

[1515] Step 9:

[1516] Career path proposal phase

[1517] Server: Proposes a career path based on the user's past evaluation results and career goals. For example, "Based on User A's past evaluation results, we propose a transition to a new, dedicated role in Process Z."

[1518] Input: User's past evaluation results, career goals

[1519] Output: Generated career path suggestions

[1520] Specific actions: Analyze evaluation data, generate appropriate career paths, and create proposals.

[1521] Step 10:

[1522] Career path proposal adjustment phase

[1523] Server: Uses an emotion engine to tailor career path suggestions based on the user's emotional state. For example, if the user is feeling anxious, add a "training session for a smooth transition."

[1524] Input: Generated career path suggestions, analyzed emotional states

[1525] Output: Tailored career path suggestions

[1526] Specific operation: Based on the results of the sentiment analysis, the content of the career path is modified as appropriate and the final proposal is generated.

[1527] Step 11:

[1528] Career path submission phase

[1529] Server: Sends the generated career path proposal to the terminal.

[1530] Input: Tailored career path proposals

[1531] Output: Career path proposal sent to the device

[1532] Specific operation: Sends data from the server to the device and displays a notification on the device.

[1533] Step 12:

[1534] Career path display phase

[1535] Terminal: Display career path suggestions and make them available for user review.

[1536] Input: Career path proposal sent from the server

[1537] Output: Displayed career path suggestions

[1538] Specific operation: The career path suggestions are displayed on the device's user interface and notified to the user.

[1539] 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.

[1540] 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.

[1541] 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.

[1542] [Fourth embodiment]

[1543] FIG. 7 shows an example of the configuration of a data processing system 410 according to the fourth embodiment.

[1544] 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.

[1545] 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).

[1546] 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.

[1547] 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.

[1548] 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).

[1549] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 are responsible for the exchange of various information between the processor 46 and the processor 28 via the network 54. The exchange of various information between the processor 46 and the processor 28 using the communication I / Fs 44 and 26 is carried out in a secure state.

[1550] 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.

[1551] 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.

[1552] 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.

[1553] 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.

[1554] 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.

[1555] 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."

[1556] This invention is a human resource development support system that collects and processes data such as employee daily reports, evaluation sheets, and human resource development charts, and then provides feedback and career path suggestions based on that data. This system is comprised of a server, terminals, and users, and these elements work together to collect and process data, generate feedback, and suggest career paths.

[1557] System configuration

[1558] Server: Mainly responsible for collecting and processing data, generating feedback, and proposing career paths.

[1559] Terminal: The user's interface, where they enter daily reports, check feedback, and select their career path.

[1560] Users: Employees and managers who use the system.

[1561] Overview of program processing

[1562] 1. Data Collection Phase

[1563] Terminal: The user enters a daily work report and sends the data to the server. For example, the user enters "Completed task A and worked on project B."

[1564] Server: Receives daily report data and stores it in a database.

[1565] 2. Data Processing Phase

[1566] Server: Performs data cleansing and preprocessing, converting collected daily report data and past evaluation materials into a unified format. For example, it corrects inconsistent data and imputes missing values.

[1567] Server: Uses trained assessment models to prepare feedback and career path suggestions based on data.

[1568] 3. Feedback generation phase

[1569] Server: Inputs daily report data into the trained evaluation model and generates feedback based on common criteria. For example, it generates comments about the user's work achievements and areas for improvement.

[1570] Server: Stores the generated feedback and prepares it for transmission to the user's device.

[1571] 4. Feedback provision phase

[1572] Server: Sends feedback and notifies the user's device.

[1573] Terminal: User sees feedback.

[1574] User: Consider ways to improve their work based on the feedback provided. For example, consider specific actions such as "Maybe I should spend a little more time on the next task C."

[1575] 5. Career path proposal phase

[1576] Server: Analyzes the evaluation data and suggests optimal career paths based on the employee's past evaluation results and career goals. For example, it generates a message such as, "Based on User A's technical skills and evaluation, we recommend promotion to project manager."

[1577] Server: Sends career path suggestions to the user's device.

[1578] Terminal: User reviews career path suggestions and is offered options.

[1579] User: Review the proposed career paths and select the most suitable plan. Users can make future career plans based on the career paths provided.

[1580] Specific examples

[1581] Data Collection Phase

[1582] Terminal: User enters daily report. Example: "I completed task A and started working on new project B."

[1583] Server: Receives the data and stores it in a database.

[1584] Data Processing Phase

[1585] Server: Cleanses and pre-processes the collected daily report data. For example, record that task A is completed and new project B has started.

[1586] Server: Analyzes the data using the trained evaluation model.

[1587] Feedback generation phase

[1588] Server: Generates feedback. Example: "User A completes Task A efficiently and transitions quickly to new work."

[1589] Feedback provision phase

[1590] Server: Sends the generated feedback to the device.

[1591] Terminal: Show feedback and notify the user.

[1592] User: Review the feedback and decide on the next action.

[1593] Career path proposal phase

[1594] Server: Suggests optimal career paths. Example: "Based on the evaluation results of User A, we recommend promotion to project manager."

[1595] Terminal: Displays suggestions and gives the user choices.

[1596] User: Review the proposals and choose the most suitable career plan.

[1597] In this way, the system can efficiently evaluate employees and create career paths, ensuring transparency and consistency.

[1598] The processing flow will be explained below.

[1599] Step 1:

[1600] Terminal: The user enters a daily work report. The user fills in the input form in detail with the work content, progress, and any issues that have arisen that day. For example, the user might write, "I have completed Task A and started working on Project B."

[1601] Step 2:

[1602] Terminal: Sends the entered daily report data to the server. Once the entry is complete, the daily report data is automatically sent to the server. Data is transferred in real time using a communication protocol.

[1603] Step 3:

[1604] Server: Receives daily report data and stores it in a database. The server analyzes the received data and stores it in the database in an appropriate format. At this time, validation is performed to ensure the consistency and completeness of the data.

[1605] Step 4:

[1606] Server: Performs data cleansing and preprocessing. Converts collected daily report data and past evaluation materials into a unified format and corrects errors and inconsistencies. For example, fills in missing values ​​and standardizes data.

[1607] Step 5:

[1608] Server: Analyzes the data using a trained evaluation model. The cleansed data is input into the evaluation model, preparing it for feedback. This model is trained on past data, enabling highly accurate evaluation.

[1609] Step 6:

[1610] Server: Generates feedback. Based on the trained evaluation model, the server automatically generates feedback on employees' work performance and areas for improvement. For example, it generates specific comments such as, "User A completed Task A efficiently and is recognized for quickly transitioning to new tasks."

[1611] Step 7:

[1612] Server: Stores the generated feedback and prepares it for transmission to the user's device. The feedback is temporarily stored in a database and then transmitted to the user's device in an appropriate format.

[1613] Step 8:

[1614] Server: Sends feedback to the user's device. The sent feedback is delivered to the device so that the user can check it.

[1615] Step 9:

[1616] Device: The user receives and checks the feedback. The user opens the feedback message on the device and checks its contents. For example, the user may consider taking specific actions, such as "Maybe I should spend a little more time on the next task C."

[1617] Step 10:

[1618] Server: Analyzes assessment data to generate career path suggestions. Designs optimal career paths based on the user's past assessment results, skill sets, career goals, etc. This analysis creates a long-term career plan for the user.

[1619] Step 11:

[1620] Server: Sends the career path proposal to the user's device. The generated career path proposal is sent to the user's device, where the user can check it.

[1621] Step 12:

[1622] Device: The user receives and confirms the career path proposal. The user reviews the proposal displayed on the device in detail and considers their career options.

[1623] Step 13:

[1624] User: Selects his / her own career plan based on the proposed career paths. The user considers the suggestions, selects the most suitable career path, and decides on the next step. For example, if the proposed career path is promotion to project manager, the user creates an action plan to achieve that goal.

[1625] Example 1

[1626] 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."

[1627] In conventional employee evaluation systems, information such as daily report data and evaluation sheets was not managed in a unified format, making data cleansing and preprocessing cumbersome. Furthermore, feedback was not automatically generated using a trained evaluation model, placing a heavy burden on administrators. Furthermore, there was a lack of support for users to consider work improvement measures based on their own feedback. This resulted in a lack of transparency and consistency in employee evaluations, making it difficult to suggest optimal career paths.

[1628] 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.

[1629] In this invention, the server includes means for collecting data such as users' daily report data, evaluation sheets, and development charts in a database, means for cleansing and preprocessing the collected data, means for generating feedback for the user using a trained evaluation model, means for transmitting the generated feedback to the user's terminal, means for proposing a career path based on the user's past evaluation results and career goals, and means for considering business improvement measures based on the user's feedback. This significantly improves the transparency and consistency of user evaluations, enabling effective feedback and the suggestion of appropriate career paths.

[1630] A "user" is an individual or organizational member who uses the system to enter daily report data and receive feedback.

[1631] "Daily report data" is information that a user inputs to report daily work content and progress.

[1632] An "evaluation sheet" is a document or table used to evaluate a user's work performance, behavior, etc.

[1633] A "development chart" is a document or database that keeps records for users' ability development and skill improvement.

[1634] A "database" is a digital storage system for efficiently storing, managing, and retrieving collected data.

[1635] "Cleansing" is a process of removing inconsistencies and unnecessary information from collected data to improve the quality of the data.

[1636] "Preprocessing" refers to the preparation of data to convert it into a format suitable for analysis or model input.

[1637] An "assessment model" is a set of algorithms that uses training data to evaluate a user's job performance and generate feedback.

[1638] "Feedback" refers to comments and advice regarding the user's business achievements and areas for improvement, which are generated from the evaluation model.

[1639] A "career path" is a plan of future jobs and roles suggested based on a user's past work performance and career goals.

[1640] "Business improvement measures" are specific actions or methods that users should take in their next business operation based on the feedback.

[1641] This system allows users to collect data such as daily reports, evaluation sheets, and development charts, cleanses and preprocesses the data, generates feedback using a trained evaluation model, and suggests career paths for users. This system consists of three main components: a server, a terminal, and a user.

[1642] server

[1643] The server is the core of this system and plays the following roles:

[1644] Data collection and storage: The server receives the daily report data, evaluation sheets, and development charts entered by the user and stores them in a database. Specifically, MySQL or PostgreSQL is used as the database.

[1645] Data cleansing and preprocessing: To ensure data consistency, use scripts such as Python or R to correct inconsistent data and impute missing values.

[1646] Execution of the evaluation model: The trained evaluation model is built using scikit-learn and TensorFlow, and is used to generate feedback based on the user's performance and areas for improvement.

[1647] Feedback and career path generation: The generated feedback and career path suggestions are stored in a database and prepared for transmission to the user's device.

[1648] Terminal

[1649] The terminal provides an interface for users to input daily report data and check feedback and career paths. It has the following functions:

[1650] Data entry and transmission: Users use a device (PC or tablet) to enter daily report data through a dedicated web application and send it to the server. Communication is carried out using the HTTPS protocol.

[1651] Show Feedback: Displays the feedback received from the server for the user to review.

[1652] Review Career Paths: Display suggested career paths and allow users to review and select.

[1653] User

[1654] Users use the system to input daily report data, receive feedback, and consider their career paths. The specific operations are as follows:

[1655] Entering daily report data: The user enters work details into an input form on the terminal, such as "Completed task A and worked on project B."

[1656] Review feedback: The user reviews the feedback received from the server and considers improvements.

[1657] Career path selection: Based on the career paths provided, select the most suitable career plan and make future plans.

[1658] Specific examples

[1659] Entering daily report data

[1660] The user accesses the web application on the terminal and enters the daily report data.

[1661] For example: "I completed task A and started working on new project B."

[1662] Generate feedback

[1663] The server generates feedback using the trained evaluation model.

[1664] For example: "User A completes Task A efficiently and transitions quickly to new tasks."

[1665] Career path suggestions

[1666] The server suggests career paths based on the user's past evaluation results and career goals.

[1667] Example: "Based on the results of User A's evaluation, I would like to recommend promotion to Project Manager."

[1668] Examples of prompt statements

[1669] "User A's daily report data: Completed Task A and started working on Project B. Past evaluation: Good. Areas for improvement: Needs detailed project plan." Use this daily report data to generate feedback and career path suggestions.

[1670] As described above, the system provides an efficient process for consistently conducting employee evaluations and career path proposals, ensuring transparency and consistency.

[1671] The flow of the identification process in the first embodiment will be described with reference to FIG.

[1672] Step 1: Data collection

[1673] On the device, the user opens a dedicated web application and enters daily report data. Input items include the completion status of tasks and details of projects worked on. For example, the user might enter, "Completed Task A and worked on Project B."

[1674] Input: User's daily report data (Task A completed, Project B started)

[1675] Output: Sending daily report data to the server

[1676] Step 2: Send and store data

[1677] Terminal: The entered daily report data is sent to the server via the HTTPS protocol. The user clicks the "Send" button, and the data is transferred to the server.

[1678] Input: User's daily report data

[1679] Output: Daily report data sent to the server

[1680] Server: The received daily report data is saved in a database (e.g., MySQL, PostgreSQL). The database stores information such as the date, user ID, and task ID as records.

[1681] Input: Daily report data sent from the terminal

[1682] Output: Daily report data stored in the database

[1683] Step 3: Data cleansing and preprocessing

[1684] Server: Using Python and R scripts, the incoming daily report data is cleansed and inconsistencies and missing values ​​are corrected, for example, to standardize date formats and add specific tagging.

[1685] Input: Saved daily report data

[1686] Output: Cleansed and preprocessed data

[1687] Step 4: Run the evaluation model

[1688] Server: Analyzes the pre-processed data using a trained evaluation model (e.g., scikit-learn, TensorFlow). This model generates feedback based on the user's performance and areas for improvement.

[1689] Input: Cleansed and preprocessed data

[1690] Output: Generated feedback

[1691] Step 5: Generate and save your feedback

[1692] Server: Stores the generated feedback in a database. Feedback is managed for each user and stored for review.

[1693] Input: Feedback generated from the evaluation model

[1694] Output: Feedback stored in a database

[1695] Step 6: Submit your feedback

[1696] Server: Sends the saved feedback to the user's device via HTTPS protocol, and the feedback is ready for the user to receive.

[1697] Input: Feedback stored in the database

[1698] Output: Feedback sent to the user's device

[1699] Step 7: View your feedback

[1700] On the device: The user opens the application to view the feedback. The feedback is displayed in a list format. The user receives a notification and can view the details.

[1701] Input: Notification that feedback was received

[1702] Output: Feedback displayed on the terminal

[1703] Step 8: Analyze and generate career paths

[1704] Server: Based on the user's past evaluation data and career goals, the server proposes a career path that combines the evaluation data and goals. To this end, it analyzes data collected in advance and generates an optimal career plan.

[1705] Input: Past evaluation data, career goals

[1706] Output: Generated career path suggestions

[1707] Step 9: Submit and view your career path

[1708] Server: The generated career path is sent to the user's device using the HTTPS protocol, allowing the user to check the career path after it has been sent.

[1709] Input: Generated career path proposal

[1710] Output: Career path proposal sent to the user device

[1711] On the device: The user opens the application to view the career path suggestions and explore their options. Career paths are displayed in a dedicated section of the dashboard.

[1712] Input: Career path proposal

[1713] Output: Career path suggestions displayed on the device

[1714] Step 10: Consider business improvement measures

[1715] Users: Based on the feedback and career path suggestions, users consider ways to improve their work and decide on specific actions to take to plan their next work or personal development.

[1716] Input: Feedback and career path suggestions displayed

[1717] Output: Considered business improvement measures and career plans

[1718] In this way, through a series of processing steps, this system can efficiently generate evaluations and career plans from users' daily report data, ensuring transparency and consistency.

[1719] (Application example 1)

[1720] 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."

[1721] Current human resource development support systems mainly focus on evaluating employee performance and proposing career paths in office work, but do not address the evaluation and career development of operators engaged in practical work in factories. As a result, there is a lack of means to efficiently support factory operators in improving their skills and building their career paths. To solve this problem, a system is needed to collect, evaluate, and provide feedback on the work data of factory operators.

[1722] 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.

[1723] In this invention, the server includes means for collecting data such as employee daily report data, evaluation sheets, and human resource development charts in a database, means for cleansing and preprocessing the collected data, means for generating feedback for employees using a trained evaluation model, means for sending the generated feedback to the employee's terminal, means for proposing a career path based on the employee's past evaluation results and career goals, means for collecting factory robot operation data and operator daily work reports, means for preprocessing the collected robot operation data and providing feedback to the operator, and means for proposing improvements to robot operation skills based on the operator's evaluation results. This makes it possible to improve the skills of factory operators and create career paths.

[1724] "Employee daily report data" refers to data about the progress of work and completed tasks that employees record in their daily work reports.

[1725] An "evaluation sheet" is a written or electronic format for recording an employee's performance evaluation or performance rating.

[1726] A "human resources development chart" is a database that records employees' past evaluation results and education and training history.

[1727] "Data cleansing" is the process of improving data quality by correcting inconsistent data, filling in missing values, etc.

[1728] "Preprocessing" is the process of converting data into a format suitable for input into data analysis or machine learning models.

[1729] A "trained evaluation model" is an analytical model that has been trained by a machine learning algorithm using historical data.

[1730] "Feedback generation" is a process that generates written recommendations for improvement and evaluation results for employees based on evaluation data.

[1731] "Feedback transmission" is the process of sending the generated feedback to the employee's terminal.

[1732] "Career path proposal" is a process that suggests the next job or position an employee should take based on their evaluation data and career goals.

[1733] "Factory robot operation data" refers to data related to the tasks and actions performed by robots used in factories.

[1734] The "operator's daily work report" is daily report data recorded by a factory operator regarding the work content and progress of the day.

[1735] "Improving robot operation skills" is the process of making suggestions and providing training to improve factory operators' robot operation capabilities based on evaluation data.

[1736] This invention is a system for supporting the operation of robots in factories and the training of their operators. This system is composed of a server, terminals, and user elements, which work together to collect and process data, generate feedback, and propose career paths.

[1737] System configuration

[1738] 1. Server: Responsible for collecting and processing data, generating feedback, and proposing career paths. Python and machine learning frameworks (TensorFlow, PyTorch) are used to run the program.

[1739] 2. Device: An interface where users can enter their daily reports and view feedback and career path suggestions. Devices include smartphones and smart glasses.

[1740] 3. Users: Factory operators and their managers who use the system.

[1741] Overview of program processing

[1742] 1. Data collection phase:

[1743] Terminal: The user inputs the daily work report and sends the data to the server. For example, the user inputs "Robot A has completed the inspection work and is now on the next manufacturing task."

[1744] Server: Receives daily report data and saves it in the database. The data format is JSON.

[1745] 2. Data Processing Phase:

[1746] Server: Performs data cleansing and preprocessing, converting collected daily work report data and past evaluation materials into a unified format. For example, it corrects inconsistent data and imputes missing values. It uses the Python pandas library.

[1747] Server: Uses the trained evaluation model to prepare feedback and career path suggestions based on the data. Uses scikit-learn to train the machine learning model.

[1748] 3. Feedback generation phase:

[1749] Server: Inputs the daily work report data into the trained evaluation model and generates feedback based on common criteria. For example, it generates comments about the user's work progress and areas for improvement.

[1750] Server: Stores the generated feedback and prepares it for transmission to the user's device.

[1751] 4. Feedback provision phase:

[1752] Server: Sends feedback and notifies the user's device.

[1753] Device: The user sees the feedback, which is displayed through a smartphone app or smart glasses.

[1754] User: Consider ways to improve their own work based on the feedback provided.

[1755] 5. Career path proposal phase:

[1756] Server: Analyzes the evaluation data and proposes the optimal career path based on the operator's past evaluation results and career goals. For example, it generates a message such as, "Based on the evaluation results of Operator A, we propose training in machine maintenance."

[1757] Server: Sends career path suggestions to the user's device.

[1758] Terminal: User reviews career path suggestions and is offered options.

[1759] User: Review the proposed career paths and select the most suitable plan. Users can make future career plans based on the career paths provided.

[1760] Example prompt sentence:

[1761] "Based on the operators' daily reports, generate feedback on their work performance and areas for improvement in their next assignment. Also, provide career path suggestions."

[1762] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[1763] Step 1:

[1764] Terminal: The user inputs the daily work report. Specifically, the user uses a smartphone or smart glasses to record the work details, such as "Robot A's inspection work has been completed and it has moved on to the next manufacturing task," and presses the send button. The data entered includes the work details, date, completion status, etc., and is sent to the server in JSON format. The output is the data sent to the server.

[1765] Step 2:

[1766] Server: Receives the sent daily work report data and saves it in a database. Specifically, the server parses the received JSON data and stores it in a database (e.g., MySQL, PostgreSQL). The input is the daily work report data sent from the terminal, and the output is the data saved in the database.

[1767] Step 3:

[1768] Server: Cleanses and preprocesses the daily report data. Specifically, it uses Python's pandas library to complement missing data and correct inconsistent data. The input is the daily work report data stored in the database, and the output is the data after cleansing and preprocessing.

[1769] Step 4:

[1770] Server: Using the trained evaluation model, analyze the daily work report data and prepare for feedback generation. Specifically, the preprocessed data is input into a machine learning model (e.g., scikit-learn's RandomForestRegressor) to predict the user's work achievement and areas for improvement. The input is the preprocessed daily work report data, and the output is the evaluation results necessary for feedback generation.

[1771] Step 5:

[1772] Server: Generates feedback using the trained evaluation model. Specifically, it generates feedback sentences based on the evaluation results and provides specific advice, such as "Operator A's task achievement rate is 80%. It would be desirable to shorten the inspection time a little more for the next task." The input is the evaluation results, and the output is the generated feedback sentences.

[1773] Step 6:

[1774] Server: Sends the generated feedback to the user's device. Specifically, it sends a message to a smartphone or smart glasses using an API for notifying the device of the feedback. The input is the generated feedback text, and the output is the feedback displayed on the user's device.

[1775] Step 7:

[1776] Device: The user checks the feedback. Specifically, the user clicks on the notification on the device to check the feedback content. Based on the information obtained from the feedback, an action plan for the next task is considered. The input is the feedback sent from the server, and the output is the user's action plan based on the feedback.

[1777] Step 8:

[1778] Server: Analyzes evaluation data and proposes career paths based on the operator's past evaluation results and career goals. Specifically, it uses evaluation data to generate career path options, proposing content such as "Based on the evaluation results of Operator A, we propose training in machine maintenance." The input is evaluation data, and the output is a written career path proposal.

[1779] Step 9:

[1780] Server: Sends career path suggestions to the user's device. Specifically, similar to feedback, it sends career path suggestions using an API to notify the device. The input is the career path suggestion text, and the output is the career path suggestion displayed on the user's device.

[1781] Step 10:

[1782] Device: The user reviews the career path proposals and selects the most suitable plan. Specifically, the user clicks on the notification on the device to review the career path proposals and decides whether to adopt them as their own career plan. The input is the career path proposal sent from the server, and the output is the career plan selected by the user.

[1783] 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.

[1784] This invention is a human resource development support system that collects and processes data such as employee daily reports, evaluation sheets, and human resource development charts, and provides feedback and career path suggestions. This system incorporates an emotion engine that recognizes the user's emotions, and individual feedback and career path suggestions are adjusted taking into account the user's emotional state.

[1785] System configuration

[1786] Server: Performs functions of data collection, processing, feedback generation, career path suggestions, and sentiment analysis.

[1787] Terminal: Functions as an interface with the user, allowing them to enter daily reports, display feedback, transmit emotional data, and select career paths.

[1788] Users: Employees and managers who use the system.

[1789] Emotion Engine: Recognizes user emotions and reflects them in feedback and career path suggestions.

[1790] Overview of program processing

[1791] 1. Data Collection Phase

[1792] Terminal: The user enters a work report, for example, "I completed task A and started working on project B."

[1793] Terminal: Daily report data is automatically sent to the server.

[1794] 2. Data Processing Phase

[1795] Server: Stores the received daily report data in a database and performs data cleansing and preprocessing, filling in missing values ​​and standardizing the data.

[1796] Server: Uses the trained evaluation model to prepare feedback and career path suggestions.

[1797] 3. Feedback generation phase

[1798] Server: Inputs daily report data into the evaluation model and generates feedback. For example, it creates specific comments such as "User A is highly evaluated because he completed Task A efficiently."

[1799] Server: Analyzes the user's emotional data using the emotion engine. Adjusts the feedback based on the user's emotional state. For example, if the user is feeling stressed, the server adds a comment to the feedback such as "Please reconsider your work balance and take a rest."

[1800] 4. Feedback provision phase

[1801] Server: Sends the generated feedback to the user's device.

[1802] Terminal: Display feedback so that the user can see it.

[1803] 5. Emotional Data Collection Phase

[1804] Terminal: Collects emotional data from user input and reactions. The emotional data is sent to the server in real time.

[1805] Emotion Engine: Analyzes the emotion data collected from the user and evaluates their current emotional state.

[1806] 6. Career path proposal phase

[1807] Server: Analyzes the evaluation data and suggests the best career path. For example, "Based on User A's past evaluation results and technical skills, we suggest promotion to project manager."

[1808] Server: Uses an emotion engine to tailor career path suggestions to the user's emotional state. For example, if the user is feeling anxious, the server might add "support systems" or "training programs" to the suggestions.

[1809] Server: Sends career path suggestions to the user's device.

[1810] Terminal: User reviews career path suggestions.

[1811] User: Select your own career plan based on the suggestions.

[1812] Specific examples

[1813] Data Collection Phase

[1814] Terminal: User enters daily report. Example: "I completed task A and started working on new project B."

[1815] Server: Receives the data and stores it in a database.

[1816] Data Processing Phase

[1817] Server: Cleanses and pre-processes the collected daily report data. For example, record that task A is completed and new project B has started.

[1818] Server: Analyzes the data using the trained evaluation model.

[1819] Feedback generation phase

[1820] Server: Generates feedback. Example: "User A completes Task A efficiently and transitions quickly to new work."

[1821] Server: Uses the emotion engine to analyze the user's emotional state and reflect it in the feedback. For example, if the user is feeling stressed, add a comment such as "Please reconsider your work balance and take a rest."

[1822] Feedback provision phase

[1823] Server: Sends the generated feedback to the device.

[1824] Terminal: Show feedback and notify the user.

[1825] User: Review the feedback and decide on the next action.

[1826] Career path proposal phase

[1827] Server: Suggests optimal career paths. Example: "Based on the evaluation results of User A, we recommend promotion to project manager."

[1828] Server: Uses an emotion engine to generate career path suggestions that reflect the user's emotional state. For example, if the user is feeling anxious, add "support systems" and "training programs" to the suggestions.

[1829] Device: Display the suggestion and make it available for the user to review.

[1830] User: Review the proposals and choose the most suitable career plan.

[1831] The processing flow will be explained below.

[1832] Step 1:

[1833] Terminal: The user enters a daily work report. The user fills in the input form on the terminal with details of the day's work, progress, and any issues they encountered. For example, they might write, "I completed task A and started working on a new project B."

[1834] Step 2:

[1835] Terminal: Sends the entered daily report data to the server. After input is complete, the daily report data is automatically sent to the server. Transmission is secure using encrypted communication protocols such as SSL.

[1836] Step 3:

[1837] Server: Receives daily report data and saves it in the database. The server converts the received daily report data into an appropriate format and stores it in the database. When saving, a validation check is performed to confirm the consistency of the data.

[1838] Step 4:

[1839] Server: Performs data cleansing and preprocessing. Corrects errors and inconsistencies in the collected daily report data and converts it into a unified format. For example, it fills in missing values ​​and standardizes date formats.

[1840] Step 5:

[1841] Server: Analyzes the data using a trained evaluation model. The cleansed data is fed into the evaluation model, preparing it for feedback generation. The model is trained using machine learning algorithms, enabling highly accurate evaluations.

[1842] Step 6:

[1843] Server: Works with the device to collect user emotion data. The emotion engine runs and collects user input and reactions, such as keystroke speed and back arching.

[1844] Step 7:

[1845] Emotion engine: Analyzes collected data and evaluates the user's emotional state. For example, if a user types faster than usual, it recognizes that the user is under stress.

[1846] Step 8:

[1847] Server: The emotion data obtained from the emotion engine is reflected in the evaluation model and feedback is generated. For example, if a user is under stress, a comment such as "Please reconsider your work balance and take some rest" is added.

[1848] Step 9:

[1849] Server: Stores the generated feedback in a database and prepares it for transmission to the user's device.

[1850] Step 10:

[1851] Server: Sends the generated feedback to the user's device. Uses a notification system to notify the user that the feedback has arrived.

[1852] Step 11:

[1853] Terminal: Feedback is displayed and made available for the user to check. The user can check the feedback on their terminal and use it to improve their own work.

[1854] Step 12:

[1855] Server: Proposes optimal career paths based on evaluation data. Generates career paths taking into account past evaluation results, the user's skill set, and long-term career goals.

[1856] Step 13:

[1857] Server: Adjust the career path suggestions based on the results of the emotion engine. For example, if the user feels anxious, add support systems or training programs to the suggestions.

[1858] Step 14:

[1859] Server: Sends tailored career path proposals to the user's device.

[1860] Step 15:

[1861] Device: The career path proposal is displayed and made available for the user to review. The user reviews the proposal in detail and considers their own career plan.

[1862] Step 16:

[1863] User: Selects his / her own career plan based on the suggested career paths. The user considers the suggestions and selects the most suitable career path. For example, if a promotion to project manager is proposed, the user creates an action plan for that promotion.

[1864] Example 2

[1865] 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."

[1866] Although conventional human resource management systems can collect employee daily report data and evaluation sheets, they do not take into account the emotional state of each employee when making feedback or career path suggestions, which means that employee motivation and performance cannot be optimized, limiting the efficiency of the organization as a whole.In addition, because employee career path suggestions are standardized, flexible suggestions based on the characteristics and goals of each employee cannot be made.

[1867] The specific processing by the specific processing unit 290 of the data processing device 12 in the second embodiment is realized by the following means.

[1868] In this invention, the server includes a means for collecting data such as employee daily reports, evaluation sheets, and human resource development charts in a database, a means for cleansing and preprocessing the collected data, a means for generating feedback for employees using a trained evaluation model, a means for analyzing user emotion data and adjusting the feedback and career path suggestions, and a means for sending the generated feedback to the employee's terminal. This enables flexible and appropriate feedback and career path suggestions that take into account the emotional state of each employee.

[1869] A "database" is a system for storing, managing, and searching data in an organized manner.

[1870] "Data cleansing" is the process of filling in missing values, correcting inaccurate data, and standardizing it.

[1871] "Preprocessing" refers to the preparatory work done before inputting data into data analysis or machine learning models, and includes data formatting and normalization.

[1872] An "evaluation model" is a trained algorithm that evaluates employee performance based on input data and generates feedback.

[1873] "Feedback" refers to evaluations and comments on employees' performance, with the aim of improving work and increasing motivation.

[1874] "Emotional data" is data used to measure and analyze a user's emotional state, and is collected from the user's input, reactions, etc.

[1875] A "career path" is the path of goals and positions that an employee should pursue within a company, including plans for growth and promotion.

[1876] The "Emotion Engine" is a system that analyzes users' emotional data and reflects it in feedback and career path suggestions.

[1877] "Collection means" refers to the method or system for collecting daily report data, evaluation sheets, etc. into a database.

[1878] "Cleansing and preprocessing means" refers to methods and systems used to prepare collected data and make it suitable for analysis.

[1879] "Feedback generator" means a method or system for generating ratings and comments for employees using a trained rating model.

[1880] "Emotion data analysis means" refers to a method or system for analyzing a user's emotional data and reflecting the results in feedback and career path suggestions.

[1881] "Transmission means" refers to a method or system for sending the generated feedback and career path suggestions to the employee's terminal.

[1882] This invention relates to a human resource development support system that collects and processes data such as employee daily reports, evaluation sheets, and human resource development charts, and provides feedback and career path suggestions. This system incorporates an emotion engine that recognizes the user's emotions, and the feedback and career path suggestions are adjusted taking into account the user's emotional state.

[1883] System configuration

[1884] Server: Performs functions such as data collection, processing, feedback generation, career path suggestions, and sentiment analysis. The server can utilize cloud-based infrastructure (e.g., AWS, Google Cloud).

[1885] Terminal: Functions as an interface with the user, allowing them to input daily reports, display feedback, transmit emotional data, and select career paths. Terminals include, for example, personal computers and smartphones.

[1886] Users: Employees and managers who use the system.

[1887] Emotion engine: Recognizes the user's emotions and reflects them in feedback and career path suggestions. For example, the IBM Watson Tone Analyzer can be used as an emotion engine.

[1888] Data collection

[1889] The terminal provides an interface for users to input daily work reports. The daily report data entered by the user is sent from the terminal to a server. The transmission is secure using a security protocol (e.g., HTTPS). The server stores the received daily report data in a database. This database uses a database management system such as "PostgreSQL."

[1890] Data Processing

[1891] The server cleanses and preprocesses the daily report data stored in the database. This process includes filling in missing values ​​and standardizing the data. Cleansing and preprocessing improves the accuracy and reliability of the data. A trained evaluation model can be built using TensorFlow, for example. The daily report data is input into this evaluation model and analyzed.

[1892] Feedback Generation

[1893] The server creates feedback based on the data generated by the evaluation model. For example, it generates a comment such as, "Employee A is highly evaluated because he completed Task A efficiently." The server also analyzes the user's emotional data using an emotion engine and adjusts the content of the feedback. For example, if the user is feeling stressed, it adds a comment such as, "It is recommended that you reconsider your work balance and take a rest."

[1894] Providing Feedback

[1895] The server sends the generated feedback to the user's device. For example, a notification service such as Firebase Cloud Messaging can be used for this purpose. The device displays the feedback and notifies the user.

[1896] Emotional Data Collection

[1897] The device collects emotional data from the user's input and reactions, which is then sent to a server in real time and analyzed by an emotion engine.

[1898] Career path suggestions

[1899] The server proposes optimal career paths based on the collected and analyzed evaluation data. For example, it generates a proposal such as, "Based on Employee A's past evaluation results and technical skills, we propose promotion to project manager." The server can also use an emotion engine to adjust the proposal content according to the user's emotional state. For example, if the user is feeling anxious, it can add a "support system" or "training program" to the proposal. The career path proposal is sent to the terminal, and the user can select their own career plan based on the proposal.

[1900] Specific examples

[1901] For example, a user enters a daily report stating, "I completed Task A and started working on new Project B." This data is sent to the server via the device and stored in a database. The server cleanses and preprocesses the data, inputs it into an evaluation model, and generates feedback. The generated feedback might be, "User A completed Task A efficiently and is moving quickly to new work." Furthermore, if the user is determined to be feeling stressed, a comment such as, "Please reconsider your work balance and take a rest" is added.

[1902] Prompt Sentence Examples

[1903] "Please explain the program of a system that generates feedback based on employees' daily report data and suggests career paths that reflect the user's emotional state. Please explain the process in detail using specific examples."

[1904] This system enables flexible and appropriate feedback and career path suggestions that take into account employees' emotional state, which is expected to improve efficiency and motivation throughout the organization.

[1905] The flow of the identification process in the second embodiment will be described with reference to FIG.

[1906] Step 1:

[1907] The user inputs a daily work report. The user uses a terminal to input daily report data, such as "Task A completed and started working on new project B." Once input is complete, the data is automatically sent from the terminal to the server.

[1908] Step 2:

[1909] The terminal sends the daily report data to the server. A security protocol (e.g. HTTPS) is used for transmission, and the data is transferred safely. Terminal input: Daily report data entered by the user. Output: Daily report data sent.

[1910] Step 3:

[1911] The server stores the received daily report data in a database. For example, "PostgreSQL" is used as the database. Server input: Daily report data sent from the terminal. Output: Daily report data stored in the database.

[1912] Step 4:

[1913] The server performs data cleansing and preprocessing. The server fills in any missing values ​​in the daily report data and standardizes the data. Server input: Daily report data read from the database. Output: Data after cleansing and preprocessing.

[1914] Step 5:

[1915] The server analyzes the data using a trained evaluation model, for example, a model built using TensorFlow. Server input: cleansed and preprocessed data. Output: analysis results.

[1916] Step 6:

[1917] The server generates feedback based on the data generated by the evaluation model. For example, it generates specific comments such as "Employee A is highly evaluated because he completed task A efficiently." Server input: Analysis results. Output: Generated feedback.

[1918] Step 7:

[1919] The server uses an emotion engine to analyze the user's emotion data and adjust the feedback content. The emotion engine used is something like "IBM Watson Tone Analyzer." For example, if the user is feeling stressed, it adds a comment saying, "We recommend that you reconsider your work balance and take a rest." Server input: Feedback and emotion data. Output: Adjusted feedback.

[1920] Step 8:

[1921] The server sends the generated feedback to the user's device. This is done using a notification service such as Firebase Cloud Messaging. Server input: Adjusted feedback. Output: Feedback sent to the user's device.

[1922] Step 9:

[1923] The device displays feedback and notifies the user. Notifications can be done using popup messages or in-app notifications. Device input: Feedback sent from the server. Output: Feedback displayed to the user.

[1924] Step 10:

[1925] The user checks the feedback on the device, and as a next step, decides on the next action and reflects it in their work.

[1926] Step 11:

[1927] The device collects emotional data from the user's input and reactions. Emotional data is collected using the user's keystroke analysis and screen touch data. Device input: User's input and reactions. Output: Collected emotional data.

[1928] Step 12:

[1929] The device sends the collected emotion data to the server in real time. Device input: Collected emotion data. Output: Emotion data sent to the server.

[1930] Step 13:

[1931] The emotion engine analyzes the user's emotional state on the server and records it in the emotion database. The analysis results are used as feedback for the generative AI model. Server input: collected emotion data. Output: analysis results and recorded emotion data.

[1932] Step 14:

[1933] The server analyzes the user's daily report data and past evaluation data to propose the optimal career path. For example, it generates a proposal such as "Based on the evaluation results of employee A, recommend promotion to project manager." Server input: Daily report data and past evaluation data. Output: Career path proposal.

[1934] Step 15:

[1935] The server uses an emotion engine to adjust the career path suggestions to fit the user's emotional state. For example, if the user is feeling anxious, the suggestions will be adjusted to include "support systems" and "training programs." Server input: Career path suggestions and emotion data. Output: Adjusted career path suggestions.

[1936] Step 16:

[1937] The server sends the career path proposal to the user's device. Server input: Adjusted career path proposal. Output: Career path proposal sent to the user's device.

[1938] Step 17:

[1939] The terminal displays the career path proposal for the user to review. Terminal input: Career path proposal sent from the server. Output: Career path proposal displayed to the user.

[1940] Step 18:

[1941] The user checks the career path suggestions on the terminal and selects the most suitable career plan. The selected career plan is sent back to the server and recorded in the database. User input: Career plan selection. Output: Selected career plan sent to the server.

[1942] The above is the specific processing flow of the program of this system.

[1943] (Application example 2)

[1944] 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."

[1945] While conventional human resource development support systems can provide feedback based on employee daily reports and evaluations, they lack the ability to provide feedback and career path suggestions that take into account employees' emotional states and the operation data of the machines used on-site. Furthermore, particularly in manufacturing sites, they are unable to provide feedback or career path suggestions that include production data and error history from machines such as robots, making it difficult to efficiently manage personnel and machines and improve their performance. Another problem is the inability to analyze emotional data collected in real time and adjust feedback accordingly.

[1946] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 2 is realized by the following means.

[1947] In this invention, the server includes means for collecting employee daily report data, evaluation sheets, human resource development charts, product production data, error history, and operator feedback data in a database, means for cleansing and preprocessing the collected data, means for generating feedback for employees and machines using a trained evaluation model, means for transmitting the generated feedback to the terminals of the employees and machine operators, means for proposing career paths for the employees and machine operators based on their past evaluation results and career goals, means for collecting and analyzing emotional data for the machine operators in real time, and means for adjusting the feedback and career path proposals based on their emotional states. This enables efficient feedback and career path proposals that take into account the emotional states of the employees and machine operators and the machine's production data.

[1948] "Employee daily report data" refers to data in which employees record their daily work progress and completed tasks.

[1949] An "appraisal sheet" is a written or electronic format used for the purpose of evaluating an employee's performance or skills.

[1950] A "human resources development chart" is a data sheet that records an employee's skills, career path, training history, etc.

[1951] "Product production data" refers to data that records the work content and production results of machines and robots used in manufacturing sites.

[1952] "Error history" is data that records details of errors and malfunctions that occur during manufacturing processes or machine operation.

[1953] "Operator feedback data" is data that records opinions and evaluations submitted by employees in charge of operating machines or robots regarding their work.

[1954] "Means of collecting data in a database" refers to functions and systems for organizing various data and storing it centrally.

[1955] "Data cleansing and preprocessing means" refers to functions and systems that perform preprocessing to improve data quality, such as filling in missing data values ​​and removing outliers.

[1956] A "trained evaluation model" is an algorithm or system that learns from past data and predicts and evaluates the performance of employees or machines.

[1957] "Means for generating feedback" refers to functions or systems for providing appropriate advice and areas for improvement based on the evaluation results.

[1958] The "means for sending feedback" refers to a communication function or system for delivering the generated feedback to the terminals of employees or operators.

[1959] "Means for suggesting career paths" are functions or systems that show employees and operators the optimal career path based on their past performance and goals.

[1960] "Means for collecting and analyzing emotional data in real time" refers to functions and systems for obtaining the emotional state of employees and operators in a timely manner and analyzing that data.

[1961] The "means for adjusting feedback and career path suggestions based on emotional state" refers to a function or system that optimizes the content of feedback and career path suggestions based on analyzed emotional data.

[1962] This invention is a system for collecting and processing employee daily report data, evaluation sheets, human resource development charts, product production data, error history, and operator feedback data, and providing feedback and career path suggestions. This system includes an emotion engine that analyzes emotional states and reflects them in feedback and career path suggestions.

[1963] The main components of the system are as follows:

[1964] Server: Responsible for data collection, data cleansing, pre-processing, feedback generation, career path suggestions, and sentiment analysis.

[1965] Terminal: Serves as an interface with the user, allowing them to enter daily reports, view feedback, send emotional data, and select career paths.

[1966] Users: Employees and machine operators who use the system.

[1967] Emotion Engine: Recognizes user emotions and reflects them in feedback and career path suggestions.

[1968] The system first collects daily report data and feedback data from employees and operators via their terminals and sends it to the server. The server stores the received data in a database and performs data cleansing and preprocessing. This process is performed using the Python pandas library, for example, by filling in missing values ​​and standardizing the data. Next, the trained evaluation model is used to generate feedback for employees and machine operators. The scikit-learn library is used to train the evaluation model.

[1969] The generated feedback is sent from the server to the device and displayed for the user to review. For example, if an employee enters "I completed Task A and started working on new Project B," the feedback displayed will read, "I commend you for completing Task A efficiently and moving quickly to new work."

[1970] The emotion engine also analyzes the user's emotional state and adjusts the feedback accordingly. For example, if the user is feeling stressed, it might add a comment like, "Reconsider your work balance and take a break." The nltk library is used to analyze emotion data. In particular, the nltk.sentiment library is used for emotion analysis.

[1971] Furthermore, the server suggests career paths based on the user's past evaluation results and career goals. For example, it might suggest, "Based on User A's past evaluation results, we suggest transitioning to a new position exclusively for Process Z." The content of this suggestion is also adjusted according to the user's emotional state. For example, if the user is feeling anxious, it might add a "training session for a smooth transition."

[1972] As a concrete example, when a user inputs a daily report, the prompt may be something like, "Please write specifically about today's work. For example, the robot frequently produced errors, but the cause was identified and corrected." This prompt is important for maintaining consistency in the input data.

[1973] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[1974] Step 1:

[1975] Data Collection Phase

[1976] Terminals: Users (employees and machine operators) enter daily report data and feedback data. For example, an employee may enter "I have completed task A and started working on new project B."

[1977] Input: Daily report data, feedback data

[1978] Output: Raw data collected

[1979] Specific operation: When a user enters data using a dedicated application and presses the "Submit" button, the data is sent to the server in real time.

[1980] Step 2:

[1981] Data transmission phase

[1982] Terminal: Automatically sends collected daily report data and feedback data to the server.

[1983] Input: Raw data collected

[1984] Output: Data sent to the server

[1985] Specific operation: The terminal uploads data to the server via the network and stores it in the database.

[1986] Step 3:

[1987] Data cleansing and preprocessing phase

[1988] Server: Cleanses and preprocesses the received data, specifically filling in missing values ​​and standardizing the data.

[1989] Input: Data stored on the server

[1990] Output: Preprocessed and clean data

[1991] Specific operation: Create a data frame using Python's pandas library, impute missing values, and standardize.

[1992] Step 4:

[1993] Feedback generation phase

[1994] Server: Uses the trained evaluation model to generate feedback, such as "User A completed task A efficiently and therefore deserves high praise."

[1995] Input: Preprocessed and clean data

[1996] Output: Generated feedback

[1997] What it does: Uses the scikit-learn library to input data into an evaluation model and generate feedback based on the prediction results.

[1998] Step 5:

[1999] Sentiment Analysis Phase

[2000] Server: Uses an emotion engine to analyze the emotional state from the user's input and reactions.

[2001] Input: User input data, response data

[2002] Output: Parsed emotional state

[2003] Specific operation: Analyzes emotional states using the nltk.sentiment module of the nltk library.

[2004] Step 6:

[2005] Feedback Adjustment Phase

[2006] Server: Adjust the feedback based on the analyzed emotional state. For example, if the user is feeling stressed, add a comment like "Please rebalance your work and take some rest."

[2007] Input: Generated feedback, parsed emotional state

[2008] Output: Regulated Feedback

[2009] Specific operation: Using the results of sentiment analysis, the feedback content is modified appropriately and the final feedback sentence is generated.

[2010] Step 7:

[2011] Feedback sending phase

[2012] Server: Sends the generated feedback to the user's device.

[2013] Input: Calibrated Feedback

[2014] Output: Feedback sent to the terminal

[2015] Specific operation: Sends data from the server to the device and displays a notification on the device.

[2016] Step 8:

[2017] Feedback display phase

[2018] Terminal: Display feedback so that the user can see it.

[2019] Input: Feedback sent by the server

[2020] Output: Displayed feedback

[2021] Specific operation: The feedback content is displayed on the device's user interface and the user is notified.

[2022] Step 9:

[2023] Career path proposal phase

[2024] Server: Proposes a career path based on the user's past evaluation results and career goals. For example, "Based on User A's past evaluation results, we propose a transition to a new, dedicated role in Process Z."

[2025] Input: User's past evaluation results, career goals

[2026] Output: Generated career path suggestions

[2027] Specific actions: Analyze evaluation data, generate appropriate career paths, and create proposals.

[2028] Step 10:

[2029] Career path proposal adjustment phase

[2030] Server: Uses an emotion engine to tailor career path suggestions based on the user's emotional state. For example, if the user is feeling anxious, add a "training session for a smooth transition."

[2031] Input: Generated career path suggestions, analyzed emotional states

[2032] Output: Tailored career path suggestions

[2033] Specific operation: Based on the results of the sentiment analysis, the content of the career path is modified as appropriate and the final proposal is generated.

[2034] Step 11:

[2035] Career path submission phase

[2036] Server: Sends the generated career path proposal to the terminal.

[2037] Input: Tailored career path proposals

[2038] Output: Career path proposal sent to the device

[2039] Specific operation: Sends data from the server to the device and displays a notification on the device.

[2040] Step 12:

[2041] Career path display phase

[2042] Terminal: Display career path suggestions and make them available for user review.

[2043] Input: Career path proposal sent from the server

[2044] Output: Displayed career path suggestions

[2045] Specific operation: The career path suggestions are displayed on the device's user interface and notified to the user.

[2046] The specific processing unit 290 transmits the result of the specific processing to the robot 414. In the robot 414, the control unit 46A causes the speaker 240 and the control target 443 to output the result of the specific processing. The microphone 238 acquires voice indicating a user input regarding the result of the specific processing. The control unit 46A transmits voice data indicating the user input acquired by the microphone 238 to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the voice data.

[2047] 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.

[2048] In the above embodiment, an example was given in which the specific processing is performed by the data processing device 12, but the technology of the present disclosure is not limited to this, and the specific processing may be performed by the robot 414.

[2049] The emotion identification model 59 as an emotion engine may determine the user's emotion according to a specific mapping. Specifically, the emotion identification model 59 may determine the user's emotion according to an emotion map (see FIG. 9), which is a specific mapping. Similarly, the emotion identification model 59 may determine the robot's emotion, and the identification processing unit 290 may perform identification processing using the robot's emotion.

[2050] FIG. 9 is a diagram illustrating an emotion map 400 on which multiple emotions are mapped. In the emotion map 400, emotions are arranged in concentric circles radiating from the center. Emotions closer to the center of the concentric circles are more primitive. Emotions representing states and actions arising from a state of mind are arranged on the outer edges of the concentric circles. The concept of emotion includes both affect and mental states. Emotions generally generated from reactions occurring in the brain are arranged on the left side of the concentric circles. Emotions generally induced by situational judgment are arranged on the right side of the concentric circles. Emotions generally generated from reactions occurring in the brain and induced by situational judgment are arranged on the upper and lower sides of the concentric circles. Furthermore, the emotion of "pleasure" is arranged on the upper side of the concentric circles, and the emotion of "discomfort" is arranged on the lower side. In this way, in the emotion map 400, multiple emotions are mapped based on the structure by which emotions are generated, and emotions that tend to occur simultaneously are mapped close to each other.

[2051] These emotions are distributed in the 3 o'clock direction on emotion map 400, and typically fluctuate between relief and anxiety. In the right half of emotion map 400, situational awareness dominates over internal sensations, resulting in a sense of calm.

[2052] The inside of emotion map 400 represents what is going on in the mind, and the outside of emotion map 400 represents behavior, so the further you go outside emotion map 400, the more visible the emotions become (the more they are expressed in behavior).

[2053] Human emotions are based on various balances, such as posture and blood sugar levels. When these balances deviate from the ideal, a state of discomfort is indicated, and when they approach the ideal, a state of pleasure is indicated. Emotions can also be created for robots, automobiles, and motorcycles, based on various balances, such as posture and remaining battery life. When these balances deviate from the ideal, a state of discomfort is indicated, and when they approach the ideal, a state of pleasure is indicated. An emotion map can be generated, for example, based on Dr. Mitsuyoshi's emotion map (Research on Voice Emotion Recognition and Emotional Brain Physiological Signal Analysis Systems, Tokushima University, Doctoral Dissertation: https: / / ci.nii.ac.jp / naid / 500000375379). The left half of the emotion map lists emotions belonging to the "reaction" domain, where sensation is dominant. The right half of the emotion map lists emotions belonging to the "situation" domain, where situational awareness is dominant.

[2054] The emotion map defines two emotions that promote learning. One is a negative emotion on the situation side, around the middle of "repentance" or "reflection." In other words, this occurs when the robot experiences negative emotions such as "I never want to feel this way again" or "I don't want to be scolded again." The other is a positive emotion on the response side, around "desire." In other words, this occurs when the robot experiences positive feelings such as "I want more" or "I want to know more."

[2055] The emotion identification model 59 inputs user input into a pre-trained neural network, obtains emotion values ​​indicating each emotion shown in the emotion map 400, and determines the user's emotion. This neural network is pre-trained based on multiple pieces of training data that are combinations of user input and emotion values ​​indicating each emotion shown in the emotion map 400. Furthermore, this neural network is trained so that emotions that are located close to each other have similar ...

Claims

1. A means of collecting data such as employee daily reports, evaluation sheets, and human resource development charts into a database, a means of cleansing and pre-processing the collected data; a means of generating feedback for employees using the trained evaluation model; a means for transmitting the generated feedback to an employee's device; A means of suggesting career paths based on employees' past evaluation results and career goals, and A system including:

2. 2. The system according to claim 1, further comprising means for receiving employee daily report data from a terminal and storing the data in a database.

3. The system of claim 1 , further comprising means for performing evaluation based on a unified standard using the trained evaluation model.

Images