system

Abstract

Provide a system. A data collection device is provided for collecting operation data; means for preprocessing the collected data by a data preprocessing device; A means for calculating an evaluation score based on data preprocessed by a generative artificial intelligence model; means for generating an assessment report based on the assessment scores; A means for making the evaluation report available for viewing; a means for recording feedback data and updating the evaluation model; A system including:

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] Traditionally, evaluations of employee work efficiency and contribution have relied on the judgment of superiors, which is heavily subjective, and have often lacked fairness and objectivity. Furthermore, stress and dissatisfaction caused by superiors' evaluations can sometimes lead to a decline in employee motivation. Furthermore, the evaluation process itself is time-consuming and labor-intensive, making it difficult to carry out efficiently. For this reason, there is a need for a system that can accurately evaluate employee contributions in a fair and efficient manner. [Means for solving the problem]

[0005] The present invention solves the above-mentioned problems with a system that includes a data collection device, a data preprocessing device, a generative AI model, and an evaluation report generator. Specifically, the data collection device automatically collects task completion status and progress data from a management tool, and the data preprocessing device formats and standardizes this data. The generative AI model calculates evaluation scores based on the preprocessed data, and the evaluation report generator generates a fair evaluation report based on the results. This allows for objective and efficient evaluation of employee contributions. Furthermore, by recording feedback data and retraining the generative AI model to improve its performance, the accuracy of evaluations can be continuously improved. This comprehensive system can improve employee motivation and achieve a fair evaluation process.

[0006] The "data collection device" is a device that automatically collects task completion and progress data from employees' work content, progress, and achieved goals, as well as project management tools.

[0007] A "data preprocessing device" is a device that formats and standardizes collected data and supplements missing information.

[0008] A "generative artificial intelligence model" is an algorithm or program that calculates an employee evaluation score based on pre-processed data and in accordance with specific evaluation criteria.

[0009] The "evaluation report generation device" is a device that automatically generates an employee evaluation report based on the evaluation score.

[0010] "Feedback data" is data that records the results of discussions between employees and their superiors based on evaluation results and areas for improvement.

[0011] "Retraining" is the process of updating a generative AI model with new feedback data to improve its evaluation accuracy. [Brief explanation of the drawings]

[0012] [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 illustrating 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

[0013] 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.

[0014] First, the terms used in the following description will be explained.

[0015] 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).

[0016] 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.

[0017] 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.

[0018] 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.

[0019] 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."

[0020] [First embodiment]

[0021] FIG. 1 shows an example of the configuration of a data processing system 10 according to the first embodiment.

[0022] 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.

[0023] 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).

[0024] 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.

[0025] 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.

[0026] 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.

[0027] 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.

[0028] FIG. 2 shows an example of the main functions of the data processing device 12 and the smart device 14.

[0029] 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.

[0030] 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.

[0031] 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.

[0032] 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."

[0033] The present invention provides a system for fairly and objectively evaluating the work efficiency and contribution of employees. Specific embodiments of the system are described below.

[0034] System Configuration

[0035] This system consists of multiple terminals and a server. The terminals are devices (such as PCs or tablets) that employees use to input data, and the server is the main processing device for collecting, preprocessing, and analyzing data, as well as generating and updating evaluation reports.

[0036] Program processing overview

[0037] Data collection

[0038] User (employee): The user inputs the details of his / her daily work, progress, goals achieved, and time used into the terminal using a dedicated interface.

[0039] Server: The server automatically collects task completion and progress data from project management tools (e.g., JIRA, Trello, Redmine), thereby integrating manual and automatically collected data.

[0040] Data Preprocessing

[0041] Server: The server formats and standardizes the collected data, checking for missing information, and in the process removing noise from the data and converting it into a unified format.

[0042] Evaluation by AI model

[0043] Server: The server inputs the preprocessed data into a generative AI model to calculate an evaluation score for each employee. The score is calculated based on multiple categories, including work efficiency, productivity, and work quality.

[0044] Evaluation report generation

[0045] Server: The server generates an evaluation report based on the evaluation scores, which includes the score for each category, the reason for the evaluation, areas for improvement, and a specific action plan.

[0046] Device: Users (employees and managers) can view the generated evaluation report and check the next goal setting and initiatives.

[0047] Feedback Loop

[0048] Users (employees and supervisors): Users (employees and supervisors) conduct feedback interviews based on the evaluation report. The feedback and improvements that emerged from the interviews are entered back into the system and reflected in the next evaluation cycle.

[0049] Server: The server retrains the generative AI model based on the feedback data to improve the accuracy of the evaluation.

[0050] Specific examples

[0051] For example, the evaluation of a project manager involves the following steps:

[0052] 1. User (Project Manager): Enters project progress, completed tasks, and team member contributions into the device.

[0053] 2. Server: The server automatically collects task completion and progress data from project management tools and consolidates all the data.

[0054] 3. Server: The data preprocessing unit formats this data, and the generative AI model calculates an evaluation score based on this.

[0055] 4. Server: Generates an evaluation report for the project manager based on the evaluation scores.

[0056] 5. Users (project managers and superiors): Users conduct feedback interviews based on the evaluation reports and enter improvements into the system as feedback.

[0057] 6. Server: The server takes the feedback data, retrains the AI ​​model, and reflects it in the next evaluation.

[0058] In this way, this system comprehensively manages a series of processes from data collection to evaluation and feedback loop, enabling objective and fair evaluation of employees.

[0059] The processing flow will be explained below.

[0060] Step 1: Data collection

[0061] User (employee): Enters daily work details, progress, achieved goals, usage time, etc. into a dedicated form on the device.

[0062] Server: Automatically collects task completion status, progress data, work logs, etc. from project management tools (e.g., JIRA, Trello, Redmine).

[0063] Step 2: Data Preprocessing

[0064] Server: Formats the collected data, such as normalizing text data, standardizing the format of time series data, and filling in missing values.

[0065] Server: The server removes noise from the collected data and converts it into the format required for evaluation, for example by filtering and standardizing the data.

[0066] Step 3: Evaluation by AI model

[0067] Server: Inputs the preprocessed data into the generative artificial intelligence model.

[0068] Server: The AI ​​model analyzes the data and calculates an evaluation score for each employee based on their work efficiency, contribution, goal achievement, etc.

[0069] Specific operation: Calculate a score based on each employee's work time, number of completed tasks, project progress, etc. Evaluation criteria include project success rate, work accuracy, productivity, etc.

[0070] Step 4: Generate an assessment report

[0071] Server: Generates an evaluation report for each employee based on the evaluation score. The report includes the evaluation score, the reason for the evaluation for each item, areas for improvement, and specific advice.

[0072] Terminal: Users (employees and managers) can view the generated evaluation report, understand their own evaluation, and identify areas for improvement.

[0073] Step 5: Provide feedback

[0074] Users (employees and managers): Conduct feedback interviews based on the evaluation reports. Enter the details of the interviews and points for improvement into the system.

[0075] Specific actions: The supervisor will refer to the evaluation report and provide specific advice to the employee, identifying areas for improvement and setting goals for the next time. The employee will then create a specific action plan based on the feedback.

[0076] Step 6: Retrain the model

[0077] Server: Collects feedback data and adds it to the training dataset of the generative AI model.

[0078] Server: Retrains the AI ​​model using new data and makes adjustments to improve the accuracy of the evaluation.

[0079] Server: Deploys the updated model to the system and makes it available for the next evaluation cycle.

[0080] Through these specific processing steps, fair and objective employee evaluations become possible, improving the efficiency and accuracy of the entire evaluation process.

[0081] Example 1

[0082] 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."

[0083] In today's business environment, it is extremely important to fairly and objectively evaluate employees' work efficiency and contributions. However, the evaluation process is complicated and subjective. Traditional evaluation systems also face issues such as being prone to human bias and lacking transparency and consistency. Furthermore, the lack of specific areas for improvement and action plans based on evaluation results makes it difficult to improve employee performance. There is a need to resolve these issues and build a fair and objective evaluation system.

[0084] 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.

[0085] In this invention, the server includes: means for collecting work data using a data collection device; means for users to input work content, progress, goals, and usage time into a terminal using a dedicated interface; means for the server to collect task completion status and progress data from a project management tool; means for standardizing and formatting the collected data using a data preprocessing device; means for processing missing data and noise data; means for calculating evaluation scores based on data preprocessed by a generative AI model; means for generating evaluation reports based on the evaluation scores; means for making the evaluation reports viewable; and means for recording feedback data and updating the evaluation model. This enables fair and objective evaluation by collecting detailed and consistent employee work data and evaluating them using a generative AI model based on preprocessed data. Furthermore, the evaluation report presents specific areas for improvement and action plans, contributing to improved employee performance.

[0086] A "data collection device" is a device for collecting data entered by a user or information automatically acquired from an external tool.

[0087] A "user" is a person who uses the system to input information such as work content, progress, goals, and usage time.

[0088] "Terminal" refers to a device used by a user to input data or view an evaluation report, including a PC or tablet.

[0089] "Server" is the central processing unit responsible for data collection, automated processing, analysis, and generation of evaluation reports.

[0090] A "project management tool" is software used to manage tasks and track progress, including tools such as JIRA and Trello.

[0091] A "data preprocessing device" is a device that standardizes and formats collected data and processes missing data and noise.

[0092] A "generative artificial intelligence model" is an artificial intelligence algorithm for calculating evaluation scores based on preprocessed data.

[0093] The "evaluation score" is a numerical indicator of a user's work efficiency and productivity calculated by a generative artificial intelligence model.

[0094] An "assessment report" is a document generated based on an assessment score, which includes details of the score, reasons for the assessment, areas for improvement, and a specific action plan.

[0095] "Feedback data" refers to information, including improvements and comments, that users input into the system based on feedback interviews.

[0096] "Retraining" is the process of using collected feedback data to improve the accuracy of a generative artificial intelligence model.

[0097] "Deployment" refers to running a retrained artificial intelligence model in a real system environment.

[0098] The present invention relates to a system for fairly and objectively evaluating the work efficiency and contribution of employees. This system is composed of multiple terminals and a server. Specific embodiments of the system are described below.

[0099] System Configuration

[0100] This system is configured as follows: The terminal is a device for users to input data, and the server is a device that performs the main processing for data collection, pre-processing, analysis, and generation and updating of evaluation reports.

[0101] Hardware and Software

[0102] Device: An input device such as a computer or tablet.

[0103] Server: A high-performance computer for data processing.

[0104] Project management tools: e.g., JIRA, Trello, Redmine, etc.

[0105] Generative artificial intelligence model: Uses machine learning frameworks such as TENSORFLOW (registered trademark) and PyTorch.

[0106] Program processing overview

[0107] Data collection

[0108] User (employee): The user inputs the details of daily work, progress, goals, and usage time into the terminal using a dedicated interface.

[0109] Server: The server automatically collects task completion and progress data from your project management tools, and consolidates all the data in one place using API requests.

[0110] Data Preprocessing

[0111] Server: The server formats and standardizes the collected data, and processes missing and noisy data. This process involves data cleansing using Python scripts.

[0112] Evaluation by AI model

[0113] Server: The preprocessed data is input into the generative AI model, and an evaluation score for each user is calculated using TensorFlow's Predict method.

[0114] Server: Generates an evaluation report based on the calculated evaluation score. The evaluation report includes details of the score, reasons for the evaluation, areas for improvement, and a specific action plan.

[0115] Viewing evaluation reports and providing feedback

[0116] Terminal: Users (employees and managers) view the evaluation report and check its contents.

[0117] Users (employees and supervisors): Users conduct feedback interviews based on the evaluation reports and enter the results of the interviews and areas for improvement into the system.

[0118] Feedback Loop

[0119] Server: Retrains the generative AI model based on the feedback data to improve the accuracy of the evaluation.

[0120] Server: Deploys the retrained model to the system and maintains consistent evaluation metrics.

[0121] Specific examples

[0122] For example, the project manager evaluation process involves the following steps:

[0123] 1. User (Project Manager): Enters project progress, completed tasks, and team member contributions into the device.

[0124] 2. Server: Automatically collects task completion and progress data from project management tools (e.g., JIRA or Trello) and consolidates all data.

[0125] 3. Server: The data preprocessing unit formats this data, and the generative AI model calculates an evaluation score based on it.

[0126] 4. Server: Generates an evaluation report for the project manager based on the evaluation scores.

[0127] 5. Users (project managers and superiors): Users conduct feedback interviews based on the evaluation reports and enter improvements into the system.

[0128] 6. Server: Ingests the feedback data, retrains the AI ​​model, and reflects it in the next evaluation.

[0129] Prompt Sentence Examples

[0130] "Please describe your contributions this week. Detail the specific tasks, results, and goals you achieved."

[0131] This system enables objective and fair evaluation of employees by managing a series of processes from data collection to evaluation and feedback loop in an integrated manner.

[0132] The flow of the identification process in the first embodiment will be described with reference to FIG.

[0133] Step 1:

[0134] Data collection

[0135] User (employee): The user uses a dedicated interface to input work content, progress, goals, and usage time into the terminal.

[0136] Input: Work, progress, goals, and time spent.

[0137] Output: The input working data.

[0138] Specific operation: The user uses a computer or tablet to enter data into a form on a web browser and presses the "Submit" button.

[0139] Server: The server issues API requests from project management tools (e.g., JIRA or Trello) to collect task completion and progress data.

[0140] Input: The API endpoint of your project management tool.

[0141] Output: Project progress data.

[0142] Specific operation: The server periodically runs an automatic script to retrieve the latest data from the project management tool and store it in the database.

[0143] Step 2:

[0144] Data Preprocessing

[0145] Server: Formats and standardizes collected data, ensures data consistency, and handles missing and noisy data.

[0146] Inputs: Task data from users and progress data collected from project management tools.

[0147] Output: Preprocessed data.

[0148] What it does: It uses a Python script to standardize date formats, fill in missing data with reasonable guesses, and filter out noisy data.

[0149] Step 3:

[0150] Evaluation by AI model

[0151] Server: The preprocessed data is input into a generative artificial intelligence model, and an evaluation score for each user is calculated.

[0152] Input: Preprocessed data.

[0153] Output: Evaluation score.

[0154] Specific operation: The server uses TensorFlow's Predict method to input preprocessed data into the AI ​​model and perform evaluation. The resulting evaluation scores are stored in the database.

[0155] Step 4:

[0156] Evaluation report generation

[0157] Server: Generates an evaluation report based on the evaluation score, which includes details of the score, reasons for the evaluation, areas for improvement, and a specific action plan.

[0158] Input: Rating score.

[0159] Output: Evaluation report.

[0160] Specific operation: Based on the evaluation score, an evaluation report is automatically generated using a template engine and saved in PDF format.

[0161] Step 5:

[0162] View the assessment report

[0163] Terminal: Users (employees and supervisors) use terminals to view the evaluation reports.

[0164] Input: Assessment report.

[0165] Output: Assessment report displayed on screen.

[0166] Specific operation: The user opens a web browser and checks the assessment report on the dashboard.

[0167] Step 6:

[0168] Gathering feedback

[0169] Users (employees and supervisors): Conduct feedback interviews based on the evaluation reports and enter the results into the system.

[0170] Input: Interview results and areas for improvement.

[0171] Output: Feedback data.

[0172] Specific actions: Enter the interview results in the feedback form and press the send button to the system.

[0173] Step 7:

[0174] Retraining generative AI models

[0175] Server: Retrains the generative AI model based on the feedback data.

[0176] Input: Feedback data.

[0177] Output: A retrained artificial intelligence model.

[0178] Specific actions: Retrain the AI ​​model with new feedback data and update the evaluation algorithm.

[0179] Step 8:

[0180] Deploying a retrained model

[0181] Server: Deploys the retrained model to the system.

[0182] Input: The retrained artificial intelligence model.

[0183] Output: Updated rating system.

[0184] Specific operation: Deploy a new AI model to the server to improve the evaluation accuracy of the entire system.

[0185] (Application example 1)

[0186] 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."

[0187] Modern factories are required to fairly and objectively evaluate the work efficiency and quality of robots and implement improvement measures in real time. However, conventional evaluation systems require a large amount of labor for data collection and preprocessing, making it difficult to ensure fair evaluations and rapid improvement. In addition, there is a lack of a mechanism for effectively reflecting feedback after evaluations in the next evaluation, making it difficult to achieve accurate evaluations and effective improvements.

[0188] 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.

[0189] In this invention, the server includes means for collecting task data using a data collection device, means for preprocessing the collected data using a data preprocessing device, means for calculating an evaluation score based on the data preprocessed by the generative artificial intelligence model, means for generating an evaluation report based on the evaluation score, means for making the evaluation report available for viewing, means for recording feedback data and updating the evaluation model, means for standardizing the collected data, and means for creating a specific action plan based on the evaluation results. This makes it possible to fairly and objectively evaluate the work efficiency and quality of a robot in real time and quickly reflect improvement measures.

[0190] A "data collection device" is a piece of equipment or software system that automatically collects work data.

[0191] A "data preprocessing device" is a device or software system that formats and standardizes collected data, removes noise, and converts it into an analyzable format.

[0192] A "generative artificial intelligence model" is an artificial intelligence algorithm or framework for calculating evaluation scores based on preprocessed data.

[0193] The "evaluation score" is an index that quantifies work efficiency and quality based on work data.

[0194] The "evaluation report generation means" is a device or software system that records the performance of each robot in detail based on the evaluation score and creates a report that presents areas for improvement and action plans.

[0195] "Feedback data" refers to data that records improvements and initiatives identified based on the evaluation results.

[0196] "Means for standardizing collected data" refers to equipment and software systems that convert collected data into a consistent format so that it can be analyzed and evaluated.

[0197] "Action plan creation means" refers to equipment or software systems used to plan and draft specific next improvement measures and initiatives based on the evaluation results.

[0198] The present invention is embodied as an evaluation system for fairly and objectively evaluating the work efficiency and quality of robots in a factory and for quickly incorporating improvement measures. Specific embodiments of the system are described below.

[0199] This system consists of a server equipped with a data collection device, a data preprocessing device, a generative AI model, an evaluation report generation means, and a feedback function, and a terminal for viewing the evaluation report.

[0200] Data collection

[0201] The server and data collection device automatically collects operational data from factory robots from automation tools such as SCADA systems, including robot operating hours, number of completed tasks, and task quality.

[0202] Data Preprocessing

[0203] The data preprocessing unit standardizes the collected data and removes noise. Specifically, it uses the Python programming language and data processing libraries such as Pandas and Scikit-learn to shape and standardize the data.

[0204] Evaluation and Analysis

[0205] The server inputs the preprocessed data into a generative artificial intelligence model to evaluate the robot's work efficiency and quality. The evaluation uses a clustering method (e.g., KMeans) to compare and analyze the performance of each robot, which then calculates an evaluation score for each robot.

[0206] Generate an assessment report

[0207] An evaluation report is generated based on the evaluation scores. The report includes the score for each robot, the reason for the evaluation, areas for improvement, and a specific action plan. The evaluation report is made available to users via their devices.

[0208] Feedback Loop

[0209] The user and their supervisor then hold a feedback interview based on the evaluation report. The feedback and areas for improvement from the interview are then re-entered into the system and reflected in the next evaluation cycle. The server uses this feedback data to retrain the generative AI model and improve the accuracy of the evaluation.

[0210] Hardware and software used

[0211] Hardware: Factory robots, SCADA systems, collection devices (sensors, etc.)

[0212] Software: Python, Pandas, Scikit-learn, server for data storage and processing

[0213] Specific examples

[0214] For example, the evaluation of a robot in a factory involves the following steps:

[0215] 1. Data collection: Collect robot operation data in CSV format through the SCADA system.

[0216] 2. Data preprocessing: Use StandardScaler to standardize the data and convert it into an analyzable format.

[0217] 3. Evaluation and Analysis: The KMeans clustering method is used to group the robots' performance and calculate the silhouette score.

[0218] 4. Evaluation report generation: An evaluation report will be created for each cluster summarizing areas for improvement and action plans.

[0219] 5. Feedback loop: Based on the evaluation results, the robot's settings and programs are fine-tuned and reflected in the next evaluation cycle.

[0220] Prompt Sentence Examples

[0221] You have collected operational data for robots in your factory. Please rate a robot with the following characteristics and provide an action plan to improve efficiency and quality:

[0222] Uptime

[0223] Number of completed tasks

[0224] Task Quality

[0225] In this way, the present invention comprehensively manages a series of processes from data collection to evaluation and feedback loops, thereby realizing efficient work management and quality improvement for factory robots.

[0226] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[0227] Step 1:

[0228] The server collects operational data from robots in the factory. Specifically, it obtains the robot's operational data through automation tools such as a SCADA system and saves it as a CSV file. Input includes data items such as the robot's operating time, number of completed tasks, and task quality. The output is a CSV file of the collected raw data.

[0229] Step 2:

[0230] The server preprocesses the collected data. Specifically, it reads the data using Python's Pandas library and standardizes the data using StandardScaler, which aligns the scale of each data item. The input includes the CSV file of raw data collected in step 1. The output is a standardized data frame.

[0231] Step 3:

[0232] The server inputs the preprocessed data into a generative artificial intelligence model and calculates an evaluation score. Specifically, it applies the KMeans clustering method using the Scikit-learn library to classify the data into clusters and calculate a silhouette score. The input includes the data frame preprocessed in step 2. The output generates a cluster number and evaluation score for each robot.

[0233] Step 4:

[0234] The server generates an evaluation report based on the evaluation scores, detailing the robot's performance and areas for improvement for each cluster. The input includes the cluster number and evaluation score generated in step 3. The output is a text file or PDF of the evaluation report.

[0235] Step 5:

[0236] The terminal provides the generated evaluation report for the user to view. Specifically, it displays the evaluation report through a web interface or a dedicated application, allowing the user to check the evaluation results. The input includes the evaluation report generated in step 4. The output includes a screen displaying the report and a printed report.

[0237] Step 6:

[0238] The user conducts a feedback interview based on the evaluation report and inputs the results into the system. Specifically, the user records the areas for improvement and the details of the efforts in an input form and reflects them in the next evaluation cycle. The input includes the user's feedback information. The output is recorded in the system.

[0239] Step 7:

[0240] The server uses the feedback data to retrain the generative AI model. Specifically, it uses the feedback data to update the model's parameters and apply them to the next evaluation. The input includes the feedback data collected in step 6. The output is a retrained AI model.

[0241] Step 8:

[0242] The server deploys the retrained model to the system and uses it for the next evaluation. Specifically, the latest model is incorporated into the system and applied to the next cycle of data collection to evaluation. The input includes the retrained model generated in step 7. The output includes the latest evaluation model installed in the system.

[0243] 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.

[0244] This invention combines a system for fairly and objectively evaluating employees' work efficiency and contribution with an emotion engine that recognizes the user's emotions. This system is composed of multiple terminals and a server, and provides more accurate evaluations and feedback.

[0245] System Configuration

[0246] The system includes a terminal, a server, a data collection device, a data preprocessing device, a generative AI model, an evaluation report generation device, a feedback data recording device, and an emotion engine. The terminal is used to input employee data and view evaluation reports, while the server is responsible for data collection, preprocessing, evaluation, report generation, feedback processing, and emotion recognition.

[0247] Program processing overview

[0248] Data collection

[0249] User (employee): The user enters daily work details, progress, achieved goals, usage time, etc. into a dedicated form on the terminal.

[0250] Server: Automatically collects task completion status and progress data from project management tools (e.g., JIRA, Trello, Redmine), and the emotion engine recognizes and records emotions in real time from user input data and interaction logs.

[0251] Data Preprocessing

[0252] Server: Formats and standardizes the collected data. For example, normalizes text data, standardizes the format of time series data, and completes missing values.

[0253] Server: Removes noise from all data, including emotion data, and converts it into the format required for evaluation.

[0254] Evaluation by AI model

[0255] Server: The preprocessed data is input into a generative artificial intelligence model to calculate evaluation scores for each employee based on efficiency, contribution, and goal achievement.

[0256] How it works: The AI ​​model calculates an evaluation score based on work time, number of completed tasks, project progress, and user emotional data, etc. Emotional data is taken into account as a correction factor for the evaluation.

[0257] Evaluation report generation

[0258] Server: Generates a rating report based on the rating scores and emotion data. The report includes the score for each category, the reason for the rating, areas for improvement, specific advice, and the user's emotional state.

[0259] Terminal: Users (employees and supervisors) view the generated evaluation report and check the evaluation results and feedback.

[0260] Providing Feedback

[0261] Users (employees and managers): Conduct feedback interviews based on the evaluation reports. Enter the details of the interviews and areas for improvement into the system, and also record emotional data.

[0262] Example: For example, when a project manager gives a progress report, the emotion engine uses facial recognition and voice analysis to assess their stress level and satisfaction in real time.

[0263] Retraining the model

[0264] Server: Collects feedback data and emotion data and adds it to the training dataset of the generative AI model.

[0265] Server: Retrains the AI ​​model with new data, makes adjustments to improve evaluation accuracy, and deploys the updated model to the system for the next evaluation cycle.

[0266] Specific examples

[0267] For example, the evaluation of a team leader involves the following steps:

[0268] 1. User (Team Leader): Enters the project progress, completed tasks, and team member contributions into the terminal. At the same time, the emotion engine records the leader's emotions when entering information.

[0269] 2. Server: Automatically collects relevant data from project management tools and consolidates all data.

[0270] 3. Server: The data preprocessor formats the data, and the generative AI model calculates an evaluation score. Emotion data from the emotion engine is also incorporated into the evaluation.

[0271] 4. Server: Generates an evaluation report for the team leader based on the evaluation scores and emotion data.

[0272] 5. Users (team leaders and superiors): Conduct feedback interviews based on the evaluation report and discuss specific improvement measures, taking into account the user's emotional state.

[0273] 6. Server: Collects feedback and sentiment data and retrains the model.

[0274] As can be seen, combining an emotion engine makes the employee evaluation process more accurate and comprehensive, providing specific and actionable feedback.

[0275] The processing flow will be explained below.

[0276] Step 1: Data collection

[0277] User (employee): Enters daily work details, progress, achieved goals, and usage time into a dedicated form on the device.

[0278] Server: Automatically collects task completion status, progress data, work logs, etc. from project management tools (e.g., JIRA, Trello, Redmine).

[0279] Server: The emotion engine recognizes and records emotions in real time from user input data and interaction logs. For example, emotion data is collected using a facial recognition camera or voice analysis software.

[0280] Step 2: Data Preprocessing

[0281] Server: Formats and standardizes the collected data. Specifically, it normalizes text data (for example, standardizing uppercase and lowercase letters), standardizes the format of time series data (for example, standardizing timestamps), and completes missing values ​​(for example, completing estimated values ​​based on previous and subsequent data).

[0282] Server: Removes noise from all data, including emotion data, and converts it into the format required for evaluation. For example, it deletes incorrect emotion recognition results and leaves only data with high recognition accuracy.

[0283] Step 3: Evaluation by AI model

[0284] Server: Inputs the preprocessed data into the generative artificial intelligence model.

[0285] Server: The AI ​​model analyzes the data and calculates an evaluation score for each employee, including their efficiency, contribution, and goal achievement. Specifically, the evaluation score is calculated based on factors such as work time, number of completed tasks, project progress, and user emotional data (e.g., stress level, satisfaction).

[0286] Server: Adjusts the evaluation score by taking into account emotional data. For example, if a person achieves high results even under high stress, the score is adjusted to be more highly rated.

[0287] Step 4: Generate an assessment report

[0288] Server: Generates an evaluation report for each employee based on the evaluation score and emotional data. The report contents include the score for each category, the reason for the evaluation, areas for improvement, specific advice, and an analysis of the employee's emotional state.

[0289] Terminal: Users (employees and supervisors) can view the generated evaluation report and compare it with their own evaluation to understand what improvements are needed.

[0290] Step 5: Provide feedback

[0291] Users (employees and managers): Conduct feedback interviews based on the evaluation reports. Re-enter the details of the interviews and areas for improvement into the system. At this time, the employee's emotional state during the interviews is also recorded to improve the quality of the feedback.

[0292] Example: For example, when a project manager gives a progress report, the emotion engine uses facial recognition and voice analysis to assess the manager's stress level and satisfaction in real time, providing feedback to improve the quality of the interview.

[0293] Step 6: Retrain the model

[0294] Server: Updates the learning dataset for the generative AI model based on feedback data and emotion data.

[0295] Server: Retrains the AI ​​model with new data and makes adjustments to improve the accuracy of the evaluation.

[0296] Server: Deploys the updated model to the system and makes it available for the next evaluation cycle.

[0297] This specific processing step enables fair and comprehensive employee evaluation, and by combining it with an emotion engine, it can provide even more accurate and actionable feedback.

[0298] Example 2

[0299] 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."

[0300] Traditional employee evaluation systems make it difficult to fairly and objectively evaluate employees' work efficiency and contributions, and often contain ambiguous standards and biases. Furthermore, because they do not take into account employees' emotions or psychological state, evaluations are one-sided and do not accurately reflect actual performance. Furthermore, because feedback and improvement measures are not specific, there are issues with them not contributing to employee growth or motivation.

[0301] 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.

[0302] In this invention, the server includes means for collecting work data using a data input device, means for collecting emotion data using an emotion recognition device, means for preprocessing the collected data using a data preprocessing device, means for calculating an evaluation score based on the data preprocessed by the generative artificial intelligence model, means for generating an evaluation report based on the evaluation score, means for making the evaluation report available for viewing, and means for recording feedback data and emotion data and updating the evaluation model. This allows for a fairer and more objective evaluation of employee work efficiency and contribution, and by incorporating emotion data, a more accurate and comprehensive evaluation is possible. It also allows for the provision of specific and practical feedback, contributing to employee growth and increased motivation.

[0303] A "data input device" is a device that allows a user to input work data such as the details of daily work, progress, goals achieved, and working hours.

[0304] An "emotion recognition device" is a device that recognizes a user's emotions in real time and collects them as emotion data.

[0305] A "data preprocessing device" is a device that formats and standardizes collected data, and performs tasks such as normalizing text data, removing noise, and filling in missing values.

[0306] A "generative artificial intelligence model" is an artificial intelligence that calculates evaluation scores for employee efficiency, contribution, and goal achievement based on preprocessed data.

[0307] An "evaluation report" is a report generated based on the evaluation scores and emotional data, and includes the scores for each category, the reasons for the evaluation, areas for improvement, specific advice, and the user's emotional state.

[0308] "Feedback data" refers to data that records what was discussed in the feedback interview and areas for improvement based on the evaluation report.

[0309] An "evaluation model" refers to the entire evaluation system, including the generative artificial intelligence model, and is used to calculate the evaluation score.

[0310] "Updating" refers to the process of adding new feedback and sentiment data to the evaluation model and retraining the model.

[0311] This invention combines an emotion recognition device with a system for fairly and objectively evaluating employees' work efficiency and contribution. The system consists of multiple terminals and a server, and provides more accurate evaluations and feedback.

[0312] System Configuration

[0313] The system includes a terminal, a server, a data input device, an emotion recognition device, a data preprocessing device, a generative AI model, an evaluation report generation device, and a feedback data recording device. The terminal is used to input employee data and view evaluation reports, while the server collects data, preprocesses it, evaluates it, generates reports, processes feedback, and recognizes emotions.

[0314] Server Configuration

[0315] The server implements the following measures:

[0316] 1. Work data collection means using a data input device: This is a device that allows users to input their daily work content, progress, goals achieved, usage time, etc. Specifically, users input this data into a dedicated form from a terminal.

[0317] 2. Emotion data collection using an emotion recognition device: Recognize the user's emotions in real time and collect emotion data using facial recognition and voice analysis. For example, facial recognition software (e.g., Microsoft® Azure® Face API) and voice analysis tools (e.g., Google® Cloud Speech-to-Text) are used.

[0318] 3. Data preprocessing device: A device that formats and standardizes collected data. For example, it normalizes text data, removes noise, and fills in missing values.

[0319] 4. Evaluation score calculation method using a generative artificial intelligence model: This is an artificial intelligence model that calculates evaluation scores for employee efficiency, contribution, and goal achievement based on preprocessed data.

[0320] 5. Evaluation report generator: A device that generates an evaluation report based on the evaluation score and emotion data.

[0321] 6. Evaluation report viewing means: This is a means for enabling users to view the evaluation report. Users can check the report via a web browser or dedicated application on their device.

[0322] 7. A means of recording feedback and sentiment data and updating the evaluation model: This is a means of recording what was discussed in the feedback interview and areas for improvement, and using that data to retrain the generative AI model.

[0323] Specific examples

[0324] For example, a team leader evaluation involves the following steps:

[0325] 1. User (Team Leader): Enters the project progress, completed tasks, and team member contributions into the terminal. At the same time, the emotion recognition device records the leader's emotions when entering information.

[0326] 2. Server: Automatically collects relevant data from project management software and consolidates all data.

[0327] 3. Server: The data preprocessor formats the data, and the generative AI model calculates an evaluation score. Emotion data from the emotion recognition device is also incorporated into the evaluation.

[0328] 4. Server: Generates an evaluation report for the team leader based on the evaluation scores and emotion data.

[0329] 5. Users (team leaders and superiors): Conduct feedback interviews based on the evaluation report and discuss specific improvement measures, taking into account the user's emotional state.

[0330] 6. Server: Collects feedback and emotion data and retrains the generative AI model.

[0331] Prompt Sentence Examples

[0332] "Calculate a rating score based on the task completion data and sentiment data entered by the user."

[0333] "Combine progress data with emotion logs to generate an evaluation report."

[0334] As described above, by combining emotion recognition devices, employee evaluations can be made more accurate and comprehensive, and specific, actionable feedback can be provided.

[0335] The flow of the identification process in the second embodiment will be described with reference to FIG.

[0336] Step 1:

[0337] Users enter work data such as daily work content, progress, achieved goals, and usage time into a dedicated form from their terminal.

[0338] Input: Work content, progress, goals, time used

[0339] Output: Record of input data

[0340] Specific operation: After the user completes the task "Document Creation" for Project X, they enter the task name, required time, degree of completion, etc. into a dedicated form on their terminal.

[0341] Step 2:

[0342] The server automatically collects task completion status and progress data from project management software (e.g., JIRA, Trello, Redmine).

[0343] Input: Task completion status data, progress data from project management software

[0344] Output: Record of collected data

[0345] Specific operation: Project and task data is periodically collected from each management software via API and stored in a database.

[0346] Step 3:

[0347] The server uses an emotion recognition device to recognize the user's emotions in real time from the user's input data and interaction logs, and records the emotion data.

[0348] Input: User input data, interaction logs

[0349] Output: Emotion data recording

[0350] What it does: Uses facial recognition software (e.g., Microsoft Azure Face API) and voice analysis tools (e.g., Google Cloud Speech-to-Text) to record the user's emotional state (stress level, satisfaction, etc.).

[0351] Step 4:

[0352] The server formats and standardizes the collected data, including emotion data, for example by normalizing text data, removing noise, and imputing missing values.

[0353] Input: Raw data collected

[0354] Output: Preprocessed data

[0355] Specific operations: Normalizing text data involves converting alphanumeric characters between half-width and full-width and removing unnecessary symbols. Eliminating noise involves correcting outliers and filling in missing data.

[0356] Step 5:

[0357] The server inputs the preprocessed data into a generative artificial intelligence model to calculate evaluation scores for each employee's efficiency, contribution, and goal achievement.

[0358] Input: Preprocessed data (work time, number of completed tasks, project progress, sentiment data, etc.)

[0359] Output: Evaluation score

[0360] How it works: Based on the input data, the AI ​​model calculates evaluation scores for efficiency, contribution, and goal achievement.

[0361] Step 6:

[0362] The server generates an evaluation report based on the evaluation score and the emotion data.

[0363] Input: Evaluation scores, emotion data

[0364] Output: Evaluation report

[0365] Specific Actions: Generate an evaluation report that includes the score for each category, the reason for the evaluation, areas for improvement, specific advice, and the user's emotional state.

[0366] Step 7:

[0367] The terminal allows users (employees and supervisors) to view the generated evaluation report.

[0368] Input: Generated assessment report

[0369] Output: User views the evaluation report

[0370] Specific operation: The user checks the evaluation report through a web browser or a dedicated app.

[0371] Step 8:

[0372] Users (employees and their superiors) conduct feedback interviews based on the evaluation reports. The system inputs the details of the discussions and areas for improvement, and also records emotional data.

[0373] Input: Evaluation report, interview details

[0374] Output: Feedback data, additional emotion data

[0375] Specific actions: Enter the specific improvement measures discussed in the feedback interview (e.g., participating in a stress management workshop) into the system, and also add your emotional state.

[0376] Step 9:

[0377] The server collects feedback data and emotion data and adds it to the training dataset of the generative artificial intelligence model.

[0378] Input: Feedback data, emotion data

[0379] Output: Updated training dataset

[0380] Specific operation: Add the feedback content and new emotion data entered into the system to the training dataset.

[0381] Step 10:

[0382] The server retrains the generative AI model with new data, makes adjustments to improve the accuracy of the evaluation, and deploys the updated model to the system.

[0383] Input: Updated training dataset

[0384] Output: Retrained AI model

[0385] Specific operation: The retrained AI model is deployed on the server and used for the next evaluation.

[0386] Through the above steps, a system is realized that can provide accurate and comprehensive evaluation and feedback that takes into account emotional data.

[0387] (Application example 2)

[0388] 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."

[0389] Conventional staff evaluation systems have problems with subjective evaluations, lacking fairness and accuracy. Furthermore, evaluations are one-sided and do not take into account the emotional state of staff, resulting in ineffective improvement measures. The present invention aims to provide a system that combines emotional data to more fairly and objectively evaluate staff work efficiency and contributions, and provide specific and practical feedback.

[0390] The specification processing by the specification processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means. In this invention, the server includes means for collecting task data by a data collection device, means for preprocessing the collected data by a data preprocessing device, means for calculating an evaluation score based on the data preprocessed by a generative artificial intelligence model, means for generating an evaluation report based on the evaluation score, means for making the evaluation report available for viewing, means for recording feedback data and updating the evaluation model, means for collecting user emotion data by an emotion engine, and means for correcting the evaluation based on the emotion data. This enables fair and objective evaluation and specific feedback that take emotion data into consideration.

[0391] The "data collection device" is a device for collecting task data, progress data, and even emotion data input by the user.

[0392] A "data preprocessing device" is a device that formats, standardizes, removes noise from, and converts collected data into a format required for evaluation.

[0393] A "generative artificial intelligence model" is an artificial intelligence technology that calculates a score to evaluate a user's efficiency, contribution, and goal achievement based on preprocessed data.

[0394] An "evaluation report" is a report that includes evaluation results, areas for improvement, and advice based on evaluation scores calculated by a generative artificial intelligence model.

[0395] An "emotion engine" is a technology that collects emotional data from users through facial recognition and voice analysis, and reflects that information in evaluations.

[0396] "Feedback data" refers to data that records the content discussed and areas for improvement in feedback interviews based on the evaluation report.

[0397] An "evaluation model" is an artificial intelligence algorithm that calculates efficiency and contribution based on a user's performance and emotional data.

[0398] "Task completion status" refers to data on the work and progress status that a user has completed using the management tool.

[0399] "Emotion data" is data that indicates the user's emotional state and is obtained through facial recognition and voice analysis.

[0400] "Preprocessed data" refers to raw data obtained from a data collection device after it has been shaped, standardized, and denoised.

[0401] This invention combines an emotion recognition engine with a system for fairly and objectively evaluating the work efficiency and contribution of staff in a brick-and-mortar store. This system is composed of a data collection device, a data preprocessing device, a generative AI model, an evaluation report generation device, a feedback data recording device, an emotion engine, and a server.

[0402] System Configuration

[0403] Data acquisition equipment:

[0404] Users enter data such as daily work details, task progress, achieved goals, and working hours into a dedicated form using a tablet or smartphone. Sales data and customer service data are also automatically collected from the POS system.

[0405] Data Preprocessor:

[0406] Format and standardize the collected data, including normalizing text data, standardizing the format of time series data, filling in missing values, and removing noise.

[0407] Generative AI models:

[0408] Based on the pre-processed data, an evaluation score is calculated for each staff member's efficiency, contribution, and goal achievement. The evaluation reflects work time, number of completed tasks, sales data, customer service data, etc. Emotion data collected by the emotion engine is used as a correction factor for the evaluation.

[0409] Evaluation report generator:

[0410] Based on the evaluation scores and emotional data, an evaluation report is automatically generated, including the score for each category, the reason for the evaluation, areas for improvement, specific advice, and the emotional state.

[0411] Feedback data recording device:

[0412] Staff members, store managers, and supervisors conduct feedback interviews based on the evaluation reports, and the results and areas for improvement are entered into the system, while emotional data is also recorded.

[0413] Emotion Engine:

[0414] Collect emotional data through facial recognition and voice analysis of staff members. Analyze and collect staff members' emotional states (e.g., stress levels, satisfaction) in real time.

[0415] server:

[0416] Oversees all data processing, including data collection, pre-processing, evaluation, report generation, feedback recording, and sentiment analysis. Generative AI models are periodically retrained based on feedback data.

[0417] Specific examples

[0418] For example, when a staff member enters the details of their work and sales data for the day on a tablet at the end of their workday, the emotion engine analyzes the staff member's stress level and satisfaction level from their facial expressions and voice. All of this data is sent to a server, where it is formatted and standardized by a pre-processing device. A generative AI model then analyzes the data and calculates an evaluation score. Finally, an evaluation report generator generates a report based on the evaluation score and emotion data, which the staff member and store manager use in feedback interviews.

[0419] Prompt Sentence Examples

[0420] Project details: Today's work and sales, task completion status, emotional data

[0421] Emotional data: stress level (high, medium, low), satisfaction (satisfied, dissatisfied, neutral)

[0422] Evaluation items: efficiency score, contribution score, goal achievement score

[0423] Feedback includes: areas for improvement, specific advice, and considerations for emotional state

[0424]

[0425] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[0426] Step 1:

[0427] Users enter data such as daily work details, task progress, achieved goals, and working hours into a dedicated form using a tablet or smartphone. The entered data is collected by a data collection device. Sales data and customer interaction data are also automatically collected from the POS system. This allows the system to obtain both input data and automatically collected data.

[0428] Step 2:

[0429] The emotion engine collects emotion data from the user's device through facial recognition and voice analysis. For example, it analyzes the user's facial expressions and voice when entering data, and converts emotions such as stress level and satisfaction into data in real time. This emotion data is also sent to the data collection device.

[0430] Step 3:

[0431] The server preprocesses the collected data using a data preprocessing device. Specifically, it normalizes text data, standardizes the format of time-series data, fills in missing values, removes noise, etc. This results in a standardized dataset.

[0432] Step 4:

[0433] The server inputs the preprocessed data into a generative AI model to calculate an evaluation score. The generative AI model calculates an evaluation score based on work time, number of completed tasks, sales data, customer service data, and emotional data. This results in an evaluation score that reflects the staff member's efficiency, contribution, and goal achievement.

[0434] Step 5:

[0435] The server generates an evaluation report based on the evaluation score and emotional data. The evaluation report generator creates a report that includes the score for each category, the reason for the evaluation, areas for improvement, specific advice, and the emotional state. This report is made available for viewing by the user, store manager, and supervisor.

[0436] Step 6:

[0437] The user and the store manager / supervisor then hold a feedback interview based on the evaluation report. The content of the discussion and areas for improvement during the interview are entered into the system, and new emotional data is also recorded. This allows feedback data to be obtained.

[0438] Step 7:

[0439] The server collects feedback data and sentiment data and adds it to the training dataset of the generative AI model. The server retrains the generative AI model with this new data to improve the accuracy of the evaluation. The updated model is deployed to the system and used in the next evaluation cycle.

[0440] 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.

[0441] The data generation model 58 is a so-called generative AI (Artificial Intelligence). An example of the data generation model 58 is ChatGPT (registered trademark) (Internet search engine).<URL: https: / / openai.com / blog / chatgpt> ), Gemini (registered trademark) (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.

[0442] 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.

[0443] [Second embodiment]

[0444] FIG. 3 shows an example of the configuration of a data processing system 210 according to the second embodiment.

[0445] 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.

[0446] 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).

[0447] 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.

[0448] 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.

[0449] 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).

[0450] 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.

[0451] 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.

[0452] 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.

[0453] 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.

[0454] 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.

[0455] 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."

[0456] The present invention provides a system for fairly and objectively evaluating the work efficiency and contribution of employees. Specific embodiments of the system are described below.

[0457] System Configuration

[0458] This system consists of multiple terminals and a server. The terminals are devices (such as PCs or tablets) that employees use to input data, and the server is the main processing device for collecting, preprocessing, and analyzing data, as well as generating and updating evaluation reports.

[0459] Program processing overview

[0460] Data collection

[0461] User (employee): The user inputs the details of his / her daily work, progress, goals achieved, and time used into the terminal using a dedicated interface.

[0462] Server: The server automatically collects task completion and progress data from project management tools (e.g., JIRA, Trello, Redmine), thereby integrating manual and automatically collected data.

[0463] Data Preprocessing

[0464] Server: The server formats and standardizes the collected data, checking for missing information, and in the process removing noise from the data and converting it into a unified format.

[0465] Evaluation by AI model

[0466] Server: The server inputs the preprocessed data into a generative AI model to calculate an evaluation score for each employee. The score is calculated based on multiple categories, including work efficiency, productivity, and work quality.

[0467] Evaluation report generation

[0468] Server: The server generates an evaluation report based on the evaluation scores, which includes the score for each category, the reason for the evaluation, areas for improvement, and a specific action plan.

[0469] Device: Users (employees and managers) can view the generated evaluation report and check the next goal setting and initiatives.

[0470] Feedback Loop

[0471] Users (employees and supervisors): Users (employees and supervisors) conduct feedback interviews based on the evaluation report. The feedback and improvements that emerged from the interviews are entered back into the system and reflected in the next evaluation cycle.

[0472] Server: The server retrains the generative AI model based on the feedback data to improve the accuracy of the evaluation.

[0473] Specific examples

[0474] For example, the evaluation of a project manager involves the following steps:

[0475] 1. User (Project Manager): Enters project progress, completed tasks, and team member contributions into the device.

[0476] 2. Server: The server automatically collects task completion and progress data from project management tools and consolidates all the data.

[0477] 3. Server: The data preprocessing unit formats this data, and the generative AI model calculates an evaluation score based on this.

[0478] 4. Server: Generates an evaluation report for the project manager based on the evaluation scores.

[0479] 5. Users (project managers and superiors): Users conduct feedback interviews based on the evaluation reports and enter improvements into the system as feedback.

[0480] 6. Server: The server takes the feedback data, retrains the AI ​​model, and reflects it in the next evaluation.

[0481] In this way, this system comprehensively manages a series of processes from data collection to evaluation and feedback loop, enabling objective and fair evaluation of employees.

[0482] The processing flow will be explained below.

[0483] Step 1: Data collection

[0484] User (employee): Enters daily work details, progress, achieved goals, usage time, etc. into a dedicated form on the device.

[0485] Server: Automatically collects task completion status, progress data, work logs, etc. from project management tools (e.g., JIRA, Trello, Redmine).

[0486] Step 2: Data Preprocessing

[0487] Server: Formats the collected data, such as normalizing text data, standardizing the format of time series data, and filling in missing values.

[0488] Server: The server removes noise from the collected data and converts it into the format required for evaluation, for example by filtering and standardizing the data.

[0489] Step 3: Evaluation by AI model

[0490] Server: Inputs the preprocessed data into the generative artificial intelligence model.

[0491] Server: The AI ​​model analyzes the data and calculates an evaluation score for each employee based on their work efficiency, contribution, goal achievement, etc.

[0492] Specific operation: Calculate a score based on each employee's work time, number of completed tasks, project progress, etc. Evaluation criteria include project success rate, work accuracy, productivity, etc.

[0493] Step 4: Generate an assessment report

[0494] Server: Generates an evaluation report for each employee based on the evaluation score. The report includes the evaluation score, the reason for the evaluation for each item, areas for improvement, and specific advice.

[0495] Terminal: Users (employees and managers) can view the generated evaluation report, understand their own evaluation, and identify areas for improvement.

[0496] Step 5: Provide feedback

[0497] Users (employees and managers): Conduct feedback interviews based on the evaluation reports. Enter the details of the interviews and points for improvement into the system.

[0498] Specific actions: The supervisor will refer to the evaluation report and provide specific advice to the employee, identifying areas for improvement and setting goals for the next time. The employee will then create a specific action plan based on the feedback.

[0499] Step 6: Retrain the model

[0500] Server: Collects feedback data and adds it to the training dataset of the generative AI model.

[0501] Server: Retrains the AI ​​model using new data and makes adjustments to improve the accuracy of the evaluation.

[0502] Server: Deploys the updated model to the system and makes it available for the next evaluation cycle.

[0503] Through these specific processing steps, fair and objective employee evaluations become possible, improving the efficiency and accuracy of the entire evaluation process.

[0504] Example 1

[0505] 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."

[0506] In today's business environment, it is extremely important to fairly and objectively evaluate employees' work efficiency and contributions. However, the evaluation process is complicated and subjective. Traditional evaluation systems also face issues such as being prone to human bias and lacking transparency and consistency. Furthermore, the lack of specific areas for improvement and action plans based on evaluation results makes it difficult to improve employee performance. There is a need to resolve these issues and build a fair and objective evaluation system.

[0507] 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.

[0508] In this invention, the server includes: means for collecting work data using a data collection device; means for users to input work content, progress, goals, and usage time into a terminal using a dedicated interface; means for the server to collect task completion status and progress data from a project management tool; means for standardizing and formatting the collected data using a data preprocessing device; means for processing missing data and noise data; means for calculating evaluation scores based on data preprocessed by a generative AI model; means for generating evaluation reports based on the evaluation scores; means for making the evaluation reports viewable; and means for recording feedback data and updating the evaluation model. This enables fair and objective evaluation by collecting detailed and consistent employee work data and evaluating them using a generative AI model based on preprocessed data. Furthermore, the evaluation report presents specific areas for improvement and action plans, contributing to improved employee performance.

[0509] A "data collection device" is a device for collecting data entered by a user or information automatically acquired from an external tool.

[0510] A "user" is a person who uses the system to input information such as work content, progress, goals, and usage time.

[0511] "Terminal" refers to a device used by a user to input data or view an evaluation report, including a PC or tablet.

[0512] "Server" is the central processing unit responsible for data collection, automated processing, analysis, and generation of evaluation reports.

[0513] A "project management tool" is software used to manage tasks and track progress, including tools such as JIRA and Trello.

[0514] A "data preprocessing device" is a device that standardizes and formats collected data and processes missing data and noise.

[0515] A "generative artificial intelligence model" is an artificial intelligence algorithm for calculating evaluation scores based on preprocessed data.

[0516] The "evaluation score" is a numerical indicator of a user's work efficiency and productivity calculated by a generative artificial intelligence model.

[0517] An "assessment report" is a document generated based on an assessment score, which includes details of the score, reasons for the assessment, areas for improvement, and a specific action plan.

[0518] "Feedback data" refers to information, including improvements and comments, that users input into the system based on feedback interviews.

[0519] "Retraining" is the process of using collected feedback data to improve the accuracy of a generative artificial intelligence model.

[0520] "Deployment" refers to running a retrained artificial intelligence model in a real system environment.

[0521] The present invention relates to a system for fairly and objectively evaluating the work efficiency and contribution of employees. This system is composed of multiple terminals and a server. Specific embodiments of the system are described below.

[0522] System Configuration

[0523] This system is configured as follows: The terminal is a device for users to input data, and the server is a device that performs the main processing for data collection, pre-processing, analysis, and generation and updating of evaluation reports.

[0524] Hardware and Software

[0525] Device: An input device such as a computer or tablet.

[0526] Server: A high-performance computer for data processing.

[0527] Project management tools: e.g., JIRA, Trello, Redmine, etc.

[0528] Generative artificial intelligence models: Use machine learning frameworks such as TensorFlow and PyTorch.

[0529] Program processing overview

[0530] Data collection

[0531] User (employee): The user inputs the details of daily work, progress, goals, and usage time into the terminal using a dedicated interface.

[0532] Server: The server automatically collects task completion and progress data from your project management tools, and consolidates all the data in one place using API requests.

[0533] Data Preprocessing

[0534] Server: The server formats and standardizes the collected data, and processes missing and noisy data. This process involves data cleansing using Python scripts.

[0535] Evaluation by AI model

[0536] Server: The preprocessed data is input into the generative AI model, and an evaluation score for each user is calculated using TensorFlow's Predict method.

[0537] Server: Generates an evaluation report based on the calculated evaluation score. The evaluation report includes details of the score, reasons for the evaluation, areas for improvement, and a specific action plan.

[0538] Viewing evaluation reports and providing feedback

[0539] Terminal: Users (employees and managers) view the evaluation report and check its contents.

[0540] Users (employees and supervisors): Users conduct feedback interviews based on the evaluation reports and enter the results of the interviews and areas for improvement into the system.

[0541] Feedback Loop

[0542] Server: Retrains the generative AI model based on the feedback data to improve the accuracy of the evaluation.

[0543] Server: Deploys the retrained model to the system and maintains consistent evaluation metrics.

[0544] Specific examples

[0545] For example, the project manager evaluation process involves the following steps:

[0546] 1. User (Project Manager): Enters project progress, completed tasks, and team member contributions into the device.

[0547] 2. Server: Automatically collects task completion and progress data from project management tools (e.g., JIRA or Trello) and consolidates all data.

[0548] 3. Server: The data preprocessing unit formats this data, and the generative AI model calculates an evaluation score based on it.

[0549] 4. Server: Generates an evaluation report for the project manager based on the evaluation scores.

[0550] 5. Users (project managers and superiors): Users conduct feedback interviews based on the evaluation reports and enter improvements into the system.

[0551] 6. Server: Ingests the feedback data, retrains the AI ​​model, and reflects it in the next evaluation.

[0552] Prompt Sentence Examples

[0553] "Please describe your contributions this week. Detail the specific tasks, results, and goals you achieved."

[0554] This system enables objective and fair evaluation of employees by managing a series of processes from data collection to evaluation and feedback loop in an integrated manner.

[0555] The flow of the identification process in the first embodiment will be described with reference to FIG.

[0556] Step 1:

[0557] Data collection

[0558] User (employee): The user uses a dedicated interface to input work content, progress, goals, and usage time into the terminal.

[0559] Input: Work, progress, goals, and time spent.

[0560] Output: The input working data.

[0561] Specific operation: The user uses a computer or tablet to enter data into a form on a web browser and presses the "Submit" button.

[0562] Server: The server issues API requests from project management tools (e.g., JIRA or Trello) to collect task completion and progress data.

[0563] Input: The API endpoint of your project management tool.

[0564] Output: Project progress data.

[0565] Specific operation: The server periodically runs an automatic script to retrieve the latest data from the project management tool and store it in the database.

[0566] Step 2:

[0567] Data Preprocessing

[0568] Server: Formats and standardizes collected data, ensures data consistency, and handles missing and noisy data.

[0569] Inputs: Task data from users and progress data collected from project management tools.

[0570] Output: Preprocessed data.

[0571] What it does: It uses a Python script to standardize date formats, fill in missing data with reasonable guesses, and filter out noisy data.

[0572] Step 3:

[0573] Evaluation by AI model

[0574] Server: The preprocessed data is input into a generative artificial intelligence model, and an evaluation score for each user is calculated.

[0575] Input: Preprocessed data.

[0576] Output: Evaluation score.

[0577] Specific operation: The server uses TensorFlow's Predict method to input preprocessed data into the AI ​​model and perform evaluation. The resulting evaluation scores are stored in the database.

[0578] Step 4:

[0579] Evaluation report generation

[0580] Server: Generates an evaluation report based on the evaluation score, which includes details of the score, reasons for the evaluation, areas for improvement, and a specific action plan.

[0581] Input: Rating score.

[0582] Output: Evaluation report.

[0583] Specific operation: Based on the evaluation score, an evaluation report is automatically generated using a template engine and saved in PDF format.

[0584] Step 5:

[0585] View the assessment report

[0586] Terminal: Users (employees and supervisors) use terminals to view the evaluation reports.

[0587] Input: Assessment report.

[0588] Output: Assessment report displayed on screen.

[0589] Specific operation: The user opens a web browser and checks the assessment report on the dashboard.

[0590] Step 6:

[0591] Gathering feedback

[0592] Users (employees and supervisors): Conduct feedback interviews based on the evaluation reports and enter the results into the system.

[0593] Input: Interview results and areas for improvement.

[0594] Output: Feedback data.

[0595] Specific actions: Enter the interview results in the feedback form and press the send button to the system.

[0596] Step 7:

[0597] Retraining generative AI models

[0598] Server: Retrains the generative AI model based on the feedback data.

[0599] Input: Feedback data.

[0600] Output: A retrained artificial intelligence model.

[0601] Specific actions: Retrain the AI ​​model with new feedback data and update the evaluation algorithm.

[0602] Step 8:

[0603] Deploying a retrained model

[0604] Server: Deploys the retrained model to the system.

[0605] Input: The retrained artificial intelligence model.

[0606] Output: Updated rating system.

[0607] Specific operation: Deploy a new AI model to the server to improve the evaluation accuracy of the entire system.

[0608] (Application example 1)

[0609] 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."

[0610] Modern factories are required to fairly and objectively evaluate the work efficiency and quality of robots and implement improvement measures in real time. However, conventional evaluation systems require a large amount of labor for data collection and preprocessing, making it difficult to ensure fair evaluations and rapid improvement. In addition, there is a lack of a mechanism for effectively reflecting feedback after evaluations in the next evaluation, making it difficult to achieve accurate evaluations and effective improvements.

[0611] 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.

[0612] In this invention, the server includes means for collecting task data using a data collection device, means for preprocessing the collected data using a data preprocessing device, means for calculating an evaluation score based on the data preprocessed by the generative artificial intelligence model, means for generating an evaluation report based on the evaluation score, means for making the evaluation report available for viewing, means for recording feedback data and updating the evaluation model, means for standardizing the collected data, and means for creating a specific action plan based on the evaluation results. This makes it possible to fairly and objectively evaluate the work efficiency and quality of a robot in real time and quickly reflect improvement measures.

[0613] A "data collection device" is a piece of equipment or software system that automatically collects work data.

[0614] A "data preprocessing device" is a device or software system that formats and standardizes collected data, removes noise, and converts it into an analyzable format.

[0615] A "generative artificial intelligence model" is an artificial intelligence algorithm or framework for calculating evaluation scores based on preprocessed data.

[0616] The "evaluation score" is an index that quantifies work efficiency and quality based on work data.

[0617] The "evaluation report generation means" is a device or software system that records the performance of each robot in detail based on the evaluation score and creates a report that presents areas for improvement and action plans.

[0618] "Feedback data" refers to data that records improvements and initiatives identified based on the evaluation results.

[0619] "Means for standardizing collected data" refers to equipment and software systems that convert collected data into a consistent format so that it can be analyzed and evaluated.

[0620] "Action plan creation means" refers to equipment or software systems used to plan and draft specific next improvement measures and initiatives based on the evaluation results.

[0621] The present invention is embodied as an evaluation system for fairly and objectively evaluating the work efficiency and quality of robots in a factory and for quickly incorporating improvement measures. Specific embodiments of the system are described below.

[0622] This system consists of a server equipped with a data collection device, a data preprocessing device, a generative AI model, an evaluation report generation means, and a feedback function, and a terminal for viewing the evaluation report.

[0623] Data collection

[0624] The server and data collection device automatically collects operational data from factory robots from automation tools such as SCADA systems, including robot operating hours, number of completed tasks, and task quality.

[0625] Data Preprocessing

[0626] The data preprocessing unit standardizes the collected data and removes noise. Specifically, it uses the Python programming language and data processing libraries such as Pandas and Scikit-learn to shape and standardize the data.

[0627] Evaluation and Analysis

[0628] The server inputs the preprocessed data into a generative artificial intelligence model to evaluate the robot's work efficiency and quality. The evaluation uses a clustering method (e.g., KMeans) to compare and analyze the performance of each robot, which then calculates an evaluation score for each robot.

[0629] Generate an assessment report

[0630] An evaluation report is generated based on the evaluation scores. The report includes the score for each robot, the reason for the evaluation, areas for improvement, and a specific action plan. The evaluation report is made available to users via their devices.

[0631] Feedback Loop

[0632] The user and their supervisor then hold a feedback interview based on the evaluation report. The feedback and areas for improvement from the interview are then re-entered into the system and reflected in the next evaluation cycle. The server uses this feedback data to retrain the generative AI model and improve the accuracy of the evaluation.

[0633] Hardware and software used

[0634] Hardware: Factory robots, SCADA systems, collection devices (sensors, etc.)

[0635] Software: Python, Pandas, Scikit-learn, server for data storage and processing

[0636] Specific examples

[0637] For example, the evaluation of a robot in a factory involves the following steps:

[0638] 1. Data collection: Collect robot operation data in CSV format through the SCADA system.

[0639] 2. Data preprocessing: Use StandardScaler to standardize the data and convert it into an analyzable format.

[0640] 3. Evaluation and Analysis: The KMeans clustering method is used to group the robots' performance and calculate the silhouette score.

[0641] 4. Evaluation report generation: An evaluation report will be created for each cluster summarizing areas for improvement and action plans.

[0642] 5. Feedback loop: Based on the evaluation results, the robot's settings and programs are fine-tuned and reflected in the next evaluation cycle.

[0643] Prompt Sentence Examples

[0644] You have collected operational data for robots in your factory. Please rate a robot with the following characteristics and provide an action plan to improve efficiency and quality:

[0645] Uptime

[0646] Number of completed tasks

[0647] Task Quality

[0648] In this way, the present invention comprehensively manages a series of processes from data collection to evaluation and feedback loops, thereby realizing efficient work management and quality improvement for factory robots.

[0649] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[0650] Step 1:

[0651] The server collects operational data from robots in the factory. Specifically, it obtains the robot's operational data through automation tools such as a SCADA system and saves it as a CSV file. Input includes data items such as the robot's operating time, number of completed tasks, and task quality. The output is a CSV file of the collected raw data.

[0652] Step 2:

[0653] The server preprocesses the collected data. Specifically, it reads the data using Python's Pandas library and standardizes the data using StandardScaler, which aligns the scale of each data item. The input includes the CSV file of raw data collected in step 1. The output is a standardized data frame.

[0654] Step 3:

[0655] The server inputs the preprocessed data into a generative artificial intelligence model and calculates an evaluation score. Specifically, it applies the KMeans clustering method using the Scikit-learn library to classify the data into clusters and calculate a silhouette score. The input includes the data frame preprocessed in step 2. The output generates a cluster number and evaluation score for each robot.

[0656] Step 4:

[0657] The server generates an evaluation report based on the evaluation scores, detailing the robot's performance and areas for improvement for each cluster. The input includes the cluster number and evaluation score generated in step 3. The output is a text file or PDF of the evaluation report.

[0658] Step 5:

[0659] The terminal provides the generated evaluation report for the user to view. Specifically, it displays the evaluation report through a web interface or a dedicated application, allowing the user to check the evaluation results. The input includes the evaluation report generated in step 4. The output includes a screen displaying the report and a printed report.

[0660] Step 6:

[0661] The user conducts a feedback interview based on the evaluation report and inputs the results into the system. Specifically, the user records the areas for improvement and the details of the efforts in an input form and reflects them in the next evaluation cycle. The input includes the user's feedback information. The output is recorded in the system.

[0662] Step 7:

[0663] The server uses the feedback data to retrain the generative AI model. Specifically, it uses the feedback data to update the model's parameters and apply them to the next evaluation. The input includes the feedback data collected in step 6. The output is a retrained AI model.

[0664] Step 8:

[0665] The server deploys the retrained model to the system and uses it for the next evaluation. Specifically, the latest model is incorporated into the system and applied to the next cycle of data collection to evaluation. The input includes the retrained model generated in step 7. The output includes the latest evaluation model installed in the system.

[0666] 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.

[0667] This invention combines a system for fairly and objectively evaluating employees' work efficiency and contribution with an emotion engine that recognizes the user's emotions. This system is composed of multiple terminals and a server, and provides more accurate evaluations and feedback.

[0668] System Configuration

[0669] The system includes a terminal, a server, a data collection device, a data preprocessing device, a generative AI model, an evaluation report generation device, a feedback data recording device, and an emotion engine. The terminal is used to input employee data and view evaluation reports, while the server is responsible for data collection, preprocessing, evaluation, report generation, feedback processing, and emotion recognition.

[0670] Program processing overview

[0671] Data collection

[0672] User (employee): The user enters daily work details, progress, achieved goals, usage time, etc. into a dedicated form on the terminal.

[0673] Server: Automatically collects task completion status and progress data from project management tools (e.g., JIRA, Trello, Redmine), and the emotion engine recognizes and records emotions in real time from user input data and interaction logs.

[0674] Data Preprocessing

[0675] Server: Formats and standardizes the collected data. For example, normalizes text data, standardizes the format of time series data, and completes missing values.

[0676] Server: Removes noise from all data, including emotion data, and converts it into the format required for evaluation.

[0677] Evaluation by AI model

[0678] Server: The preprocessed data is input into a generative artificial intelligence model to calculate evaluation scores for each employee based on efficiency, contribution, and goal achievement.

[0679] How it works: The AI ​​model calculates an evaluation score based on work time, number of completed tasks, project progress, and user emotional data, etc. Emotional data is taken into account as a correction factor for the evaluation.

[0680] Evaluation report generation

[0681] Server: Generates a rating report based on the rating scores and emotion data. The report includes the score for each category, the reason for the rating, areas for improvement, specific advice, and the user's emotional state.

[0682] Terminal: Users (employees and supervisors) view the generated evaluation report and check the evaluation results and feedback.

[0683] Providing Feedback

[0684] Users (employees and managers): Conduct feedback interviews based on the evaluation reports. Enter the details of the interviews and areas for improvement into the system, and also record emotional data.

[0685] Example: For example, when a project manager gives a progress report, the emotion engine uses facial recognition and voice analysis to assess their stress level and satisfaction in real time.

[0686] Retraining the model

[0687] Server: Collects feedback data and emotion data and adds it to the training dataset of the generative AI model.

[0688] Server: Retrains the AI ​​model with new data, makes adjustments to improve evaluation accuracy, and deploys the updated model to the system for the next evaluation cycle.

[0689] Specific examples

[0690] For example, the evaluation of a team leader involves the following steps:

[0691] 1. User (Team Leader): Enters the project progress, completed tasks, and team member contributions into the terminal. At the same time, the emotion engine records the leader's emotions when entering information.

[0692] 2. Server: Automatically collects relevant data from project management tools and consolidates all data.

[0693] 3. Server: The data preprocessor formats the data, and the generative AI model calculates an evaluation score. Emotion data from the emotion engine is also incorporated into the evaluation.

[0694] 4. Server: Generates an evaluation report for the team leader based on the evaluation scores and emotion data.

[0695] 5. Users (team leaders and superiors): Conduct feedback interviews based on the evaluation report and discuss specific improvement measures, taking into account the user's emotional state.

[0696] 6. Server: Collects feedback and sentiment data and retrains the model.

[0697] As can be seen, combining an emotion engine makes the employee evaluation process more accurate and comprehensive, providing specific and actionable feedback.

[0698] The processing flow will be explained below.

[0699] Step 1: Data collection

[0700] User (employee): Enters daily work details, progress, achieved goals, and usage time into a dedicated form on the device.

[0701] Server: Automatically collects task completion status, progress data, work logs, etc. from project management tools (e.g., JIRA, Trello, Redmine).

[0702] Server: The emotion engine recognizes and records emotions in real time from user input data and interaction logs. For example, emotion data is collected using a facial recognition camera or voice analysis software.

[0703] Step 2: Data Preprocessing

[0704] Server: Formats and standardizes the collected data. Specifically, it normalizes text data (for example, standardizing uppercase and lowercase letters), standardizes the format of time series data (for example, standardizing timestamps), and completes missing values ​​(for example, completing estimated values ​​based on previous and subsequent data).

[0705] Server: Removes noise from all data, including emotion data, and converts it into the format required for evaluation. For example, it deletes incorrect emotion recognition results and leaves only data with high recognition accuracy.

[0706] Step 3: Evaluation by AI model

[0707] Server: Inputs the preprocessed data into the generative artificial intelligence model.

[0708] Server: The AI ​​model analyzes the data and calculates an evaluation score for each employee, including their efficiency, contribution, and goal achievement. Specifically, the evaluation score is calculated based on factors such as work time, number of completed tasks, project progress, and user emotional data (e.g., stress level, satisfaction).

[0709] Server: Adjusts the evaluation score by taking into account emotional data. For example, if a person achieves high results even under high stress, the score is adjusted to be more highly rated.

[0710] Step 4: Generate an assessment report

[0711] Server: Generates an evaluation report for each employee based on the evaluation score and emotional data. The report contents include the score for each category, the reason for the evaluation, areas for improvement, specific advice, and an analysis of the employee's emotional state.

[0712] Terminal: Users (employees and supervisors) can view the generated evaluation report and compare it with their own evaluation to understand what improvements are needed.

[0713] Step 5: Provide feedback

[0714] Users (employees and managers): Conduct feedback interviews based on the evaluation reports. Re-enter the details of the interviews and areas for improvement into the system. At this time, the employee's emotional state during the interviews is also recorded to improve the quality of the feedback.

[0715] Example: For example, when a project manager gives a progress report, the emotion engine uses facial recognition and voice analysis to assess the manager's stress level and satisfaction in real time, providing feedback to improve the quality of the interview.

[0716] Step 6: Retrain the model

[0717] Server: Updates the learning dataset for the generative AI model based on feedback data and emotion data.

[0718] Server: Retrains the AI ​​model with new data and makes adjustments to improve the accuracy of the evaluation.

[0719] Server: Deploys the updated model to the system and makes it available for the next evaluation cycle.

[0720] This specific processing step enables fair and comprehensive employee evaluation, and by combining it with an emotion engine, it can provide even more accurate and actionable feedback.

[0721] Example 2

[0722] 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."

[0723] Traditional employee evaluation systems make it difficult to fairly and objectively evaluate employees' work efficiency and contributions, and often contain ambiguous standards and biases. Furthermore, because they do not take into account employees' emotions or psychological state, evaluations are one-sided and do not accurately reflect actual performance. Furthermore, because feedback and improvement measures are not specific, there are issues with them not contributing to employee growth or motivation.

[0724] 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.

[0725] In this invention, the server includes means for collecting work data using a data input device, means for collecting emotion data using an emotion recognition device, means for preprocessing the collected data using a data preprocessing device, means for calculating an evaluation score based on the data preprocessed by the generative artificial intelligence model, means for generating an evaluation report based on the evaluation score, means for making the evaluation report available for viewing, and means for recording feedback data and emotion data and updating the evaluation model. This allows for a fairer and more objective evaluation of employee work efficiency and contribution, and by incorporating emotion data, a more accurate and comprehensive evaluation is possible. It also allows for the provision of specific and practical feedback, contributing to employee growth and increased motivation.

[0726] A "data input device" is a device that allows a user to input work data such as the details of daily work, progress, goals achieved, and working hours.

[0727] An "emotion recognition device" is a device that recognizes a user's emotions in real time and collects them as emotion data.

[0728] A "data preprocessing device" is a device that formats and standardizes collected data, and performs tasks such as normalizing text data, removing noise, and filling in missing values.

[0729] A "generative artificial intelligence model" is an artificial intelligence that calculates evaluation scores for employee efficiency, contribution, and goal achievement based on preprocessed data.

[0730] An "evaluation report" is a report generated based on the evaluation scores and emotional data, and includes the scores for each category, the reasons for the evaluation, areas for improvement, specific advice, and the user's emotional state.

[0731] "Feedback data" refers to data that records what was discussed in the feedback interview and areas for improvement based on the evaluation report.

[0732] An "evaluation model" refers to the entire evaluation system, including the generative artificial intelligence model, and is used to calculate the evaluation score.

[0733] "Updating" refers to the process of adding new feedback and sentiment data to the evaluation model and retraining the model.

[0734] This invention combines an emotion recognition device with a system for fairly and objectively evaluating employees' work efficiency and contribution. The system consists of multiple terminals and a server, and provides more accurate evaluations and feedback.

[0735] System Configuration

[0736] The system includes a terminal, a server, a data input device, an emotion recognition device, a data preprocessing device, a generative AI model, an evaluation report generation device, and a feedback data recording device. The terminal is used to input employee data and view evaluation reports, while the server collects data, preprocesses it, evaluates it, generates reports, processes feedback, and recognizes emotions.

[0737] Server Configuration

[0738] The server implements the following measures:

[0739] 1. Work data collection means using a data input device: This is a device that allows users to input their daily work content, progress, goals achieved, usage time, etc. Specifically, users input this data into a dedicated form from a terminal.

[0740] 2. Emotion data collection using emotion recognition devices: Recognizing users' emotions in real time and collecting emotion data using facial recognition and voice analysis. For example, facial recognition software (e.g., Microsoft Azure Face API) and voice analysis tools (e.g., Google Cloud Speech-to-Text) are used.

[0741] 3. Data preprocessing device: A device that formats and standardizes collected data. For example, it normalizes text data, removes noise, and fills in missing values.

[0742] 4. Evaluation score calculation method using a generative artificial intelligence model: This is an artificial intelligence model that calculates evaluation scores for employee efficiency, contribution, and goal achievement based on preprocessed data.

[0743] 5. Evaluation report generator: A device that generates an evaluation report based on the evaluation score and emotion data.

[0744] 6. Evaluation report viewing means: This is a means for enabling users to view the evaluation report. Users can check the report via a web browser or dedicated application on their device.

[0745] 7. A means of recording feedback and sentiment data and updating the evaluation model: This is a means of recording what was discussed in the feedback interview and areas for improvement, and using that data to retrain the generative AI model.

[0746] Specific examples

[0747] For example, a team leader evaluation involves the following steps:

[0748] 1. User (Team Leader): Enters the project progress, completed tasks, and team member contributions into the terminal. At the same time, the emotion recognition device records the leader's emotions when entering information.

[0749] 2. Server: Automatically collects relevant data from project management software and consolidates all data.

[0750] 3. Server: The data preprocessor formats the data, and the generative AI model calculates an evaluation score. Emotion data from the emotion recognition device is also incorporated into the evaluation.

[0751] 4. Server: Generates an evaluation report for the team leader based on the evaluation scores and emotion data.

[0752] 5. Users (team leaders and superiors): Conduct feedback interviews based on the evaluation report and discuss specific improvement measures, taking into account the user's emotional state.

[0753] 6. Server: Collects feedback and emotion data and retrains the generative AI model.

[0754] Prompt Sentence Examples

[0755] "Calculate a rating score based on the task completion data and sentiment data entered by the user."

[0756] "Combine progress data with emotion logs to generate an evaluation report."

[0757] As described above, by combining emotion recognition devices, employee evaluations can be made more accurate and comprehensive, and specific, actionable feedback can be provided.

[0758] The flow of the identification process in the second embodiment will be described with reference to FIG.

[0759] Step 1:

[0760] Users enter work data such as daily work content, progress, achieved goals, and usage time into a dedicated form from their terminal.

[0761] Input: Work content, progress, goals, time used

[0762] Output: Record of input data

[0763] Specific operation: After the user completes the task "Document Creation" for Project X, they enter the task name, required time, degree of completion, etc. into a dedicated form on their terminal.

[0764] Step 2:

[0765] The server automatically collects task completion status and progress data from project management software (e.g., JIRA, Trello, Redmine).

[0766] Input: Task completion status data, progress data from project management software

[0767] Output: Record of collected data

[0768] Specific operation: Project and task data is periodically collected from each management software via API and stored in a database.

[0769] Step 3:

[0770] The server uses an emotion recognition device to recognize the user's emotions in real time from the user's input data and interaction logs, and records the emotion data.

[0771] Input: User input data, interaction logs

[0772] Output: Emotion data recording

[0773] What it does: Uses facial recognition software (e.g., Microsoft Azure Face API) and voice analysis tools (e.g., Google Cloud Speech-to-Text) to record the user's emotional state (stress level, satisfaction, etc.).

[0774] Step 4:

[0775] The server formats and standardizes the collected data, including emotion data, for example by normalizing text data, removing noise, and imputing missing values.

[0776] Input: Raw data collected

[0777] Output: Preprocessed data

[0778] Specific operations: Normalizing text data involves converting alphanumeric characters between half-width and full-width and removing unnecessary symbols. Eliminating noise involves correcting outliers and filling in missing data.

[0779] Step 5:

[0780] The server inputs the preprocessed data into a generative artificial intelligence model to calculate evaluation scores for each employee's efficiency, contribution, and goal achievement.

[0781] Input: Preprocessed data (work time, number of completed tasks, project progress, sentiment data, etc.)

[0782] Output: Evaluation score

[0783] How it works: Based on the input data, the AI ​​model calculates evaluation scores for efficiency, contribution, and goal achievement.

[0784] Step 6:

[0785] The server generates an evaluation report based on the evaluation score and the emotion data.

[0786] Input: Evaluation scores, emotion data

[0787] Output: Evaluation report

[0788] Specific Actions: Generate an evaluation report that includes the score for each category, the reason for the evaluation, areas for improvement, specific advice, and the user's emotional state.

[0789] Step 7:

[0790] The terminal allows users (employees and supervisors) to view the generated evaluation report.

[0791] Input: Generated assessment report

[0792] Output: User views the evaluation report

[0793] Specific operation: The user checks the evaluation report through a web browser or a dedicated app.

[0794] Step 8:

[0795] Users (employees and their superiors) conduct feedback interviews based on the evaluation reports. The system inputs the details of the discussions and areas for improvement, and also records emotional data.

[0796] Input: Evaluation report, interview details

[0797] Output: Feedback data, additional emotion data

[0798] Specific actions: Enter the specific improvement measures discussed in the feedback interview (e.g., participating in a stress management workshop) into the system, and also add your emotional state.

[0799] Step 9:

[0800] The server collects feedback data and emotion data and adds it to the training dataset of the generative artificial intelligence model.

[0801] Input: Feedback data, emotion data

[0802] Output: Updated training dataset

[0803] Specific operation: Add the feedback content and new emotion data entered into the system to the training dataset.

[0804] Step 10:

[0805] The server retrains the generative AI model with new data, makes adjustments to improve the accuracy of the evaluation, and deploys the updated model to the system.

[0806] Input: Updated training dataset

[0807] Output: Retrained AI model

[0808] Specific operation: The retrained AI model is deployed on the server and used for the next evaluation.

[0809] Through the above steps, a system is realized that can provide accurate and comprehensive evaluation and feedback that takes into account emotional data.

[0810] (Application example 2)

[0811] 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."

[0812] Conventional staff evaluation systems have problems with subjective evaluations, lacking fairness and accuracy. Furthermore, evaluations are one-sided and do not take into account the emotional state of staff, resulting in ineffective improvement measures. The present invention aims to provide a system that combines emotional data to more fairly and objectively evaluate staff work efficiency and contributions, and provide specific and practical feedback.

[0813] The specification processing by the specification processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means. In this invention, the server includes means for collecting task data by a data collection device, means for preprocessing the collected data by a data preprocessing device, means for calculating an evaluation score based on the data preprocessed by a generative artificial intelligence model, means for generating an evaluation report based on the evaluation score, means for making the evaluation report available for viewing, means for recording feedback data and updating the evaluation model, means for collecting user emotion data by an emotion engine, and means for correcting the evaluation based on the emotion data. This enables fair and objective evaluation and specific feedback that take emotion data into consideration.

[0814] The "data collection device" is a device for collecting task data, progress data, and even emotion data input by the user.

[0815] A "data preprocessing device" is a device that formats, standardizes, removes noise from, and converts collected data into a format required for evaluation.

[0816] A "generative artificial intelligence model" is an artificial intelligence technology that calculates a score to evaluate a user's efficiency, contribution, and goal achievement based on preprocessed data.

[0817] An "evaluation report" is a report that includes evaluation results, areas for improvement, and advice based on evaluation scores calculated by a generative artificial intelligence model.

[0818] An "emotion engine" is a technology that collects emotional data from users through facial recognition and voice analysis, and reflects that information in evaluations.

[0819] "Feedback data" refers to data that records the content discussed and areas for improvement in feedback interviews based on the evaluation report.

[0820] An "evaluation model" is an artificial intelligence algorithm that calculates efficiency and contribution based on a user's performance and emotional data.

[0821] "Task completion status" refers to data on the work and progress status that a user has completed using the management tool.

[0822] "Emotion data" is data that indicates the user's emotional state and is obtained through facial recognition and voice analysis.

[0823] "Preprocessed data" refers to raw data obtained from a data collection device after it has been shaped, standardized, and denoised.

[0824] This invention combines an emotion recognition engine with a system for fairly and objectively evaluating the work efficiency and contribution of staff in a brick-and-mortar store. This system is composed of a data collection device, a data preprocessing device, a generative AI model, an evaluation report generation device, a feedback data recording device, an emotion engine, and a server.

[0825] System Configuration

[0826] Data acquisition equipment:

[0827] Users enter data such as daily work details, task progress, achieved goals, and working hours into a dedicated form using a tablet or smartphone. Sales data and customer service data are also automatically collected from the POS system.

[0828] Data Preprocessor:

[0829] Format and standardize the collected data, including normalizing text data, standardizing the format of time series data, filling in missing values, and removing noise.

[0830] Generative AI models:

[0831] Based on the pre-processed data, an evaluation score is calculated for each staff member's efficiency, contribution, and goal achievement. The evaluation reflects work time, number of completed tasks, sales data, customer service data, etc. Emotion data collected by the emotion engine is used as a correction factor for the evaluation.

[0832] Evaluation report generator:

[0833] Based on the evaluation scores and emotional data, an evaluation report is automatically generated, including the score for each category, the reason for the evaluation, areas for improvement, specific advice, and the emotional state.

[0834] Feedback data recording device:

[0835] Staff members, store managers, and supervisors conduct feedback interviews based on the evaluation reports, and the results and areas for improvement are entered into the system, while emotional data is also recorded.

[0836] Emotion Engine:

[0837] Collect emotional data through facial recognition and voice analysis of staff members. Analyze and collect staff members' emotional states (e.g., stress levels, satisfaction) in real time.

[0838] server:

[0839] Oversees all data processing, including data collection, pre-processing, evaluation, report generation, feedback recording, and sentiment analysis. Generative AI models are periodically retrained based on feedback data.

[0840] Specific examples

[0841] For example, when a staff member enters the details of their work and sales data for the day on a tablet at the end of their workday, the emotion engine analyzes the staff member's stress level and satisfaction level from their facial expressions and voice. All of this data is sent to a server, where it is formatted and standardized by a pre-processing device. A generative AI model then analyzes the data and calculates an evaluation score. Finally, an evaluation report generator generates a report based on the evaluation score and emotion data, which the staff member and store manager use in feedback interviews.

[0842] Prompt Sentence Examples

[0843] Project details: Today's work and sales, task completion status, emotional data

[0844] Emotional data: stress level (high, medium, low), satisfaction (satisfied, dissatisfied, neutral)

[0845] Evaluation items: efficiency score, contribution score, goal achievement score

[0846] Feedback includes: areas for improvement, specific advice, and considerations for emotional state

[0847]

[0848] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[0849] Step 1:

[0850] Users enter data such as daily work details, task progress, achieved goals, and working hours into a dedicated form using a tablet or smartphone. The entered data is collected by a data collection device. Sales data and customer interaction data are also automatically collected from the POS system. This allows the system to obtain both input data and automatically collected data.

[0851] Step 2:

[0852] The emotion engine collects emotion data from the user's device through facial recognition and voice analysis. For example, it analyzes the user's facial expressions and voice when entering data, and converts emotions such as stress level and satisfaction into data in real time. This emotion data is also sent to the data collection device.

[0853] Step 3:

[0854] The server preprocesses the collected data using a data preprocessing device. Specifically, it normalizes text data, standardizes the format of time-series data, fills in missing values, removes noise, etc. This results in a standardized dataset.

[0855] Step 4:

[0856] The server inputs the preprocessed data into a generative AI model to calculate an evaluation score. The generative AI model calculates an evaluation score based on work time, number of completed tasks, sales data, customer service data, and emotional data. This results in an evaluation score that reflects the staff member's efficiency, contribution, and goal achievement.

[0857] Step 5:

[0858] The server generates an evaluation report based on the evaluation score and emotional data. The evaluation report generator creates a report that includes the score for each category, the reason for the evaluation, areas for improvement, specific advice, and the emotional state. This report is made available for viewing by the user, store manager, and supervisor.

[0859] Step 6:

[0860] The user and the store manager / supervisor then hold a feedback interview based on the evaluation report. The content of the discussion and areas for improvement during the interview are entered into the system, and new emotional data is also recorded. This allows feedback data to be obtained.

[0861] Step 7:

[0862] The server collects feedback data and sentiment data and adds it to the training dataset of the generative AI model. The server retrains the generative AI model with this new data to improve the accuracy of the evaluation. The updated model is deployed to the system and used in the next evaluation cycle.

[0863] 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.

[0864] 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.

[0865] 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.

[0866] [Third embodiment]

[0867] FIG. 5 shows an example of the configuration of a data processing system 310 according to the third embodiment.

[0868] 5, the data processing system 310 includes the data processing device 12 and a headset type terminal 314. An example of the data processing device 12 is a server.

[0869] 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).

[0870] 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.

[0871] 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.

[0872] 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).

[0873] 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.

[0874] 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.

[0875] 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.

[0876] 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.

[0877] 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.

[0878] 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."

[0879] The present invention provides a system for fairly and objectively evaluating the work efficiency and contribution of employees. Specific embodiments of the system are described below.

[0880] System Configuration

[0881] This system consists of multiple terminals and a server. The terminals are devices (such as PCs or tablets) that employees use to input data, and the server is the main processing device for collecting, preprocessing, and analyzing data, as well as generating and updating evaluation reports.

[0882] Program processing overview

[0883] Data collection

[0884] User (employee): The user inputs the details of his / her daily work, progress, goals achieved, and time used into the terminal using a dedicated interface.

[0885] Server: The server automatically collects task completion and progress data from project management tools (e.g., JIRA, Trello, Redmine), thereby integrating manual and automatically collected data.

[0886] Data Preprocessing

[0887] Server: The server formats and standardizes the collected data, checking for missing information, and in the process removing noise from the data and converting it into a unified format.

[0888] Evaluation by AI model

[0889] Server: The server inputs the preprocessed data into a generative AI model to calculate an evaluation score for each employee. The score is calculated based on multiple categories, including work efficiency, productivity, and work quality.

[0890] Evaluation report generation

[0891] Server: The server generates an evaluation report based on the evaluation scores, which includes the score for each category, the reason for the evaluation, areas for improvement, and a specific action plan.

[0892] Device: Users (employees and managers) can view the generated evaluation report and check the next goal setting and initiatives.

[0893] Feedback Loop

[0894] Users (employees and supervisors): Users (employees and supervisors) conduct feedback interviews based on the evaluation report. The feedback and improvements that emerged from the interviews are entered back into the system and reflected in the next evaluation cycle.

[0895] Server: The server retrains the generative AI model based on the feedback data to improve the accuracy of the evaluation.

[0896] Specific examples

[0897] For example, the evaluation of a project manager involves the following steps:

[0898] 1. User (Project Manager): Enters project progress, completed tasks, and team member contributions into the device.

[0899] 2. Server: The server automatically collects task completion and progress data from project management tools and consolidates all the data.

[0900] 3. Server: The data preprocessing unit formats this data, and the generative AI model calculates an evaluation score based on this.

[0901] 4. Server: Generates an evaluation report for the project manager based on the evaluation scores.

[0902] 5. Users (project managers and superiors): Users conduct feedback interviews based on the evaluation reports and enter improvements into the system as feedback.

[0903] 6. Server: The server takes the feedback data, retrains the AI ​​model, and reflects it in the next evaluation.

[0904] In this way, this system comprehensively manages a series of processes from data collection to evaluation and feedback loop, enabling objective and fair evaluation of employees.

[0905] The processing flow will be explained below.

[0906] Step 1: Data collection

[0907] User (employee): Enters daily work details, progress, achieved goals, usage time, etc. into a dedicated form on the device.

[0908] Server: Automatically collects task completion status, progress data, work logs, etc. from project management tools (e.g., JIRA, Trello, Redmine).

[0909] Step 2: Data Preprocessing

[0910] Server: Formats the collected data, such as normalizing text data, standardizing the format of time series data, and filling in missing values.

[0911] Server: The server removes noise from the collected data and converts it into the format required for evaluation, for example by filtering and standardizing the data.

[0912] Step 3: Evaluation by AI model

[0913] Server: Inputs the preprocessed data into the generative artificial intelligence model.

[0914] Server: The AI ​​model analyzes the data and calculates an evaluation score for each employee based on their work efficiency, contribution, goal achievement, etc.

[0915] Specific operation: Calculate a score based on each employee's work time, number of completed tasks, project progress, etc. Evaluation criteria include project success rate, work accuracy, productivity, etc.

[0916] Step 4: Generate an assessment report

[0917] Server: Generates an evaluation report for each employee based on the evaluation score. The report includes the evaluation score, the reason for the evaluation for each item, areas for improvement, and specific advice.

[0918] Terminal: Users (employees and managers) can view the generated evaluation report, understand their own evaluation, and identify areas for improvement.

[0919] Step 5: Provide feedback

[0920] Users (employees and managers): Conduct feedback interviews based on the evaluation reports. Enter the details of the interviews and points for improvement into the system.

[0921] Specific actions: The supervisor will refer to the evaluation report and provide specific advice to the employee, identifying areas for improvement and setting goals for the next time. The employee will then create a specific action plan based on the feedback.

[0922] Step 6: Retrain the model

[0923] Server: Collects feedback data and adds it to the training dataset of the generative AI model.

[0924] Server: Retrains the AI ​​model using new data and makes adjustments to improve the accuracy of the evaluation.

[0925] Server: Deploys the updated model to the system and makes it available for the next evaluation cycle.

[0926] Through these specific processing steps, fair and objective employee evaluations become possible, improving the efficiency and accuracy of the entire evaluation process.

[0927] Example 1

[0928] 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."

[0929] In today's business environment, it is extremely important to fairly and objectively evaluate employees' work efficiency and contributions. However, the evaluation process is complicated and subjective. Traditional evaluation systems also face issues such as being prone to human bias and lacking transparency and consistency. Furthermore, the lack of specific areas for improvement and action plans based on evaluation results makes it difficult to improve employee performance. There is a need to resolve these issues and build a fair and objective evaluation system.

[0930] 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.

[0931] In this invention, the server includes: means for collecting work data using a data collection device; means for users to input work content, progress, goals, and usage time into a terminal using a dedicated interface; means for the server to collect task completion status and progress data from a project management tool; means for standardizing and formatting the collected data using a data preprocessing device; means for processing missing data and noise data; means for calculating evaluation scores based on data preprocessed by a generative AI model; means for generating evaluation reports based on the evaluation scores; means for making the evaluation reports viewable; and means for recording feedback data and updating the evaluation model. This enables fair and objective evaluation by collecting detailed and consistent employee work data and evaluating them using a generative AI model based on preprocessed data. Furthermore, the evaluation report presents specific areas for improvement and action plans, contributing to improved employee performance.

[0932] A "data collection device" is a device for collecting data entered by a user or information automatically acquired from an external tool.

[0933] A "user" is a person who uses the system to input information such as work content, progress, goals, and usage time.

[0934] "Terminal" refers to a device used by a user to input data or view an evaluation report, including a PC or tablet.

[0935] "Server" is the central processing unit responsible for data collection, automated processing, analysis, and generation of evaluation reports.

[0936] A "project management tool" is software used to manage tasks and track progress, including tools such as JIRA and Trello.

[0937] A "data preprocessing device" is a device that standardizes and formats collected data and processes missing data and noise.

[0938] A "generative artificial intelligence model" is an artificial intelligence algorithm for calculating evaluation scores based on preprocessed data.

[0939] The "evaluation score" is a numerical indicator of a user's work efficiency and productivity calculated by a generative artificial intelligence model.

[0940] An "assessment report" is a document generated based on an assessment score, which includes details of the score, reasons for the assessment, areas for improvement, and a specific action plan.

[0941] "Feedback data" refers to information, including improvements and comments, that users input into the system based on feedback interviews.

[0942] "Retraining" is the process of using collected feedback data to improve the accuracy of a generative artificial intelligence model.

[0943] "Deployment" refers to running a retrained artificial intelligence model in a real system environment.

[0944] The present invention relates to a system for fairly and objectively evaluating the work efficiency and contribution of employees. This system is composed of multiple terminals and a server. Specific embodiments of the system are described below.

[0945] System Configuration

[0946] This system is configured as follows: The terminal is a device for users to input data, and the server is a device that performs the main processing for data collection, pre-processing, analysis, and generation and updating of evaluation reports.

[0947] Hardware and Software

[0948] Device: An input device such as a computer or tablet.

[0949] Server: A high-performance computer for data processing.

[0950] Project management tools: e.g., JIRA, Trello, Redmine, etc.

[0951] Generative artificial intelligence models: Use machine learning frameworks such as TensorFlow and PyTorch.

[0952] Program processing overview

[0953] Data collection

[0954] User (employee): The user inputs the details of daily work, progress, goals, and usage time into the terminal using a dedicated interface.

[0955] Server: The server automatically collects task completion and progress data from your project management tools, and consolidates all the data in one place using API requests.

[0956] Data Preprocessing

[0957] Server: The server formats and standardizes the collected data, and processes missing and noisy data. This process involves data cleansing using Python scripts.

[0958] Evaluation by AI model

[0959] Server: The preprocessed data is input into the generative AI model, and an evaluation score for each user is calculated using TensorFlow's Predict method.

[0960] Server: Generates an evaluation report based on the calculated evaluation score. The evaluation report includes details of the score, reasons for the evaluation, areas for improvement, and a specific action plan.

[0961] Viewing evaluation reports and providing feedback

[0962] Terminal: Users (employees and managers) view the evaluation report and check its contents.

[0963] Users (employees and supervisors): Users conduct feedback interviews based on the evaluation reports and enter the results of the interviews and areas for improvement into the system.

[0964] Feedback Loop

[0965] Server: Retrains the generative AI model based on the feedback data to improve the accuracy of the evaluation.

[0966] Server: Deploys the retrained model to the system and maintains consistent evaluation metrics.

[0967] Specific examples

[0968] For example, the project manager evaluation process involves the following steps:

[0969] 1. User (Project Manager): Enters project progress, completed tasks, and team member contributions into the device.

[0970] 2. Server: Automatically collects task completion and progress data from project management tools (e.g., JIRA or Trello) and consolidates all data.

[0971] 3. Server: The data preprocessing unit formats this data, and the generative AI model calculates an evaluation score based on it.

[0972] 4. Server: Generates an evaluation report for the project manager based on the evaluation scores.

[0973] 5. Users (project managers and superiors): Users conduct feedback interviews based on the evaluation reports and enter improvements into the system.

[0974] 6. Server: Ingests the feedback data, retrains the AI ​​model, and reflects it in the next evaluation.

[0975] Prompt Sentence Examples

[0976] "Please describe your contributions this week. Detail the specific tasks, results, and goals you achieved."

[0977] This system enables objective and fair evaluation of employees by managing a series of processes from data collection to evaluation and feedback loop in an integrated manner.

[0978] The flow of the identification process in the first embodiment will be described with reference to FIG.

[0979] Step 1:

[0980] Data collection

[0981] User (employee): The user uses a dedicated interface to input work content, progress, goals, and usage time into the terminal.

[0982] Input: Work, progress, goals, and time spent.

[0983] Output: The input working data.

[0984] Specific operation: The user uses a computer or tablet to enter data into a form on a web browser and presses the "Submit" button.

[0985] Server: The server issues API requests from project management tools (e.g., JIRA or Trello) to collect task completion and progress data.

[0986] Input: The API endpoint of your project management tool.

[0987] Output: Project progress data.

[0988] Specific operation: The server periodically runs an automatic script to retrieve the latest data from the project management tool and store it in the database.

[0989] Step 2:

[0990] Data Preprocessing

[0991] Server: Formats and standardizes collected data, ensures data consistency, and handles missing and noisy data.

[0992] Inputs: Task data from users and progress data collected from project management tools.

[0993] Output: Preprocessed data.

[0994] What it does: It uses a Python script to standardize date formats, fill in missing data with reasonable guesses, and filter out noisy data.

[0995] Step 3:

[0996] Evaluation by AI model

[0997] Server: The preprocessed data is input into a generative artificial intelligence model, and an evaluation score for each user is calculated.

[0998] Input: Preprocessed data.

[0999] Output: Evaluation score.

[1000] Specific operation: The server uses TensorFlow's Predict method to input preprocessed data into the AI ​​model and perform evaluation. The resulting evaluation scores are stored in the database.

[1001] Step 4:

[1002] Evaluation report generation

[1003] Server: Generates an evaluation report based on the evaluation score, which includes details of the score, reasons for the evaluation, areas for improvement, and a specific action plan.

[1004] Input: Rating score.

[1005] Output: Evaluation report.

[1006] Specific operation: Based on the evaluation score, an evaluation report is automatically generated using a template engine and saved in PDF format.

[1007] Step 5:

[1008] View the assessment report

[1009] Terminal: Users (employees and supervisors) use terminals to view the evaluation reports.

[1010] Input: Assessment report.

[1011] Output: Assessment report displayed on screen.

[1012] Specific operation: The user opens a web browser and checks the assessment report on the dashboard.

[1013] Step 6:

[1014] Gathering feedback

[1015] Users (employees and supervisors): Conduct feedback interviews based on the evaluation reports and enter the results into the system.

[1016] Input: Interview results and areas for improvement.

[1017] Output: Feedback data.

[1018] Specific actions: Enter the interview results in the feedback form and press the send button to the system.

[1019] Step 7:

[1020] Retraining generative AI models

[1021] Server: Retrains the generative AI model based on the feedback data.

[1022] Input: Feedback data.

[1023] Output: A retrained artificial intelligence model.

[1024] Specific actions: Retrain the AI ​​model with new feedback data and update the evaluation algorithm.

[1025] Step 8:

[1026] Deploying a retrained model

[1027] Server: Deploys the retrained model to the system.

[1028] Input: The retrained artificial intelligence model.

[1029] Output: Updated rating system.

[1030] Specific operation: Deploy a new AI model to the server to improve the evaluation accuracy of the entire system.

[1031] (Application example 1)

[1032] 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."

[1033] Modern factories are required to fairly and objectively evaluate the work efficiency and quality of robots and implement improvement measures in real time. However, conventional evaluation systems require a large amount of labor for data collection and preprocessing, making it difficult to ensure fair evaluations and rapid improvement. In addition, there is a lack of a mechanism for effectively reflecting feedback after evaluations in the next evaluation, making it difficult to achieve accurate evaluations and effective improvements.

[1034] 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.

[1035] In this invention, the server includes means for collecting task data using a data collection device, means for preprocessing the collected data using a data preprocessing device, means for calculating an evaluation score based on the data preprocessed by the generative artificial intelligence model, means for generating an evaluation report based on the evaluation score, means for making the evaluation report available for viewing, means for recording feedback data and updating the evaluation model, means for standardizing the collected data, and means for creating a specific action plan based on the evaluation results. This makes it possible to fairly and objectively evaluate the work efficiency and quality of a robot in real time and quickly reflect improvement measures.

[1036] A "data collection device" is a piece of equipment or software system that automatically collects work data.

[1037] A "data preprocessing device" is a device or software system that formats and standardizes collected data, removes noise, and converts it into an analyzable format.

[1038] A "generative artificial intelligence model" is an artificial intelligence algorithm or framework for calculating evaluation scores based on preprocessed data.

[1039] The "evaluation score" is an index that quantifies work efficiency and quality based on work data.

[1040] The "evaluation report generation means" is a device or software system that records the performance of each robot in detail based on the evaluation score and creates a report that presents areas for improvement and action plans.

[1041] "Feedback data" refers to data that records improvements and initiatives identified based on the evaluation results.

[1042] "Means for standardizing collected data" refers to equipment and software systems that convert collected data into a consistent format so that it can be analyzed and evaluated.

[1043] "Action plan creation means" refers to equipment or software systems used to plan and draft specific next improvement measures and initiatives based on the evaluation results.

[1044] The present invention is embodied as an evaluation system for fairly and objectively evaluating the work efficiency and quality of robots in a factory and for quickly incorporating improvement measures. Specific embodiments of the system are described below.

[1045] This system consists of a server equipped with a data collection device, a data preprocessing device, a generative AI model, an evaluation report generation means, and a feedback function, and a terminal for viewing the evaluation report.

[1046] Data collection

[1047] The server and data collection device automatically collects operational data from factory robots from automation tools such as SCADA systems, including robot operating hours, number of completed tasks, and task quality.

[1048] Data Preprocessing

[1049] The data preprocessing unit standardizes the collected data and removes noise. Specifically, it uses the Python programming language and data processing libraries such as Pandas and Scikit-learn to shape and standardize the data.

[1050] Evaluation and Analysis

[1051] The server inputs the preprocessed data into a generative artificial intelligence model to evaluate the robot's work efficiency and quality. The evaluation uses a clustering method (e.g., KMeans) to compare and analyze the performance of each robot, which then calculates an evaluation score for each robot.

[1052] Generate an assessment report

[1053] An evaluation report is generated based on the evaluation scores. The report includes the score for each robot, the reason for the evaluation, areas for improvement, and a specific action plan. The evaluation report is made available to users via their devices.

[1054] Feedback Loop

[1055] The user and their supervisor then hold a feedback interview based on the evaluation report. The feedback and areas for improvement from the interview are then re-entered into the system and reflected in the next evaluation cycle. The server uses this feedback data to retrain the generative AI model and improve the accuracy of the evaluation.

[1056] Hardware and software used

[1057] Hardware: Factory robots, SCADA systems, collection devices (sensors, etc.)

[1058] Software: Python, Pandas, Scikit-learn, server for data storage and processing

[1059] Specific examples

[1060] For example, the evaluation of a robot in a factory involves the following steps:

[1061] 1. Data collection: Collect robot operation data in CSV format through the SCADA system.

[1062] 2. Data preprocessing: Use StandardScaler to standardize the data and convert it into an analyzable format.

[1063] 3. Evaluation and Analysis: The KMeans clustering method is used to group the robots' performance and calculate the silhouette score.

[1064] 4. Evaluation report generation: An evaluation report will be created for each cluster summarizing areas for improvement and action plans.

[1065] 5. Feedback loop: Based on the evaluation results, the robot's settings and programs are fine-tuned and reflected in the next evaluation cycle.

[1066] Prompt Sentence Examples

[1067] You have collected operational data for robots in your factory. Please rate a robot with the following characteristics and provide an action plan to improve efficiency and quality:

[1068] Uptime

[1069] Number of completed tasks

[1070] Task Quality

[1071] In this way, the present invention comprehensively manages a series of processes from data collection to evaluation and feedback loops, thereby realizing efficient work management and quality improvement for factory robots.

[1072] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[1073] Step 1:

[1074] The server collects operational data from robots in the factory. Specifically, it obtains the robot's operational data through automation tools such as a SCADA system and saves it as a CSV file. Input includes data items such as the robot's operating time, number of completed tasks, and task quality. The output is a CSV file of the collected raw data.

[1075] Step 2:

[1076] The server preprocesses the collected data. Specifically, it reads the data using Python's Pandas library and standardizes the data using StandardScaler, which aligns the scale of each data item. The input includes the CSV file of raw data collected in step 1. The output is a standardized data frame.

[1077] Step 3:

[1078] The server inputs the preprocessed data into a generative artificial intelligence model and calculates an evaluation score. Specifically, it applies the KMeans clustering method using the Scikit-learn library to classify the data into clusters and calculate a silhouette score. The input includes the data frame preprocessed in step 2. The output generates a cluster number and evaluation score for each robot.

[1079] Step 4:

[1080] The server generates an evaluation report based on the evaluation scores, detailing the robot's performance and areas for improvement for each cluster. The input includes the cluster number and evaluation score generated in step 3. The output is a text file or PDF of the evaluation report.

[1081] Step 5:

[1082] The terminal provides the generated evaluation report for the user to view. Specifically, it displays the evaluation report through a web interface or a dedicated application, allowing the user to check the evaluation results. The input includes the evaluation report generated in step 4. The output includes a screen displaying the report and a printed report.

[1083] Step 6:

[1084] The user conducts a feedback interview based on the evaluation report and inputs the results into the system. Specifically, the user records the areas for improvement and the details of the efforts in an input form and reflects them in the next evaluation cycle. The input includes the user's feedback information. The output is recorded in the system.

[1085] Step 7:

[1086] The server uses the feedback data to retrain the generative AI model. Specifically, it uses the feedback data to update the model's parameters and apply them to the next evaluation. The input includes the feedback data collected in step 6. The output is a retrained AI model.

[1087] Step 8:

[1088] The server deploys the retrained model to the system and uses it for the next evaluation. Specifically, the latest model is incorporated into the system and applied to the next cycle of data collection to evaluation. The input includes the retrained model generated in step 7. The output includes the latest evaluation model installed in the system.

[1089] 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.

[1090] This invention combines a system for fairly and objectively evaluating employees' work efficiency and contribution with an emotion engine that recognizes the user's emotions. This system is composed of multiple terminals and a server, and provides more accurate evaluations and feedback.

[1091] System Configuration

[1092] The system includes a terminal, a server, a data collection device, a data preprocessing device, a generative AI model, an evaluation report generation device, a feedback data recording device, and an emotion engine. The terminal is used to input employee data and view evaluation reports, while the server is responsible for data collection, preprocessing, evaluation, report generation, feedback processing, and emotion recognition.

[1093] Program processing overview

[1094] Data collection

[1095] User (employee): The user enters daily work details, progress, achieved goals, usage time, etc. into a dedicated form on the terminal.

[1096] Server: Automatically collects task completion status and progress data from project management tools (e.g., JIRA, Trello, Redmine), and the emotion engine recognizes and records emotions in real time from user input data and interaction logs.

[1097] Data Preprocessing

[1098] Server: Formats and standardizes the collected data. For example, normalizes text data, standardizes the format of time series data, and completes missing values.

[1099] Server: Removes noise from all data, including emotion data, and converts it into the format required for evaluation.

[1100] Evaluation by AI model

[1101] Server: The preprocessed data is input into a generative artificial intelligence model to calculate evaluation scores for each employee based on efficiency, contribution, and goal achievement.

[1102] How it works: The AI ​​model calculates an evaluation score based on work time, number of completed tasks, project progress, and user emotional data, etc. Emotional data is taken into account as a correction factor for the evaluation.

[1103] Evaluation report generation

[1104] Server: Generates a rating report based on the rating scores and emotion data. The report includes the score for each category, the reason for the rating, areas for improvement, specific advice, and the user's emotional state.

[1105] Terminal: Users (employees and supervisors) view the generated evaluation report and check the evaluation results and feedback.

[1106] Providing Feedback

[1107] Users (employees and managers): Conduct feedback interviews based on the evaluation reports. Enter the details of the interviews and areas for improvement into the system, and also record emotional data.

[1108] Example: For example, when a project manager gives a progress report, the emotion engine uses facial recognition and voice analysis to assess their stress level and satisfaction in real time.

[1109] Retraining the model

[1110] Server: Collects feedback data and emotion data and adds it to the training dataset of the generative AI model.

[1111] Server: Retrains the AI ​​model with new data, makes adjustments to improve evaluation accuracy, and deploys the updated model to the system for the next evaluation cycle.

[1112] Specific examples

[1113] For example, the evaluation of a team leader involves the following steps:

[1114] 1. User (Team Leader): Enters the project progress, completed tasks, and team member contributions into the terminal. At the same time, the emotion engine records the leader's emotions when entering information.

[1115] 2. Server: Automatically collects relevant data from project management tools and consolidates all data.

[1116] 3. Server: The data preprocessor formats the data, and the generative AI model calculates an evaluation score. Emotion data from the emotion engine is also incorporated into the evaluation.

[1117] 4. Server: Generates an evaluation report for the team leader based on the evaluation scores and emotion data.

[1118] 5. Users (team leaders and superiors): Conduct feedback interviews based on the evaluation report and discuss specific improvement measures, taking into account the user's emotional state.

[1119] 6. Server: Collects feedback and sentiment data and retrains the model.

[1120] As can be seen, combining an emotion engine makes the employee evaluation process more accurate and comprehensive, providing specific and actionable feedback.

[1121] The processing flow will be explained below.

[1122] Step 1: Data collection

[1123] User (employee): Enters daily work details, progress, achieved goals, and usage time into a dedicated form on the device.

[1124] Server: Automatically collects task completion status, progress data, work logs, etc. from project management tools (e.g., JIRA, Trello, Redmine).

[1125] Server: The emotion engine recognizes and records emotions in real time from user input data and interaction logs. For example, emotion data is collected using a facial recognition camera or voice analysis software.

[1126] Step 2: Data Preprocessing

[1127] Server: Formats and standardizes the collected data. Specifically, it normalizes text data (for example, standardizing uppercase and lowercase letters), standardizes the format of time series data (for example, standardizing timestamps), and completes missing values ​​(for example, completing estimated values ​​based on previous and subsequent data).

[1128] Server: Removes noise from all data, including emotion data, and converts it into the format required for evaluation. For example, it deletes incorrect emotion recognition results and leaves only data with high recognition accuracy.

[1129] Step 3: Evaluation by AI model

[1130] Server: Inputs the preprocessed data into the generative artificial intelligence model.

[1131] Server: The AI ​​model analyzes the data and calculates an evaluation score for each employee, including their efficiency, contribution, and goal achievement. Specifically, the evaluation score is calculated based on factors such as work time, number of completed tasks, project progress, and user emotional data (e.g., stress level, satisfaction).

[1132] Server: Adjusts the evaluation score by taking into account emotional data. For example, if a person achieves high results even under high stress, the score is adjusted to be more highly rated.

[1133] Step 4: Generate an assessment report

[1134] Server: Generates an evaluation report for each employee based on the evaluation score and emotional data. The report contents include the score for each category, the reason for the evaluation, areas for improvement, specific advice, and an analysis of the employee's emotional state.

[1135] Terminal: Users (employees and supervisors) can view the generated evaluation report and compare it with their own evaluation to understand what improvements are needed.

[1136] Step 5: Provide feedback

[1137] Users (employees and managers): Conduct feedback interviews based on the evaluation reports. Re-enter the details of the interviews and areas for improvement into the system. At this time, the employee's emotional state during the interviews is also recorded to improve the quality of the feedback.

[1138] Example: For example, when a project manager gives a progress report, the emotion engine uses facial recognition and voice analysis to assess the manager's stress level and satisfaction in real time, providing feedback to improve the quality of the interview.

[1139] Step 6: Retrain the model

[1140] Server: Updates the learning dataset for the generative AI model based on feedback data and emotion data.

[1141] Server: Retrains the AI ​​model with new data and makes adjustments to improve the accuracy of the evaluation.

[1142] Server: Deploys the updated model to the system and makes it available for the next evaluation cycle.

[1143] This specific processing step enables fair and comprehensive employee evaluation, and by combining it with an emotion engine, it can provide even more accurate and actionable feedback.

[1144] Example 2

[1145] 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."

[1146] Traditional employee evaluation systems make it difficult to fairly and objectively evaluate employees' work efficiency and contributions, and often contain ambiguous standards and biases. Furthermore, because they do not take into account employees' emotions or psychological state, evaluations are one-sided and do not accurately reflect actual performance. Furthermore, because feedback and improvement measures are not specific, there are issues with them not contributing to employee growth or motivation.

[1147] 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.

[1148] In this invention, the server includes means for collecting work data using a data input device, means for collecting emotion data using an emotion recognition device, means for preprocessing the collected data using a data preprocessing device, means for calculating an evaluation score based on the data preprocessed by the generative artificial intelligence model, means for generating an evaluation report based on the evaluation score, means for making the evaluation report available for viewing, and means for recording feedback data and emotion data and updating the evaluation model. This allows for a fairer and more objective evaluation of employee work efficiency and contribution, and by incorporating emotion data, a more accurate and comprehensive evaluation is possible. It also allows for the provision of specific and practical feedback, contributing to employee growth and increased motivation.

[1149] A "data input device" is a device that allows a user to input work data such as the details of daily work, progress, goals achieved, and working hours.

[1150] An "emotion recognition device" is a device that recognizes a user's emotions in real time and collects them as emotion data.

[1151] A "data preprocessing device" is a device that formats and standardizes collected data, and performs tasks such as normalizing text data, removing noise, and filling in missing values.

[1152] A "generative artificial intelligence model" is an artificial intelligence that calculates evaluation scores for employee efficiency, contribution, and goal achievement based on preprocessed data.

[1153] An "evaluation report" is a report generated based on the evaluation scores and emotional data, and includes the scores for each category, the reasons for the evaluation, areas for improvement, specific advice, and the user's emotional state.

[1154] "Feedback data" refers to data that records what was discussed in the feedback interview and areas for improvement based on the evaluation report.

[1155] An "evaluation model" refers to the entire evaluation system, including the generative artificial intelligence model, and is used to calculate the evaluation score.

[1156] "Updating" refers to the process of adding new feedback and sentiment data to the evaluation model and retraining the model.

[1157] This invention combines an emotion recognition device with a system for fairly and objectively evaluating employees' work efficiency and contribution. The system consists of multiple terminals and a server, and provides more accurate evaluations and feedback.

[1158] System Configuration

[1159] The system includes a terminal, a server, a data input device, an emotion recognition device, a data preprocessing device, a generative AI model, an evaluation report generation device, and a feedback data recording device. The terminal is used to input employee data and view evaluation reports, while the server collects data, preprocesses it, evaluates it, generates reports, processes feedback, and recognizes emotions.

[1160] Server Configuration

[1161] The server implements the following measures:

[1162] 1. Work data collection means using a data input device: This is a device that allows users to input their daily work content, progress, goals achieved, usage time, etc. Specifically, users input this data into a dedicated form from a terminal.

[1163] 2. Emotion data collection using emotion recognition devices: Recognizing users' emotions in real time and collecting emotion data using facial recognition and voice analysis. For example, facial recognition software (e.g., Microsoft Azure Face API) and voice analysis tools (e.g., Google Cloud Speech-to-Text) are used.

[1164] 3. Data preprocessing device: A device that formats and standardizes collected data. For example, it normalizes text data, removes noise, and fills in missing values.

[1165] 4. Evaluation score calculation method using a generative artificial intelligence model: This is an artificial intelligence model that calculates evaluation scores for employee efficiency, contribution, and goal achievement based on preprocessed data.

[1166] 5. Evaluation report generator: A device that generates an evaluation report based on the evaluation score and emotion data.

[1167] 6. Evaluation report viewing means: This is a means for enabling users to view the evaluation report. Users can check the report via a web browser or dedicated application on their device.

[1168] 7. A means of recording feedback and sentiment data and updating the evaluation model: This is a means of recording what was discussed in the feedback interview and areas for improvement, and using that data to retrain the generative AI model.

[1169] Specific examples

[1170] For example, a team leader evaluation involves the following steps:

[1171] 1. User (Team Leader): Enters the project progress, completed tasks, and team member contributions into the terminal. At the same time, the emotion recognition device records the leader's emotions when entering information.

[1172] 2. Server: Automatically collects relevant data from project management software and consolidates all data.

[1173] 3. Server: The data preprocessor formats the data, and the generative AI model calculates an evaluation score. Emotion data from the emotion recognition device is also incorporated into the evaluation.

[1174] 4. Server: Generates an evaluation report for the team leader based on the evaluation scores and emotion data.

[1175] 5. Users (team leaders and superiors): Conduct feedback interviews based on the evaluation report and discuss specific improvement measures, taking into account the user's emotional state.

[1176] 6. Server: Collects feedback and emotion data and retrains the generative AI model.

[1177] Prompt Sentence Examples

[1178] "Calculate a rating score based on the task completion data and sentiment data entered by the user."

[1179] "Combine progress data with emotion logs to generate an evaluation report."

[1180] As described above, by combining emotion recognition devices, employee evaluations can be made more accurate and comprehensive, and specific, actionable feedback can be provided.

[1181] The flow of the identification process in the second embodiment will be described with reference to FIG.

[1182] Step 1:

[1183] Users enter work data such as daily work content, progress, achieved goals, and usage time into a dedicated form from their terminal.

[1184] Input: Work content, progress, goals, time used

[1185] Output: Record of input data

[1186] Specific operation: After the user completes the task "Document Creation" for Project X, they enter the task name, required time, degree of completion, etc. into a dedicated form on their terminal.

[1187] Step 2:

[1188] The server automatically collects task completion status and progress data from project management software (e.g., JIRA, Trello, Redmine).

[1189] Input: Task completion status data, progress data from project management software

[1190] Output: Record of collected data

[1191] Specific operation: Project and task data is periodically collected from each management software via API and stored in a database.

[1192] Step 3:

[1193] The server uses an emotion recognition device to recognize the user's emotions in real time from the user's input data and interaction logs, and records the emotion data.

[1194] Input: User input data, interaction logs

[1195] Output: Emotion data recording

[1196] What it does: Uses facial recognition software (e.g., Microsoft Azure Face API) and voice analysis tools (e.g., Google Cloud Speech-to-Text) to record the user's emotional state (stress level, satisfaction, etc.).

[1197] Step 4:

[1198] The server formats and standardizes the collected data, including emotion data, for example by normalizing text data, removing noise, and imputing missing values.

[1199] Input: Raw data collected

[1200] Output: Preprocessed data

[1201] Specific operations: Normalizing text data involves converting alphanumeric characters between half-width and full-width and removing unnecessary symbols. Eliminating noise involves correcting outliers and filling in missing data.

[1202] Step 5:

[1203] The server inputs the preprocessed data into a generative artificial intelligence model to calculate evaluation scores for each employee's efficiency, contribution, and goal achievement.

[1204] Input: Preprocessed data (work time, number of completed tasks, project progress, sentiment data, etc.)

[1205] Output: Evaluation score

[1206] How it works: Based on the input data, the AI ​​model calculates evaluation scores for efficiency, contribution, and goal achievement.

[1207] Step 6:

[1208] The server generates an evaluation report based on the evaluation score and the emotion data.

[1209] Input: Evaluation scores, emotion data

[1210] Output: Evaluation report

[1211] Specific Actions: Generate an evaluation report that includes the score for each category, the reason for the evaluation, areas for improvement, specific advice, and the user's emotional state.

[1212] Step 7:

[1213] The terminal allows users (employees and supervisors) to view the generated evaluation report.

[1214] Input: Generated assessment report

[1215] Output: User views the evaluation report

[1216] Specific operation: The user checks the evaluation report through a web browser or a dedicated app.

[1217] Step 8:

[1218] Users (employees and their superiors) conduct feedback interviews based on the evaluation reports. The system inputs the details of the discussions and areas for improvement, and also records emotional data.

[1219] Input: Evaluation report, interview details

[1220] Output: Feedback data, additional emotion data

[1221] Specific actions: Enter the specific improvement measures discussed in the feedback interview (e.g., participating in a stress management workshop) into the system, and also add your emotional state.

[1222] Step 9:

[1223] The server collects feedback data and emotion data and adds it to the training dataset of the generative artificial intelligence model.

[1224] Input: Feedback data, emotion data

[1225] Output: Updated training dataset

[1226] Specific operation: Add the feedback content and new emotion data entered into the system to the training dataset.

[1227] Step 10:

[1228] The server retrains the generative AI model with new data, makes adjustments to improve the accuracy of the evaluation, and deploys the updated model to the system.

[1229] Input: Updated training dataset

[1230] Output: Retrained AI model

[1231] Specific operation: The retrained AI model is deployed on the server and used for the next evaluation.

[1232] Through the above steps, a system is realized that can provide accurate and comprehensive evaluation and feedback that takes into account emotional data.

[1233] (Application example 2)

[1234] 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."

[1235] Conventional staff evaluation systems have problems with subjective evaluations, lacking fairness and accuracy. Furthermore, evaluations are one-sided and do not take into account the emotional state of staff, resulting in ineffective improvement measures. The present invention aims to provide a system that combines emotional data to more fairly and objectively evaluate staff work efficiency and contributions, and provide specific and practical feedback.

[1236] The specification processing by the specification processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means. In this invention, the server includes means for collecting task data by a data collection device, means for preprocessing the collected data by a data preprocessing device, means for calculating an evaluation score based on the data preprocessed by a generative artificial intelligence model, means for generating an evaluation report based on the evaluation score, means for making the evaluation report available for viewing, means for recording feedback data and updating the evaluation model, means for collecting user emotion data by an emotion engine, and means for correcting the evaluation based on the emotion data. This enables fair and objective evaluation and specific feedback that take emotion data into consideration.

[1237] The "data collection device" is a device for collecting task data, progress data, and even emotion data input by the user.

[1238] A "data preprocessing device" is a device that formats, standardizes, removes noise from, and converts collected data into a format required for evaluation.

[1239] A "generative artificial intelligence model" is an artificial intelligence technology that calculates a score to evaluate a user's efficiency, contribution, and goal achievement based on preprocessed data.

[1240] An "evaluation report" is a report that includes evaluation results, areas for improvement, and advice based on evaluation scores calculated by a generative artificial intelligence model.

[1241] An "emotion engine" is a technology that collects emotional data from users through facial recognition and voice analysis, and reflects that information in evaluations.

[1242] "Feedback data" refers to data that records the content discussed and areas for improvement in feedback interviews based on the evaluation report.

[1243] An "evaluation model" is an artificial intelligence algorithm that calculates efficiency and contribution based on a user's performance and emotional data.

[1244] "Task completion status" refers to data on the work and progress status that a user has completed using the management tool.

[1245] "Emotion data" is data that indicates the user's emotional state and is obtained through facial recognition and voice analysis.

[1246] "Preprocessed data" refers to raw data obtained from a data collection device after it has been shaped, standardized, and denoised.

[1247] This invention combines an emotion recognition engine with a system for fairly and objectively evaluating the work efficiency and contribution of staff in a brick-and-mortar store. This system is composed of a data collection device, a data preprocessing device, a generative AI model, an evaluation report generation device, a feedback data recording device, an emotion engine, and a server.

[1248] System Configuration

[1249] Data acquisition equipment:

[1250] Users enter data such as daily work details, task progress, achieved goals, and working hours into a dedicated form using a tablet or smartphone. Sales data and customer service data are also automatically collected from the POS system.

[1251] Data Preprocessor:

[1252] Format and standardize the collected data, including normalizing text data, standardizing the format of time series data, filling in missing values, and removing noise.

[1253] Generative AI models:

[1254] Based on the pre-processed data, an evaluation score is calculated for each staff member's efficiency, contribution, and goal achievement. The evaluation reflects work time, number of completed tasks, sales data, customer service data, etc. Emotion data collected by the emotion engine is used as a correction factor for the evaluation.

[1255] Evaluation report generator:

[1256] Based on the evaluation scores and emotional data, an evaluation report is automatically generated, including the score for each category, the reason for the evaluation, areas for improvement, specific advice, and the emotional state.

[1257] Feedback data recording device:

[1258] Staff members, store managers, and supervisors conduct feedback interviews based on the evaluation reports, and the results and areas for improvement are entered into the system, while emotional data is also recorded.

[1259] Emotion Engine:

[1260] Collect emotional data through facial recognition and voice analysis of staff members. Analyze and collect staff members' emotional states (e.g., stress levels, satisfaction) in real time.

[1261] server:

[1262] Oversees all data processing, including data collection, pre-processing, evaluation, report generation, feedback recording, and sentiment analysis. Generative AI models are periodically retrained based on feedback data.

[1263] Specific examples

[1264] For example, when a staff member enters the details of their work and sales data for the day on a tablet at the end of their workday, the emotion engine analyzes the staff member's stress level and satisfaction level from their facial expressions and voice. All of this data is sent to a server, where it is formatted and standardized by a pre-processing device. A generative AI model then analyzes the data and calculates an evaluation score. Finally, an evaluation report generator generates a report based on the evaluation score and emotion data, which the staff member and store manager use in feedback interviews.

[1265] Prompt Sentence Examples

[1266] Project details: Today's work and sales, task completion status, emotional data

[1267] Emotional data: stress level (high, medium, low), satisfaction (satisfied, dissatisfied, neutral)

[1268] Evaluation items: efficiency score, contribution score, goal achievement score

[1269] Feedback includes: areas for improvement, specific advice, and considerations for emotional state

[1270]

[1271] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[1272] Step 1:

[1273] Users enter data such as daily work details, task progress, achieved goals, and working hours into a dedicated form using a tablet or smartphone. The entered data is collected by a data collection device. Sales data and customer interaction data are also automatically collected from the POS system. This allows the system to obtain both input data and automatically collected data.

[1274] Step 2:

[1275] The emotion engine collects emotion data from the user's device through facial recognition and voice analysis. For example, it analyzes the user's facial expressions and voice when entering data, and converts emotions such as stress level and satisfaction into data in real time. This emotion data is also sent to the data collection device.

[1276] Step 3:

[1277] The server preprocesses the collected data using a data preprocessing device. Specifically, it normalizes text data, standardizes the format of time-series data, fills in missing values, removes noise, etc. This results in a standardized dataset.

[1278] Step 4:

[1279] The server inputs the preprocessed data into a generative AI model to calculate an evaluation score. The generative AI model calculates an evaluation score based on work time, number of completed tasks, sales data, customer service data, and emotional data. This results in an evaluation score that reflects the staff member's efficiency, contribution, and goal achievement.

[1280] Step 5:

[1281] The server generates an evaluation report based on the evaluation score and emotional data. The evaluation report generator creates a report that includes the score for each category, the reason for the evaluation, areas for improvement, specific advice, and the emotional state. This report is made available for viewing by the user, store manager, and supervisor.

[1282] Step 6:

[1283] The user and the store manager / supervisor then hold a feedback interview based on the evaluation report. The content of the discussion and areas for improvement during the interview are entered into the system, and new emotional data is also recorded. This allows feedback data to be obtained.

[1284] Step 7:

[1285] The server collects feedback data and sentiment data and adds it to the training dataset of the generative AI model. The server retrains the generative AI model with this new data to improve the accuracy of the evaluation. The updated model is deployed to the system and used in the next evaluation cycle.

[1286] 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.

[1287] 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.

[1288] 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.

[1289] [Fourth embodiment]

[1290] FIG. 7 shows an example of the configuration of a data processing system 410 according to the fourth embodiment.

[1291] 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.

[1292] 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).

[1293] 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.

[1294] 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.

[1295] 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).

[1296] 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.

[1297] 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.

[1298] 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.

[1299] 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.

[1300] 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.

[1301] 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.

[1302] 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."

[1303] The present invention provides a system for fairly and objectively evaluating the work efficiency and contribution of employees. Specific embodiments of the system are described below.

[1304] System Configuration

[1305] This system consists of multiple terminals and a server. The terminals are devices (such as PCs or tablets) that employees use to input data, and the server is the main processing device for collecting, preprocessing, and analyzing data, as well as generating and updating evaluation reports.

[1306] Program processing overview

[1307] Data collection

[1308] User (employee): The user inputs the details of his / her daily work, progress, goals achieved, and time used into the terminal using a dedicated interface.

[1309] Server: The server automatically collects task completion and progress data from project management tools (e.g., JIRA, Trello, Redmine), thereby integrating manual and automatically collected data.

[1310] Data Preprocessing

[1311] Server: The server formats and standardizes the collected data, checking for missing information, and in the process removing noise from the data and converting it into a unified format.

[1312] Evaluation by AI model

[1313] Server: The server inputs the preprocessed data into a generative AI model to calculate an evaluation score for each employee. The score is calculated based on multiple categories, including work efficiency, productivity, and work quality.

[1314] Evaluation report generation

[1315] Server: The server generates an evaluation report based on the evaluation scores, which includes the score for each category, the reason for the evaluation, areas for improvement, and a specific action plan.

[1316] Device: Users (employees and managers) can view the generated evaluation report and check the next goal setting and initiatives.

[1317] Feedback Loop

[1318] Users (employees and supervisors): Users (employees and supervisors) conduct feedback interviews based on the evaluation report. The feedback and improvements that emerged from the interviews are entered back into the system and reflected in the next evaluation cycle.

[1319] Server: The server retrains the generative AI model based on the feedback data to improve the accuracy of the evaluation.

[1320] Specific examples

[1321] For example, the evaluation of a project manager involves the following steps:

[1322] 1. User (Project Manager): Enters project progress, completed tasks, and team member contributions into the device.

[1323] 2. Server: The server automatically collects task completion and progress data from project management tools and consolidates all the data.

[1324] 3. Server: The data preprocessing unit formats this data, and the generative AI model calculates an evaluation score based on this.

[1325] 4. Server: Generates an evaluation report for the project manager based on the evaluation scores.

[1326] 5. Users (project managers and superiors): Users conduct feedback interviews based on the evaluation reports and enter improvements into the system as feedback.

[1327] 6. Server: The server takes the feedback data, retrains the AI ​​model, and reflects it in the next evaluation.

[1328] In this way, this system comprehensively manages a series of processes from data collection to evaluation and feedback loop, enabling objective and fair evaluation of employees.

[1329] The processing flow will be explained below.

[1330] Step 1: Data collection

[1331] User (employee): Enters daily work details, progress, achieved goals, usage time, etc. into a dedicated form on the device.

[1332] Server: Automatically collects task completion status, progress data, work logs, etc. from project management tools (e.g., JIRA, Trello, Redmine).

[1333] Step 2: Data Preprocessing

[1334] Server: Formats the collected data, such as normalizing text data, standardizing the format of time series data, and filling in missing values.

[1335] Server: The server removes noise from the collected data and converts it into the format required for evaluation, for example by filtering and standardizing the data.

[1336] Step 3: Evaluation by AI model

[1337] Server: Inputs the preprocessed data into the generative artificial intelligence model.

[1338] Server: The AI ​​model analyzes the data and calculates an evaluation score for each employee based on their work efficiency, contribution, goal achievement, etc.

[1339] Specific operation: Calculate a score based on each employee's work time, number of completed tasks, project progress, etc. Evaluation criteria include project success rate, work accuracy, productivity, etc.

[1340] Step 4: Generate an assessment report

[1341] Server: Generates an evaluation report for each employee based on the evaluation score. The report includes the evaluation score, the reason for the evaluation for each item, areas for improvement, and specific advice.

[1342] Terminal: Users (employees and managers) can view the generated evaluation report, understand their own evaluation, and identify areas for improvement.

[1343] Step 5: Provide feedback

[1344] Users (employees and managers): Conduct feedback interviews based on the evaluation reports. Enter the details of the interviews and points for improvement into the system.

[1345] Specific actions: The supervisor will refer to the evaluation report and provide specific advice to the employee, identifying areas for improvement and setting goals for the next time. The employee will then create a specific action plan based on the feedback.

[1346] Step 6: Retrain the model

[1347] Server: Collects feedback data and adds it to the training dataset of the generative AI model.

[1348] Server: Retrains the AI ​​model using new data and makes adjustments to improve the accuracy of the evaluation.

[1349] Server: Deploys the updated model to the system and makes it available for the next evaluation cycle.

[1350] Through these specific processing steps, fair and objective employee evaluations become possible, improving the efficiency and accuracy of the entire evaluation process.

[1351] Example 1

[1352] 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."

[1353] In today's business environment, it is extremely important to fairly and objectively evaluate employees' work efficiency and contributions. However, the evaluation process is complicated and subjective. Traditional evaluation systems also face issues such as being prone to human bias and lacking transparency and consistency. Furthermore, the lack of specific areas for improvement and action plans based on evaluation results makes it difficult to improve employee performance. There is a need to resolve these issues and build a fair and objective evaluation system.

[1354] 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.

[1355] In this invention, the server includes: means for collecting work data using a data collection device; means for users to input work content, progress, goals, and usage time into a terminal using a dedicated interface; means for the server to collect task completion status and progress data from a project management tool; means for standardizing and formatting the collected data using a data preprocessing device; means for processing missing data and noise data; means for calculating evaluation scores based on data preprocessed by a generative AI model; means for generating evaluation reports based on the evaluation scores; means for making the evaluation reports viewable; and means for recording feedback data and updating the evaluation model. This enables fair and objective evaluation by collecting detailed and consistent employee work data and evaluating them using a generative AI model based on preprocessed data. Furthermore, the evaluation report presents specific areas for improvement and action plans, contributing to improved employee performance.

[1356] A "data collection device" is a device for collecting data entered by a user or information automatically acquired from an external tool.

[1357] A "user" is a person who uses the system to input information such as work content, progress, goals, and usage time.

[1358] "Terminal" refers to a device used by a user to input data or view an evaluation report, including a PC or tablet.

[1359] "Server" is the central processing unit responsible for data collection, automated processing, analysis, and generation of evaluation reports.

[1360] A "project management tool" is software used to manage tasks and track progress, including tools such as JIRA and Trello.

[1361] A "data preprocessing device" is a device that standardizes and formats collected data and processes missing data and noise.

[1362] A "generative artificial intelligence model" is an artificial intelligence algorithm for calculating evaluation scores based on preprocessed data.

[1363] The "evaluation score" is a numerical indicator of a user's work efficiency and productivity calculated by a generative artificial intelligence model.

[1364] An "assessment report" is a document generated based on an assessment score, which includes details of the score, reasons for the assessment, areas for improvement, and a specific action plan.

[1365] "Feedback data" refers to information, including improvements and comments, that users input into the system based on feedback interviews.

[1366] "Retraining" is the process of using collected feedback data to improve the accuracy of a generative artificial intelligence model.

[1367] "Deployment" refers to running a retrained artificial intelligence model in a real system environment.

[1368] The present invention relates to a system for fairly and objectively evaluating the work efficiency and contribution of employees. This system is composed of multiple terminals and a server. Specific embodiments of the system are described below.

[1369] System Configuration

[1370] This system is configured as follows: The terminal is a device for users to input data, and the server is a device that performs the main processing for data collection, pre-processing, analysis, and generation and updating of evaluation reports.

[1371] Hardware and Software

[1372] Device: An input device such as a computer or tablet.

[1373] Server: A high-performance computer for data processing.

[1374] Project management tools: e.g., JIRA, Trello, Redmine, etc.

[1375] Generative artificial intelligence models: Use machine learning frameworks such as TensorFlow and PyTorch.

[1376] Program processing overview

[1377] Data collection

[1378] User (employee): The user inputs the details of daily work, progress, goals, and usage time into the terminal using a dedicated interface.

[1379] Server: The server automatically collects task completion and progress data from your project management tools, and consolidates all the data in one place using API requests.

[1380] Data Preprocessing

[1381] Server: The server formats and standardizes the collected data, and processes missing and noisy data. This process involves data cleansing using Python scripts.

[1382] Evaluation by AI model

[1383] Server: The preprocessed data is input into the generative AI model, and an evaluation score for each user is calculated using TensorFlow's Predict method.

[1384] Server: Generates an evaluation report based on the calculated evaluation score. The evaluation report includes details of the score, reasons for the evaluation, areas for improvement, and a specific action plan.

[1385] Viewing evaluation reports and providing feedback

[1386] Terminal: Users (employees and managers) view the evaluation report and check its contents.

[1387] Users (employees and supervisors): Users conduct feedback interviews based on the evaluation reports and enter the results of the interviews and areas for improvement into the system.

[1388] Feedback Loop

[1389] Server: Retrains the generative AI model based on the feedback data to improve the accuracy of the evaluation.

[1390] Server: Deploys the retrained model to the system and maintains consistent evaluation metrics.

[1391] Specific examples

[1392] For example, the project manager evaluation process involves the following steps:

[1393] 1. User (Project Manager): Enters project progress, completed tasks, and team member contributions into the device.

[1394] 2. Server: Automatically collects task completion and progress data from project management tools (e.g., JIRA or Trello) and consolidates all data.

[1395] 3. Server: The data preprocessing unit formats this data, and the generative AI model calculates an evaluation score based on it.

[1396] 4. Server: Generates an evaluation report for the project manager based on the evaluation scores.

[1397] 5. Users (project managers and superiors): Users conduct feedback interviews based on the evaluation reports and enter improvements into the system.

[1398] 6. Server: Ingests the feedback data, retrains the AI ​​model, and reflects it in the next evaluation.

[1399] Prompt Sentence Examples

[1400] "Please describe your contributions this week. Detail the specific tasks, results, and goals you achieved."

[1401] This system enables objective and fair evaluation of employees by managing a series of processes from data collection to evaluation and feedback loop in an integrated manner.

[1402] The flow of the identification process in the first embodiment will be described with reference to FIG.

[1403] Step 1:

[1404] Data collection

[1405] User (employee): The user uses a dedicated interface to input work content, progress, goals, and usage time into the terminal.

[1406] Input: Work, progress, goals, and time spent.

[1407] Output: The input working data.

[1408] Specific operation: The user uses a computer or tablet to enter data into a form on a web browser and presses the "Submit" button.

[1409] Server: The server issues API requests from project management tools (e.g., JIRA or Trello) to collect task completion and progress data.

[1410] Input: The API endpoint of your project management tool.

[1411] Output: Project progress data.

[1412] Specific operation: The server periodically runs an automatic script to retrieve the latest data from the project management tool and store it in the database.

[1413] Step 2:

[1414] Data Preprocessing

[1415] Server: Formats and standardizes collected data, ensures data consistency, and handles missing and noisy data.

[1416] Inputs: Task data from users and progress data collected from project management tools.

[1417] Output: Preprocessed data.

[1418] What it does: It uses a Python script to standardize date formats, fill in missing data with reasonable guesses, and filter out noisy data.

[1419] Step 3:

[1420] Evaluation by AI model

[1421] Server: The preprocessed data is input into a generative artificial intelligence model, and an evaluation score for each user is calculated.

[1422] Input: Preprocessed data.

[1423] Output: Evaluation score.

[1424] Specific operation: The server uses TensorFlow's Predict method to input preprocessed data into the AI ​​model and perform evaluation. The resulting evaluation scores are stored in the database.

[1425] Step 4:

[1426] Evaluation report generation

[1427] Server: Generates an evaluation report based on the evaluation score, which includes details of the score, reasons for the evaluation, areas for improvement, and a specific action plan.

[1428] Input: Rating score.

[1429] Output: Evaluation report.

[1430] Specific operation: Based on the evaluation score, an evaluation report is automatically generated using a template engine and saved in PDF format.

[1431] Step 5:

[1432] View the assessment report

[1433] Terminal: Users (employees and supervisors) use terminals to view the evaluation reports.

[1434] Input: Assessment report.

[1435] Output: Assessment report displayed on screen.

[1436] Specific operation: The user opens a web browser and checks the assessment report on the dashboard.

[1437] Step 6:

[1438] Gathering feedback

[1439] Users (employees and supervisors): Conduct feedback interviews based on the evaluation reports and enter the results into the system.

[1440] Input: Interview results and areas for improvement.

[1441] Output: Feedback data.

[1442] Specific actions: Enter the interview results in the feedback form and press the send button to the system.

[1443] Step 7:

[1444] Retraining generative AI models

[1445] Server: Retrains the generative AI model based on the feedback data.

[1446] Input: Feedback data.

[1447] Output: A retrained artificial intelligence model.

[1448] Specific actions: Retrain the AI ​​model with new feedback data and update the evaluation algorithm.

[1449] Step 8:

[1450] Deploying a retrained model

[1451] Server: Deploys the retrained model to the system.

[1452] Input: The retrained artificial intelligence model.

[1453] Output: Updated rating system.

[1454] Specific operation: Deploy a new AI model to the server to improve the evaluation accuracy of the entire system.

[1455] (Application example 1)

[1456] 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."

[1457] Modern factories are required to fairly and objectively evaluate the work efficiency and quality of robots and implement improvement measures in real time. However, conventional evaluation systems require a large amount of labor for data collection and preprocessing, making it difficult to ensure fair evaluations and rapid improvement. In addition, there is a lack of a mechanism for effectively reflecting feedback after evaluations in the next evaluation, making it difficult to achieve accurate evaluations and effective improvements.

[1458] 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.

[1459] In this invention, the server includes means for collecting task data using a data collection device, means for preprocessing the collected data using a data preprocessing device, means for calculating an evaluation score based on the data preprocessed by the generative artificial intelligence model, means for generating an evaluation report based on the evaluation score, means for making the evaluation report available for viewing, means for recording feedback data and updating the evaluation model, means for standardizing the collected data, and means for creating a specific action plan based on the evaluation results. This makes it possible to fairly and objectively evaluate the work efficiency and quality of a robot in real time and quickly reflect improvement measures.

[1460] A "data collection device" is a piece of equipment or software system that automatically collects work data.

[1461] A "data preprocessing device" is a device or software system that formats and standardizes collected data, removes noise, and converts it into an analyzable format.

[1462] A "generative artificial intelligence model" is an artificial intelligence algorithm or framework for calculating evaluation scores based on preprocessed data.

[1463] The "evaluation score" is an index that quantifies work efficiency and quality based on work data.

[1464] The "evaluation report generation means" is a device or software system that records the performance of each robot in detail based on the evaluation score and creates a report that presents areas for improvement and action plans.

[1465] "Feedback data" refers to data that records improvements and initiatives identified based on the evaluation results.

[1466] "Means for standardizing collected data" refers to equipment and software systems that convert collected data into a consistent format so that it can be analyzed and evaluated.

[1467] "Action plan creation means" refers to equipment or software systems used to plan and draft specific next improvement measures and initiatives based on the evaluation results.

[1468] The present invention is embodied as an evaluation system for fairly and objectively evaluating the work efficiency and quality of robots in a factory and for quickly incorporating improvement measures. Specific embodiments of the system are described below.

[1469] This system consists of a server equipped with a data collection device, a data preprocessing device, a generative AI model, an evaluation report generation means, and a feedback function, and a terminal for viewing the evaluation report.

[1470] Data collection

[1471] The server and data collection device automatically collects operational data from factory robots from automation tools such as SCADA systems, including robot operating hours, number of completed tasks, and task quality.

[1472] Data Preprocessing

[1473] The data preprocessing unit standardizes the collected data and removes noise. Specifically, it uses the Python programming language and data processing libraries such as Pandas and Scikit-learn to shape and standardize the data.

[1474] Evaluation and Analysis

[1475] The server inputs the preprocessed data into a generative artificial intelligence model to evaluate the robot's work efficiency and quality. The evaluation uses a clustering method (e.g., KMeans) to compare and analyze the performance of each robot, which then calculates an evaluation score for each robot.

[1476] Generate an assessment report

[1477] An evaluation report is generated based on the evaluation scores. The report includes the score for each robot, the reason for the evaluation, areas for improvement, and a specific action plan. The evaluation report is made available to users via their devices.

[1478] Feedback Loop

[1479] The user and their supervisor then hold a feedback interview based on the evaluation report. The feedback and areas for improvement from the interview are then re-entered into the system and reflected in the next evaluation cycle. The server uses this feedback data to retrain the generative AI model and improve the accuracy of the evaluation.

[1480] Hardware and software used

[1481] Hardware: Factory robots, SCADA systems, collection devices (sensors, etc.)

[1482] Software: Python, Pandas, Scikit-learn, server for data storage and processing

[1483] Specific examples

[1484] For example, the evaluation of a robot in a factory involves the following steps:

[1485] 1. Data collection: Collect robot operation data in CSV format through the SCADA system.

[1486] 2. Data preprocessing: Use StandardScaler to standardize the data and convert it into an analyzable format.

[1487] 3. Evaluation and Analysis: The KMeans clustering method is used to group the robots' performance and calculate the silhouette score.

[1488] 4. Evaluation report generation: An evaluation report will be created for each cluster summarizing areas for improvement and action plans.

[1489] 5. Feedback loop: Based on the evaluation results, the robot's settings and programs are fine-tuned and reflected in the next evaluation cycle.

[1490] Prompt Sentence Examples

[1491] You have collected operational data for robots in your factory. Please rate a robot with the following characteristics and provide an action plan to improve efficiency and quality:

[1492] Uptime

[1493] Number of completed tasks

[1494] Task Quality

[1495] In this way, the present invention comprehensively manages a series of processes from data collection to evaluation and feedback loops, thereby realizing efficient work management and quality improvement for factory robots.

[1496] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[1497] Step 1:

[1498] The server collects operational data from robots in the factory. Specifically, it obtains the robot's operational data through automation tools such as a SCADA system and saves it as a CSV file. Input includes data items such as the robot's operating time, number of completed tasks, and task quality. The output is a CSV file of the collected raw data.

[1499] Step 2:

[1500] The server preprocesses the collected data. Specifically, it reads the data using Python's Pandas library and standardizes the data using StandardScaler, which aligns the scale of each data item. The input includes the CSV file of raw data collected in step 1. The output is a standardized data frame.

[1501] Step 3:

[1502] The server inputs the preprocessed data into a generative artificial intelligence model and calculates an evaluation score. Specifically, it applies the KMeans clustering method using the Scikit-learn library to classify the data into clusters and calculate a silhouette score. The input includes the data frame preprocessed in step 2. The output generates a cluster number and evaluation score for each robot.

[1503] Step 4:

[1504] The server generates an evaluation report based on the evaluation scores, detailing the robot's performance and areas for improvement for each cluster. The input includes the cluster number and evaluation score generated in step 3. The output is a text file or PDF of the evaluation report.

[1505] Step 5:

[1506] The terminal provides the generated evaluation report for the user to view. Specifically, it displays the evaluation report through a web interface or a dedicated application, allowing the user to check the evaluation results. The input includes the evaluation report generated in step 4. The output includes a screen displaying the report and a printed report.

[1507] Step 6:

[1508] The user conducts a feedback interview based on the evaluation report and inputs the results into the system. Specifically, the user records the areas for improvement and the details of the efforts in an input form and reflects them in the next evaluation cycle. The input includes the user's feedback information. The output is recorded in the system.

[1509] Step 7:

[1510] The server uses the feedback data to retrain the generative AI model. Specifically, it uses the feedback data to update the model's parameters and apply them to the next evaluation. The input includes the feedback data collected in step 6. The output is a retrained AI model.

[1511] Step 8:

[1512] The server deploys the retrained model to the system and uses it for the next evaluation. Specifically, the latest model is incorporated into the system and applied to the next cycle of data collection to evaluation. The input includes the retrained model generated in step 7. The output includes the latest evaluation model installed in the system.

[1513] 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.

[1514] This invention combines a system for fairly and objectively evaluating employees' work efficiency and contribution with an emotion engine that recognizes the user's emotions. This system is composed of multiple terminals and a server, and provides more accurate evaluations and feedback.

[1515] System Configuration

[1516] The system includes a terminal, a server, a data collection device, a data preprocessing device, a generative AI model, an evaluation report generation device, a feedback data recording device, and an emotion engine. The terminal is used to input employee data and view evaluation reports, while the server is responsible for data collection, preprocessing, evaluation, report generation, feedback processing, and emotion recognition.

[1517] Program processing overview

[1518] Data collection

[1519] User (employee): The user enters daily work details, progress, achieved goals, usage time, etc. into a dedicated form on the terminal.

[1520] Server: Automatically collects task completion status and progress data from project management tools (e.g., JIRA, Trello, Redmine), and the emotion engine recognizes and records emotions in real time from user input data and interaction logs.

[1521] Data Preprocessing

[1522] Server: Formats and standardizes the collected data. For example, normalizes text data, standardizes the format of time series data, and completes missing values.

[1523] Server: Removes noise from all data, including emotion data, and converts it into the format required for evaluation.

[1524] Evaluation by AI model

[1525] Server: The preprocessed data is input into a generative artificial intelligence model to calculate evaluation scores for each employee based on efficiency, contribution, and goal achievement.

[1526] How it works: The AI ​​model calculates an evaluation score based on work time, number of completed tasks, project progress, and user emotional data, etc. Emotional data is taken into account as a correction factor for the evaluation.

[1527] Evaluation report generation

[1528] Server: Generates a rating report based on the rating scores and emotion data. The report includes the score for each category, the reason for the rating, areas for improvement, specific advice, and the user's emotional state.

[1529] Terminal: Users (employees and supervisors) view the generated evaluation report and check the evaluation results and feedback.

[1530] Providing Feedback

[1531] Users (employees and managers): Conduct feedback interviews based on the evaluation reports. Enter the details of the interviews and areas for improvement into the system, and also record emotional data.

[1532] Example: For example, when a project manager gives a progress report, the emotion engine uses facial recognition and voice analysis to assess their stress level and satisfaction in real time.

[1533] Retraining the model

[1534] Server: Collects feedback data and emotion data and adds it to the training dataset of the generative AI model.

[1535] Server: Retrains the AI ​​model with new data, makes adjustments to improve evaluation accuracy, and deploys the updated model to the system for the next evaluation cycle.

[1536] Specific examples

[1537] For example, the evaluation of a team leader involves the following steps:

[1538] 1. User (Team Leader): Enters the project progress, completed tasks, and team member contributions into the terminal. At the same time, the emotion engine records the leader's emotions when entering information.

[1539] 2. Server: Automatically collects relevant data from project management tools and consolidates all data.

[1540] 3. Server: The data preprocessor formats the data, and the generative AI model calculates an evaluation score. Emotion data from the emotion engine is also incorporated into the evaluation.

[1541] 4. Server: Generates an evaluation report for the team leader based on the evaluation scores and emotion data.

[1542] 5. Users (team leaders and superiors): Conduct feedback interviews based on the evaluation report and discuss specific improvement measures, taking into account the user's emotional state.

[1543] 6. Server: Collects feedback and sentiment data and retrains the model.

[1544] As can be seen, combining an emotion engine makes the employee evaluation process more accurate and comprehensive, providing specific and actionable feedback.

[1545] The processing flow will be explained below.

[1546] Step 1: Data collection

[1547] User (employee): Enters daily work details, progress, achieved goals, and usage time into a dedicated form on the device.

[1548] Server: Automatically collects task completion status, progress data, work logs, etc. from project management tools (e.g., JIRA, Trello, Redmine).

[1549] Server: The emotion engine recognizes and records emotions in real time from user input data and interaction logs. For example, emotion data is collected using a facial recognition camera or voice analysis software.

[1550] Step 2: Data Preprocessing

[1551] Server: Formats and standardizes the collected data. Specifically, it normalizes text data (for example, standardizing uppercase and lowercase letters), standardizes the format of time series data (for example, standardizing timestamps), and completes missing values ​​(for example, completing estimated values ​​based on previous and subsequent data).

[1552] Server: Removes noise from all data, including emotion data, and converts it into the format required for evaluation. For example, it deletes incorrect emotion recognition results and leaves only data with high recognition accuracy.

[1553] Step 3: Evaluation by AI model

[1554] Server: Inputs the preprocessed data into the generative artificial intelligence model.

[1555] Server: The AI ​​model analyzes the data and calculates an evaluation score for each employee, including their efficiency, contribution, and goal achievement. Specifically, the evaluation score is calculated based on factors such as work time, number of completed tasks, project progress, and user emotional data (e.g., stress level, satisfaction).

[1556] Server: Adjusts the evaluation score by taking into account emotional data. For example, if a person achieves high results even under high stress, the score is adjusted to be more highly rated.

[1557] Step 4: Generate an assessment report

[1558] Server: Generates an evaluation report for each employee based on the evaluation score and emotional data. The report contents include the score for each category, the reason for the evaluation, areas for improvement, specific advice, and an analysis of the employee's emotional state.

[1559] Terminal: Users (employees and supervisors) can view the generated evaluation report and compare it with their own evaluation to understand what improvements are needed.

[1560] Step 5: Provide feedback

[1561] Users (employees and managers): Conduct feedback interviews based on the evaluation reports. Re-enter the details of the interviews and areas for improvement into the system. At this time, the employee's emotional state during the interviews is also recorded to improve the quality of the feedback.

[1562] Example: For example, when a project manager gives a progress report, the emotion engine uses facial recognition and voice analysis to assess the manager's stress level and satisfaction in real time, providing feedback to improve the quality of the interview.

[1563] Step 6: Retrain the model

[1564] Server: Updates the learning dataset for the generative AI model based on feedback data and emotion data.

[1565] Server: Retrains the AI ​​model with new data and makes adjustments to improve the accuracy of the evaluation.

[1566] Server: Deploys the updated model to the system and makes it available for the next evaluation cycle.

[1567] This specific processing step enables fair and comprehensive employee evaluation, and by combining it with an emotion engine, it can provide even more accurate and actionable feedback.

[1568] Example 2

[1569] 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."

[1570] Traditional employee evaluation systems make it difficult to fairly and objectively evaluate employees' work efficiency and contributions, and often contain ambiguous standards and biases. Furthermore, because they do not take into account employees' emotions or psychological state, evaluations are one-sided and do not accurately reflect actual performance. Furthermore, because feedback and improvement measures are not specific, there are issues with them not contributing to employee growth or motivation.

[1571] 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.

[1572] In this invention, the server includes means for collecting work data using a data input device, means for collecting emotion data using an emotion recognition device, means for preprocessing the collected data using a data preprocessing device, means for calculating an evaluation score based on the data preprocessed by the generative artificial intelligence model, means for generating an evaluation report based on the evaluation score, means for making the evaluation report available for viewing, and means for recording feedback data and emotion data and updating the evaluation model. This allows for a fairer and more objective evaluation of employee work efficiency and contribution, and by incorporating emotion data, a more accurate and comprehensive evaluation is possible. It also allows for the provision of specific and practical feedback, contributing to employee growth and increased motivation.

[1573] A "data input device" is a device that allows a user to input work data such as the details of daily work, progress, goals achieved, and working hours.

[1574] An "emotion recognition device" is a device that recognizes a user's emotions in real time and collects them as emotion data.

[1575] A "data preprocessing device" is a device that formats and standardizes collected data, and performs tasks such as normalizing text data, removing noise, and filling in missing values.

[1576] A "generative artificial intelligence model" is an artificial intelligence that calculates evaluation scores for employee efficiency, contribution, and goal achievement based on preprocessed data.

[1577] An "evaluation report" is a report generated based on the evaluation scores and emotional data, and includes the scores for each category, the reasons for the evaluation, areas for improvement, specific advice, and the user's emotional state.

[1578] "Feedback data" refers to data that records what was discussed in the feedback interview and areas for improvement based on the evaluation report.

[1579] An "evaluation model" refers to the entire evaluation system, including the generative artificial intelligence model, and is used to calculate the evaluation score.

[1580] "Updating" refers to the process of adding new feedback and sentiment data to the evaluation model and retraining the model.

[1581] This invention combines an emotion recognition device with a system for fairly and objectively evaluating employees' work efficiency and contribution. The system consists of multiple terminals and a server, and provides more accurate evaluations and feedback.

[1582] System Configuration

[1583] The system includes a terminal, a server, a data input device, an emotion recognition device, a data preprocessing device, a generative AI model, an evaluation report generation device, and a feedback data recording device. The terminal is used to input employee data and view evaluation reports, while the server collects data, preprocesses it, evaluates it, generates reports, processes feedback, and recognizes emotions.

[1584] Server Configuration

[1585] The server implements the following measures:

[1586] 1. Work data collection means using a data input device: This is a device that allows users to input their daily work content, progress, goals achieved, usage time, etc. Specifically, users input this data into a dedicated form from a terminal.

[1587] 2. Emotion data collection using emotion recognition devices: Recognizing users' emotions in real time and collecting emotion data using facial recognition and voice analysis. For example, facial recognition software (e.g., Microsoft Azure Face API) and voice analysis tools (e.g., Google Cloud Speech-to-Text) are used.

[1588] 3. Data preprocessing device: A device that formats and standardizes collected data. For example, it normalizes text data, removes noise, and fills in missing values.

[1589] 4. Evaluation score calculation method using a generative artificial intelligence model: This is an artificial intelligence model that calculates evaluation scores for employee efficiency, contribution, and goal achievement based on preprocessed data.

[1590] 5. Evaluation report generator: A device that generates an evaluation report based on the evaluation score and emotion data.

[1591] 6. Evaluation report viewing means: This is a means for enabling users to view the evaluation report. Users can check the report via a web browser or dedicated application on their device.

[1592] 7. A means of recording feedback and sentiment data and updating the evaluation model: This is a means of recording what was discussed in the feedback interview and areas for improvement, and using that data to retrain the generative AI model.

[1593] Specific examples

[1594] For example, a team leader evaluation involves the following steps:

[1595] 1. User (Team Leader): Enters the project progress, completed tasks, and team member contributions into the terminal. At the same time, the emotion recognition device records the leader's emotions when entering information.

[1596] 2. Server: Automatically collects relevant data from project management software and consolidates all data.

[1597] 3. Server: The data preprocessor formats the data, and the generative AI model calculates an evaluation score. Emotion data from the emotion recognition device is also incorporated into the evaluation.

[1598] 4. Server: Generates an evaluation report for the team leader based on the evaluation scores and emotion data.

[1599] 5. Users (team leaders and superiors): Conduct feedback interviews based on the evaluation report and discuss specific improvement measures, taking into account the user's emotional state.

[1600] 6. Server: Collects feedback and emotion data and retrains the generative AI model.

[1601] Prompt Sentence Examples

[1602] "Calculate a rating score based on the task completion data and sentiment data entered by the user."

[1603] "Combine progress data with emotion logs to generate an evaluation report."

[1604] As described above, by combining emotion recognition devices, employee evaluations can be made more accurate and comprehensive, and specific, actionable feedback can be provided.

[1605] The flow of the identification process in the second embodiment will be described with reference to FIG.

[1606] Step 1:

[1607] Users enter work data such as daily work content, progress, achieved goals, and usage time into a dedicated form from their terminal.

[1608] Input: Work content, progress, goals, time used

[1609] Output: Record of input data

[1610] Specific operation: After the user completes the task "Document Creation" for Project X, they enter the task name, required time, degree of completion, etc. into a dedicated form on their terminal.

[1611] Step 2:

[1612] The server automatically collects task completion status and progress data from project management software (e.g., JIRA, Trello, Redmine).

[1613] Input: Task completion status data, progress data from project management software

[1614] Output: Record of collected data

[1615] Specific operation: Project and task data is periodically collected from each management software via API and stored in a database.

[1616] Step 3:

[1617] The server uses an emotion recognition device to recognize the user's emotions in real time from the user's input data and interaction logs, and records the emotion data.

[1618] Input: User input data, interaction logs

[1619] Output: Emotion data recording

[1620] What it does: Uses facial recognition software (e.g., Microsoft Azure Face API) and voice analysis tools (e.g., Google Cloud Speech-to-Text) to record the user's emotional state (stress level, satisfaction, etc.).

[1621] Step 4:

[1622] The server formats and standardizes the collected data, including emotion data, for example by normalizing text data, removing noise, and imputing missing values.

[1623] Input: Raw data collected

[1624] Output: Preprocessed data

[1625] Specific operations: Normalizing text data involves converting alphanumeric characters between half-width and full-width and removing unnecessary symbols. Eliminating noise involves correcting outliers and filling in missing data.

[1626] Step 5:

[1627] The server inputs the preprocessed data into a generative artificial intelligence model to calculate evaluation scores for each employee's efficiency, contribution, and goal achievement.

[1628] Input: Preprocessed data (work time, number of completed tasks, project progress, sentiment data, etc.)

[1629] Output: Evaluation score

[1630] How it works: Based on the input data, the AI ​​model calculates evaluation scores for efficiency, contribution, and goal achievement.

[1631] Step 6:

[1632] The server generates an evaluation report based on the evaluation score and the emotion data.

[1633] Input: Evaluation scores, emotion data

[1634] Output: Evaluation report

[1635] Specific Actions: Generate an evaluation report that includes the score for each category, the reason for the evaluation, areas for improvement, specific advice, and the user's emotional state.

[1636] Step 7:

[1637] The terminal allows users (employees and supervisors) to view the generated evaluation report.

[1638] Input: Generated assessment report

[1639] Output: User views the evaluation report

[1640] Specific operation: The user checks the evaluation report through a web browser or a dedicated app.

[1641] Step 8:

[1642] Users (employees and their superiors) conduct feedback interviews based on the evaluation reports. The system inputs the details of the discussions and areas for improvement, and also records emotional data.

[1643] Input: Evaluation report, interview details

[1644] Output: Feedback data, additional emotion data

[1645] Specific actions: Enter the specific improvement measures discussed in the feedback interview (e.g., participating in a stress management workshop) into the system, and also add your emotional state.

[1646] Step 9:

[1647] The server collects feedback data and emotion data and adds it to the training dataset of the generative artificial intelligence model.

[1648] Input: Feedback data, emotion data

[1649] Output: Updated training dataset

[1650] Specific operation: Add the feedback content and new emotion data entered into the system to the training dataset.

[1651] Step 10:

[1652] The server retrains the generative AI model with new data, makes adjustments to improve the accuracy of the evaluation, and deploys the updated model to the system.

[1653] Input: Updated training dataset

[1654] Output: Retrained AI model

[1655] Specific operation: The retrained AI model is deployed on the server and used for the next evaluation.

[1656] Through the above steps, a system is realized that can provide accurate and comprehensive evaluation and feedback that takes into account emotional data.

[1657] (Application example 2)

[1658] 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."

[1659] Conventional staff evaluation systems have problems with subjective evaluations, lacking fairness and accuracy. Furthermore, evaluations are one-sided and do not take into account the emotional state of staff, resulting in ineffective improvement measures. The present invention aims to provide a system that combines emotional data to more fairly and objectively evaluate staff work efficiency and contributions, and provide specific and practical feedback.

[1660] The specification processing by the specification processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means. In this invention, the server includes means for collecting task data by a data collection device, means for preprocessing the collected data by a data preprocessing device, means for calculating an evaluation score based on the data preprocessed by a generative artificial intelligence model, means for generating an evaluation report based on the evaluation score, means for making the evaluation report available for viewing, means for recording feedback data and updating the evaluation model, means for collecting user emotion data by an emotion engine, and means for correcting the evaluation based on the emotion data. This enables fair and objective evaluation and specific feedback that take emotion data into consideration.

[1661] The "data collection device" is a device for collecting task data, progress data, and even emotion data input by the user.

[1662] A "data preprocessing device" is a device that formats, standardizes, removes noise from, and converts collected data into a format required for evaluation.

[1663] A "generative artificial intelligence model" is an artificial intelligence technology that calculates a score to evaluate a user's efficiency, contribution, and goal achievement based on preprocessed data.

[1664] An "evaluation report" is a report that includes evaluation results, areas for improvement, and advice based on evaluation scores calculated by a generative artificial intelligence model.

[1665] An "emotion engine" is a technology that collects emotional data from users through facial recognition and voice analysis, and reflects that information in evaluations.

[1666] "Feedback data" refers to data that records the content discussed and areas for improvement in feedback interviews based on the evaluation report.

[1667] An "evaluation model" is an artificial intelligence algorithm that calculates efficiency and contribution based on a user's performance and emotional data.

[1668] "Task completion status" refers to data on the work and progress status that a user has completed using the management tool.

[1669] "Emotion data" is data that indicates the user's emotional state and is obtained through facial recognition and voice analysis.

[1670] "Preprocessed data" refers to raw data obtained from a data collection device after it has been shaped, standardized, and denoised.

[1671] This invention combines an emotion recognition engine with a system for fairly and objectively evaluating the work efficiency and contribution of staff in a brick-and-mortar store. This system is composed of a data collection device, a data preprocessing device, a generative AI model, an evaluation report generation device, a feedback data recording device, an emotion engine, and a server.

[1672] System Configuration

[1673] Data acquisition equipment:

[1674] Users enter data such as daily work details, task progress, achieved goals, and working hours into a dedicated form using a tablet or smartphone. Sales data and customer service data are also automatically collected from the POS system.

[1675] Data Preprocessor:

[1676] Format and standardize the collected data, including normalizing text data, standardizing the format of time series data, filling in missing values, and removing noise.

[1677] Generative AI models:

[1678] Based on the pre-processed data, an evaluation score is calculated for each staff member's efficiency, contribution, and goal achievement. The evaluation reflects work time, number of completed tasks, sales data, customer service data, etc. Emotion data collected by the emotion engine is used as a correction factor for the evaluation.

[1679] Evaluation report generator:

[1680] Based on the evaluation scores and emotional data, an evaluation report is automatically generated, including the score for each category, the reason for the evaluation, areas for improvement, specific advice, and the emotional state.

[1681] Feedback data recording device:

[1682] Staff members, store managers, and supervisors conduct feedback interviews based on the evaluation reports, and the results and areas for improvement are entered into the system, while emotional data is also recorded.

[1683] Emotion Engine:

[1684] Collect emotional data through facial recognition and voice analysis of staff members. Analyze and collect staff members' emotional states (e.g., stress levels, satisfaction) in real time.

[1685] server:

[1686] Oversees all data processing, including data collection, pre-processing, evaluation, report generation, feedback recording, and sentiment analysis. Generative AI models are periodically retrained based on feedback data.

[1687] Specific examples

[1688] For example, when a staff member enters the details of their work and sales data for the day on a tablet at the end of their workday, the emotion engine analyzes the staff member's stress level and satisfaction level from their facial expressions and voice. All of this data is sent to a server, where it is formatted and standardized by a pre-processing device. A generative AI model then analyzes the data and calculates an evaluation score. Finally, an evaluation report generator generates a report based on the evaluation score and emotion data, which the staff member and store manager use in feedback interviews.

[1689] Prompt Sentence Examples

[1690] Project details: Today's work and sales, task completion status, emotional data

[1691] Emotional data: stress level (high, medium, low), satisfaction (satisfied, dissatisfied, neutral)

[1692] Evaluation items: efficiency score, contribution score, goal achievement score

[1693] Feedback includes: areas for improvement, specific advice, and considerations for emotional state

[1694]

[1695] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[1696] Step 1:

[1697] Users enter data such as daily work details, task progress, achieved goals, and working hours into a dedicated form using a tablet or smartphone. The entered data is collected by a data collection device. Sales data and customer interaction data are also automatically collected from the POS system. This allows the system to obtain both input data and automatically collected data.

[1698] Step 2:

[1699] The emotion engine collects emotion data from the user's device through facial recognition and voice analysis. For example, it analyzes the user's facial expressions and voice when entering data, and converts emotions such as stress level and satisfaction into data in real time. This emotion data is also sent to the data collection device.

[1700] Step 3:

[1701] The server preprocesses the collected data using a data preprocessing device. Specifically, it normalizes text data, standardizes the format of time-series data, fills in missing values, removes noise, etc. This results in a standardized dataset.

[1702] Step 4:

[1703] The server inputs the preprocessed data into a generative AI model to calculate an evaluation score. The generative AI model calculates an evaluation score based on work time, number of completed tasks, sales data, customer service data, and emotional data. This results in an evaluation score that reflects the staff member's efficiency, contribution, and goal achievement.

[1704] Step 5:

[1705] The server generates an evaluation report based on the evaluation score and emotional data. The evaluation report generator creates a report that includes the score for each category, the reason for the evaluation, areas for improvement, specific advice, and the emotional state. This report is made available for viewing by the user, store manager, and supervisor.

[1706] Step 6:

[1707] The user and the store manager / supervisor then hold a feedback interview based on the evaluation report. The content of the discussion and areas for improvement during the interview are entered into the system, and new emotional data is also recorded. This allows feedback data to be obtained.

[1708] Step 7:

[1709] The server collects feedback data and sentiment data and adds it to the training dataset of the generative AI model. The server retrains the generative AI model with this new data to improve the accuracy of the evaluation. The updated model is deployed to the system and used in the next evaluation cycle.

[1710] 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.

[1711] 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.

[1712] 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.

[1713] 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.

[1714] 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.

[1715] 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.

[1716] 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).

[1717] 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.

[1718] 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."

[1719] The emotion identification model 59 inputs user input into a pre-trained neural network, obtains emotion values ​​indicating each emotion shown in the emotion map 400, and determines the user's emotion. This neural network is pre-trained based on multiple pieces of training data that are combinations of user input and emotion values ​​indicating each emotion shown in the emotion map 400. Furthermore, this neural network is trained so that emotions that are located close to each other have similar values, as in the emotion map 900 shown in FIG. 10. FIG. 10 shows an example in which multiple emotions, "relieved," "calm," and "reassuring," have similar emotion values.

[1720] The system according to the present disclosure has been described above mainly with respect to the functions of the data processing device 12, but the system according to the present disclosure is not necessarily implemented on a server. The system according to the present disclosure may be implemented as a general information processing system. The present disclosure may be implemented, for example, as a software program running on a personal computer or an application running on a smartphone, etc. The method according to the present disclosure may be provided to users in the form of SaaS (Software as a Service).

[1721] In the above embodiment, an example was given in which the specific processing is performed by one computer 22, but the technology of the present disclosure is not limited to this, and the specific processing may be distributed and performed by a plurality of computers including the computer 22. For example, the data generation model 58 may be provided in an external device of the data processing device 12, and data may be generated in the external device in accordance with input data.

[1722] In the above embodiment, an example in which the specific processing program 56 is stored in the storage 32 has been described, but the technology of the present disclosure is not limited to this. For example, the specific processing program 56 may be stored in a portable, computer-readable, non-transitory storage medium such as a USB (Universal Serial Bus) memory. The specific processing program 56 stored in the non-transitory storage medium is installed in the computer 22 of the data processing device 12. The processor 28 executes the specific processing in accordance with the specific processing program 56.

[1723] Alternatively, the specific processing program 56 may be stored in a storage device such as a server connected to the data processing device 12 via the network 54, and the specific processing program 56 may be downloaded and installed on the computer 22 in response to a request from the data processing device 12.

[1724] It is not necessary to store all of the specific processing program 56 in a storage device such as a server connected to the data processing device 12 via the network 54, or to store all of the specific processing program 56 in the storage 32; only a portion of the specific processing program 56 may be stored.

[1725] The hardware resource for executing a specific process can be any of the following processors: An example of a processor is a CPU, which is a general-purpose processor that functions as a hardware resource for executing a specific process by executing software, i.e., a program. Another example of a processor is a dedicated electrical circuit, such as an FPGA (Field-Programmable Gate Array), a PLD (Programmable Logic Device), or an ASIC (Application Specific Integrated Circuit), which is a processor with a circuit configuration designed specifically for executing a specific process. Each processor has built-in or connected memory, and each processor uses the memory to execute the specific process.

[1726] The hardware resource that executes the specific processing may be configured with one of these various processors, or may be configured with a combination of two or more processors of the same or different types (for example, a combination of multiple FPGAs, or a combination of a CPU and an FPGA). Also, the hardware resource that executes the specific processing may be a single processor.

[1727] As an example of a system configured with a single processor, first, one processor is configured by combining one or more CPUs and software, and this processor functions as a hardware resource that executes a specific process. Second, there is a system that uses a processor that realizes the functions of an entire system including multiple hardware resources that execute a specific process on a single IC chip, as typified by SoC (System-on-a-chip). In this way, a specific process is realized using one or more of the above-mentioned various processors as hardware resources.

[1728] Furthermore, the hardware structure of these various processors can be, more specifically, an electric circuit that combines circuit elements such as semiconductor devices. The specific processing described above is merely an example. Therefore, it goes without saying that unnecessary steps may be deleted, new steps may be added, or the processing order may be rearranged, without departing from the spirit of the invention.

[1729] The above-described description and illustrations are a detailed explanation of the parts related to the technology of the present disclosure and are merely an example of the technology of the present disclosure. For example, the above description of the configuration, functions, actions, and effects is an explanation of an example of the configuration, functions, actions, and effects of the parts related to the technology of the present disclosure. Therefore, it goes without saying that unnecessary parts may be deleted, new elements may be added, or replacements may be made to the above-described description and illustrations within the scope of the gist of the technology of the present disclosure. Furthermore, to avoid confusion and facilitate understanding of the parts related to the technology of the present disclosure, the above-described description and illustrations omit explanations of common technical knowledge that do not require particular explanation to enable the implementation of the technology of the present disclosure.

[1730] All publications, patent applications, and technical standards mentioned in this specification are herein incorporated by reference to the same extent as if each individual publication, patent application, or technical standard was specifically and individually indicated to be incorporated by reference.

[1731] The following is further disclosed regarding the above embodiment.

[1732] (Claim 1)

[1733] means for collecting operation data by a data collection device;

[1734] means for preprocessing the collected data by a data preprocessing device;

[1735] A means for calculating an evaluation score based on data preprocessed by a generative artificial intelligence model;

[1736] means for generating an assessment report based on the assessment scores;

[1737] A means for making the evaluation report available for viewing;

[1738] a means for recording feedback data and updating the evaluation model;

[1739] A system including:

[1740] (Claim 2)

[1741] a means for automatically collecting task completion status and progress data from the management tool by a data collection device;

[1742] 10. The system of claim 1, further comprising:

[1743] (Claim 3)

[1744] a means of collecting feedback data and retraining the artificial intelligence model; and

[1745] A means for deploying the retrained model to the system; and

[1746] 10. The system of claim 1, further comprising:

[1747] "Example 1"

[1748] (Claim 1)

[1749] means for collecting operation data by a data collection device;

[1750] A means for a user to input work content, progress, goals to be achieved, and usage time into the terminal using a dedicated interface;

[1751] means for the server to collect task completion status and progress data from the project management tool;

[1752] means for standardizing and formatting the data collected by the data preprocessing device;

[1753] means for handling missing and noisy data;

[1754] A means for calculating an evaluation score based on data preprocessed by a generative artificial intelligence model;

[1755] means for generating an assessment report based on the assessment scores;

[1756] A means for making the evaluation report available for viewing;

[1757] a means for recording feedback data and updating the evaluation model;

[1758] A system including:

[1759] (Claim 2)

[1760] a means for automatically collecting task completion status and progress data from the management tool by a data collection device;

[1761] a means for users to input feedback data into the system based on the feedback interview;

[1762] a means for implementing the retrained artificial intelligence model into the system; and

[1763] 10. The system of claim 1, further comprising:

[1764] (Claim 3)

[1765] a means for collecting feedback data and retraining the generative artificial intelligence model; and

[1766] A means for deploying the retrained model to the system; and

[1767] 10. The system of claim 1, further comprising:

[1768] "Application Example 1"

[1769] (Claim 1)

[1770] means for collecting operation data by a data collection device;

[1771] means for preprocessing the collected data by a data preprocessing device;

[1772] A means for calculating an evaluation score based on data preprocessed by a generative artificial intelligence model;

[1773] means for generating an assessment report based on the assessment scores;

[1774] A means for making the evaluation report available for viewing;

[1775] a means for recording feedback data and updating the evaluation model;

[1776] a means of standardizing the collected data;

[1777] A means of creating a concrete action plan based on the evaluation results;

[1778] A system including:

[1779] (Claim 2)

[1780] a means for automatically collecting task completion status and progress data from the management tool by a data collection device;

[1781] A means for automatically collecting robot operation data;

[1782] 10. The system of claim 1, further comprising:

[1783] (Claim 3)

[1784] a means of collecting feedback data and retraining the artificial intelligence model; and

[1785] A means for deploying the retrained model to the system; and

[1786] A means to fine-tune the robot's settings based on the evaluation report, and

[1787] 10. The system of claim 1, further comprising:

[1788] "Example 2: Combining Emotion Engines"

[1789] (Claim 1)

[1790] means for collecting operation data by a data input device;

[1791] means for collecting emotion data by an emotion recognition device;

[1792] means for preprocessing the collected data by a data preprocessing device;

[1793] A means for calculating an evaluation score based on data preprocessed by a generative artificial intelligence model;

[1794] means for generating an assessment report based on the assessment scores;

[1795] A means for making the evaluation report available for viewing;

[1796] a means for recording feedback data and sentiment data and updating the evaluation model;

[1797] A system including:

[1798] (Claim 2)

[1799] means for automatically collecting task completion status and progress data from the management software by a data collection device;

[1800] 10. The system of claim 1, further comprising:

[1801] (Claim 3)

[1802] a means of collecting feedback and sentiment data and retraining the artificial intelligence model; and

[1803] A means for deploying the retrained model to the system; and

[1804] 10. The system of claim 1, further comprising:

[1805] "Application example 2 when combining emotion engines"

[1806] (Claim 1)

[1807] means for collecting operation data by a data collection device;

[1808] means for preprocessing the collected data by a data preprocessing device;

[1809] A means for calculating an evaluation score based on data preprocessed by a generative artificial intelligence model;

[1810] means for generating an assessment report based on the assessment scores;

[1811] A means for making the evaluation report available for viewing;

[1812] a means for recording feedback data and updating the evaluation model;

[1813] means for collecting user emotion data by an emotion engine;

[1814] A means for correcting the evaluation based on the emotion data;

[1815] A system including:

[1816] (Claim 2)

[1817] a means for automatically collecting task completion status and progress data from the management tool by a data collection device;

[1818] a means for collecting emotion data based on facial recognition and voice analysis by an emotion engine;

[1819] 10. The system of claim 1, further comprising:

[1820] (Claim 3)

[1821] a means of collecting feedback data and retraining the artificial intelligence model; and

[1822] A means for deploying the retrained model to the system; and

[1823] A means for improving the accuracy of the evaluation model based on feedback data and emotion data; and

[1824] 10. The system of claim 1, further comprising: [Explanation of symbols]

[1825] 10, 210, 310, 410 Data Processing Systems 12 Data Processing Device 14 Smart Devices 214 Smart Glasses 314 Headset-type terminal 414 Robot< / url:> < / url:> < / url:> < / url:>

Claims

1. means for collecting operation data by a data collection device; means for preprocessing the collected data by a data preprocessing device; A means for calculating an evaluation score based on data preprocessed by a generative artificial intelligence model; means for generating an assessment report based on the assessment scores; A means for making the evaluation report available for viewing; a means for recording feedback data and updating the evaluation model; A system including:

2. a means for automatically collecting task completion status and progress data from the management tool by a data collection device; The system of claim 1 further comprising:

3. a means of collecting feedback data and retraining the artificial intelligence model; and A means for deploying the retrained model to the system; and The system of claim 1 further comprising:

Images