system

Abstract

We provide the system. [Solution] Data collection methods for collecting employee work data, A means for setting evaluation criteria, An AI analysis tool that analyzes and scores collected business data based on evaluation criteria, A feedback generation means that generates feedback based on the scoring results, A notification display method that notifies and displays feedback to employees, A system that includes this.

Description

【Technical Field】 【0001】 The technology of the present disclosure relates to a system. 【Background Art】 【0002】 Patent Document 1 discloses a method for controlling a persona chatbot, which is performed by at least one processor, including steps of receiving a user utterance, adding the user utterance to a prompt including an instruction sentence related to an explanation of the chatbot's character, encoding the prompt, and inputting the encoded prompt into a language model to generate a chatbot utterance as a response to the user utterance. 【Prior Art Documents】 【Patent Documents】 【0003】 【Patent Document 1】 Japanese Patent Application Laid-Open No. 2022-180282 【Summary of the Invention】 【Problems to be Solved by the Invention】 【0004】 Conventionally, in the evaluation of employees, subjective and unfair judgments are often made. In particular, employees who have achieved high-quality results efficiently in a short period may not be properly evaluated. As a result, a sense of unfairness arises among employees, leading to problems such as a decrease in motivation and productivity. Also, due to the opacity of evaluation criteria and processes, the reliability of the results may decrease. 【Means for Solving the Problems】 【0005】 This invention provides an evaluation system that enables objective and quantitative evaluation. It includes a data collection means for efficiently collecting employee work data and an evaluation criteria setting means that allows managers to set evaluation criteria based on organizational policies. Furthermore, an AI analysis means analyzes the work data based on the evaluation criteria and performs scoring. This AI analysis means has the function of learning from past evaluation history and improving the accuracy of evaluations. Based on the analysis results, a feedback generation means creates feedback in natural language, and a notification display means provides employees with transparent evaluation results, thereby solving the problem. 【0006】 "Data collection means" refers to a device or program for efficiently acquiring and organizing employees' work data. 【0007】 "Methods for setting evaluation criteria" refer to tools and interfaces for setting the criteria necessary for evaluation, and allow for customization to match the organization's policies. 【0008】 "AI analysis tools" refer to artificial intelligence algorithms or systems that have the function of automatically analyzing collected business data and calculating scores based on evaluation criteria. 【0009】 A "feedback generation method" is a system for creating specific feedback for employees in natural language based on analysis results. 【0010】 A "notification display method" refers to a system or device used to notify employees of evaluation results and feedback and to display them visually. [Brief explanation of the drawing] 【0011】 [Figure 1] This is a conceptual diagram showing an example of the configuration of a data processing system according to the first embodiment. [Figure 2] This is a conceptual diagram showing an example of the essential functions of a data processing device and a smart device according to the first embodiment. [Figure 3]This is a conceptual diagram showing an example of the configuration of a data processing system according to the second embodiment. [Figure 4] This is a conceptual diagram showing an example of the main functions of a data processing device and smart glasses according to the second embodiment. [Figure 5] This is a conceptual diagram showing an example of the configuration of a data processing system according to the third embodiment. [Figure 6] This is a conceptual diagram showing an example of the main functions of a data processing device and a headset-type terminal according to the third embodiment. [Figure 7] This is a conceptual diagram showing an example of the configuration of a data processing system according to the fourth embodiment. [Figure 8] This is a conceptual diagram showing an example of the main functions of a data processing device and a robot according to the fourth embodiment. [Figure 9] This shows an emotion map where multiple emotions are mapped. [Figure 10] This shows an emotion map where multiple emotions are mapped. [Figure 11] This is a sequence diagram showing the processing flow of the data processing system in Example 1. [Figure 12] This is a sequence diagram showing the processing flow of the data processing system in Application Example 1. [Figure 13] This is a sequence diagram showing the processing flow of the data processing system in Example 2, which incorporates an emotion engine. [Figure 14] This is a sequence diagram showing the processing flow of the data processing system in Application Example 2, which combines an emotion engine. [Modes for carrying out the invention] 【0012】 Hereinafter, an example of an embodiment of the system relating to the technology of this disclosure will be described with reference to the attached drawings. 【0013】 First, let's explain the terminology used in the following explanation. 【0014】 In the following embodiments, the numbered processor (hereinafter simply referred to as "processor") may be a single arithmetic unit or a combination of multiple arithmetic units. Also, the processor may be a single type of arithmetic unit or a combination of multiple types of arithmetic units. Examples of arithmetic units include a CPU (Central Processing Unit), a GPU (Graphics Processing Unit), a GPGPU (General-Purpose computing on Graphics Processing Units), an APU (Accelerated Processing Unit), and the like. 【0015】 In the following embodiments, the numbered RAM (Random Access Memory) is a memory in which information is temporarily stored and is used as a work memory by the processor. 【0016】 In the following embodiments, the numbered storage is one or more non-volatile storage devices that store various programs and various parameters, etc. Examples of non-volatile storage devices include flash memory (SSD (Solid State Drive)), magnetic disks (e.g., hard disks), or magnetic tapes, etc. 【0017】 In the following embodiments, the numbered communication I / F (Interface) is an interface including a communication processor and 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), or Bluetooth (registered trademark), etc. 【0018】 In the following embodiments, "A and / or B" is synonymous with "at least one of A and B." That is, "A and / or B" means that it may be A alone, or B alone, or a combination of A and B. Furthermore, in this specification, the same concept as "A and / or B" applies when expressing three or more things linked by "and / or." 【0019】 [First Embodiment] 【0020】 Figure 1 shows an example of the configuration of the data processing system 10 according to the first embodiment. 【0021】 As shown in Figure 1, the 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. 【0022】 The data processing device 12 comprises a computer 22, a database 24, and a communication interface 26. The computer 22 is an example of a "computer" related to the technology of this disclosure. The computer 22 comprises a processor 28, RAM 30, and storage 32. The processor 28, RAM 30, and storage 32 are connected to a bus 34. The database 24 and the communication interface 26 are also connected to the bus 34. The communication interface 26 is connected to a network 54. An example of the network 54 is a WAN (Wide Area Network) and / or a LAN (Local Area Network). 【0023】 The smart device 14 comprises a computer 36, a reception device 38, an output device 40, a camera 42, and a communication interface 44. The computer 36 comprises a processor 46, RAM 48, and storage 50. The processor 46, RAM 48, and storage 50 are connected to a bus 52. The reception device 38, output device 40, and camera 42 are also connected to the bus 52. 【0024】 The reception device 38 is equipped with a touch panel 38A and a microphone 38B, etc., and receives user input. The touch panel 38A receives user input by detecting contact with an object (e.g., a pen or finger). The microphone 38B receives user input by detecting the user's voice. The control unit 46A transmits data indicating the user input received by the touch panel 38A and 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. 【0025】 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 perceptible to the user 20 (e.g., audio and / or text). The display 40A displays visible information such as text and images according to instructions from the processor 46. The speaker 40B outputs audio according to instructions from the processor 46. The camera 42 is a small digital camera equipped with an optical system such as a lens, aperture, and shutter, and an image sensor such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor. 【0026】 Communication interface 44 is connected to network 54. Communication interfaces 44 and 26 are responsible for the exchange of various types of information between processor 46 and processor 28 via network 54. 【0027】 Figure 2 shows an example of the main functions of the data processing device 12 and the smart device 14. 【0028】 As shown in Figure 2, in the data processing device 12, a specific processing 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" related to the technology of this 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 according to the specific processing program 56 executed on the RAM 30. 【0029】 The storage 32 stores the data generation model 58 and the emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290. 【0030】 In the smart device 14, the processor 46 performs the reception output processing. The storage 50 stores the reception output program 60. The reception output program 60 is used in conjunction with a 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 processing is realized by the processor 46 operating as a control unit 46A according to the reception output program 60 executed on the RAM 48. 【0031】 Next, the specific processing performed by the specific processing unit 290 of the data processing device 12 will be described. In the following description, the data processing device 12 will be referred to as the "server" and the smart device 14 as the "terminal". 【0032】 This invention provides an evaluation system for objectively and efficiently evaluating employee performance, thereby realizing a fair and transparent evaluation process. This system automates a series of steps, from collecting employee performance data and setting fair evaluation criteria to analyzing and evaluating the data using artificial intelligence technology, and generating and notifying feedback. 【0033】 First, the server collects data related to employees' work on a regular or real-time basis. Data sources include project management tools and work time tracking systems. APIs are used to retrieve necessary information, which is then organized and stored in a database. This data collection method enables the accurate handling of large amounts of data. 【0034】 Next, the terminal provides an interface for administrators, allowing them to set evaluation criteria. This interface makes it easy to adjust the weighting of each evaluation criterion according to organizational policies, and administrators (users) can set the items they consider important, such as "quality of deliverables," "achievement level," and "contribution to the team." 【0035】 Subsequently, the server uses AI analysis tools to analyze the collected business data based on pre-defined evaluation criteria. The AI ​​model learns each employee's activities from past data and calculates a score according to the individual criteria. This improves the accuracy and reliability of the data, enabling a more objective evaluation. 【0036】 Furthermore, the server automatically generates feedback based on the AI's analysis results. This feedback generation method uses natural language processing technology to describe specific evaluation content for each employee, including both positive aspects and areas for improvement. 【0037】 Finally, the terminal notifies employees of the generated feedback, which is then displayed on their client devices. This evaluation result notification utilizes email notifications or a dashboard display within the system. Employees can review their evaluations and use the feedback to improve their work and prepare for their next evaluation. 【0038】 For example, if employee A completes a high-quality project in a short period of time, the system collects the data. Based on the "efficiency" and "quality" standards set by the manager, the AI ​​calculates a high score. As a result, the feedback specifically evaluates the achievement of results in a short period of time, and additional advice such as "Next time, you should also be mindful of your contribution to the team" is added. 【0039】 Thus, the system of the present invention contributes to improving motivation and trust within the organization by automating the entire process and enabling rapid and fair employee evaluations. 【0040】 The following describes the processing flow. 【0041】 Step 1: 【0042】 The server collects data related to employees' work from various systems. Specifically, it connects to data sources such as project management tools and time management systems via APIs to obtain information such as the number of completed projects, working hours, and the number of errors in deliverables, and stores this information in a database. 【0043】 Step 2: 【0044】 The terminal displays an interface for administrators and provides the functionality to set evaluation criteria. Administrators, as users, use the evaluation criteria interface to set priorities and weights for each evaluation criterion, such as "quality of deliverables," "efficiency," and "team contribution." These settings are sent to the server and used for subsequent evaluations. 【0045】 Step 3: 【0046】 The server operates an AI analysis tool based on the collected business data. The AI ​​model analyzes the data based on pre-set evaluation criteria and scores each employee's activities. This makes it possible to objectively evaluate each employee's performance and contributions. The AI ​​model improves its proficiency by referring to past data, thus increasing the accuracy of the analysis results. 【0047】 Step 4: 【0048】 The server generates feedback based on scoring results from AI analysis. The feedback generation system uses natural language processing to create customized feedback messages for individual employees. This feedback includes positive evaluation points and suggestions for improvement. 【0049】 Step 5: 【0050】 The terminal notifies each employee (user) of the generated feedback and evaluation results. The feedback is displayed via email or an on-screen dashboard. Employees can use this information to review their own work performance and work towards improvement. 【0051】 (Example 1) 【0052】 Next, we will describe Example 1. In the following description, the data processing device 12 will be referred to as the "server," and the smart device 14 will be referred to as the "terminal." 【0053】 Traditional systems often relied on subjective evaluation of employee performance, lacking fairness and transparency. Furthermore, the evaluation process was time-consuming and labor-intensive, making rapid feedback difficult. Additionally, limitations in setting evaluation criteria and improving analytical accuracy made it challenging to flexibly adapt to organizational policies. 【0054】 The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 1 is realized by the following means. 【0055】 In this invention, the server includes means for an information processing device to periodically or in real time acquire job information related to individual tasks from various sources; means for an operating terminal to provide an interface for setting evaluation criteria according to the organization's evaluation policy; and means for a computing processing device to analyze and quantify the acquired job information using a machine learning model based on pre-set evaluation criteria. This makes it possible to perform employee job evaluations objectively and efficiently. 【0056】 An "information processing system" is a computer system used to collect and manage data such as job-related information. 【0057】 "Job information related to individual tasks" refers to detailed information about the tasks performed by employees, such as the progress, results, and working hours. 【0058】 "Information sources" refer to data providers for collecting job-related information, including project management tools and work time tracking systems. 【0059】 An "operation terminal" is a device that provides an interface for administrators to access the system and set evaluation criteria. 【0060】 "Evaluation criteria" refer to the indicators and standards used to evaluate an employee's work, and include weighting determined according to the organization's policies. 【0061】 A "processing unit" is a device that uses machine learning models to analyze and quantify data based on acquired job information. 【0062】 A "machine learning model" is an algorithm or mathematical model that learns patterns from data and performs analysis based on new data. 【0063】 "Natural language processing technology" refers to the technology that analyzes, understands, and generates human language, and is used to generate evaluation results as text. 【0064】 A "notification device" is a device or software system that communicates generated feedback to employees and displays it visually. 【0065】 "Quantification" is the process of calculating a score or indicator to quantitatively evaluate an employee's work performance based on the analyzed data. 【0066】 This invention is a system that combines an information processing device, an operating terminal, a computing device, and a notification device in order to objectively evaluate employee performance. Specific embodiments are described below. 【0067】 First, the server functions as an information processing device, utilizing APIs from various sources to collect job-related information for individual tasks. This includes retrieving data from project management tools and work time tracking systems. The hardware consists of a standard server computer, and the software is a program (e.g., a Python script) for handling API calls. 【0068】 Next, the terminal provides an operating interface to the administrator, enabling the setting of evaluation criteria. Through this interface, the administrator can adjust the importance of each evaluation criterion based on the organization's evaluation policy. The interface is implemented using a web-based GUI (using JavaScript® and HTML5) to provide an intuitive user experience. 【0069】 The server then acts as a computing device, analyzing the acquired data. It utilizes machine learning models (such as scikit-learn or TENSORFLOW®) to quantify job information based on pre-defined evaluation criteria. This enables data-driven scoring, allowing for more objective evaluations. 【0070】 Furthermore, the server uses natural language processing techniques to generate evaluation results as text. Natural language processing libraries (such as NLTK and GPT models) are used in this process. For example, feedback such as "The time efficiency was very high" is generated. 【0071】 Finally, the terminal acts as a notification device, transmitting the generated feedback to employees. This feedback is provided to each employee through email notifications and display on the system's dashboard. 【0072】 As a concrete example, if employee A completes a high-quality project in a short period of time, the system automatically collects the project completion data. For example, by entering a prompt such as, "Generate a fair evaluation and feedback based on employee A's work data," the server executes the corresponding evaluation process. In this way, this invention realizes an efficient and fair work evaluation process. 【0073】 The flow of the specific processing in Example 1 will be explained using Figure 11. 【0074】 Step 1: 【0075】 The server begins collecting job information. Input data comes from project management tools and work time tracking systems via APIs. The server periodically retrieves this data and stores it in a database. By using API calls to aggregate project task progress and completed work time data, and organizing and storing it in a storage system, the server transforms large amounts of data into a manageable format. 【0076】 Step 2: 【0077】 The terminal provides an interface for administrators to log in and set evaluation criteria. Input in this step is the administrator's instructions or selections, and output is the weighting of evaluation criteria and specific evaluation items. The administrator, as a user, operates the GUI on the terminal and inputs numerical values ​​for the importance of evaluation items such as "quality of deliverables," "achievement level," and "contribution to the team." These values ​​are sent to the server and stored as guidelines for evaluation. 【0078】 Step 3: 【0079】 The server performs data analysis based on the configured evaluation criteria. Input includes job information collected in Step 1 and the evaluation criteria set in Step 2. The server uses a machine learning model to analyze the job information and quantify each employee's score. For example, it might use the scikit-learn library in Python to analyze the data and use a learning algorithm that references historical data to quantitatively evaluate individual job performance. 【0080】 Step 4: 【0081】 The server generates feedback based on the analyzed data. The input is the scores and evaluation results obtained in step 3, and the output is a feedback message directed at each employee. Utilizing natural language processing libraries (e.g., NLTK and GPT models), the generated feedback includes both positive evaluations and points for improvement. Specifically, by transcribing each score into text, the evaluation content for each employee is clearly communicated. 【0082】 Step 5: 【0083】 The terminal notifies employees of the generated feedback. The input is the feedback text generated in step 4, and the output is displayed via email or on the company's internal system dashboard. Employees, as users, can receive timely feedback through the terminal, allowing them to review their work and consider improvement measures for the next evaluation. 【0084】 (Application Example 1) 【0085】 Next, we will explain Application Example 1. In the following explanation, the data processing device 12 will be referred to as the "server," and the smart device 14 will be referred to as the "terminal." 【0086】 To achieve efficient operational management of work equipment in factories, it is crucial to accurately and quickly evaluate the operational performance of each piece of equipment and identify areas for improvement. However, human evaluation is subjective and often lacks consistency. This invention aims to solve this problem and build a system that provides reliable analysis and feedback. 【0087】 The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 1 is realized by the following means. 【0088】 In this invention, the server includes data collection means for collecting operational data of the work device, criteria setting means for setting evaluation criteria, AI analysis means for analyzing and evaluating the collected operational data based on the evaluation criteria, feedback generation means for generating feedback based on the evaluation results, and notification display means for notifying and displaying the feedback to the manager of the work device. This enables objective and reliable evaluation of the work device. 【0089】 "Work equipment" is a general term for machines and equipment designed to perform specific tasks or operations. 【0090】 "Operational data" refers to digital data that includes information about the operating status and performance of the work equipment. 【0091】 "Data acquisition means" refers to technical means for acquiring operational data from a work device and appropriately storing or transmitting it. 【0092】 A "standard setting means" is a technical means for determining and adjusting the standards and conditions used in evaluation. 【0093】 "AI analysis methods" refer to technical means that use artificial intelligence to analyze collected data and perform specific evaluations. 【0094】 A "feedback generation method" is a technical means for creating improvement points and evaluation content based on the results of AI analysis. 【0095】 A "notification display means" is a technical means for communicating generated feedback to relevant parties and displaying it visually. 【0096】 To implement this invention, the server collects operational data in real time through sensors attached to work equipment within the factory. This data collection utilizes a connection device and communication network that aggregates information from each sensor. The data is centrally managed and stored in a central database for processing. 【0097】 The server provides an interface that factory managers can operate as a means of setting standards, where evaluation criteria such as work efficiency and quality indicators can be set. Through this interface, the weighting of the standards can be adjusted, enabling flexible evaluations that align with the factory's production policies. 【0098】 As an AI analysis tool, the server uses machine learning libraries such as TensorFlow to analyze the collected operational data. The AI ​​model learns from past data and calculates a score to evaluate the efficiency of each work device. This allows for understanding performance trends and identifying areas where individual devices need improvement. 【0099】 As a means of generating feedback, the server utilizes natural language processing technology to generate feedback based on the analysis results. The generated feedback is written in a way that is specific and practical for the administrator of the work equipment. 【0100】 Finally, as a means of displaying notifications, the server displays feedback on the administrator's terminal. Administrators can be notified via dashboards or email notifications and encouraged to take corrective action. For example, if a device is found to have good work efficiency but inconsistent quality, the feedback might state, "It is desirable to consider focused improvements to quality control." An example of a prompt using a generative AI model would be, "Based on the latest performance data of robot A, generate feedback on areas for improvement in work efficiency and product quality." 【0101】 In this way, the present invention promotes efficient operation and continuous improvement in factory settings, contributing to an overall increase in productivity. 【0102】 The flow of a specific process in Application Example 1 will be explained using Figure 12. 【0103】 Step 1: 【0104】 The server collects operational data from sensors on work equipment installed in the factory. This collection is performed by receiving the real-time data stream generated by the sensors. The input is the operational parameters from the sensors, and the output is the storage of this data in an organized database. After collection, the data is stored in the database on the server and used for subsequent processing. 【0105】 Step 2: 【0106】 The terminal (factory administrator's console) inputs evaluation criteria through a criteria setting interface. The administrator adjusts the weighting as needed, such as for work efficiency and quality indicators. The input is the evaluation criteria set by the administrator, and the output is the set of criteria used by the server for evaluation. The specific actions performed by the terminal are providing a setting form and registering the criteria in the database. 【0107】 Step 3: 【0108】 The server evaluates the collected motion data using AI analysis tools. The AI ​​model incorporates pre-generated AI model technology for analysis, and calculates a performance score based on the input motion data. The input consists of motion data and evaluation criteria, and the output is the evaluation score for each work device. The server performs data processing using the TensorFlow library. 【0109】 Step 4: 【0110】 The server generates feedback based on the AI ​​analysis results. Using a generative AI model, it creates specific feedback tailored to individual results. The input is an evaluation score, and the output is a feedback statement including areas for improvement and an assessment of the current situation. Specifically, it utilizes OpenAI's NLP technology to generate easily understandable feedback in natural language. 【0111】 Step 5: 【0112】 The server notifies the user of the feedback using notification display methods. In this case, notifications are sent to the terminal via email or dashboard display. The input is the generated feedback, and the output is the user's confirmation of the feedback. The terminal uses front-end technology to display the feedback to the administrator. 【0113】 This process enables efficient management of work equipment and the proposal of improvement measures. 【0114】 Furthermore, an emotion engine that estimates the user's emotions may be incorporated. That is, the identification processing unit 290 may use the emotion identification model 59 to estimate the user's emotions and perform identification processing using the user's emotions. 【0115】 This invention is an evaluation system for enhancing the assessment of employees' work performance, and further improves the evaluation process by incorporating an emotion engine. This system objectively evaluates employees' work data and optimizes the quality of feedback by considering the user's emotional state. 【0116】 First, the server executes a process to collect employee work data. It uses APIs to retrieve information such as the number of completed projects, working hours, and the number of errors in deliverables from project management tools and time management systems, and stores it in a database. 【0117】 Next, the terminal provides an interface for administrators to set evaluation criteria. Through this interface, the administrator (user) weights the criteria and customizes them according to organizational policies. This configuration information is also stored on the server and used during the evaluation process. 【0118】 The server uses AI analysis tools for performance evaluations. It analyzes collected work data based on evaluation criteria and performs scoring using an AI model. During this process, the AI ​​learns from past data to improve the accuracy of the evaluations. Furthermore, a key feature of this system is the inclusion of an emotion engine, which collects and utilizes user emotions regarding past feedback, in addition to user evaluations. 【0119】 Next, the server generates feedback based on the scoring results and the user's emotional information obtained from the emotion engine. The feedback generation mechanism utilizes natural language processing technology to create feedback text that takes emotional information into account. The feedback includes evaluation points and specific improvement suggestions, but the emotion engine analyzes the user's current emotions and expresses the feedback in an appropriate tone, making it more readily accepted. 【0120】 Finally, the terminal notifies the employee (user) of the generated feedback. The evaluation results are displayed via email and on the system's dashboard, allowing the user to review their own evaluation and feedback. A key feature is that, thanks to the built-in emotion engine, the evaluation is presented not merely as a numerical value, but in a way that is emotionally relatable to the user. 【0121】 For example, if employee B experiences some difficulties in completing a new task but ultimately submits an excellent deliverable, this data is collected by the system. According to the evaluation criteria for "effort" and "deliverable quality" set by the manager, the AI ​​scores employee B highly. Simultaneously, the emotion engine selects an appropriate expression based on employee B's responses to past feedback and provides gentle, explanatory feedback stating, "The effort and results you demonstrated through this task are extremely valuable." 【0122】 This system enables performance evaluation while maintaining employee motivation, ultimately contributing to improved productivity across the entire organization. 【0123】 The following describes the processing flow. 【0124】 Step 1: 【0125】 The server collects employee work data. Specifically, it connects to APIs of project management tools and time management systems to collect project progress, work hours, and deliverable quality indicators, and systematically stores this data in a database. 【0126】 Step 2: 【0127】 The device displays an evaluation criteria setting interface for administrators. Administrators, acting as users, set the weighting of each evaluation criterion, such as "quality of deliverables," "goal achievement rate," and "team contribution," using drag-and-drop or sliders, based on the organization's policies. The settings are saved on the server. 【0128】 Step 3: 【0129】 The server begins analyzing the collected business data using AI analysis tools. The AI ​​model analyzes the data based on established evaluation criteria and scores each employee. At this time, the AI ​​model learns from past evaluation data to improve its accuracy and evaluates each employee's contribution from multiple perspectives. 【0130】 Step 4: 【0131】 The server operates an emotion engine, collecting emotion data relevant to the current performance evaluation while referencing the user's past feedback responses. Emotion data is inferred from the history of how the user received feedback. 【0132】 Step 5: 【0133】 The server generates feedback based on AI analysis results and emotion engine data. The feedback generation method utilizes natural language processing to create emotionally sensitive feedback messages. This feedback includes positive evaluations and specific suggestions for improvement, and its expression reflects the user's emotional state. 【0134】 Step 6: 【0135】 The device notifies the employee (user) of the feedback, and the feedback content is displayed visually through a dashboard or email. Employees can review their evaluation and feedback in detail and receive feedback to improve their work. This approach makes the feedback more emotionally receptive, positively impacting user response and motivation. 【0136】 (Example 2) 【0137】 Next, we will describe Example 2. In the following description, the data processing device 12 will be referred to as the "server," and the smart device 14 will be referred to as the "terminal." 【0138】 Traditional employee evaluation systems primarily focus on numerically assessing work performance, resulting in feedback that doesn't adequately consider the feelings and reactions of individual users. Consequently, feedback can sometimes have an inappropriate tone or content for employees, potentially reducing their acceptance of the evaluation results. Furthermore, the failure to utilize responses to past feedback meant that similar problems were likely to recur. 【0139】 The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 2 is realized by the following means. 【0140】 In this invention, the server includes an information gathering means for collecting business information, a criteria setting means for setting evaluation criteria, an artificial intelligence analysis means for analyzing and quantifying the collected business information based on the criteria, an information generation means for generating information based on the quantification results and past feedback, and a notification display means for notifying and displaying the information to the user. This makes it possible to generate feedback that takes the user's emotions into consideration and to provide evaluation results that are highly acceptable. 【0141】 "Business information" refers to data related to an employee's work, including quantifiable data such as the number of completed projects, working hours, and the number of errors in deliverables. 【0142】 "Information gathering means" refers to the processes and functions used to acquire business information from external systems and tools. 【0143】 "Means of setting standards" refers to interfaces and functions for defining evaluation criteria and adjusting them based on organizational policies. 【0144】 "Artificial intelligence analysis means" refers to an algorithm or system that analyzes and quantifies collected business information. 【0145】 "Information generation means" refers to processes and functions that generate new information based on quantified results and past feedback. 【0146】 "Notification display means" refers to a function that informs the user of generated information and displays it visually. 【0147】 This system aims to enhance employee performance evaluations by incorporating emotional factors. Its implementation requires the coordinated operation of servers, terminals, and users. 【0148】 First, the server will acquire business information via APIs from project management tools and time management systems as a means of information gathering. Specifically, it will collect data such as the number of completed projects, working hours, and the number of errors in deliverables in real time or periodically, and store it in a database. The software used within the server is expected to include data analysis libraries in Python and Java (registered trademark). 【0149】 Next, evaluation criteria are set via a terminal. The administrator, acting as the user, inputs the evaluation criteria and assigns weights through an interface displayed on the terminal. The terminal often uses a browser-based GUI tool, typically a web application based on HTML / CSS / JavaScript. The set criteria are sent to the server and stored in a database. 【0150】 For evaluation, the server uses artificial intelligence analysis tools. Based on the collected business information, the data is analyzed and quantified according to evaluation criteria. This analysis utilizes a generative AI model, and data scoring is performed using machine learning libraries in Python and R. To improve the accuracy of the analysis, the AI ​​model is continuously trained based on past evaluation history. 【0151】 Furthermore, in generating feedback, the server utilizes an emotion engine to leverage user emotion data from past feedback. Based on the obtained numerical results and emotion data, natural language processing techniques are used to generate feedback text in a format that is easily accepted by the user. 【0152】 Finally, the terminal notifies the employee (user) of the generated feedback. In this process, the feedback is sent via email or displayed on the system dashboard. Employees can review the feedback and use it to improve their work. 【0153】 As a concrete example, if employee B overcomes difficulties and submits excellent results, the server generates a text prompt in the form of "Generate feedback on employee B's work. Please consider past response data and use language that evaluates effort and achievement," which is input into an AI model to generate an emotionally sensitive feedback message. This allows employee B to emotionally accept the evaluation and increases their motivation for future tasks. 【0154】 The flow of the specific processing in Example 2 will be explained using Figure 13. 【0155】 Step 1: 【0156】 The server collects business information using data gathering tools. Input data includes data obtained from APIs of project management tools and time management systems. Based on this, the server retrieves data such as the number of completed projects, working hours, and the number of errors in deliverables. The server then stores this data in a database, preparing it for any necessary analysis. 【0157】 Step 2: 【0158】 The terminal provides a means for setting evaluation criteria, and the administrator, as the user, sets the evaluation criteria. Inputs include various evaluation criteria and their weights, specified by the administrator using the interface. These can be visually adjusted on the terminal using sliders and checkboxes. Output is the set criteria information, which is sent to the server and stored in the database. 【0159】 Step 3: 【0160】 The server uses artificial intelligence analysis tools to analyze and score business information. The input consists of collected business information and evaluation criteria set in step 2. The AI ​​model analyzes the data based on this information and quantifies employee performance. The output is a scoring result, which is then used in the next feedback process. 【0161】 Step 4: 【0162】 The server uses an emotion engine to collect and analyze emotional information about the user's past feedback. The input includes past feedback content and the user's response to it. The server analyzes this and accumulates it as an emotion information database. The output serves as material for generating feedback that incorporates emotional elements. 【0163】 Step 5: 【0164】 The server uses a feedback generation mechanism to generate feedback. The input consists of scoring results and collected sentiment information. The server utilizes natural language processing techniques to construct feedback sentences that are easily accepted by the user. As output, a sentiment-conscious feedback sentence is generated. 【0165】 Step 6: 【0166】 The terminal notifies the employee (user) of the generated feedback. The input consists of the generated feedback text and the user's contact information. The terminal then performs actions such as sending the notification via email or displaying it on a dashboard within the system. As an output, the user can review and accept the evaluation. 【0167】 (Application Example 2) 【0168】 Next, we will explain application example 2. In the following explanation, the data processing device 12 will be referred to as a "server" and the smart device 14 as a "terminal". 【0169】 There is a need for a system that efficiently and accurately evaluates the operation of machinery in industry and provides appropriate feedback to managers. However, conventional systems have shortcomings in collecting and analyzing machine operation data and are unable to provide feedback that takes into account emotions and tone. This makes it difficult for managers to take appropriate corrective actions. 【0170】 The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means. 【0171】 In this invention, the server includes information gathering means for collecting operational data of business machines, evaluation criteria setting means for setting evaluation criteria, and artificial intelligence analysis means for analyzing the collected operational data based on the evaluation criteria and performing scoring. This makes it possible to efficiently and accurately evaluate the operation of machines and generate and provide feedback that takes emotions into account to administrators. 【0172】 "Business machinery" is a general term for devices and systems that automatically perform specific tasks in industry. 【0173】 "Operational data" refers to a collection of information generated when a machine performs a task, including working time, error rate, and the quality of the finished product. 【0174】 "Information gathering means" refers to methods and technologies for acquiring operational data from business machinery, and includes the use of sensors and network interfaces. 【0175】 "Evaluation criteria" are settings that define indicators and standards for evaluating the operation of business machinery, and include quality, efficiency, error rate, etc. 【0176】 "Evaluation criteria setting means" refers to a function for adjusting and setting evaluation criteria for business machinery based on the organization's policies. 【0177】 "Artificial intelligence analysis means" refers to a technology that automatically analyzes the performance of equipment and generates a score based on operational data, using machine learning and data mining techniques. 【0178】 A "feedback generation method" refers to a method or technology for generating appropriate feedback content from scoring results and emotional information and providing it to an administrator. 【0179】 "Notification display means" refers to devices or software that communicate generated feedback to administrators for their review, and includes methods such as email sending and dashboard display. 【0180】 The system for realizing this invention combines multiple means to collect operational data from business machines and perform evaluations based on that data. In the overall process, a server acts as the central point for collecting, analyzing, generating feedback on, and notifying the results of the information. 【0181】 The server first collects operational data from sensors attached to each machine to obtain operational data. This information is stored in a cloud database such as AWS® RDS. The server then analyzes this data using Python, pandas, and scikit-learn, and scores it based on evaluation criteria. Furthermore, an artificial intelligence model learns from past data through machine learning libraries such as TensorFlow, improving the accuracy of the analysis. 【0182】 In generating feedback, the server uses tools such as the Google® NLP API to produce feedback in a tone that is easily accepted by administrators. During this process, sentiment analysis is performed based on past response data to ensure that the generated feedback is appropriate for organizational policies and individual circumstances. 【0183】 Ultimately, the server sends the generated feedback to the administrator via a notification display mechanism. The administrator can then review the evaluation results using a web dashboard built with React.js and take necessary administrative measures. The following example prompt is effective for generating feedback: "Based on Robot A's work data, please use the emotion engine to create feedback statements regarding time efficiency and quality improvement." 【0184】 The flow of a specific process in Application Example 2 will be explained using Figure 14. 【0185】 Step 1: 【0186】 The server acquires operational data from the business machinery. Data from sensors is collected in a cloud database such as AWS RDS, and information about the operation is stored. The input is real-time data obtained from the sensors, and the output is structured data stored in the database. 【0187】 Step 2: 【0188】 The server processes the collected data using Python's pandas library. It removes unnecessary data, extracts only the essential parts, and formats them. The input is the raw data extracted from the database, and the output is cleaned up and formatted for analysis. 【0189】 Step 3: 【0190】 The server uses scikit-learn or TensorFlow to input data into a machine learning model and score its performance. In this process, the AI ​​model calculates performance evaluation metrics based on the input data. The input is formatted data, and the output is the performance score for each machine. 【0191】 Step 4: 【0192】 The server utilizes the Google NLP API to generate feedback. It uses the obtained behavioral scores and past feedback from administrators as data to create easy-to-understand feedback in natural language. The input is the score and past sentiment data, and the output is a feedback text that is easy for administrators to understand. 【0193】 Step 5: 【0194】 The server generates feedback and sends it to the administrator using a notification display mechanism. Here, the results are visualized using a web dashboard built with React.js. The input is the generated feedback text, and the output is the content displayed on the dashboard viewed by the administrator. 【0195】 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 user input for the result of the specific processing. The control unit 46A transmits the audio data indicating 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. 【0196】 Data generation model 58 is a so-called generative AI (Artificial Intelligence). An example of data generation model 58 is ChatGPT (registered trademark) (Internet search).<URL: https: / / openai.com / blog / chatgpt> ), Gemini (registered trademark) (Internet search) <url: https: gemini.google.com ?hl="ja">Examples of generative AI include the following. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 is input with prompts containing instructions, and with inference data such as audio data representing speech, text data representing text, and image data representing images. The data generation model 58 infers from the input inference data according to the instructions indicated by the prompts, and outputs the inference results in data formats such as audio data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization. 【0197】 In the above embodiment, an example was given in which specific processing is performed by the data processing device 12, but the technology of this disclosure is not limited thereto, and the specific processing may also be performed by the smart device 14. 【0198】 [Second Embodiment] 【0199】 Figure 3 shows an example of the configuration of the data processing system 210 according to the second embodiment. 【0200】 As shown in Figure 3, the data processing system 210 includes a data processing device 12 and smart glasses 214. An example of the data processing device 12 is a server. 【0201】 The data processing device 12 comprises a computer 22, a database 24, and a communication interface 26. The computer 22 is an example of a "computer" related to the technology of this disclosure. The computer 22 comprises a processor 28, RAM 30, and storage 32. The processor 28, RAM 30, and storage 32 are connected to a bus 34. The database 24 and the communication interface 26 are also connected to the bus 34. The communication interface 26 is connected to a network 54. An example of the network 54 is a WAN (Wide Area Network) and / or a LAN (Local Area Network). 【0202】 The smart glasses 214 include a computer 36, a microphone 238, a speaker 240, a camera 42, and a communication interface 44. The computer 36 includes a processor 46, RAM 48, and storage 50. The processor 46, RAM 48, and storage 50 are connected to a bus 52. The microphone 238, speaker 240, and camera 42 are also connected to the bus 52. 【0203】 The microphone 238 receives voice signals from the user 20 and receives instructions from the user 20. The microphone 238 captures the voice signals from the user 20, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio according to the instructions from the processor 46. 【0204】 Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an image sensor such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, and captures images of the area around the user 20 (for example, an imaging range defined by a field of view equivalent to the width of a typical healthy person's field of vision). 【0205】 Communication interface 44 is connected to network 54. Communication interfaces 44 and 26 are responsible for the exchange of various information between processor 46 and processor 28 via network 54. The exchange of various information between processor 46 and processor 28 using communication interfaces 44 and 26 is performed in a secure manner. 【0206】 Figure 4 shows an example of the main functions of the data processing device 12 and the smart glasses 214. As shown in Figure 4, the data processing device 12 performs specific processing using the processor 28. The storage 32 stores the specific processing program 56. 【0207】 The specific processing program 56 is an example of a "program" relating to the technology of this 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. 【0208】 The storage 32 stores the data generation model 58 and the emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290. 【0209】 In the smart glasses 214, the processor 46 performs the reception output processing. The storage 50 stores the reception output program 60. 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 processing is realized by the processor 46 operating as a control unit 46A according to the reception output program 60 executed on the RAM 48. 【0210】 Next, the identification processing performed by the identification processing unit 290 of the data processing device 12 will be described. 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". 【0211】 This invention provides an evaluation system for objectively and efficiently evaluating employee performance, thereby realizing a fair and transparent evaluation process. This system automates a series of steps, from collecting employee performance data and setting fair evaluation criteria to analyzing and evaluating the data using artificial intelligence technology, and generating and notifying feedback. 【0212】 First, the server collects data related to employees' work on a regular or real-time basis. Data sources include project management tools and work time tracking systems. APIs are used to retrieve necessary information, which is then organized and stored in a database. This data collection method enables the accurate handling of large amounts of data. 【0213】 Next, the terminal provides an interface for administrators, allowing them to set evaluation criteria. This interface makes it easy to adjust the weighting of each evaluation criterion according to organizational policies, and administrators (users) can set the items they consider important, such as "quality of deliverables," "achievement level," and "contribution to the team." 【0214】 Subsequently, the server uses AI analysis tools to analyze the collected business data based on pre-defined evaluation criteria. The AI ​​model learns each employee's activities from past data and calculates a score according to the individual criteria. This improves the accuracy and reliability of the data, enabling a more objective evaluation. 【0215】 Furthermore, the server automatically generates feedback based on the AI's analysis results. This feedback generation method uses natural language processing technology to describe specific evaluation content for each employee, including both positive aspects and areas for improvement. 【0216】 Finally, the terminal notifies employees of the generated feedback, which is then displayed on their client devices. This evaluation result notification utilizes email notifications or a dashboard display within the system. Employees can review their evaluations and use the feedback to improve their work and prepare for their next evaluation. 【0217】 For example, if employee A completes a high-quality project in a short period of time, the system collects the data. Based on the "efficiency" and "quality" standards set by the manager, the AI ​​calculates a high score. As a result, the feedback specifically evaluates the achievement of results in a short period of time, and additional advice such as "Next time, you should also be mindful of your contribution to the team" is added. 【0218】 Thus, the system of the present invention contributes to improving motivation and trust within the organization by automating the entire process and enabling rapid and fair employee evaluations. 【0219】 The following describes the processing flow. 【0220】 Step 1: 【0221】 The server collects data related to employees' work from various systems. Specifically, it connects to data sources such as project management tools and time management systems via APIs to obtain information such as the number of completed projects, working hours, and the number of errors in deliverables, and stores this information in a database. 【0222】 Step 2: 【0223】 The terminal displays an interface for administrators and provides the functionality to set evaluation criteria. Administrators, as users, use the evaluation criteria interface to set priorities and weights for each evaluation criterion, such as "quality of deliverables," "efficiency," and "team contribution." These settings are sent to the server and used for subsequent evaluations. 【0224】 Step 3: 【0225】 The server operates an AI analysis tool based on the collected business data. The AI ​​model analyzes the data based on pre-set evaluation criteria and scores each employee's activities. This makes it possible to objectively evaluate each employee's performance and contributions. The AI ​​model improves its proficiency by referring to past data, thus increasing the accuracy of the analysis results. 【0226】 Step 4: 【0227】 The server generates feedback based on scoring results from AI analysis. The feedback generation system uses natural language processing to create customized feedback messages for individual employees. This feedback includes positive evaluation points and suggestions for improvement. 【0228】 Step 5: 【0229】 The terminal notifies each employee (user) of the generated feedback and evaluation results. The feedback is displayed via email or an on-screen dashboard. Employees can use this information to review their own work performance and work towards improvement. 【0230】 (Example 1) 【0231】 Next, we will describe Example 1. 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." 【0232】 Traditional systems often relied on subjective evaluation of employee performance, lacking fairness and transparency. Furthermore, the evaluation process was time-consuming and labor-intensive, making rapid feedback difficult. Additionally, limitations in setting evaluation criteria and improving analytical accuracy made it challenging to flexibly adapt to organizational policies. 【0233】 The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 1 is realized by the following means. 【0234】 In this invention, the server includes means for an information processing device to periodically or in real time acquire job information related to individual tasks from various sources; means for an operating terminal to provide an interface for setting evaluation criteria according to the organization's evaluation policy; and means for a computing processing device to analyze and quantify the acquired job information using a machine learning model based on pre-set evaluation criteria. This makes it possible to perform employee job evaluations objectively and efficiently. 【0235】 An "information processing system" is a computer system used to collect and manage data such as job-related information. 【0236】 "Job information related to individual tasks" refers to detailed information about the tasks performed by employees, such as the progress, results, and working hours. 【0237】 "Information sources" refer to data providers for collecting job-related information, including project management tools and work time tracking systems. 【0238】 An "operation terminal" is a device that provides an interface for administrators to access the system and set evaluation criteria. 【0239】 "Evaluation criteria" refer to the indicators and standards used to evaluate an employee's work, and include weighting determined according to the organization's policies. 【0240】 A "processing unit" is a device that uses machine learning models to analyze and quantify data based on acquired job information. 【0241】 A "machine learning model" is an algorithm or mathematical model that learns patterns from data and performs analysis based on new data. 【0242】 "Natural language processing technology" refers to the technology that analyzes, understands, and generates human language, and is used to generate evaluation results as text. 【0243】 A "notification device" is a device or software system that communicates generated feedback to employees and displays it visually. 【0244】 "Quantification" is the process of calculating a score or indicator to quantitatively evaluate an employee's work performance based on the analyzed data. 【0245】 This invention is a system that combines an information processing device, an operating terminal, a computing device, and a notification device in order to objectively evaluate employee performance. Specific embodiments are described below. 【0246】 First, the server functions as an information processing device, utilizing APIs from various sources to collect job-related information for individual tasks. This includes retrieving data from project management tools and work time tracking systems. The hardware consists of a standard server computer, and the software is a program (e.g., a Python script) for handling API calls. 【0247】 Next, the terminal provides an operating interface to the administrator, enabling the setting of evaluation criteria. Through this interface, the administrator can adjust the importance of each evaluation criterion based on the organization's evaluation policy. The interface is implemented using a web-based GUI (using JavaScript and HTML5) to provide an intuitive user experience. 【0248】 The server then acts as a computing device, analyzing the acquired data. It utilizes machine learning models (e.g., scikit-learn or TensorFlow) to quantify job information based on pre-defined evaluation criteria. This enables data-driven scoring, allowing for more objective evaluations. 【0249】 Furthermore, the server uses natural language processing techniques to generate evaluation results as text. Natural language processing libraries (such as NLTK and GPT models) are used in this process. For example, feedback such as "The time efficiency was very high" is generated. 【0250】 Finally, the terminal acts as a notification device, transmitting the generated feedback to employees. This feedback is provided to each employee through email notifications and display on the system's dashboard. 【0251】 As a concrete example, if employee A completes a high-quality project in a short period of time, the system automatically collects the project completion data. For example, by entering a prompt such as, "Generate a fair evaluation and feedback based on employee A's work data," the server executes the corresponding evaluation process. In this way, this invention realizes an efficient and fair work evaluation process. 【0252】 The flow of the specific processing in Example 1 will be explained using Figure 11. 【0253】 Step 1: 【0254】 The server begins collecting job information. Input data comes from project management tools and work time tracking systems via APIs. The server periodically retrieves this data and stores it in a database. By using API calls to aggregate project task progress and completed work time data, and organizing and storing it in a storage system, the server transforms large amounts of data into a manageable format. 【0255】 Step 2: 【0256】 The terminal provides an interface for administrators to log in and set evaluation criteria. Input in this step is the administrator's instructions or selections, and output is the weighting of evaluation criteria and specific evaluation items. The administrator, as a user, operates the GUI on the terminal and inputs numerical values ​​for the importance of evaluation items such as "quality of deliverables," "achievement level," and "contribution to the team." These values ​​are sent to the server and stored as guidelines for evaluation. 【0257】 Step 3: 【0258】 The server performs data analysis based on the configured evaluation criteria. Input includes job information collected in Step 1 and the evaluation criteria set in Step 2. The server uses a machine learning model to analyze the job information and quantify each employee's score. For example, it might use the scikit-learn library in Python to analyze the data and use a learning algorithm that references historical data to quantitatively evaluate individual job performance. 【0259】 Step 4: 【0260】 The server generates feedback based on the analyzed data. The input is the scores and evaluation results obtained in step 3, and the output is a feedback message directed at each employee. Utilizing natural language processing libraries (e.g., NLTK and GPT models), the generated feedback includes both positive evaluations and points for improvement. Specifically, by transcribing each score into text, the evaluation content for each employee is clearly communicated. 【0261】 Step 5: 【0262】 The terminal notifies employees of the generated feedback. The input is the feedback text generated in step 4, and the output is displayed via email or on the company's internal system dashboard. Employees, as users, can receive timely feedback through the terminal, allowing them to review their work and consider improvement measures for the next evaluation. 【0263】 (Application Example 1) 【0264】 Next, we will explain Application Example 1. In the following explanation, the data processing device 12 will be referred to as the "server," and the smart glasses 214 will be referred to as the "terminal." 【0265】 To achieve efficient operational management of work equipment in factories, it is crucial to accurately and quickly evaluate the operational performance of each piece of equipment and identify areas for improvement. However, human evaluation is subjective and often lacks consistency. This invention aims to solve this problem and build a system that provides reliable analysis and feedback. 【0266】 The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 1 is realized by the following means. 【0267】 In this invention, the server includes data collection means for collecting operational data of the work device, criteria setting means for setting evaluation criteria, AI analysis means for analyzing and evaluating the collected operational data based on the evaluation criteria, feedback generation means for generating feedback based on the evaluation results, and notification display means for notifying and displaying the feedback to the manager of the work device. This enables objective and reliable evaluation of the work device. 【0268】 "Work equipment" is a general term for machines and equipment designed to perform specific tasks or operations. 【0269】 "Operational data" refers to digital data that includes information about the operating status and performance of the work equipment. 【0270】 "Data acquisition means" refers to technical means for acquiring operational data from a work device and appropriately storing or transmitting it. 【0271】 A "standard setting means" is a technical means for determining and adjusting the standards and conditions used in evaluation. 【0272】 "AI analysis methods" refer to technical means that use artificial intelligence to analyze collected data and perform specific evaluations. 【0273】 A "feedback generation method" is a technical means for creating improvement points and evaluation content based on the results of AI analysis. 【0274】 A "notification display means" is a technical means for communicating generated feedback to relevant parties and displaying it visually. 【0275】 To implement this invention, the server collects operational data in real time through sensors attached to work equipment within the factory. This data collection utilizes a connection device and communication network that aggregates information from each sensor. The data is centrally managed and stored in a central database for processing. 【0276】 The server provides an interface that factory managers can operate as a means of setting standards, where evaluation criteria such as work efficiency and quality indicators can be set. Through this interface, the weighting of the standards can be adjusted, enabling flexible evaluations that align with the factory's production policies. 【0277】 As an AI analysis tool, the server uses machine learning libraries such as TensorFlow to analyze the collected operational data. The AI ​​model learns from past data and calculates a score to evaluate the efficiency of each work device. This allows for understanding performance trends and identifying areas where individual devices need improvement. 【0278】 As a means of generating feedback, the server utilizes natural language processing technology to generate feedback based on the analysis results. The generated feedback is written in a way that is specific and practical for the administrator of the work equipment. 【0279】 Finally, as a notification display means, the server displays feedback on the administrator's terminal. It can notify the administrator using a dashboard or email notification and prompt the execution of improvement measures. As a specific example, when it is found that a certain device has good work efficiency but quality variations, the feedback states "It is desirable to consider focused improvements in quality control." An example of a prompt sentence using the generative AI model is "Based on the latest performance data of Robot A, please generate feedback on the improvement points of work efficiency and product quality." 【0280】 In this way, the present invention promotes the efficient operation and continuous improvement of the factory floor, contributing to the overall improvement of productivity. 【0281】 The flow of the specific process in Application Example 1 will be described using FIG. 12. 【0282】 Step 1: 【0283】 The server collects operation data from the sensors of the working devices installed in the factory. This collection is performed by receiving the real-time data stream generated by the sensors. The input is the operation parameters from the sensors, and the output is the storage of these data in an organized database. After the data is collected, it is stored in the database within the server and used in subsequent processing. 【0284】 Step 2: 【0285】 The terminal (the console of the factory administrator) inputs evaluation criteria through the reference setting interface. The administrator adjusts the weighting as needed, such as work efficiency and quality indicators. The input is the evaluation criteria set by the administrator, and the output is the set of criteria used by the server for evaluation. The specific operations performed by the terminal are the provision of a setting form and the registration of the criteria in the database. 【0286】 Step 3: 【0287】 The server evaluates the collected motion data using AI analysis tools. The AI ​​model incorporates pre-generated AI model technology for analysis, and calculates a performance score based on the input motion data. The input consists of motion data and evaluation criteria, and the output is the evaluation score for each work device. The server performs data processing using the TensorFlow library. 【0288】 Step 4: 【0289】 The server generates feedback based on the AI ​​analysis results. Using a generative AI model, it creates specific feedback tailored to individual results. The input is an evaluation score, and the output is a feedback statement including areas for improvement and an assessment of the current situation. Specifically, it utilizes OpenAI's NLP technology to generate feedback that is easy to understand in natural language. 【0290】 Step 5: 【0291】 The server notifies the user of the feedback using notification display methods. In this case, notifications are sent to the terminal via email or dashboard display. The input is the generated feedback, and the output is the user's confirmation of the feedback. The terminal uses front-end technology to display the feedback to the administrator. 【0292】 This process enables efficient management of work equipment and the proposal of improvement measures. 【0293】 Furthermore, an emotion engine that estimates the user's emotions may be incorporated. That is, the identification processing unit 290 may use the emotion identification model 59 to estimate the user's emotions and perform identification processing using the user's emotions. 【0294】 This invention is an evaluation system for enhancing the assessment of employees' work performance, and further improves the evaluation process by incorporating an emotion engine. This system objectively evaluates employees' work data and optimizes the quality of feedback by considering the user's emotional state. 【0295】 First, the server executes a process to collect employee work data. It uses APIs to retrieve information such as the number of completed projects, working hours, and the number of errors in deliverables from project management tools and time management systems, and stores it in a database. 【0296】 Next, the terminal provides an interface for administrators to set evaluation criteria. Through this interface, the administrator (user) weights the criteria and customizes them according to organizational policies. This configuration information is also stored on the server and used during the evaluation process. 【0297】 The server uses AI analysis tools for performance evaluations. It analyzes collected work data based on evaluation criteria and performs scoring using an AI model. During this process, the AI ​​learns from past data to improve the accuracy of the evaluations. Furthermore, a key feature of this system is the inclusion of an emotion engine, which collects and utilizes user emotions regarding past feedback, in addition to user evaluations. 【0298】 Next, the server generates feedback based on the scoring results and the user's emotional information obtained from the emotion engine. The feedback generation mechanism utilizes natural language processing technology to create feedback text that takes emotional information into account. The feedback includes evaluation points and specific improvement suggestions, but the emotion engine analyzes the user's current emotions and expresses the feedback in an appropriate tone, making it more readily accepted. 【0299】 Finally, the terminal notifies the employee (user) of the generated feedback. The evaluation results are displayed via email and on the system's dashboard, allowing the user to review their own evaluation and feedback. A key feature is that, thanks to the built-in emotion engine, the evaluation is presented not merely as a numerical value, but in a way that is emotionally relatable to the user. 【0300】 For example, if employee B experiences some difficulties in completing a new task but ultimately submits an excellent deliverable, this data is collected by the system. According to the evaluation criteria for "effort" and "deliverable quality" set by the manager, the AI ​​scores employee B highly. Simultaneously, the emotion engine selects an appropriate expression based on employee B's responses to past feedback and provides gentle, explanatory feedback stating, "The effort and results you demonstrated through this task are extremely valuable." 【0301】 This system enables performance evaluation while maintaining employee motivation, ultimately contributing to improved productivity across the entire organization. 【0302】 The following describes the processing flow. 【0303】 Step 1: 【0304】 The server collects employee work data. Specifically, it connects to APIs of project management tools and time management systems to collect project progress, work hours, and deliverable quality indicators, and systematically stores this data in a database. 【0305】 Step 2: 【0306】 The device displays an evaluation criteria setting interface for administrators. Administrators, acting as users, set the weighting of each evaluation criterion, such as "quality of deliverables," "goal achievement rate," and "team contribution," using drag-and-drop or sliders, based on the organization's policies. The settings are saved on the server. 【0307】 Step 3: 【0308】 The server starts analyzing the collected business data using AI analysis means. It analyzes the data based on the evaluation criteria set by the AI model and implements scoring for each employee. At this time, the AI model learns from past evaluation data to improve accuracy and evaluates each employee's contribution from multiple perspectives. 【0309】 Step 4: 【0310】 The server operates the emotion engine and collects emotion data related to the current business evaluation while referring to the user's past feedback responses. The emotion data is inferred from the history of how the user received feedback. 【0311】 Step 5: 【0312】 The server generates feedback based on the AI analysis results and the data of the emotion engine. The feedback generation means utilizes natural language processing to create a feedback message that takes emotions into account. This feedback includes positive evaluations and specific suggestions for improvement, and the expression reflects the user's emotional situation. 【0313】 Step 6: 【0314】 The terminal notifies the feedback to the employee who is the user and visually displays the feedback content through a dashboard or email. The employee can check their evaluation and feedback in detail and receive feedback for business improvement. This approach makes the feedback more acceptable on an emotional level and has a good impact on the user's reaction and motivation. 【0315】 (Example 2)[[ID=I35]] 【0316】 Next, we will describe Example 2. 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". 【0317】 Traditional employee evaluation systems primarily focus on numerically assessing work performance, resulting in feedback that doesn't adequately consider the feelings and reactions of individual users. Consequently, feedback can sometimes have an inappropriate tone or content for employees, potentially reducing their acceptance of the evaluation results. Furthermore, the failure to utilize responses to past feedback meant that similar problems were likely to recur. 【0318】 The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 2 is realized by the following means. 【0319】 In this invention, the server includes an information gathering means for collecting business information, a criteria setting means for setting evaluation criteria, an artificial intelligence analysis means for analyzing and quantifying the collected business information based on the criteria, an information generation means for generating information based on the quantification results and past feedback, and a notification display means for notifying and displaying the information to the user. This makes it possible to generate feedback that takes the user's emotions into consideration and to provide evaluation results that are highly acceptable. 【0320】 "Business information" refers to data related to an employee's work, including quantifiable data such as the number of completed projects, working hours, and the number of errors in deliverables. 【0321】 "Information gathering means" refers to the processes and functions used to acquire business information from external systems and tools. 【0322】 "Means of setting standards" refers to interfaces and functions for defining evaluation criteria and adjusting them based on organizational policies. 【0323】 "Artificial intelligence analysis means" refers to an algorithm or system that analyzes and quantifies collected business information. 【0324】 "Information generation means" refers to processes and functions that generate new information based on quantified results and past feedback. 【0325】 "Notification display means" refers to a function that informs the user of generated information and displays it visually. 【0326】 This system aims to enhance employee performance evaluations by incorporating emotional factors. Its implementation requires the coordinated operation of servers, terminals, and users. 【0327】 First, the server will acquire business information via APIs from project management tools and time management systems as a means of information gathering. Specifically, it will collect data such as the number of completed projects, working hours, and the number of errors in deliverables in real time or periodically, and store it in a database. The software used within the server is expected to include data analysis libraries for Python and Java. 【0328】 Next, evaluation criteria are set via a terminal. The administrator, acting as the user, inputs the evaluation criteria and assigns weights through an interface displayed on the terminal. The terminal often uses a browser-based GUI tool, typically a web application based on HTML / CSS / JavaScript. The set criteria are sent to the server and stored in a database. 【0329】 For evaluation, the server uses artificial intelligence analysis tools. Based on the collected business information, the data is analyzed and quantified according to evaluation criteria. This analysis utilizes a generative AI model, and data scoring is performed using machine learning libraries in Python and R. To improve the accuracy of the analysis, the AI ​​model is continuously trained based on past evaluation history. 【0330】 Furthermore, in generating feedback, the server utilizes an emotion engine to leverage user emotion data from past feedback. Based on the obtained numerical results and emotion data, natural language processing techniques are used to generate feedback text in a format that is easily accepted by the user. 【0331】 Finally, the terminal notifies the employee (user) of the generated feedback. In this process, the feedback is sent via email or displayed on the system dashboard. Employees can review the feedback and use it to improve their work. 【0332】 As a concrete example, if employee B overcomes difficulties and submits excellent results, the server generates a text prompt in the form of "Generate feedback on employee B's work. Please consider past response data and use language that evaluates effort and achievement," which is input into an AI model to generate an emotionally sensitive feedback message. This allows employee B to emotionally accept the evaluation and increases their motivation for future tasks. 【0333】 The flow of the specific processing in Example 2 will be explained using Figure 13. 【0334】 Step 1: 【0335】 The server collects business information using data gathering tools. Input data includes data obtained from APIs of project management tools and time management systems. Based on this, the server retrieves data such as the number of completed projects, working hours, and the number of errors in deliverables. The server then stores this data in a database, preparing it for any necessary analysis. 【0336】 Step 2: 【0337】 The terminal provides a means for setting evaluation criteria, and the administrator, as the user, sets the evaluation criteria. Inputs include various evaluation criteria and their weights, specified by the administrator using the interface. These can be visually adjusted on the terminal using sliders and checkboxes. Output is the set criteria information, which is sent to the server and stored in the database. 【0338】 Step 3: 【0339】 The server uses artificial intelligence analysis tools to analyze and score business information. The input consists of collected business information and evaluation criteria set in step 2. The AI ​​model analyzes the data based on this information and quantifies employee performance. The output is a scoring result, which is then used in the next feedback process. 【0340】 Step 4: 【0341】 The server uses an emotion engine to collect and analyze emotional information about the user's past feedback. The input includes past feedback content and the user's response to it. The server analyzes this and accumulates it as an emotion information database. The output serves as material for generating feedback that incorporates emotional elements. 【0342】 Step 5: 【0343】 The server uses a feedback generation mechanism to generate feedback. The input consists of scoring results and collected sentiment information. The server utilizes natural language processing techniques to construct feedback sentences that are easily accepted by the user. As output, a sentiment-conscious feedback sentence is generated. 【0344】 Step 6: 【0345】 The terminal notifies the employee (user) of the generated feedback. The input consists of the generated feedback text and the user's contact information. The terminal then performs actions such as sending the notification via email or displaying it on a dashboard within the system. As an output, the user can review and accept the evaluation. 【0346】 (Application Example 2) 【0347】 Next, we will explain application example 2. In the following explanation, the data processing device 12 will be referred to as the "server," and the smart glasses 214 will be referred to as the "terminal." 【0348】 There is a need for a system that efficiently and accurately evaluates the operation of machinery in industry and provides appropriate feedback to managers. However, conventional systems have shortcomings in collecting and analyzing machine operation data and are unable to provide feedback that takes into account emotions and tone. This makes it difficult for managers to take appropriate corrective actions. 【0349】 The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means. 【0350】 In this invention, the server includes information gathering means for collecting operational data of business machines, evaluation criteria setting means for setting evaluation criteria, and artificial intelligence analysis means for analyzing the collected operational data based on the evaluation criteria and performing scoring. This makes it possible to efficiently and accurately evaluate the operation of machines and generate and provide feedback that takes emotions into account to administrators. 【0351】 "Business machinery" is a general term for devices and systems that automatically perform specific tasks in industry. 【0352】 "Operational data" refers to a collection of information generated when a machine performs a task, including working time, error rate, and the quality of the finished product. 【0353】 "Information gathering means" refers to methods and technologies for acquiring operational data from business machinery, and includes the use of sensors and network interfaces. 【0354】 "Evaluation criteria" are settings that define indicators and standards for evaluating the operation of business machinery, and include quality, efficiency, error rate, etc. 【0355】 "Evaluation criteria setting means" refers to a function for adjusting and setting evaluation criteria for business machinery based on the organization's policies. 【0356】 "Artificial intelligence analysis means" refers to a technology that automatically analyzes the performance of equipment and generates a score based on operational data, using machine learning and data mining techniques. 【0357】 A "feedback generation method" refers to a method or technology for generating appropriate feedback content from scoring results and emotional information and providing it to an administrator. 【0358】 "Notification display means" refers to devices or software that communicate generated feedback to administrators for their review, and includes methods such as email sending and dashboard display. 【0359】 The system for realizing this invention combines multiple means to collect operational data from business machines and perform evaluations based on that data. In the overall process, a server acts as the central point for collecting, analyzing, generating feedback on, and notifying the results of the information. 【0360】 The server first collects operational data from sensors attached to each machine. This information is stored in a cloud database such as AWS RDS. The server then analyzes this data using Python, pandas, and scikit-learn, and scores it based on evaluation criteria. Furthermore, an artificial intelligence model learns from past data through machine learning libraries such as TensorFlow, improving the accuracy of the analysis. 【0361】 In generating feedback, the server uses tools such as the Google NLP API to produce feedback in a tone that is easily accepted by administrators. During this process, sentiment analysis is performed based on past response data to ensure that the generated feedback is appropriate for organizational policies and individual circumstances. 【0362】 Ultimately, the server sends the generated feedback to the administrator via a notification display mechanism. The administrator can then review the evaluation results using a web dashboard built with React.js and take necessary administrative measures. The following example prompt is effective for generating feedback: "Based on Robot A's work data, please use the emotion engine to create feedback statements regarding time efficiency and quality improvement." 【0363】 The flow of a specific process in Application Example 2 will be explained using Figure 14. 【0364】 Step 1: 【0365】 The server acquires operational data from the business machinery. Data from sensors is collected in a cloud database such as AWS RDS, and information about the operation is stored. The input is real-time data obtained from the sensors, and the output is structured data stored in the database. 【0366】 Step 2: 【0367】 The server processes the collected data using Python's pandas library. It removes unnecessary data, extracts only the essential parts, and formats them. The input is the raw data extracted from the database, and the output is cleaned up and formatted for analysis. 【0368】 Step 3: 【0369】 The server uses scikit-learn or TensorFlow to input data into a machine learning model and score its performance. In this process, the AI ​​model calculates performance evaluation metrics based on the input data. The input is formatted data, and the output is the performance score for each machine. 【0370】 Step 4: 【0371】 The server utilizes the Google NLP API to generate feedback. It uses the obtained behavioral scores and past feedback from administrators as data to create easy-to-understand feedback in natural language. The input is the score and past sentiment data, and the output is a feedback text that is easy for administrators to understand. 【0372】 Step 5: 【0373】 The server generates feedback and sends it to the administrator using a notification display mechanism. Here, the results are visualized using a web dashboard built with React.js. The input is the generated feedback text, and the output is the content displayed on the dashboard viewed by the administrator. 【0374】 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 user input for the result of the specific processing. The control unit 46A transmits the audio data indicating user input acquired by the microphone 238 to the data processing unit 12. In the data processing unit 12, the specific processing unit 290 acquires the audio data. 【0375】 Data generation model 58 is a type of so-called generative AI (Artificial Intelligence). One example of data generation model 58 is ChatGPT (Internet search<URL: https: / / openai.com / blog / chatgpt> ), Gemini (Internet search) <url: https: gemini.google.com ?hl="ja">Examples of generative AI include the following. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 is input with prompts containing instructions, and with inference data such as audio data representing speech, text data representing text, and image data representing images. The data generation model 58 infers from the input inference data according to the instructions indicated by the prompts, and outputs the inference results in data formats such as audio data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization. 【0376】 In the above embodiment, an example was given in which specific processing is performed by the data processing device 12, but the technology of this disclosure is not limited thereto, and the specific processing may also be performed by the smart glasses 214. 【0377】 [Third Embodiment] 【0378】 Figure 5 shows an example of the configuration of the data processing system 310 according to the third embodiment. 【0379】 As shown in Figure 5, the data processing system 310 includes a data processing device 12 and a headset terminal 314. An example of the data processing device 12 is a server. 【0380】 The data processing device 12 comprises a computer 22, a database 24, and a communication interface 26. The computer 22 is an example of a "computer" related to the technology of this disclosure. The computer 22 comprises a processor 28, RAM 30, and storage 32. The processor 28, RAM 30, and storage 32 are connected to a bus 34. The database 24 and the communication interface 26 are also connected to the bus 34. The communication interface 26 is connected to a network 54. An example of the network 54 is a WAN (Wide Area Network) and / or a LAN (Local Area Network). 【0381】 The headset terminal 314 includes a computer 36, a microphone 238, a speaker 240, a camera 42, a communication interface 44, and a display 343. The computer 36 includes a processor 46, RAM 48, and storage 50. The processor 46, RAM 48, and storage 50 are connected to a bus 52. The microphone 238, speaker 240, camera 42, and display 343 are also connected to the bus 52. 【0382】 The microphone 238 receives voice signals from the user 20 and receives instructions from the user 20. The microphone 238 captures the voice signals from the user 20, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio according to the instructions from the processor 46. 【0383】 Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an image sensor such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, and captures images of the area around the user 20 (for example, an imaging range defined by a field of view equivalent to the width of a typical healthy person's field of vision). 【0384】 Communication interface 44 is connected to network 54. Communication interfaces 44 and 26 are responsible for the exchange of various information between processor 46 and processor 28 via network 54. The exchange of various information between processor 46 and processor 28 using communication interfaces 44 and 26 is performed in a secure manner. 【0385】 Figure 6 shows an example of the main functions of the data processing device 12 and the headset terminal 314. As shown in Figure 6, the data processing device 12 performs specific processing using the processor 28. The storage 32 stores the specific processing program 56. 【0386】 The specific processing program 56 is an example of a "program" relating to the technology of this 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. 【0387】 The storage 32 stores the data generation model 58 and the emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290. 【0388】 In the headset terminal 314, the processor 46 performs the reception output processing. The storage 50 stores the reception output program 60. 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 processing is realized by the processor 46 operating as a control unit 46A according to the reception output program 60 executed on the RAM 48. 【0389】 Next, the specific processing performed by the specific processing unit 290 of the data processing device 12 will be described. In the following description, the data processing device 12 will be referred to as the "server" and the headset terminal 314 will be referred to as the "terminal". 【0390】 This invention provides an evaluation system for objectively and efficiently evaluating employee performance, thereby realizing a fair and transparent evaluation process. This system automates a series of steps, from collecting employee performance data and setting fair evaluation criteria to analyzing and evaluating the data using artificial intelligence technology, and generating and notifying feedback. 【0391】 First, the server collects data related to employees' work on a regular or real-time basis. Data sources include project management tools and work time tracking systems. APIs are used to retrieve necessary information, which is then organized and stored in a database. This data collection method enables the accurate handling of large amounts of data. 【0392】 Next, the terminal provides an interface for administrators, allowing them to set evaluation criteria. This interface makes it easy to adjust the weighting of each evaluation criterion according to organizational policies, and administrators (users) can set the items they consider important, such as "quality of deliverables," "achievement level," and "contribution to the team." 【0393】 Subsequently, the server uses AI analysis tools to analyze the collected business data based on pre-defined evaluation criteria. The AI ​​model learns each employee's activities from past data and calculates a score according to the individual criteria. This improves the accuracy and reliability of the data, enabling a more objective evaluation. 【0394】 Furthermore, the server automatically generates feedback based on the AI's analysis results. This feedback generation method uses natural language processing technology to describe specific evaluation content for each employee, including both positive aspects and areas for improvement. 【0395】 Finally, the terminal notifies employees of the generated feedback, which is then displayed on their client devices. This evaluation result notification utilizes email notifications or a dashboard display within the system. Employees can review their evaluations and use the feedback to improve their work and prepare for their next evaluation. 【0396】 For example, if employee A completes a high-quality project in a short period of time, the system collects the data. Based on the "efficiency" and "quality" standards set by the manager, the AI ​​calculates a high score. As a result, the feedback specifically evaluates the achievement of results in a short period of time, and additional advice such as "Next time, you should also be mindful of your contribution to the team" is added. 【0397】 Thus, the system of the present invention contributes to improving motivation and trust within the organization by automating the entire process and enabling rapid and fair employee evaluations. 【0398】 The following describes the processing flow. 【0399】 Step 1: 【0400】 The server collects data related to employees' work from various systems. Specifically, it connects to data sources such as project management tools and time management systems via APIs to obtain information such as the number of completed projects, working hours, and the number of errors in deliverables, and stores this information in a database. 【0401】 Step 2: 【0402】 The terminal displays an interface for administrators and provides the functionality to set evaluation criteria. Administrators, as users, use the evaluation criteria interface to set priorities and weights for each evaluation criterion, such as "quality of deliverables," "efficiency," and "team contribution." These settings are sent to the server and used for subsequent evaluations. 【0403】 Step 3: 【0404】 The server operates an AI analysis tool based on the collected business data. The AI ​​model analyzes the data based on pre-set evaluation criteria and scores each employee's activities. This makes it possible to objectively evaluate each employee's performance and contributions. The AI ​​model improves its proficiency by referring to past data, thus increasing the accuracy of the analysis results. 【0405】 Step 4: 【0406】 The server generates feedback based on scoring results from AI analysis. The feedback generation system uses natural language processing to create customized feedback messages for individual employees. This feedback includes positive evaluation points and suggestions for improvement. 【0407】 Step 5: 【0408】 The terminal notifies each employee (user) of the generated feedback and evaluation results. The feedback is displayed via email or an on-screen dashboard. Employees can use this information to review their own work performance and work towards improvement. 【0409】 (Example 1) 【0410】 Next, we will describe Example 1. 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." 【0411】 Traditional systems often relied on subjective evaluation of employee performance, lacking fairness and transparency. Furthermore, the evaluation process was time-consuming and labor-intensive, making rapid feedback difficult. Additionally, limitations in setting evaluation criteria and improving analytical accuracy made it challenging to flexibly adapt to organizational policies. 【0412】 The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 1 is realized by the following means. 【0413】 In this invention, the server includes means for an information processing device to periodically or in real time acquire job information related to individual tasks from various sources; means for an operating terminal to provide an interface for setting evaluation criteria according to the organization's evaluation policy; and means for a computing processing device to analyze and quantify the acquired job information using a machine learning model based on pre-set evaluation criteria. This makes it possible to perform employee job evaluations objectively and efficiently. 【0414】 An "information processing system" is a computer system used to collect and manage data such as job-related information. 【0415】 "Job information related to individual tasks" refers to detailed information about the tasks performed by employees, such as the progress, results, and working hours. 【0416】 "Information sources" refer to data providers for collecting job-related information, including project management tools and work time tracking systems. 【0417】 An "operation terminal" is a device that provides an interface for administrators to access the system and set evaluation criteria. 【0418】 "Evaluation criteria" refer to the indicators and standards used to evaluate an employee's work, and include weighting determined according to the organization's policies. 【0419】 A "processing unit" is a device that uses machine learning models to analyze and quantify data based on acquired job information. 【0420】 A "machine learning model" is an algorithm or mathematical model that learns patterns from data and performs analysis based on new data. 【0421】 "Natural language processing technology" refers to the technology that analyzes, understands, and generates human language, and is used to generate evaluation results as text. 【0422】 A "notification device" is a device or software system that communicates generated feedback to employees and displays it visually. 【0423】 "Quantification" is the process of calculating a score or indicator to quantitatively evaluate an employee's work performance based on the analyzed data. 【0424】 This invention is a system that combines an information processing device, an operating terminal, a computing device, and a notification device in order to objectively evaluate employee performance. Specific embodiments are described below. 【0425】 First, the server functions as an information processing device, utilizing APIs from various sources to collect job-related information for individual tasks. This includes retrieving data from project management tools and work time tracking systems. The hardware consists of a standard server computer, and the software is a program (e.g., a Python script) for handling API calls. 【0426】 Next, the terminal provides an operating interface to the administrator, enabling the setting of evaluation criteria. Through this interface, the administrator can adjust the importance of each evaluation criterion based on the organization's evaluation policy. The interface is implemented using a web-based GUI (using JavaScript and HTML5) to provide an intuitive user experience. 【0427】 The server then acts as a computing device, analyzing the acquired data. It utilizes machine learning models (e.g., scikit-learn or TensorFlow) to quantify job information based on pre-defined evaluation criteria. This enables data-driven scoring, allowing for more objective evaluations. 【0428】 Furthermore, the server uses natural language processing techniques to generate evaluation results as text. Natural language processing libraries (such as NLTK and GPT models) are used in this process. For example, feedback such as "The time efficiency was very high" is generated. 【0429】 Finally, the terminal acts as a notification device, transmitting the generated feedback to employees. This feedback is provided to each employee through email notifications and display on the system's dashboard. 【0430】 As a concrete example, if employee A completes a high-quality project in a short period of time, the system automatically collects the project completion data. For example, by entering a prompt such as, "Generate a fair evaluation and feedback based on employee A's work data," the server executes the corresponding evaluation process. In this way, this invention realizes an efficient and fair work evaluation process. 【0431】 The flow of the specific processing in Example 1 will be explained using Figure 11. 【0432】 Step 1: 【0433】 The server begins collecting job information. Input data comes from project management tools and work time tracking systems via APIs. The server periodically retrieves this data and stores it in a database. By using API calls to aggregate project task progress and completed work time data, and organizing and storing it in a storage system, the server transforms large amounts of data into a manageable format. 【0434】 Step 2: 【0435】 The terminal provides an interface for administrators to log in and set evaluation criteria. Input in this step is the administrator's instructions or selections, and output is the weighting of evaluation criteria and specific evaluation items. The administrator, as a user, operates the GUI on the terminal and inputs numerical values ​​for the importance of evaluation items such as "quality of deliverables," "achievement level," and "contribution to the team." These values ​​are sent to the server and stored as guidelines for evaluation. 【0436】 Step 3: 【0437】 The server performs data analysis based on the configured evaluation criteria. Input includes job information collected in Step 1 and the evaluation criteria set in Step 2. The server uses a machine learning model to analyze the job information and quantify each employee's score. For example, it might use the scikit-learn library in Python to analyze the data and use a learning algorithm that references historical data to quantitatively evaluate individual job performance. 【0438】 Step 4: 【0439】 The server generates feedback based on the analyzed data. The input is the scores and evaluation results obtained in step 3, and the output is a feedback message directed at each employee. Utilizing natural language processing libraries (e.g., NLTK and GPT models), the generated feedback includes both positive evaluations and points for improvement. Specifically, by transcribing each score into text, the evaluation content for each employee is clearly communicated. 【0440】 Step 5: 【0441】 The terminal notifies employees of the generated feedback. The input is the feedback text generated in step 4, and the output is displayed via email or on the company's internal system dashboard. Employees, as users, can receive timely feedback through the terminal, allowing them to review their work and consider improvement measures for the next evaluation. 【0442】 (Application Example 1) 【0443】 Next, we will explain Application Example 1. In the following explanation, 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." 【0444】 To achieve efficient operational management of work equipment in factories, it is crucial to accurately and quickly evaluate the operational performance of each piece of equipment and identify areas for improvement. However, human evaluation is subjective and often lacks consistency. This invention aims to solve this problem and build a system that provides reliable analysis and feedback. 【0445】 The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 1 is realized by the following means. 【0446】 In this invention, the server includes data collection means for collecting operational data of the work device, criteria setting means for setting evaluation criteria, AI analysis means for analyzing and evaluating the collected operational data based on the evaluation criteria, feedback generation means for generating feedback based on the evaluation results, and notification display means for notifying and displaying the feedback to the manager of the work device. This enables objective and reliable evaluation of the work device. 【0447】 "Work equipment" is a general term for machines and equipment designed to perform specific tasks or operations. 【0448】 "Operational data" refers to digital data that includes information about the operating status and performance of the work equipment. 【0449】 "Data acquisition means" refers to technical means for acquiring operational data from a work device and appropriately storing or transmitting it. 【0450】 A "standard setting means" is a technical means for determining and adjusting the standards and conditions used in evaluation. 【0451】 "AI analysis methods" refer to technical means that use artificial intelligence to analyze collected data and perform specific evaluations. 【0452】 A "feedback generation method" is a technical means for creating improvement points and evaluation content based on the results of AI analysis. 【0453】 A "notification display means" is a technical means for communicating generated feedback to relevant parties and displaying it visually. 【0454】 To implement this invention, the server collects operational data in real time through sensors attached to work equipment within the factory. This data collection utilizes a connection device and communication network that aggregates information from each sensor. The data is centrally managed and stored in a central database for processing. 【0455】 The server provides an interface that factory managers can operate as a means of setting standards, where evaluation criteria such as work efficiency and quality indicators can be set. Through this interface, the weighting of the standards can be adjusted, enabling flexible evaluations that align with the factory's production policies. 【0456】 As an AI analysis tool, the server uses machine learning libraries such as TensorFlow to analyze the collected operational data. The AI ​​model learns from past data and calculates a score to evaluate the efficiency of each work device. This allows for understanding performance trends and identifying areas where individual devices need improvement. 【0457】 As a means of generating feedback, the server utilizes natural language processing technology to generate feedback based on the analysis results. The generated feedback is written in a way that is specific and practical for the administrator of the work equipment. 【0458】 Finally, as a means of displaying notifications, the server displays feedback on the administrator's terminal. Administrators can be notified via dashboards or email notifications and encouraged to take corrective action. For example, if a device is found to have good work efficiency but inconsistent quality, the feedback might state, "It is desirable to consider focused improvements to quality control." An example of a prompt using a generative AI model would be, "Based on the latest performance data of robot A, generate feedback on areas for improvement in work efficiency and product quality." 【0459】 In this way, the present invention promotes efficient operation and continuous improvement in factory settings, contributing to an overall increase in productivity. 【0460】 The flow of a specific process in Application Example 1 will be explained using Figure 12. 【0461】 Step 1: 【0462】 The server collects operational data from sensors on work equipment installed in the factory. This collection is performed by receiving the real-time data stream generated by the sensors. The input is the operational parameters from the sensors, and the output is the storage of this data in an organized database. After collection, the data is stored in the database on the server and used for subsequent processing. 【0463】 Step 2: 【0464】 The terminal (factory administrator's console) inputs evaluation criteria through a criteria setting interface. The administrator adjusts the weighting as needed, such as for work efficiency and quality indicators. The input is the evaluation criteria set by the administrator, and the output is the set of criteria used by the server for evaluation. The specific actions performed by the terminal are providing a setting form and registering the criteria in the database. 【0465】 Step 3: 【0466】 The server evaluates the collected motion data using AI analysis tools. The AI ​​model incorporates pre-generated AI model technology for analysis, and calculates a performance score based on the input motion data. The input consists of motion data and evaluation criteria, and the output is the evaluation score for each work device. The server performs data processing using the TensorFlow library. 【0467】 Step 4: 【0468】 The server generates feedback based on the AI ​​analysis results. Using a generative AI model, it creates specific feedback tailored to individual results. The input is an evaluation score, and the output is a feedback statement including areas for improvement and an assessment of the current situation. Specifically, it utilizes OpenAI's NLP technology to generate feedback that is easy to understand in natural language. 【0469】 Step 5: 【0470】 The server notifies the user of the feedback using notification display methods. In this case, notifications are sent to the terminal via email or dashboard display. The input is the generated feedback, and the output is the user's confirmation of the feedback. The terminal uses front-end technology to display the feedback to the administrator. 【0471】 This process enables efficient management of work equipment and the proposal of improvement measures. 【0472】 Furthermore, an emotion engine that estimates the user's emotions may be incorporated. That is, the identification processing unit 290 may use the emotion identification model 59 to estimate the user's emotions and perform identification processing using the user's emotions. 【0473】 This invention is an evaluation system for enhancing the assessment of employees' work performance, and further improves the evaluation process by incorporating an emotion engine. This system objectively evaluates employees' work data and optimizes the quality of feedback by considering the user's emotional state. 【0474】 First, the server executes a process to collect employee work data. It uses APIs to retrieve information such as the number of completed projects, working hours, and the number of errors in deliverables from project management tools and time management systems, and stores it in a database. 【0475】 Next, the terminal provides an interface for administrators to set evaluation criteria. Through this interface, the administrator (user) weights the criteria and customizes them according to organizational policies. This configuration information is also stored on the server and used during the evaluation process. 【0476】 The server uses AI analysis tools for performance evaluations. It analyzes collected work data based on evaluation criteria and performs scoring using an AI model. During this process, the AI ​​learns from past data to improve the accuracy of the evaluations. Furthermore, a key feature of this system is the inclusion of an emotion engine, which collects and utilizes user emotions regarding past feedback, in addition to user evaluations. 【0477】 Next, the server generates feedback based on the scoring results and the user's emotional information obtained from the emotion engine. The feedback generation mechanism utilizes natural language processing technology to create feedback text that takes emotional information into account. The feedback includes evaluation points and specific improvement suggestions, but the emotion engine analyzes the user's current emotions and expresses the feedback in an appropriate tone, making it more readily accepted. 【0478】 Finally, the terminal notifies the employee (user) of the generated feedback. The evaluation results are displayed via email and on the system's dashboard, allowing the user to review their own evaluation and feedback. A key feature is that, thanks to the built-in emotion engine, the evaluation is presented not merely as a numerical value, but in a way that is emotionally relatable to the user. 【0479】 For example, if employee B experiences some difficulties in completing a new task but ultimately submits an excellent deliverable, this data is collected by the system. According to the evaluation criteria for "effort" and "deliverable quality" set by the manager, the AI ​​scores employee B highly. Simultaneously, the emotion engine selects an appropriate expression based on employee B's responses to past feedback and provides gentle, explanatory feedback stating, "The effort and results you demonstrated through this task are extremely valuable." 【0480】 This system enables performance evaluation while maintaining employee motivation, ultimately contributing to improved productivity across the entire organization. 【0481】 The following describes the processing flow. 【0482】 Step 1: 【0483】 The server collects employee work data. Specifically, it connects to APIs of project management tools and time management systems to collect project progress, work hours, and deliverable quality indicators, and systematically stores this data in a database. 【0484】 Step 2: 【0485】 The device displays an evaluation criteria setting interface for administrators. Administrators, acting as users, set the weighting of each evaluation criterion, such as "quality of deliverables," "goal achievement rate," and "team contribution," using drag-and-drop or sliders, based on the organization's policies. The settings are saved on the server. 【0486】 Step 3: 【0487】 The server begins analyzing the collected business data using AI analysis tools. The AI ​​model analyzes the data based on established evaluation criteria and scores each employee. At this time, the AI ​​model learns from past evaluation data to improve its accuracy and evaluates each employee's contribution from multiple perspectives. 【0488】 Step 4: 【0489】 The server operates an emotion engine, collecting emotion data relevant to the current performance evaluation while referencing the user's past feedback responses. Emotion data is inferred from the history of how the user received feedback. 【0490】 Step 5: 【0491】 The server generates feedback based on AI analysis results and emotion engine data. The feedback generation method utilizes natural language processing to create emotionally sensitive feedback messages. This feedback includes positive evaluations and specific suggestions for improvement, and its expression reflects the user's emotional state. 【0492】 Step 6: 【0493】 The device notifies the employee (user) of the feedback, and the feedback content is displayed visually through a dashboard or email. Employees can review their evaluation and feedback in detail and receive feedback to improve their work. This approach makes the feedback more emotionally receptive, positively impacting user response and motivation. 【0494】 (Example 2) 【0495】 Next, we will describe Example 2. 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." 【0496】 Traditional employee evaluation systems primarily focus on numerically assessing work performance, resulting in feedback that doesn't adequately consider the feelings and reactions of individual users. Consequently, feedback can sometimes have an inappropriate tone or content for employees, potentially reducing their acceptance of the evaluation results. Furthermore, the failure to utilize responses to past feedback meant that similar problems were likely to recur. 【0497】 The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 2 is realized by the following means. 【0498】 In this invention, the server includes an information gathering means for collecting business information, a criteria setting means for setting evaluation criteria, an artificial intelligence analysis means for analyzing and quantifying the collected business information based on the criteria, an information generation means for generating information based on the quantification results and past feedback, and a notification display means for notifying and displaying the information to the user. This makes it possible to generate feedback that takes the user's emotions into consideration and to provide evaluation results that are highly acceptable. 【0499】 "Business information" refers to data related to an employee's work, including quantifiable data such as the number of completed projects, working hours, and the number of errors in deliverables. 【0500】 "Information gathering means" refers to the processes and functions used to acquire business information from external systems and tools. 【0501】 "Means of setting standards" refers to interfaces and functions for defining evaluation criteria and adjusting them based on organizational policies. 【0502】 "Artificial intelligence analysis means" refers to an algorithm or system that analyzes and quantifies collected business information. 【0503】 "Information generation means" refers to processes and functions that generate new information based on quantified results and past feedback. 【0504】 "Notification display means" refers to a function that informs the user of generated information and displays it visually. 【0505】 This system aims to enhance employee performance evaluations by incorporating emotional factors. Its implementation requires the coordinated operation of servers, terminals, and users. 【0506】 First, the server will acquire business information via APIs from project management tools and time management systems as a means of information gathering. Specifically, it will collect data such as the number of completed projects, working hours, and the number of errors in deliverables in real time or periodically, and store it in a database. The software used within the server is expected to include data analysis libraries for Python and Java. 【0507】 Next, evaluation criteria are set via a terminal. The administrator, acting as the user, inputs the evaluation criteria and assigns weights through an interface displayed on the terminal. The terminal often uses a browser-based GUI tool, typically a web application based on HTML / CSS / JavaScript. The set criteria are sent to the server and stored in a database. 【0508】 For evaluation, the server uses artificial intelligence analysis tools. Based on the collected business information, the data is analyzed and quantified according to evaluation criteria. This analysis utilizes a generative AI model, and data scoring is performed using machine learning libraries in Python and R. To improve the accuracy of the analysis, the AI ​​model is continuously trained based on past evaluation history. 【0509】 Furthermore, in generating feedback, the server utilizes an emotion engine to leverage user emotion data from past feedback. Based on the obtained numerical results and emotion data, natural language processing techniques are used to generate feedback text in a format that is easily accepted by the user. 【0510】 Finally, the terminal notifies the employee (user) of the generated feedback. In this process, the feedback is sent via email or displayed on the system dashboard. Employees can review the feedback and use it to improve their work. 【0511】 As a concrete example, if employee B overcomes difficulties and submits excellent results, the server generates a text prompt in the form of "Generate feedback on employee B's work. Please consider past response data and use language that evaluates effort and achievement," which is input into an AI model to generate an emotionally sensitive feedback message. This allows employee B to emotionally accept the evaluation and increases their motivation for future tasks. 【0512】 The flow of the specific processing in Example 2 will be explained using Figure 13. 【0513】 Step 1: 【0514】 The server collects business information using data gathering tools. Input data includes data obtained from APIs of project management tools and time management systems. Based on this, the server retrieves data such as the number of completed projects, working hours, and the number of errors in deliverables. The server then stores this data in a database, preparing it for any necessary analysis. 【0515】 Step 2: 【0516】 The terminal provides a means for setting evaluation criteria, and the administrator, as the user, sets the evaluation criteria. Inputs include various evaluation criteria and their weights, specified by the administrator using the interface. These can be visually adjusted on the terminal using sliders and checkboxes. Output is the set criteria information, which is sent to the server and stored in the database. 【0517】 Step 3: 【0518】 The server uses artificial intelligence analysis tools to analyze and score business information. The input consists of collected business information and evaluation criteria set in step 2. The AI ​​model analyzes the data based on this information and quantifies employee performance. The output is a scoring result, which is then used in the next feedback process. 【0519】 Step 4: 【0520】 The server uses an emotion engine to collect and analyze emotional information about the user's past feedback. The input includes past feedback content and the user's response to it. The server analyzes this and accumulates it as an emotion information database. The output serves as material for generating feedback that incorporates emotional elements. 【0521】 Step 5: 【0522】 The server uses a feedback generation mechanism to generate feedback. The input consists of scoring results and collected sentiment information. The server utilizes natural language processing techniques to construct feedback sentences that are easily accepted by the user. As output, a sentiment-conscious feedback sentence is generated. 【0523】 Step 6: 【0524】 The terminal notifies the employee (user) of the generated feedback. The input consists of the generated feedback text and the user's contact information. The terminal then performs actions such as sending the notification via email or displaying it on a dashboard within the system. As an output, the user can review and accept the evaluation. 【0525】 (Application Example 2) 【0526】 Next, we will explain Application Example 2. In the following explanation, 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." 【0527】 There is a need for a system that efficiently and accurately evaluates the operation of machinery in industry and provides appropriate feedback to managers. However, conventional systems have shortcomings in collecting and analyzing machine operation data and are unable to provide feedback that takes into account emotions and tone. This makes it difficult for managers to take appropriate corrective actions. 【0528】 The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means. 【0529】 In this invention, the server includes information gathering means for collecting operational data of business machines, evaluation criteria setting means for setting evaluation criteria, and artificial intelligence analysis means for analyzing the collected operational data based on the evaluation criteria and performing scoring. This makes it possible to efficiently and accurately evaluate the operation of machines and generate and provide feedback that takes emotions into account to administrators. 【0530】 "Business machinery" is a general term for devices and systems that automatically perform specific tasks in industry. 【0531】 "Operational data" refers to a collection of information generated when a machine performs a task, including working time, error rate, and the quality of the finished product. 【0532】 "Information gathering means" refers to methods and technologies for acquiring operational data from business machinery, and includes the use of sensors and network interfaces. 【0533】 "Evaluation criteria" are settings that define indicators and standards for evaluating the operation of business machinery, and include quality, efficiency, error rate, etc. 【0534】 "Evaluation criteria setting means" refers to a function for adjusting and setting evaluation criteria for business machinery based on the organization's policies. 【0535】 "Artificial intelligence analysis means" refers to a technology that automatically analyzes the performance of equipment and generates a score based on operational data, using machine learning and data mining techniques. 【0536】 A "feedback generation method" refers to a method or technology for generating appropriate feedback content from scoring results and emotional information and providing it to an administrator. 【0537】 "Notification display means" refers to devices or software that communicate generated feedback to administrators for their review, and includes methods such as email sending and dashboard display. 【0538】 The system for realizing this invention combines multiple means to collect operational data from business machines and perform evaluations based on that data. In the overall process, a server acts as the central point for collecting, analyzing, generating feedback on, and notifying the results of the information. 【0539】 The server first collects operational data from sensors attached to each machine. This information is stored in a cloud database such as AWS RDS. The server then analyzes this data using Python, pandas, and scikit-learn, and scores it based on evaluation criteria. Furthermore, an artificial intelligence model learns from past data through machine learning libraries such as TensorFlow, improving the accuracy of the analysis. 【0540】 In generating feedback, the server uses tools such as the Google NLP API to produce feedback in a tone that is easily accepted by administrators. During this process, sentiment analysis is performed based on past response data to ensure that the generated feedback is appropriate for organizational policies and individual circumstances. 【0541】 Ultimately, the server sends the generated feedback to the administrator via a notification display mechanism. The administrator can then review the evaluation results using a web dashboard built with React.js and take necessary administrative measures. The following example prompt is effective for generating feedback: "Based on Robot A's work data, please use the emotion engine to create feedback statements regarding time efficiency and quality improvement." 【0542】 The flow of a specific process in Application Example 2 will be explained using Figure 14. 【0543】 Step 1: 【0544】 The server acquires operational data from the business machinery. Data from sensors is collected in a cloud database such as AWS RDS, and information about the operation is stored. The input is real-time data obtained from the sensors, and the output is structured data stored in the database. 【0545】 Step 2: 【0546】 The server processes the collected data using Python's pandas library. It removes unnecessary data, extracts only the essential parts, and formats them. The input is the raw data extracted from the database, and the output is cleaned up and formatted for analysis. 【0547】 Step 3: 【0548】 The server uses scikit-learn or TensorFlow to input data into a machine learning model and score its performance. In this process, the AI ​​model calculates performance evaluation metrics based on the input data. The input is formatted data, and the output is the performance score for each machine. 【0549】 Step 4: 【0550】 The server utilizes the Google NLP API to generate feedback. It uses the obtained behavioral scores and past feedback from administrators as data to create easy-to-understand feedback in natural language. The input is the score and past sentiment data, and the output is a feedback text that is easy for administrators to understand. 【0551】 Step 5: 【0552】 The server generates feedback and sends it to the administrator using a notification display mechanism. Here, the results are visualized using a web dashboard built with React.js. The input is the generated feedback text, and the output is the content displayed on the dashboard viewed by the administrator. 【0553】 The specific processing unit 290 transmits the result of the specific processing to the headset terminal 314. In the headset terminal 314, the control unit 46A causes the speaker 240 and display 343 to output the result of the specific processing. The microphone 238 acquires audio indicating user input for the result of the specific processing. The control unit 46A transmits the audio data indicating user input acquired by the microphone 238 to the data processing unit 12. In the data processing unit 12, the specific processing unit 290 acquires the audio data. 【0554】 Data generation model 58 is a type of so-called generative AI (Artificial Intelligence). One example of data generation model 58 is ChatGPT (Internet search<URL: https: / / openai.com / blog / chatgpt> ), Gemini (Internet search) <url: https: gemini.google.com ?hl="ja">Examples of generative AI include the following. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 is input with prompts containing instructions, and with inference data such as audio data representing speech, text data representing text, and image data representing images. The data generation model 58 infers from the input inference data according to the instructions indicated by the prompts, and outputs the inference results in data formats such as audio data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization. 【0555】 In the above embodiment, an example was given in which specific processing is performed by the data processing device 12, but the technology of this disclosure is not limited thereto, and specific processing may also be performed by the headset terminal 314. 【0556】 [Fourth Embodiment] 【0557】 Figure 7 shows an example of the configuration of the data processing system 410 according to the fourth embodiment. 【0558】 As shown in Figure 7, the 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. 【0559】 The data processing device 12 comprises a computer 22, a database 24, and a communication interface 26. The computer 22 is an example of a "computer" related to the technology of this disclosure. The computer 22 comprises a processor 28, RAM 30, and storage 32. The processor 28, RAM 30, and storage 32 are connected to a bus 34. The database 24 and the communication interface 26 are also connected to the bus 34. The communication interface 26 is connected to a network 54. An example of the network 54 is a WAN (Wide Area Network) and / or a LAN (Local Area Network). 【0560】 The robot 414 includes a computer 36, a microphone 238, a speaker 240, a camera 42, a communication interface 44, and a controlled object 443. The computer 36 includes a processor 46, RAM 48, and storage 50. The processor 46, RAM 48, and storage 50 are connected to a bus 52. The microphone 238, speaker 240, camera 42, and controlled object 443 are also connected to the bus 52. 【0561】 The microphone 238 receives voice signals from the user 20 and receives instructions from the user 20. The microphone 238 captures the voice signals from the user 20, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio according to the instructions from the processor 46. 【0562】 Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an image sensor such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, and captures images of the area around the user 20 (for example, an imaging range defined by a field of view equivalent to the width of a typical healthy person's field of vision). 【0563】 Communication interface 44 is connected to network 54. Communication interfaces 44 and 26 are responsible for the exchange of various information between processor 46 and processor 28 via network 54. The exchange of various information between processor 46 and processor 28 using communication interfaces 44 and 26 is performed in a secure manner. 【0564】 The controlled object 443 includes a display device, LEDs in the eyes, and motors that drive 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 robot 414's emotions can be expressed by controlling these motors. Furthermore, the robot 414's facial expressions can also be expressed by controlling the illumination state of the LEDs in its eyes. 【0565】 Figure 8 shows an example of the main functions of the data processing device 12 and the robot 414. As shown in Figure 8, the data processing device 12 performs specific processing using the processor 28. The storage 32 stores the specific processing program 56. 【0566】 The specific processing program 56 is an example of a "program" relating to the technology of this 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. 【0567】 The storage 32 stores the data generation model 58 and the emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290. 【0568】 In robot 414, the processor 46 performs the reception output processing. The storage 50 stores the reception output program 60. 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 processing is realized by the processor 46 operating as a control unit 46A according to the reception output program 60 executed on the RAM 48. 【0569】 Next, the specific processing performed by the specific processing unit 290 of the data processing device 12 will be described. In the following description, the data processing device 12 will be referred to as the "server" and the robot 414 as the "terminal". 【0570】 This invention provides an evaluation system for objectively and efficiently evaluating employee performance, thereby realizing a fair and transparent evaluation process. This system automates a series of steps, from collecting employee performance data and setting fair evaluation criteria to analyzing and evaluating the data using artificial intelligence technology, and generating and notifying feedback. 【0571】 First, the server collects data related to employees' work on a regular or real-time basis. Data sources include project management tools and work time tracking systems. APIs are used to retrieve necessary information, which is then organized and stored in a database. This data collection method enables the accurate handling of large amounts of data. 【0572】 Next, the terminal provides an interface for administrators, allowing them to set evaluation criteria. This interface makes it easy to adjust the weighting of each evaluation criterion according to organizational policies, and administrators (users) can set the items they consider important, such as "quality of deliverables," "achievement level," and "contribution to the team." 【0573】 Subsequently, the server uses AI analysis tools to analyze the collected business data based on pre-defined evaluation criteria. The AI ​​model learns each employee's activities from past data and calculates a score according to the individual criteria. This improves the accuracy and reliability of the data, enabling a more objective evaluation. 【0574】 Furthermore, the server automatically generates feedback based on the AI's analysis results. This feedback generation method uses natural language processing technology to describe specific evaluation content for each employee, including both positive aspects and areas for improvement. 【0575】 Finally, the terminal notifies employees of the generated feedback, which is then displayed on their client devices. This evaluation result notification utilizes email notifications or a dashboard display within the system. Employees can review their evaluations and use the feedback to improve their work and prepare for their next evaluation. 【0576】 For example, if employee A completes a high-quality project in a short period of time, the system collects the data. Based on the "efficiency" and "quality" standards set by the manager, the AI ​​calculates a high score. As a result, the feedback specifically evaluates the achievement of results in a short period of time, and additional advice such as "Next time, you should also be mindful of your contribution to the team" is added. 【0577】 Thus, the system of the present invention contributes to improving motivation and trust within the organization by automating the entire process and enabling rapid and fair employee evaluations. 【0578】 The following describes the processing flow. 【0579】 Step 1: 【0580】 The server collects data related to employees' work from various systems. Specifically, it connects to data sources such as project management tools and time management systems via APIs to obtain information such as the number of completed projects, working hours, and the number of errors in deliverables, and stores this information in a database. 【0581】 Step 2: 【0582】 The terminal displays an interface for administrators and provides the functionality to set evaluation criteria. Administrators, as users, use the evaluation criteria interface to set priorities and weights for each evaluation criterion, such as "quality of deliverables," "efficiency," and "team contribution." These settings are sent to the server and used for subsequent evaluations. 【0583】 Step 3: 【0584】 The server operates an AI analysis tool based on the collected business data. The AI ​​model analyzes the data based on pre-set evaluation criteria and scores each employee's activities. This makes it possible to objectively evaluate each employee's performance and contributions. The AI ​​model improves its proficiency by referring to past data, thus increasing the accuracy of the analysis results. 【0585】 Step 4: 【0586】 The server generates feedback based on scoring results from AI analysis. The feedback generation system uses natural language processing to create customized feedback messages for individual employees. This feedback includes positive evaluation points and suggestions for improvement. 【0587】 Step 5: 【0588】 The terminal notifies each employee (user) of the generated feedback and evaluation results. The feedback is displayed via email or an on-screen dashboard. Employees can use this information to review their own work performance and work towards improvement. 【0589】 (Example 1) 【0590】 Next, we will describe Example 1. In the following description, the data processing device 12 will be referred to as the "server" and the robot 414 as the "terminal". 【0591】 Traditional systems often relied on subjective evaluation of employee performance, lacking fairness and transparency. Furthermore, the evaluation process was time-consuming and labor-intensive, making rapid feedback difficult. Additionally, limitations in setting evaluation criteria and improving analytical accuracy made it challenging to flexibly adapt to organizational policies. 【0592】 The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 1 is realized by the following means. 【0593】 In this invention, the server includes means for an information processing device to periodically or in real time acquire job information related to individual tasks from various sources; means for an operating terminal to provide an interface for setting evaluation criteria according to the organization's evaluation policy; and means for a computing processing device to analyze and quantify the acquired job information using a machine learning model based on pre-set evaluation criteria. This makes it possible to perform employee job evaluations objectively and efficiently. 【0594】 An "information processing system" is a computer system used to collect and manage data such as job-related information. 【0595】 "Job information related to individual tasks" refers to detailed information about the tasks performed by employees, such as the progress, results, and working hours. 【0596】 "Information sources" refer to data providers for collecting job-related information, including project management tools and work time tracking systems. 【0597】 An "operation terminal" is a device that provides an interface for administrators to access the system and set evaluation criteria. 【0598】 "Evaluation criteria" refer to the indicators and standards used to evaluate an employee's work, and include weighting determined according to the organization's policies. 【0599】 A "processing unit" is a device that uses machine learning models to analyze and quantify data based on acquired job information. 【0600】 A "machine learning model" is an algorithm or mathematical model that learns patterns from data and performs analysis based on new data. 【0601】 "Natural language processing technology" refers to the technology that analyzes, understands, and generates human language, and is used to generate evaluation results as text. 【0602】 A "notification device" is a device or software system that communicates generated feedback to employees and displays it visually. 【0603】 "Quantification" is the process of calculating a score or indicator to quantitatively evaluate an employee's work performance based on the analyzed data. 【0604】 This invention is a system that combines an information processing device, an operating terminal, a computing device, and a notification device in order to objectively evaluate employee performance. Specific embodiments are described below. 【0605】 First, the server functions as an information processing device, utilizing APIs from various sources to collect job-related information for individual tasks. This includes retrieving data from project management tools and work time tracking systems. The hardware consists of a standard server computer, and the software is a program (e.g., a Python script) for handling API calls. 【0606】 Next, the terminal provides an operating interface to the administrator, enabling the setting of evaluation criteria. Through this interface, the administrator can adjust the importance of each evaluation criterion based on the organization's evaluation policy. The interface is implemented using a web-based GUI (using JavaScript and HTML5) to provide an intuitive user experience. 【0607】 The server then acts as a computing device, analyzing the acquired data. It utilizes machine learning models (e.g., scikit-learn or TensorFlow) to quantify job information based on pre-defined evaluation criteria. This enables data-driven scoring, allowing for more objective evaluations. 【0608】 Furthermore, the server uses natural language processing techniques to generate evaluation results as text. Natural language processing libraries (such as NLTK and GPT models) are used in this process. For example, feedback such as "The time efficiency was very high" is generated. 【0609】 Finally, the terminal acts as a notification device, transmitting the generated feedback to employees. This feedback is provided to each employee through email notifications and display on the system's dashboard. 【0610】 As a concrete example, if employee A completes a high-quality project in a short period of time, the system automatically collects the project completion data. For example, by entering a prompt such as, "Generate a fair evaluation and feedback based on employee A's work data," the server executes the corresponding evaluation process. In this way, this invention realizes an efficient and fair work evaluation process. 【0611】 The flow of the specific processing in Example 1 will be explained using Figure 11. 【0612】 Step 1: 【0613】 The server begins collecting job information. Input data comes from project management tools and work time tracking systems via APIs. The server periodically retrieves this data and stores it in a database. By using API calls to aggregate project task progress and completed work time data, and organizing and storing it in a storage system, the server transforms large amounts of data into a manageable format. 【0614】 Step 2: 【0615】 The terminal provides an interface for administrators to log in and set evaluation criteria. Input in this step is the administrator's instructions or selections, and output is the weighting of evaluation criteria and specific evaluation items. The administrator, as a user, operates the GUI on the terminal and inputs numerical values ​​for the importance of evaluation items such as "quality of deliverables," "achievement level," and "contribution to the team." These values ​​are sent to the server and stored as guidelines for evaluation. 【0616】 Step 3: 【0617】 The server performs data analysis based on the configured evaluation criteria. Input includes job information collected in Step 1 and the evaluation criteria set in Step 2. The server uses a machine learning model to analyze the job information and quantify each employee's score. For example, it might use the scikit-learn library in Python to analyze the data and use a learning algorithm that references historical data to quantitatively evaluate individual job performance. 【0618】 Step 4: 【0619】 The server generates feedback based on the analyzed data. The input is the scores and evaluation results obtained in step 3, and the output is a feedback message directed at each employee. Utilizing natural language processing libraries (e.g., NLTK and GPT models), the generated feedback includes both positive evaluations and points for improvement. Specifically, by transcribing each score into text, the evaluation content for each employee is clearly communicated. 【0620】 Step 5: 【0621】 The terminal notifies employees of the generated feedback. The input is the feedback text generated in step 4, and the output is displayed via email or on the company's internal system dashboard. Employees, as users, can receive timely feedback through the terminal, allowing them to review their work and consider improvement measures for the next evaluation. 【0622】 (Application Example 1) 【0623】 Next, we will explain Application Example 1. In the following explanation, the data processing device 12 will be referred to as the "server" and the robot 414 as the "terminal". 【0624】 To achieve efficient operational management of work equipment in factories, it is crucial to accurately and quickly evaluate the operational performance of each piece of equipment and identify areas for improvement. However, human evaluation is subjective and often lacks consistency. This invention aims to solve this problem and build a system that provides reliable analysis and feedback. 【0625】 The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 1 is realized by the following means. 【0626】 In this invention, the server includes data collection means for collecting operational data of the work device, criteria setting means for setting evaluation criteria, AI analysis means for analyzing and evaluating the collected operational data based on the evaluation criteria, feedback generation means for generating feedback based on the evaluation results, and notification display means for notifying and displaying the feedback to the manager of the work device. This enables objective and reliable evaluation of the work device. 【0627】 "Work equipment" is a general term for machines and equipment designed to perform specific tasks or operations. 【0628】 "Operational data" refers to digital data that includes information about the operating status and performance of the work equipment. 【0629】 "Data acquisition means" refers to technical means for acquiring operational data from a work device and appropriately storing or transmitting it. 【0630】 A "standard setting means" is a technical means for determining and adjusting the standards and conditions used in evaluation. 【0631】 "AI analysis methods" refer to technical means that use artificial intelligence to analyze collected data and perform specific evaluations. 【0632】 A "feedback generation method" is a technical means for creating improvement points and evaluation content based on the results of AI analysis. 【0633】 A "notification display means" is a technical means for communicating generated feedback to relevant parties and displaying it visually. 【0634】 To implement this invention, the server collects operational data in real time through sensors attached to work equipment within the factory. This data collection utilizes a connection device and communication network that aggregates information from each sensor. The data is centrally managed and stored in a central database for processing. 【0635】 The server provides an interface that factory managers can operate as a means of setting standards, where evaluation criteria such as work efficiency and quality indicators can be set. Through this interface, the weighting of the standards can be adjusted, enabling flexible evaluations that align with the factory's production policies. 【0636】 As an AI analysis tool, the server uses machine learning libraries such as TensorFlow to analyze the collected operational data. The AI ​​model learns from past data and calculates a score to evaluate the efficiency of each work device. This allows for understanding performance trends and identifying areas where individual devices need improvement. 【0637】 As a means of generating feedback, the server utilizes natural language processing technology to generate feedback based on the analysis results. The generated feedback is written in a way that is specific and practical for the administrator of the work equipment. 【0638】 Finally, as a means of displaying notifications, the server displays feedback on the administrator's terminal. Administrators can be notified via dashboards or email notifications and encouraged to take corrective action. For example, if a device is found to have good work efficiency but inconsistent quality, the feedback might state, "It is desirable to consider focused improvements to quality control." An example of a prompt using a generative AI model would be, "Based on the latest performance data of robot A, generate feedback on areas for improvement in work efficiency and product quality." 【0639】 In this way, the present invention promotes efficient operation and continuous improvement in factory settings, contributing to an overall increase in productivity. 【0640】 The flow of a specific process in Application Example 1 will be explained using Figure 12. 【0641】 Step 1: 【0642】 The server collects operational data from sensors on work equipment installed in the factory. This collection is performed by receiving the real-time data stream generated by the sensors. The input is the operational parameters from the sensors, and the output is the storage of this data in an organized database. After collection, the data is stored in the database on the server and used for subsequent processing. 【0643】 Step 2: 【0644】 The terminal (factory administrator's console) inputs evaluation criteria through a criteria setting interface. The administrator adjusts the weighting as needed, such as for work efficiency and quality indicators. The input is the evaluation criteria set by the administrator, and the output is the set of criteria used by the server for evaluation. The specific actions performed by the terminal are providing a setting form and registering the criteria in the database. 【0645】 Step 3: 【0646】 The server evaluates the collected motion data using AI analysis tools. The AI ​​model incorporates pre-generated AI model technology for analysis, and calculates a performance score based on the input motion data. The input consists of motion data and evaluation criteria, and the output is the evaluation score for each work device. The server performs data processing using the TensorFlow library. 【0647】 Step 4: 【0648】 The server generates feedback based on the AI ​​analysis results. Using a generative AI model, it creates specific feedback tailored to individual results. The input is an evaluation score, and the output is a feedback statement including areas for improvement and an assessment of the current situation. Specifically, it utilizes OpenAI's NLP technology to generate feedback that is easy to understand in natural language. 【0649】 Step 5: 【0650】 The server notifies the user of the feedback using notification display methods. In this case, notifications are sent to the terminal via email or dashboard display. The input is the generated feedback, and the output is the user's confirmation of the feedback. The terminal uses front-end technology to display the feedback to the administrator. 【0651】 This process enables efficient management of work equipment and the proposal of improvement measures. 【0652】 Furthermore, an emotion engine that estimates the user's emotions may be incorporated. That is, the identification processing unit 290 may use the emotion identification model 59 to estimate the user's emotions and perform identification processing using the user's emotions. 【0653】 This invention is an evaluation system for enhancing the assessment of employees' work performance, and further improves the evaluation process by incorporating an emotion engine. This system objectively evaluates employees' work data and optimizes the quality of feedback by considering the user's emotional state. 【0654】 First, the server executes a process to collect employee work data. It uses APIs to retrieve information such as the number of completed projects, working hours, and the number of errors in deliverables from project management tools and time management systems, and stores it in a database. 【0655】 Next, the terminal provides an interface for administrators to set evaluation criteria. Through this interface, the administrator (user) weights the criteria and customizes them according to organizational policies. This configuration information is also stored on the server and used during the evaluation process. 【0656】 The server uses AI analysis tools for performance evaluations. It analyzes collected work data based on evaluation criteria and performs scoring using an AI model. During this process, the AI ​​learns from past data to improve the accuracy of the evaluations. Furthermore, a key feature of this system is the inclusion of an emotion engine, which collects and utilizes user emotions regarding past feedback, in addition to user evaluations. 【0657】 Next, the server generates feedback based on the scoring results and the user's emotional information obtained from the emotion engine. The feedback generation mechanism utilizes natural language processing technology to create feedback text that takes emotional information into account. The feedback includes evaluation points and specific improvement suggestions, but the emotion engine analyzes the user's current emotions and expresses the feedback in an appropriate tone, making it more readily accepted. 【0658】 Finally, the terminal notifies the employee (user) of the generated feedback. The evaluation results are displayed via email and on the system's dashboard, allowing the user to review their own evaluation and feedback. A key feature is that, thanks to the built-in emotion engine, the evaluation is presented not merely as a numerical value, but in a way that is emotionally relatable to the user. 【0659】 For example, if employee B experiences some difficulties in completing a new task but ultimately submits an excellent deliverable, this data is collected by the system. According to the evaluation criteria for "effort" and "deliverable quality" set by the manager, the AI ​​scores employee B highly. Simultaneously, the emotion engine selects an appropriate expression based on employee B's responses to past feedback and provides gentle, explanatory feedback stating, "The effort and results you demonstrated through this task are extremely valuable." 【0660】 This system enables performance evaluation while maintaining employee motivation, ultimately contributing to improved productivity across the entire organization. 【0661】 The following describes the processing flow. 【0662】 Step 1: 【0663】 The server collects employee work data. Specifically, it connects to APIs of project management tools and time management systems to collect project progress, work hours, and deliverable quality indicators, and systematically stores this data in a database. 【0664】 Step 2: 【0665】 The device displays an evaluation criteria setting interface for administrators. Administrators, acting as users, set the weighting of each evaluation criterion, such as "quality of deliverables," "goal achievement rate," and "team contribution," using drag-and-drop or sliders, based on the organization's policies. The settings are saved on the server. 【0666】 Step 3: 【0667】 The server begins analyzing the collected business data using AI analysis tools. The AI ​​model analyzes the data based on established evaluation criteria and scores each employee. At this time, the AI ​​model learns from past evaluation data to improve its accuracy and evaluates each employee's contribution from multiple perspectives. 【0668】 Step 4: 【0669】 The server operates an emotion engine, collecting emotion data relevant to the current performance evaluation while referencing the user's past feedback responses. Emotion data is inferred from the history of how the user received feedback. 【0670】 Step 5: 【0671】 The server generates feedback based on AI analysis results and emotion engine data. The feedback generation method utilizes natural language processing to create emotionally sensitive feedback messages. This feedback includes positive evaluations and specific suggestions for improvement, and its expression reflects the user's emotional state. 【0672】 Step 6: 【0673】 The device notifies the employee (user) of the feedback, and the feedback content is displayed visually through a dashboard or email. Employees can review their evaluation and feedback in detail and receive feedback to improve their work. This approach makes the feedback more emotionally receptive, positively impacting user response and motivation. 【0674】 (Example 2) 【0675】 Next, we will describe Example 2. In the following description, the data processing device 12 will be referred to as the "server" and the robot 414 as the "terminal". 【0676】 Traditional employee evaluation systems primarily focus on numerically assessing work performance, resulting in feedback that doesn't adequately consider the feelings and reactions of individual users. Consequently, feedback can sometimes have an inappropriate tone or content for employees, potentially reducing their acceptance of the evaluation results. Furthermore, the failure to utilize responses to past feedback meant that similar problems were likely to recur. 【0677】 The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 2 is realized by the following means. 【0678】 In this invention, the server includes an information gathering means for collecting business information, a criteria setting means for setting evaluation criteria, an artificial intelligence analysis means for analyzing and quantifying the collected business information based on the criteria, an information generation means for generating information based on the quantification results and past feedback, and a notification display means for notifying and displaying the information to the user. This makes it possible to generate feedback that takes the user's emotions into consideration and to provide evaluation results that are highly acceptable. 【0679】 "Business information" refers to data related to an employee's work, including quantifiable data such as the number of completed projects, working hours, and the number of errors in deliverables. 【0680】 "Information gathering means" refers to the processes and functions used to acquire business information from external systems and tools. 【0681】 "Means of setting standards" refers to interfaces and functions for defining evaluation criteria and adjusting them based on organizational policies. 【0682】 "Artificial intelligence analysis means" refers to an algorithm or system that analyzes and quantifies collected business information. 【0683】 "Information generation means" refers to processes and functions that generate new information based on quantified results and past feedback. 【0684】 "Notification display means" refers to a function that informs the user of generated information and displays it visually. 【0685】 This system aims to enhance employee performance evaluations by incorporating emotional factors. Its implementation requires the coordinated operation of servers, terminals, and users. 【0686】 First, the server will acquire business information via APIs from project management tools and time management systems as a means of information gathering. Specifically, it will collect data such as the number of completed projects, working hours, and the number of errors in deliverables in real time or periodically, and store it in a database. The software used within the server is expected to include data analysis libraries for Python and Java. 【0687】 Next, evaluation criteria are set via a terminal. The administrator, acting as the user, inputs the evaluation criteria and assigns weights through an interface displayed on the terminal. The terminal often uses a browser-based GUI tool, typically a web application based on HTML / CSS / JavaScript. The set criteria are sent to the server and stored in a database. 【0688】 For evaluation, the server uses artificial intelligence analysis tools. Based on the collected business information, the data is analyzed and quantified according to evaluation criteria. This analysis utilizes a generative AI model, and data scoring is performed using machine learning libraries in Python and R. To improve the accuracy of the analysis, the AI ​​model is continuously trained based on past evaluation history. 【0689】 Furthermore, in generating feedback, the server utilizes an emotion engine to leverage user emotion data from past feedback. Based on the obtained numerical results and emotion data, natural language processing techniques are used to generate feedback text in a format that is easily accepted by the user. 【0690】 Finally, the terminal notifies the employee (user) of the generated feedback. In this process, the feedback is sent via email or displayed on the system dashboard. Employees can review the feedback and use it to improve their work. 【0691】 As a concrete example, if employee B overcomes difficulties and submits excellent results, the server generates a text prompt in the form of "Generate feedback on employee B's work. Please consider past response data and use language that evaluates effort and achievement," which is input into an AI model to generate an emotionally sensitive feedback message. This allows employee B to emotionally accept the evaluation and increases their motivation for future tasks. 【0692】 The flow of the specific processing in Example 2 will be explained using Figure 13. 【0693】 Step 1: 【0694】 The server collects business information using data gathering tools. Input data includes data obtained from APIs of project management tools and time management systems. Based on this, the server retrieves data such as the number of completed projects, working hours, and the number of errors in deliverables. The server then stores this data in a database, preparing it for any necessary analysis. 【0695】 Step 2: 【0696】 The terminal provides a means for setting evaluation criteria, and the administrator, as the user, sets the evaluation criteria. Inputs include various evaluation criteria and their weights, specified by the administrator using the interface. These can be visually adjusted on the terminal using sliders and checkboxes. Output is the set criteria information, which is sent to the server and stored in the database. 【0697】 Step 3: 【0698】 The server uses artificial intelligence analysis tools to analyze and score business information. The input consists of collected business information and evaluation criteria set in step 2. The AI ​​model analyzes the data based on this information and quantifies employee performance. The output is a scoring result, which is then used in the next feedback process. 【0699】 Step 4: 【0700】 The server uses an emotion engine to collect and analyze emotional information about the user's past feedback. The input includes past feedback content and the user's response to it. The server analyzes this and accumulates it as an emotion information database. The output serves as material for generating feedback that incorporates emotional elements. 【0701】 Step 5: 【0702】 The server uses a feedback generation mechanism to generate feedback. The input consists of scoring results and collected sentiment information. The server utilizes natural language processing techniques to construct feedback sentences that are easily accepted by the user. As output, a sentiment-conscious feedback sentence is generated. 【0703】 Step 6: 【0704】 The terminal notifies the employee (user) of the generated feedback. The input consists of the generated feedback text and the user's contact information. The terminal then performs actions such as sending the notification via email or displaying it on a dashboard within the system. As an output, the user can review and accept the evaluation. 【0705】 (Application Example 2) 【0706】 Next, we will explain application example 2. In the following explanation, the data processing device 12 will be referred to as the "server" and the robot 414 as the "terminal". 【0707】 There is a need for a system that efficiently and accurately evaluates the operation of machinery in industry and provides appropriate feedback to managers. However, conventional systems have shortcomings in collecting and analyzing machine operation data and are unable to provide feedback that takes into account emotions and tone. This makes it difficult for managers to take appropriate corrective actions. 【0708】 The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means. 【0709】 In this invention, the server includes information gathering means for collecting operational data of business machines, evaluation criteria setting means for setting evaluation criteria, and artificial intelligence analysis means for analyzing the collected operational data based on the evaluation criteria and performing scoring. This makes it possible to efficiently and accurately evaluate the operation of machines and generate and provide feedback that takes emotions into account to administrators. 【0710】 "Business machinery" is a general term for devices and systems that automatically perform specific tasks in industry. 【0711】 "Operational data" refers to a collection of information generated when a machine performs a task, including working time, error rate, and the quality of the finished product. 【0712】 "Information gathering means" refers to methods and technologies for acquiring operational data from business machinery, and includes the use of sensors and network interfaces. 【0713】 "Evaluation criteria" are settings that define indicators and standards for evaluating the operation of business machinery, and include quality, efficiency, error rate, etc. 【0714】 "Evaluation criteria setting means" refers to a function for adjusting and setting evaluation criteria for business machinery based on the organization's policies. 【0715】 "Artificial intelligence analysis means" refers to a technology that automatically analyzes the performance of equipment and generates a score based on operational data, using machine learning and data mining techniques. 【0716】 A "feedback generation method" refers to a method or technology for generating appropriate feedback content from scoring results and emotional information and providing it to an administrator. 【0717】 "Notification display means" refers to devices or software that communicate generated feedback to administrators for their review, and includes methods such as email sending and dashboard display. 【0718】 The system for realizing this invention combines multiple means to collect operational data from business machines and perform evaluations based on that data. In the overall process, a server acts as the central point for collecting, analyzing, generating feedback on, and notifying the results of the information. 【0719】 The server first collects operational data from sensors attached to each machine. This information is stored in a cloud database such as AWS RDS. The server then analyzes this data using Python, pandas, and scikit-learn, and scores it based on evaluation criteria. Furthermore, an artificial intelligence model learns from past data through machine learning libraries such as TensorFlow, improving the accuracy of the analysis. 【0720】 In generating feedback, the server uses tools such as the Google NLP API to produce feedback in a tone that is easily accepted by administrators. During this process, sentiment analysis is performed based on past response data to ensure that the generated feedback is appropriate for organizational policies and individual circumstances. 【0721】 Ultimately, the server sends the generated feedback to the administrator via a notification display mechanism. The administrator can then review the evaluation results using a web dashboard built with React.js and take necessary administrative measures. The following example prompt is effective for generating feedback: "Based on Robot A's work data, please use the emotion engine to create feedback statements regarding time efficiency and quality improvement." 【0722】 The flow of a specific process in Application Example 2 will be explained using Figure 14. 【0723】 Step 1: 【0724】 The server acquires operational data from the business machinery. Data from sensors is collected in a cloud database such as AWS RDS, and information about the operation is stored. The input is real-time data obtained from the sensors, and the output is structured data stored in the database. 【0725】 Step 2: 【0726】 The server processes the collected data using Python's pandas library. It removes unnecessary data, extracts only the essential parts, and formats them. The input is the raw data extracted from the database, and the output is cleaned up and formatted for analysis. 【0727】 Step 3: 【0728】 The server uses scikit-learn or TensorFlow to input data into a machine learning model and score its performance. In this process, the AI ​​model calculates performance evaluation metrics based on the input data. The input is formatted data, and the output is the performance score for each machine. 【0729】 Step 4: 【0730】 The server utilizes the Google NLP API to generate feedback. It uses the obtained behavioral scores and past feedback from administrators as data to create easy-to-understand feedback in natural language. The input is the score and past sentiment data, and the output is a feedback text that is easy for administrators to understand. 【0731】 Step 5: 【0732】 The server generates feedback and sends it to the administrator using a notification display mechanism. Here, the results are visualized using a web dashboard built with React.js. The input is the generated feedback text, and the output is the content displayed on the dashboard viewed by the administrator. 【0733】 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 controlled object 443 to output the result of the specific processing. The microphone 238 acquires audio indicating user input for the result of the specific processing. The control unit 46A transmits the audio data indicating user input acquired by the microphone 238 to the data processing unit 12. In the data processing unit 12, the specific processing unit 290 acquires the audio data. 【0734】 Data generation model 58 is a type of so-called generative AI (Artificial Intelligence). One example of data generation model 58 is ChatGPT (Internet search<URL: https: / / openai.com / blog / chatgpt> ), Gemini (Internet search) <url: https: gemini.google.com ?hl="ja">Examples of generative AI include the following. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 is input with prompts containing instructions, and with inference data such as audio data representing speech, text data representing text, and image data representing images. The data generation model 58 infers from the input inference data according to the instructions indicated by the prompts, and outputs the inference results in data formats such as audio data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization. 【0735】 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 this disclosure is not limited thereto, and the specific processing may also be performed by the robot 414. 【0736】 Furthermore, the emotion identification model 59, acting 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 a specific mapping, which is an emotion map (see Figure 9). Similarly, the emotion identification model 59 may also determine the robot's emotion, and the identification processing unit 290 may perform identification processing using the robot's emotion. 【0737】 Figure 9 shows an emotion map 400 in which multiple emotions are mapped. In the emotion map 400, emotions are arranged in concentric circles radiating from the center. The closer to the center of the concentric circles, the more primitive the emotions are located. Further out of the concentric circles, emotions representing states and actions arising from mental states are located. Emotion is a concept that includes feelings and mental states. On the left side of the concentric circles, emotions that are generally generated from reactions occurring in the brain are located. On the right side of the concentric circles, emotions that are generally induced by situational judgment are located. Above and below the concentric circles, emotions that are generally generated from reactions occurring in the brain and induced by situational judgment are located. In addition, the emotion of "pleasure" is located on the upper side of the concentric circles, and the emotion of "displeasure" is located on the lower side. Thus, in the emotion map 400, multiple emotions are mapped based on the structure in which emotions arise, and emotions that are likely to occur simultaneously are mapped close together. 【0738】 These emotions are distributed at the 3 o'clock position on the Emotion Map 400, and usually fluctuate between feelings of security and anxiety. In the right half of the Emotion Map 400, situational awareness takes precedence over internal feelings, resulting in a calm impression. 【0739】 The inside of the Emotion Map 400 represents inner thoughts, while the outside represents actions. Therefore, the further you go from the outside of the Emotion Map 400, the more visible (expressed in actions) your emotions become. 【0740】 Here, human emotions are based on various balances, such as posture and blood sugar levels. When these balances deviate from the ideal, it results in discomfort, and when they approach the ideal, it results in pleasure. Similarly, in robots, cars, motorcycles, etc., emotions can be created based on various balances, such as posture and battery level. When these balances deviate from the ideal, it results in discomfort, and when they approach the ideal, it results in pleasure. The emotion map can be generated, for example, based on Dr. Mitsuyoshi's emotion map (Research on a system for analyzing brain physiological signals of speech emotion recognition and emotion, Tokushima University, doctoral dissertation: https: / / ci.nii.ac.jp / naid / 500000375379). The left half of the emotion map contains emotions belonging to a region called "response," where sensation is dominant. The right half of the emotion map contains emotions belonging to a region called "situation," where situational awareness is dominant. 【0741】 The emotion map defines two emotions that promote learning. One is the emotion around the middle of the negative "repentance" and "reflection" on the situation side. In other words, it is 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 the emotion around the positive "desire" on the reaction side. In other words, it is when the robot has positive feelings such as "I want more" or "I want to know more." 【0742】 The emotion identification model 59 inputs user input into a pre-trained neural network, obtains emotion values ​​representing each emotion shown in the emotion map 400, and determines the user's emotion. This neural network is pre-trained based on multiple training data sets, which are combinations of user input and emotion values ​​representing each emotion shown in the emotion map 400. Furthermore, this neural network is trained so that emotions located close together have similar values, as shown in the emotion map 900 in Figure 10. Figure 10 shows an example where multiple emotions such as "reassured," "calm," and "confident" have similar emotion values. 【0743】 The above description primarily focuses on the functions of the data processing device 12 in relation to this disclosure. However, the system related to this disclosure is not necessarily implemented on a server. The system related to this disclosure may be implemented as a general information processing system. This disclosure may be implemented, for example, as a software program that runs on a personal computer or as an application that runs on a smartphone. The method related to this disclosure may be provided to users in SaaS (Software as a Service) format. 【0744】 In the above embodiment, an example was given in which a specific process is performed by a single computer 22. However, the technology of this disclosure is not limited thereto, and a distributed processing of the specific process may be performed by multiple computers, including computer 22. For example, a data generation model 58 may be provided in an external device of the data processing device 12, and the external device may generate data according to the input data. 【0745】 In the above embodiment, an example was given in which the specific processing program 56 is stored in the storage 32, but the technology of this disclosure is not limited thereto. For example, the specific processing program 56 may be stored in a portable, computer-readable, non-temporary storage medium such as a USB (Universal Serial Bus) memory. The specific processing program 56 stored in the non-temporary storage medium is installed in the computer 22 of the data processing device 12. The processor 28 executes specific processing according to the specific processing program 56. 【0746】 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. 【0747】 Furthermore, it is not necessary to store the entirety 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 the entirety of the specific processing program 56 in the storage 32; it is acceptable to store only a portion of the specific processing program 56. 【0748】 The following types of processors can be used as hardware resources to perform specific processing. Examples of processors include a CPU, a general-purpose processor that functions as a hardware resource to perform specific processing by executing software, i.e., a program. Other examples of processors include dedicated electrical circuits, such as FPGAs (Field-Programmable Gate Arrays), PLDs (Programmable Logic Devices), or ASICs (Application Specific Integrated Circuits), which have circuit configurations specifically designed to perform specific processing. All of these processors have built-in or connected memory, and all of them perform specific processing by using memory. 【0749】 The hardware resource that performs a specific process may consist of one of these various processors, or it may consist of 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). Alternatively, the hardware resource that performs a specific process may consist of a single processor. 【0750】 Examples of configurations using a single processor include, firstly, a configuration in which one or more CPUs and software are combined to form a single processor, and this processor functions as a hardware resource that performs a specific process. Secondly, there is a configuration using a processor that realizes the functions of the entire system, including multiple hardware resources that perform a specific process, on a single IC chip, as exemplified by SoCs (System-on-a-chip). In this way, a specific process is realized using one or more of the above types of processors as hardware resources. 【0751】 Furthermore, the hardware structure of these various processors can more specifically utilize electrical circuits that combine circuit elements such as semiconductor devices. Also, the specific processing described above is merely an example. Therefore, it goes without saying that unnecessary steps can be deleted, new steps added, or the processing order rearranged, as long as it does not deviate from the main purpose. 【0752】 The descriptions and illustrations presented above are detailed explanations of the technical aspects of this disclosure and are merely examples of the technical aspects. For example, the above descriptions of the structure, function, operation, and effect are examples of the structure, function, operation, and effect of the technical aspects of this disclosure. Therefore, it goes without saying that you may delete unnecessary parts, add new elements, or replace elements in the descriptions and illustrations presented above, as long as you do not deviate from the essence of the technical aspects of this disclosure. Furthermore, in order to avoid confusion and facilitate understanding of the technical aspects of this disclosure, explanations of common technical knowledge and the like that do not require special explanation to enable the implementation of the technical aspects of this disclosure have been omitted from the descriptions and illustrations presented above. 【0753】 All documents, patent applications, and technical standards described herein are incorporated by reference to the same extent as if each individual document, patent application, and technical standard were specifically and individually noted as being incorporated by reference. 【0754】 The following is further disclosed regarding the embodiments described above. 【0755】 (Claim 1) 【0756】 Data collection methods for collecting employee work data, 【0757】 A means for setting evaluation criteria, 【0758】 An AI analysis tool that analyzes and scores collected business data based on evaluation criteria, 【0759】 A feedback generation means that generates feedback based on the scoring results, 【0760】 A notification display method that notifies and displays feedback to employees, 【0761】 A system that includes this. 【0762】 (Claim 2) 【0763】 The system according to claim 1, wherein the AI ​​analysis means continuously learns using past evaluation history to improve the accuracy of evaluations. 【0764】 (Claim 3) 【0765】 The system according to claim 1, wherein the evaluation criteria setting means allows for adjustment of the importance of each evaluation criterion based on the organization's policies. 【0766】 "Example 1" 【0767】 (Claim 1) 【0768】 The information processing device provides means for acquiring job information related to individual tasks from various sources on a regular or real-time basis, 【0769】 The operating terminal provides a means for setting evaluation criteria in accordance with the organization's evaluation policy, 【0770】 A processing unit analyzes acquired job information using a machine learning model based on pre-set evaluation criteria and quantifies the results. 【0771】 A language processing device provides a means for generating evaluation results as text using natural language processing technology based on the results of analyzing job information, 【0772】 The notification device includes means for transmitting the generated text to individual information terminals and displaying it visually, 【0773】 A system that includes this. 【0774】 (Claim 2) 【0775】 The system according to claim 1, wherein the processing unit continuously performs machine learning based on past analysis results to improve the accuracy of the analysis. 【0776】 (Claim 3) 【0777】 The system according to claim 1, wherein the operating terminal provides an interface for adjusting the importance of evaluation criteria based on the organization's policies. 【0778】 "Application Example 1" 【0779】 (Claim 1) 【0780】 A data collection means for collecting operational data of a work device, 【0781】 A means for setting evaluation criteria, 【0782】 An AI analysis tool that analyzes and evaluates collected motion data based on evaluation criteria, 【0783】 A feedback generation means that generates feedback based on the evaluation results, 【0784】 A notification display means that notifies and displays feedback to the administrator of the work device, 【0785】 A system that includes this. 【0786】 (Claim 2) 【0787】 The system according to claim 1, wherein the AI ​​analysis means continuously learns using past evaluation history to improve the accuracy of evaluations. 【0788】 (Claim 3) 【0789】 The system according to claim 1, wherein the criteria setting means allows for adjustment of the importance of each evaluation criterion based on the organization's guidelines. 【0790】 "Example 2 of combining an emotion engine" 【0791】 (Claim 1) 【0792】 Information gathering methods for collecting business information, 【0793】 A means for setting evaluation criteria, 【0794】 An artificial intelligence analysis tool that analyzes and quantifies collected business information based on standards, 【0795】 Information generation means that generates information based on quantified results and past feedback, 【0796】 A notification display means that notifies and displays information to the user, 【0797】 A system that includes this. 【0798】 (Claim 2) 【0799】 The system according to claim 1, wherein the artificial intelligence analysis means continuously learns using past evaluation history to improve the accuracy of the analysis. 【0800】 (Claim 3) 【0801】 The system according to claim 1, wherein the criteria setting means allows for adjustment of the importance of each evaluation criterion based on the organization's policies. 【0802】 "Application example 2 when combining with an emotional engine" 【0803】 (Claim 1) 【0804】 Information collection means for collecting operational data of business machinery, 【0805】 A means for setting evaluation criteria, 【0806】 An artificial intelligence analysis tool that analyzes collected motion data based on evaluation criteria and performs scoring, 【0807】 A feedback generation means that generates feedback based on scoring results and emotional information, 【0808】 A notification display means that notifies and displays the generated feedback to the administrator, 【0809】 A system that includes this. 【0810】 (Claim 2) 【0811】 The system according to claim 1, wherein the artificial intelligence analysis means continuously learns using past evaluation history to improve the accuracy of evaluations. 【0812】 (Claim 3) 【0813】 The system according to claim 1, wherein the evaluation criteria setting means allows for adjustment of the importance of each evaluation criterion based on the organization's policies. [Explanation of symbols] 【0814】 10, 210, 310, 410 Data Processing Systems 12 Data Processing Devices 14 Smart Devices 214 Smart Glasses 314 Headset-type terminal 414 Robots< / url:> < / url:> < / url:> < / url:>

Claims

[Claim 1] Data collection methods for collecting employee work data, A means for setting evaluation criteria, An AI analysis tool that analyzes and scores collected business data based on evaluation criteria, A feedback generation means that generates feedback based on the scoring results, A notification display method that notifies and displays feedback to employees, A system that includes this. [Claim 2] The system according to claim 1, wherein the AI ​​analysis means continuously learns using past evaluation history to improve the accuracy of evaluations. [Claim 3] The system according to claim 1, wherein the evaluation criteria setting means allows for adjustment of the importance of each evaluation criterion based on the organization's policies.

Images